Nothing Special   »   [go: up one dir, main page]

CN110969512B - Commodity recommendation method and device based on user purchasing behavior - Google Patents

Commodity recommendation method and device based on user purchasing behavior Download PDF

Info

Publication number
CN110969512B
CN110969512B CN201911215731.7A CN201911215731A CN110969512B CN 110969512 B CN110969512 B CN 110969512B CN 201911215731 A CN201911215731 A CN 201911215731A CN 110969512 B CN110969512 B CN 110969512B
Authority
CN
China
Prior art keywords
information
commodity
obtaining
purchasing
shop
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
Application number
CN201911215731.7A
Other languages
Chinese (zh)
Other versions
CN110969512A (en
Inventor
刘铁
熊磊
许先才
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Yunintegral Technology Co ltd
Original Assignee
Shenzhen Yunintegral Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Yunintegral Technology Co ltd filed Critical Shenzhen Yunintegral Technology Co ltd
Priority to CN201911215731.7A priority Critical patent/CN110969512B/en
Publication of CN110969512A publication Critical patent/CN110969512A/en
Application granted granted Critical
Publication of CN110969512B publication Critical patent/CN110969512B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0631Item recommendations

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a commodity recommendation method and device based on user purchasing behavior, and relates to the technical field of information pushing, wherein first shop information is obtained and comprises a first commodity; obtaining first member information for purchasing a first commodity in a first shop, wherein the first member has first address information; obtaining second shop information, wherein the second shop information comprises a second commodity; obtaining second member information for purchasing a second commodity in a second shop, the second member having second address information; judging whether the first address information and the second address information meet a first preset condition or not; when satisfied, the first member and the second member have a first association relationship; obtaining a first commonality factor for the first commodity and the second commodity; judging whether the first member and the second member have a first purchasing relationship; when the commodity recommending method is available, the first commodity is recommended to the second member, the second commodity is recommended to the first member, and the technical effect of accurately recommending commodities to the user is achieved.

