CN115510329B - Brand marketing software management method based on cloud computing big data - Google Patents
Brand marketing software management method based on cloud computing big data Download PDFInfo
- Publication number
- CN115510329B CN115510329B CN202211243829.5A CN202211243829A CN115510329B CN 115510329 B CN115510329 B CN 115510329B CN 202211243829 A CN202211243829 A CN 202211243829A CN 115510329 B CN115510329 B CN 115510329B
- Authority
- CN
- China
- Prior art keywords
- commodity
- customer
- commodities
- information
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of cloud computing, in particular to a brand marketing software management method based on cloud computing big data. The method comprises the steps that S1, information of commodities purchased by a customer is collected by a merchant, and the types of the commodities purchased by the customer, the quantity of the commodities and the steps are determined; s2, calculating the stage of purchasing the commodity by the customer according to the commodity type and the commodity number purchased by the customer, determining the commodity associated with the commodity and storing the commodity in a database. According to the commodity information purchased by the customer, the stage of the customer for purchasing the commodity is deduced, the commodity associated with the commodity purchased by the customer is analyzed according to the purchased commodity information and the stage, corresponding commodity recommending information is sent to the customer at regular time, and the adaptive information of the commodity and the customer is provided, so that the commodity linkage marketing scheme is increased, commodity marketing diversity is improved, the purchasing demand of the customer is predicted, and a proper commodity type is provided for the customer in corresponding time.
Description
Technical Field
The invention relates to the technical field of cloud computing, in particular to a brand marketing software management method based on cloud computing big data.
Background
Marketing management refers to a set of information collected and organized about organizations or consumer individuals for a marketing purpose to predict, describe, manage and control the market, thereby maximizing sales process datamation, profit maximization and sustainable market development; the purpose of marketing data analysis is to ensure that marketing measures are implemented so that each process of marketing is performed more accurately.
Most of the prior marketing management methods judge that the customers purchase goods through big data and recommend similar goods according to the types of the goods, but some goods have timeliness, that is, after a certain period of time, the customers do not need the products, at the moment, the goods or the goods similar to the goods are continuously recommended to the customers, so that the sales volume of the goods is difficult to increase, and meanwhile, the customers are also caused to feel dislike, the recommended information is shielded or even reported by the customers, and the recommending effect is greatly reduced.
Disclosure of Invention
The invention aims to provide a brand marketing software management method based on cloud computing big data, which aims to solve the problems in the background technology.
In order to achieve the above purpose, a brand marketing software management method based on cloud computing big data is provided, which comprises the following steps:
s1, acquiring information of commodities purchased by a customer by a merchant, and determining the types and the quantity of the commodities purchased by the customer;
s2, calculating the stage of purchasing the commodity by the customer according to the commodity type and the commodity number purchased by the customer, determining the commodity associated with the commodity and storing the commodity in a database;
s3, combining the stage of purchasing the commodity by the customer, analyzing the related commodity which is consistent with the demand of the customer in the commodities related to the commodity, predicting the commodity which the customer wants to purchase in the later period, and comparing the commodity in the inventory of the merchant with the related commodity;
s4, sending corresponding commodity information to the customer at regular time, and providing adaptation information of the commodity and the customer;
s5, receiving customer feedback information, and comparing calculation results;
and S6, obtaining a calculation difference according to the comparison result, updating the database in time, and providing a corresponding new commodity type according to the feedback result.
As a further improvement of the technical scheme, the method for collecting the information of the commodity purchased by the customer in S1 is as follows:
s1.1, extracting commodity information purchased by a customer in the same period by combining background purchase information;
s1.2, judging the types of commodities purchased by the same customer, and analyzing whether the single property exists in each commodity;
s1.3, marking the commodities with singleness, and not considering the commodities when the commodities are related in the later period.
As a further improvement of the technical scheme, the singleness analysis in S1.2 adopts a singleness judgment algorithm, and the algorithm formula is as follows:
where F is the unity ratio, ω is the unity constant,is the number of commodities, usually 1,/or->For the total number of items associated with the item, F (x) is a singleness calculation function, x is a singleness ratio, F is a singleness ratio threshold, when the singleness ratio F is not less than 1 and the singleness ratio threshold F is not less than 1, the singleness calculation function F (x) output is 0, indicating that the item is singleness at this time, and when the singleness ratio F is less than 1, the singleness calculation function F (x) output is 1, indicating that the item is not singleness at this time.
As a further improvement of the present technical solution, the method for identifying related goods in S2 includes the following steps:
s2.1, analyzing the crowd suitable for purchased commodities;
s2.2, according to the type of the purchased commodity, simultaneously analyzing the requirements of customers purchasing the commodity in different periods;
s2.3, obtaining commodities which are of the same type and are suitable for different stages, and eliminating commodities corresponding to the stage where the customer is located;
and S2.4, marking the removed rest commodities according to time sequence, and sequentially marking the removed rest commodities as commodities associated with the initial purchase of the commodity by the customer.
As a further improvement of the technical scheme, the method for identifying whether the merchant stores the corresponding commodity at S3 is as follows:
s3.1, judging characteristic points of the related commodity by combining the use effect of the related commodity;
s3.2, retrieving merchant commodity database information and comparing the merchant commodity database information with characteristic points of related commodities;
s3.3, analyzing the database commodity which is most attached to the related commodity according to the comparison result.
As a further improvement of the technical scheme, the characteristic point comparison method of the related commodity in S3.2 adopts a characteristic point comparison algorithm, and the algorithm formula is as follows:
A＝[a 1 ，a 2 ，...，a n ]；
B＝[b 1 ，b 2 ，…，b m ]；
wherein A is each feature point set of the related commodity, a 1 To a n B is a merchant database commodity characteristic point set, B 1 To b m For each feature point of the merchant database commodity, f (C) is a mapping function of each feature point set B of the merchant database commodity and each feature point set A of the associated commodity, C is a comparison weight ratio,for the comparison coincidence rate threshold value, when the comparison coincidence rate C is smaller than the comparison coincidence rate threshold value +.>The output of the mapping function f (C) is 0, which indicates that the characteristic points of the database commodity selected by the merchant database are not coincident with the characteristic points of the related commodity, when the comparison coincidence rate C is not less than the comparison coincidence rate threshold value +.>And the output of the mapping function f (C) is 1, which indicates that the characteristic points of the database commodity selected by the merchant database are coincident with the characteristic points of the related commodity.
As a further improvement of the present technical solution, the method for providing the information of the adaptation between the commodity and the customer in S4 is as follows:
s4.1, recommending related commodities to a customer on time;
s4.2, obtaining the beneficial effects of the associated commodity according to the characteristic points of the associated commodity;
s4.3, binding the beneficial effects of the related commodities to the related commodities and recommending the related commodities to the customer.
As a further improvement of the technical scheme, the method for receiving the customer feedback information and comparing the calculation result in the S5 is as follows:
s5.1, tracking feedback information after the customer receives the recommended information;
s5.2, judging whether the customer purchases the related commodity in the corresponding time;
s5.3, comparing feedback information provided by customers who do not purchase the related commodity, and judging a calculation result.
As a further improvement of the present technical solution, the method for updating the database in S6 is as follows:
s6.1, identifying the related commodity with the error according to the comparison result;
s6.2, analyzing the current period and the calculation result of the customer according to the information fed back by the customer;
s6.3, analyzing the error reasons, and timely retrieving corresponding commodities in a commodity database according to information fed back by customers.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the brand marketing software management method based on the cloud computing big data, the stage of purchasing the commodity by the customer is deduced according to commodity information purchased by the customer, the commodity related to the commodity purchased by the customer is analyzed according to the commodity information purchased and the stage, corresponding commodity recommending information is sent to the customer at regular time, and the adaptation information of the commodity and the customer is provided, so that commodity linkage marketing schemes are increased, commodity marketing diversity is improved, purchasing demands of the customer are predicted, and proper commodity types are provided for the customer in corresponding time.
