CN113065932A - Article recommendation method and device - Google Patents
Article recommendation method and device Download PDFInfo
- Publication number
- CN113065932A CN113065932A CN202110489879.0A CN202110489879A CN113065932A CN 113065932 A CN113065932 A CN 113065932A CN 202110489879 A CN202110489879 A CN 202110489879A CN 113065932 A CN113065932 A CN 113065932A
- Authority
- CN
- China
- Prior art keywords
- article
- item
- target
- articles
- behavior data
- 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
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an article recommendation method and device, and relates to the technical field of computers. One embodiment of the method comprises: acquiring user behavior data, and a target user and a target object corresponding to the user behavior data; if the user behavior data is first behavior data, acquiring a related article corresponding to the target article according to a pre-generated article combination, and recommending the related article corresponding to the target article to the target user, wherein the first behavior data comprises: purchase data and order data; if the user behavior data is second behavior data, obtaining similar articles corresponding to the target article according to the article combination, and recommending the similar articles corresponding to the target article to the target user, wherein the second behavior data comprises: search data, browse data, click data, and collection data. According to the method and the system, the articles can be recommended to the user by combining different shopping scenes, the article recommendation accuracy is improved, and better use experience is brought to the user.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an article recommendation method and device.
Background
More and more users select online shopping, and with the continuous development of online shopping platforms, the items provided on the platforms are diversified, so that the method has important significance on how to recommend the items of interest to the users. Currently, the item recommendation method is as follows: after a user searches, browses and purchases an item, the same type of item of the item is still recommended on the platform.
However, the user has placed an order to purchase an item, if the same type of item of the item is continuously recommended, the shopping desire of the user is not great, so that the item recommendation accuracy is low, and if the price/performance ratio of the recommended item is better than that of the item that the user has placed the order to purchase, the user may place an order again, so that the user experience is poor.
Disclosure of Invention
In view of this, the embodiment of the invention provides an article recommendation method and apparatus, which can recommend an article to a user in combination with different shopping scenes, improve the accuracy of article recommendation, and bring better use experience to the user.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided an item recommendation method.
The article recommendation method provided by the embodiment of the invention comprises the following steps: acquiring user behavior data, and a target user and a target object corresponding to the user behavior data; if the user behavior data is first behavior data, acquiring a related article corresponding to the target article according to a pre-generated article combination, and recommending the related article corresponding to the target article to the target user, wherein the first behavior data comprises: purchase data and order data; if the user behavior data is second behavior data, obtaining similar articles corresponding to the target article according to the article combination, and recommending the similar articles corresponding to the target article to the target user, wherein the second behavior data comprises: search data, browse data, click data, and collection data.
Optionally, the combination of articles comprises: associating an item combination and a similar item combination; and, the combination of items is generated according to the following process: acquiring historical behavior data and at least one article corresponding to the historical behavior data; aiming at each article in the at least one article, acquiring a related article and a similar article corresponding to each article according to the historical behavior data; generating the associated item combination according to each item and the associated item corresponding to each item; and generating the same-class article combination according to each article and the same-class article corresponding to each article.
Optionally, the obtaining, according to the historical behavior data, the associated item and the similar item corresponding to each item includes: according to the historical behavior data, acquiring the co-occurrence article corresponding to each article, wherein the co-occurrence article corresponding to the article is the article which commonly appears in the same historical behavior data with the article; classifying the co-occurrence articles to obtain optional associated articles and optional similar articles corresponding to each article; according to the number of times of the common occurrence of each article and the optional associated articles, selecting the associated article corresponding to each article from the optional associated articles; and selecting the similar articles corresponding to each article from the selectable similar articles according to the common occurrence frequency of each article and the selectable similar articles.
Optionally, classifying the co-occurring articles to obtain an optional associated article and an optional similar article corresponding to each article, including: judging whether the article classification to which the co-occurrence article belongs is the same as the article classification to which each article belongs; if yes, determining the co-occurrence articles as optional similar articles corresponding to each article; if not, determining that the co-occurrence articles are optional associated articles corresponding to each article.
Optionally, after obtaining the associated item corresponding to the target item, the method further includes: and adjusting the associated article corresponding to the target article according to the set article association relation.
Optionally, after obtaining the similar item corresponding to the target item, the method further includes: according to the set article similarity relation, adjusting the same kind of articles corresponding to the target article; determining the article classification of the target article, and acquiring hot-sell articles corresponding to the article classification; and according to the hot-selling articles, adjusting the similar articles corresponding to the target articles.
Optionally, after recommending the associated item corresponding to the target item to the target user, the method further includes: if the target user purchases or purchases the associated article corresponding to the target article within a preset time, acquiring the associated article corresponding to the associated article according to the article combination; and selecting an article to be recommended from the associated article corresponding to the target article and the associated article corresponding to the associated article, and recommending the article to be recommended to the target user.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an article recommendation device.
The article recommendation device of the embodiment of the invention comprises: the acquisition module is used for acquiring user behavior data, and a target user and a target object corresponding to the user behavior data; a first recommending module, configured to, if the user behavior data is first behavior data, obtain, according to a pre-generated article combination, a related article corresponding to the target article, and recommend, to the target user, the related article corresponding to the target article, where the first behavior data includes: purchase data and order data; a second recommending module, configured to, if the user behavior data is second behavior data, obtain, according to the item combination, a similar item corresponding to the target item, and recommend, to the target user, the similar item corresponding to the target item, where the second behavior data includes: search data, browse data, click data, and collection data.