Description

Commodity recommendation method and device based on user purchasing behavior
Technical Field
The invention relates to the technical field of information pushing, in particular to a commodity recommendation method and device based on user purchasing behavior.
Background
With the coming of the internet era, living habits and shopping habits of people are changed, and more consumers begin to shop and consume on the internet. With the development and application of electronic commerce, in order to facilitate merchants to perform targeted and targeted recommendation on different users, many enterprises develop a service mode of personalized information recommendation based on big data. The electronic commerce website provides products and services for users, and simultaneously increases the difficulty of the users to quickly and accurately find product information meeting the requirements of the users in massive commodity information. In the existing E-commerce enterprises, commodity recommendation depends on collecting and analyzing behavior data and shopping records of users to carry out related recommendation for the users.
However, the applicant of the present invention finds that the prior art has at least the following technical problems:
the number of commodities in the existing E-commerce platform is large, information overload is easily caused to cause difficulty in selection of users, recommended commodities cannot meet the requirements of the users, personalized commodity recommendation is difficult to perform for the users, shopping experience of the users is reduced, commodity recommendation cannot be performed more scientifically and reasonably, and personalized commodity recommendation for each user is formed.
Disclosure of Invention
The embodiment of the invention provides a commodity recommendation method and device based on user purchasing behavior, and solves the technical problems that in the prior art, the number of commodities in an e-commerce platform is large, information overload is easily caused, the user selection is difficult, the recommended commodities cannot meet the requirements of the user, personalized commodity recommendation is difficult for the user, and the shopping experience of the user is reduced, so that commodities which accord with the preference of the user can be recommended to the user in a more targeted manner, the personalized requirements of the user are better met, an intelligent commodity recommendation mode is favorably established, and the shopping experience of the user is improved.
In view of the foregoing problems, the embodiments of the present application are provided to provide a method and an apparatus for recommending a product based on a user purchasing behavior.
In a first aspect, the present invention provides a method for recommending a commodity based on a user purchasing behavior, the method including: obtaining first shop information, wherein the first shop information comprises a first commodity; obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information; obtaining second shop information, wherein the second shop information comprises a second commodity; obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information; judging whether the first address information and the second address information meet a first preset condition or not; when the first preset condition is met, the first member and the second member have a first association relationship; obtaining a first commonality factor for the first and second merchandise; judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor; and when the first purchasing relationship exists, recommending the first commodity to the second member, and recommending the second commodity to the first member.
Preferably, the method further comprises: acquiring a first geographical position according to the first address information; obtaining first label information according to the first geographic position; obtaining a second geographic position according to the second address information; obtaining second label information according to the second geographic position; judging whether the first label information and the second label information meet a second preset condition or not; and when the second preset condition is met, the first member and the second member have a first association relationship.
Preferably, the method further comprises: when the first label information and the second label information do not meet a second preset condition, obtaining first historical order information of the first member; obtaining a third commodity according to the first historical order information, wherein the third commodity and the first commodity are in the same commodity category; obtaining third label information according to the third commodity; judging whether the second label information and the third label information meet a third preset condition or not; and when the third preset condition is met, the first member and the second member have a first association relationship.
Preferably, the obtaining a first commonality factor for the first article and the second article includes: obtaining fourth label information according to the first commodity; obtaining a first preference keyword according to the fourth label information; acquiring fifth label information according to the second commodity; obtaining a second preferred keyword according to the fifth label information; judging whether the first preferred keywords and the second preferred keywords meet a fourth preset condition or not; and when the fourth preset condition is met, obtaining the first common factor according to the first preferred keyword and the second keyword.
Preferably, before recommending the first commodity to the second member and recommending the second commodity to the first member, the method further comprises: obtaining a first price for the first item; obtaining a second price for the second item; obtaining a first price difference value according to the first price and the second price; judging whether the first price difference value meets a first preset threshold value or not; when the first preset threshold is met, obtaining a first purchase frequency of the first member for the first commodity, and obtaining a second purchase frequency of the second member for the second commodity; respectively judging whether the first purchase frequency and the second purchase frequency meet a second preset threshold value; and when the first purchase times and the second purchase times both meet the second preset threshold, recommending the first commodity to the second member, and recommending the second commodity to the first member.
Preferably, the method further comprises: obtaining second historical order information of the second member; obtaining first purchasing preference information of the second member according to the second historical order information; obtaining first promotion information of the first shop according to the first purchasing preference information, wherein the first promotion information comprises the first commodity; and sending the first promotion information to the second member.
In a second aspect, the present invention provides a commodity recommendation apparatus based on user purchasing behavior, the apparatus comprising:
the system comprises a first obtaining unit, a second obtaining unit and a display unit, wherein the first obtaining unit is used for obtaining first shop information, and the first shop information comprises a first commodity;
a second obtaining unit, configured to obtain first store information, where the first store information includes a first commodity;
a third obtaining unit configured to obtain second store information, where the second store information includes a second item;
a fourth obtaining unit configured to obtain second member information for purchasing the second item in the second store, wherein the second member has second address information;
a first judging unit, configured to judge whether the first address information and the second address information satisfy a first preset condition;
the first execution unit is used for enabling the first member and the second member to have a first association relationship when the first preset condition is met;
a fifth obtaining unit for obtaining a first commonality factor of the first article and the second article;
a second judging unit, configured to judge whether the first member and the second member have a first purchasing relationship according to the first association relationship and the first commonality factor;
a first recommending unit configured to recommend the first commodity to the second member and recommend the second commodity to the first member when the first recommending unit has a first purchasing relationship.
Preferably, the apparatus further comprises:
a sixth obtaining unit, configured to obtain a first geographic location according to the first address information;
a seventh obtaining unit, configured to obtain first tag information according to the first geographic location;
an eighth obtaining unit, configured to obtain a second geographic location according to the second address information;
a ninth obtaining unit, configured to obtain second tag information according to the second geographic location;
a third judging unit, configured to judge whether the first tag information and the second tag information satisfy a second preset condition;
and the second execution unit is used for enabling the first member and the second member to have a first association relationship when the second preset condition is met.
Preferably, the apparatus further comprises: a tenth obtaining unit, configured to obtain first historical order information of the first member when the first tag information and the second tag information do not satisfy a second preset condition;
an eleventh obtaining unit, configured to obtain a third commodity according to the first historical order information, where the third commodity and the first commodity are in the same commodity category;
a twelfth obtaining unit, configured to obtain third tag information according to the third item;
a fourth judging unit, configured to judge whether the second tag information and the third tag information satisfy a third preset condition;
a third executing unit, configured to, when the third preset condition is met, enable the first member and the second member to have a first association relationship.
Preferably, the apparatus further comprises: a thirteenth obtaining unit configured to obtain fourth tag information from the first article;
a fourteenth obtaining unit, configured to obtain a first preference keyword according to the fourth tag information;
a fifteenth obtaining unit, configured to obtain fifth tag information according to the second article;
a sixteenth obtaining unit, configured to obtain a second preference keyword according to the fifth tag information;
a fifth judging unit configured to judge whether the first preferred keyword and the second preferred keyword satisfy a fourth preset condition;
a seventeenth obtaining unit, configured to, when the fourth preset condition is met, obtain the first commonality factor according to the first preferred keyword and the second keyword.
Preferably, the apparatus further comprises:
an eighteenth obtaining unit configured to obtain a first price of the first item;
a nineteenth obtaining unit for obtaining a second price of the second item;
a twentieth obtaining unit for obtaining a first price difference value from the first price and the second price;
a sixth judging unit, configured to judge whether the first price difference value satisfies a first preset threshold;
a twenty-first obtaining unit, configured to obtain a first number of times of purchase of the first commodity by the first member and obtain a second number of times of purchase of the second commodity by the second member when the first preset threshold is met;
a seventh judging unit, configured to respectively judge whether the first purchase frequency and the second purchase frequency satisfy a second preset threshold;
and the second recommending unit is used for recommending the first commodity to the second member and recommending the second commodity to the first member when the first purchasing times and the second purchasing times both meet the second preset threshold value.
