CN116957727A - Commodity recommendation method and device - Google Patents
Commodity recommendation method and device Download PDFInfo
- Publication number
- CN116957727A CN116957727A CN202310902659.5A CN202310902659A CN116957727A CN 116957727 A CN116957727 A CN 116957727A CN 202310902659 A CN202310902659 A CN 202310902659A CN 116957727 A CN116957727 A CN 116957727A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- label
- preset
- recommended
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012545 processing Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 description 15
- 241000220225 Malus Species 0.000 description 12
- 238000004891 communication Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 102000004169 proteins and genes Human genes 0.000 description 5
- 108090000623 proteins and genes Proteins 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000843 powder Substances 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 235000021016 apples Nutrition 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 235000013365 dairy product Nutrition 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 235000014438 salad dressings Nutrition 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 230000004580 weight loss Effects 0.000 description 1
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
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A commodity recommendation method and device relate to the field of commodity recommendation; the method comprises the following steps: acquiring a commodity label of a commodity to be recommended, wherein the commodity label comprises a commodity color, a commodity producing place and a commodity brand; inputting the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises a corresponding relation between commodity labels and first user labels; matching a user corresponding to the first user tag in a preset user image library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user portrait library comprises the corresponding relation between the user and the second user tag; pushing the commodity to be recommended to the user. By implementing the technical scheme provided by the application, the commodity recommendation efficiency of the cross-border electronic commerce platform can be improved.
Description
Technical Field
The application relates to the field of commodity recommendation, in particular to a commodity recommendation method and device.
Background
With the popularity of online shopping, many online shopping platforms push goods that users prefer to purchase by various methods.
At present, in order to better improve commodity recommendation accuracy, an algorithm for recommending based on commodity attributes is complex, and a large amount of commodity data and user data are required to be input; in addition, in the calculation process, a large amount of calculation resources and time are needed due to large data volume and parameter adjustment, and high requirements are also made on the performance of the calculation equipment; in the cross-border electronic commerce platform, the commodity number is not more than that of the domestic electronic commerce platform, so that the commodity data can be provided relatively less, and the volume of the transaction is relatively less. Under the condition, how to further improve commodity recommendation efficiency by using the cross-border electronic commerce platform becomes a problem to be solved urgently.
Therefore, a commodity recommendation method and apparatus are needed.
Disclosure of Invention
The application provides a commodity recommendation method and device, which can improve commodity recommendation efficiency of a cross-border electronic commerce platform.
The application provides a commodity recommending method in a first aspect, which is applied to a server and comprises the following steps: acquiring a commodity label of a commodity to be recommended, wherein the commodity label comprises a commodity color, a commodity producing place and a commodity brand; inputting the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises a corresponding relation between commodity labels and first user labels; matching a user corresponding to the first user tag in a preset user image library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user portrait library comprises the corresponding relation between the user and the second user tag; pushing the commodity to be recommended to the user.
By adopting the technical scheme, the server can match the users with the corresponding labels for the commodities to be recommended through the two groups of corresponding relations, compared with the complex recommendation algorithm in the existing cross-border e-commerce platform, the calculation steps of the server in the process are relatively fewer, and the method with relatively fewer calculation steps in the scene of recommending the commodities by the cross-border e-commerce can be used for recommending the commodities more rapidly and pertinently although the accuracy is not very high.
Optionally, the acquiring the label of the to-be-recommended commodity specifically includes any one of the following modes: acquiring an article label of the article to be recommended from an article detail page of the article to be recommended; in response to an input operation by a user, the input operation is for inputting a commodity label of a commodity to be recommended.
By adopting the technical scheme, the server can obtain the commodity label in two ways, namely, obtaining commodity parameters and introduction in the commodity detail page so as to obtain the commodity label; another is to obtain the merchandise tag by way of user input.
Optionally, before the user corresponding to the first user tag is matched in the preset user image library, constructing the preset user image library specifically includes: acquiring information of a plurality of commodities purchased by a user, wherein the plurality of commodities comprise a first commodity and a second commodity; acquiring a plurality of commodity labels of a first commodity and acquiring a plurality of commodity labels of a second commodity; confirming that the first commodity label and the second commodity label are labels of users, wherein the plurality of commodity labels of the first commodity comprise the first commodity label and the second commodity label, and the plurality of commodity labels of the second commodity comprise the first commodity label and the second commodity label; constructing a preset user portrait library; the preset user portrait library comprises the corresponding relation between the user and the first commodity label and the corresponding relation between the user and the second commodity label.
