CN111415219A - Commodity recommendation method and device based on family and community shopping big data - Google Patents

Commodity recommendation method and device based on family and community shopping big data Download PDF

Info

Publication number
CN111415219A
CN111415219A CN202010134629.0A CN202010134629A CN111415219A CN 111415219 A CN111415219 A CN 111415219A CN 202010134629 A CN202010134629 A CN 202010134629A CN 111415219 A CN111415219 A CN 111415219A
Authority
CN
China
Prior art keywords
user
commodity list
recommended
list
recommended commodity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010134629.0A
Other languages
Chinese (zh)
Other versions
CN111415219B (en
Inventor
张磊
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.)
Qingdao Juhaolian Technology Co ltd
Original Assignee
Qingdao Juhaolian 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 Qingdao Juhaolian Technology Co ltd filed Critical Qingdao Juhaolian Technology Co ltd
Priority to CN202010134629.0A priority Critical patent/CN111415219B/en
Publication of CN111415219A publication Critical patent/CN111415219A/en
Application granted granted Critical
Publication of CN111415219B publication Critical patent/CN111415219B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • 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
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Accounting & Taxation (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Finance (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a commodity recommendation method and device based on family and community shopping big data, which comprises the following steps: the method comprises the steps of obtaining label information of a user in an intelligent community, determining a user recommended commodity list, a family recommended commodity list, a community recommended commodity list and recommendation coefficients in the user recommended commodity list, determining a feature vector of each category in each recommended commodity list, determining similarity between the user recommended commodity list and the same category in the family recommended commodity list and similarity between the user recommended commodity list and the same category in the community recommended commodity list, determining influence coefficients of the user for purchasing one category of commodities, generating a modified user recommended commodity list, and pushing the modified user recommended commodity list to the user. The commodity recommendation method for the user based on the relationship between the family and the smart community and the user is achieved, so that commodity recommendation for the user is more intelligent and accurate, and user experience is improved.

Description

Commodity recommendation method and device based on family and community shopping big data
Technical Field
The invention relates to the field of big data, in particular to a commodity recommendation method and device based on family and community shopping big data.
Background
With the development of electronic commerce, each large electronic commerce is pretty to perform large data portrait and commodity recommendation on users, however, in the traditional electronic commerce commodity recommendation system, besides performing user portrait and recommendation on the basis of information such as personal browsing and purchase records, group division, portrait and commodity recommendation on the basis of geographical location information, receiving address information and the like of the users are commonly used, however, the thorn method has large errors, and meanwhile, because the relationship and the familiarity of customers are unknown, the relationship is not clear enough, and more intelligentization, smaller granularity and more accurate commodity recommendation service cannot be performed.
Some users in familiar groups have homogenization requirements on similar products, but the commodity requirements of family relation users often have correlation and complementarity requirements, and currently, in the industry, user portrayal is performed by purchasing and browsing commodity big data by individuals and related commodity recommendation is performed, and correlation recommendation can not be performed based on the relation between individuals. For commodity recommendation based on relationships among consumer figures, fuzzy analysis and recommendation are mostly performed by analyzing geographic position information of consumers and shopping receiving address information, and the relationship among the consumer figures cannot be clarified due to the fact that part of consumers often use working places as receiving addresses and big data recommendation performed according to the receiving address information, so that the recommendation method is not accurate and the using effect is not ideal.
Disclosure of Invention
The embodiment of the invention provides a commodity recommendation method and device based on family and community shopping big data, which are used for realizing a commodity recommendation method for users based on the relation between families and intelligent communities and the users, so that commodity recommendation for the users is more intelligent and accurate, and user experience is improved.
In a first aspect, an embodiment of the present invention provides a method for recommending a commodity based on family and community shopping big data, including:
the method comprises the steps of obtaining label information of a user in an intelligent community, wherein the label information of the user comprises a user label, a family label and a community label of the user;
respectively determining a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user according to the user label, the family label and the community label; each recommended commodity list comprises a recommendation coefficient of each commodity;
clustering the first N commodities in each recommended commodity list, and determining a feature vector of each category in each recommended commodity list; n is a positive integer;
according to the feature vector of each category in each recommended commodity list, determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list;
determining the influence coefficient of each type of commodity purchased by the user according to the similarity of the same type in the user recommended commodity list and the family recommended commodity list and the similarity of the same type in the user recommended commodity list and the community recommended commodity list;
and according to the influence coefficient of each type of commodity purchased by the user, correcting the recommendation coefficient of each commodity in the user recommended commodity list, and pushing the corrected user recommended commodity list to the user.
According to the technical scheme, label information of a user is obtained in an intelligent community based on information and intelligent management and service, wherein the label information of the user comprises a user label, a family label and a community label of the user, a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user are determined according to the obtained user label, the obtained family label and the obtained community label, each recommended commodity list comprises a recommendation coefficient of each commodity, the position of each commodity in the recommended commodity list is determined according to the recommendation coefficient of the commodity, clustering calculation is carried out on the first N commodities in each recommended commodity list, a feature vector of each category in each recommended commodity list is determined, N is a positive integer, and the similarity of the same category in the user recommended commodity list and the family recommended commodity list and the similarity of the user recommended commodity list and the community list are determined according to the feature vector of each category in each recommended commodity The method comprises the steps of determining similarity of the same category in a district recommended commodity list, determining influence coefficients of the category of commodities purchased by a user according to the similarity of the same category in a user recommended commodity list and a family recommended commodity list and the similarity of the same category in a user recommended commodity list and a community recommended commodity list, wherein the influence coefficients refer to influence coefficients of the category of commodities purchased desire or probability of purchase of the user under the influence of the family and community purchased commodities, correcting recommendation coefficients of various commodities in the user recommended commodity list according to the determined influence coefficients of the category of commodities purchased by the user, arranging the commodities in the user recommended commodity list in a descending mode according to the recommendation coefficients, generating a corrected user recommended commodity list, and pushing the corrected user recommended commodity list to the user. The commodity recommendation method for the user based on the relationship between the family and the smart community and the user is achieved, so that commodity recommendation for the user is more intelligent and accurate, and user experience is improved.
Optionally, determining an influence coefficient of the commodity purchased by the user according to the following formula (1);
Figure BDA0002396883440000031
wherein, the SIMiInfluence coefficients of purchasing i-type commodities for users; a is a first preset influence weight value of the family recommended goods list on the user recommended goods list,
Figure BDA0002396883440000032
similarity between the recommended commodity list of the user and the ith category in the family recommended commodity list;
Figure BDA0002396883440000033
recommending feature vectors of the ith category in the first N commodities in the commodity list for the user;
Figure BDA0002396883440000034
recommending feature vectors of the ith category in the first N commodities in the commodity list for the family; b is a second preset influence weighted value of the community recommended commodity list on the user recommended commodity list;
Figure BDA0002396883440000035
similarity between the recommended commodity list for the user and the ith category in the community recommended commodity list;
Figure BDA0002396883440000036
recommending feature vectors of the ith category in the first N commodities in the commodity list for the community; i is a positive integer.
Optionally, determining and correcting a recommendation coefficient of each commodity in the user recommended commodity list according to the following formula (2);
Figure BDA0002396883440000037
wherein, P'xRecommending the revised recommendation coefficient of the xth commodity in the commodity list for the user; pxRecommending a recommendation coefficient before modification for the xth commodity in the commodity list for the user; x is a positive integer; SIM (subscriber identity Module)iAn influence coefficient for purchasing the i-type commodity for the user; i is a positive integer; n is the number of the categories to which the x-th goods in the user recommended goods list belong.
Optionally, the pushing the modified user recommended commodity list to the user includes:
according to the corrected recommendation coefficients of the commodities in the user recommended commodity list, arranging the commodities in the user recommended commodity list in a descending mode of the recommendation coefficients, generating a corrected user recommended commodity list, and sending the corrected user recommended commodity list to the terminal equipment of the user, so that the terminal equipment of the user displays the corrected user recommended commodity list to the user.
Optionally, the method further includes:
respectively obtaining front M commodities in a family recommended commodity list and a community recommended commodity list, wherein M is a positive integer;
carrying out commodity category duplication removal on the front M commodities in the family recommended commodity list and the community recommended commodity list according to the front K commodities in the corrected user recommended commodity list, wherein K is the product of n and M;
inserting the commodity after the duplication removal into the position, which is ahead of the commodity sequence, in the corrected user recommended commodity list;