Optionally, the apparatus further comprises a generating module, configured to generate the combination of items according to the following process: acquiring historical behavior data and at least one article corresponding to the historical behavior data; aiming at each article in the at least one article, acquiring a related article and a similar article corresponding to each article according to the historical behavior data; generating the associated item combination according to each item and the associated item corresponding to each item; and generating the same-class article combination according to each article and the same-class article corresponding to each article. Wherein the combination of articles comprises: related item combinations and similar item combinations.
Optionally, the generating module is further configured to: according to the historical behavior data, acquiring the co-occurrence article corresponding to each article, wherein the co-occurrence article corresponding to the article is the article which commonly appears in the same historical behavior data with the article; classifying the co-occurrence articles to obtain optional associated articles and optional similar articles corresponding to each article; according to the number of times of the common occurrence of each article and the optional associated articles, selecting the associated article corresponding to each article from the optional associated articles; and selecting the similar articles corresponding to each article from the selectable similar articles according to the common occurrence frequency of each article and the selectable similar articles.
Optionally, the generating module is further configured to: judging whether the article classification to which the co-occurrence article belongs is the same as the article classification to which each article belongs; if yes, determining the co-occurrence articles as optional similar articles corresponding to each article; if not, determining that the co-occurrence articles are optional associated articles corresponding to each article.
Optionally, the first recommending module is further configured to: and adjusting the associated article corresponding to the target article according to the set article association relation.
Optionally, the second recommending module is further configured to: according to the set article similarity relation, adjusting the same kind of articles corresponding to the target article; determining the article classification of the target article, and acquiring hot-sell articles corresponding to the article classification; and according to the hot-selling articles, adjusting the similar articles corresponding to the target articles.
Optionally, the first recommending module is further configured to: if the target user purchases or purchases the associated article corresponding to the target article within a preset time, acquiring the associated article corresponding to the associated article according to the article combination; and selecting an article to be recommended from the associated article corresponding to the target article and the associated article corresponding to the associated article, and recommending the article to be recommended to the target user.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus.
An electronic device of an embodiment of the present invention includes: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by one or more processors, the one or more processors implement the item recommendation method of the embodiment of the invention.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a computer-readable medium.
A computer-readable medium of an embodiment of the present invention has a computer program stored thereon, and the program, when executed by a processor, implements an item recommendation method of an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: the acquired user behavior data can be analyzed, if the user purchases or places an order, the related item corresponding to the item is recommended to the user, if the user searches, browses, clicks or collects the item, the similar item corresponding to the item is recommended to the user, and the related item or the similar item can be recommended to the user by combining different shopping scenes, so that the item recommendation accuracy can be improved, and better use experience is brought to the user.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of an item recommendation method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of the main process of generating a combination of items according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a main flow of an item recommendation method according to an embodiment of the invention;
FIG. 4 is a schematic diagram of the main modules of an item recommendation device according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of the main steps of an item recommendation method according to an embodiment of the present invention.
As shown in fig. 1, the main steps of the item recommendation method may include:
step S101, acquiring user behavior data, a target user corresponding to the user behavior data and a target object;
step S102, if the user behavior data is the first behavior data, acquiring a related article corresponding to the target article according to a pre-generated article combination, and recommending the related article corresponding to the target article to the target user;
step S103, if the user behavior data is the second behavior data, obtaining similar articles corresponding to the target articles according to the article combination, and recommending the similar articles corresponding to the target articles to the target user.
The user behavior data is operation data of the online shopping platform of the user, such as user search data. After the user behavior data is obtained, analyzing the user behavior data to obtain a target user and a target article corresponding to the user behavior data, wherein if the user behavior data is used for searching for a certain article for the user A, the user A is the target user, and the article is the target article.
After the user behavior data, the target user and the target article are acquired through step S101, the user behavior data may be analyzed to acquire an article that needs to be recommended to the target user. In the embodiment of the invention, the analysis is mainly performed from two aspects of the user behavior data being the first behavior data and the second behavior data. Wherein the first behavior data may include: purchase data and order data; the second behavior data may include: search data, browse data, click data, and collection data. The shopping data refers to the items being added to the shopping cart by the user, and the order data refers to the order submitted by the user. Of course, the first behavior data and the second behavior data may also include other operation data of the user, which is not limited in this embodiment of the present invention.
It should be noted that the user behavior data in the embodiment of the present invention is the current operation data of the user, that is, the current operation data of the user is analyzed, and then the item recommendation is performed.
In step S102, if the user behavior data is the first behavior data, that is, if the user behavior data is the purchase data or the order data, the associated item corresponding to the target item is acquired according to the pre-generated item combination, and then the associated item corresponding to the target item is recommended to the target user.