By adopting the technical scheme, the server can obtain the corresponding commodity label according to the commodity purchased by each user; and (3) corresponding each user and the repeated commodity labels of the purchased commodities respectively, and establishing a corresponding relation, so as to construct a preset user portrait library, namely, the portrait library stores the corresponding relation between a plurality of users and the commodity labels with the preferences respectively.
Optionally, the acquiring information of the plurality of commodities purchased by the user specifically includes any one of the following modes: acquiring information of a plurality of commodities purchased by a user in a first preset time period every interval; and when the commodity purchasing operation of the user is monitored, acquiring information of a plurality of commodities purchased by the user in a first preset time period.
By adopting the technical scheme, the server can automatically acquire the commodity information purchased by the user and the user at intervals of a set period so as to automatically update the user portrait library; the user image library can be updated in time when the user makes purchasing behavior.
Optionally, before inputting the commodity label into the preset commodity label library, constructing the preset commodity label library specifically includes: acquiring information of a plurality of users who purchase goods to be recommended, wherein the plurality of users comprise a first user and a second user; acquiring a plurality of user tags of a first user, and acquiring a plurality of user tags of a second user; confirming that a third user tag and a fourth user tag are tags of goods to be recommended, wherein the plurality of user tags of the first user comprise the third user tag and the fourth user tag, and the plurality of user tags of the second user comprise the third user tag and the fourth user tag; constructing a preset association library; the preset association library comprises the corresponding relation between the label of the commodity to be recommended and the third user label and the corresponding relation between the label of the commodity to be recommended and the fourth user label.
By adopting the technical scheme, the server can correlate the label of the commodity to be recommended with the user label of the user who has purchased the commodity related to the commodity to be recommended, the corresponding relationship between the label of the commodity to be recommended and the user label is constructed, and then the preset correlation library is constructed.
Optionally, the acquiring information of the plurality of users purchasing the commodity to be recommended specifically includes any one of the following modes: acquiring information of multiple users purchasing goods to be recommended in a second preset time period every second preset time period; and responding to the operation of purchasing the commodity to be recommended by the multiple users, and acquiring information of the multiple users.
By adopting the technical scheme, the server can automatically update the preset association library every a preset time interval; the preset association library can also be updated when a user purchases goods to be recommended.
Optionally, pushing the commodity to be recommended to the user specifically includes: acquiring a historical ordering time period of a user, wherein the historical ordering time period is a time period in which the number of times of ordering and purchasing commodities by the user exceeds a preset number of times; and pushing the commodity to be recommended to the user in the historical ordering time period.
By adopting the technical scheme, the server can push the commodity to be recommended to the user according to the ordering preference time period of the user, and accords with the ordering habit of the user so as to improve the purchase probability of the user for the commodity to be recommended.
The application provides a commodity recommending device in a second aspect, wherein the device is a server, and a processor comprises an acquisition unit and a processing unit;
the acquisition unit is used for acquiring commodity labels of the commodities to be recommended, wherein the commodity labels comprise commodity colors, commodity places and commodity brands;
the processing unit is used for inputting the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises a corresponding relation between commodity labels and first user labels; matching a user corresponding to the first user tag in a preset user image library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user portrait library comprises the corresponding relation between the user and the second user tag; pushing the commodity to be recommended to the user.
Optionally, the acquiring unit is configured to acquire a label of the to-be-recommended commodity, and specifically includes any one of the following modes: acquiring an article label of the article to be recommended from an article detail page of the article to be recommended; in response to an input operation by a user, the input operation is for inputting a commodity label of a commodity to be recommended.
Optionally, the acquiring unit is configured to acquire information of a plurality of articles purchased by a user, where the plurality of articles includes a first article and a second article; acquiring a plurality of commodity labels of a first commodity and acquiring a plurality of commodity labels of a second commodity; the processing unit is used for confirming that the first commodity label and the second commodity label are labels of users, wherein the plurality of commodity labels of the first commodity comprise the first commodity label and the second commodity label, and the plurality of commodity labels of the second commodity comprise the first commodity label and the second commodity label; constructing a preset user portrait library; the preset user portrait library comprises the corresponding relation between the user and the first commodity label and the corresponding relation between the user and the second commodity label.
Optionally, the acquiring unit is configured to acquire information of multiple commodities purchased by a user, and specifically includes any one of the following modes: acquiring information of a plurality of commodities purchased by a user in a first preset time period every interval; and when the commodity purchasing operation of the user is monitored, acquiring information of a plurality of commodities purchased by the user in a first preset time period.