2. According to the brand marketing software management method based on the cloud computing big data, the requirements of customers who purchase the goods in different periods are analyzed through a related goods confirming method, the goods required in different periods are determined according to the requirements of the customers in different periods, meanwhile, the goods corresponding to the previous stage of the customers are removed, the remaining goods after removal are marked according to time sequence, and the goods are marked as goods related to the initial purchase of the goods by the customers in sequence.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a flow chart of the acquisition method of the present invention;
FIG. 3 is a flow chart of a method for validating associated merchandise in accordance with the present invention;
FIG. 4 is a flow chart of an identification method of the present invention;
FIG. 5 is a flow chart of a method for adapting information according to the present invention;
FIG. 6 is a flow chart of a method for comparing calculation results according to the present invention;
FIG. 7 is a flow chart of a method for updating a database according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Referring to fig. 1-7, a brand marketing software management method based on cloud computing big data is provided, which includes the following steps:
s1, acquiring information of commodities purchased by a customer by a merchant, and determining the types and the quantity of the commodities purchased by the customer;
s2, calculating the stage of purchasing the commodity by the customer according to the commodity type and the commodity number purchased by the customer, determining the commodity associated with the commodity and storing the commodity in a database;
s3, combining the stage of purchasing the commodity by the customer, analyzing the related commodity which is consistent with the demand of the customer in the commodities related to the commodity, predicting the commodity which the customer wants to purchase in the later period, and comparing the commodity in the inventory of the merchant with the related commodity;
s4, sending corresponding commodity information to the customer at regular time, and providing adaptation information of the commodity and the customer;
s5, receiving customer feedback information, and comparing calculation results;
and S6, obtaining a calculation difference according to the comparison result, updating the database in time, and providing a corresponding new commodity type according to the feedback result.
Specific marketing process: firstly, the merchant collects the information of the commodity purchased by the customer according to the background statistics purchase information, determines the commodity type and commodity quantity purchased by the customer, determines the commodity purchasing time of the customer, then calculates the commodity purchasing stage according to the commodity type and commodity quantity purchased by the customer, for example, the customer purchases a type of milk powder which is only suitable for infants of two ages, simultaneously deduces that the customer needs to purchase a new type of milk powder with higher suitable age according to the time of the purchased commodity, stores the calculated information into a database, later invokes the information through the database, then analyzes the commodity related to the commodity purchased by the customer according to the calculation result (for example, after judging the commodity type purchased by the current stage of the infant is different in different stages, the commodity type required by the different stages is calculated), analyzes the commodity type required by the customer, and the commodities are related to the commodity originally purchased by the customer), predicts the commodity required by the customer in the later stage, compares the new commodity type required by the customer with the new commodity type required by the purchased by the customer, stores the calculated information into a database, later analyzes the information according to the calculation result, analyzes the commodity related to the commodity required by the customer (for the commodity type required by the customer is different in different stages, judges the commodity type required by the current stage is different in the different stages, and the commodity is calculated by the commodity is accurately corresponding to the commodity, and the recommended by the commodity is calculated by the customer, and the information is calculated when the information is calculated and the information is accurately comparing the information is calculated and the information is compared with the commodity type required by the commodity which is calculated and the commodity which is calculated by the commodity which is calculated and the commodity type purchased by the commodity, according to the commodity information purchased by the customer, the stage of the customer for purchasing the commodity is deduced, the commodity associated with the commodity purchased by the customer is analyzed according to the purchased commodity information and the stage, corresponding commodity recommending information is sent to the customer at regular time, and the adaptive information of the commodity and the customer is provided, so that the commodity linkage marketing scheme is increased, commodity marketing diversity is improved, the purchasing demand of the customer is predicted, and a proper commodity type is provided for the customer in corresponding time.
The method for collecting information on the commodity purchased by the customer in S1 is as follows:
s1.1, extracting commodity information purchased by a customer in the same period by combining background purchase information;
s1.2, judging the types of commodities purchased by the same customer, and analyzing whether the single property exists in each commodity;
s1.3, marking the commodities with singleness, and not considering the commodities when the commodities are related in the later period.