Wherein the combination of articles may comprise: related item combinations and similar item combinations. Two items may be considered to be related items if there is a relationship between the two items and the two items do not belong to the same item class. For example, there are relations between shoes and socks, shoes and insoles, shoes and shoe polish, and they belong to different article categories, so socks, insoles and shoe polish are all associated articles of shoes. The associated article combination refers to an associated article combination corresponding to each article, for example, socks, insoles and shoe polish are associated articles of shoes, and then the associated article combination corresponding to the shoes is the socks, the insoles and the shoe polish. If the article classifications to which two articles belong are the same, the two articles can be considered to be the same kind of article. The similar article combination refers to similar article combinations corresponding to each article, for example, the apple, the banana and the peach are similar articles, the similar article combination corresponding to the apple is the banana and the peach, and the similar article combination corresponding to the banana is the apple and the peach.
In step S102, if the target user adds the target item to the shopping cart or the user places an order to purchase the target item, the associated item corresponding to the target item is recommended to the target user. Therefore, the associated item corresponding to the target item can be queried according to the associated item combination so as to be recommended to the target user.
In step S103, if the user behavior data is the second behavior data, that is, if the user behavior data is search data, browsing data, clicking data or collection data, that is, if the target user searches, browses, clicks or collects the target item, then the similar item corresponding to the target item is recommended to the target user. Specifically, the similar items corresponding to the target item may be queried according to the similar item combinations, and then recommended to the target user.
For ease of understanding, specific examples are provided below for illustration. If the user A searches for the man business leather shoes, the user A can be recommended with the man business leather shoes of different brands and styles, such as the recommendation in a sales volume or comprehensive recommendation manner. If the user A has added the man's business leather shoes to a shopping cart or purchased them directly on their order, the user A may be recommended the associated items of the man's business leather shoes, such as insoles, socks, business belts, business handbags, etc.
According to the conventional item recommendation method, if a user orders and purchases an item, the same type of item of the item is continuously recommended, the shopping desire of the user is not large, the item recommendation accuracy is low, and if the price/performance ratio of the recommended item is better than that of the item purchased by the user, the user may order again, so that the user experience is poor. However, according to the item recommendation method provided by the embodiment of the invention, the acquired user behavior data can be analyzed, if the user purchases or places a list of items, the associated item corresponding to the item is recommended to the user, if the user searches, browses, clicks or collects the items, the similar item corresponding to the item is recommended to the user, and the associated item or the similar item can be recommended to the user in combination with different shopping scenes, so that the item recommendation accuracy can be improved, and better use experience is brought to the user.
The item combination is an important part of the item recommendation method of the embodiment of the invention. FIG. 2 is a schematic diagram of the main process of generating a combination of items according to an embodiment of the invention. As shown in fig. 2, the main process of generating the combination of items may include steps S201 to S204.
Step S201: and acquiring historical behavior data and at least one article corresponding to the historical behavior data.
The historical behavior data refers to data generated by all users operating on an online shopping platform, such as search data, browsing data, clicking data, collecting data, purchase adding data, order data and the like. At least one item corresponding to the historical behavior data refers to a specific item contained in the data, such as a searched item, a browsed item, a clicked item, a collected item, a purchased item and an ordered item. For example, the user behavior data of the latest period of time is analyzed to obtain at least one article, and the relationship of the same kind among the at least one article are determined to generate the combination of the same kind article and the combination of the related articles.
Step S202: and aiming at each article in at least one article, acquiring a related article and a similar article corresponding to each article according to historical behavior data.
After at least one item in the historical behavior data is obtained, each item can be analyzed to obtain a related item and a similar item corresponding to the item. The specific method can be as follows:
(1) and acquiring the co-occurrence articles corresponding to each article according to the historical behavior data.
The quantity of the historical behavior data is multiple, and the co-occurrence article corresponding to a certain article is the article co-occurring with the article in the same historical behavior data. For example, if a certain historical behavior data is order data, and the order data includes items W1, W2, and W3, then W1, W2, and W3 are commonly-occurring items, or W2 and W3 are co-occurring items corresponding to W1, W1 and W3 are co-occurring items corresponding to W2, and W1 and W2 are co-occurring items corresponding to W3. For another example, if a user browses, searches, collects, or clicks on multiple items over a period of time to generate historical behavior data, then the items are co-occurring items. In addition, browsing data, searching data, collecting data and click data can be divided into a class of data, and then analyzed, for example, if the user A browses the item W4, collects the item W5 and searches the item W6 within half an hour, the items W4, W5 and W6 can be considered as co-occurring items; the browsing data, the search data, the collection data, and the click data may also be analyzed separately.
After the historical behavior data is acquired, each historical behavior data can be analyzed to obtain at least one co-occurrence article corresponding to each article.
(2) And classifying the co-occurrence articles to obtain optional associated articles and optional similar articles corresponding to each article.
As already explained above, two items can be considered to be related items if there is a relationship between the two items and the two items do not belong to the same item class. In the technical scheme, if two articles appear in the same historical behavior data together and the two articles do not belong to the same article classification, the two articles can be considered as being related articles. After the historical behavior data is analyzed to obtain at least one co-occurring article corresponding to each article, each co-occurring article corresponding to the article can be judged. If a co-occurring article and the article do not belong to the same article category, the co-occurring article can be considered as an optional associated article corresponding to the article. For example, W2 and W3 are co-occurring articles corresponding to W1, the article categories corresponding to W2 and W1 are different, and W2 is an optionally associated article corresponding to W1.