Optionally, the acquiring unit is configured to acquire information of a plurality of users who purchase the commodity to be recommended, where the plurality of users includes a first user and a second user; acquiring a plurality of user tags of a first user, and acquiring a plurality of user tags of a second user; the processing unit is used for confirming that the third user tag and the fourth user tag are tags of the commodity to be recommended, the plurality of user tags of the first user comprise the third user tag and the fourth user tag, and the plurality of user tags of the second user comprise the third user tag and the fourth user tag; constructing a preset association library; the preset association library comprises the corresponding relation between the label of the commodity to be recommended and the third user label and the corresponding relation between the label of the commodity to be recommended and the fourth user label.
Optionally, the acquiring unit is configured to acquire information of multiple users purchasing the commodity to be recommended, and specifically includes any one of the following modes: acquiring information of multiple users purchasing goods to be recommended in a second preset time period every second preset time period; and responding to the operation of purchasing the commodity to be recommended by the multiple users, and acquiring information of the multiple users.
Optionally, the acquiring unit is configured to acquire a historical ordering time period of the user, where the historical ordering time period is a time period when the number of times of ordering and purchasing the commodity by the user exceeds a preset number of times; the processing unit is used for pushing the commodity to be recommended to the user in the historical ordering time period.
The present application provides in a third aspect an electronic device comprising a processor, a memory for storing instructions, a user interface and a network interface for communicating with other devices, the processor for executing instructions stored in the memory to cause the electronic device to perform any one of the possible implementation methods of the first aspect or the first aspect above.
The present application provides in a fourth aspect a computer readable storage medium storing a computer program for execution by a processor as described above or any one of the possible implementation manners of the first aspect.
In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. compared with the complex recommendation algorithm in the existing cross-border e-commerce platform, the calculation steps of the server in the process are relatively fewer, and the method with relatively fewer calculation steps in the scene of recommending the commodity by the cross-border e-commerce can be used for recommending the commodity in a targeted manner more quickly although the accuracy is not very high.
2. The server can obtain corresponding commodity labels according to the commodities purchased by each user; and (3) corresponding each user and the repeated commodity labels of the purchased commodities respectively, and establishing a corresponding relation, so as to construct a preset user portrait library, namely, the portrait library stores the corresponding relation between a plurality of users and the commodity labels with the preferences respectively.
3. The server can associate the label of the commodity to be recommended with the user label of the user who has purchased the commodity related to the commodity to be recommended, and the corresponding relation between the label of the commodity to be recommended and the user label is constructed, so that a preset association library is constructed.
Drawings
Fig. 1 is a schematic flow chart of a commodity recommendation method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a commodity recommendation device according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Reference numerals illustrate: 201. an acquisition unit; 202. a processing unit; 300. an electronic device; 301. a processor; 302. a communication bus; 303. a user interface; 304. a network interface; 305. a memory.
Detailed Description
In order that those skilled in the art will better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments.
In describing embodiments of the present application, words such as "for example" or "for example" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "such as" or "for example" in embodiments of the application should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.
In the description of embodiments of the application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Compared with the domestic electronic commerce platform, the number of commodities on the cross-border electronic commerce platform is relatively small, and the user scale is relatively small, so that pushing accuracy as the domestic electronic commerce platform is not required to be pursued too much when commodity recommendation is carried out. On the other hand, due to small commodity quantity and user quantity, the existing complex recommendation algorithm can cause the problem of inaccurate pushing due to insufficient data; and the cross-border e-commerce platform can adopt a simpler method to recommend so as to increase the commodity exposure and promote the improvement of the transaction amount of the platform.
Therefore, the commodity recommendation method can improve commodity recommendation efficiency of the cross-border electronic commerce platform.
It should be noted that, the user mentioned in the present application refers to a person who uses the e-commerce platform to make online shopping; and the manager refers to a worker on the e-commerce platform side.
The application provides a commodity recommending method, referring to fig. 1, fig. 1 is a flow diagram of a commodity recommending method provided by the embodiment of the application, which is applied to a commodity recommending server of a cross-border e-commerce platform, wherein the server comprises a processor, a memory and a network communication module, such as a desktop computer. The embodiment of the application takes a scene that a desktop computer carries out commodity recommendation on a cross-border electronic commerce platform as an example. The method includes steps S101 to S104.