Preferably, the apparatus further comprises:
a twenty-second obtaining unit configured to obtain second historical order information of the second member;
a twenty-third obtaining unit, configured to obtain first purchase preference information of the second member according to the second historical order information;
a twenty-fourth obtaining unit, configured to obtain first promotional information of the first store according to the first purchase preference information, where the first promotional information includes the first item;
a third recommending unit for sending the first promotional information to the second member.
In a third aspect, the present invention provides a commodity recommendation device based on user purchasing behavior, including a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of any one of the above methods when executing the program.
In a fourth aspect, the invention provides a computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of any of the methods described above.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
according to the commodity recommendation method and device based on the user purchasing behavior, provided by the embodiment of the invention, first shop information is obtained, wherein the first shop information comprises a first commodity; obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information; obtaining second shop information, wherein the second shop information comprises a second commodity; obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information; judging whether the first address information and the second address information meet a first preset condition or not; when the first preset condition is met, the first member and the second member have a first association relationship; obtaining a first commonality factor for the first commodity and the second commodity; judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor; when a first purchasing relation exists, the first commodity is recommended to the second member, and the second commodity is recommended to the first member, so that the technical problems that in the prior art, the quantity of commodities in an e-commerce platform is large, information overload is easily caused, user selection is difficult, the recommended commodities cannot meet the requirements of users, personalized commodity recommendation is difficult to perform for the users, shopping experience of the users is reduced, commodities which accord with the preference of the users are recommended to the users in a more targeted mode, the personalized requirements of the users are better met, an intelligent commodity recommendation mode is favorably built, and the technical effect of the shopping experience of the users is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Fig. 1 is a schematic flowchart of a commodity recommendation method based on user purchasing behavior in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a commodity recommending apparatus based on user purchasing behavior according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of another commodity recommending device based on user purchasing behavior according to an embodiment of the present invention.
Description of reference numerals: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 306.
Detailed Description
The embodiment of the invention provides a commodity recommendation method and device based on user purchasing behavior, and aims to solve the technical problems that in the prior art, the quantity of commodities in an e-commerce platform is large, information overload is easily caused, user selection is difficult, recommended commodities cannot meet the requirements of users, personalized commodity recommendation is difficult for the users, and the shopping experience of the users is reduced.
The technical scheme provided by the invention has the following general idea:
obtaining first shop information, wherein the first shop information comprises a first commodity; obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information; obtaining second shop information, wherein the second shop information comprises a second commodity; obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information; judging whether the first address information and the second address information meet a first preset condition or not; when the first preset condition is met, the first member and the second member have a first association relationship; obtaining a first commonality factor for the first and second merchandise; judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor; and when the first purchasing relationship exists, recommending the first commodity to the second member, and recommending the second commodity to the first member.
The technical solutions of the present invention are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present invention are described in detail in the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
Example one
Fig. 1 is a schematic flowchart of a commodity recommendation method based on user purchasing behavior in an embodiment of the present invention. As shown in fig. 1, an embodiment of the present invention provides a method for recommending a commodity based on a user purchasing behavior, where the method includes:
step 110: first shop information is obtained, wherein the first shop information comprises first commodities.
Specifically, the first store is an online store provided on an e-commerce platform, and the first store is also in the form of e-commerce, so that the user can view a desired product while browsing the stores, and can purchase the product, and finally, the user can perform payment through various online payment means to complete a transaction. For example, the first shop may be an online shop, such as a good shop flagship shop, a blue moon flagship shop, etc., which are provided on an online trading platform such as nao, jingdong, wei hui, suting and so on. Further, the first store information is basic information related to the first store, which includes a set of related information such as a geographic location, a time and a year of opening the store, a type of a sold product, a store consumption location, an after-sales service, a customer rating, a fan attention number, a store competition heat, and the like of the first store, and therefore, a plurality of products are included in the first store, and the first product is one type of the products. For example, when the first store is a blue moon flagship store, the first commodity may be a laundry detergent, a hand sanitizer, or the like, and when the first store is a millet flagship store, the first commodity may be a mobile phone, a tablet computer, or the like.
Step 120: obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information.
Specifically, in the first shop, after the user purchases the first commodity, the first member information for purchasing the first commodity can be obtained accordingly. The first member information is the information such as personal account data registered in the first store, and can become one member of fan groups of the first store after being authorized to be registered as a member of the first store, so that when a user purchases in the store, corresponding point integrating operation can be performed according to consumption amount, member points are accumulated and preferential offers are given to the user to enjoy member treatment, and meanwhile, by utilizing a marketing mode of a membership system, consumer groups with the same interest and consistent orientation can be reasonably classified, so that the shop can research and develop products according to the interest of the member, thereby better serving the user, stimulating the consumption capacity of the user and improving the popularity and the sales volume of the store. The first member information specifically comprises member names, member grades, point data, registration time, consumption times, goods receiving information, mobile phone number identification numbers and other related personal information. Therefore, in the first shop, after the first member purchases the first commodity, the first address information of the first member can be correspondingly obtained according to the first member, wherein the first address information is a delivery address of the first member, and the address information can be a company, a home, a school, and the like. For example, when the first store is a black duck flagship store, and the first commodity is a duck neck, and after a member king purchases a duck neck on the black duck flagship store, the receiving address information of the king can be further obtained, for example, the member king is a city in sichuan province.
Step 130: second store information is obtained, wherein the second store information comprises a second commodity.
Specifically, as described in the foregoing step 110, similarly, the second store is an online store provided on the e-commerce platform, and the second store is also in the form of e-commerce. Therefore, the first store and the second store are two different stores, and the first store and the second store may belong to the same e-commerce platform flag or may belong to different e-commerce platforms. Further, the second store information is basic information related to the second store, which includes a set of related information such as a geographic location, a time and a year of opening the store, a type of a sold commodity, a store consumption location, an after-sales service, a customer rating, a fan attention number, a store competition heat, and the like of the second store, and similarly, a plurality of commodities are included in the second store, and the second commodity is one type of the commodities. For example, when the second store is a flagship store in the united states, the second commodity may be an air conditioner, a refrigerator, an oven, an induction cooker, or the like, and when the second store is an adidas flagship store, the second commodity may be a shoe, a garment, a backpack, or the like.
Step 140: obtaining second member information for purchasing the second commodity in the second store, wherein the second member has second address information.
Specifically, as described in step 120, similarly, in the second store, after the user purchases the second product, the second member information for purchasing the second product can be obtained accordingly. The second member information is related information such as personal account data registered in the second store, and can become one member of the fan group of the second store after being authorized to be registered as a member of the second store. The second member information specifically includes member names, member grades, receiving information, point data, registration time, consumption times, mobile phone number identification numbers and other related personal information. Therefore, in the second shop, after the second member purchases the second commodity, the second address information of the second member can be correspondingly obtained according to the second member, wherein the second address information is the receiving address of the second member, and the address information can be company, home, school, etc. For example, when the second store is a sika flagship store and the second commodity is a panda shoe, and when the member litter purchases a panda shoe on the sika flagship store, the receiving address information of the litter may be further obtained, for example, the receiving address information is a celebration city.
Step 150: and judging whether the first address information and the second address information meet a first preset condition.
Step 160: and when the first preset condition is met, the first member and the second member have a first association relationship.
