CN114066533A - Product recommendation method and device, electronic equipment and storage medium - Google Patents

Product recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114066533A
CN114066533A CN202111431235.2A CN202111431235A CN114066533A CN 114066533 A CN114066533 A CN 114066533A CN 202111431235 A CN202111431235 A CN 202111431235A CN 114066533 A CN114066533 A CN 114066533A
Authority
CN
China
Prior art keywords
product
user
recommended
attribute
calculating
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.)
Pending
Application number
CN202111431235.2A
Other languages
Chinese (zh)
Inventor
黄嘉文
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.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen 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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN202111431235.2A priority Critical patent/CN114066533A/en
Publication of CN114066533A publication Critical patent/CN114066533A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • 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
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0253—During e-commerce, i.e. online transactions

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of artificial intelligence, and discloses a product recommendation method, a product recommendation device, electronic equipment and a storage medium, wherein the method comprises the following steps: identifying the preferred products of the users to be recommended, and inquiring the purchased products of each historical user from a pre-constructed user library, wherein the user library comprises the users to be recommended and the historical users; extracting product characteristics of a preference product and a purchase product to respectively obtain a first product characteristic and a second product characteristic; calculating the product similarity of the first product characteristic and the second product characteristic, and taking the historical user with the product similarity larger than a preset threshold value as a similar user of the user to be recommended; selecting products meeting preset conditions from the purchased products of similar users as products to be recommended, and pushing the products to be recommended to the users to be recommended. In addition, the invention also relates to a block chain technology, and the product to be recommended can be stored in the block chain. The invention can guarantee the feasibility of product recommendation and improve the accuracy of product recommendation.

Description

Product recommendation method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a method and an apparatus for recommending a product, an electronic device, and a computer-readable storage medium.
Background
Today, with e-commerce, social platforms, and short videos emerging, each of the large internet platforms provides personalized results to users by using past browsing, purchasing, and collecting data information of the users, and the recommendation system slowly replaces the old inherent way of searching and filtering information, and becomes an important way for the users to obtain information.
Two recommendation engine algorithms that are currently mainly used in the industry are: content-based Recommendation (Content-based Recommendation) and Collaborative-Filtering-based Recommendation (Collaborative Filtering). Based on the recommendation of the content, according to the metadata of the articles or the content, the intuitive relevance is discovered, and then based on the attributes and labels of the articles purchased or favored by the user at present, similar articles are recommended for the user; collaborative filtering based recommendations are then classified as user-based collaborative filtering: searching favorite articles of a user similar to the target user by using a statistical correlation technique, and recommending the favorite articles to the target user; article-based collaborative filtering: and calculating similar articles of the articles favored by the target user, and recommending the articles to the target user.
However, the two product recommendation methods have the problems of sparseness and new users, that is, when the user data volume of the service system is not large enough, some users and articles lack similar types which cannot be matched with effective data, so that product recommendation cannot be completed, and before a product is not purchased, a new user is difficult to find a user or an article which is related to the new user through an algorithm for product recommendation, so that a phenomenon of product recommendation failure occurs, and the feasibility of product recommendation cannot be guaranteed.
Disclosure of Invention
The invention provides a product recommendation method, a product recommendation device, electronic equipment and a computer-readable storage medium, and mainly aims to guarantee the feasibility of product recommendation and improve the accuracy of product recommendation.
In order to achieve the above object, the present invention provides a product recommendation method, including:
acquiring a user to be recommended, identifying a preference product of the user to be recommended, and inquiring a purchased product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users;
extracting product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic;
calculating the product similarity of the first product characteristic and the second product characteristic, and taking the historical user with the product similarity larger than a preset threshold value as a similar user of the user to be recommended;
selecting products meeting preset conditions from the purchased products of the similar users as products to be recommended, and pushing the products to be recommended to the users to be recommended.
Optionally, the identifying a preferred product of the user to be recommended includes:
acquiring a behavior record of the user to be recommended by using a point burying technology, and inquiring product browsing information of the user to be recommended according to the behavior record;
and determining the preference product of the user to be recommended according to the product browsing information.
Optionally, the collecting, by using a buried point technology, the behavior record of the user to be recommended includes:
configuring a click event in a user browsing page by using the embedded point technology, and loading the click event into an embedded point control;
and acquiring click information of the user to be recommended in the click event based on the embedded point control to obtain a behavior record of the user to be recommended.