S101, acquiring a commodity label of a commodity to be recommended, wherein the commodity label comprises a commodity color, a commodity place of origin and a commodity brand.
In the above step, the server obtains a tag of the item to be recommended, the tag including a number of attributes of the item.
For example, the server obtains a label of an apple to be recommended, the label of the apple being fruit, crispy, produced from the city X and brand XX.
In one possible implementation, step S101 specifically includes: the method for acquiring the label of the commodity to be recommended specifically comprises any one of the following modes: acquiring an article label of the article to be recommended from an article detail page of the article to be recommended; in response to an input operation by a user, the input operation is for inputting a commodity label of a commodity to be recommended.
Specifically, the server performs feature extraction on the text of the commodity detail page to obtain commodity keywords, and takes the commodity keywords as commodity labels, and the commodity keywords can also be obtained from the existing evaluation labels in the comment page; the manager can also directly input the label of the commodity to be recommended to make the recommendation.
S102, inputting the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises the corresponding relation between commodity labels and first user labels.
In the step, the server inputs the commodity label of the commodity to be recommended into a preset commodity label library which is built in advance, and the preset commodity label library is matched with a user label which is carried by a user who can buy the commodity; the first user tag generally refers to a plurality of user tags, and the preset merchandise tag library stores a plurality of corresponding relationships.
In the above example, the commodity label of the commodity apple to be recommended is input into a preset commodity label library, and the label of the user who can purchase the apple is obtained as follows: fruit is often purchased, weight loss people and salad dressing are often purchased.
In a possible implementation manner, before inputting the product label into the preset product label library in step S102, the method further includes: acquiring information of a plurality of users who purchase goods to be recommended, wherein the plurality of users comprise a first user and a second user; acquiring a plurality of user tags of a first user, and acquiring a plurality of user tags of a second user; confirming that a third user tag and a fourth user tag are tags of goods to be recommended, wherein the plurality of user tags of the first user comprise the third user tag and the fourth user tag, and the plurality of user tags of the second user comprise the third user tag and the fourth user tag; constructing a preset association library; the preset association library comprises the corresponding relation between the label of the commodity to be recommended and the third user label and the corresponding relation between the label of the commodity to be recommended and the fourth user label.
Specifically, the server obtains user tags of a plurality of users who purchased the commodity to be recommended from information of the users who purchased the commodity to be recommended through data cleaning and feature extraction through information of the users who purchased the commodity to be recommended at one time, wherein the information comprises behavior information of the users and information of the purchased commodity.
It should be noted that, in order to represent more than one user who purchased the commodity to be recommended, a first user and a second user are set for convenience of expression; setting a third user tag and a fourth user tag for expressing a plurality of user tags shared by a plurality of users, namely, the first user and the second user all possess a plurality of identical tags, and the plurality of identical tags are expressed as the third user tag and the fourth user tag; and respectively associating the third user tag and the fourth user tag with the commodity tag to be recommended to obtain the relationship between the user tag shared by a plurality of users and the commodity tag to be recommended, and further constructing a preset commodity tag library.
In the above example, users who have purchased apples as goods to be recommended have user a and user B, obtain their behavior information and purchased goods information, and obtain user labels of user a through data cleaning and feature extraction, which have fitness, frequently purchase fruits and frequently purchase protein powder; the user labels of the user B are frequently purchased vegetables, kitchens and frequently purchased fruits, and the common labels of the user A and the user B can be obtained as the frequently purchased fruits, and the common labels are associated to obtain: fruit-frequent purchase of fruit, crisp mouthfeel-frequent purchase of fruit, production from X market-frequent purchase of fruit, XX brand-frequent purchase of fruit, and storing the four associations in a preset commodity label library.
In one possible implementation manner, acquiring information of a plurality of users purchasing goods to be recommended specifically includes any one of the following ways: acquiring information of multiple users purchasing goods to be recommended in a second preset time period every second preset time period; and responding to the operation of purchasing the commodity to be recommended by the multiple users, and acquiring information of the multiple users.
Specifically, the server acquires information of a plurality of users in a preset time period every interval of the preset time period so as to automatically update a preset commodity label library, and the length of the preset time period can be set by a manager; or when the user purchases the commodity to be recommended, the server also responds to and updates the preset trademark library.
In the above example, the server obtains information of users who purchased apples within 24 hours every 24 hours; for another example, when a user purchases an apple, the server obtains information of the user who purchased the apple within 1 h.
S103, matching a user corresponding to the first user tag in a preset user image library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user portrait library comprises the corresponding relation between the user and the second user tag.