Specifically, after the first address information of the first member and the second address information of the second member are obtained, it is further possible to determine whether the two addresses satisfy the first preset condition according to the first address information and the second address information. The specific judgment logic is as follows: and obtaining a first distance difference according to the first address information and the second address information, judging whether the first distance difference is in a preset range, and if so, indicating that the first address information and the second address information are in the preset range, and further indicating that the first member and the second member have a first association relationship. The first association relationship is an association degree between the first member and the second member, that is, based on the address information of the first member and the second member being within a predetermined range, the first member and the second member may be determined to have certain common attribute information or have similar attribute information according to the geographic location. Further, based on the first association relationship, it can be determined that the first member and the second member have certain common preference information. For example, when the delivery address of the first member is the city of Sichuan province and the delivery address of the second member is the city of Sichuan province, the second member is the city of Sichuan province and Yangyang, if the preset range is the same province, the address information of the first member and the second member meets a first preset condition, the first member and the second member are indicated to have a first association relationship, and the common preference of the first member and the second member can be determined as liking to eating spicy; for another example, when the receiving address of the second member is Chongqing city, if the predetermined range is 700 km, the address information of the second member and the receiving address satisfy the first preset condition, which indicates that the first member and the second member have the first association relationship, and similarly, the common preference of the first member and the second member can be determined as liking to eat spicy food.
Step 170: a first commonality factor is obtained for the first commodity and the second commodity.
Further, the obtaining a first commonality factor for the first commodity and the second commodity includes: obtaining fourth label information according to the first commodity; obtaining a first preference keyword according to the fourth label information; acquiring fifth label information according to the second commodity; obtaining a second preferred keyword according to the fifth label information; judging whether the first preferred keywords and the second preferred keywords both meet a fourth preset condition; and when the fourth preset condition is met, obtaining the first common factor according to the first preferred keyword and the second keyword.
Specifically, the first commonalities factor is a degree of similarity between the first commodity and the second commodity, that is, an attribute property that the first commodity and the second commodity have in common. The specific acquisition mode is as follows: first, according to the first commodity information, fourth label information of the first commodity is obtained, wherein the fourth label information is related mark information of the first commodity, and a target product can be conveniently searched and positioned. For different categories of commodities, the label information also differs, for example, when the first commodity is clothes, the fourth label information includes one or more of the producing area, price, material and cleaning method of the clothes, and when the first commodity is food, the fourth label information includes one or more of the producing area, producing date, quality guarantee period, taste and eating method. Further, the keyword determined for the first product, that is, the first preference keyword, that is, the feature information representing the first product, may be extracted accordingly according to the fourth tag information. Further, as described above, according to the second commodity information, fifth tag information of the second commodity is obtained, where the fifth tag information is related mark information of the second commodity, so that a target product can be conveniently searched and located, and a keyword determined for the second commodity, that is, a second preference keyword, that is, feature information representing the second commodity, can be correspondingly extracted according to the fifth tag information. Therefore, after the keywords corresponding to the two commodities are obtained, whether the first preferred keyword and the second preferred keyword both meet the fourth preset condition needs to be judged according to the first preferred keyword and the second preferred keyword, namely whether the similarity between the first preferred keyword and the second preferred keyword meets the preset requirement is judged, when the similarity meets the preset requirement, a certain similar characteristic exists between the first commodity and the second commodity, and the first common factor between the first commodity and the second commodity is obtained according to the first preferred keyword and the second preferred keyword. For example, when the first product is turkey noodles, the characteristic information of the first product is spicy, the second product is sliced beef, and the taste attribute purchased by the user is spicy, therefore, the keyword spicy of the turkey noodles and the keyword spicy of the sliced beef have a certain similarity, and the similarity is 90%, and when the preset requirement is 70%, it is stated that the two products of the turkey noodles and the sliced beef have spicy commonality, that is, the commonality factor between the two products is spicy.
Step 180: and judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor.
Step 190: and when the first purchasing relationship exists, recommending the first commodity to the second member, and recommending the second commodity to the first member.
Specifically, after determining that the first member and the second member have the first association relationship, the common preference information between the two members is obtained based on the association relationship, and the first commonality factor between the first commodity and the second commodity is obtained, it may be further determined whether the first member and the second member have the first purchasing relationship, that is, whether the first member and the second member have the common purchasing ability, based on the common preference and the first commonality factor. The specific judgment logic is as follows: and obtaining corresponding favorite keywords according to the common favorite information, obtaining corresponding common keywords according to the common factors, further judging whether the similarity between the favorite keywords and the common keywords meets the threshold requirement, and if so, indicating that the first member and the second member have common purchasing characteristics. Then, the first item is recommended to the second member, and the second item is recommended to the first member. Therefore, the difficulty of finding product information meeting the requirements of a user in massive commodity information quickly and accurately is reduced, potential customers can be mined and developed for shops, the sales volume of E-commerce enterprises can be effectively increased, accurate commodity recommendation is realized, and the system has the advantages of high working efficiency and wide application range. For example, when a commodity purchased by a first member in a herbal store on a panning pot is a spicy baby fish, the delivery address of the first member is Sichuan, a commodity purchased by a second member in a non-defective shop on the panning pot is a spicy strip, and the delivery address of the second member is Chongqing, common hobbies of the first member and the second member can be determined as hobbies of eating spicy food according to the Sichuan and Chongqing places, and a common factor of the purchased baby fish and the spicy strip is spicy, so that the common hobbies of the first member and the second member and the common factors of the baby fish and the spicy strip are spicy, common purchasing characteristics between the first member and the second member are described, mixed recommendation can be performed, that is, the baby fish can be recommended to the second member, and the spicy strip is recommended to the first member.
Therefore, the commodity recommendation method based on the user purchasing behavior in the embodiment can be used for recommending commodities which meet the preference of the user to the user in a more targeted manner, the personalized requirements of the user are better met, the intelligent commodity recommendation mode can be set up conveniently, and the shopping experience of the user is improved, so that the technical problems that in the prior art, the quantity of commodities in an e-commerce platform is large, the user selection is difficult due to information overload, the recommended commodities cannot meet the requirements of the user, the personalized commodity recommendation is difficult for the user, and the shopping experience of the user is reduced are solved.
Further, the commodity recommendation method based on the user purchasing behavior in this embodiment may also be implemented by combining an Artificial Intelligence technology, wherein the english abbreviation of Artificial Intelligence is AI (Artificial Intelligence), which is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human Intelligence. The method comprises the following specific steps: obtaining a first shop information photo and a second shop information photo; the first shop information photo and the second shop information photo are sequentially input into a model, the model is obtained by using multiple groups of data through machine learning training, each group of data in the multiple groups of data comprises a first class data group and a second class data group, and each group of data in the first class data group comprises: a first store information photo, first identification information for identifying a first commodity in the first store information photo, second identification information for identifying first member information for purchasing the first commodity in the first store information photo, and third identification information for identifying first address information of the first member in the first store information photo; each group of data of the second type data group comprises: a second store information photo, fourth identification information identifying a second commodity in the second store information photo, fifth identification information identifying second member information purchasing the second commodity in the second store information photo, and sixth identification information identifying second address information of the second member in the second store information photo; and recommending the first commodity to the second member and recommending the second commodity to the first member when the first member and the second member have a first purchasing relationship. Wherein, the first member and the second member have a first purchasing relationship according to a judgment mode that: judging whether the first address information and the second address information meet a first preset condition or not; when the first preset condition is met, the first member and the second member have a first association relationship; further obtaining a first commonness factor of the first commodity and the second commodity; and judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor.
Further, the method further comprises: acquiring a first geographical position according to the first address information; obtaining first label information according to the first geographic position; obtaining a second geographic position according to the second address information; obtaining second label information according to the second geographic position; judging whether the first label information and the second label information meet a second preset condition or not; and when the second preset condition is met, the first member and the second member have a first association relationship.
Specifically, in this embodiment, the first association relationship between the first member and the second member may be obtained as follows: first, a first geographical location is obtained according to first address information of a first member, where the first geographical location is positioning information of the first address information, that is, a correlation between time and space of the first address information, and then, corresponding first tag information can be obtained according to the first geographical location, where the first tag information is related attribute information of the first geographical location, and the first tag information may include one or more of demographic information, climate information, tourist attraction information, and eating habit information. Further, similarly, a second geographic location may be obtained according to second address information of a second member, where the second geographic location is positioning information of the second address information, that is, a correlation between time and space of the second address information, and then corresponding second tag information may be obtained according to the second geographic location, where the second tag information is related attribute information of the second geographic location, and the second tag information may include one or more of demographic information, climate information, tourist attraction information, and eating habit information, and in this embodiment, the second tag information is used as an optimal preference for eating habits. Further, after the first tag information and the second tag information are obtained, whether the first tag information and the second tag information meet a second preset condition or not can be further judged, and when the second preset condition is met, it is indicated that a first association relationship exists between the first member and the second member. The specific judgment logic is as follows: the first diet preference information can be determined according to the first label information, and the second diet preference information can be determined according to the second label information, so that the association degree between the first diet preference information and the second diet preference information can be obtained according to the first diet preference information and the second diet preference information, and whether the association degree meets the association degree threshold requirement or not is further judged, when the association degree threshold requirement is met, the association degree between the first label information and the second label information meets the preset condition, and further the first association relation between the first member and the second member can be obtained. For example, when the address information of zhangji is guangzhou city, the province to which zhangji belongs is guangdong province, so that the zhangji can be considered to enjoy eating sweet food, and when the address information of zhou person is shenzhen city, the province to which zhou person belongs is also guangdong province, so that the zhou person can be considered to enjoy eating sweet food, so that the zhangji and the zhou person can obtain the same or similar eating taste, which indicates that the two users have the common eating taste information, and the association degree between the two user tastes is 89%, and when the preset association degree is 65%, the two users can be determined to have a certain association relationship, so that accurate commodity recommendation can be performed for the users according to the personal taste of the users, the commodity recommendation efficiency is improved, and the discomfort of the users due to the fact that uninteresting contents are pushed for the users is avoided.
Further, the method further comprises: when the first label information and the second label information do not meet a second preset condition, obtaining first historical order information of the first member; obtaining a third commodity according to the first historical order information, wherein the third commodity and the first commodity are in the same commodity category; obtaining third label information according to the third commodity; judging whether the second label information and the third label information meet a third preset condition or not; and when the third preset condition is met, the first member and the second member have a first association relationship.
Specifically, when the similarity between the first tag information and the second tag information does not satisfy the second preset condition, the first historical order information of the first member may be obtained, where the first historical order information is a historical purchase condition of the user within a preset time, for example, a purchase record of the first member in the past month, a quarter, or a half year, and the specific preset time may be adjusted according to an actual situation, and is not limited in this embodiment. And the first historical order information comprises information such as historical consumption amount, purchase time, receiving time, quantity of purchased commodities and the like of the first member, so that third commodity information can be correspondingly acquired from the first historical order, wherein the third commodity is a product which is second to the first commodity in purchase times. In the present embodiment, it is preferable that the third product is the same as the first product and the second product, and for example, the first product, the second product, and the third product are all food products, or clothing, beauty cosmetics, mother and baby products, and the like. Further, third label information can be obtained correspondingly according to a third commodity, wherein the third label information is related mark information of the third commodity, and a target product can be conveniently searched and positioned. For different commodity categories, the label information also differs, for example, when the third commodity is clothes, the third label information includes one or more of the production place, price, material and cleaning method of the clothes, and when the third commodity is food, the third label information includes one or more of the production place, production date, shelf life, taste and eating method. Then, whether the third label information meets a third preset condition or not can be judged, namely, the third label information and the second label information are compared to obtain the association degree between the third label information and the second label information, whether the association degree between the third label information and the second label information meets a preset requirement or not is judged, and when the preset requirement is met, the first member and the second member are indicated to have a first association relation. And then the adjustment of recommended commodities can be carried out according to the actual purchasing behaviors of the users, so that the purposes of more scientifically and reasonably recommending the commodities and forming personalized commodity recommendation for each user are achieved. For example, when the first tag information of a first member wang and the second tag information of a second member zhang do not satisfy the second preset condition, the historical order record of the first member wang in the past three months is further obtained, and then the third commodity such as a duck neck is obtained from the historical order, the purchase frequency of the duck neck reaches the threshold requirement, and through analysis on the historical order, the taste of the wang is mostly spicy, and at the moment, the spicy can be used as the tag information of the duck neck, so that when the geographical position of the zhang is in Hunan and the corresponding tag is good for eating the spicy food, the association degree between the two tags is 85%, and when the preset association degree is 60%, the similar diet preference between the zhang and zhang is stated, and the association relationship between the two tags can be obtained.
Further, when the first label information and the second label information do not meet a second preset condition, historical order information of the second member can be obtained; obtaining a fourth commodity according to the historical order information of the second member, wherein the fourth commodity and the second commodity are in the same commodity category; acquiring sixth label information according to the fourth commodity; judging whether the sixth label information and the first label information meet a third preset condition or not; and when the third preset condition is met, the first member and the second member have a first association relationship.
Further, before recommending the first commodity to the second member and recommending the second commodity to the first member, the method further comprises: obtaining a first price for the first item; obtaining a second price for the second item; obtaining a first price difference value according to the first price and the second price; judging whether the first price difference value meets a first preset threshold value or not; when the first preset threshold is met, obtaining a first purchase frequency of the first member for the first commodity, and obtaining a second purchase frequency of the second member for the second commodity; respectively judging whether the first purchasing times and the second purchasing times meet a second preset threshold value; and when the first purchase times and the second purchase times both meet the second preset threshold value, recommending the first commodity to the second member, and recommending the second commodity to the first member.
Specifically, in order to more accurately recommend a product to a user, before recommending a first product to a second member and recommending a second product to the first member, processing and analysis must be performed according to a corresponding judgment logic. Specifically, the method comprises the following steps: and obtaining a first price of the first commodity and a second price of the second commodity, wherein the first price and the second price are transaction amounts corresponding to the first commodity and the second commodity respectively. And correspondingly judging the consumption capacities corresponding to the first member and the second member according to the first price and the second price. And then calculating the difference between the first price and the second price according to the first price and the second price, judging whether the difference is within a first preset threshold range, and if so, indicating that the consumption levels of the first member and the second member are equivalent and the member crowd at the same consumption level. Further, a first purchase frequency of the first member for purchasing the first commodity within a first preset time and a second purchase frequency of the second member for purchasing the second commodity within the first preset time are obtained, and then whether the first purchase frequency and the second purchase frequency meet a second preset threshold value is judged. When the first purchase times and the second purchase times of the two users in the same time range both meet a second preset threshold value, the first commodity can be recommended to the second member, and meanwhile, the second commodity is recommended to the first member. The method further achieves the technical effects that recommended commodities are enabled to better meet the requirements of each user, an intelligent commodity recommendation system is favorably built, stable user groups are favorably established for E-commerce websites, the service quality is improved, and the market competitiveness of enterprises is improved. For example, when the first commodity is turkey noodles, the price of the turkey noodles is 10 yuan, the second commodity is duck neck, the price of the duck neck is 20 yuan, the price difference between the two commodities is 10 yuan, and if the preset price difference is set to be 30 yuan, the price difference between the two commodities is in the preset range, which indicates that the consumption levels of the first user and the second user are at the same level. Further, when the number of times that the first user purchases turkey noodles in half a year is 18, the number of times that the second user purchases duck necks in half a year is 15, and when the preset number of times is 10, it indicates that the number of times that the two users purchase both satisfy the threshold requirement, that is, the first commodity and the second commodity both satisfy the pushing requirement, and then the first commodity can be recommended to the second member, and the second commodity is recommended to the first member.
Further, the method further comprises: obtaining second historical order information of the second member; obtaining first purchasing preference information of the second member according to the second historical order information; obtaining first promotion information of the first shop according to the first purchasing preference information, wherein the first promotion information comprises the first commodity; and sending the first promotion information to the second member.
Specifically, as described above, the second historical order information is the historical purchase condition of the user in the second store within the preset time, and therefore, the purchase preference information of the second member can be correspondingly obtained from the second historical order, where the first purchase preference information is a consumption activity form that the second member tends to, for example, the member often purchases articles at a discount or purchases gifted activities, and the member purchases the articles at a fair price less frequently, which indicates that the consumption purchase form that the member likes is a preferential form, so that the first promotion activity information about the first article in the first store can be obtained, and then the first promotion information is sent to the second member, which further meets the requirement of each user for recommended articles, is favorable for building an intelligent article recommendation system, and is favorable for a provider website to build a stable user group and improve the market service quality, thereby improving the technical effect of competitiveness of an enterprise.
Further, in this embodiment, the first member may further obtain first historical order information of the first member; obtaining second purchase preference information of the first member; obtaining second promotion information of the second shop according to the second purchasing preference information, wherein the second promotion information comprises the second commodity; transmitting the second promotional information to the first member.
Example two
Based on the same inventive concept as the commodity recommendation method based on the user purchasing behavior in the foregoing embodiment, the present invention further provides a commodity recommendation method apparatus based on the user purchasing behavior, as shown in fig. 2, the apparatus includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first store information, and the first store information includes a first commodity;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain first store information, where the first store information includes a first commodity;
a third obtaining unit 13, where the third obtaining unit 13 is configured to obtain second store information, and the second store information includes a second item;
a fourth obtaining unit 14, the fourth obtaining unit 14 being configured to obtain second member information for purchasing the second item in the second store, wherein the second member has second address information;
a first judging unit 15, where the first judging unit 15 is configured to judge whether the first address information and the second address information satisfy a first preset condition;
a first executing unit 16, where the first executing unit 16 is configured to, when the first preset condition is met, enable the first member and the second member to have a first association relationship
A fifth obtaining unit 17, the fifth obtaining unit 17 being configured to obtain a first commonality factor for the first article and the second article;
a second determining unit 18, wherein the second determining unit 18 is configured to determine whether the first member and the second member have a first purchasing relationship according to the first association relationship and the first common factor;
a first recommending unit 19, wherein the first recommending unit 19 is configured to recommend the first commodity to the second member and recommend the second commodity to the first member when the first recommending unit 19 has a first purchasing relationship.
Further, the apparatus further comprises: a sixth obtaining unit, configured to obtain a first geographic location according to the first address information;
a seventh obtaining unit, configured to obtain first tag information according to the first geographic location;
an eighth obtaining unit, configured to obtain a second geographic location according to the second address information;
a ninth obtaining unit, configured to obtain second tag information according to the second geographic location;
a third determining unit, configured to determine whether the first tag information and the second tag information satisfy a second preset condition;
and the second execution unit is used for enabling the first member and the second member to have a first association relationship when the second preset condition is met.
Further, the apparatus further comprises: a tenth obtaining unit, configured to obtain first historical order information of the first member when the first tag information and the second tag information do not satisfy a second preset condition;
an eleventh obtaining unit, configured to obtain a third commodity according to the first historical order information, where the third commodity and the first commodity are in the same commodity category;
a twelfth obtaining unit, configured to obtain third tag information according to the third item;
a fourth judging unit, configured to judge whether the second tag information and the third tag information satisfy a third preset condition;
a third executing unit, configured to, when the third preset condition is met, enable the first member and the second member to have a first association relationship.
Further, the apparatus further comprises: a thirteenth obtaining unit configured to obtain fourth tag information from the first article;
a fourteenth obtaining unit, configured to obtain a first preference keyword according to the fourth tag information;
a fifteenth obtaining unit, configured to obtain fifth tag information according to the second article;
a sixteenth obtaining unit, configured to obtain a second preference keyword according to the fifth tag information;
a fifth judging unit configured to judge whether the first preferred keyword and the second preferred keyword satisfy a fourth preset condition;
a seventeenth obtaining unit, configured to, when the fourth preset condition is met, obtain the first commonality factor according to the first preferred keyword and the second keyword.
Further, the apparatus further comprises: an eighteenth obtaining unit configured to obtain a first price of the first item;
a nineteenth obtaining unit for obtaining a second price of the second item;
a twentieth obtaining unit for obtaining a first price difference value from the first price and the second price;
a sixth judging unit, configured to judge whether the first price difference value satisfies a first preset threshold;
a twenty-first obtaining unit, configured to obtain a first number of times of purchase of the first commodity by the first member and obtain a second number of times of purchase of the second commodity by the second member when the first preset threshold is met;
a seventh judging unit, configured to respectively judge whether the first purchase frequency and the second purchase frequency satisfy a second preset threshold;
and the second recommending unit is used for recommending the first commodity to the second member and recommending the second commodity to the first member when the first purchase frequency and the second purchase frequency both meet the second preset threshold value.
Further, the apparatus further comprises: a twenty-second obtaining unit configured to obtain second historical order information of the second member;
a twenty-third obtaining unit, configured to obtain first purchase preference information of the second member according to the second historical order information;
a twenty-fourth obtaining unit, configured to obtain first promotional information of the first store according to the first purchase preference information, where the first promotional information includes the first item;
a third recommending unit, configured to send the first promotional information to the second member.
Various changes and specific examples of the aforementioned commodity recommendation method based on user purchasing behavior in the first embodiment of fig. 1 are also applicable to the commodity recommendation device based on user purchasing behavior in the present embodiment, and through the aforementioned detailed description of the commodity recommendation method based on user purchasing behavior, those skilled in the art can clearly know the implementation method of the commodity recommendation device based on user purchasing behavior in the present embodiment, so for the sake of brevity of the description, detailed descriptions are not repeated here.
EXAMPLE III
Based on the same inventive concept as the commodity recommending method based on the user purchasing behavior in the previous embodiment, the invention further provides a commodity recommending device based on the user purchasing behavior, wherein a computer program is stored on the commodity recommending device, and when the computer program is executed by a processor, the steps of any one of the above commodity recommending method based on the user purchasing behavior are realized.
Wherein in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be one and the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
Example four
Based on the same inventive concept as the method for recommending a commodity based on user purchasing behavior in the foregoing embodiments, the present invention further provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the steps of any of the above-described methods.
In this embodiment, the program may further implement any one of the method steps of the first embodiment when the program is executed by a processor.
One or more technical solutions in the embodiments of the present application at least have one or more of the following technical effects:
according to the commodity recommendation method and device based on the user purchasing behavior, provided by the embodiment of the invention, first shop information is obtained, wherein the first shop information comprises a first commodity; obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information; obtaining second shop information, wherein the second shop information comprises a second commodity; obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information; judging whether the first address information and the second address information meet a first preset condition or not; when the first preset condition is met, the first member and the second member have a first association relationship; obtaining a first commonality factor for the first and second merchandise; judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor; when a first purchasing relation exists, the first commodity is recommended to the second member, and the second commodity is recommended to the first member, so that the technical problems that in the prior art, the quantity of commodities in an e-commerce platform is large, information overload is easily caused, user selection is difficult, the recommended commodities cannot meet the requirements of users, personalized commodity recommendation is difficult to perform for the users, shopping experience of the users is reduced, commodities which accord with the preference of the users are recommended to the users in a more targeted mode, the personalized requirements of the users are better met, an intelligent commodity recommendation mode is favorably built, and the technical effect of the shopping experience of the users is improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (9)

