CN116385101A - Commodity information recommendation method based on e-commerce platform, server, e-commerce system and related equipment - Google Patents
Commodity information recommendation method based on e-commerce platform, server, e-commerce system and related equipment Download PDFInfo
- Publication number
- CN116385101A CN116385101A CN202310253324.5A CN202310253324A CN116385101A CN 116385101 A CN116385101 A CN 116385101A CN 202310253324 A CN202310253324 A CN 202310253324A CN 116385101 A CN116385101 A CN 116385101A
- Authority
- CN
- China
- Prior art keywords
- commodity
- recommendation
- user
- target
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000001914 filtration Methods 0.000 claims description 8
- 230000010365 information processing Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 10
- AYEKOFBPNLCAJY-UHFFFAOYSA-O thiamine pyrophosphate Chemical compound CC1=C(CCOP(O)(=O)OP(O)(O)=O)SC=[N+]1CC1=CN=C(C)N=C1N AYEKOFBPNLCAJY-UHFFFAOYSA-O 0.000 description 10
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application discloses a commodity information recommendation method based on an electronic commerce platform, a server, an electronic commerce system and related equipment. The commodity information recommending method based on the e-commerce platform comprises the following steps: acquiring commodity information of the specified commodity based on a user request of the user for the specified commodity; generating a commodity recommendation set according to commodity information; generating a target commodity recommendation list based on the commodity recommendation set and user behavior data of a user side, wherein the user behavior data at least comprises one of preset behavior data, a commodity clicking sequence and a commodity exposure sequence; and sending the target commodity recommendation list to the user side so as to update and display the target commodity recommendation list at the user side.
Description
Technical Field
The application relates to the technical field of Internet, in particular to a commodity information recommendation method based on an e-commerce platform, a server, an e-commerce system and related equipment.
Background
With the development of internet technology, online shopping based on an e-commerce platform is in the middle of people's daily life.
In order to improve shopping intention of users, the electronic commerce platform often makes commodity recommendation to users. If the commodity recommendation of the current e-commerce platform is based on the past shopping habit, the historical shopping order and other information of the user, the user is recommended to the commodity similar to the purchased commodity, for example, the e-commerce platform displays the recommended commodity on the preset display position of the commodity recommendation page.
However, the inventor finds that most of the current commodity recommendation pages are updated regularly or the page is updated according to manual refreshing of a user, so that when the user browses commodities, the e-commerce platform cannot actively and real-timely sense the change of shopping interests of the user.
Therefore, the inventor believes that the current commodity recommendation method has hysteresis for capturing the shopping interests of the user, and cannot accurately touch the real-time shopping intentions of the user. Based on this, the inventors consider that the current commodity recommendation method has yet to be improved.
Disclosure of Invention
The application discloses a commodity information recommending method based on an electronic commerce platform, a server, an electronic commerce system and related equipment, which are used for solving the problem that the current commodity information recommending method based on the electronic commerce platform has hysteresis for capturing shopping interests of users and cannot accurately touch real-time shopping intentions of the users.
According to one aspect of the application, the application provides a commodity information recommendation method based on an e-commerce platform. The commodity information recommendation method comprises the following steps: acquiring commodity information of the specified commodity based on a user request of the user for the specified commodity; generating a commodity recommendation set according to commodity information; generating a target commodity recommendation list based on the commodity recommendation set and user behavior data of a user side, wherein the user behavior data at least comprises one of preset behavior data, a commodity clicking sequence and a commodity exposure sequence; and sending the target commodity recommendation list to the user side so as to update and display the target commodity recommendation list at the user side.
According to some embodiments of the present application, generating a target commodity recommendation list based on a commodity recommendation set and user behavior data of a user side includes: judging whether the user behavior data comprises preset behavior data or not; if yes, generating a target commodity recommendation list and a target commodity cache list according to a preset sequence of the commodity recommendation set; if not, generating a target commodity recommendation list according to the preset sequence of the target commodity cache list under the condition that the target commodity cache list is not empty; and generating a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set under the condition that the target commodity cache list is empty.
According to some embodiments of the present application, generating a target commodity recommendation list based on a commodity recommendation set and user behavior data of a user side includes: and generating a target commodity recommendation list through a preset algorithm model based on the commodity clicking sequence and the commodity exposure sequence.
According to some embodiments of the present application, generating the target commodity recommendation list based on the commodity recommendation set and the user behavior data of the user side further includes: and performing exposure filtering processing on the target commodity recommendation list based on the commodity exposure sequence.
According to another aspect of the present application, a server is also provided. The server comprises a commodity information processing unit and a commodity recommendation processing unit. The commodity information processing unit acquires commodity information of the specified commodity based on a user request of the user for the specified commodity; the commodity recommendation processing unit generates a commodity recommendation set according to commodity information, generates a target commodity recommendation list based on the commodity recommendation set and user behavior data of the user side, and sends the target commodity recommendation list to the user side so as to update and display the target commodity recommendation list on the user side; the user behavior data at least comprises one of preset behavior data, commodity clicking sequences and commodity exposure sequences.
According to some embodiments of the present application, the commodity recommendation processing unit determines whether the user behavior data includes preset behavior data; the commodity recommendation processing unit generates a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set under the condition that the user behavior data comprises preset behavior data; the commodity recommendation processing unit generates a target commodity recommendation list according to the preset sequence of the target commodity cache list under the condition that the user behavior data does not comprise preset behavior data and the target commodity cache list is not empty; and the commodity recommendation processing unit generates a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set under the condition that the user behavior data does not comprise the preset behavior data and the target commodity cache list is empty.
According to some embodiments of the application, the commodity recommendation processing unit generates a target commodity recommendation list through a preset algorithm model based on the commodity click sequence and the commodity exposure sequence.
According to some embodiments of the present application, the commodity recommendation processing unit further performs exposure filtering processing on the target commodity recommendation list based on the commodity exposure sequence.
According to still another aspect of the present application, an e-commerce system is also provided. The e-commerce system comprises a server as described above.
According to yet another aspect of the present application, an electronic device is also provided. The electronic device comprises one or more processors and storage means for storing one or more programs that, when executed by the one or more processors, enable the one or more processors to implement the merchandise information recommendation method as described above.
According to yet another aspect of the present application, there is also provided a non-volatile computer-readable storage medium. The storage medium stores a computer program that can implement the commodity information recommendation method as described above.
According to the method, through a user request of a user on a specified commodity, commodity information of the specified commodity is obtained, a commodity recommendation set is generated according to the commodity information, a target commodity recommendation list is generated based on the commodity recommendation set and user behavior data of a user side, and the target commodity recommendation list is sent to the user side so that the target commodity recommendation list can be updated and displayed on the user side.
The method and the system can sense real-time behavior data of the user in real time, timely trigger updating of the commodity recommendation page, generate a target commodity recommendation list in real time according to user interests and changes of similar commodities in a commodity database of the cloud through interaction with the cloud, and update and display commodities to be recommended in real time at a user side. The updated commodity recommendation list is more in line with user preference and expectation, so that relevant commodity recommendation is automatically updated for the user in a targeted manner, and user experience satisfaction is improved. The method and the device are applicable to automatic updating of the commodity recommendation page under various scenes of the e-commerce platform.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a commodity information recommendation method according to an exemplary embodiment of the present application;
FIG. 2 is another flow chart of a method for recommending merchandise information according to an example embodiment of the present application;
FIG. 3 shows a process schematic of a merchandise recommendation method of an example embodiment of the present application;
fig. 4 shows a schematic structural diagram of a server according to an exemplary embodiment of the present application.
Reference numerals illustrate:
a server 1; a commodity information processing unit 10; and a commodity recommendation processing unit 20.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted.
The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the disclosed aspects may be practiced without one or more of the specific details, or with other methods, components, materials, apparatus, etc. In these instances, well-known structures, methods, devices, implementations, materials, or operations are not shown or described in detail.
Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order.
The following description of the embodiments of the present application, taken in conjunction with the accompanying drawings, will clearly and fully describe the technical aspects of the present application, and it will be apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
The inventors found that in the current commodity recommendation mode, the CTR (Click-Through-Rate) of the commodity at the front of the display is much higher than the CTR at the rear of the display. Analysis shows that this phenomenon indicates that the currently recommended merchandise does not adequately capture the actual points of interest of the user, who may simply click on the merchandise in front of the display based on habits.