In the above step, the second user label refers to a plurality of user labels and does not refer to one; the method comprises the steps that a server inputs a first user tag into a preset user portrait library, a user with a tag similar to the first user tag is obtained through matching, the similarity judging method is that the similarity is larger than a preset threshold, and the preset similarity threshold can be set by a manager; similarity is the sub-label repetition of two types of labels.
For example, a first user tag is obtained from a preset merchandise tag library: milk commodities are purchased frequently, diaper is purchased frequently, and baby toys are purchased frequently; inputting the first user tag into a preset user portrait library, and matching the first user tag to a second user tag with the similarity being greater than 50% of a preset threshold value: the similarity degree is 66.6% when the baby toy is purchased, the dairy commodity is purchased frequently and the children book is purchased frequently, and the users with the second user labels are obtained by matching according to the association relationship in the preset user portrait library.
In a possible implementation manner, before the matching of the user corresponding to the first user tag in the preset user image library in step S103, the method further includes: acquiring information of a plurality of commodities purchased by a user, wherein the plurality of commodities comprise a first commodity and a second commodity; acquiring a plurality of commodity labels of a first commodity and acquiring a plurality of commodity labels of a second commodity; confirming that the first commodity label and the second commodity label are labels of users, wherein the plurality of commodity labels of the first commodity comprise the first commodity label and the second commodity label, and the plurality of commodity labels of the second commodity comprise the first commodity label and the second commodity label; constructing a preset user portrait library; the preset user portrait library comprises the corresponding relation between the user and the first commodity label and the corresponding relation between the user and the second commodity label.
Specifically, the server obtains a plurality of commodity labels of the commodities through feature extraction by acquiring information of a plurality of commodities purchased by a user, wherein the commodity labels have commodity labels with higher repeatability, and preferably, the commodity labels with higher repeatability are used as user labels of the user, in other words, the commodity labels with lower repeatability than a preset threshold value have lower occurrence frequency and are not used as user labels of the user; it should be noted that the first commodity and the second commodity are set to conveniently represent a plurality of commodities once purchased by the user, and the first commodity label and the second commodity label represent a plurality of commodity labels shared by the plurality of commodities; after the user tag of the user is obtained, the association relation between the user and a plurality of user tags is established, and then a preset user portrait library is established.
In the above example, the server obtains the information of the plurality of commodities purchased by the user a, obtains the commodity labels of the commodities, and adds up the commodity labels to obtain the repetition degree of the fitness commodity label reaching 20%, namely 20% of the commodities purchased by the user a have the fitness label, and the repetition degree 20% is greater than 5% of the preset threshold value, so that the user label can be used as a user label of the user a; the repetition of the commodity label of the fruit reaches 18 percent and exceeds a preset threshold value by 5 percent, a frequently purchased field is added into the commodity label, the frequently purchased fruit is taken as a user label of the user A, and the fact that the addition or non-addition of the frequently purchased field does not influence the judgment of the label by the server is realized, so that the commodity label and the user label are distinguished conveniently; the repeatability of the protein powder commodity label is 14%, the repetition exceeds a preset threshold value by 5%, a frequently purchased field is added into the commodity label, and the frequently purchased protein powder is used as a user label of a user A; above, user A has three user labels of body building, frequent purchasing of fruit and frequent purchasing of protein powder, and builds body building-user A, frequent purchasing of fruit-user A, frequent purchasing of protein powder-user A, and stores in a preset user image library.
In one possible implementation manner, the obtaining information of the plurality of commodities purchased by the user specifically includes any one of the following modes: acquiring information of a plurality of commodities purchased by a user in a first preset time period every interval; and when the commodity purchasing operation of the user is monitored, acquiring information of a plurality of commodities purchased by the user in a first preset time period.
Specifically, the server acquires information of commodities purchased by a user in a preset time period every interval of the preset time period, so that a preset user portrait library can be automatically updated, and the preset time period can be set by a manager; or each time the user orders and purchases the commodity, the server acquires information of the commodity purchased by the user in the first preset time period.
For example, the server obtains information of the goods purchased by the user a within 12 hours every 12 hours; for another example, when the user a purchases a commodity, the server acquires information of the commodity purchased by the user a within 6 hours.
S104, pushing the commodity to be recommended to the user.
In the above steps, the server pushes the goods to be recommended to the matched one or more users.
In the above example, the server pushes the commodity apple to be recommended to user a and user B who purchase fruit frequently.
In one possible implementation, step S104 specifically includes: acquiring a historical ordering time period of a user, wherein the historical ordering time period is a time period in which the number of times of ordering and purchasing commodities by the user exceeds a preset number of times; and pushing the commodity to be recommended to the user in the historical ordering time period.
Specifically, the server acquires a time period in which a time point when the user purchased the commodity is too long in a preset time period, and the accumulated purchase times in the time period exceed preset times, wherein the preset times can be set by a manager; after a time period frequently ordered by a user is acquired, pushing the commodity to be recommended in the time period.
For example, the server obtains that the cumulative number of purchases of the user C from 16 to 17 points in the day reaches 5 times in the last month, exceeds the preset number of times for 3 times, and further determines that the user C tends to purchase the commodity from 16 to 17 points; the server pushes the goods to be recommended to the user C from 16 to 17 points per day.
For ease of understanding, a brief summary of the complete recommendation procedure of the embodiments is provided herein: the server acquires information on the apple commodity detail page, and the commodity label of the apple is obtained after feature extraction: fruit, crisp in mouth feel, produced from market X and brand XX; inputting the commodity label into a preset commodity label library constructed in advance, and obtaining a user label through the corresponding relation in the preset commodity label library: fruit is often purchased; inputting the user labels into a preset user image library constructed in advance, and according to the association relation in the preset user image library: fruit-user a is often purchased, resulting in the user to be recommended: a user A; the apples are pushed to user a during the time period that user a frequently places an order.
In the complete recommendation flow, the server can match the user with the corresponding label for the commodity to be recommended through the two groups of corresponding relations, compared with the complex recommendation algorithm in the existing cross-border e-commerce platform such as the recommendation algorithm based on deep learning, the calculation steps of the server in the process are relatively fewer, the commodity recommendation can be performed in a targeted manner more quickly, and the commodity recommendation efficiency of the cross-border e-commerce platform can be improved.
The application also provides a commodity recommending device, which comprises an acquisition unit 201 and a processing unit 202, and is shown in FIG. 2.
An acquiring unit 201, configured to acquire a commodity label of a commodity to be recommended, where the commodity label includes a commodity color, a commodity origin, and a commodity brand;
the processing unit 202 is configured to input the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises a corresponding relation between commodity labels and first user labels; matching a user corresponding to the first user tag in a preset user image library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user portrait library comprises the corresponding relation between the user and the second user tag; pushing the commodity to be recommended to the user.
In a possible implementation manner, the acquiring unit 201 is configured to acquire a label of an article to be recommended, and specifically includes any one of the following ways: acquiring an article label of the article to be recommended from an article detail page of the article to be recommended; in response to an input operation by a user, the input operation is for inputting a commodity label of a commodity to be recommended.
In one possible embodiment, the obtaining unit 201 is configured to obtain information of a plurality of articles purchased by a user, where the plurality of articles includes a first article and a second article; acquiring a plurality of commodity labels of a first commodity and acquiring a plurality of commodity labels of a second commodity; the processing unit 202 is configured to confirm that the first and second merchandise tags are tags of a user, wherein the plurality of merchandise tags of the first merchandise include the first merchandise tag and the second merchandise tag, and the plurality of merchandise tags of the second merchandise include the first merchandise tag and the second merchandise tag; constructing a preset user portrait library; the preset user portrait library comprises the corresponding relation between the user and the first commodity label and the corresponding relation between the user and the second commodity label.
In one possible implementation manner, the obtaining unit 201 is configured to obtain information of multiple items purchased by a user, and specifically includes any one of the following manners: acquiring information of a plurality of commodities purchased by a user in a first preset time period every interval; and when the commodity purchasing operation of the user is monitored, acquiring information of a plurality of commodities purchased by the user in a first preset time period.
In one possible embodiment, the obtaining unit 201 is configured to obtain information of a plurality of users who purchase goods to be recommended, where the plurality of users includes a first user and a second user; acquiring a plurality of user tags of a first user, and acquiring a plurality of user tags of a second user; the processing unit 202 is configured to confirm that the third user tag and the fourth user tag are tags of the to-be-recommended article, where the plurality of user tags of the first user include the third user tag and the fourth user tag, and the plurality of user tags of the second user include the third user tag and the fourth user tag; constructing a preset association library; the preset association library comprises the corresponding relation between the label of the commodity to be recommended and the third user label and the corresponding relation between the label of the commodity to be recommended and the fourth user label.
In one possible implementation manner, the obtaining unit 201 is configured to obtain information of multiple users purchasing goods to be recommended, and specifically includes any one of the following ways: acquiring information of multiple users purchasing goods to be recommended in a second preset time period every second preset time period; and responding to the operation of purchasing the commodity to be recommended by the multiple users, and acquiring information of the multiple users.
In a possible implementation manner, the obtaining unit 201 is configured to obtain a historical ordering time period of the user, where the historical ordering time period is a time period when the number of times of ordering the commodity by the user exceeds a preset number of times; the processing unit 202 is configured to push the commodity to be recommended to the user in the historical order time period.
It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
The present application also discloses a computer-readable storage medium storing a computer program for executing the commodity recommendation method disclosed in the above specification by a processor.
The application also discloses electronic equipment. Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one communication bus 302, at least one user interface 303, a network interface 304, a memory 305.
Wherein the communication bus 302 is used to enable connected communication between these components.
The user interface 303 may include a Display screen (Display), a Camera (Camera), and the optional user interface 303 may further include a standard wired interface, and a wireless interface.
The network interface 304 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and lines to connect various portions of the overall server, perform various functions of the server and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and invoking data stored in the memory 305. Alternatively, the processor 301 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 301 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 301 and may be implemented by a single chip.
The Memory 305 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 305 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 305 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. Memory 305 may also optionally be at least one storage device located remotely from the aforementioned processor 301. Referring to fig. 3, an operating system, a network communication module, a user interface module, and a commodity recommendation application may be included in the memory 305, which is one type of computer storage medium.
In the electronic device 300 shown in fig. 3, the user interface 303 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 301 may be configured to invoke the merchandise recommendation application stored in the memory 305, which when executed by the one or more processors 301, causes the electronic device 300 to perform the method as in one or more of the embodiments described above. It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.
The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure.
This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (10)
1. A commodity recommendation method, applied to a server, comprising:
acquiring a commodity label of a commodity to be recommended, wherein the commodity label comprises a commodity color, a commodity producing place and a commodity brand;
inputting the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises a corresponding relation between the commodity label and the first user label;
matching a user corresponding to the first user tag in a preset user portrait library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user image library comprises the corresponding relation between the user and the second user label;
Pushing the commodity to be recommended to the user.
2. The method according to claim 1, wherein the acquiring the label of the commodity to be recommended specifically includes any one of the following modes:
acquiring the commodity label of the commodity to be recommended from a commodity detail page of the commodity to be recommended;
and responding to input operation of a user, wherein the input operation is used for inputting the commodity label of the commodity to be recommended.
3. The method according to claim 1, wherein the constructing the preset user portrayal library before the user corresponding to the first user tag is matched in the preset user portrayal library, the constructing the preset user portrayal library specifically includes:
acquiring information of a plurality of commodities purchased by a user, wherein the plurality of commodities comprise a first commodity and a second commodity;
acquiring a plurality of commodity labels of the first commodity and acquiring a plurality of commodity labels of the second commodity;
confirming a first commodity label and a second commodity label as labels of the user, wherein the plurality of commodity labels of the first commodity comprise the first commodity label and the second commodity label, and the plurality of commodity labels of the second commodity comprise the first commodity label and the second commodity label;
Constructing a preset user portrait library; the preset user image library comprises the corresponding relation between the user and the first commodity label and the corresponding relation between the user and the second commodity label.
4. A method according to claim 3, wherein the obtaining information about the plurality of articles purchased by the user specifically includes any one of the following means:
acquiring information of a plurality of commodities purchased by a user in a first preset time period every interval;
and when the commodity purchasing operation of the user is monitored, acquiring information of a plurality of commodities purchased by the user in the first preset time period.
5. The method according to claim 1, wherein the building the preset article tag library before the article tag is input into the preset article tag library, the building the preset article tag library specifically comprises:
acquiring information of a plurality of users who purchase the commodity to be recommended, wherein the plurality of users comprise a first user and a second user;
acquiring a plurality of user tags of the first user, and acquiring a plurality of user tags of the second user;
confirming a third user tag and a fourth user tag as tags of the commodity to be recommended, wherein the plurality of user tags of the first user comprise the third user tag and the fourth user tag, and the plurality of user tags of the second user comprise the third user tag and the fourth user tag;
Constructing a preset association library; the preset association library comprises the corresponding relation between the label of the commodity to be recommended and the third user label and the corresponding relation between the label of the commodity to be recommended and the fourth user label.
6. The method of claim 5, wherein the obtaining information of the plurality of users purchasing the goods to be recommended specifically includes any one of the following ways:
acquiring information of multiple users purchasing the commodity to be recommended in a second preset time period every interval;
and responding to the operation of purchasing the commodity to be recommended by the plurality of users, and acquiring information of the plurality of users.
7. The method of claim 1, wherein pushing the item to be recommended to the user specifically comprises:
acquiring a historical ordering time period of the user, wherein the historical ordering time period is a time period when the number of times of ordering and purchasing goods by the user exceeds a preset number of times;
and pushing the commodity to be recommended to the user in the historical order-placing time period.
8. A commodity recommendation device, characterized in that the device is a server comprising an acquisition unit (201) and a processing unit (202):
The acquisition unit (201) is used for acquiring commodity labels of commodities to be recommended, wherein the commodity labels comprise commodity colors, commodity places and commodity brands;
the processing unit (202) is used for inputting the commodity label into a preset commodity label library to obtain a first user label corresponding to the commodity label; the preset commodity label library comprises a corresponding relation between the commodity label and the first user label; matching a user corresponding to the first user tag in a preset user portrait library, wherein the user has a second user tag, and the similarity between the first user tag and the second user tag is larger than a preset similarity threshold; the preset user image library comprises the corresponding relation between the user and the second user label; pushing the commodity to be recommended to the user.
9. An electronic device comprising a processor (301), a memory (305), a user interface (303) and a network interface (304), the memory (305) being for storing instructions, the user interface (303) and the network interface (304) being for communicating to other devices, the processor (301) being for executing the instructions stored in the memory (305) for causing the electronic device (300) to perform the method according to any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method of any of the preceding claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310902659.5A CN116957727A (en) | 2023-07-21 | 2023-07-21 | Commodity recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310902659.5A CN116957727A (en) | 2023-07-21 | 2023-07-21 | Commodity recommendation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116957727A true CN116957727A (en) | 2023-10-27 |
Family
ID=88450667
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310902659.5A Pending CN116957727A (en) | 2023-07-21 | 2023-07-21 | Commodity recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116957727A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117573945A (en) * | 2024-01-17 | 2024-02-20 | 每日互动股份有限公司 | User tag processing method, device, equipment and medium |
-
2023
- 2023-07-21 CN CN202310902659.5A patent/CN116957727A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117573945A (en) * | 2024-01-17 | 2024-02-20 | 每日互动股份有限公司 | User tag processing method, device, equipment and medium |
CN117573945B (en) * | 2024-01-17 | 2024-05-03 | 每日互动股份有限公司 | User tag processing method, device, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110827114A (en) | Commodity recommendation method and device | |
US20160165312A1 (en) | Electronic device, and method and storage medium | |
CN111984837B (en) | Commodity data processing method, device and equipment | |
CN111699503A (en) | Advertisement recommendation method and device and electronic equipment | |
CN105931066A (en) | Transaction data processing method and device | |
JP6413508B2 (en) | Information recommendation program and information processing apparatus | |
JP7162417B2 (en) | Estimation device, estimation method, and estimation program | |
CN112396456A (en) | Advertisement pushing method and device, storage medium and terminal | |
CN107220876B (en) | Commodity information management method and device and mobile terminal | |
CN116957727A (en) | Commodity recommendation method and device | |
CN110602532A (en) | Entity article recommendation method, device, server and storage medium | |
CN111582979A (en) | Clothing matching recommendation method and device and electronic equipment | |
WO2020016204A1 (en) | Determining item relevancy | |
JP6059169B2 (en) | Calculation device, calculation method, and calculation program | |
CN108122126B (en) | Method for extending association rule, device using same and computer readable medium | |
JP6509028B2 (en) | Item recommendation device, item recommendation method and program | |
CA3138745A1 (en) | Method and device for circling and creating target population | |
JP7447800B2 (en) | Receipt processing device, control method, and program | |
CN107967637B (en) | Commodity object model recommendation method and device and electronic equipment | |
CN112561581A (en) | Recommendation method and device, electronic equipment and storage medium | |
JP2011113323A (en) | Server and program for managing customer information | |
US20150006285A1 (en) | Method and system for providing information regarding items in a retail store and computer programs thereof | |
JP2020140635A (en) | Purchase management device, control method, and program | |
JP6203352B2 (en) | Calculation device, calculation method, and calculation program | |
CN111192112A (en) | Multi-platform interaction method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |