CN113393271A - Product customer big data application matching system and computer storage medium - Google Patents
Product customer big data application matching system and computer storage medium Download PDFInfo
- Publication number
- CN113393271A CN113393271A CN202110658542.8A CN202110658542A CN113393271A CN 113393271 A CN113393271 A CN 113393271A CN 202110658542 A CN202110658542 A CN 202110658542A CN 113393271 A CN113393271 A CN 113393271A
- Authority
- CN
- China
- Prior art keywords
- product
- label
- module
- user
- characteristic 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.)
- Granted
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention provides a product customer big data application matching system and a computer storage medium, which comprise a product input module, a product analysis module, a user analysis module, an application matching module, a fixed-point release module and a fixed-point feedback module, wherein a merchant uploads relevant data of a product by using the product input module, the product analysis module analyzes the uploaded data to obtain a plurality of labels, the user analysis module analyzes characteristic data of a user based on browsing and shopping records of the user, the application matching module calculates the application degree of the product to each user according to the labels and the characteristic data, the fixed-point release module releases a message to the user for the product with the usage degree exceeding a threshold value, and the fixed-point feedback module performs record feedback according to the reaction of the user to the released product message; the system can realize accurate putting of products, and enables merchants and consumers to achieve a win-win effect.
Description
Technical Field
The invention relates to the technical field of Internet e-commerce, in particular to a product customer application matching system based on big data.
Background
The problem that how to accurately put products into target customers exists in current internet e-commerce is that the more accurate the product customer matching is, the lower the generated cost is, the higher the profit is, and for consumers, the current internet is filled with a large amount of irrelevant product information, so that the experience of the consumers is reduced, the difficulty of obtaining interested products by the consumers is increased, and how to realize win-win in the product putting process by the merchants and the consumers is the problem to be solved by the system.
A number of product matching systems have been developed, and through extensive search and reference, it is found that the existing matching systems are disclosed as KR101099309B1, KR101037821B1 and KR101486207B1, and include: the user login module is used for receiving and verifying login information of a user; the product adding module is used for displaying the loan product types to the user; the product information input module is used for receiving the product information which is input by the user and aims at the loan product type; the storage module is used for storing the product information input by the user through the product information input module; the detail display module is used for displaying the product information issued by the user; the screening matching module is used for matching the keywords provided by the user in the issued product information; and the information output module is used for displaying the information of the at least one product obtained by the screening and matching module to a user. However, a large number of products which are not interested by consumers still appear in the matching result of the system, and the accuracy is not high.
Disclosure of Invention
The invention aims to provide a product customer application matching system based on big data aiming at the existing defects,
in order to overcome the defects of the prior art, the invention adopts the following technical scheme:
a product customer application matching system based on big data comprises a merchant client, a center server and a consumer client, wherein the merchant client is used for uploading products and extracting product labels, the consumer client is used for generating characteristic data according to browsing and purchasing records of a user, and the center server is used for matching according to the product labels and the characteristic data and sending applicable product information to the consumer client;
the method is characterized in that labels extracted by a merchant client comprise a numerical label and a universal label, and the numerical label is divided into a plurality of grades;
the characteristic data generated by the consumer client comprises browsing characteristic data and purchasing characteristic data, wherein the browsing characteristic data is the accumulated browsing times of the general tags of the commodities, and the purchasing characteristic data is the ratio statistical distribution of the numerical tags of the commodities;
the central server calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the central server calculates a label matching index Q of the product uploaded by the merchant client:
wherein P (M)iOne of the significance indices of the largest n universal tags in the product;
the products with the label matching indexes exceeding the threshold value form products to be selected, the central server calculates the applicability U of the products to be selected according to the purchase characteristic data, and the products with high applicability U are sent to the consumer client side;
further, the calculation formula of the applicability U is:
U＝ΠY(A，B，a)；
the function Y (A, B, a) is used for representing the number of numerical label ratios F in the purchase characteristic data, wherein F is x: Y, x belongs to [ A-a, A + a ] and Y belongs to [ B-a, B + a ];
further, the consumer client comprises a user analysis module, a fixed point release module and a fixed point feedback module, wherein the user analysis module is used for analyzing browsing and shopping records of a user and generating characteristic data, the fixed point release module is used for displaying product information sent by the central server, the fixed point feedback module is used for recording and feeding back operation processing of the user on product information, the consumer client is controlled to be in an open or closed state by the user, and the consumer client is connected with the central server only in the open state and works normally;
further, the central server sorts the products to be selected from high to low according to the suitability and creates a label pool, the product with the highest suitability is sent to the consumer client and puts the general label into the label pool, the rest products to be selected are re-sorted after the suitability weight is corrected, and the process is continuously repeated until the product message received by the consumer client reaches the upper limit;
further, the suitability weight is modified to be a new suitability obtained by multiplying the weight of the product to be selected by the original suitability, and the weight G is:
wherein Z is the total number of labels in the label pool, and n is the number of self-used labels of the products contained in the label pool;
a computer-readable storage medium, comprising a big-data based product-customer applicable matching system program, wherein when executed by a processor, the big-data based product-customer applicable matching system program implements a big-data based product-customer applicable matching system step.