When the commodity type identification system is specifically used, first, the background purchasing information is combined, commodity information purchased by customers in the same period is extracted, the types of commodities are analyzed, whether the commodities belong to food types or use types are judged, whether the commodities are unique is judged after the commodity types are confirmed, for example, certain commodities are only used in the period of infants, the commodities of the types are not used after the period of infants is spent, the fact that the commodities are not related is indicated to be unique is also shown, the commodities are not considered in the process of commodity association in the later period, pre-sorting treatment is carried out on the commodities purchased by the customers in advance, the system is helped to remove the commodities with the unique in advance, and judging efficiency of commodities related to the commodities purchased in the later period is improved.
Further, the singleness analysis in S1.2 adopts a singleness judgment algorithm, and the algorithm formula is as follows:
wherein F is the unity ratio and ω is the unityA constant of the one-way property,is the number of commodities, usually 1,/or->For the total number of items associated with the item, F (x) is a singleness calculation function, x is a singleness ratio, F is a singleness ratio threshold, when the singleness ratio F is not less than 1 and the singleness ratio threshold F is not less than 1, the singleness calculation function F (x) output is 0, indicating that the item is singleness at this time, and when the singleness ratio F is less than 1, the singleness calculation function F (x) output is 1, indicating that the item is not singleness at this time.
Still further, the method for confirming the associated commodity in S2 includes the steps of:
s2.1, analyzing the crowd suitable for purchased commodities;
s2.2, according to the type of the purchased commodity, simultaneously analyzing the requirements of customers purchasing the commodity in different periods;
s2.3, obtaining commodities which are of the same type and are suitable for different stages, and eliminating commodities corresponding to the stage where the customer is located;
and S2.4, marking the removed rest commodities according to time sequence, and sequentially marking the removed rest commodities as commodities associated with the initial purchase of the commodity by the customer.
In the specific use, in the commodity confirmation process related to the initial commodity purchase of the customer, firstly, the proper crowd of the purchased commodity is analyzed, according to the type of the purchased commodity, the demands of the customer who purchases the commodity in different periods are analyzed, the commodity required in different periods is determined according to the demands of the customer in different periods, meanwhile, the commodity corresponding to the stage of the customer before is removed, the rest of removed commodity is marked according to time sequence, the commodity related to the initial commodity purchase of the customer is marked in sequence, for example, infant milk powder is generally suitable for children of 1 to 12 years, and the nutrients required by the children in different periods are different, the types of infant milk powder consumed are different, but the milk powder is the milk powder required in the process of 1 to 12 years old of children, the milk powder is related to each other, when a customer purchases the milk powder corresponding to 4 years old, the milk powder related to the infant milk powder is the milk powder corresponding to 1 to 3 years old and the milk powder corresponding to 5 to 12 years old, at the moment, the milk powder corresponding to 1 to 3 years old is removed, because the customer has spent the period of 1 to 3 years old, the prior corresponding milk powder is not required to be recommended to the customer, the related milk powder corresponding to 5 to 12 years old is marked according to time sequence, and the later can be used as related commodity to be recommended to the customer at regular time.
Specifically, the method for identifying whether the merchant inventory has the corresponding commodity in S3 is as follows:
s3.1, judging characteristic points of the related commodity by combining the use effect of the related commodity;
s3.2, retrieving merchant commodity database information and comparing the merchant commodity database information with characteristic points of related commodities;
s3.3, analyzing the database commodity which is most attached to the related commodity according to the comparison result.
When the method is specifically used, firstly, the use effect of the associated commodity is analyzed, for example, the associated commodity can bring positive influences to customers, characteristic points of the associated commodity are judged according to the positive influences, then, merchant commodity database information is called, the characteristic points of the associated commodity are compared, the comparison coincidence rate of the database commodity and the characteristic points of the associated commodity is judged, the database commodity which is most attached to the associated commodity is obtained, and the database commodity is used as the associated commodity which corresponds to the purchased commodity of the merchant and is recommended to the customers as the commodity which is recommended in the later period.