inserting L commodities in the mall which are not in the modified user recommended commodity list into the middle position of a commodity sequence in the modified user recommended commodity list, wherein L is a positive integer;
combining the de-duplicated commodities with L commodities in a shopping mall to generate a new user recommended commodity list;
and pushing the new user recommended commodity list to the user.
In the technical scheme, after a modified user recommended commodity list is obtained, the front M commodities in the family recommended commodity list and the community recommended commodity list are respectively obtained, wherein M is a positive integer, commodity category duplication elimination is carried out on the front M commodities in the family recommended commodity list and the community recommended commodity list according to the front K commodities in the modified user recommended commodity list, K is the product of N and M, N is the number of categories of the front N commodities in the user recommended commodity list, then the commodities after duplication elimination are inserted into the positions, close to the front, of the commodity sequences in the modified user recommended commodity list, L commodities, which are not in the modified user recommended commodity list, are inserted into the positions, in the middle, of the commodity sequences in the modified user recommended commodity list, L is a positive integer, so that the modified user recommended commodity list can be added with the commodities, which are not in the modified user recommended commodity list, a new user commodity list is generated, the community commodity list is sent to a user, and user experience is improved based on the family and the user experience.
In a second aspect, an embodiment of the present invention provides an apparatus for recommending a commodity based on family and community shopping big data, including:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring the label information of a user in an intelligent community, and the label information of the user comprises a user label, a family label and a community label of the user;
the processing module is used for respectively determining a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user according to the user label, the family label and the community label; each recommended commodity list comprises a recommendation coefficient of each commodity; clustering the first N commodities in each recommended commodity list, and determining a feature vector of each category in each recommended commodity list; n is a positive integer; according to the feature vector of each category in each recommended commodity list, determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list; determining an influence coefficient of a user for purchasing a class of commodities according to the similarity of the same class in the user recommended commodity list and the family recommended commodity list and the similarity of the same class in the user recommended commodity list and the community recommended commodity list; and according to the influence coefficient of the user for purchasing one type of commodities, correcting the recommendation coefficient of each commodity in the user recommended commodity list, and pushing the corrected user recommended commodity list to the user.
Optionally, the processing module is specifically configured to:
determining an influence coefficient of a user for purchasing a type of commodities according to the following formula (1);
Figure BDA0002396883440000051
wherein, the SIMiInfluence coefficients of purchasing i-type commodities for users; a is a first preset influence weight value of the family recommended goods list on the user recommended goods list,
Figure BDA0002396883440000052
similarity between the recommended commodity list of the user and the ith category in the family recommended commodity list;
Figure BDA0002396883440000053
recommending feature vectors of the ith category in the first N commodities in the commodity list for the user;
Figure BDA0002396883440000061
recommending feature vectors of the ith category in the first N commodities in the commodity list for the family; b is a second preset influence weighted value of the community recommended commodity list on the user recommended commodity list;
Figure BDA0002396883440000062
similarity between the recommended commodity list for the user and the ith category in the community recommended commodity list;
Figure 1
recommending feature vectors of the ith category in the first N commodities in the commodity list for the community; i is a positive integer.
Optionally, the processing module is specifically configured to:
determining and correcting a recommendation coefficient of each commodity in the user recommended commodity list according to the following formula (2);
Figure BDA0002396883440000064
wherein, P'xRecommending the revised recommendation coefficient of the xth commodity in the commodity list for the user; pxRecommending a recommendation coefficient before modification for the xth commodity in the commodity list for the user; x is a positive integer; SIM (subscriber identity Module)iAn influence coefficient for purchasing the i-type commodity for the user; and i is a positive integer n and is the number of categories to which the x-th commodity in the user recommended commodity list belongs.
Optionally, the processing module is specifically configured to:
according to the corrected recommendation coefficients of the commodities in the user recommended commodity list, arranging the commodities in the user recommended commodity list in a descending mode of the recommendation coefficients, generating a corrected user recommended commodity list, and sending the corrected user recommended commodity list to the terminal equipment of the user, so that the terminal equipment of the user displays the corrected user recommended commodity list to the user.
Optionally, the processing module is further configured to:
the control acquisition module respectively acquires front M commodities in a family recommended commodity list and a community recommended commodity list, wherein M is a positive integer;
the method comprises the steps of conducting commodity category duplication elimination on front M commodities in a family recommended commodity list and a community recommended commodity list according to front K commodities in a user recommended commodity list after correction, wherein K is the product of n and M, inserting commodities after duplication elimination to the position, close to the front, of a commodity sequence in the user recommended commodity list after correction, inserting L commodities in a mall, which are not in the user recommended commodity list after correction, to the position, in the middle of the commodity sequence in the user recommended commodity list after correction, wherein L is a positive integer, combining the commodities after duplication elimination and L commodities in the mall to generate a new user recommended commodity list, and pushing the new user recommended commodity list to a user.
In a third aspect, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the commodity recommendation method based on the family and community shopping big data according to the obtained program.
In a fourth aspect, the present invention further provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the above method for recommending goods based on family and community shopping big data.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a system architecture diagram according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for recommending commodities based on big data of home and community shopping according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for recommending commodities based on big data of home and community shopping according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus for recommending commodities based on big data of home and community shopping according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 schematically shows a system architecture to which the embodiment of the present invention is applicable, and the system architecture includes a label system unit 110, an algorithm unit 120, and a list creation unit 130.
The tag hierarchy unit 110 includes user tag or portrait information, home tag or portrait information, community tag or portrait information, content tag information, and merchandise tag information. The label system unit 110 is a label system formed by association between the attribute type of the object (product, user, etc.) and the object itself, such as coconut label system, fruit type, tropical fruit type, price at the middle level, etc. The user tag or the portrait information refers to existing data of a user (for example, information data of a user who purchases or browses a commodity fixedly and network or real world behavior data), the family tag or the portrait information refers to existing data of a family (for example, information data of a member in the family who purchases or browses a commodity fixedly and network or real world behavior data), the community tag or the portrait information refers to existing data of a family (for example, information data of a member in the community who purchases or browses a commodity fixedly and network or real world behavior data), the content tag information refers to personal information of the user, the identity of the user at home and the identity of the user in the community, and the commodity tag information refers to commodity category information (for example, categories such as fruits, kitchen ware, and the like).