Optionally, the extracting the product features of the preferred product and the purchased product to obtain a first product feature and a second product feature respectively includes:
obtaining product attributes existing in the preference product and the purchase product, and respectively obtaining a first product attribute and a second product attribute;
calculating the information entropy of the first product attribute and the preference product corresponding to the first product attribute, calculating the splitting information quantity of the first product attribute, calculating a first gain rate of the first product attribute according to the information entropy of the first product attribute and the preference product corresponding to the first product attribute and the splitting information quantity of the first product attribute, and taking the first product attribute of which the first gain rate is greater than a preset gain rate as the first product characteristic;
calculating the second product attribute and the information entropy of the purchased product corresponding to the second product attribute, and calculating the splitting information quantity of the second product attribute; and calculating a second gain rate of the second product attribute according to the second product attribute, the corresponding information entropy of the purchased product and the splitting information amount of the second product attribute, and taking the second product attribute with the second gain rate larger than the preset gain rate as the second product characteristic.
Optionally, the calculating the splitting information amount of the first product attribute includes:
calculating a split information volume for the first product attribute using the following formula:
Figure BDA0003380213120000021
wherein SplitInfoA(A) Amount of split information representing first product attribute, m represents number of product attributes of preferred product, | Dj| represents the jth product attribute in the preferred product, | D | represents the preferred product.
Optionally, the calculating a first gain ratio of the first product attribute comprises:
calculating a first gain ratio for the first product attribute using the following equation:
Figure BDA0003380213120000031
wherein, gain ratio (A) represents the first gain rate of the first product attribute, Info (D) represents the information entropy of the preferred product, InfoA(D) Entropy of information, SplitInfo, representing a first product attributeA(A) A split information volume representing a first product attribute.
Optionally, the calculating the product similarity of the first product feature and the second product feature includes:
converting the first and second product features into first and second product vectors, respectively;
and calculating the vector similarity of the first product vector and the second product vector, and taking the vector similarity as the product similarity of the first product characteristic and the second product characteristic.
In order to solve the above problems, the present invention also provides a product recommendation apparatus, comprising:
the product acquisition module is used for acquiring a user to be recommended, identifying a preference product of the user to be recommended, and inquiring a purchased product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users;
the characteristic extraction module is used for extracting the product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic;
the similar user identification module is used for calculating the product similarity of the first product characteristic and the second product characteristic and taking the historical user with the product similarity larger than a preset threshold value as the similar user of the user to be recommended;
and the product pushing module is used for selecting a product meeting a preset condition from the purchased products of the similar users as a product to be recommended and pushing the product to be recommended to the user to be recommended.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to implement the product recommendation method described above.
In order to solve the above problem, the present invention also provides a computer-readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the product recommendation method described above.
Compared with the phenomenon that products cannot be pushed due to sparse or new users in the prior art, the method and the device for recommending the products achieve calculation of the similarity of the products of the users to be recommended and the historical users by obtaining the preferred products of the users to be recommended and combining the products purchased by each historical user in the pre-constructed user library, so that the similar users of the users to be recommended can be generated, the problem that the products cannot be recommended due to the fact that the users to be recommended lack similar users with effective data and cannot be matched is solved, the phenomenon that the products cannot be pushed due to the fact that the users to be recommended do not purchase the products is avoided, feasibility of product recommendation is guaranteed, and accuracy of product recommendation is improved. Therefore, the product recommendation method, the product recommendation device, the electronic device and the computer-readable storage medium provided by the embodiment of the invention can guarantee the feasibility of product recommendation and improve the accuracy of product recommendation.
Drawings
Fig. 1 is a schematic flowchart of a product recommendation method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a product recommendation device according to an embodiment of the present invention;
fig. 3 is a schematic internal structural diagram of an electronic device implementing a product recommendation method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a product recommendation method. The execution subject of the product recommendation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the product recommendation method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Referring to fig. 1, a flowchart of a product recommendation method according to an embodiment of the present invention is shown. In an embodiment of the present invention, the product recommendation method includes:
s1, obtaining a user to be recommended, identifying the preference product of the user to be recommended, and inquiring the purchase product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users.
In the embodiment of the invention, the user to be recommended refers to a user needing product recommendation, and is obtained by positioning through different service recommendation scenes, for example, in an insurance product recommendation scene, the user to be recommended may be a user who has not purchased insurance or a user who has purchased insurance due, in an asset product recommendation scene, the user to be recommended may be a family who has purchased a financial product user or a user who has not purchased and browsed a financial product, and the preference product refers to a product which the user to be recommended is interested in.