The beneficial effects obtained by the invention are as follows:
for merchants, products of the system are put into a target group which is easy to purchase, income is improved, for consumers, received product information is more targeted, junk information cannot occur, products which are unexpected but can be interested easily occur, consumption experience is improved, the consumers can actively control the opening and closing of the consumer clients, personal data are stored in a local system, and malicious leakage of personal information is avoided.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
Fig. 1 is a schematic view of an overall structural framework.
FIG. 2 is a schematic diagram of product match screening.
Fig. 3 is a schematic diagram of a process of correcting the applicability weight of a product to be selected.
Fig. 4 is a view illustrating browsing characteristic data.
FIG. 5 is a schematic diagram of a statistical distribution of ratios of a pair of numerical labels in purchase characteristics data.
Detailed Description
In order to make the objects and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the following embodiments; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Other systems, methods, and/or features of the present embodiments will become apparent to those skilled in the art upon review of the following detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description, be within the scope of the invention, and be protected by the accompanying claims. Additional features of the disclosed embodiments are described in, and will be apparent from, the detailed description that follows.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not indicated or implied that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limitations of the present patent, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
The first embodiment.
A product customer application matching system based on big data comprises a merchant client, a center server and a consumer client, wherein the merchant client is used for uploading products and extracting product labels, the consumer client is used for generating characteristic data according to browsing and purchasing records of a user, and the center server is used for matching according to the product labels and the characteristic data and sending applicable product information to the consumer client;
the method is characterized in that labels extracted by a merchant client comprise a numerical label and a universal label, and the numerical label is divided into a plurality of grades;
the characteristic data generated by the consumer client comprises browsing characteristic data and purchasing characteristic data, wherein the browsing characteristic data is the accumulated browsing times of the general tags of the commodities, and the purchasing characteristic data is the ratio statistical distribution of the numerical tags of the commodities;
the central server calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the central server calculates a label matching index Q of the product uploaded by the merchant client:
wherein P (M)iTo the said productOne of the significance indices of the largest n universal tags in the product;
the products with the label matching indexes exceeding the threshold value form products to be selected, the central server calculates the applicability U of the products to be selected according to the purchase characteristic data, and the products with high applicability U are sent to the consumer client side;
the calculation formula of the suitability degree U is as follows:
U＝ΠY(A，B，a)；
the function Y (A, B, a) is used for representing the number of numerical label ratios F in the purchase characteristic data, wherein F is x: Y, x belongs to [ A-a, A + a ] and Y belongs to [ B-a, B + a ];
the consumer client comprises a user analysis module, a fixed point releasing module and a fixed point feedback module, wherein the user analysis module is used for analyzing browsing and shopping records of a user and generating characteristic data, the fixed point releasing module is used for displaying product information sent by the central server, the fixed point feedback module is used for recording and feeding back operation processing of the user on the product information, the consumer client is controlled to be in an open or closed state by the user, and the consumer client is connected with the central server only in the open state and works normally;
the central server sorts the products to be selected from high to low according to the applicability and creates a label pool, the product with the highest applicability is sent to the consumer client and a universal label of the product is put into the label pool, the rest products to be selected are re-sorted after the applicability weight is corrected, and the process is repeated continuously until the product message received by the consumer client reaches the upper limit;
and correcting the weight of the suitability degree into a new suitability degree obtained by multiplying the weight of the product to be selected by the original suitability degree, wherein the weight G is as follows:
wherein Z is the total number of labels in the label pool, and n is the number of self-used labels of the products contained in the label pool;
a computer-readable storage medium, comprising a big-data based product-customer applicable matching system program, wherein when executed by a processor, the big-data based product-customer applicable matching system program implements a big-data based product-customer applicable matching system step.
Example two.
A product customer application matching system based on big data comprises a merchant client, a center server and a consumer client, wherein the merchant client is used for uploading products and extracting product labels, the consumer client is used for generating characteristic data according to browsing and purchasing records of a user, and the center server is used for matching according to the product labels and the characteristic data and sending applicable product information to the consumer client;
the method is characterized in that labels extracted by a merchant client comprise a numerical label and a universal label, and the numerical label is divided into a plurality of grades;
the characteristic data generated by the consumer client comprises browsing characteristic data and purchasing characteristic data, wherein the browsing characteristic data is the accumulated browsing times of the general tags of the commodities, and the purchasing characteristic data is the ratio statistical distribution of the numerical tags of the commodities;
the central server calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the central server calculates a label matching index Q of the product uploaded by the merchant client:
wherein P (M)iOne of the significance indices of the largest n universal tags in the product;
the products with the label matching indexes exceeding the threshold value form products to be selected, the central server calculates the applicability U of the products to be selected according to the purchase characteristic data, and the products with high applicability U are sent to the consumer client side;
the calculation formula of the suitability degree U is as follows:
U＝ΠY(A，B，a)；
the function Y (A, B, a) is used for representing the number of numerical label ratios F in the purchase characteristic data, wherein F is x: Y, x belongs to [ A-a, A + a ] and Y belongs to [ B-a, B + a ];
the consumer client comprises a user analysis module, a fixed point releasing module and a fixed point feedback module, wherein the user analysis module is used for analyzing browsing and shopping records of a user and generating characteristic data, the fixed point releasing module is used for displaying product information sent by the central server, the fixed point feedback module is used for recording and feeding back operation processing of the user on the product information, the consumer client is controlled to be in an open or closed state by the user, and the consumer client is connected with the central server only in the open state and works normally;
the central server sorts the products to be selected from high to low according to the applicability and creates a label pool, the product with the highest applicability is sent to the consumer client and a universal label of the product is put into the label pool, the rest products to be selected are re-sorted after the applicability weight is corrected, and the process is repeated continuously until the product message received by the consumer client reaches the upper limit;
and correcting the weight of the suitability degree into a new suitability degree obtained by multiplying the weight of the product to be selected by the original suitability degree, wherein the weight G is as follows:
wherein Z is the total number of labels in the label pool, and n is the number of self-used labels of the products contained in the label pool;
a computer-readable storage medium, wherein the computer-readable storage medium comprises a big data based product customer adaptive matching system program, and when the big data based product customer adaptive matching system program is executed by a processor, the big data based product customer adaptive matching system program implements a big data based product customer adaptive matching system step;
based on the product customer application matching system based on big data, the product customer application matching system comprises a product input module, a product analysis module, a user analysis module, an application matching module, a fixed-point release module and a fixed-point feedback module, a merchant uploads relevant data of products by using the product input module, the product analysis module analyzes the uploaded data to obtain a plurality of labels, the user analysis module analyzes feature data of users based on browsing and shopping records of the users, the application matching module calculates the applicability of the products to each user according to the labels and the feature data, the fixed-point release module releases the products with the usage exceeding a threshold value to the users, and the fixed-point feedback module performs record feedback according to the reaction of the users to the released product messages;
the product input module and the product analysis module are integrated in a merchant client, product information needing to be input through the product input module comprises a product picture, a product size, a product function and a product price, the product analysis module obtains an aesthetic label according to the product picture, obtains a spatial label according to the product size and obtains an economic label according to the product price, the aesthetic label, the spatial label and the economic label are numerical labels and are divided into a plurality of grades, the grades are respectively represented by A, B, C, and the product analysis module extracts keywords from description of the product function and obtains a plurality of general labels according to the keywords;
the user analysis module, the fixed point releasing module and the fixed point feedback module are integrated in a consumer client, a user can open or close the consumer client, when the consumer client is opened, the user analysis module can record the browsing process and the purchasing process of the user and generate browsing characteristic data and purchasing characteristic data, such as browsing a product, the user analysis module can generate a general label of the product and add 1 to the general label in an accumulated way, the browsing characteristic data is the total browsing times of each general label, such as purchasing a product, the user analysis module can generate the aesthetic degree grade, the space degree grade and the economic degree grade of the product and record the ratio of the aesthetic degree grade, the space degree grade and the economic degree grade of the product, the purchasing characteristic data is a statistic value of each ratio, and the fixed point releasing module can form a display interface in the consumer client, the display interface displays product information applicable to the user, the display quantity and the updating time of the products are set by the customer, the user can jump to a specific purchasing interface to check more specific product information and decide whether to purchase the products by clicking a product information link, and the fixed point feedback module is used for recording the product click rate and the click and purchase conversion rate of the user and feeding back the product click rate and the click and purchase conversion rate to the use tracking module.
Example three.
A product customer application matching system based on big data comprises a merchant client, a center server and a consumer client, wherein the merchant client is used for uploading products and extracting product labels, the consumer client is used for generating characteristic data according to browsing and purchasing records of a user, and the center server is used for matching according to the product labels and the characteristic data and sending applicable product information to the consumer client;
the method is characterized in that labels extracted by a merchant client comprise a numerical label and a universal label, and the numerical label is divided into a plurality of grades;
the characteristic data generated by the consumer client comprises browsing characteristic data and purchasing characteristic data, wherein the browsing characteristic data is the accumulated browsing times of the general tags of the commodities, and the purchasing characteristic data is the ratio statistical distribution of the numerical tags of the commodities;
the central server calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the central server calculates a label matching index Q of the product uploaded by the merchant client:
wherein P (M)iOne of the significance indices of the largest n universal tags in the product;
the products with the label matching indexes exceeding the threshold value form products to be selected, the central server calculates the applicability U of the products to be selected according to the purchase characteristic data, and the products with high applicability U are sent to the consumer client side;
the calculation formula of the suitability degree U is as follows:
U＝ΠY(A，B，a)；
the function Y (A, B, a) is used for representing the number of numerical label ratios F in the purchase characteristic data, wherein F is x: Y, x belongs to [ A-a, A + a ] and Y belongs to [ B-a, B + a ];
the consumer client comprises a user analysis module, a fixed point releasing module and a fixed point feedback module, wherein the user analysis module is used for analyzing browsing and shopping records of a user and generating characteristic data, the fixed point releasing module is used for displaying product information sent by the central server, the fixed point feedback module is used for recording and feeding back operation processing of the user on the product information, the consumer client is controlled to be in an open or closed state by the user, and the consumer client is connected with the central server only in the open state and works normally;
the central server sorts the products to be selected from high to low according to the applicability and creates a label pool, the product with the highest applicability is sent to the consumer client and a universal label of the product is put into the label pool, the rest products to be selected are re-sorted after the applicability weight is corrected, and the process is repeated continuously until the product message received by the consumer client reaches the upper limit;
and correcting the weight of the suitability degree into a new suitability degree obtained by multiplying the weight of the product to be selected by the original suitability degree, wherein the weight G is as follows:
wherein Z is the total number of labels in the label pool, and n is the number of self-used labels of the products contained in the label pool;
a computer-readable storage medium, wherein the computer-readable storage medium comprises a big data based product customer adaptive matching system program, and when the big data based product customer adaptive matching system program is executed by a processor, the big data based product customer adaptive matching system program implements a big data based product customer adaptive matching system step;
based on the product customer application matching system based on big data, the product customer application matching system comprises a product input module, a product analysis module, a user analysis module, an application matching module, a fixed-point release module and a fixed-point feedback module, a merchant uploads relevant data of products by using the product input module, the product analysis module analyzes the uploaded data to obtain a plurality of labels, the user analysis module analyzes feature data of users based on browsing and shopping records of the users, the application matching module calculates the applicability of the products to each user according to the labels and the feature data, the fixed-point release module releases the products with the usage exceeding a threshold value to the users, and the fixed-point feedback module performs record feedback according to the reaction of the users to the released product messages;
the product input module and the product analysis module are integrated in a merchant client, product information needing to be input through the product input module comprises a product picture, a product size, a product function and a product price, the product analysis module obtains an aesthetic label according to the product picture, obtains a spatial label according to the product size and obtains an economic label according to the product price, the aesthetic label, the spatial label and the economic label are numerical labels and are divided into a plurality of grades, the grades are respectively represented by A, B, C, and the product analysis module extracts keywords from description of the product function and obtains a plurality of general labels according to the keywords;
the user analysis module, the fixed point releasing module and the fixed point feedback module are integrated in a consumer client, a user can open or close the consumer client, when the consumer client is opened, the user analysis module can record the browsing process and the purchasing process of the user and generate browsing characteristic data and purchasing characteristic data, such as browsing a product, the user analysis module can generate a general label of the product and add 1 to the general label in an accumulated way, the browsing characteristic data is the total browsing times of each general label, such as purchasing a product, the user analysis module can generate the aesthetic degree grade, the space degree grade and the economic degree grade of the product and record the ratio of the aesthetic degree grade, the space degree grade and the economic degree grade of the product, the purchasing characteristic data is a statistic value of each ratio, and the fixed point releasing module can form a display interface in the consumer client, the display interface displays product information applicable to the user, the display quantity and the updating time of the products are set by the customer, the user can jump to a specific purchasing interface to check more specific product information and decide whether to purchase the products by clicking a product information link, and the fixed point feedback module is used for recording the product click rate and the click and purchase conversion rate of the user and feeding back the product click rate and the click and purchase conversion rate to the use tracking module;
the applicable matching module is arranged in a central server which is communicated with all merchant clients and opened consumer clients and forms a network, the applicable matching module will collect the product tag data of the product analysis module and store it in a product database, a product communication area is established between the applicable matching module and the consumer client, the product communication area will submit an application to the applicable matching module according to the browsing characteristic data of the user, the applicable matching module acquires products meeting the browsing characteristic data from the product database according to the application and sends the products to the product communication area, the product communication area calculates the suitability of each product according to the purchase characteristic data of the user and ranks the products according to the suitability, the consumer client obtains a certain amount of product messages for display according to the suitability ranking and the own setting of the user;
the browsing characteristic data sent to the product communication area is the browsing characteristic data in a recent period of time, and the product communication area calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the important index data of the universal label forms an application submitted by a product communication area;
for a product in a product database, the applicable matching module extracts 5 general labels with the top 5 of the important indexes in the product based on the submitted application, and the important indexes corresponding to the 5 general labels are marked as P (M)iAnd i takes a value from 1 to 5, and the label matching index Q of the product is calculated as follows:
the applicable matching module sends the products with the tag matching indexes exceeding the threshold value to the product communication area to serve as the products to be selected;
the purchase characteristic data are three ratios F1、F2And F3Distribution statistics of (1), ratio F1Is the ratio of aesthetic degree grade to space degree grade, the ratio F2Is the ratio of aesthetic degree grade to economic degree grade, the ratio F3F is the ratio of the spacial level to the economic level, e.g., the aesthetic level, spacial level, and economic level of purchasing a good are 3, 8, and 4, respectively1＝3:8，F2＝3:4，F3Note that the ratio is the original data, and is not reduced, i.e., 8:4 ≠ 2: 1;
the product communication area calculates the applicability U of each product to be selected:
U＝Y(A，B，a)·Y(A，C，a)·Y(B，C，a)；
wherein A, B and C are the aesthetic degree grade, the space degree grade and the economic degree grade of the product to be selected, a is an offset value, and a function Y (A, B and a) is used for expressing a ratio F in purchase characteristic data1Satisfies F1＝x:y，x∈[A-a，A+a]And y is ∈ [ B-a, B + a ]]Is used to represent the ratio F in the purchase characteristics data2Satisfies F2＝x:y，x∈[A-a，A+a]And y is [ C-a, C + a ]]Is used to represent the ratio F in the purchase characteristics data3Satisfies F3＝x:y，x∈[B-a，B+a]And y is [ C-a, C + a ]]The number of (2) is a natural number;
and the product communication area selects the product to be selected with high applicability U and sends the product to the customer end for display.
Example four.
A product customer application matching system based on big data comprises a merchant client, a center server and a consumer client, wherein the merchant client is used for uploading products and extracting product labels, the consumer client is used for generating characteristic data according to browsing and purchasing records of a user, and the center server is used for matching according to the product labels and the characteristic data and sending applicable product information to the consumer client;
the method is characterized in that labels extracted by a merchant client comprise a numerical label and a universal label, and the numerical label is divided into a plurality of grades;
the characteristic data generated by the consumer client comprises browsing characteristic data and purchasing characteristic data, wherein the browsing characteristic data is the accumulated browsing times of the general tags of the commodities, and the purchasing characteristic data is the ratio statistical distribution of the numerical tags of the commodities;
the central server calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the central server calculates a label matching index Q of the product uploaded by the merchant client:
wherein P (M)iOne of the significance indices of the largest n universal tags in the product;
the products with the label matching indexes exceeding the threshold value form products to be selected, the central server calculates the applicability U of the products to be selected according to the purchase characteristic data, and the products with high applicability U are sent to the consumer client side;
the calculation formula of the suitability degree U is as follows:
U＝ΠY(A，B，a)；
the function Y (A, B, a) is used for representing the number of numerical label ratios F in the purchase characteristic data, wherein F is x: Y, x belongs to [ A-a, A + a ] and Y belongs to [ B-a, B + a ];
the consumer client comprises a user analysis module, a fixed point releasing module and a fixed point feedback module, wherein the user analysis module is used for analyzing browsing and shopping records of a user and generating characteristic data, the fixed point releasing module is used for displaying product information sent by the central server, the fixed point feedback module is used for recording and feeding back operation processing of the user on the product information, the consumer client is controlled to be in an open or closed state by the user, and the consumer client is connected with the central server only in the open state and works normally;
the central server sorts the products to be selected from high to low according to the applicability and creates a label pool, the product with the highest applicability is sent to the consumer client and a universal label of the product is put into the label pool, the rest products to be selected are re-sorted after the applicability weight is corrected, and the process is repeated continuously until the product message received by the consumer client reaches the upper limit;
and correcting the weight of the suitability degree into a new suitability degree obtained by multiplying the weight of the product to be selected by the original suitability degree, wherein the weight G is as follows:
wherein Z is the total number of labels in the label pool, and n is the number of self-used labels of the products contained in the label pool;
a computer-readable storage medium, wherein the computer-readable storage medium comprises a big data based product customer adaptive matching system program, and when the big data based product customer adaptive matching system program is executed by a processor, the big data based product customer adaptive matching system program implements a big data based product customer adaptive matching system step;
based on the product customer application matching system based on big data, the product customer application matching system comprises a product input module, a product analysis module, a user analysis module, an application matching module, a fixed-point release module and a fixed-point feedback module, a merchant uploads relevant data of products by using the product input module, the product analysis module analyzes the uploaded data to obtain a plurality of labels, the user analysis module analyzes feature data of users based on browsing and shopping records of the users, the application matching module calculates the applicability of the products to each user according to the labels and the feature data, the fixed-point release module releases the products with the usage exceeding a threshold value to the users, and the fixed-point feedback module performs record feedback according to the reaction of the users to the released product messages;
the product input module and the product analysis module are integrated in a merchant client, product information needing to be input through the product input module comprises a product picture, a product size, a product function and a product price, the product analysis module obtains an aesthetic label according to the product picture, obtains a spatial label according to the product size and obtains an economic label according to the product price, the aesthetic label, the spatial label and the economic label are numerical labels and are divided into a plurality of grades, the grades are respectively represented by A, B, C, and the product analysis module extracts keywords from description of the product function and obtains a plurality of general labels according to the keywords;
the user analysis module, the fixed point releasing module and the fixed point feedback module are integrated in a consumer client, a user can open or close the consumer client, when the consumer client is opened, the user analysis module can record the browsing process and the purchasing process of the user and generate browsing characteristic data and purchasing characteristic data, such as browsing a product, the user analysis module can generate a general label of the product and add 1 to the general label in an accumulated way, the browsing characteristic data is the total browsing times of each general label, such as purchasing a product, the user analysis module can generate the aesthetic degree grade, the space degree grade and the economic degree grade of the product and record the ratio of the aesthetic degree grade, the space degree grade and the economic degree grade of the product, the purchasing characteristic data is a statistic value of each ratio, and the fixed point releasing module can form a display interface in the consumer client, the display interface displays product information applicable to the user, the display quantity and the updating time of the products are set by the customer, the user can jump to a specific purchasing interface to check more specific product information and decide whether to purchase the products by clicking a product information link, and the fixed point feedback module is used for recording the product click rate and the click and purchase conversion rate of the user and feeding back the product click rate and the click and purchase conversion rate to the use tracking module;
the applicable matching module is arranged in a central server which is communicated with all merchant clients and opened consumer clients and forms a network, the applicable matching module will collect the product tag data of the product analysis module and store it in a product database, a product communication area is established between the applicable matching module and the consumer client, the product communication area will submit an application to the applicable matching module according to the browsing characteristic data of the user, the applicable matching module acquires products meeting the browsing characteristic data from the product database according to the application and sends the products to the product communication area, the product communication area calculates the suitability of each product according to the purchase characteristic data of the user and ranks the products according to the suitability, the consumer client obtains a certain amount of product messages for display according to the suitability ranking and the own setting of the user;
the browsing characteristic data sent to the product communication area is the browsing characteristic data in a recent period of time, and the product communication area calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the important index data of the universal label forms an application submitted by a product communication area;
for a product in the product database, the applicable matching module extracts important indexes in the product before ranking based on the submitted application5, the important indexes corresponding to the 5 general tags are marked as P (M)iAnd i takes a value from 1 to 5, and the label matching index Q of the product is calculated as follows:
the applicable matching module sends the products with the tag matching indexes exceeding the threshold value to the product communication area to serve as the products to be selected;
the purchase characteristic data are three ratios F1、F2And F3Distribution statistics of (1), ratio F1Is the ratio of aesthetic degree grade to space degree grade, the ratio F2Is the ratio of aesthetic degree grade to economic degree grade, the ratio F3F is the ratio of the spacial level to the economic level, e.g., the aesthetic level, spacial level, and economic level of purchasing a good are 3, 8, and 4, respectively1＝3:8，F2＝3:4，F3Note that the ratio is the original data, and is not reduced, i.e., 8:4 ≠ 2: 1;
the product communication area calculates the applicability U of each product to be selected:
U＝Y(A，B，a)·Y(A，C，a)·Y(B，C，a)；
wherein A, B and C are the aesthetic degree grade, the space degree grade and the economic degree grade of the product to be selected, a is an offset value, and a function Y (A, B and a) is used for expressing a ratio F in purchase characteristic data1Satisfies F1＝x:y，x∈[A-a，A+a]And y is ∈ [ B-a, B + a ]]Is used to represent the ratio F in the purchase characteristics data2Satisfies F2＝x:y，x∈[A-a，A+a]And y is [ C-a, C + a ]]Is used to represent the ratio F in the purchase characteristics data3Satisfies F3＝x:y，x∈[B-a，B+a]And y is [ C-a, C + a ]]The number of (2) is a natural number;
the product communication area selects the product to be selected with high applicability U and sends the product to the customer end to be displayed;
the product communication area adds label repeated weight to the products to be selected, so that the situation that the types of the products sent to a customer client are single is prevented, the products to be selected are firstly sequenced from high to low according to the suitability degree in the product communication area, an initial weight G is given to each product to be selected, the G value is 1, a label pool is created, a general label of the product to be selected with the highest suitability degree is put into the label pool and then is directly sent to the customer client, the weight G of the rest products to be selected is corrected according to the labels in the label pool and the general label of the rest products, and the correction formula is as follows:
wherein Z is the total number of labels in the label pool, and n is the number of self-used labels of the products contained in the label pool;
multiplying the weight by the suitability to obtain new suitability, reordering the products to be selected according to the new suitability, sending the products to be selected with the highest suitability to the customer client, putting the labels of the products to be selected into a label pool, performing weight correction on the rest products to be selected, and continuously repeating the process until the number of the products in the customer client reaches the standard;
the consumer client can click the product message to check the purchase link or directly delete the product message, three historical databases are arranged in the consumer client, one historical database is a purchase historical database, data of commodities purchased through the consumer client are stored in the purchase historical database, the other historical database is a click historical database, data related to products which are clicked but not purchased are stored in the click historical database, the other historical database is a deletion historical database, and data related to products which are directly deleted are stored in the deletion historical database.
Although the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the invention. That is, the methods, systems, and devices discussed above are examples. Various configurations may omit, substitute, or add various procedures or components as appropriate. For example, in alternative configurations, the methods may be performed in an order different than that described, and/or various components may be added, omitted, and/or combined. Moreover, features described with respect to certain configurations may be combined in various other configurations, as different aspects and elements of the configurations may be combined in a similar manner. Further, elements therein may be updated as technology evolves, i.e., many elements are examples and do not limit the scope of the disclosure or claims.
Specific details are given in the description to provide a thorough understanding of the exemplary configurations including implementations. However, configurations may be practiced without these specific details, for example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configuration of the claims. Rather, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.
In conclusion, it is intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that these examples are illustrative only and are not intended to limit the scope of the invention. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (6)
1. A product customer application matching system based on big data comprises a merchant client, a center server and a consumer client, wherein the merchant client is used for uploading products and extracting product labels, the consumer client is used for generating characteristic data according to browsing and purchasing records of a user, and the center server is used for matching according to the product labels and the characteristic data and sending applicable product information to the consumer client;
the method is characterized in that labels extracted by a merchant client comprise a numerical label and a universal label, and the numerical label is divided into a plurality of grades;
the characteristic data generated by the consumer client comprises browsing characteristic data and purchasing characteristic data, wherein the browsing characteristic data is the accumulated browsing times of the general tags of the commodities, and the purchasing characteristic data is the ratio statistical distribution of the numerical tags of the commodities;
the central server calculates each universal label M according to the browsing characteristic dataiIs the significance index P (M)i):
Wherein, N (M) represents the browsing times of the general label M, i, j are subscripts, and the subscripts are numbers or Chinese;
the central server calculates a label matching index Q of the product uploaded by the merchant client:
wherein P (M)iOne of the significance indices of the largest n universal tags in the product;
and the products with the label matching indexes exceeding the threshold value form products to be selected, the central server calculates the applicability U of the products to be selected according to the purchase characteristic data, and sends the products with high applicability U to the customer client.
2. The big data based product customer suitability matching system as claimed in claim 1, wherein the calculation formula of the suitability degree U is:
U＝ΠY(A，B，a)；
wherein, a and B are the rank values of any two numerical labels, a is the deviation value, and the function Y (a, B, a) is used to represent the number of numerical label ratios F in the purchase feature data, which satisfy F ═ x: Y, x ∈ [ a-a, a + a ], and Y ∈ [ B-a, B + a ].
3. The big data based product client application matching system as claimed in claim 2, wherein the consumer client comprises a user analysis module, a fixed point delivery module and a fixed point feedback module, the user analysis module is used for analyzing browsing and shopping records of a user and generating characteristic data, the fixed point delivery module is used for displaying product information sent by the central server, the fixed point feedback module is used for recording and feeding back operation processing of the user on the product information, the consumer client is controlled by the user to be in an on or off state, and the consumer client is connected with the central server only in the on state and works normally.
4. The big data based product customer suitability matching system as claimed in claim 3, wherein the central server sorts the products to be selected according to the suitability from high to low and creates a label pool, the product with the highest suitability is sent to the customer client and puts its general label into the label pool, the rest products to be selected are re-sorted after the suitability weight is modified, and the process is repeated until the product message received by the customer client reaches the upper limit.
5. The big data-based product customer suitability matching system as claimed in claim 4, wherein the suitability weight is modified by multiplying the weight of the selected product by the original suitability to obtain a new suitability, and the weight G is:
wherein Z is the total number of the labels in the label pool, and n is the number of the self universal labels of the products contained in the label pool.
6. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a big-data based product customer applicable matching system program, which when executed by a processor implements a big-data based product customer applicable matching system step as recited in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110658542.8A CN113393271B (en) | 2021-06-15 | 2021-06-15 | Product customer big data application matching system and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110658542.8A CN113393271B (en) | 2021-06-15 | 2021-06-15 | Product customer big data application matching system and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113393271A true CN113393271A (en) | 2021-09-14 |
| CN113393271B CN113393271B (en) | 2022-09-23 |
Family
ID=77620959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110658542.8A Active CN113393271B (en) | 2021-06-15 | 2021-06-15 | Product customer big data application matching system and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113393271B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408377A (en) * | 2016-08-31 | 2017-02-15 | 广东华邦云计算股份有限公司 | Shopping recommended method and system |
| CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
| CN110264252A (en) * | 2019-06-01 | 2019-09-20 | 浙江华坤道威数据科技有限公司 | A kind of advertisement fixed point jettison system based on LBS positioning |
| CN110874788A (en) * | 2019-11-13 | 2020-03-10 | 合肥美的电冰箱有限公司 | Product recommendation method and device and computer storage medium |
| WO2020085086A1 (en) * | 2018-10-23 | 2020-04-30 | 株式会社ピーステックラボ | Commodity recommendation system |
| CN112348430A (en) * | 2020-10-19 | 2021-02-09 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
-
2021
- 2021-06-15 CN CN202110658542.8A patent/CN113393271B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408377A (en) * | 2016-08-31 | 2017-02-15 | 广东华邦云计算股份有限公司 | Shopping recommended method and system |
| WO2020085086A1 (en) * | 2018-10-23 | 2020-04-30 | 株式会社ピーステックラボ | Commodity recommendation system |
| CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
| CN110264252A (en) * | 2019-06-01 | 2019-09-20 | 浙江华坤道威数据科技有限公司 | A kind of advertisement fixed point jettison system based on LBS positioning |
| CN110874788A (en) * | 2019-11-13 | 2020-03-10 | 合肥美的电冰箱有限公司 | Product recommendation method and device and computer storage medium |
| CN112348430A (en) * | 2020-10-19 | 2021-02-09 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 冯勇等: "一种基于标签用户模型的个性化信息检索方法", 《小型微型计算机系统》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113393271B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101993771B1 (en) | Chatbot searching system and program | |
| US9703828B2 (en) | System and method for idempotent interactive disparate object discovery, retrieval and display | |
| US20110196716A1 (en) | Lead qualification based on contact relationships and customer experience | |
| WO2020088058A1 (en) | Information generating method and device | |
| CN111461841A (en) | Article recommendation method, device, server and storage medium | |
| CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
| CN111949887A (en) | Item recommendation method and device and computer-readable storage medium | |
| CN107480227A (en) | A kind of information-pushing method based on big data | |
| CN113850649A (en) | Customized recommendation method and recommendation system based on multi-platform user data | |
| CN116562992B (en) | Method, device and medium for recommending items for modeling uncertainty of new interests of user | |
| CN112765478A (en) | Method, apparatus, device, medium, and program product for recommending content | |
| CN106294676A (en) | A kind of data retrieval method of ecommerce government system | |
| CN115760202A (en) | Product operation management system and method based on artificial intelligence | |
| CN111429161A (en) | Feature extraction method, feature extraction device, storage medium, and electronic apparatus | |
| CN114282100A (en) | E-commerce platform-oriented personalized recommendation method and device based on cloud computing technology | |
| CN114493786A (en) | Information recommendation method and device | |
| CN111654714B (en) | Information processing method, apparatus, electronic device and storage medium | |
| CN113393271B (en) | Product customer big data application matching system and computer storage medium | |
| CN116823404A (en) | Commodity combination recommendation method, device, equipment and medium thereof | |
| TWM633789U (en) | Matching system | |
| JP5011185B2 (en) | Information analysis apparatus, information analysis method, and information analysis program | |
| CN113254775A (en) | Credit card product recommendation method based on client browsing behavior sequence | |
| CN113362141A (en) | Associated commodity recommendation method, device, medium and electronic equipment | |
| CN113327145A (en) | Article recommendation method and device | |
| TWI818213B (en) | System and method of product recommendation and computer readable medium |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230105 Address after: 311100 Room 801-805, Floor 8, Building 1, Haichuang Science and Technology Center, Cangqian Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou Dongdian Technology Co.,Ltd. Address before: 412000 No.79, wisdom road, Yunlong demonstration zone, Zhuzhou City, Hunan Province (New Campus of Hunan Automotive Engineering Vocational College) Patentee before: HUNAN AUTOMOTIVE ENGINEERING VOCATIONAL College |
|
| TR01 | Transfer of patent right |