In addition, the characteristic point comparison method of the related commodity in S3.2 adopts a characteristic point comparison algorithm, and the algorithm formula is as follows:
A＝[a 1 ，a 2 ，…，a n ]；
B＝[b 1 ，b 2 ，…，b m ]；
wherein A is offFeature point set of commodity 1 To a n B is a merchant database commodity characteristic point set, B 1 To b m For each feature point of the merchant database commodity, f (f) is a mapping function of each feature point set B of the merchant database commodity and each feature point set A of the associated commodity, C is a comparison weight,for the comparison coincidence rate threshold value, when the comparison coincidence rate C is smaller than the comparison coincidence rate threshold value +.>The output of the mapping function f (C) is 0, which indicates that the characteristic points of the database commodity selected by the merchant database are not coincident with the characteristic points of the related commodity, when the comparison coincidence rate C is not less than the comparison coincidence rate threshold value +.>And the output of the mapping function f (C) is 1, which indicates that the characteristic points of the database commodity selected by the merchant database are coincident with the characteristic points of the related commodity.
Further, the method for providing the adaptation information of the commodity and the customer in S4 is as follows:
s4.1, recommending related commodities to a customer on time;
s4.2, obtaining the beneficial effects of the associated commodity according to the characteristic points of the associated commodity;
s4.3, binding the beneficial effects of the related commodities to the related commodities and recommending the related commodities to the customer.
When the method is specifically used, related commodities are recommended to customers on time according to the time points determined by the related commodities, the beneficial effects of the related commodities are obtained according to the characteristic points of the related commodities, the beneficial effects which can be obtained by the customers using the commodities in the current period are described, the beneficial effects of the related commodities are bound with the related commodities and are recommended to the customers together for screening by the customers, the customers are helped to timely obtain the commodities required in the current period, and the time of the customers for pre-purchasing the commodities in the current period is reduced.
Still further, in S5, the method for receiving the feedback information of the customer and comparing the calculation result is as follows:
s5.1, tracking feedback information after the customer receives the recommended information;
s5.2, judging whether the customer purchases the related commodity in the corresponding time;
s5.3, comparing feedback information provided by customers who do not purchase the related commodity, and judging a calculation result.
When the method is specifically used, feedback information after a customer receives recommendation information is tracked, whether the customer purchases the associated commodity in the corresponding time is judged, when the customer purchases the associated commodity in the corresponding time, the customer is indicated to accept the recommendation result, the associated commodity is suitable for the customer in the current period, when the customer does not purchase the associated commodity in the corresponding time, the customer is indicated to not accept the recommendation result, at the moment, the feedback information provided by the customer is received, whether a calculation error occurs or not is judged according to the feedback information, the sequence of the associated commodity is changed, and error correction is timely made.
In addition, the method of updating the database in S6 is as follows:
s6.1, identifying the related commodity with the error according to the comparison result;
s6.2, analyzing the current period and the calculation result of the customer according to the information fed back by the customer;
s6.3, analyzing the error reasons, and timely retrieving corresponding commodities in a commodity database according to information fed back by customers.
When the method is specifically used, when the related commodity errors occur according to the comparison results, the related commodities with the errors are identified, at the moment, the current period and the calculation result of the customer are analyzed according to the information fed back by the customer, or the customer does not accept the currently recommended commodity due to other reasons, so that the merchant is helped to timely analyze the reason of failure in recommending the commodity, timely make adjustment, timely retrieve the corresponding commodity in the commodity database according to the information fed back by the customer, and timely recommend the commodity to the customer.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A brand marketing software management method based on cloud computing big data is characterized by comprising the following steps:
s1, acquiring information of commodities purchased by a customer by a merchant, and determining the types and the quantity of the commodities purchased by the customer;
s2, calculating the stage of purchasing the commodity by the customer according to the commodity type and the commodity number purchased by the customer, determining the commodity associated with the commodity and storing the commodity in a database;
s3, combining the stage of purchasing the commodity by the customer, analyzing the related commodity which is consistent with the demand of the customer in the commodities related to the commodity, predicting the commodity which the customer wants to purchase in the later period, and comparing the commodity in the inventory of the merchant with the related commodity;
s4, sending corresponding commodity information to the customer at regular time, and providing adaptation information of the commodity and the customer;
s5, receiving customer feedback information, and comparing calculation results;
s6, obtaining a calculation difference according to the comparison result, updating a database in time, and providing a corresponding new commodity type according to the feedback result;
the method for collecting the information of the commodity purchased by the customer in S1 is as follows:
s1.1, extracting commodity information purchased by a customer in the same period by combining background purchase information;
s1.2, judging the types of commodities purchased by the same customer, and analyzing whether the single property exists in each commodity;
s1.3, marking the commodities with singleness, and not considering the commodities when the commodities are associated in the later period;
the singleness analysis in S1.2 adopts a singleness judgment algorithm, and the algorithm formula is as follows:
wherein F is a unity ratio, ω is a unity constant,is the number of commodities, usually 1,/or->For the total number of commodities associated with the commodity, F (x) is a singleness calculation function, x is a singleness ratio, F is a singleness ratio threshold, when the singleness ratio F is not less than 1 on the singleness ratio F, the output of the singleness calculation function F (x) is 0, which indicates that the commodity has singleness at the moment, and when the singleness ratio F is less than 1 on the singleness ratio F, the output of the singleness calculation function F (x) is 1, which indicates that the commodity has no singleness at the moment;
the method for identifying whether the merchant stores the corresponding commodities in S3 is as follows:
s3.1, judging characteristic points of the related commodity by combining the use effect of the related commodity;
s3.2, retrieving merchant commodity database information and comparing the merchant commodity database information with characteristic points of related commodities;
s3.3, analyzing database commodities which are most fit with the related commodities according to the comparison result;
the characteristic point comparison algorithm is adopted by the related commodity characteristic point comparison method in the S3.2, and the algorithm formula is as follows:
A＝[a 1 ，a 2 ，…，a n ]；
B＝[b 1 ，b 2 ，…，b m ]；
wherein A is each feature point set of the related commodity, a 1 To a n B is a merchant database commodity characteristic point set, B 1 To b m For each feature point of the merchant database commodity, f (C) is a mapping function of each feature point set B of the merchant database commodity and each feature point set A of the associated commodity, C is a comparison weight ratio,for the comparison coincidence rate threshold value, when the comparison coincidence rate C is smaller than the comparison coincidence rate threshold value +.>The output of the mapping function f (C) is 0, which indicates that the characteristic points of the database commodity selected by the merchant database are not coincident with the characteristic points of the related commodity, when the comparison coincidence rate C is not less than the comparison coincidence rate threshold valueAnd the output of the mapping function f (C) is 1, which indicates that the characteristic points of the database commodity selected by the merchant database are coincident with the characteristic points of the related commodity.
2. The brand marketing software management method based on cloud computing big data of claim 1, wherein: the method for confirming the related commodity in the S2 comprises the following steps:
s2.1, analyzing the crowd suitable for purchased commodities;
s2.2, according to the type of the purchased commodity, simultaneously analyzing the requirements of customers purchasing the commodity in different periods;
s2.3, obtaining commodities which are of the same type and are suitable for different stages, and eliminating commodities corresponding to the stage where the customer is located;
and S2.4, marking the removed rest commodities according to time sequence, and sequentially marking the removed rest commodities as commodities associated with the initial purchase of the commodity by the customer.
3. The brand marketing software management method based on cloud computing big data of claim 1, wherein: the method for providing the adaptation information of the commodity and the customer in the step S4 is as follows:
s4.1, recommending related commodities to a customer on time;
s4.2, obtaining the beneficial effects of the associated commodity according to the characteristic points of the associated commodity;
s4.3, binding the beneficial effects of the related commodities to the related commodities and recommending the related commodities to the customer.
4. The brand marketing software management method based on cloud computing big data of claim 1, wherein: and S5, receiving customer feedback information, and comparing the calculation results as follows:
s5.1, tracking feedback information after the customer receives the recommended information;
s5.2, judging whether the customer purchases the related commodity in the corresponding time;
s5.3, comparing feedback information provided by customers who do not purchase the related commodity, and judging a calculation result.
