CN114581174A - Recommendation method and device, electronic equipment and storage medium - Google Patents

Abstract

The invention belongs to the technical field of online platform commodity recommendation, and particularly relates to a recommendation method, a recommendation device, electronic equipment and a storage medium. According to the method and the device, the scene mode of the commodity of the user is determined by obtaining the browsing condition of the historical order of the user, the database corresponding to the commodity is determined by the scene mode, and the commodity information with high association level with the order commodity browsed by the user in the database is pushed to the user, so that the commodity recommendation mode is optimized, the user can quickly obtain the commodity information related to the order, the commodity preview quantity is increased, and the commodity transaction rate is improved. A recommendation method, comprising: acquiring first commodity information in order information triggered by a user; determining a scene mode of a first commodity corresponding to the first commodity information according to the first commodity information; determining a database corresponding to the scene mode; and determining target commodity information in the database according to the first commodity information.

Description

A recommended method, device, electronic device and storage medium

technical field

The invention belongs to the technical field of online platform product recommendation, and specifically relates to a recommendation method, device, electronic device and storage medium.

Background technique

The rapid development of online shopping has made the Internet more and more influential on social life, and the variety of goods on the shopping network has become more and more abundant. However, when shopping, users need to spend a lot of time to choose the products they need, and it is difficult to buy their favorite products quickly, which in turn affects the transaction rate of the platform and the shopping efficiency of users.

In order to solve the above-mentioned problems, the current platforms are equipped with a product recommendation mode. However, the existing product recommendation model only recommends popular products, and cannot make the recommended products targeted to users. As a result, the existing product recommendation method is likely to cause poor user experience and cannot stimulate the user's purchasing desire, resulting in unsatisfactory product recommendation effect and difficulty in improving the purchase rate of the recommended product.

SUMMARY OF THE INVENTION

In view of the above technical problems, the present invention proposes a recommendation method, device, electronic device and storage medium. This application determines the scene mode of the commodity that the user belongs to by obtaining the browsing status of the user's historical orders, determines the database corresponding to the commodity through the scene mode, and pushes the commodity information in the database with the high level of the order commodity browsed by the user to the user. For users, the product recommendation method is optimized, so that users can quickly obtain product information related to orders, increase the amount of product previews and improve the transaction rate of products.

In order to solve the above technical problems, the technical solution adopted by the present invention includes four aspects.

In a first aspect, a recommendation method is provided, comprising: acquiring first commodity information in order information triggered by a user; determining, according to the first commodity information, a scene mode of a first commodity corresponding to the first commodity information and determine the database corresponding to the scene mode; determine target commodity information in the database according to the first commodity information; and recommend the target commodity information to the user.

In some embodiments, the first commodity information includes: the original serial number of the commodity; and the determining, according to the first commodity information, the scene mode of the first commodity corresponding to the first commodity information includes: according to the commodity The original number determines the scene mode to which the first commodity belongs.

In some embodiments, the determining the target commodity information in the database according to the first commodity information includes: acquiring second commodity information of each second commodity in the database; according to the second commodity information and The first commodity information determines an association level between the second commodity and the first commodity; and the second commodity information whose association level exceeds an association level threshold is determined as target commodity information.

In some embodiments, after acquiring the first commodity information in the order information triggered by the user, the method further includes: acquiring the number of triggering times of the order information; when the number of triggering times is greater than or equal to a first threshold, Acquire an affiliated commodity of the first commodity corresponding to the first commodity information; and recommend the affiliated commodity to the user.

In some embodiments, the method further includes: acquiring transactional order data; determining a scene mode corresponding to each commodity according to commodity information of each commodity in the order data; establishing a corresponding relationship between each scene mode and the database.

In some embodiments, the method further includes: acquiring commodity information of each commodity in each database; determining an association level between each commodity according to the commodity information of each commodity; and storing the association level between each commodity.

In some embodiments, the commodity information of each commodity includes at least one of the following: price, size, and color.

In some embodiments, after the determining the database corresponding to the scene mode, the method further includes: acquiring popular product information of popular products in the database; Sort popular items; acquire target popular item information in the popular items within the sorting threshold; and recommend the target popular item information to the user.

In a second aspect, the present application provides a recommendation device, comprising: a first acquisition module, configured to acquire first commodity information in order information triggered by a user; a first determination module, adapted to obtain first commodity information according to the first commodity information determining the scene mode of the first commodity corresponding to the first commodity information; and determining the database corresponding to the scene mode; a second determining module, configured to determine target commodity information in the database according to the first commodity information ; a first execution module, configured to recommend the target commodity information to the user.

A third aspect provides an electronic device, comprising a storage and a processor, wherein the storage stores a computer program, and the processor implements the steps of a recommended method when the processor executes the computer program.

A fourth aspect provides a storage medium, where a computer program stored in the storage medium can be executed by one or more processors, and the computer program can be used to implement the steps of any one of the recommended methods in the first aspect.

Beneficial effects created by the invention: the present application determines the scene mode to which the commodity purchased by the user belongs by obtaining the browsing situation of the user's historical orders, determines the database corresponding to the purchased commodity through the scene mode, and then determines the target commodity information in the database, and uses the scene mode to determine the target commodity information. The target product information is pushed to the user, which optimizes the product recommendation method, so that the user can quickly obtain the product information related to the order, increase the product preview volume and improve the product transaction rate.

Description of drawings

The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The drawings included are:

FIG. 1 is an overall flowchart of a recommendation method provided by an embodiment of the present application;

FIG. 2 is a structural block diagram of a recommendation apparatus provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described in further detail below with reference to the accompanying drawings. All other embodiments obtained under the premise of creative work fall within the scope of protection of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" can be the same or a different subset of all possible embodiments, and Can be combined with each other without conflict.

If a similar description of "first\second\third" appears in the application documents, the following description will be added. In the following description, the terms "first\second\third" are only used to distinguish and similar Objects do not represent a specific order for objects. It is understood that "first\second\third" can be interchanged in a specific order or sequence if permitted, so that the embodiments of the present application described herein can be Sequential implementations other than those illustrated or described herein.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

Example 1:

In view of the problems existing in the background art, as shown in FIG. 1 , the present application provides a recommended method, which is applied to an electronic device, and the electronic device may be a server, a mobile terminal, a computer, a cloud platform, or the like. The functions implemented by the device data processing provided by the embodiments of the present application may be implemented by calling a program code by a processor of an electronic device, wherein the program code may be stored in a computer storage medium, and the recommended method includes:

Step S1: Obtain the first commodity information in the order information triggered by the user.

When the user operates the completed order on the online platform, the triggering of the order is completed. The operations here include browsing details, clicking to view, etc. After detecting the user's operation on the order, obtain the order information in the order operated by the user. And obtain the commodity information in the order information, in order to distinguish clearly, the commodity is called the first commodity information.

Step S2: Determine the scene mode to which the first commodity corresponding to the first commodity information belongs according to the first commodity information. And determine the database corresponding to the scene mode.

The first commodity information includes basic commodity information such as the original serial number, price, size, and color of the first commodity.

In some embodiments, step S2 ": determining the scene mode of the first commodity corresponding to the first commodity information according to the first commodity information" includes:

Step S21: Determine the scene mode to which the first commodity belongs according to the commodity original serial number.

The original serial number of the commodity describes the scene mode described by the commodity, that is, the scene that the commodity is commonly used in life. For example, refrigerators are mainly used to store food and are related to cooking. Therefore, refrigerators belong to the kitchen scene, so they can be given an original number according to the functional characteristics of the refrigerator. The format of the original number can be CF-DBX. CF is used to indicate that the product belongs to the kitchen mode, so the scene mode described by the product can be determined by the original serial number of the product.

Therefore, in some embodiments, the recommendation method further discloses how to establish the corresponding relationship between each scene mode and the database. The steps are as follows:

Step S22: Acquire data of orders that have already been executed.

Get all historical order data that has been traded.

Step S23: Determine a scene mode corresponding to each commodity according to commodity information of each commodity in the order data.

The scene mode to which each commodity belongs is determined according to the functional characteristics of each commodity in the historical order data.

Step S24: Establish the correspondence between each scene mode and the database.

Each product in the same scene mode will be divided into different databases according to other product information such as size, color and price. For example, a double-door refrigerator can be attributed to the large-size commodity database in the kitchen scene. For example, a white refrigerator can be attributed to the light-color database in the kitchen scene. Therefore, in addition to determining the scene mode to which the first commodity belongs by the original number, the database corresponding to the scene mode also needs to be determined by the size, price, and color of the first commodity. All the products related to the first product may be recommended to the user.

Step S3: Determine target commodity information in the database according to the first commodity information.

According to the size, color, price, etc. of the first commodity, a plurality of related databases are selected, and a commodity that the user may like is used as a target commodity.

In some embodiments, step S3 "determining target commodity information in the database according to the first commodity information" includes:

Step S31: Acquire second commodity information of each second commodity in the database.

For the convenience of distinction, the second commodity is used here to represent the commodity related to the first commodity in the database. Therefore, the commodity information of the second commodity is the second commodity information.

Step S32: Determine the association level between the second commodity and the first commodity according to the second commodity information and the first commodity information.

In some embodiments, the method of the present application further discloses how to obtain the association level between the second commodity and the first commodity, and the method further includes:

Step S321: Obtain commodity information of each commodity in each database.

Product information includes: product color, price and size.

Step S322: Determine the association level between the commodities according to the commodity information of the commodities.

The association level is determined by various pieces of information of the second commodity. Generally, an association level can be assigned to the second commodity according to various information of the second commodity, and finally the final association level of the second commodity can be obtained. The final association level is the sum of the association level assignments for each piece of information. The assignment of the association level depends on the user's preference characteristics. The association level assignments corresponding to different users are different.

Therefore, the method of the present application also includes:

Step S324: Obtain the historical order record of the user. The user's personal preference is analyzed according to the information of each commodity in the historical order record.

For example, by analyzing all the shopping orders of the user, it is found that the user prefers light-colored products, followed by large-sized products, and finally, in terms of price, he prefers cost-effective products. Then, when determining the association level, the color information of the product will give the product the largest association level assignment, while the size of the commodity is assigned to the second largest association level, and the cost-effectiveness of the product is assigned to the third largest association level. Of course, the association level assignment depends on the similarity with the commodity.

The association level mainly expresses the degree of association between at least two different commodities in the same scene mode. By obtaining the information of the two commodities, the characteristics of the two commodities can be associated, and then the degree of association between the two commodities can be obtained. For example, rice cookers and refrigerators are also in the kitchen scene. Among them, the rice cooker is 100 yuan, which is a low-priced product in the rice cooker, and the 300-yuan refrigerator is also a low-priced product in the refrigerator, so the correlation level between the 100-yuan rice cooker and the 300-yuan refrigerator is assigned. will be larger. But at this time there is still a 1,000-yuan mid-range refrigerator, so the price correlation between a 1,000-yuan refrigerator and a 100-yuan rice cooker will be relatively low.

Step S323: Store the association level between each commodity.

The association level assignments of various commodity information of the commodity are superimposed, and the association level between the commodity and other commodities is finally calculated, and the association level is used as the screening condition in step S32.

Step S33: Determine the second commodity information whose association level exceeds the association level threshold as the target commodity information.

For products whose association level does not exceed the preset association level threshold, they will not be recommended as target products. The associated product threshold depends on the user's purchase rate of the recommended product.

Step S4: Recommend the target commodity information to the user.

Send the product information of the target product to the user. It can be displayed on the terminal that the user is using in the form of a pop-up window, or the user can learn about the target product in other ways. In order to enable users to quickly obtain the product information related to the order, the amount of product preview and the transaction rate of the product are improved.

The above steps S1 to S4 are mainly to recommend products according to the product characteristics of the user's order, but sometimes the user may need to buy products that do not belong to the same scene mode as the purchased product, but may also be additional products of the purchased product or. Ancillary merchandise. For example, if the user's order is a mobile phone, then the user may want to buy accessories such as earphones, data cables, and mobile phone brackets.

Therefore, in some embodiments, after step S1 "obtaining the first commodity information in the order information triggered by the user", the method further includes:

Step S5: Acquire the trigger times of the order information.

Step S6: When the number of triggering times is greater than or equal to the first threshold, acquire an accessory commodity of the first commodity corresponding to the first commodity information.

Generally, when a user triggers order information within a limited number of times, a product recommendation that belongs to the same scene mode as the first product and has a high correlation level will be obtained. However, if the user triggers the order information multiple times, it means that what the user needs is not the product recommendation in the same scenario. It is possible that the user needs an accessory item of the first item. Therefore, when the number of triggering times for the order information is greater than or equal to 3 times, the affiliated commodities of the first commodity are acquired.

Step S7: Recommend the affiliated product to the user.

The product information of the affiliated product is sent to the user. It can be displayed on the terminal that the user is using in the form of a pop-up window, or the user can learn about the target product in other ways. In order to enable users to quickly obtain the information of the affiliated products related to the order, the preview volume of the products and the transaction rate of the products are improved.

In order to improve the transaction rate and preview volume, and there may be errors in the above recommendations, in order to improve the error tolerance rate, the method of the present application also includes recommending popular products to users.

In some embodiments, after step S2 "determining the database corresponding to the scene mode", the method further includes:

Step S81: Obtain popular commodity information of popular commodities in the database.

Step S82: Sort the popular commodities according to the popularity index of the popular commodity information.

The popularity index of a popular product is calculated mainly based on the sales information of the product, such as the purchase rate, repurchase rate, and collection conversion rate of the product by other users.

Step S83: Acquire target popular commodity information within the sorting threshold in the popular commodities.

Step S84: Recommend the target popular commodity information to the user.

The recommendation of popular products is mainly based on the products purchased by different users in the same scene mode to recommend users, so that users can quickly obtain the information of ancillary products related to the order, increase the amount of product preview and improve the transaction of products. Rate.

Example 2:

Based on the foregoing embodiments, the embodiments of the present application provide a recommendation device. Each module included in the device and each unit included in each module can be implemented by a processor in a computer device; of course, it can also be implemented by a specific logic circuit. Implementation; in the process of implementation, the processor can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Microprocessor Unit), a digital signal processor (DSP, Digital Signal Processing) or a field programmable gate array ( FPGA, Field Programmable Gate Array), etc.

As shown in FIG. 2 , a second aspect provides a recommendation apparatus, including: a first acquisition module 1 , a first determination module 2 , a second determination module 3 and a first execution module 4 .

The first obtaining module 1 is configured to obtain the first commodity information in the order information triggered by the user. The first determination module 2 is configured to determine, according to the first commodity information, the scene mode to which the first commodity corresponding to the first commodity information belongs. And determine the database corresponding to the scene mode. The second determining module 3 is configured to determine target commodity information in the database according to the first commodity information. The first execution module 4 is configured to recommend the target commodity information to the user.

In some embodiments, the first determination module 2 includes: a third determination module. The third determination module is configured to determine the scene mode to which the first commodity belongs according to the original number of the commodity.

In some embodiments, the second determination module 3 includes: a second acquisition module, a seventh determination module and a fourth determination module.

The second acquiring module is configured to acquire second commodity information of each second commodity in the database. The seventh determination module is configured to determine the association level between the second commodity and the first commodity according to the second commodity information and the first commodity information. The fourth determination module is configured to determine the second commodity information whose association level exceeds the association level threshold as the target commodity information.

In some embodiments, the recommending apparatus further includes: a third obtaining module, a fourth obtaining module and a second executing module.

The third obtaining module is used for obtaining the trigger times of the order information. The fourth obtaining module is configured to obtain an affiliated product of the first product corresponding to the first product information when the number of triggering times is greater than or equal to the first threshold. The third execution module is used for recommending the affiliated product to the user.

In some embodiments, the recommending apparatus further includes: a fifth acquiring module, a fifth determining module and a fourth executing module.

The fifth obtaining module is used to obtain the executed order data. The fifth determination module is configured to determine the scene mode corresponding to each commodity according to commodity information of each commodity in the order data. The fourth execution module is used to establish the corresponding relationship between each scene mode and the database.

In some embodiments, the recommending apparatus further includes: a sixth obtaining module, a sixth determining module and a fifth executing module.

The sixth acquiring module is used for acquiring commodity information of each commodity in each database. The sixth determination module is used for determining the association level between the various commodities according to the commodity information of each commodity. The fifth execution module is used for storing the association level between the various commodities.

In some embodiments, the recommending apparatus further includes: a seventh obtaining module, a sixth executing module, an eighth obtaining module and a seventh executing module.

The seventh obtaining module is used for obtaining popular commodity information of popular commodities in the database. The sixth execution module is configured to sort the popular commodities according to the popularity index of the popular commodity information. The eighth acquisition module is configured to acquire target hot commodity information within the sorting threshold in the hot commodities. The seventh execution module is used for recommending the target popular commodity information to the user.

All or part of each module in the above-mentioned recommended apparatus may be implemented by software, hardware, or a combination thereof. The above modules may be embedded in or independent of the processor in the device in the form of hardware, and may also be stored in the memory of the processing device in the form of software, so that the processor can call and execute operations corresponding to the above modules. It should be noted that, the division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

Example 3:

A third aspect provides an electronic device including a storage and a processor, the storage stores a computer program, and the processor implements steps of a recommended method when executing the computer program.

Example 4:

A fourth aspect provides a storage medium, the storage medium stores a computer program that can be executed by one or more processors, and the computer program can be used to implement the steps of any one of the methods recommended in the first aspect.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. The non-volatile memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, and the like. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM).

It is to be understood that reference throughout the specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic associated with the embodiment is included in at least one embodiment of the present application. Thus, appearances of "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not imply the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation. The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms. of.

The unit described above as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit; it may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be all integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integration The unit can be implemented either in the form of hardware or in the form of hardware plus software functional units.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware, the aforementioned program may be stored in a computer-readable storage medium, and when the program is executed, the execution includes: The steps of the above method embodiments; and the aforementioned storage medium includes: a removable storage device, a read only memory (ROM, Read Only Memory), a magnetic disk or an optical disk and other media that can store program codes.

Alternatively, if the above-mentioned integrated units of the present application are implemented in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products in essence or in the parts that make contributions to the prior art. The computer software products are stored in a storage medium and include several instructions for One controller is made to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.

The above is only the embodiment of the present application, but the protection scope of the present application is not limited to this. Covered within the scope of protection of this application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims (11)

1. a recommendation method, is characterized in that, comprises: Obtain the first commodity information in the order information triggered by the user; Determine the scene mode to which the first commodity corresponding to the first commodity information belongs according to the first commodity information; and determine the database corresponding to the scene mode; determining target commodity information in the database according to the first commodity information; The target commodity information is recommended to the user. 2 . The recommendation method according to claim 1 , wherein the first commodity information comprises: an original commodity number; the first commodity information corresponding to the first commodity information is determined according to the first commodity information. 3 . The scene mode to which the product belongs, including: The scene mode to which the first commodity belongs is determined according to the original commodity number. 3 . The recommendation method according to claim 1 , wherein the determining the target commodity information in the database according to the first commodity information comprises: 3 . acquiring second commodity information of each second commodity in the database; Determine the association level between the second commodity and the first commodity according to the second commodity information and the first commodity information; The second commodity information whose association level exceeds the association level threshold is determined as the target commodity information. 4. A recommendation method according to claim 1, characterized in that after acquiring the first commodity information in the order information triggered by the user, the method further comprises: obtaining the trigger times of the order information; When the number of triggers is greater than or equal to the first threshold, acquiring the affiliated commodities of the first commodity corresponding to the first commodity information; The affiliated product is recommended to the user. 5. A recommendation method according to claim 3, wherein the method further comprises: Get the executed order data; Determine the scene mode corresponding to each commodity according to the commodity information of each commodity in the order data; Establish the corresponding relationship between each scene mode and the database. 6. The method according to claim 5, wherein the method further comprises: Obtain the commodity information of each commodity in each database; Determine the association level between each commodity according to the commodity information of each commodity; Stores the level of association between each item. 7. The method according to claim 6, wherein the commodity information of each commodity comprises at least one of the following: price, size, and color. 8. A recommendation method according to claim 1, characterized in that after said determining the database corresponding to the scene mode, the method further comprises: Obtain popular commodity information of popular commodities in the database; Sort the popular commodities according to the popularity index of the popular commodity information; Obtain target popular product information within the sorting threshold in the popular products; The target popular commodity information is recommended to the user. 9. A recommending device, characterized in that it comprises: a first obtaining module, configured to obtain the first commodity information in the order information triggered by the user; a first determining module, configured to determine the scene mode to which the first commodity corresponding to the first commodity information belongs according to the first commodity information; and determine the database corresponding to the scene mode; a second determining module, configured to determine target commodity information in the database according to the first commodity information; The first execution module is used for recommending the target commodity information to the user. 10. An electronic device, characterized in that, comprising: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, a recommended method according to any one of claims 1 to 8 is executed. 11. A storage medium, characterized in that, a computer program stored in the storage medium can be executed by one or more processors, and the computer program can be used to implement any one of claims 1 to 8. steps of a recommended method.

Images