As an embodiment of the present invention, the identifying a preferred product of the user to be recommended includes: and acquiring the behavior record of the user to be recommended by using a point burying technology, inquiring the product browsing information of the user to be recommended according to the behavior record, and determining the preference product of the user to be recommended according to the product browsing information.
The behavior record refers to behavior information recorded when the user to be recommended browses a page on line, and the product browsing information refers to record information containing a product in the behavior record.
Further, in an optional embodiment of the present invention, the collecting, by using a point burying technology, the behavior record of the user to be recommended includes: and configuring a click event in a user browsing page by using the embedded point technology, loading the click event into an embedded point control, and acquiring click information of the user to be recommended in the click event based on the embedded point control to obtain a behavior record of the user to be recommended.
The user browsing page is a product display page, the click event is an event generated by the behavior of a UI control clicked by a user at a mobile terminal or a webpage terminal, the UI control can be a login control, a purchase control, a view control and the like, the embedded point control is used for collecting behavior data of the user, such as Vue control, and the click event can be loaded through a Hook technology.
Further, in an optional embodiment of the present invention, the product browsing information is queried through a query statement, such as a select statement in SQL.
Further, in an optional embodiment of the present invention, the determining, according to the product browsing information, a preferred product of the user to be recommended includes: and acquiring the collected products, the purchased products and the checked products of the user to be recommended according to the product browsing information, and taking the collected products, the purchased products and the checked products as preference products of the user to be recommended.
Further, in the embodiment of the present invention, the pre-constructed user library is generated based on the different service recommendation scenarios, and includes the user to be recommended and the historical user, for example, for an insurance product recommendation scenario, the user library may be a database composed of users who purchased insurance products, and for a financial product recommendation scenario, the user library may be a database composed of users who purchased financial products.
As an embodiment of the invention, the querying the purchased products of each historical user from the pre-constructed user library comprises the following steps: and identifying the query object and the query identifier of each historical user, converting the query object and the query identifier into a query statement, and querying the purchased products of each historical user in the pre-constructed user library according to the query statement.
The query object refers to a product index which needs to be queried by each historical user, the query identifier refers to an identity information identifier of each historical user, and the query statement refers to the structured data characteristics of the query object and the query identifier, and can be compiled and converted through SQL language.
Based on the acquisition of the preference product and the purchase product, the generation of a premise by similar users of the user to be recommended can be guaranteed, and thus the product recommendation premise of the user to be recommended can be guaranteed.
And S2, extracting the product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic.
It should be understood that a great deal of product information such as product name, product date, product function, product structure and the like exists in the preferred product and the purchased product, and in order to improve the processing speed of the preferred product and the purchased product, the embodiment of the invention screens out useless data in the preferred product and the purchased product by extracting the product characteristics of the preferred product and the purchased product, so as to improve the subsequent data processing speed.
As an embodiment of the present invention, the extracting product features of the preferred product and the purchased product to obtain a first product feature and a second product feature respectively includes: obtaining product attributes existing in the preference product and the purchase product, and respectively obtaining a first product attribute and a second product attribute; calculating the information entropy of the first product attribute and the corresponding preference product, and calculating the splitting information quantity of the first product attribute; calculating a first gain rate of the first product attribute according to the first product attribute, the information entropy of the preference product corresponding to the first product attribute and the splitting information amount of the first product attribute, and taking the first product attribute of which the first gain rate is greater than a preset gain rate as the first product characteristic; calculating the second product attribute and the information entropy of the purchased product corresponding to the second product attribute, and calculating the splitting information quantity of the second product attribute; and calculating a second gain rate of the second product attribute according to the second product attribute, the corresponding information entropy of the purchased product and the splitting information amount of the second product attribute, and taking the second product attribute with the second gain rate larger than the preset gain rate as the second product characteristic.
The gain rate can be understood as a ratio value of a proportion of data in a subsequent data processing process, and the larger the information gain rate is, the more important the corresponding data is, therefore, the product attribute with the gain rate greater than the preset gain rate is taken as a product characteristic, optionally, the preset gain rate can be set as the product characteristic, and also can be set according to an actual service scene.
In an alternative embodiment, the amount of splitting information for the first product attribute is calculated using the following formula:
Figure BDA0003380213120000061
wherein SplitInfoA(A) Amount of split information representing first product attribute, m represents number of product attributes of preferred product, | Dj| represents the jth product attribute in the preferred product, | D | represents the preferred product.