1. A commodity recommendation method based on user purchasing behavior is characterized by comprising the following steps:
the method comprises the steps of obtaining first shop information, wherein the first shop information comprises first commodities;
obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information;
obtaining second shop information, wherein the second shop information comprises a second commodity;
obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information;
judging whether the first address information and the second address information meet a first preset condition or not;
when the first preset condition is met, the first member and the second member have a first association relationship;
obtaining a first commonality factor for the first commodity and the second commodity;
judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor;
and when the first purchasing relationship exists, recommending the first commodity to the second member, and recommending the second commodity to the first member.
2. The method of claim 1, wherein the method further comprises:
acquiring a first geographical position according to the first address information;
obtaining first label information according to the first geographic position;
obtaining a second geographic position according to the second address information;
obtaining second label information according to the second geographic position;
judging whether the first label information and the second label information meet a second preset condition or not;
and when the second preset condition is met, the first member and the second member have a first association relationship.
3. The method of claim 2, wherein the method further comprises:
when the first label information and the second label information do not meet a second preset condition, obtaining first historical order information of the first member;
obtaining a third commodity according to the first historical order information, wherein the third commodity and the first commodity are in the same commodity category;
obtaining third label information according to the third commodity;
judging whether the second label information and the third label information meet a third preset condition or not;
and when the third preset condition is met, the first member and the second member have a first association relationship.
4. The method of claim 1, wherein obtaining a first commonality factor for the first article and the second article comprises:
obtaining fourth label information according to the first commodity;
obtaining a first preference keyword according to the fourth label information;
acquiring fifth label information according to the second commodity;
obtaining a second preferred keyword according to the fifth label information;
judging whether the first preferred keywords and the second preferred keywords meet a fourth preset condition or not;
and when the fourth preset condition is met, obtaining the first common factor according to the first preference keyword and the second preference keyword.
5. The method of claim 1, wherein prior to recommending the first item to the second member and recommending the second item to the first member, the method further comprises:
obtaining a first price for the first item;
obtaining a second price for the second item;
obtaining a first price difference value according to the first price and the second price;
judging whether the first price difference value meets a first preset threshold value or not;
when the first preset threshold is met, obtaining a first purchase frequency of the first member for the first commodity, and obtaining a second purchase frequency of the second member for the second commodity;
respectively judging whether the first purchasing times and the second purchasing times meet a second preset threshold value;
and when the first purchase times and the second purchase times both meet the second preset threshold value, recommending the first commodity to the second member, and recommending the second commodity to the first member.
6. The method of claim 1, wherein the method further comprises:
obtaining second historical order information of the second member;
obtaining first purchasing preference information of the second member according to the second historical order information;
obtaining first promotion information of the first shop according to the first purchasing preference information, wherein the first promotion information comprises the first commodity;
and sending the first promotion information to the second member.
7. An apparatus for recommending a commodity based on a purchase behavior of a user, the apparatus comprising:
the system comprises a first obtaining unit, a second obtaining unit and a display unit, wherein the first obtaining unit is used for obtaining first shop information, and the first shop information comprises a first commodity;
a second obtaining unit, configured to obtain first store information, where the first store information includes a first item;
a third obtaining unit, configured to obtain second store information, where the second store information includes a second item;
a fourth obtaining unit configured to obtain second member information for purchasing the second commodity in the second store, wherein the second member has second address information;
a first judging unit, configured to judge whether the first address information and the second address information satisfy a first preset condition;
a first execution unit, configured to, when the first preset condition is met, enable the first member and the second member to have a first association relationship
A fifth obtaining unit configured to obtain a first commonality factor of the first commodity and the second commodity;
a second determining unit, configured to determine whether the first member and the second member have a first purchasing relationship according to the first association relationship and the first common factor;
a first recommending unit configured to recommend the first commodity to the second member and recommend the second commodity to the first member when the first recommending unit has a first purchasing relationship.
8. A merchandise recommendation device based on user purchasing behavior, comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor when executing the program implements the steps of:
the method comprises the steps of obtaining first shop information, wherein the first shop information comprises first commodities;
obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information;
obtaining second shop information, wherein the second shop information comprises a second commodity;
obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information;
judging whether the first address information and the second address information meet a first preset condition or not;
when the first preset condition is met, the first member and the second member have a first association relationship;
obtaining a first commonality factor for the first and second merchandise;
judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor;
and when the first purchasing relationship exists, recommending the first commodity to the second member, and recommending the second commodity to the first member.
9. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, performing the steps of:
the method comprises the steps of obtaining first shop information, wherein the first shop information comprises first commodities;
obtaining first member information for purchasing the first commodity in the first shop, wherein the first member has first address information;
obtaining second shop information, wherein the second shop information comprises a second commodity;
obtaining second member information for purchasing the second commodity in the second shop, wherein the second member has second address information;
judging whether the first address information and the second address information meet a first preset condition or not;
when the first preset condition is met, the first member and the second member have a first association relationship;
obtaining a first commonality factor for the first and second merchandise;
judging whether the first member and the second member have a first purchasing relationship or not according to the first association relationship and the first common factor;
and when the first purchasing relationship exists, recommending the first commodity to the second member, and recommending the second commodity to the first member.
CN201911215731.7A 2019-12-02 2019-12-02 Commodity recommendation method and device based on user purchasing behavior Active CN110969512B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911215731.7A CN110969512B (en) 2019-12-02 2019-12-02 Commodity recommendation method and device based on user purchasing behavior