And when the shopping interest points of the user change, the electronic commerce platform cannot actively sense the change of the shopping intention of the user in real time and cannot actively trigger the update of the commodity recommendation page, so that the current commodity recommendation method cannot acquire the shopping intention of the user in time and the accuracy of commodity pushing is affected.
Based on the information, one aspect of the application provides a commodity information recommendation method based on an e-commerce platform. According to the method, the shopping interests and the changes of the user can be perceived according to the real-time behavior data of the user on the e-commerce platform, and the update of the related commodity recommendation page can be updated in time according to the shopping intention of the user, so that the accurate recommendation of commodity information is realized.
The technical scheme of the application will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a commodity information recommendation method according to an exemplary embodiment of the present application. As shown in fig. 1, the commodity information recommendation method includes steps S100 to S400. According to example embodiments, the item information recommendation method may be performed by a server.
It will be understood that the e-commerce platform may be an APP-based e-commerce platform or a web-based e-commerce platform, which is not limited in this application.
In step S100, the server acquires commodity information of the specified commodity based on a user request for the specified commodity from the user.
According to an example embodiment, the user request includes a click request of a link to the item by the user and a search request for the item.
For example, when the user clicks a certain commodity link in the global domain of the e-commerce platform (such as the home page of the e-commerce platform and the commodity recommendation page), the server receives a click request of the commodity and determines commodity information of the commodity corresponding to the click request. The commodity information includes, but is not limited to, commodity ID, category, price, specification, style, and the like.
For another example, when the user searches a certain commodity on the e-commerce platform search page, the server receives a search request of the commodity and determines commodity information of the commodity corresponding to the search request.
In step S200, the server generates a commodity recommendation set according to commodity information.
For example, after receiving a user request, the server acquires a plurality of commodities similar to the commodity information from a commodity database in the cloud according to a preset algorithm, and forms a commodity recommendation set from the plurality of commodities.
In step S300, the server generates a target commodity recommendation list based on the commodity recommendation set and the user behavior data of the user terminal. The user behavior data at least comprises one of preset behavior data, commodity clicking sequences and commodity exposure sequences.
According to an example embodiment, the preset behavior data includes forward behavior data of the user. The forward behavior data is behavior which can clearly reflect the browsing interest points or the purchasing intention of the user commodity. For example, the forward behavior data may be commodity click behavior data, commodity search behavior data, shopping behavior data, or the like.
According to an example embodiment, after a server generates a commodity recommendation set according to a user request, according to real-time user behavior data of a user side, shopping intention and shopping interest points of the user are perceived, and a target commodity recommendation list is generated according to a preset algorithm by combining the commodity recommendation set and the real-time user behavior data of the user side.
In step S400, the server sends the target commodity recommendation list to the user terminal, so as to update and display the target commodity recommendation list at the user terminal.
For example, the server sends the generated target commodity recommendation list to a commodity recommendation page of the user side, and covers the current commodity recommendation list with the target commodity recommendation list to complete updating of the recommended commodity of the commodity recommendation page.
Through the above example embodiment, the method and the device can sense the shopping intention and the shopping interest change of the user in real time according to the real-time user behavior data of the user on the e-commerce platform, so that the related commodity recommendation can be automatically updated in time in a targeted manner, and the accurate recommendation of commodity information is realized.
Optionally, fig. 2 shows another flowchart of the commodity information recommendation method according to an exemplary embodiment of the present application. As shown in fig. 2, generating a target commodity recommendation list based on the commodity recommendation set and the user behavior data of the user side in step S300 includes steps S310 to S340.
In step S310, the server determines whether the user behavior data includes preset behavior data. The preset behavior data are described in detail above and will not be described here again.
If the server determines that the user behavior data includes the preset behavior data, the process proceeds to step S320, otherwise, the process proceeds to step S330.
In step S320, the server generates a target commodity recommendation list and a target commodity cache list according to a preset order of the commodity recommendation set.
For example, the commodity recommendation set generated by the server in step S200 includes 110 recommended commodities similar to the commodity corresponding to the user request, and the preset order may be an order of the commodity recommendation set from front to back. If the server generates a target commodity recommendation list according to the first 1-22 recommended commodities in the commodity recommendation set, and the server generates a target commodity cache list according to the last 23-110 recommended commodities in the commodity recommendation set.
In step S330, the server determines whether the target cache list is empty. If the target cache list is empty, step S320 is performed, where the server generates a target commodity recommendation list and a target commodity cache list according to the preset order of the commodity recommendation set.
If the target cache list is not empty, step S340 is performed, where the server generates a target commodity recommendation list according to the preset order of the target commodity cache list.
For example, the preset order may be the order of the target commodity cache list from front to back, for example, the server generates the target commodity recommendation list according to the first 1-22 recommended commodities in the target commodity cache list, and deletes the first 1-22 recommended commodities from the target commodity cache list to avoid repeated recommendation.
It can be understood that, after the server performs an algorithm process on the related recommended goods, the cloud database stores the target goods cache list of the related recommended goods. And after the server senses the same user behavior data again, enabling the target commodity cache list corresponding to the related recommended product by the server. By the arrangement, under the condition that no preset behavior data of a user exist, the algorithm model and the feature factors of the commodity recommendation set generated by the server are unchanged, the server can directly acquire the target commodity cache list in the cloud commodity database, and the target commodity recommendation list is not generated through the algorithm again, so that the calculated amount of the cloud can be reduced, and cloud resources are saved.
Optionally, in step S300, the generating, by the server, the target commodity recommendation list based on the commodity recommendation set and the user behavior data of the user side may further include: and generating a target commodity recommendation list through a preset algorithm model based on the commodity clicking sequence and the commodity exposure sequence.
According to an example embodiment, the item click sequence is an information sequence formed by serially concatenating a plurality of page events of an item detail page of an item accessed by a user, the page events including, for example, offerId, access time, and the like.
The commodity exposure sequence is an information sequence formed by serially splicing a plurality of exposure events of commodity links of the current commodity recommendation page, wherein the exposure events comprise, for example, offerId, a current scene, a current position, access time and the like.
For example, when the server updates the commodity recommendation page according to the user request, the server also obtains a commodity clicking sequence and a commodity exposure sequence implemented by the user between the current user request and the last user request. The server adds the user behavior sequences such as the commodity clicking sequence, the commodity exposing sequence and the like into the user preference category, and can more accurately generate a target commodity recommendation list conforming to the user preference according to a preset algorithm model by combining the commodity recommendation set. By the arrangement, the accuracy of recall of similar commodities can be improved, and the updated commodity recommendation list is more in line with user preference and expectations.
Optionally, the generating, by the server, the target commodity recommendation list based on the commodity recommendation set and the user behavior data of the user side may further include: and performing exposure filtering processing on the target commodity recommendation list based on the commodity exposure sequence.
For example, the server also adds the commodity exposure sequence implemented by the user between the current user request and the last user request to the exposure filtering process of the current target commodity recommendation list, so as to filter the recommended commodities which are recommended in the user side but not browsed by the user, and avoid invalid recommendation again. By the arrangement, an algorithm model of commodity recommendation can be further optimized, and accuracy of commodity recommendation is improved.
Example embodiment
Taking an e-commerce platform at an APP end as an example, fig. 3 shows a process schematic diagram of a commodity recommendation method according to an example embodiment of the present application.
As shown in fig. 3, the server receives a user request input by a user through an e-commerce platform at the APP end, and triggers the server to recommend the commodity. The server acquires user behavior data (such as forward behavior data, commodity clicking sequences and commodity exposure sequences) of the user side, and transmits the user behavior data to the recommendation unified access layer. The recommendation unified access layer transmits data to a fine-ranking TPP (TPP: a platform for developing and hosting universal JVM codes), and the fine-ranking TPP generates a target commodity recommendation list and/or a target commodity cache list according to a preset algorithm model.
And the fine-ranking TPP transmits the target commodity recommendation list back to the recommendation unified access layer, and transmits the UI commodity list back to the server after the commodity UI TPP processing. And the server transmits the final UI commodity list back to the E-commerce platform, and covers the previously recommended commodity to complete the updating of the commodity recommendation page.