In an alternative embodiment, the first gain ratio for the first product attribute is calculated using the following equation:
Figure BDA0003380213120000071
wherein, gain ratio (A) represents the first gain rate of the first product attribute, Info (D) represents the information entropy of the preferred product, InfoA(D) Entropy of information, SplitInfo, representing a first product attributeA(A) A split information volume representing a first product attribute.
It should be noted that the calculation principle of the splitting information amount and the second gain ratio of the second product attribute is the same as the calculation principle of the splitting information amount and the second gain ratio of the first product attribute, and further description thereof is omitted here.
S3, calculating the product similarity of the first product characteristic and the second product characteristic, and taking the historical user with the product similarity larger than a preset threshold value as the similar user of the user to be recommended.
In an embodiment of the present invention, the calculating the product similarity between the first product feature and the second product feature includes: converting the first and second product features into first and second product vectors, respectively; and calculating the vector similarity of the first product vector and the second product vector, and taking the vector similarity as the product similarity of the first product characteristic and the second product characteristic. The vector conversion of the first product feature and the second product feature is realized by a vector conversion algorithm, such as a one-hot algorithm, a word2vec algorithm, and the like.
Further, in an optional embodiment of the present invention, the vector similarity between the first product vector and the second product vector is calculated by using the following formula:
Figure BDA0003380213120000072
wherein R represents vector similarity, AxRepresents the x-th first product vector, ByRepresenting the y-th second product vector in the data code table.
Further, in the embodiment of the present invention, the historical user whose product similarity is greater than the preset threshold is used as the similar user of the user to be recommended, so as to ensure the product recommendation premise of the user to be recommended. The preset threshold may be set to 0.6, or may be set according to an actual service scenario.
S4, selecting products meeting preset conditions from the purchased products of the similar users as products to be recommended, and pushing the products to be recommended to the users to be recommended.
In the embodiment of the present invention, the preset condition may be set according to the number of purchases of the purchased product, for example, a product with the number of purchases of the purchased product exceeding three times is selected as the product to be recommended, or may be set according to the time of purchasing the product, for example, a product in a last week of the purchased product is selected as the product to be recommended, which is not further limited herein. Further, the embodiment of the invention adopts one or a combination of several ways to push the product to be recommended to the user to be recommended: the method comprises the steps of firstly, pushing contents such as mails and short messages; a mode, a push mode through telephone voice; and thirdly, pushing through a page popup.
Further, in order to ensure privacy and security of the product to be recommended, the product to be recommended may also be stored in a blockchain node.
The product push of the user to be recommended is realized based on the similar users, the problem that the product recommendation cannot be completed due to the fact that the user to be recommended lacks similar users with effective data matching, and the phenomenon that the product cannot be pushed due to the fact that the user to be recommended does not purchase the product can be solved, the product recommendation feasibility of the user to be recommended is guaranteed, and the product recommendation accuracy is improved.
Compared with the phenomenon that products cannot be pushed due to sparse or new users in the prior art, the method and the device for recommending the products achieve calculation of the similarity of the products of the users to be recommended and the historical users by obtaining the preferred products of the users to be recommended and combining the products purchased by each historical user in the pre-constructed user library, so that the similar users of the users to be recommended can be generated, the problem that the products cannot be recommended due to the fact that the users to be recommended lack similar users with effective data and cannot be matched is solved, the phenomenon that the products cannot be pushed due to the fact that the users to be recommended do not purchase the products is avoided, feasibility of product recommendation is guaranteed, and accuracy of product recommendation is improved. Therefore, the product recommendation method provided by the embodiment of the invention can guarantee the feasibility of product recommendation and improve the accuracy of product recommendation.
Fig. 2 is a functional block diagram of the product recommendation device of the present invention.
The product recommendation device 100 of the present invention may be installed in an electronic device. According to the realized functions, the product recommendation device may include a product acquisition module 101, a feature extraction module 102, a similar user identification module 103, and a product push module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and is stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the product obtaining module 101 is configured to obtain a user to be recommended, identify a preferred product of the user to be recommended, and query a purchased product of each historical user from a pre-constructed user library, where the user library includes the user to be recommended and the historical users.
In the embodiment of the invention, the user to be recommended refers to a user needing product recommendation, and is obtained by positioning through different service recommendation scenes, for example, in an insurance product recommendation scene, the user to be recommended may be a user who has not purchased insurance or a user who has purchased insurance due, in an asset product recommendation scene, the user to be recommended may be a family who has purchased a financial product user or a user who has not purchased and browsed a financial product, and the preference product refers to a product which the user to be recommended is interested in.
As an embodiment of the present invention, the product obtaining module 101 performs the following steps to identify the preferred product of the user to be recommended: and acquiring the behavior record of the user to be recommended by using a point burying technology, inquiring the product browsing information of the user to be recommended according to the behavior record, and determining the preference product of the user to be recommended according to the product browsing information.
The behavior record refers to behavior information recorded when the user to be recommended browses a page on line, and the product browsing information refers to record information containing a product in the behavior record.
Further, in an optional embodiment of the present invention, the behavior record of the user to be recommended is collected by using a point burying technology, and the product obtaining module 101 is implemented in the following manner: and configuring a click event in a user browsing page by using the embedded point technology, loading the click event into an embedded point control, and acquiring click information of the user to be recommended in the click event based on the embedded point control to obtain a behavior record of the user to be recommended.
The user browsing page is a product display page, the click event is an event generated by the behavior of a UI control clicked by a user at a mobile terminal or a webpage terminal, the UI control can be a login control, a purchase control, a view control and the like, the embedded point control is used for collecting behavior data of the user, such as Vue control, and the click event can be loaded through a Hook technology.
Further, in an optional embodiment of the present invention, the product browsing information is queried through a query statement, such as a select statement in SQL.
Further, in an optional embodiment of the present invention, in the step of determining the preferred product of the user to be recommended according to the product browsing information, the product obtaining module 101 is implemented in the following manner: and acquiring the collected products, the purchased products and the checked products of the user to be recommended according to the product browsing information, and taking the collected products, the purchased products and the checked products as preference products of the user to be recommended.
Further, in the embodiment of the present invention, the pre-constructed user library is generated based on the different service recommendation scenarios, and includes the user to be recommended and the historical user, for example, for an insurance product recommendation scenario, the user library may be a database composed of users who purchased insurance products, and for a financial product recommendation scenario, the user library may be a database composed of users who purchased financial products.
As an embodiment of the present invention, the product acquisition module 101 queries a user library of users from a pre-built user library for each purchased product of the historical user, and performs the following steps: and identifying the query object and the query identifier of each historical user, converting the query object and the query identifier into a query statement, and querying the purchased products of each historical user in the pre-constructed user library according to the query statement.
The query object refers to a product index which needs to be queried by each historical user, the query identifier refers to an identity information identifier of each historical user, and the query statement refers to the structured data characteristics of the query object and the query identifier, and can be compiled and converted through SQL language.
Based on the acquisition of the preference product and the purchase product, the generation of a premise by similar users of the user to be recommended can be guaranteed, and thus the product recommendation premise of the user to be recommended can be guaranteed.
The feature extraction module 102 is configured to extract product features of the preferred product and the purchased product to obtain a first product feature and a second product feature, respectively.
It should be understood that a great deal of product information such as product name, product date, product function, product structure and the like exists in the preferred product and the purchased product, and in order to improve the processing speed of the preferred product and the purchased product, the embodiment of the invention screens out useless data in the preferred product and the purchased product by extracting the product characteristics of the preferred product and the purchased product, so as to improve the subsequent data processing speed.
As an embodiment of the present invention, the extracting product features of the preferred product and the purchased product to obtain a first product feature and a second product feature respectively, the feature extracting module 102 performs the following steps: obtaining product attributes existing in the preference product and the purchase product, and respectively obtaining a first product attribute and a second product attribute; calculating the information entropy of the first product attribute and the corresponding preference product, and calculating the splitting information quantity of the first product attribute; calculating a first gain rate of the first product attribute according to the first product attribute, the information entropy of the preference product corresponding to the first product attribute and the splitting information amount of the first product attribute, and taking the first product attribute of which the first gain rate is greater than a preset gain rate as the first product characteristic; calculating the second product attribute and the information entropy of the purchased product corresponding to the second product attribute, and calculating the splitting information quantity of the second product attribute; and calculating a second gain rate of the second product attribute according to the second product attribute, the corresponding information entropy of the purchased product and the splitting information amount of the second product attribute, and taking the second product attribute with the second gain rate larger than the preset gain rate as the second product characteristic.