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911215731.7A CN110969512B (en) 2019-12-02 2019-12-02 Commodity recommendation method and device based on user purchasing behavior

Publications (2)

Publication Number Publication Date
CN110969512A CN110969512A (en) 2020-04-07
CN110969512B true CN110969512B (en) 2022-11-15

Family

ID=70032822

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911215731.7A Active CN110969512B (en) 2019-12-02 2019-12-02 Commodity recommendation method and device based on user purchasing behavior

Country Status (1)

Country Link
CN (1) CN110969512B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210390436A1 (en) * 2020-06-11 2021-12-16 Sap Se Determining Categories For Data Objects Based On Machine Learning
CN112085561A (en) * 2020-08-25 2020-12-15 王娟 Cloud platform e-commerce data processing method and system based on big data
CN113129053B (en) * 2021-03-29 2024-05-21 北京沃东天骏信息技术有限公司 Information recommendation model training method, information recommendation method and storage medium
JP7130093B1 (en) * 2021-05-31 2022-09-02 楽天グループ株式会社 Information processing system, method and program
CN114117235A (en) * 2021-12-07 2022-03-01 绥化市纯互联网商务有限公司 E-commerce content pushing method adopting artificial intelligence analysis and E-commerce big data system
CN114936911B (en) * 2022-07-26 2022-11-08 成都纳宝科技有限公司 Intelligent marketing popularization system
CN117391820A (en) * 2023-12-01 2024-01-12 深圳市思迅网络科技有限公司 SaaS service comprehensive management method and system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106296329A (en) * 2015-06-09 2017-01-04 阿里巴巴集团控股有限公司 Business object information processing, credential information processing method and processing device
CN106991598A (en) * 2017-04-07 2017-07-28 北京百分点信息科技有限公司 Data push method and its system
CN109214893A (en) * 2018-08-31 2019-01-15 深圳春沐源控股有限公司 Method of Commodity Recommendation, recommender system and computer installation
CN109711936A (en) * 2018-12-25 2019-05-03 福建破缸茶业发展有限公司 A kind of Tea Industry platform trading algorithms and device
CN109816441A (en) * 2018-12-29 2019-05-28 江苏云天励飞技术有限公司 Tactful method for pushing, system and relevant apparatus
CN110503466A (en) * 2019-08-15 2019-11-26 深圳市云积分科技有限公司 A kind of consumer demographics' acquisition methods and device based on interactive event

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106296329A (en) * 2015-06-09 2017-01-04 阿里巴巴集团控股有限公司 Business object information processing, credential information processing method and processing device
CN106991598A (en) * 2017-04-07 2017-07-28 北京百分点信息科技有限公司 Data push method and its system
CN109214893A (en) * 2018-08-31 2019-01-15 深圳春沐源控股有限公司 Method of Commodity Recommendation, recommender system and computer installation
CN109711936A (en) * 2018-12-25 2019-05-03 福建破缸茶业发展有限公司 A kind of Tea Industry platform trading algorithms and device
CN109816441A (en) * 2018-12-29 2019-05-28 江苏云天励飞技术有限公司 Tactful method for pushing, system and relevant apparatus
CN110503466A (en) * 2019-08-15 2019-11-26 深圳市云积分科技有限公司 A kind of consumer demographics' acquisition methods and device based on interactive event

Also Published As

Publication number Publication date
CN110969512A (en) 2020-04-07

Similar Documents

Publication Publication Date Title
CN110969512B (en) Commodity recommendation method and device based on user purchasing behavior
CN112837118B (en) Commodity recommendation method and device for enterprise users
KR20200108058A (en) Recommended device and method
CN107507037B (en) Server, gift pushing method of gift box and storage medium
CN110348868A (en) Information on services acquisition methods and device
CN110910179B (en) Grouping marketing method and device
JP6780992B2 (en) Judgment device, judgment method and judgment program
CN110807669B (en) Cross-platform user information management method and device
Sathiyaraj et al. Consumer perception towards online grocery stores, Chennai
CN104615721A (en) Method and system for recommending communities based on returned goods related information
CN111127133A (en) Position-based peripheral physical store commodity display and selling method and system
CN110751537A (en) Online and offline intelligent marketing method and device
CN110933472A (en) Method and device for realizing video recommendation
Maulana et al. The influence of viral marketing and price discounts through social media Instagram to purchase decision on marketplace Shopee
CN110807691B (en) Cross-commodity-class commodity recommendation method and device
KR20170091402A (en) System for searching fashion item
CN111815351A (en) Cooperative filtering and association rule-based clothing recommendation method
JP7140588B2 (en) Decision device, decision method and decision program
JP6543576B2 (en) System and method for providing customized search results based on a user's shopping history, a retailer's identity and items promoted by the retailer
CN108399550B (en) User grouping method
US20150006285A1 (en) Method and system for providing information regarding items in a retail store and computer programs thereof
CN110781399A (en) Cross-platform information pushing method and device
CN111178974B (en) Method and device for improving multi-platform fusion
CN110738521B (en) Client selling method and device for multi-merchant brand
US20210150613A1 (en) Information processing device, information processing method, and information 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