Through the above example embodiment, the method and the device can sense the real-time behavior data of the user in real time, trigger the update of the commodity recommendation page in time, generate the target commodity recommendation list in real time according to the user interests and the changes of the similar commodities in the commodity database of the cloud through interaction with the cloud, and update and display the commodities to be recommended in real time at the user side. The updated commodity recommendation list is more in line with user preference and expectation, so that relevant commodity recommendation is automatically updated for the user in a targeted manner, and user experience and satisfaction are improved. The method and the device are applicable to automatic updating of the commodity recommendation page under various scenes of the e-commerce platform.
According to another aspect of the present application, a server is also provided. The server is applied to commodity recommendation of the e-commerce platform, and can sense shopping interests and changes of the user according to real-time behavior data of the user on the e-commerce platform, update relevant commodity recommendation pages in time according to shopping intentions of the user, and therefore accurate recommendation of commodity information is achieved.
Fig. 4 shows a schematic structural diagram of a server according to an exemplary embodiment of the present application. As shown in fig. 4, the server 1 includes a commodity information processing unit 10 and a commodity recommendation processing unit 20.
It will be understood that the e-commerce platform may be an APP-based e-commerce platform or a web-based e-commerce platform, which is not limited in this application.
According to an exemplary embodiment, the article information processing unit 10 acquires article information of a specified article based on a user request of the user for the specified article.
The user request includes a click request of the commodity link by the user and a search request of the commodity.
For example, when the user clicks a certain commodity link in the global domain of the e-commerce platform (such as the home page of the e-commerce platform, the commodity recommendation page, etc.), the commodity information processing unit 10 receives a click request of the commodity and determines commodity information of the commodity corresponding to the click request. The commodity information includes, but is not limited to, commodity ID, category, price, specification, style, and the like.
For another example, when the user searches for a certain commodity on the e-commerce platform search page, the commodity information processing unit 10 receives a search request for the commodity and determines commodity information of the commodity corresponding to the search request.
According to an example embodiment, the item recommendation processing unit 20 generates an item recommendation set from item information.
For example, after receiving the user request, the commodity recommendation processing unit 20 obtains a plurality of commodities similar to the commodity information from the commodity database in the cloud according to a preset algorithm, and composes the plurality of commodities into a commodity recommendation set.
The commodity recommendation processing unit 20 generates a target commodity recommendation list based on the commodity recommendation set and the user behavior data of the user side. The user behavior data at least comprises one of preset behavior data, commodity clicking sequences and commodity exposure sequences.
According to an example embodiment, the preset behavior data includes forward behavior data of the user. The forward behavior data is behavior which can clearly reflect the browsing interest points or the purchasing intention of the user commodity. For example, the forward behavior data may be commodity click behavior data, commodity search behavior data, shopping behavior data, or the like.
According to an exemplary embodiment, after the commodity recommendation processing unit 20 generates the commodity recommendation set according to the user request, the shopping intention and the shopping interest point of the user are perceived according to the real-time user behavior data of the user side, and the target commodity recommendation list is generated according to a preset algorithm by combining the commodity recommendation set and the real-time user behavior data of the user side.
The commodity recommendation processing unit 20 also sends the target commodity recommendation list to the user side, so that the target commodity recommendation list is updated and displayed on the user side.
For example, the commodity recommendation processing unit 20 sends the generated target commodity recommendation list to the commodity recommendation page of the user side, and overlays the target commodity recommendation list on the current commodity recommendation list to complete updating of the recommended commodity of the commodity recommendation page.
Through the above example embodiment, the method and the device can sense the shopping intention and the shopping interest change of the user in real time according to the real-time user behavior data of the user on the e-commerce platform, so that the related commodity recommendation can be automatically updated in time in a targeted manner, and the accurate recommendation of commodity information is realized.
Alternatively, the commodity recommendation processing unit 20 determines whether the user behavior data includes preset behavior data.
The commodity recommendation processing unit 20 generates a target commodity recommendation list and a target commodity cache list according to a preset order of the commodity recommendation set in the case that it is determined that the user behavior data includes preset behavior data.
For example, the commodity recommendation set generated by the commodity recommendation processing unit 20 includes 110 recommended commodities similar to the commodities corresponding to the user request, and the preset order may be an order of the commodity recommendation set from front to back, for example, the commodity recommendation processing unit 20 generates a target commodity recommendation list according to the first 1 to 22 recommended commodities of the commodity recommendation set, and the commodity recommendation processing unit 20 generates a target commodity cache list according to the last 23 to 110 recommended commodities of the commodity recommendation set.
The commodity recommendation processing unit 20 generates a target commodity recommendation list according to the preset order of the target commodity cache list in the case that it is determined that the user behavior data does not include the preset behavior data and the target commodity cache list is not empty.
For example, the preset order may be an order of the target commodity cache list from front to back, for example, the commodity recommendation processing unit 20 generates a target commodity recommendation list according to the first 1 to 22 recommended commodities in the target commodity cache list, and deletes the first 1 to 22 recommended commodities from the target commodity cache list to avoid repeated recommendation.
The commodity recommendation processing unit 20 generates a target commodity recommendation list and a target commodity cache list according to the preset order of the commodity recommendation set in the case that it is determined that the user behavior data does not include the preset behavior data and the target commodity cache list is empty.
It will be understood that, after the commodity recommendation processing unit 20 performs an algorithm process for related recommended commodities, the cloud database stores the above-mentioned target commodity cache list of related recommended commodities. When the commodity recommendation processing unit 20 senses the same user behavior data again, the commodity recommendation processing unit 20 enables the target commodity cache list corresponding to the related recommended product. By the arrangement, under the condition that no preset behavior data of a user exists, the commodity recommendation processing unit 20 generates an algorithm model of a commodity recommendation set, and the characteristic factors are not changed, so that the commodity recommendation processing unit 20 can directly acquire a target commodity cache list in a cloud commodity database, and the target commodity recommendation list is not generated through the algorithm again, and therefore the calculated amount of the cloud can be reduced, and cloud resources are saved.
Alternatively, the commodity recommendation processing unit 20 generates the target commodity recommendation list through a preset algorithm model based on the commodity click sequence and the commodity exposure sequence.
According to an example embodiment, the item click sequence is an information sequence formed by serially concatenating a plurality of page events of an item detail page of an item accessed by a user, the page events including, for example, offerId, access, and the like.
The commodity exposure sequence is an information sequence formed by serially splicing a plurality of exposure events of commodity links of the current commodity recommendation page, wherein the exposure events comprise, for example, offerId, a current scene, a current position, access time and the like.
For example, when the commodity recommendation processing unit 20 updates the commodity recommendation page according to the user request, the commodity recommendation processing unit 20 also acquires a commodity click sequence and a commodity exposure sequence implemented by the user between the current user request and the last user request. The commodity recommendation processing unit 20 adds the commodity click sequence, the commodity exposure sequence and other user behavior sequences into the user preference category, and can more accurately generate a target commodity recommendation list which accords with the user preference according to a preset algorithm model by combining the commodity recommendation set. By the arrangement, the accuracy of recall of similar commodities can be improved, and the updated commodity recommendation list is more in line with user preference and expectations.
Optionally, the commodity recommendation processing unit 20 further performs exposure filtering processing on the target commodity recommendation list based on the commodity exposure sequence.
For example, the commodity recommendation processing unit 20 further adds the commodity exposure sequence implemented by the user between the current user request and the last user request to the exposure filtering process of the current target commodity recommendation list, so as to filter the recommended commodity previously recommended by the user terminal but not browsed by the user, and avoid invalidating recommendation again. By the arrangement, an algorithm model of commodity recommendation can be further optimized, and accuracy of commodity recommendation is improved.
Example embodiment
Taking an e-commerce platform at the APP end as an example, the server receives a user request input by a user through the e-commerce platform at the APP end, and triggers the server to recommend the commodity. The server acquires user behavior data (such as forward behavior data, commodity clicking sequences and commodity exposure sequences) of the user side, and transmits the user behavior data to the recommendation unified access layer. The recommendation unified access layer transmits data to a fine-ranking TPP (TPP: a platform for developing and hosting universal JVM codes), and the fine-ranking TPP generates a target commodity recommendation list and/or a target commodity cache list according to a preset algorithm model.
And the fine-ranking TPP transmits the target commodity recommendation list back to the recommendation unified access layer, and transmits the UI commodity list back to the server after the commodity UI TPP processing. And the server transmits the final UI commodity list back to the E-commerce platform, and covers the previously recommended commodity to complete the updating of the commodity recommendation page.
Through the above example embodiment, the method and the device can sense the real-time behavior data of the user in real time, trigger the update of the commodity recommendation page in time, generate the target commodity recommendation list in real time according to the user interests and the changes of the similar commodities in the commodity database of the cloud through interaction with the cloud, and update and display the commodities to be recommended in real time at the user side. The updated commodity recommendation list is more in line with user preference and expectation, so that relevant commodity recommendation is automatically updated for the user in a targeted manner, and user experience satisfaction is improved. The method and the device are applicable to automatic updating of the commodity recommendation page under various scenes of the e-commerce platform.
According to still another aspect of the present application, an e-commerce system is also provided. The e-commerce system comprises a server as described above.
According to yet another aspect of the present application, an electronic device is also provided. The electronic device comprises one or more processors and storage means for storing one or more programs that, when executed by the one or more processors, enable the one or more processors to implement the merchandise information recommendation method as described above.
According to yet another aspect of the present application, there is also provided a non-volatile computer-readable storage medium. The storage medium stores a computer program that can implement the commodity information recommendation method as described above.
Finally, it should be noted that the foregoing description is only a preferred embodiment of the present application, and is not intended to limit the present application, and although the detailed description of the present application is given with reference to the foregoing embodiment, it will be obvious to those skilled in the art that various modifications may be made to the technical solutions of the foregoing embodiments, or that equivalents may be substituted for some of the technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (11)
1. The commodity information recommending method based on the e-commerce platform is characterized by comprising the following steps of:
acquiring commodity information of a specified commodity based on a user request of a user for the specified commodity;
generating a commodity recommendation set according to the commodity information;
generating a target commodity recommendation list based on the commodity recommendation set and user behavior data of a user side, wherein the user behavior data at least comprises one of preset behavior data, a commodity clicking sequence and a commodity exposure sequence;
and sending the target commodity recommendation list to a user side so as to update and display the target commodity recommendation list at the user side.
2. The merchandise information recommendation method according to claim 1, wherein the generating a target merchandise recommendation list based on the merchandise recommendation set and user behavior data of the user side comprises:
judging whether the user behavior data comprises the preset behavior data or not;
if yes, generating a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set;
if not, generating a target commodity recommendation list according to the preset sequence of the target commodity cache list under the condition that the target commodity cache list is not empty; and generating a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set under the condition that the target commodity cache list is empty.
3. The merchandise information recommendation method according to claim 1, wherein the generating a target merchandise recommendation list based on the merchandise recommendation set and user behavior data of the user side comprises:
and generating a target commodity recommendation list through a preset algorithm model based on the commodity click sequence and the commodity exposure sequence.
4. The merchandise information recommendation method according to claim 3, wherein generating the target merchandise recommendation list based on the merchandise recommendation set and the user behavior data of the user side further comprises:
and performing exposure filtering processing on the target commodity recommendation list based on the commodity exposure sequence.
5. A server, comprising:
a commodity information processing unit for acquiring commodity information of a specified commodity based on a user request of the user for the specified commodity;
the commodity recommendation processing unit generates a commodity recommendation set according to the commodity information, generates a target commodity recommendation list based on the commodity recommendation set and user behavior data of a user side, and sends the target commodity recommendation list to the user side so as to update and display the target commodity recommendation list on the user side;
the user behavior data at least comprises one of preset behavior data, commodity clicking sequences and commodity exposure sequences.
6. The server according to claim 5, wherein the commodity recommendation processing unit determines whether the user behavior data includes the preset behavior data;
the commodity recommendation processing unit generates a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set under the condition that the user behavior data comprises the preset behavior data;
the commodity recommendation processing unit generates a target commodity recommendation list according to a preset sequence of the target commodity cache list under the condition that the user behavior data does not comprise the preset behavior data and the target commodity cache list is not empty;
and the commodity recommendation processing unit generates a target commodity recommendation list and a target commodity cache list according to the preset sequence of the commodity recommendation set under the condition that the user behavior data does not comprise the preset behavior data and the target commodity cache list is empty.
7. The server according to claim 5, wherein the commodity recommendation processing unit generates a target commodity recommendation list by a preset algorithm model based on the commodity click sequence and the commodity exposure sequence.
8. The server according to claim 5, wherein the commodity recommendation processing unit further performs exposure filtering processing on the target commodity recommendation list based on the commodity exposure sequence.
9. An e-commerce system comprising a server as claimed in any one of claims 5 to 8.
10. An electronic device, comprising:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the merchandise information recommendation method of any one of claims 1-4.
11. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program implements the merchandise information recommendation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310253324.5A CN116385101A (en) | 2023-03-09 | 2023-03-09 | Commodity information recommendation method based on e-commerce platform, server, e-commerce system and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310253324.5A CN116385101A (en) | 2023-03-09 | 2023-03-09 | Commodity information recommendation method based on e-commerce platform, server, e-commerce system and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116385101A true CN116385101A (en) | 2023-07-04 |
Family
ID=86963949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310253324.5A Pending CN116385101A (en) | 2023-03-09 | 2023-03-09 | Commodity information recommendation method based on e-commerce platform, server, e-commerce system and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385101A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290609A (en) * | 2023-11-24 | 2023-12-26 | 中国科学技术大学 | Product data recommendation method and product data recommendation device |
-
2023
- 2023-03-09 CN CN202310253324.5A patent/CN116385101A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290609A (en) * | 2023-11-24 | 2023-12-26 | 中国科学技术大学 | Product data recommendation method and product data recommendation device |
| CN117290609B (en) * | 2023-11-24 | 2024-03-29 | 中国科学技术大学 | Product data recommendation method and product data recommendation device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101852581B1 (en) | Image evaluation | |
| JP7198853B2 (en) | A wishlist user interface within a web browser that notifies users of price changes | |
| US10409821B2 (en) | Search result ranking using machine learning | |
| US10922327B2 (en) | Search guidance | |
| AU2006290220B2 (en) | Framework for selecting and delivering advertisements over a network based on user behaviorial interests | |
| US9720883B2 (en) | Multi-level architecture for image display | |
| US20220383380A1 (en) | Methods and systems for reducing item selection error in an e-commerce environment | |
| US20140249935A1 (en) | Systems and methods for forwarding users to merchant websites | |
| CN110851699A (en) | Deep reinforcement learning-based information flow recommendation method, device, equipment and medium | |
| WO2018107102A1 (en) | Network interaction system | |
| CN110929138A (en) | Recommendation information generation method, device, equipment and storage medium | |
| CN111338724A (en) | Page configuration method and device, electronic equipment and computer readable medium | |
| US10248991B1 (en) | Linking image items to an electronic catalog | |
| KR102332945B1 (en) | Method and apparatus for providing information based on list of search result of item | |
| US10600114B2 (en) | Manufacture for providing access to product information and related functionalities | |
| CN116385101A (en) | Commodity information recommendation method based on e-commerce platform, server, e-commerce system and related equipment | |
| CN109416806B (en) | System and method for linking database entries of a network platform | |
| CN113781149A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| JP6251465B1 (en) | RECOMMENDED INFORMATION PROVIDING SYSTEM AND RECOMMENDED INFORMATION PROVIDING METHOD | |
| KR20190079582A (en) | Service mehtod for recommending gifts and server usingn the same | |
| JP4992088B2 (en) | Web server device, web page management method, and web server program | |
| JP2001076002A (en) | Information supply system provided with information needs estimation function | |
| JP2013145604A (en) | Advertisement system, method for controlling advertisement system, program, and information storage medium | |
| JP6499332B1 (en) | Proposing device, proposing method, and program | |
| CN111161026A (en) | Commodity information pushing method and device based on e-commerce platform |
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 |