The gain rate can be understood as a ratio value of a proportion of data in a subsequent data processing process, and the larger the information gain rate is, the more important the corresponding data is, therefore, the product attribute with the gain rate greater than the preset gain rate is taken as a product characteristic, optionally, the preset gain rate can be set as the product characteristic, and also can be set according to an actual service scene.
In an alternative embodiment, the feature extraction module 102 calculates the split information content of the first product attribute using the following formula:
Figure BDA0003380213120000101
wherein SplitInfoA(A) Amount of split information representing first product attribute, m represents number of product attributes of preferred product, | Dj| represents the jth product attribute in the preferred product, | D | represents the preferred product.
In an alternative embodiment, the feature extraction module 102 calculates the first gain ratio for the first product attribute using the following equation:
Figure BDA0003380213120000111
wherein, gain ratio (A) represents the first gain rate of the first product attribute, Info (D) represents the information entropy of the preferred product, InfoA(D) Entropy of information, SplitInfo, representing a first product attributeA(A) A split information volume representing a first product attribute.
It should be noted that the calculation principle of the splitting information amount and the second gain ratio of the second product attribute is the same as the calculation principle of the splitting information amount and the second gain ratio of the first product attribute, and further description thereof is omitted here.
The similar user identification module 103 is configured to calculate a product similarity between the first product feature and the second product feature, and use a historical user whose product similarity is greater than a preset threshold as a similar user of the user to be recommended.
In this embodiment of the present invention, the calculating the product similarity between the first product characteristic and the second product characteristic is performed by the similar user identifying module 103 in the following manner: converting the first and second product features into first and second product vectors, respectively; and calculating the vector similarity of the first product vector and the second product vector, and taking the vector similarity as the product similarity of the first product characteristic and the second product characteristic. The vector conversion of the first product feature and the second product feature is realized by a vector conversion algorithm, such as a one-hot algorithm, a word2vec algorithm, and the like.
Further, in an optional embodiment of the present invention, the similar user identifying module 103 calculates the vector similarity between the first product vector and the second product vector by using the following formula:
Figure BDA0003380213120000112
wherein R represents vector similarity, AxRepresents the x-th first product vector, ByRepresenting the y-th second product vector in the data code table.
Further, in the embodiment of the present invention, the historical user whose product similarity is greater than the preset threshold is used as the similar user of the user to be recommended, so as to ensure the product recommendation premise of the user to be recommended. The preset threshold may be set to 0.6, or may be set according to an actual service scenario.
The product pushing module 104 is configured to select a product meeting a preset condition from the purchased products of the similar users as a product to be recommended, and push the product to be recommended to the user to be recommended.
In the embodiment of the present invention, the preset condition may be set according to the number of purchases of the purchased product, for example, a product with the number of purchases of the purchased product exceeding three times is selected as the product to be recommended, or may be set according to the time of purchasing the product, for example, a product in a last week of the purchased product is selected as the product to be recommended, which is not further limited herein. Further, the embodiment of the invention adopts one or a combination of several ways to push the product to be recommended to the user to be recommended: the method comprises the steps of firstly, pushing contents such as mails and short messages; a mode, a push mode through telephone voice; and thirdly, pushing through a page popup.
Further, in order to ensure privacy and security of the product to be recommended, the product to be recommended may also be stored in a blockchain node.
The product push of the user to be recommended is realized based on the similar users, the problem that the product recommendation cannot be completed due to the fact that the user to be recommended lacks similar users with effective data matching, and the phenomenon that the product cannot be pushed due to the fact that the user to be recommended does not purchase the product can be solved, the product recommendation feasibility of the user to be recommended is guaranteed, and the product recommendation accuracy is improved.
Compared with the phenomenon that products cannot be pushed due to sparse or new users in the prior art, the method and the device for recommending the products achieve calculation of the similarity of the products of the users to be recommended and the historical users by obtaining the preferred products of the users to be recommended and combining the products purchased by each historical user in the pre-constructed user library, so that the similar users of the users to be recommended can be generated, the problem that the products cannot be recommended due to the fact that the users to be recommended lack similar users with effective data and cannot be matched is solved, the phenomenon that the products cannot be pushed due to the fact that the users to be recommended do not purchase the products is avoided, feasibility of product recommendation is guaranteed, and accuracy of product recommendation is improved. Therefore, the product recommendation device provided by the embodiment of the invention can guarantee the feasibility of product recommendation and improve the accuracy of product recommendation.