The algorithm unit 120 includes an acquaintance algorithm (such as cosine similarity, pearson similarity, improved cosine similarity, etc.) and an influence coefficient algorithm, and is configured to calculate similarity between the user recommended product list and the same category in the family recommended product list and similarity between the user recommended product list and the same category in the community recommended product list, and further calculate an influence coefficient for a user to purchase a category of products.
The list creating unit 130 is configured to modify the recommendation coefficient of each product in the user recommended product list according to the calculated influence coefficient of the user purchasing a type of product, and push the modified user recommended product list to the user. For example, if a user frequently views information of steak-type food, the user gives a label or portrait information such as a favorite meat, steak, or cooking man, and after calculating a product or commodity related to the label or portrait information of the user, the user is recommended a steak-type commodity, a steak cooking skill article, a video, a frying pan for cooking steak, other meat-type commodities, or other contents. The information of the label or the portrait, such as the user identity information, the commodity information and the like, which can be further subdivided, comprises information such as the address of the user, the ethnicity of the user, the origin of beef related commodities, the type of beef, the consumption level of the user, the warehousing and logistics conditions of the beef related commodities and the like.
It should be noted that the structure shown in fig. 1 is only an example, and the embodiment of the present invention is not limited thereto.
Based on the above description, fig. 2 exemplarily shows a flow of a method for recommending goods based on family and community shopping big data according to an embodiment of the present invention, which can be performed by an apparatus for recommending goods based on family and community shopping big data.
As shown in fig. 2, the process specifically includes:
step 201, obtaining the label information of the users in the smart community.
In the embodiment of the invention, the label information of the user comprises a user label, a family label and a community label of the user, and in an intelligent community based on informatization, intelligent management and service, the relation of the user in the community and the identity data of the user in the family are obtained, and the data used by all the users for purchasing or browsing the commodities can also be obtained. For example, a user often browses information on steak-like food, the user will be given tag information for favorite meat, steak, cook-up, etc.
Step 202, respectively determining a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user according to the user label, the family label and the community label; and each recommended commodity list comprises the recommendation coefficient of each commodity.
According to the embodiment of the invention, calculation is carried out according to the history of purchasing commodities by users in big data and the data of browsing commodities, the user labels, the family labels and the community labels of the users are respectively calculated, then the user recommended commodity list, the family recommended commodity list and the community recommended commodity list of the users are respectively generated according to the user labels, the family labels and the community labels of the users, each recommended commodity list comprises the recommendation coefficient of each commodity, for example, the user recommended commodity list, the family recommended commodity list and the community recommended commodity list of the users are respectively P, F and C, and each recommended commodity list comprises the recommendation coefficient of each commodity Px、FxAnd CxWhere x is the xth commodity in each recommended commodity list, it should be noted that, the larger the recommendation coefficient is, the higher the possibility of the purchase behavior of the user is, the corresponding category commodity needs to be placed at the position in the recommended commodity list that is arranged at the front.
Step 203, clustering the first N commodities in each recommended commodity list, and determining a feature vector of each category in each recommended commodity list; n is a positive integer.
According to the embodiment of the invention, the first N commodities in each recommended commodity list are respectively subjected to clustering calculation, and each recommended commodity list is calculatedFeature vectors for each category in the table, where N is a positive integer. If the first N commodities in the user recommended commodity list P, the family recommended commodity list F and the community recommended commodity list C of the user are respectively calculated, the feature vector of each corresponding category in the user recommended commodity list P, the family recommended commodity list F and the community recommended commodity list C of the user is calculated
Figure BDA0002396883440000101
And
Figure BDA0002396883440000102
such as:
Figure BDA0002396883440000103
and recommending the feature vector of the 2 nd category (such as the household appliance category) in the first N commodities in the commodity list for the user.
It should be noted that in the calculation process, the single commodities may be repeatedly clustered into different categories, for example, a notebook computer belongs to both a household appliance category and a stationery book category.
And 204, determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list according to the feature vector of each category in each recommended commodity list.
According to the feature vector of each corresponding category in the user recommended commodity list, the feature vector of each corresponding category in the family recommended commodity list and the feature vector of each corresponding category in the community recommended commodity list, the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list are calculated, for example: calculating the characteristic vector of the corresponding ith category in the recommended commodity list of the user
Figure BDA0002396883440000104
Corresponding to the family recommended goods listFeature vectors of i classes
Figure BDA0002396883440000105
The similarity between them is
Figure BDA0002396883440000106
Calculating the characteristic vector of the corresponding ith category in the recommended commodity list of the user
Figure BDA0002396883440000107
Characteristic vector of ith category corresponding to community recommended commodity list
Figure BDA0002396883440000108
The degree of mutual understanding between them is
Figure BDA0002396883440000109
Step 205, determining an influence coefficient of a user purchasing a type of goods according to the similarity between the user recommended goods list and the same type in the family recommended goods list and the similarity between the user recommended goods list and the same type in the community recommended goods list.
According to the embodiment of the invention, the influence coefficient of purchasing a type of commodities by a user is determined according to the following formula (1);
Figure BDA0002396883440000111
wherein, the SIMiInfluence coefficients of purchasing i-type commodities for users; a is a first preset influence weight value of the family recommended goods list on the user recommended goods list,
Figure BDA0002396883440000112
similarity between the recommended commodity list for the user and the ith category in the family recommended commodity list;
Figure BDA0002396883440000113
recommending ith category in first N commodities in commodity list for userThe feature vector of (2);
Figure BDA0002396883440000114
recommending feature vectors of the ith category in the first N commodities in the commodity list for the family; b is a second preset influence weighted value of the community recommended commodity list on the user recommended commodity list;
Figure BDA0002396883440000115
similarity between the recommended commodity list for the user and the ith category in the community recommended commodity list;
Figure BDA0002396883440000116
recommending feature vectors of ith categories in the first N commodities in a commodity list for the community; i is a positive integer.
The influence coefficient of the user purchasing a category of goods is an influence coefficient of a purchasing desire or a purchasing probability of the category i goods under the influence of the family members and the community members. For example, if 30% of the members of the intelligent community in which the user is located have data of buying or browsing beef steaks within a period of time, the influence coefficient of the beef class commodities possibly bought by the user is determined according to a formula.
And step 206, according to the influence coefficient of the user to purchase one type of goods, correcting the recommendation coefficient of each goods in the user recommended goods list, and pushing the corrected user recommended goods list to the user.
According to the embodiment of the invention, the recommendation coefficient of each commodity in the corrected user recommended commodity list is determined according to the following formula (2);
Figure BDA0002396883440000117
wherein, P'xRecommending the revised recommendation coefficient of the xth commodity in the commodity list for the user; pxRecommending a recommendation coefficient before modification of the xth commodity in the commodity list for the user; x is a positive integer; SIM (subscriber identity Module)iInfluence coefficients of purchasing i-type commodities for users; i is a positive integer; n is the user recommended goods listNumber of categories to which the xth item belongs. For example, if a notebook computer belongs to both the household appliance category and the stationery book category, n is 2.
According to the recommendation coefficients of all commodities in the corrected user recommended commodity list, the commodities in the user recommended commodity list are arranged according to a mode from large to small, a corrected user recommended commodity list is generated and sent to the terminal equipment of the user, so that the terminal equipment of the user displays the corrected user recommended commodity list to the user, wherein the terminal equipment comprises a PC terminal of the user and a mobile terminal of the user, the PC terminal of the user generally refers to a computer terminal (such as a personal computer), an application client (such as a PC terminal of the Jingdong City), for example, the PC terminal of the Jingdong City is installed on the PC terminal of the user, the mobile terminal of the user generally refers to a mobile communication terminal (such as a personal mobile phone), software APPs (such as Taobao and Taobao APPs) can be installed, and for example, the Taobao APP is installed on the mobile terminal of the user.
For example, the modified user recommended commodity list is sent to a kyoto mall PC end in the PC terminal of the user for display or sent to a kyoto mall in a browser in the PC terminal of the user for display, and the modified user recommended commodity list is sent to a panning APP in the mobile terminal of the user for display.
The following are examples of embodiments of the present invention.
Example one
The user A has the science popularization article related to the browsing dehumidifier and retrieves the data related to the dehumidifier product, label information and related weight values of the dehumidifier, the electric appliance and the like are given to the user according to the information of browsing content, duration and the like, wherein the weight values are larger according to the longer browsing time and the larger the weight value according to the larger the clicking times, the user B has the related data for browsing the humidifier product, the users A and B are users in the same smart community, and more than 30% of families in the smart community purchase the dehumidifier, in the process of calculating the user recommended commodity list, the user recommended commodity list of the user A must contain the dehumidifier product, the user recommended commodity list of the user B must contain the humidifier, but the user recommended commodity list of the user B must contain the dehumidifier product, when the user recommended commodity list of the user A is operated as above, since many families in the smart community where the user A is located purchase dehumidifiers, the order of dehumidifier products in the user recommended commodity list of the user A is increased, and since the user B browses humidifiers, that is, the characteristic vector of the category of the humidifiers in the user recommended commodity list of the user B is opposite to the characteristic vector of the category of the dehumidifiers in the user recommended commodity list of the user B, but the humidifiers and the dehumidifiers both have household appliance label information, the dehumidifier commodities or the dehumidifier commodities cannot be ranked backwards in the user recommended commodity list of the user B, and if the user B clicks or browses the dehumidifiers, the position of the dehumidifier in the user recommended commodity list modified by the user B is increased according to the calculation.
Example two
And the user C and the user D are in a couple relationship, the user C browses or clicks the milk powder, the user D browses or clicks the baby diaper, wherein the milk powder and the baby diaper belong to the same label information of baby products, and the ranking of the baby category commodities in the modified user recommended commodity list of the user C and the user D in the modified user recommended commodity list is increased according to the calculation.
After the modified user recommended commodity list is obtained, the front M commodities in the family recommended commodity list and the community recommended commodity list are respectively obtained, wherein M is a positive integer, commodity category deduplication is performed on the front M commodities in the family recommended commodity list and the community recommended commodity list according to the front K commodities in the modified user recommended commodity list, wherein K is a product of N and M, and N is the number of categories of the front N commodities in the user recommended commodity list, then the commodities after deduplication are inserted into positions, which are near the front of the commodity sequence, in the modified user recommended commodity list, L commodities, which are not in the modified user recommended commodity list, are inserted into positions, which are near the middle of the commodity sequence, in the modified user recommended commodity list, wherein L is a positive integer, so that the modified user recommended commodity list can be added with newly recommended commodities, which are not in the modified user recommended commodity list, the new user recommended commodities list is generated, and is given to a user, for example, in the community user recommended commodity list, the user B, which is browsed by the user B, and the user who has never purchased the home recommended commodity list, and most of the user who has the problem that the user recommended commodity list appears in the home recommended commodity list is solved.
It should be noted that, if the user moves to a certain smart community, the user does not have any data of browsing the goods, and the user recommended goods list can be provided for the user according to the goods purchased by the members in the smart community by the above method.
In the embodiment of the invention, through obtaining the label information of the user and the label information of the user in the intelligent community including the user label, the family label and the community label of the user, the user recommended commodity list, the family recommended commodity list and the community recommended commodity list of the user and the recommended coefficient of each commodity in each recommended commodity list are determined, then the clustering calculation is carried out on the first N commodities in each recommended commodity list to determine the feature vector of each category in each recommended commodity list, then according to the feature vector of each category in each recommended commodity list, the similarity between the same category in the user recommended commodity list and the family recommended commodity list and the similarity between the same category in the user recommended commodity list and the community recommended commodity list are determined to determine the influence coefficient of the user for purchasing one category of commodities, and then according to the determined influence coefficient of the user for purchasing one category of commodities, and after the modified user recommended commodity list is created, commodities of which the commodity categories are removed from the commodity categories of the family recommended commodity list and the community recommended commodity list and commodities which are not in the modified user recommended commodity list can be inserted into the modified user recommended commodity list to serve as a new user recommended commodity list and pushed to the user. The commodity recommendation method for the user based on the relationship between the family and the smart community and the user is achieved, so that commodity recommendation for the user is more intelligent and accurate, and user experience is improved.
In order to better explain the technical solution, fig. 3 exemplarily shows a flow of a method for recommending goods based on family and community shopping big data according to an embodiment of the present invention.
As shown in fig. 3, the specific process includes:
step 301, obtaining all data of shopping and browsing commodities of the user in the family and the smart community.
The method comprises the steps of obtaining all shopping data of a user, all shopping data of family members and all shopping data of members in the smart community where the user is located, clicking data of browsed commodities, and obtaining tag information of the user in the smart community.
Step 302, determining recommended commodity lists of users, families and communities respectively.
And respectively determining a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user according to the acquired label information of the user in the intelligent community.
And 303, clustering according to the recommended commodity list commodities, and calculating the feature vector of each category in the recommended commodity list.
And respectively carrying out clustering calculation on the first N commodities in the user recommended commodity list, the family recommended commodity list and the community recommended commodity list of the user, and calculating the characteristic vector of each category in each recommended commodity list.
And step 304, respectively obtaining the similarity of the characteristic vectors after the family and community recommended commodity lists are clustered.
And determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list according to the feature vector of each category in the user recommended commodity list, the family recommended commodity list and the community recommended commodity list.
And 305, correcting the user recommendation list according to the similarity.
Determining the influence coefficient of the user for purchasing a class of commodities according to the similarity of the same class in the user recommended commodity list and the family recommended commodity list and the similarity of the same class in the user recommended commodity list and the community recommended commodity list, correcting the recommendation coefficient of each commodity in the user recommended commodity list according to the influence coefficient of the user for purchasing a class of commodities, and generating a corrected user recommended commodity list.
And step 306, revising the revised user recommended commodity list according to the family and community recommended commodity list.
And inserting the commodities with commodity categories removed from the family recommended commodity list and the community recommended commodity list into the corrected user recommended commodity list according to the corrected user recommended commodity list, and correcting the corrected user recommended commodity list again to generate a new user recommended commodity list.
And 307, pushing the new user recommended commodity list to the terminal equipment of the user.
And pushing the new user recommended commodity list to the terminal equipment of the user so that the terminal equipment of the user displays the new user recommended commodity list to the user.
The embodiment of the invention determines a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of a user by acquiring data of all shopping and browsing commodities of the user in a family and a smart community, performs clustering calculation on commodities in each recommended commodity list to determine a feature vector of each category in each recommended commodity list, determines the similarity of the same category in the user recommended commodity list and the family recommended commodity list and the similarity of the same category in the user recommended commodity list and the community recommended commodity list according to the feature vector of each category in each recommended commodity list to determine the influence coefficient of the user for purchasing one category of commodities, generates a modified user recommended commodity list according to the determined influence coefficient of the user for purchasing one category of commodities, and after the modified user recommended commodity list is created, and inserting the commodities of which the commodity categories are removed from the family recommended commodity list and the community recommended commodity list according to the corrected user recommended commodity list and the commodities which are not in the corrected user recommended commodity list into the corrected user recommended commodity list to serve as a new user recommended commodity list, and pushing the new user recommended commodity list to the terminal equipment of the user. The commodity recommendation method for the user based on the relationship between the family and the smart community and the user is achieved, so that commodity recommendation for the user is more intelligent and accurate, and user experience is improved.
Based on the same technical concept, fig. 4 exemplarily shows a structure of an apparatus for recommending goods based on family and community shopping big data according to an embodiment of the present invention, which can perform a flow of a method for recommending goods based on family and community shopping big data.
As shown in fig. 4, the apparatus specifically includes:
the obtaining module 401 is configured to obtain tag information of a user in an intelligent community, where the tag information of the user includes a user tag of the user, a home tag, and a community tag;
a processing module 402, configured to determine a user recommended commodity list, a family recommended commodity list, and a community recommended commodity list of the user according to the user tag, the family tag, and the community tag, respectively; each recommended commodity list comprises a recommendation coefficient of each commodity; clustering the first N commodities in each recommended commodity list, and determining a feature vector of each category in each recommended commodity list; n is a positive integer; according to the feature vector of each category in each recommended commodity list, determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list; determining an influence coefficient of a user for purchasing a class of commodities according to the similarity of the same class in the user recommended commodity list and the family recommended commodity list and the similarity of the same class in the user recommended commodity list and the community recommended commodity list; and according to the influence coefficient of the user for purchasing one type of commodities, correcting the recommendation coefficient of each commodity in the user recommended commodity list, and pushing the corrected user recommended commodity list to the user.
Optionally, the processing module 402 is specifically configured to:
determining an influence coefficient of a user for purchasing a type of commodities according to the following formula (1);
Figure BDA0002396883440000171
wherein, the SIMiInfluence coefficients of purchasing i-type commodities for users; a is a first preset influence weight value of the family recommended goods list on the user recommended goods list,
Figure BDA0002396883440000172
similarity between the recommended commodity list of the user and the ith category in the family recommended commodity list;
Figure BDA0002396883440000173
recommending feature vectors of each category in the first N ith items in the item list for the user;
Figure BDA0002396883440000174
recommending feature vectors of the ith category in the first N commodities in the commodity list for the family; b is a second preset influence weighted value of the community recommended commodity list on the user recommended commodity list;
Figure BDA0002396883440000175
recommending the ith category in the commodity list for the user and the commodity list recommended for the communitySimilarity;
Figure BDA0002396883440000176
recommending feature vectors of the ith category in the first N commodities in the commodity list for the community; i is a positive integer.
Optionally, the processing module 402 is specifically configured to:
determining and correcting a recommendation coefficient of each commodity in the user recommended commodity list according to the following formula (2);
Figure BDA0002396883440000177
wherein, P'xRecommending the revised recommendation coefficient of the xth commodity in the commodity list for the user; pxRecommending a recommendation coefficient before modification for the xth commodity in the commodity list for the user; x is a positive integer; SIM (subscriber identity Module)iAn influence coefficient for purchasing the i-type commodity for the user; i is a positive integer; n is the number of the categories to which the x-th goods in the user recommended goods list belong.
Optionally, the processing module 402 is specifically configured to:
according to the corrected recommendation coefficients of the commodities in the user recommended commodity list, arranging the commodities in the user recommended commodity list in a descending mode of the recommendation coefficients, generating a corrected user recommended commodity list, and sending the corrected user recommended commodity list to the terminal equipment of the user, so that the terminal equipment of the user displays the corrected user recommended commodity list to the user.
Optionally, the processing module 402 is further configured to:
the control acquisition module respectively acquires front M commodities in a family recommended commodity list and a community recommended commodity list, wherein M is a positive integer;
the method comprises the steps of conducting commodity category duplication elimination on front M commodities in a family recommended commodity list and a community recommended commodity list according to front K commodities in a user recommended commodity list after correction, wherein K is the product of n and M, inserting commodities after duplication elimination to the position, close to the front, of a commodity sequence in the user recommended commodity list after correction, inserting L commodities in a mall, which are not in the user recommended commodity list after correction, to the position, in the middle of the commodity sequence in the user recommended commodity list after correction, wherein L is a positive integer, combining the commodities after duplication elimination and L commodities in the mall to generate a new user recommended commodity list, and pushing the new user recommended commodity list to a user.
Based on the same technical concept, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the commodity recommendation method based on the family and community shopping big data according to the obtained program.
Based on the same technical concept, the embodiment of the invention also provides a computer-readable storage medium storing computer-executable instructions, which are used for enabling a computer to execute the method for recommending commodities based on family and community shopping big data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. 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 application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (10)

1. A commodity recommendation method based on family and community shopping big data is characterized by comprising the following steps:
the method comprises the steps of obtaining label information of a user in an intelligent community, wherein the label information of the user comprises a user label, a family label and a community label of the user;
respectively determining a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user according to the user label, the family label and the community label; each recommended commodity list comprises a recommendation coefficient of each commodity;
clustering the first N commodities in each recommended commodity list, and determining a feature vector of each category in each recommended commodity list; n is a positive integer;
according to the feature vector of each category in each recommended commodity list, determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list;
determining an influence coefficient of a user for purchasing a class of commodities according to the similarity of the same class in the user recommended commodity list and the family recommended commodity list and the similarity of the same class in the user recommended commodity list and the community recommended commodity list;
and according to the influence coefficient of the user for purchasing one type of commodities, correcting the recommendation coefficient of each commodity in the user recommended commodity list, and pushing the corrected user recommended commodity list to the user.
2. The method of claim 1, wherein the influence coefficient of a user's purchase of a type of merchandise is determined according to the following formula (1);
Figure FDA0002396883430000011
wherein, the SIMiInfluence coefficients of purchasing i-type commodities for users; a is a first preset influence weight value of the family recommended goods list on the user recommended goods list,
Figure FDA0002396883430000012
similarity between the recommended commodity list of the user and the ith category in the family recommended commodity list;
Figure FDA0002396883430000013
recommending feature vectors of the ith category in the first N commodities in the commodity list for the user;
Figure FDA0002396883430000021
recommending feature vectors of the ith category in the first N commodities in the commodity list for the family; b is a second preset influence weighted value of the community recommended commodity list on the user recommended commodity list;
Figure FDA0002396883430000022
similarity between the recommended commodity list for the user and the ith category in the community recommended commodity list;
Figure FDA0002396883430000023
recommending feature vectors of the ith category in the first N commodities in the commodity list for the community; i is a positive integer.
3. The method according to claim 1, wherein the recommendation coefficient for correcting each item in the user recommended item list is determined according to the following formula (2);
Figure FDA0002396883430000024
wherein, P'xRecommending the revised recommendation coefficient of the xth commodity in the commodity list for the user; pxRecommending a recommendation coefficient before modification for the xth commodity in the commodity list for the user; x is a positive integer; SIM (subscriber identity Module)iAn influence coefficient for purchasing the i-type commodity for the user; i is a positive integer; n is the number of the categories to which the x-th goods in the user recommended goods list belong.
4. The method of claim 1, wherein the pushing the modified user recommended goods list to the user comprises:
according to the corrected recommendation coefficients of the commodities in the user recommended commodity list, arranging the commodities in the user recommended commodity list in a descending mode of the recommendation coefficients, generating a corrected user recommended commodity list, and sending the corrected user recommended commodity list to the terminal equipment of the user, so that the terminal equipment of the user displays the corrected user recommended commodity list to the user.
5. The method of any of claims 1 to 4, further comprising:
respectively obtaining front M commodities in a family recommended commodity list and a community recommended commodity list, wherein M is a positive integer;
carrying out commodity category duplication removal on the front M commodities in the family recommended commodity list and the community recommended commodity list according to the front K commodities in the corrected user recommended commodity list, wherein K is the product of n and M;
inserting the commodity after the duplication removal into the position, which is ahead of the commodity sequence, in the corrected user recommended commodity list;
inserting L commodities in the mall which are not in the modified user recommended commodity list into the middle position of a commodity sequence in the modified user recommended commodity list, wherein L is a positive integer;
combining the de-duplicated commodities with L commodities in a shopping mall to generate a new user recommended commodity list;
and pushing the new user recommended commodity list to the user.
6. A commodity recommendation device based on family and community shopping big data is characterized by comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring the label information of a user in an intelligent community, and the label information of the user comprises a user label, a family label and a community label of the user;
the processing module is used for respectively determining a user recommended commodity list, a family recommended commodity list and a community recommended commodity list of the user according to the user label, the family label and the community label; each recommended commodity list comprises a recommendation coefficient of each commodity; clustering the first N commodities in each recommended commodity list, and determining a feature vector of each category in each recommended commodity list; n is a positive integer; according to the feature vector of each category in each recommended commodity list, determining the similarity between the user recommended commodity list and the same category in the family recommended commodity list and the similarity between the user recommended commodity list and the same category in the community recommended commodity list; determining an influence coefficient of a user for purchasing a class of commodities according to the similarity of the same class in the user recommended commodity list and the family recommended commodity list and the similarity of the same class in the user recommended commodity list and the community recommended commodity list; and according to the influence coefficient of the user for purchasing one type of commodities, correcting the recommendation coefficient of each commodity in the user recommended commodity list, and pushing the corrected user recommended commodity list to the user.
7. The apparatus of claim 6, wherein the processing module is specifically configured to:
determining an influence coefficient of a commodity purchased by a user according to the following formula (1);
Figure FDA0002396883430000031
wherein, the SIMiInfluence coefficients of purchasing i-type commodities for users; a is a first preset influence weight value of the family recommended goods list on the user recommended goods list,
Figure FDA0002396883430000032
similarity between the recommended commodity list of the user and the ith category in the family recommended commodity list;
Figure FDA0002396883430000041
recommending feature vectors of the ith category in the first N commodities in the commodity list for the user;
Figure FDA0002396883430000042
recommending feature vectors of the ith category in the first N commodities in the commodity list for the family; b is community recommendationThe commodity list is used for recommending a second preset influence weighted value of the commodity list to the user;
Figure FDA0002396883430000043
similarity between the recommended commodity list for the user and the ith category in the community recommended commodity list;
Figure FDA0002396883430000044
recommending feature vectors of the ith category in the first N commodities in the commodity list for the community; i is a positive integer.
8. The apparatus of claim 6, wherein the processing module is specifically configured to:
determining and correcting a recommendation coefficient of each commodity in the user recommended commodity list according to the following formula (2);
Figure FDA0002396883430000045
wherein, P'xRecommending the revised recommendation coefficient of the xth commodity in the commodity list for the user; pxRecommending a recommendation coefficient before modification for the xth commodity in the commodity list for the user; x is a positive integer; SIM (subscriber identity Module)iAn influence coefficient for purchasing the i-type commodity for the user; i is a positive integer; n is the number of the categories to which the x-th goods in the user recommended goods list belong.
9. A computing device, comprising:
a memory for storing program instructions;
a processor for calling program instructions stored in said memory to execute the method of any one of claims 1 to 5 in accordance with the obtained program.
10. A computer storage medium having computer-executable instructions stored thereon for causing a computer to perform the method of any one of claims 1 to 5.
CN202010134629.0A 2020-03-02 2020-03-02 Commodity recommendation method and device based on big data of home and community shopping Active CN111415219B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010134629.0A CN111415219B (en) 2020-03-02 2020-03-02 Commodity recommendation method and device based on big data of home and community shopping