In addition, it is mentioned above that two items can be considered to be of the same type if the categories of the items to which they belong are the same. In consideration, the accuracy of item recommendation is reduced by directly determining the selectable similar items corresponding to the items according to the item classification and then recommending the items. Therefore, analysis can be performed in conjunction with the co-occurring article. Specifically, after at least one co-occurring article corresponding to each article is obtained by analyzing the historical behavior data, each co-occurring article corresponding to the article may be determined. If a co-occurrence article and the article belong to the same article category, the co-occurrence article can be considered as an optional similar article corresponding to the article. For example, W2 and W3 are co-occurring articles corresponding to W1, the article categories corresponding to W3 and W1 are the same, and then W3 is an optional homogeneous article corresponding to W1.
Therefore, at least one co-occurrence article corresponding to each article is classified, and the optional related article and the optional similar article corresponding to each article can be obtained. Specifically, whether the article classification to which each co-occurrence article corresponding to each article belongs is the same as the article classification to which the article belongs is judged; if yes, determining the co-occurrence article as the optional similar article corresponding to the article; if not, determining that the co-occurrence article is the optional associated article corresponding to the article.
(3) According to the common occurrence times of each article and the selectable associated articles, selecting the associated article corresponding to each article from the selectable associated articles; and selecting the similar articles corresponding to each article from the selectable similar articles according to the common occurrence times of each article and the selectable similar articles.
If the number of times that a certain item and a certain optional associated item corresponding to the item appear together is larger, it is indicated that the item and the optional associated item have stronger association, that is, the user has a higher interest level in the optional associated item when purchasing or purchasing the item. Therefore, after determining the optional associated item corresponding to each item, the number of times that the item and each optional associated item corresponding to the item co-occur can be counted. And then, selecting the selectable associated item with the highest common occurrence frequency as the associated item corresponding to the item. For example, the number of associated articles corresponding to the article is set to 5, and articles W2, W4, W5, W6, and W7 that appear 5 times before the common occurrence are selected as associated articles corresponding to article W1 from selectable associated articles corresponding to article W1. Of course, the number of the associated items corresponding to the item may be set according to actual requirements, which is not limited in the embodiment of the present invention.
Similarly, if the number of times that an item and a selectable similar item corresponding to the item appear together is larger, it indicates that the item and the selectable similar item have a stronger association, that is, the user has a higher interest level in the selectable similar item when browsing, searching, collecting, or clicking the item. Therefore, after determining the selectable similar items corresponding to each item, the number of times that the item and each selectable similar item corresponding to the item commonly appear can be counted. Then, the selectable similar articles with the common occurrence times ranked at the top are selected as the similar articles corresponding to the articles. For example, the number of similar articles corresponding to the article is set to be 4, and articles W3, W8, W9, and W10 which appear 4 times before the common occurrence are selected from selectable similar articles corresponding to article W1 as similar articles corresponding to article W1. Of course, the number of similar articles corresponding to the article may be set according to actual requirements, which is not limited in the embodiment of the present invention.
Step S203: generating a related item combination according to each item and the related item corresponding to each item; step S204: and generating a similar article combination according to each article and the similar article corresponding to each article.
After the associated item corresponding to each item is obtained through the above steps S201 to S202, an associated item combination corresponding to each item may be generated. Similarly, after similar articles corresponding to each article are obtained, similar article combinations corresponding to each article can be generated.
In addition, in the embodiment of the invention, historical behavior data can be acquired regularly, and then the related item combination and the similar item combination are updated. In addition, in the embodiment of the present invention, an association relationship between the articles may also be preset, for example, if the sports shoes and the sports socks have a strong association and belong to different article categories, it is considered that an association relationship exists between all the articles under the article category to which the sports shoes belong and all the articles under the article category to which the sports socks belong, and then all the articles under the article category to which the sports socks belong may be regarded as the associated articles corresponding to the sports shoes.
Step S201 to step S204, the historical behavior data is analyzed to obtain a related article combination and a similar article combination, so that after the user behavior data, the target user and the target article are obtained, under the condition that the user behavior data is the first behavior data, the related article corresponding to the target article can be obtained according to the related article combination, and then recommended to the target user; and under the condition that the user behavior data is the second behavior data, acquiring similar articles corresponding to the target article according to the similar article combination, and recommending the similar articles to the target user.
As an embodiment of the present invention, after obtaining the associated item corresponding to the target item, the item recommendation method may further include: and adjusting the associated article corresponding to the target article according to the set article association relation.
As mentioned above, the association relationship between the objects may be preset, and then the associated object corresponding to the target object may be adjusted according to the set association relationship between the objects. The advantage of doing so is that, if new products appear, there is less data about the new products in the historical behavior data, that is, there may not be new products in the item association combination, and further, the popularization of the new products may be affected. If the association relation between the preset objects is utilized, the associated objects of the target object are adjusted, object recommendation only according to historical behavior data is avoided, new product popularization is facilitated, and better experience can be brought to a user. In addition, the set item association relationship can be understood as strong association between the designated items, so that the item recommendation accuracy can be further improved by adjusting the associated items corresponding to the target items by using the set item association relationship.