Fig. 3 is a schematic structural diagram of an electronic device 1 for implementing the product recommendation method according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a product recommendation program, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device 1, connects various components of the electronic device 1 by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., executing product recommendation programs, etc.) stored in the memory 11 and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of product recommendation programs, etc., but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device 1 and other devices, and includes a network interface and an employee interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices 1. The employee interface may be a Display (Display), an input unit, such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visual staff interface.
Fig. 3 shows only the electronic device 1 with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the embodiments described are for illustrative purposes only and that the scope of the claimed invention is not limited to this configuration.
The product recommendation program stored in the memory 11 of the electronic device 1 is a combination of computer programs, which when run in the processor 10, may implement:
acquiring a user to be recommended, identifying a preference product of the user to be recommended, and inquiring a purchased product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users;
extracting product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic;
calculating the product similarity of the first product characteristic and the second product characteristic, and taking the historical user with the product similarity larger than a preset threshold value as a similar user of the user to be recommended;
selecting products meeting preset conditions from the purchased products of the similar users as products to be recommended, and pushing the products to be recommended to the users to be recommended.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-volatile computer-readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device 1, may implement:
acquiring a user to be recommended, identifying a preference product of the user to be recommended, and inquiring a purchased product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users;
extracting product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic;
calculating the product similarity of the first product characteristic and the second product characteristic, and taking the historical user with the product similarity larger than a preset threshold value as a similar user of the user to be recommended;
selecting products meeting preset conditions from the purchased products of the similar users as products to be recommended, and pushing the products to be recommended to the users to be recommended.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A method for recommending products, the method comprising:
acquiring a user to be recommended, identifying a preference product of the user to be recommended, and inquiring a purchased product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users;
extracting product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic;
calculating the product similarity of the first product characteristic and the second product characteristic, and taking the historical user with the product similarity larger than a preset threshold value as a similar user of the user to be recommended;
selecting products meeting preset conditions from the purchased products of the similar users as products to be recommended, and pushing the products to be recommended to the users to be recommended.
2. The product recommendation method of claim 1, wherein said identifying the preferred product of the user to be recommended comprises:
acquiring a behavior record of the user to be recommended by using a point burying technology, and inquiring product browsing information of the user to be recommended according to the behavior record;
and determining the preference product of the user to be recommended according to the product browsing information.
3. The product recommendation method of claim 2, wherein the collecting the behavior record of the user to be recommended by using a buried point technology comprises:
configuring a click event in a user browsing page by using the embedded point technology, and loading the click event into an embedded point control;
and acquiring click information of the user to be recommended in the click event based on the embedded point control to obtain a behavior record of the user to be recommended.
4. The product recommendation method of claim 1, wherein said extracting product features of said preferred product and said purchased product to obtain a first product feature and a second product feature, respectively, comprises:
obtaining product attributes existing in the preference product and the purchase product, and respectively obtaining a first product attribute and a second product attribute;
calculating the information entropy of the first product attribute and the preference product corresponding to the first product attribute, calculating the splitting information quantity of the first product attribute, calculating a first gain rate of the first product attribute according to the information entropy of the first product attribute and the preference product corresponding to the first product attribute and the splitting information quantity of the first product attribute, and taking the first product attribute of which the first gain rate is greater than a preset gain rate as the first product characteristic;
calculating the second product attribute and the information entropy of the purchased product corresponding to the second product attribute, and calculating the splitting information quantity of the second product attribute; and calculating a second gain rate of the second product attribute according to the second product attribute, the corresponding information entropy of the purchased product and the splitting information amount of the second product attribute, and taking the second product attribute with the second gain rate larger than the preset gain rate as the second product characteristic.
5. The product recommendation method of claim 4, wherein said calculating the split information volume for the first product attribute comprises:
calculating a split information volume for the first product attribute using the following formula:
Figure FDA0003380213110000021
wherein SplitInfoA(A) Amount of split information representing first product attribute, m represents number of product attributes of preferred product, | Dj| represents the jth product attribute in the preferred product, | D | represents the preferred product.
6. The product recommendation method of claim 4, wherein said calculating a first gain ratio for said first product attribute comprises:
calculating a first gain ratio for the first product attribute using the following equation:
Figure FDA0003380213110000022
wherein, GainRatio (A) tableA first gain rate indicating a first product attribute, Info (D) information entropy indicating a preferred product, InfoA(D) Entropy of information, SplitInfo, representing a first product attributeA(A) A split information volume representing a first product attribute.