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010134629.0A CN111415219B (en) 2020-03-02 2020-03-02 Commodity recommendation method and device based on big data of home and community shopping

Publications (2)

Publication Number Publication Date
CN111415219A true CN111415219A (en) 2020-07-14
CN111415219B CN111415219B (en) 2023-08-25

Family

ID=71494209

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010134629.0A Active CN111415219B (en) 2020-03-02 2020-03-02 Commodity recommendation method and device based on big data of home and community shopping

Country Status (1)

Country Link
CN (1) CN111415219B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150379609A1 (en) * 2014-06-30 2015-12-31 Kobo Incorporated Generating recommendations for unfamiliar users by utilizing social side information
CN106157156A (en) * 2016-07-29 2016-11-23 电子科技大学 A kind of cooperation recommending system based on communities of users
CN106651546A (en) * 2017-01-03 2017-05-10 重庆邮电大学 Intelligent community oriented electronic commerce information recommendation method
CN107633430A (en) * 2017-09-20 2018-01-26 哈尔滨工业大学 A kind of Method of Commodity Recommendation based on community of colony
CN110413870A (en) * 2018-12-18 2019-11-05 北京沃东天骏信息技术有限公司 Method of Commodity Recommendation, device and server

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150379609A1 (en) * 2014-06-30 2015-12-31 Kobo Incorporated Generating recommendations for unfamiliar users by utilizing social side information
CN106157156A (en) * 2016-07-29 2016-11-23 电子科技大学 A kind of cooperation recommending system based on communities of users
CN106651546A (en) * 2017-01-03 2017-05-10 重庆邮电大学 Intelligent community oriented electronic commerce information recommendation method
CN107633430A (en) * 2017-09-20 2018-01-26 哈尔滨工业大学 A kind of Method of Commodity Recommendation based on community of colony
CN110413870A (en) * 2018-12-18 2019-11-05 北京沃东天骏信息技术有限公司 Method of Commodity Recommendation, device and server

Also Published As

Publication number Publication date
CN111415219B (en) 2023-08-25

Similar Documents

Publication Publication Date Title
CN110135915B (en) Commodity recommendation method and system
US9613371B2 (en) Dynamic taxonomy generation with demand-based product groups
CN110827114A (en) Commodity recommendation method and device
CN104965889A (en) Content recommendation method and apparatus
CN109658206A (en) Information recommendation method and device
US20130275270A1 (en) Method, web server and web browser of providing information
CN110134783B (en) Personalized recommendation method, device, equipment and medium
CN110335123B (en) Commodity recommendation method, system, computer readable medium and device based on social e-commerce platform
CN112837118A (en) Commodity recommendation method and device for enterprise users
CN110929138A (en) Recommendation information generation method, device, equipment and storage medium
CN110969512B (en) Commodity recommendation method and device based on user purchasing behavior
CN113689259A (en) Commodity personalized recommendation method and system based on user behaviors
CN113689258A (en) Commodity recommendation heat generation method and system
US20190205769A1 (en) Data Processing Method, Apparatus, Device and Computer Readable Storage Media
CN106708871A (en) Method and device for identifying social service characteristics user
Aprilianti et al. Implementation of weighted parallel hybrid recommender systems for e-commerce in indonesia
CN107358508B (en) Similar commodity item management method and device
CA3138745A1 (en) Method and device for circling and creating target population
CN110110206A (en) Relation excavation and recommended method, device, calculating equipment, storage medium between article
CN106682968B (en) Navigation menu generation method and device and server
CN112561581A (en) Recommendation method and device, electronic equipment and storage medium
CN111415219B (en) Commodity recommendation method and device based on big data of home and community shopping
CN111523982A (en) Commodity information recommendation method, commodity information recommendation device, server and storage medium
CN106469403B (en) Information display method and device
CN107437200A (en) Information determines method and device

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