As an embodiment of the present invention, after obtaining similar items corresponding to a target item, the item recommendation method may further include: according to the set article similarity relation, adjusting the similar articles corresponding to the target article; determining the article classification of the target article, and acquiring hot-sell articles corresponding to the article classification; and according to the hot-sold articles, adjusting the similar articles corresponding to the target articles.
Specifically, the article similarity relationship may be preset, for example, the categories of the articles to which the apples, the oranges and the oranges belong are the same, but the oranges and the oranges may be set to have strong similarity, and then the similar articles corresponding to the target article are adjusted according to the set article similarity relationship. The advantage of doing so is that, if new products appear, there is less data about the new products in the historical behavior data, that is, there may not be new products in the combination of the same kind of articles, and then the popularization of the new products will be affected. If the same-kind relation of the objects is preset, the same-kind objects of the target object are adjusted, object recommendation only according to historical behavior data is avoided, new product popularization is facilitated, and better experience can be brought to users. In addition, the set article similarity can be understood as strong similarity between the specified articles, so that the set article similarity is utilized to adjust the similar articles corresponding to the target article, and the article recommendation accuracy can be further improved.
In addition, after the similar articles corresponding to the target articles are obtained, the article classification to which the target articles belong can be determined, hot-sold articles corresponding to the article classification to which the target articles belong are obtained, and then the similar articles corresponding to the target articles are adjusted according to the hot-sold articles. For example, if the user a searches for the business leather shoes for men and recommends the business leather shoes for men of different brands and styles to the user a, the recommendation can be made by combining the similar article combination corresponding to the business leather shoes for men and the sales volume of the business leather shoes for men. Of course, the recommendation may be performed in combination with the sales amount, and may also be performed in combination with the comprehensive ranking of the items, which is not limited in the embodiment of the present invention.
As an embodiment of the present invention, after recommending a related item corresponding to a target item to a target user, the item recommendation method may further include: if the target user additionally purchases or purchases the associated articles corresponding to the target articles within the preset time, acquiring the associated articles corresponding to the associated articles according to the article combination; and selecting an article to be recommended from the associated article corresponding to the target article and the associated article corresponding to the associated article, and recommending the article to be recommended to the target user.
After the target user purchases or adds the target item, the associated item corresponding to the target item is recommended to the target user. For convenience of understanding, the associated items corresponding to the target items are assumed to be B1, B2, B3, B4 and B5. If the target user buys or purchases the recommended associated item B1 within a preset time (which may be, but is not limited to, half an hour, and may be specifically set according to actual needs), then the item to be recommended continues to be recommended to the target user. The object to be recommended is selected from the associated objects B2, B3, B4 and B5 corresponding to the target object and the associated objects C1, C2, C3 and C4 corresponding to the associated object B1. Specifically, half of B2, B3, B4 and B5 and half of C1, C2, C3 and C4 may be selected as the items to be recommended, and of course, the specific selection number and the selection rule may be set according to actual requirements. By analogy, if the target user purchases or purchases the recommended associated item B1 and then continues to recommend items B2, B3, C1 and C2 to the target user, and the target user purchases or purchases item B2 within a preset time (which may be, but is not limited to, half an hour, and may be specifically set according to actual needs), then the item that continues to be recommended to the target user is selected from the three corresponding associated items, namely, the target item, B1 and B2, until the target user leaves the online shopping platform.
The method has the advantages that if the associated articles corresponding to the target articles are continuously recommended to the target user, the recommended article categories are not updated, and poor shopping experience is brought to the user; if the associated item corresponding to the associated item is continuously recommended to the target user, the associated item corresponding to the target item is ignored, and the shopping experience of the user is also influenced. Therefore, after the target user purchases or purchases the recommended related item, the item recommendation can be continued to the target user in combination with the related item corresponding to the target item and the related item corresponding to the related item. In addition, when the user logs in the online shopping platform next time, recommended articles when the user leaves last time can be displayed on the interface, and better use experience is brought to the user.
Fig. 3 is a schematic diagram of a main flow of an item recommendation method according to an embodiment of the present invention.
As shown in fig. 3, the main flow of the item recommendation method may include:
step S301, acquiring user behavior data, a target user corresponding to the user behavior data and a target object;
step S302, determining whether the user behavior data is the first behavior data, if so, performing step S303, and if not, performing step S307;
step S303, acquiring a related article corresponding to the target article according to a pre-generated related article combination, and then adjusting the related article corresponding to the target article according to the set article association relation;
step S304, recommending the associated article corresponding to the target article to the target user;
step S305, if the target user purchases or purchases the associated article corresponding to the target article within the preset time, acquiring the associated article corresponding to the associated article according to the associated article combination;
step S306, selecting an article to be recommended from the associated article corresponding to the target article and the associated article corresponding to the associated article, and recommending the article to be recommended to the target user;
step S307, judging whether the user behavior data is second behavior data, if so, executing step S308;
step S308, according to the pre-generated similar article combination, obtaining similar articles corresponding to the target article, and recommending the similar articles corresponding to the target article to the target user;
step S309, adjusting the same kind of articles corresponding to the target article according to the set article similarity relation;
step S310, determining the article classification of the target article, acquiring a hot-sell article corresponding to the article classification, and then adjusting the similar article corresponding to the target article according to the hot-sell article.
Wherein the first behavior data may include: purchase data and order data; the second behavior data may include: search data, browse data, click data, and collection data. Also, the generation process of the associated item combination and the like item combination has been described above through steps S201 to S204, and will not be described here again. And after recommending the item to be recommended to the target user in step S306, if the target user purchases or purchases the item to be recommended, the item recommendation may be continued to the target user until the target user leaves the online shopping platform, which is described in detail above and will not be repeated here. The execution sequence of step S309 and step S310 may be adjusted according to actual situations, and is not limited in this embodiment of the present invention. It should be noted that the user behavior data may also be user registration data or other data unrelated to user shopping, and therefore may end in the case where it is determined that the user behavior data is not the first behavior data and the second behavior data.
According to the item recommendation method provided by the embodiment of the invention, the acquired user behavior data can be analyzed, if the user purchases or places a list of items, the associated items corresponding to the items are recommended to the user, if the user searches, browses, clicks or collects the items, the similar items corresponding to the items are recommended to the user, and the associated items or the similar items can be recommended to the user by combining different shopping scenes, so that the item recommendation accuracy can be improved, and better use experience is brought to the user.
Fig. 4 is a schematic diagram of main blocks of an item recommendation device according to an embodiment of the present invention. As shown in fig. 4, the main modules of the item recommendation device 400 may include: an acquisition module 401, a first recommendation module 402 and a second recommendation module 403.
Wherein the obtaining module 401 may be configured to: acquiring user behavior data, and a target user and a target object corresponding to the user behavior data; the first recommendation module 402 is operable to: if the user behavior data is the first behavior data, acquiring a related article corresponding to the target article according to a pre-generated article combination, and recommending the related article corresponding to the target article to the target user; the second recommendation module 403 may be used to: and if the user behavior data is the second behavior data, acquiring similar articles corresponding to the target article according to the article combination, and recommending the similar articles corresponding to the target article to the target user. Wherein the first behavior data may include: purchase data and order data; the second behavior data may include: search data, browse data, click data, and collection data.
As can be seen from fig. 4, the item recommendation apparatus 400 may further include a generation module 404. The generation module 404 may be configured to generate the combination of items according to the following process: acquiring historical behavior data and at least one article corresponding to the historical behavior data; aiming at each article in at least one article, acquiring a related article and a similar article corresponding to each article according to historical behavior data; generating a related item combination according to each item and the related item corresponding to each item; and generating a similar article combination according to each article and the similar article corresponding to each article. Wherein the combination of articles may comprise: related item combinations and similar item combinations.
As an embodiment of the present invention, the generating module 404 may further be configured to: acquiring a co-occurrence article corresponding to each article according to the historical behavior data, wherein the co-occurrence article corresponding to the article is an article which commonly appears in the same historical behavior data with the article; classifying the co-occurrence articles to obtain optional associated articles and optional similar articles corresponding to each article; according to the common occurrence times of each article and the selectable associated articles, selecting the associated article corresponding to each article from the selectable associated articles; and selecting the similar articles corresponding to each article from the selectable similar articles according to the common occurrence times of each article and the selectable similar articles.
As an embodiment of the present invention, the generating module 404 may further be configured to: judging whether the article classification to which the co-occurrence article belongs is the same as the article classification to which each article belongs; if yes, determining the co-occurrence articles as optional similar articles corresponding to each article; if not, determining that the co-occurrence articles are optional associated articles corresponding to each article.
As an embodiment of the present invention, the first recommending module 402 may further be configured to: and adjusting the associated article corresponding to the target article according to the set article association relation.
As an embodiment of the present invention, the second recommending module 403 may be further configured to: according to the set article similarity relation, adjusting the similar articles corresponding to the target article; determining the article classification of the target article, and acquiring hot-sell articles corresponding to the article classification; and according to the hot-sold articles, adjusting the similar articles corresponding to the target articles.
As an embodiment of the present invention, the first recommending module 402 may further be configured to: if the target user additionally purchases or purchases the associated articles corresponding to the target articles within the preset time, acquiring the associated articles corresponding to the associated articles according to the article combination; and selecting an article to be recommended from the associated article corresponding to the target article and the associated article corresponding to the associated article, and recommending the article to be recommended to the target user.
According to the item recommendation device provided by the embodiment of the invention, the acquired user behavior data can be analyzed, if a user purchases or places an order, the associated item corresponding to the item is recommended to the user, if the user searches, browses, clicks or collects the item, the similar item corresponding to the item is recommended to the user, and the associated item or the similar item can be recommended to the user by combining different shopping scenes, so that the item recommendation accuracy can be improved, and better use experience is brought to the user.
Fig. 5 illustrates an exemplary system architecture 500 of an item recommendation method or apparatus to which embodiments of the invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server providing various services, for example, a background management server (for example only) providing support in the process of recommending items by using the terminal devices 501, 502, 503 by a user; as another example, the server 505 may perform item recommendation in accordance with embodiments of the present invention.
It should be noted that the item recommendation method provided in the embodiment of the present invention is generally executed by the server 505, and accordingly, the item recommendation apparatus is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an acquisition module, a first recommendation module, and a second recommendation module. The names of the modules do not limit the modules themselves in some cases, for example, the acquiring module may also be described as a module for acquiring user behavior data, target users corresponding to the user behavior data, and target articles.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring user behavior data, and a target user and a target object corresponding to the user behavior data; if the user behavior data is first behavior data, acquiring a related article corresponding to the target article according to a pre-generated article combination, and recommending the related article corresponding to the target article to the target user, wherein the first behavior data comprises: purchase data and order data; if the user behavior data is second behavior data, obtaining similar articles corresponding to the target article according to the article combination, and recommending the similar articles corresponding to the target article to the target user, wherein the second behavior data comprises: search data, browse data, click data, and collection data.
According to the technical scheme of the embodiment of the invention, the acquired user behavior data can be analyzed, if the user purchases or places a list of articles, the related articles corresponding to the articles are recommended to the user, if the user searches, browses, clicks or collects the articles, the similar articles corresponding to the articles are recommended to the user, and the related articles or the similar articles can be recommended to the user by combining different shopping scenes, so that the article recommendation accuracy can be improved, and better use experience is brought to the user.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An item recommendation method, comprising:
acquiring user behavior data, and a target user and a target object corresponding to the user behavior data;
if the user behavior data is first behavior data, acquiring a related article corresponding to the target article according to a pre-generated article combination, and recommending the related article corresponding to the target article to the target user, wherein the first behavior data comprises: purchase data and order data;
if the user behavior data is second behavior data, obtaining similar articles corresponding to the target article according to the article combination, and recommending the similar articles corresponding to the target article to the target user, wherein the second behavior data comprises: search data, browse data, click data, and collection data.
2. The method of claim 1, wherein the combination of items comprises: associating an item combination and a similar item combination; and the number of the first and second groups,
the combination of items is generated according to the following process:
acquiring historical behavior data and at least one article corresponding to the historical behavior data;
aiming at each article in the at least one article, acquiring a related article and a similar article corresponding to each article according to the historical behavior data;
generating the associated item combination according to each item and the associated item corresponding to each item;
and generating the same-class article combination according to each article and the same-class article corresponding to each article.
3. The method according to claim 2, wherein the obtaining of the associated item and the similar item corresponding to each item according to the historical behavior data comprises:
according to the historical behavior data, acquiring the co-occurrence article corresponding to each article, wherein the co-occurrence article corresponding to the article is the article which commonly appears in the same historical behavior data with the article;
classifying the co-occurrence articles to obtain optional associated articles and optional similar articles corresponding to each article;
according to the number of times of the common occurrence of each article and the optional associated articles, selecting the associated article corresponding to each article from the optional associated articles;
and selecting the similar articles corresponding to each article from the selectable similar articles according to the common occurrence frequency of each article and the selectable similar articles.
4. The method of claim 3, wherein classifying the co-occurring articles to obtain the selectable associated articles and the selectable homogeneous articles corresponding to each article comprises:
judging whether the article classification to which the co-occurrence article belongs is the same as the article classification to which each article belongs;
if yes, determining the co-occurrence articles as optional similar articles corresponding to each article;
if not, determining that the co-occurrence articles are optional associated articles corresponding to each article.
5. The method according to claim 1, wherein after obtaining the associated item corresponding to the target item, the method further comprises:
and adjusting the associated article corresponding to the target article according to the set article association relation.
6. The method according to claim 1, wherein after obtaining the similar item corresponding to the target item, the method further comprises:
according to the set article similarity relation, adjusting the same kind of articles corresponding to the target article; and the number of the first and second groups,
determining the article classification of the target article, and acquiring hot-sell articles corresponding to the article classification;
and according to the hot-selling articles, adjusting the similar articles corresponding to the target articles.
7. The method of claim 1, wherein after recommending the associated item corresponding to the target item to the target user, the method further comprises:
if the target user purchases or purchases the associated article corresponding to the target article within a preset time, acquiring the associated article corresponding to the associated article according to the article combination;
and selecting an article to be recommended from the associated article corresponding to the target article and the associated article corresponding to the associated article, and recommending the article to be recommended to the target user.
8. An item recommendation device, comprising:
the acquisition module is used for acquiring user behavior data, and a target user and a target object corresponding to the user behavior data;
a first recommending module, configured to, if the user behavior data is first behavior data, obtain, according to a pre-generated article combination, a related article corresponding to the target article, and recommend, to the target user, the related article corresponding to the target article, where the first behavior data includes: purchase data and order data;
a second recommending module, configured to, if the user behavior data is second behavior data, obtain, according to the item combination, a similar item corresponding to the target item, and recommend, to the target user, the similar item corresponding to the target item, where the second behavior data includes: search data, browse data, click data, and collection data.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110489879.0A CN113065932A (en) | 2021-05-06 | 2021-05-06 | Article recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110489879.0A CN113065932A (en) | 2021-05-06 | 2021-05-06 | Article recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113065932A true CN113065932A (en) | 2021-07-02 |
Family
ID=76568128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110489879.0A Pending CN113065932A (en) | 2021-05-06 | 2021-05-06 | Article recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065932A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482065A (en) * | 2022-09-22 | 2022-12-16 | 保利和悦生活科技服务有限公司 | Shopping data sharing method and system based on big data and electronic mall platform |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013126648A1 (en) * | 2012-02-22 | 2013-08-29 | Cobrain Company | Methods and apparatus for recommending products and services |
| CN108009897A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing |
| CN108153792A (en) * | 2016-12-02 | 2018-06-12 | 阿里巴巴集团控股有限公司 | A kind of data processing method and relevant apparatus |
| CN108665333A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, electronic equipment and storage medium |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| CN109034935A (en) * | 2018-06-06 | 2018-12-18 | 平安科技（深圳）有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN110298716A (en) * | 2018-03-22 | 2019-10-01 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN110473043A (en) * | 2018-05-11 | 2019-11-19 | 北京京东尚科信息技术有限公司 | A kind of item recommendation method and device based on user behavior |
| CN111125460A (en) * | 2019-12-24 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
| CN111260447A (en) * | 2020-02-11 | 2020-06-09 | 深圳前海达闼云端智能科技有限公司 | Commodity recommendation method and device for vending robot |
| CN111310028A (en) * | 2020-01-19 | 2020-06-19 | 浙江连信科技有限公司 | Recommendation method and device based on psychological characteristics |
| CN111339401A (en) * | 2020-02-07 | 2020-06-26 | 北京明略软件系统有限公司 | Method and device for recommending articles, computer storage medium and terminal |
| CN112116426A (en) * | 2020-09-21 | 2020-12-22 | 中国建设银行股份有限公司 | Method and device for pushing article information |
| CN112330382A (en) * | 2020-05-28 | 2021-02-05 | 北京沃东天骏信息技术有限公司 | Item recommendation method and device, computing equipment and medium |
-
2021
- 2021-05-06 CN CN202110489879.0A patent/CN113065932A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013126648A1 (en) * | 2012-02-22 | 2013-08-29 | Cobrain Company | Methods and apparatus for recommending products and services |
| CN108153792A (en) * | 2016-12-02 | 2018-06-12 | 阿里巴巴集团控股有限公司 | A kind of data processing method and relevant apparatus |
| CN108665333A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, electronic equipment and storage medium |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| CN108009897A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing |
| CN110298716A (en) * | 2018-03-22 | 2019-10-01 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN110473043A (en) * | 2018-05-11 | 2019-11-19 | 北京京东尚科信息技术有限公司 | A kind of item recommendation method and device based on user behavior |
| CN109034935A (en) * | 2018-06-06 | 2018-12-18 | 平安科技（深圳）有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN111125460A (en) * | 2019-12-24 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
| CN111310028A (en) * | 2020-01-19 | 2020-06-19 | 浙江连信科技有限公司 | Recommendation method and device based on psychological characteristics |
| CN111339401A (en) * | 2020-02-07 | 2020-06-26 | 北京明略软件系统有限公司 | Method and device for recommending articles, computer storage medium and terminal |
| CN111260447A (en) * | 2020-02-11 | 2020-06-09 | 深圳前海达闼云端智能科技有限公司 | Commodity recommendation method and device for vending robot |
| CN112330382A (en) * | 2020-05-28 | 2021-02-05 | 北京沃东天骏信息技术有限公司 | Item recommendation method and device, computing equipment and medium |
| CN112116426A (en) * | 2020-09-21 | 2020-12-22 | 中国建设银行股份有限公司 | Method and device for pushing article information |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482065A (en) * | 2022-09-22 | 2022-12-16 | 保利和悦生活科技服务有限公司 | Shopping data sharing method and system based on big data and electronic mall platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108664513B (en) | Method, device and equipment for pushing keywords | |
| US8626602B2 (en) | Consumer shopping and purchase support system and marketplace | |
| US8285602B1 (en) | System for recommending item bundles | |
| CN106708821A (en) | User personalized shopping behavior-based commodity recommendation method | |
| US20120005044A1 (en) | System And Method To Provide A Table Of Products Based On Ranked User Specified Product Attributes | |
| CN105718184A (en) | Data processing method and apparatus | |
| CN108198019A (en) | Item recommendation method and device, storage medium, electronic equipment | |
| WO2012009180A1 (en) | Value maximizing recommendation systems | |
| US20160019621A1 (en) | Review based navigation and product discovery platform | |
| CN110298716A (en) | Information-pushing method and device | |
| CN112528153B (en) | Content recommendation method, device, apparatus, storage medium, and program product | |
| CN110111167A (en) | A kind of method and apparatus of determining recommended | |
| CN111914188A (en) | Method, system, device and storage medium for selecting recommendation target user | |
| CN111311294A (en) | Data processing method, device, medium and electronic equipment | |
| CN106776697A (en) | Content recommendation method and device | |
| CN112116426A (en) | Method and device for pushing article information | |
| CN111626804A (en) | Commodity recommendation method and device, electronic equipment and computer readable medium | |
| US9552425B2 (en) | System and method for determining query aspects at appropriate category levels | |
| WO2013096749A2 (en) | System and method for generating user recommendations | |
| CN113065932A (en) | Article recommendation method and device | |
| US20230005051A1 (en) | Context-based personalization of user interfaces | |
| CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
| CN113077319A (en) | Dynamic recommendation method and device for micro detail page | |
| CN110827044A (en) | Method and device for extracting user interest mode | |
| CN110659919A (en) | Data matching method, device, medium and electronic equipment |
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 |