5. The brand marketing software management method based on cloud computing big data of claim 1, wherein: the method for updating the database in the step S6 is as follows:
s6.1, identifying the related commodity with the error according to the comparison result;
s6.2, analyzing the current period and the calculation result of the customer according to the information fed back by the customer;
s6.3, analyzing the error reasons, and timely retrieving corresponding commodities in a commodity database according to information fed back by customers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211243829.5A CN115510329B (en) | 2022-10-11 | 2022-10-11 | Brand marketing software management method based on cloud computing big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211243829.5A CN115510329B (en) | 2022-10-11 | 2022-10-11 | Brand marketing software management method based on cloud computing big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115510329A CN115510329A (en) | 2022-12-23 |
| CN115510329B true CN115510329B (en) | 2023-09-15 |
Family
ID=84510369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211243829.5A Active CN115510329B (en) | 2022-10-11 | 2022-10-11 | Brand marketing software management method based on cloud computing big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115510329B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115880037B (en) * | 2023-03-03 | 2023-05-12 | 量子数科科技有限公司 | Commodity recommendation method based on multi-project planning integration analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106981011A (en) * | 2017-03-20 | 2017-07-25 | 北京小米移动软件有限公司 | Recommendation method, device and the terminal of article |
| CN110992115A (en) * | 2020-03-05 | 2020-04-10 | 深圳市莱华仕生物科技有限公司 | Method and device for preparing beverage powder and apparatus |
| CN112270589A (en) * | 2020-12-01 | 2021-01-26 | 盐城志娟网络科技有限公司 | Online shopping mall commodity recommendation system based on cloud computing big data analysis |
| CN114169927A (en) * | 2021-12-07 | 2022-03-11 | 合肥工业大学 | Product personalized combination recommendation method based on multi-arm slot machine algorithm |
-
2022
- 2022-10-11 CN CN202211243829.5A patent/CN115510329B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106981011A (en) * | 2017-03-20 | 2017-07-25 | 北京小米移动软件有限公司 | Recommendation method, device and the terminal of article |
| CN110992115A (en) * | 2020-03-05 | 2020-04-10 | 深圳市莱华仕生物科技有限公司 | Method and device for preparing beverage powder and apparatus |
| CN112270589A (en) * | 2020-12-01 | 2021-01-26 | 盐城志娟网络科技有限公司 | Online shopping mall commodity recommendation system based on cloud computing big data analysis |
| CN114169927A (en) * | 2021-12-07 | 2022-03-11 | 合肥工业大学 | Product personalized combination recommendation method based on multi-arm slot machine algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115510329A (en) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9785953B2 (en) | System and method for generating demand groups | |
| CN109544233B (en) | Fashion demand prediction method for E-business service | |
| US20100010870A1 (en) | System and Method for Tuning Demand Coefficients | |
| CN109727078B (en) | Sales prediction correction method based on commodity category tree | |
| CN114219558B (en) | Intelligent agricultural product recommendation system based on data mining | |
| CN111738805B (en) | Behavior log-based search recommendation model generation method, device and storage medium | |
| US20110131079A1 (en) | System and Method for Modeling by Customer Segments | |
| CN115510329B (en) | Brand marketing software management method based on cloud computing big data | |
| CN116205560A (en) | Inventory automation management system and method thereof | |
| CN110503456B (en) | Fresh product production guiding method and system | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| CN108470301A (en) | A kind of commodity network method of commerce | |
| CN113570398A (en) | Promotion data processing method, model training method, system and storage medium | |
| CN113139768B (en) | Goods shortage monitoring method based on unmanned vending machine | |
| CN111401975B (en) | Big data-based supply and demand early warning method | |
| CN113159828A (en) | Promotion scheme recommendation method and device and computer readable storage medium | |
| CN113159885A (en) | E-commerce platform virtual commodity order delivery method | |
| CN112396496A (en) | Intelligent commodity recommendation management system of electronic commerce platform based on cloud computing | |
| CN111415208A (en) | New product pricing system and method based on reverse thrust method and dynamic pricing model | |
| CN110634051B (en) | Fresh agricultural product recommendation method based on multi-granularity fuzzy data | |
| CN116012086A (en) | Commodity price estimating method, commodity price estimating device, electronic equipment and storage medium | |
| CN105913276A (en) | Price error-proofing method based on SKU | |
| CN115880037A (en) | Commodity recommendation method based on multi-project planning integration analysis | |
| CN115936819A (en) | Commodity scoring system and establishment method | |
| CN111768139B (en) | Stock processing method, apparatus, device and storage 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 |