7. The product recommendation method of any of claims 1-6, wherein said calculating a product similarity of the first product feature and the second product feature comprises:
converting the first and second product features into first and second product vectors, respectively;
and calculating the vector similarity of the first product vector and the second product vector, and taking the vector similarity as the product similarity of the first product characteristic and the second product characteristic.
8. A product recommendation device, the device comprising:
the product acquisition module is used for acquiring a user to be recommended, identifying a preference product of the user to be recommended, and inquiring a purchased product of each historical user from a pre-constructed user library, wherein the user library comprises the user to be recommended and the historical users;
the characteristic extraction module is used for extracting the product characteristics of the preference product and the purchase product to respectively obtain a first product characteristic and a second product characteristic;
the similar user identification module is used for calculating the product similarity of the first product characteristic and the second product characteristic and taking the historical user with the product similarity larger than a preset threshold value as the similar user of the user to be recommended;
and the product pushing module is used for selecting a product meeting a preset condition from the purchased products of the similar users as a product to be recommended and pushing the product to be recommended to the user to be recommended.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the product recommendation method of any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the product recommendation method of any one of claims 1 to 7.
CN202111431235.2A 2021-11-29 2021-11-29 Product recommendation method and device, electronic equipment and storage medium Pending CN114066533A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111431235.2A CN114066533A (en) 2021-11-29 2021-11-29 Product recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111431235.2A CN114066533A (en) 2021-11-29 2021-11-29 Product recommendation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114066533A true CN114066533A (en) 2022-02-18

Family

ID=80277172

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111431235.2A Pending CN114066533A (en) 2021-11-29 2021-11-29 Product recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114066533A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114969249A (en) * 2022-04-28 2022-08-30 江苏四象软件有限公司 Data mining system and data mining method
CN116739794A (en) * 2023-08-10 2023-09-12 北京中关村银行股份有限公司 User personalized scheme recommendation method and system based on big data and machine learning

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114969249A (en) * 2022-04-28 2022-08-30 江苏四象软件有限公司 Data mining system and data mining method
CN116739794A (en) * 2023-08-10 2023-09-12 北京中关村银行股份有限公司 User personalized scheme recommendation method and system based on big data and machine learning
CN116739794B (en) * 2023-08-10 2023-10-20 北京中关村银行股份有限公司 User personalized scheme recommendation method and system based on big data and machine learning

Similar Documents

Publication Publication Date Title
CN106383887B (en) Method and system for collecting, recommending and displaying environment-friendly news data
US8370358B2 (en) Tagging content with metadata pre-filtered by context
CN113836131B (en) Big data cleaning method and device, computer equipment and storage medium
CN111008321B (en) Logistic regression recommendation-based method, device, computing equipment and readable storage medium
CN105354202B (en) Data push method and device
US20130254181A1 (en) Aggregation and Categorization
CN114066533A (en) Product recommendation method and device, electronic equipment and storage medium
CN115002200A (en) User portrait based message pushing method, device, equipment and storage medium
CN113886708A (en) Product recommendation method, device, equipment and storage medium based on user information
CN114386509A (en) Data fusion method and device, electronic equipment and storage medium
CN113220657A (en) Data processing method and device and computer equipment
CN113362162A (en) Wind control identification method and device based on network behavior data, electronic equipment and medium
CN112559923A (en) Website resource recommendation method and device, electronic equipment and computer storage medium
CN114138784A (en) Information tracing method and device based on storage library, electronic equipment and medium
CN115018588A (en) Product recommendation method and device, electronic equipment and readable storage medium
CN112927057A (en) Object information display method and device, computer equipment and readable storage medium
CN113706249B (en) Data recommendation method and device, electronic equipment and storage medium
CN113449002A (en) Vehicle recommendation method and device, electronic equipment and storage medium
CN114840388A (en) Data monitoring method and device, electronic equipment and storage medium
CN113139049B (en) Associated document recommending method, device, computer equipment and storage medium
CN112149391B (en) Information processing method, information processing apparatus, terminal device, and storage medium
CN113761102B (en) Data processing method, device, server, system and storage medium
CN113344674A (en) Product recommendation method, device, equipment and storage medium based on user purchasing power
CN113434660A (en) Product recommendation method, device, equipment and storage medium based on multi-domain classification
CN114219544A (en) Consumption tendency analysis method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination