CN117333262A - Big data demand prediction method and system based on artificial intelligence for electronic commerce platform - Google Patents
Big data demand prediction method and system based on artificial intelligence for electronic commerce platform Download PDFInfo
- Publication number
- CN117333262A CN117333262A CN202311302488.9A CN202311302488A CN117333262A CN 117333262 A CN117333262 A CN 117333262A CN 202311302488 A CN202311302488 A CN 202311302488A CN 117333262 A CN117333262 A CN 117333262A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- shopping
- demand
- commodity
- 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.)
- Withdrawn
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000007726 management method Methods 0.000 claims description 37
- 238000004458 analytical method Methods 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 21
- 230000006399 behavior Effects 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims description 13
- 230000007774 longterm Effects 0.000 claims description 10
- 238000012800 visualization Methods 0.000 claims description 9
- 230000010354 integration Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 230000001737 promoting effect Effects 0.000 claims description 2
- 238000013468 resource allocation Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
-
- 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
-
- 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]
-
- 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]
- G06Q30/0611—Request for offers or quotes
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an artificial intelligence-based big data demand prediction method and system for an e-commerce platform. Firstly, users are classified, and the resource allocation degree for carrying out demand prediction on the users is selected according to the user types, so that the accuracy of prediction is improved. Secondly, on the basis of realizing accurate commodity demand prediction, the individual shopping demand is custom-built for the user, and the accuracy of shopping demand prediction is further improved. Finally, through the active adjustment of the user to the automatically generated purchase scheme, the system can continuously perfect and adapt to the demand prediction function of the user according to the frequency of the user using the one-key shopping function.
Description
Technical Field
The invention relates to the field of big data processing, in particular to an artificial intelligence-based big data demand prediction method and system for an electronic commerce platform.
Background
The e-commerce platform refers to a virtual platform for e-commerce transactions and business activities realized through internet technology. It provides an online transaction environment, so that buyers and sellers can conveniently conduct commercial activities such as commodity transaction, information exchange and payment.
However, in the prior art, the e-commerce platform lacks comprehensiveness in predicting the shopping demands of users, cannot fully analyze information of all aspects of the users, performs resource allocation according to the whole users in predicting the commodity demands of the users, and cannot perform personalized demand prediction for different user types.
Disclosure of Invention
The invention aims to solve the technical problems and provides an artificial intelligence-based big data demand prediction method and system for an electronic commerce platform.
The technical scheme of the invention is realized as follows:
the big data demand prediction system based on artificial intelligence for electronic commerce platform includes user data reading module, user operation analysis module, user demand prediction module, personalized intelligent management module and commodity recommendation intelligent generation module, the user data reading module output is connected with user demand prediction module and personalized intelligent management module input respectively, user operation analysis module output is connected with user demand prediction module input, user demand prediction module output is connected with personalized intelligent management module, personalized intelligent management module is connected with commodity recommendation intelligent generation module in two directions.
Further, the user data reading module comprises a data reading unit, a data classifying unit and a data converting unit;
the data reading unit acquires various data of the user from the electronic commerce platform, integrates the user data and transmits the user data to the data classifying unit;
the data classifying unit classifies the user data to obtain long-term demand data of the user, short-term demand data of the user and preference data of the user, and transmits the classified user data to the data converting unit for conversion;
the data conversion unit converts the long-term demand data of the user, the short-term demand data of the user and the preference data of the user, obtains commodity quality acceptance degree and commodity price acceptance degree of the user through conversion, calculates commodity cost performance, and transmits the obtained commodity quality acceptance degree and commodity price acceptance degree of the user and the calculated commodity cost performance to the user demand prediction module and the personalized intelligent management module.
Further, the user operation analysis module comprises a user operation history acquisition unit, an operation history conversion unit and an operation data analysis unit;
the user operation history acquisition unit acquires user operation data and transmits the user operation data to the operation history conversion unit;
the operation history conversion unit converts the user operation data to obtain shopping habit data of the user, and transmits the shopping habit data to the operation data analysis unit;
the operation data analysis unit analyzes shopping habit data to obtain user shopping demand data, and transmits the user shopping demand data to the user demand prediction module.
Further, the user demand prediction module comprises a user demand analysis unit, a demand degree calculation unit, a user classification unit and a user demand prediction unit;
the user demand analysis unit further analyzes the shopping demand data of the user to obtain shopping demand data of the user, and transmits the shopping demand data to the demand degree calculation unit;
the demand computing unit computes shopping demand according to the shopping demand data, and transmits the shopping demand to the user classifying unit and the user demand predicting unit;
the user classification unit classifies the users according to the shopping demand degrees of the users, and the obtained user types are transmitted to the user demand prediction unit;
and the user demand prediction unit analyzes and predicts the demand commodity data of the user according to the shopping demand degree and the user type of the user, and transmits the demand commodity data to the personalized intelligent management module.
Further, the personalized intelligent management module comprises a commodity picking unit, a user personalized demand customizing unit and a user shopping simplifying unit;
the commodity picking unit is used for further picking commodities according to the required commodity data to obtain accurate required commodity data, and transmitting the accurate required commodity data to the user individual requirement customizing unit;
the user individual demand customizing unit customizes the shopping individual demand of the user according to the commodity quality acceptance degree, commodity price acceptance degree and commodity price ratio and accurate demand commodity data obtained by calculation of the user, and transmits the shopping demand of the user to the user shopping simplifying unit;
the user shopping simplifying unit establishes a one-key shopping function, can generate and simplify a shopping list according to the shopping individuality requirement according to a purchase scheme, obtains a simplified shopping list, and transmits the simplified shopping list to the commodity recommending intelligent generating module.
Further, the commodity recommendation intelligent generation module comprises a commodity data integration unit, a commodity recommendation visualization unit and a commodity purchase scheme generation unit;
the commodity data integration unit is used for further accurately obtaining the simplified shopping list, and transmitting the accurate shopping list to the commodity recommendation visualization unit and the commodity purchase scheme generation unit respectively;
the commodity recommendation visualization unit visualizes the accurate shopping list into a commodity recommendation list and transmits the commodity recommendation list to the commodity purchase scheme generation unit to assist in generating a purchase scheme;
and the commodity purchase scheme generating unit generates a purchase scheme according to the accurate shopping list and the commodity recommendation list, and transmits the purchase scheme to the personalized intelligent management module for one-key shopping.
The aim and the technical problems of the invention can be further realized by adopting the following technical measures.
An artificial intelligence based big data demand prediction method for an electronic commerce platform comprises the following steps:
s1, acquiring various data of a user from an electronic commerce platform through a user data reading module, classifying and converting the user data, primarily judging the user, judging the commodity quality acceptance degree and commodity price acceptance degree of the user, and calculating the commodity cost performance;
s2, further analyzing operation data of the user, analyzing shopping habits and shopping demands of the user, and further predicting the demands of the user based on the shopping demands of the user;
s3, calculating the shopping demand degree of the user through the user demand data, and classifying the user based on the shopping demand degree so as to generate the shopping individual demand subsequently;
s4, predicting the demand commodities of the user by using a user demand prediction module, and picking the commodities by using a personalized intelligent management module to find more accurate demand commodities so as to customize shopping personalized demands for the user;
s5, the personalized intelligent management module establishes a one-key shopping function, and one-key shopping processing can be carried out on a purchase scheme customized by the commodity recommendation intelligent generation module for a user;
and S6, the commodity recommendation intelligent generation module can also conduct accurate and visual on the shopping list of the user, so that basic data is provided for further generation of a purchase scheme, and shopping demand prediction of the user is completed and the purchase process of the user is intelligent.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, the shopping demand of the user is fully predicted by multi-azimuth analysis of the user. Firstly, users are classified, and the resource allocation degree for carrying out demand prediction on the users is selected according to the user types, so that the accuracy of prediction is improved. Secondly, on the basis of realizing accurate commodity demand prediction, the individual shopping demand is custom-built for the user, and the accuracy of shopping demand prediction is further improved. Finally, through the active adjustment of the user on the automatically generated purchase scheme, the system can continuously perfect and adapt to the demand prediction function of the user according to the frequency of the user using the one-key shopping function;
2. the invention solves several problems existing in the prior art:
(1) in the prior art, prediction of shopping demands of users often lacks comprehensiveness, and information of all aspects of users cannot be fully analyzed. The shopping demand of the user is predicted more accurately by carrying out multidirectional analysis on the user;
(2) in the prior art, the resource allocation is often carried out according to the whole user, and personalized demand prediction cannot be carried out for different user types;
(3) in the prior art, the active adjustment and feedback of the purchase scheme by the user are limited, and the invention can continuously perfect and adapt to the demand prediction function of the user through the active adjustment and feedback of the user, thereby providing shopping experience which meets the demand of the user.
Drawings
FIG. 1 is a system frame diagram of an artificial intelligence based big data demand prediction system for an e-commerce platform according to the present invention;
FIG. 2 is a schematic diagram of the operation of the user data reading module of the present invention;
FIG. 3 is a schematic diagram of the operation of the user operation analysis module according to the present invention;
FIG. 4 is a schematic diagram illustrating the operation of the user demand prediction module of the present invention;
FIG. 5 is a schematic diagram of the operation of the personalized intelligent management module of the present invention;
FIG. 6 is a schematic diagram of the operation of the intelligent commodity recommendation generation module of the present invention;
FIG. 7 is a flow chart of an artificial intelligence based big data demand prediction method for an e-commerce platform according to the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the embodiments described below are only some embodiments of the present invention, not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1-6, the big data demand prediction system based on artificial intelligence for electronic commerce platform includes a user data reading module, a user operation analysis module, a user demand prediction module, a personalized intelligent management module and a commodity recommendation intelligent generation module, wherein the output end of the user data reading module is connected with the input ends of the user demand prediction module and the personalized intelligent management module respectively, the output end of the user operation analysis module is connected with the input end of the user demand prediction module, the output end of the user demand prediction module is connected with the personalized intelligent management module, and the personalized intelligent management module is connected with the commodity recommendation intelligent generation module in a bidirectional connection mode.
Further, the user data reading module comprises a data reading unit, a data classifying unit and a data converting unit;
the data reading unit acquires various data of the user from the electronic commerce platform, integrates the user data and transmits the user data to the data classifying unit;
the data classifying unit classifies the user data to obtain long-term demand data of the user, short-term demand data of the user and preference data of the user, and transmits the classified user data to the data converting unit for conversion;
the data conversion unit converts the long-term demand data of the user, the short-term demand data of the user and the preference data of the user, obtains commodity quality acceptance degree and commodity price acceptance degree of the user through conversion, calculates commodity cost performance, and transmits the obtained commodity quality acceptance degree and commodity price acceptance degree of the user and the calculated commodity cost performance to the user demand prediction module and the personalized intelligent management module.
By collecting shopping data of the user, such as shopping cart data, collection data, browsing data, evaluation data, order completion price data, peak expenditure data, quality data and after-sales data of the user, a relative cost performance index can be obtained by comparing the quality score of the commodity with the price, and the relative cost performance index is used for measuring the balance degree between the quality and the price of the commodity under the given price. A higher cost performance means that the product provides better performance and quality relative to its price, while a lower cost performance means that the performance and quality of the product is insufficient to compensate for its price; the cost performance calculation can help the user to better select commodities in the shopping process, and the commodities with higher price selectivity are selected, so that shopping experience with performance and quality matched with the price is obtained.
The embodiment can obtain the evaluation of the commodity quality acceptance degree and commodity price acceptance degree of the user by comprehensively analyzing the data. An algorithm or model may be used to weight the data together to derive the overall acceptance of the quality and price of the good by the user. This may be a numerical score or a range or rating; meanwhile, the cost performance of the commodity can be calculated. The cost performance represents a balance between the quality of the commodity and the acceptance of the user at a certain price. According to the purchasing behavior and preference data of the user, the price and quality data of the commodity are combined, so that the cost performance of the commodity can be calculated, namely, under the view angle of the user, the cost performance of the commodity is estimated; and transmitting the commodity quality acceptance degree, commodity price acceptance degree and the calculated commodity cost performance of the user to a user demand prediction module and a personalized intelligent management module, and providing more personalized shopping experience meeting the user demand as the basis of prediction and management.
Further, the user operation analysis module comprises a user operation history acquisition unit, an operation history conversion unit and an operation data analysis unit;
the user operation history acquisition unit acquires user operation data and transmits the user operation data to the operation history conversion unit;
the operation history conversion unit converts the user operation data to obtain shopping habit data of the user, and transmits the shopping habit data to the operation data analysis unit;
the operation data analysis unit analyzes shopping habit data to obtain user shopping demand data, and transmits the user shopping demand data to the user demand prediction module.
The collected user operation data includes user click data, user shopping operation data, user shopping time data, item collection time data, and platform usage data.
Through comprehensive analysis and mining of the operation data, shopping habit data of the user can be obtained, wherein the shopping habit data comprises commodity preference, purchase frequency, shopping time preference and the like of the user. These shopping habit data may be used to predict the shopping needs of the user; in the operation data analysis unit, shopping habit data can be processed and analyzed by using a data analysis algorithm and a model, and shopping demands of users can be further mined by combining other user data, such as personal information of the users, historical purchase records and the like. These shopping demand data may be transmitted as input to a user demand prediction module for further demand prediction and personalized recommendation.
Further, the user demand prediction module comprises a user demand analysis unit, a demand degree calculation unit, a user classification unit and a user demand prediction unit;
the user demand analysis unit further analyzes the shopping demand data of the user to obtain shopping demand data of the user, and transmits the shopping demand data to the demand degree calculation unit;
the demand computing unit computes shopping demand according to the shopping demand data, and transmits the shopping demand to the user classifying unit and the user demand predicting unit;
according to the purchase frequency of users: the frequency of purchasing a certain type of commodity by the user, namely the ratio of the number of times of purchasing or the number of days of purchasing to the total observation time is calculated. A user with a higher frequency of purchases may indicate a higher demand for such merchandise.
According to the purchase amount of the user: the total or average amount of consumption of the user to purchase a certain type of merchandise is calculated. A user with a higher purchase amount may indicate a higher demand for the type of merchandise.
According to the interaction behavior of the user: according to the interactive behaviors of the user on the shopping platform, such as browsing, shopping cart adding, collection, evaluation and the like, indexes such as the interactive frequency, the interactive duration and the like of the user on certain types of commodities are calculated. A user with more frequent interactions may indicate a higher demand for the type of merchandise, with a 1-100 demand score.
The user classification unit classifies the users according to the shopping demand degrees of the users, and the obtained user types are transmitted to the user demand prediction unit;
in the demand degree score of 1-100, the demand degree of 1-30 is taken as a low-demand classified user, and the user does not need to spend a large amount of resources to generate the personalized shopping demand;
users with the demand degree of 31-70 are used as medium demand classification users, and the users are general users, so that resources can be selected to be spent to generate individual shopping demands, but the updating frequency of the individual shopping demands is reduced;
users with a demand level of 71-100 are classified as high demand users, and such users can spend a great deal of resources to generate their individual shopping demands and keep the individual shopping demands updated at a high frequency.
And the user demand prediction unit analyzes and predicts the demand commodity data of the user according to the shopping demand degree and the user type of the user, and transmits the demand commodity data to the personalized intelligent management module.
Further, the personalized intelligent management module comprises a commodity picking unit, a user personalized demand customizing unit and a user shopping simplifying unit;
the commodity picking unit is used for further picking commodities according to the required commodity data to obtain accurate required commodity data, and transmitting the accurate required commodity data to the user individual requirement customizing unit;
the user individual demand customizing unit customizes the shopping individual demand of the user according to the commodity quality acceptance degree, commodity price acceptance degree and commodity price ratio and accurate demand commodity data obtained by calculation of the user, and transmits the shopping demand of the user to the user shopping simplifying unit;
the user shopping simplifying unit establishes a one-key shopping function, can generate and simplify a shopping list according to the shopping individuality requirement according to a purchase scheme, obtains a simplified shopping list, and transmits the simplified shopping list to the commodity recommending intelligent generating module.
Further, the commodity recommendation intelligent generation module comprises a commodity data integration unit, a commodity recommendation visualization unit and a commodity purchase scheme generation unit;
the commodity data integration unit is used for further accurately obtaining the simplified shopping list, and transmitting the accurate shopping list to the commodity recommendation visualization unit and the commodity purchase scheme generation unit respectively;
the commodity recommendation visualization unit visualizes the accurate shopping list into a commodity recommendation list and transmits the commodity recommendation list to the commodity purchase scheme generation unit to assist in generating a purchase scheme;
and the commodity purchase scheme generating unit generates a purchase scheme according to the accurate shopping list and the commodity recommendation list, and transmits the purchase scheme to the personalized intelligent management module for one-key shopping.
The user can actively adjust the purchase scheme, the system can record the adjustment record of the user on the purchase scheme, so that the user purchase scheme can be automatically generated more accurately, and the demand prediction function of the system is perfected.
Example two
An artificial intelligence based big data demand prediction method for an electronic commerce platform comprises the following steps:
s1, acquiring various data of a user from an electronic commerce platform through a user data reading module, classifying and converting the user data, primarily judging the user, judging the commodity quality acceptance degree and commodity price acceptance degree of the user, and calculating the commodity cost performance; according to the provided data, the commodity quality acceptance degree and commodity price acceptance degree of the user are obtained through conversion:
a1, shopping cart data, collection data and browsing data: and analyzing commodities selected by the user in shopping carts, collection and browsing processes, and analyzing purchase intention and preference. More frequent occurrences of merchandise may suggest a higher level of acceptance by the user of its quality.
A2, evaluation data: and analyzing the commodity evaluation of the user, including text evaluation, star evaluation and the like. And judging the acceptance degree of the user on the commodity quality according to the content and the score of the evaluation.
A3, price data of the completed order and peak expenditure data: the purchasing behavior of the user in different price ranges and the peak expense condition in a specific time period are analyzed. It may be indicated that the user has different acceptance levels for goods of different price segments;
a4, quality data and after-market data: and analyzing data related to commodity quality, such as return rate, complaint number, maintenance times and the like, of the user. A high return rate or number of complaints may indicate that the user has a low acceptance of the quality of the good;
the cost performance calculation process of the commodity comprises the following steps:
(1) completion order price data: according to the price of the commodity purchased by the user, the price is used as one of indexes for measuring the commodity cost.
(2) Quality data: the data including quality score of the commodity, after-sales feedback of the user and the like can be used as one of indexes for measuring the quality of the commodity.
(3) After-market data: the data including the goods return rate, complaint number, maintenance times and the like can reflect the durability, reliability and after-sales service quality of the goods.
(4) The cost performance of the commodity can be calculated using the following formula:
cost performance = commodity mass fraction/commodity price
The commodity quality score is a score for evaluating commodity quality according to quality data, after-sales data and the like, and can be obtained based on methods such as statistical analysis or user evaluation. The commodity price is the price of the commodity purchased by the user based on the price data of the completed order;
s2, further analyzing operation data of the user, analyzing shopping habits and shopping demands of the user, and further predicting the demands of the user based on the shopping demands of the user; according to the provided user operation data, converting to obtain shopping habit data of the user, and analyzing shopping demand data of the user by an operation data analysis unit:
b1, clicking data by a user: and analyzing clicking behaviors of the user, including information of the clicked commodity category, brands, functions and the like, and knowing interest preference and focus of the user. Through statistics and analysis of click data, purchasing habit data of users on commodities of different categories or brands can be obtained.
B2, user purchasing operation data: the user's shopping behavior is analyzed, including the operation of adding merchandise to a shopping cart or a wish list. The shopping behavior frequency and the type of the preference commodity of the user can be observed, and the shopping habit and the demand of the user can be known.
B3, user shopping time data: shopping behaviors of the user during different time periods, such as during the day, night, weekend, etc., are analyzed. The shopping habit and the active time period of the user can be known according to the shopping time data of the user.
B4, storing time data of the articles: the collection time of the user on the commodities is analyzed, and the interest degree and the attention degree of the user on different commodities can be known. The long-term stored merchandise may indicate that the user has a high purchase demand for it.
B5, platform use data: the user's usage behavior on the platform is analyzed, such as data for browsing pages for stay time, searching keywords, participating in promotional campaigns, etc. The user's habit and shopping preference of the platform can be known, so that the shopping requirement of the user can be presumed;
s3, calculating the shopping demand degree of the user through the user demand data, and classifying the user based on the shopping demand degree so as to generate the shopping individual demand subsequently;
s4, predicting the demand commodities of the user by using a user demand prediction module, and picking the commodities by using a personalized intelligent management module to find more accurate demand commodities so as to customize shopping personalized demands for the user;
s5, the personalized intelligent management module establishes a one-key shopping function, and one-key shopping processing can be carried out on a purchase scheme customized by the commodity recommendation intelligent generation module for a user;
and S6, the commodity recommendation intelligent generation module can also conduct accurate and visual on the shopping list of the user, so that basic data is provided for further generation of a purchase scheme, and shopping demand prediction of the user is completed and the purchase process of the user is intelligent.
Claims (9)
1. An artificial intelligence based big data demand prediction method and system for an electronic commerce platform are characterized in that: the big data demand prediction system based on artificial intelligence for the electronic commerce platform comprises a user data reading module, a user operation analysis module, a user demand prediction module, a personalized intelligent management module and a commodity recommendation intelligent generation module, wherein the output end of the user data reading module is respectively connected with the input ends of the user demand prediction module and the personalized intelligent management module, the output end of the user operation analysis module is connected with the input end of the user demand prediction module, the output end of the user demand prediction module is connected with the personalized intelligent management module, and the personalized intelligent management module is connected with the commodity recommendation intelligent generation module in a bidirectional connection manner;
the user data reading module is used for acquiring various data of a user from the electronic commerce platform, integrating the user data, classifying the user data to obtain long-term demand data of the user, short-term demand data of the user and preference data of the user, converting the long-term demand data of the user, the short-term demand data of the user and the preference data of the user to obtain commodity quality acceptance degree and commodity price acceptance degree of the user, calculating commodity cost performance, and transmitting the commodity quality acceptance degree and commodity price acceptance degree of the user and the commodity cost performance obtained by calculation to the user demand prediction module and the personalized intelligent management module;
the user operation analysis module is used for acquiring user operation data, converting the user operation data to obtain shopping habit data of a user, and analyzing the shopping habit data to obtain shopping demand data of the user;
the user demand prediction module is used for further analyzing the shopping demand data of the user to obtain shopping demand data of the user, calculating to obtain shopping demand degrees according to the shopping demand data, classifying the user according to the shopping demand degrees of the user, analyzing and predicting to obtain demand commodity data of the user according to the shopping demand degrees of the user and the user types, and transmitting the demand commodity data to the personalized intelligent management module;
the personalized intelligent management module is used for further picking commodities according to the required commodity data to obtain accurate required commodity data, customizing the shopping personalized demand of the user according to the commodity quality acceptance degree and commodity price acceptance degree of the user and the commodity cost performance and the accurate required commodity data obtained by calculation, establishing a one-key shopping function, generating and simplifying a shopping list according to the shopping personalized demand according to a purchase scheme, obtaining a simplified shopping list and transmitting the simplified shopping list to the commodity recommendation intelligent generation module;
the commodity recommendation intelligent generation module is used for further accurately obtaining the simplified shopping list, visualizing the accurate shopping list into a commodity recommendation list, generating a purchase scheme according to the accurate shopping list and the commodity recommendation list, and transmitting the purchase scheme to the personalized intelligent management module for one-key shopping.
2. The artificial intelligence based big data demand prediction system for electronic commerce platform according to claim 1, wherein: the user data reading module comprises a data reading unit, a data classifying unit and a data converting unit;
the data reading unit acquires various data of the user from the electronic commerce platform, integrates the user data and transmits the user data to the data classifying unit;
the data classifying unit classifies the user data to obtain long-term demand data of the user, short-term demand data of the user and preference data of the user, and transmits the classified user data to the data converting unit for conversion;
the data conversion unit converts the long-term demand data of the user, the short-term demand data of the user and the preference data of the user, obtains commodity quality acceptance degree and commodity price acceptance degree of the user through conversion, calculates commodity cost performance, and transmits the obtained commodity quality acceptance degree and commodity price acceptance degree of the user and the calculated commodity cost performance to the user demand prediction module and the personalized intelligent management module.
3. The artificial intelligence based big data demand prediction system for electronic commerce platform according to claim 1, wherein: the user operation analysis module comprises a user operation history acquisition unit, an operation history conversion unit and an operation data analysis unit;
the user operation history acquisition unit acquires user operation data and transmits the user operation data to the operation history conversion unit;
the operation history conversion unit converts the user operation data to obtain shopping habit data of the user, and transmits the shopping habit data to the operation data analysis unit;
the operation data analysis unit analyzes shopping habit data to obtain user shopping demand data, and transmits the user shopping demand data to the user demand prediction module.
4. The artificial intelligence based big data demand prediction system for electronic commerce platform according to claim 1, wherein: the user demand prediction module comprises a user demand analysis unit, a demand degree calculation unit, a user classification unit and a user demand prediction unit;
the user demand analysis unit further analyzes the shopping demand data of the user to obtain shopping demand data of the user, and transmits the shopping demand data to the demand degree calculation unit;
the demand computing unit computes shopping demand according to the shopping demand data, and transmits the shopping demand to the user classifying unit and the user demand predicting unit;
the user classification unit classifies the users according to the shopping demand degrees of the users, and the obtained user types are transmitted to the user demand prediction unit;
and the user demand prediction unit analyzes and predicts the demand commodity data of the user according to the shopping demand degree and the user type of the user, and transmits the demand commodity data to the personalized intelligent management module.
5. The artificial intelligence based big data demand prediction system for electronic commerce platform according to claim 1, wherein: the personalized intelligent management module comprises a commodity picking unit, a user personalized demand customizing unit and a user shopping simplifying unit;
the commodity picking unit is used for further picking commodities according to the required commodity data to obtain accurate required commodity data, and transmitting the accurate required commodity data to the user individual requirement customizing unit;
the user individual demand customizing unit customizes the shopping individual demand of the user according to the commodity quality acceptance degree, commodity price acceptance degree and commodity price ratio and accurate demand commodity data obtained by calculation of the user, and transmits the shopping demand of the user to the user shopping simplifying unit;
the user shopping simplifying unit establishes a one-key shopping function, can generate and simplify a shopping list according to the shopping individuality requirement according to a purchase scheme, obtains a simplified shopping list, and transmits the simplified shopping list to the commodity recommending intelligent generating module.
6. The artificial intelligence based big data demand prediction system for electronic commerce platform according to claim 1, wherein: the commodity recommendation intelligent generation module comprises a commodity data integration unit, a commodity recommendation visualization unit and a commodity purchase scheme generation unit;
the commodity data integration unit is used for further accurately obtaining the simplified shopping list, and transmitting the accurate shopping list to the commodity recommendation visualization unit and the commodity purchase scheme generation unit respectively;
the commodity recommendation visualization unit visualizes the accurate shopping list into a commodity recommendation list and transmits the commodity recommendation list to the commodity purchase scheme generation unit to assist in generating a purchase scheme;
and the commodity purchase scheme generating unit generates a purchase scheme according to the accurate shopping list and the commodity recommendation list, and transmits the purchase scheme to the personalized intelligent management module for one-key shopping.
7. An artificial intelligence based big data demand prediction method for an electronic commerce platform is characterized by comprising the following steps:
s1, acquiring various data of a user from an electronic commerce platform through a user data reading module, classifying and converting the user data, primarily judging the user, judging the commodity quality acceptance degree and commodity price acceptance degree of the user, and calculating the commodity cost performance;
s2, further analyzing operation data of the user, analyzing shopping habits and shopping demands of the user, and further predicting the demands of the user based on the shopping demands of the user;
s3, calculating the shopping demand degree of the user through the user demand data, and classifying the user based on the shopping demand degree so as to generate the shopping individual demand subsequently;
s4, predicting the demand commodities of the user by using a user demand prediction module, and picking the commodities by using a personalized intelligent management module to find more accurate demand commodities so as to customize shopping personalized demands for the user;
s5, the personalized intelligent management module establishes a one-key shopping function, and one-key shopping processing can be carried out on a purchase scheme customized by the commodity recommendation intelligent generation module for a user;
and S6, the commodity recommendation intelligent generation module can also conduct accurate and visual on the shopping list of the user, so that basic data is provided for further generation of a purchase scheme, and shopping demand prediction of the user is completed and the purchase process of the user is intelligent.
8. The artificial intelligence based big data demand prediction method for electronic commerce platform according to claim 7, wherein: and in the step S1, according to the provided data, the commodity quality acceptance degree and commodity price acceptance degree of the user are obtained through conversion:
a1, shopping cart data, collection data and browsing data: and analyzing commodities selected by the user in shopping carts, collection and browsing processes, and analyzing purchase intention and preference.
A2, evaluation data: and analyzing the commodity evaluation of the user, including text evaluation, star evaluation and the like. And judging the acceptance degree of the user on the commodity quality according to the content and the score of the evaluation.
A3, price data of the completed order and peak expenditure data: the purchasing behavior of the user in different price ranges and the peak expense condition in a specific time period are analyzed.
A4, quality data and after-market data: and analyzing data related to commodity quality, such as return rate, complaint number and maintenance times, of the user.
9. The artificial intelligence based big data demand prediction method for electronic commerce platform according to claim 7, wherein: in the step S2, according to the provided user operation data, shopping habit data of the user is obtained through conversion, and the operation data analysis unit analyzes shopping demand data of the user, wherein the step comprises the following steps:
b1, clicking data by a user: and analyzing clicking behaviors of the user, including information of the clicked commodity category, brands, functions and the like, and knowing interest preference and focus of the user. Through statistics and analysis of click data, purchasing habit data of users on commodities of different categories or brands can be obtained.
B2, user purchasing operation data: the user's shopping behavior is analyzed, including the operation of adding merchandise to a shopping cart or a wish list. The shopping behavior frequency and the type of the preference commodity of the user can be observed, and the shopping habit and the demand of the user can be known.
B3, user shopping time data: shopping behaviors of the user during different time periods, such as during the day, night, weekend, etc., are analyzed. The shopping habit and the active time period of the user can be known according to the shopping time data of the user.
B4, storing time data of the articles: the collection time of the user on the commodities is analyzed, and the interest degree and the attention degree of the user on different commodities can be known. The long-term stored merchandise may indicate that the user has a high purchase demand for it.
B5, platform use data: the user's usage behavior on the platform is analyzed, such as data for browsing pages for stay time, searching keywords, participating in promotional campaigns, etc. The user's usage habits and shopping preferences of the platform can be known, thereby inferring the user's shopping needs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311302488.9A CN117333262A (en) | 2023-10-09 | 2023-10-09 | Big data demand prediction method and system based on artificial intelligence for electronic commerce platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311302488.9A CN117333262A (en) | 2023-10-09 | 2023-10-09 | Big data demand prediction method and system based on artificial intelligence for electronic commerce platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117333262A true CN117333262A (en) | 2024-01-02 |
Family
ID=89291378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311302488.9A Withdrawn CN117333262A (en) | 2023-10-09 | 2023-10-09 | Big data demand prediction method and system based on artificial intelligence for electronic commerce platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117333262A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118071458A (en) * | 2024-03-06 | 2024-05-24 | 广州精粹智能科技股份有限公司 | Commodity demand prediction method and system based on big data analysis |
-
2023
- 2023-10-09 CN CN202311302488.9A patent/CN117333262A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118071458A (en) * | 2024-03-06 | 2024-05-24 | 广州精粹智能科技股份有限公司 | Commodity demand prediction method and system based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bose et al. | Quantitative models for direct marketing: A review from systems perspective | |
| Greenstein-Messica et al. | Personal price aware multi-seller recommender system: Evidence from eBay | |
| US20220318858A1 (en) | Systems and methods for transformation of raw data to actionable data | |
| US20080052278A1 (en) | System and method for modeling value of an on-line advertisement campaign | |
| US20220076299A1 (en) | Intelligent electronic advertisement generation and distribution | |
| US11321724B1 (en) | Product evaluation system and method of use | |
| CN111738805B (en) | Behavior log-based search recommendation model generation method, device and storage medium | |
| CN116452261B (en) | Advertisement delivery data processing method based on cross-border E-commerce service platform | |
| CN117333262A (en) | Big data demand prediction method and system based on artificial intelligence for electronic commerce platform | |
| CN118071458A (en) | Commodity demand prediction method and system based on big data analysis | |
| CN115131101A (en) | Individualized intelligent recommendation system for insurance products | |
| CN117557306B (en) | Management system for classifying consumers based on behaviors and characteristics | |
| WO2002079901A2 (en) | Customer preference system | |
| CN117131261A (en) | E-commerce content recommendation system based on AI and big data analysis | |
| CN117495415A (en) | Pricing decision analysis method and system based on commodity purchase cost and market bidding | |
| CN110490682A (en) | The method and apparatus for analyzing item property | |
| Matos et al. | A deep learning-based decision support system for mobile performance marketing | |
| KR20230072097A (en) | System and method for recommending product based on rate of return | |
| CN113362141A (en) | Associated commodity recommendation method, device, medium and electronic equipment | |
| Kim et al. | Predicting Session Conversion on E-commerce: A Deep Learning-based Multimodal Fusion Approach | |
| CN118411191B (en) | Store customer information acquisition and quotation optimization method and device of ERP system | |
| Cheng | Construction of User Behavior Analysis and Prediction Model in Multi-Pathway E-commerce Environment | |
| Chie et al. | Customer satisfaction towards the application of artificial intelligence in e-commerce | |
| Brahma et al. | Dynamic Modeling of Brand Loyalty in Retail: A Semi-Supervised Approach Incorporating Temporal Effects and Purchase Behavior Sequences | |
| US20240338600A1 (en) | System and method for automatically generating and presenting insight data in form of natural language |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240102 |
|
| WW01 | Invention patent application withdrawn after publication |