CN116245609A

CN116245609A - Shopping recommendation method, system, device and storage medium

Info

Publication number: CN116245609A
Application number: CN202310186978.0A
Authority: CN
Inventors: 林毕成
Original assignee: Shanghai Zhongtongji Network Technology Co Ltd
Current assignee: Shanghai Zhongtongji Network Technology Co Ltd
Priority date: 2023-02-28
Filing date: 2023-02-28
Publication date: 2023-06-09

Abstract

The application relates to the technical field of artificial intelligence and intelligent recommendation, in particular to a shopping recommendation method, system, device and storage medium, comprising the following steps: acquiring user related data information; obtaining behavior feature vector information by utilizing the user related data information; constructing an engine recommendation model by utilizing the behavior feature vector information; and generating recommendation information by using the engine recommendation model, and sending the recommendation information to related users. By utilizing the engine recommendation model, recommendation information is generated and sent to related users, so that the purchasing requirements of customers can be accurately positioned, and intelligent recommendation can be realized.

Description

Shopping recommendation method, system, device and storage medium

Technical Field

The application relates to the technical field of artificial intelligence and intelligent recommendation, in particular to a shopping recommendation method, system, device and storage medium.

Background

Consumers (users) may not actually obtain their own desired or useful goods from them when faced with a large amount of information or items. At the same time, manufacturers have trouble in how to present their own merchandise to more users and how to stand out from a huge amount of merchandise. The conventional shopping recommendation system adopts an algorithm that the user submits the purchase requirement, combines the user position, the article type and the like to recommend the commodity, but the commodity recommended by the method has low association degree with the client, and cannot accurately position the purchase requirement of the client to conduct intelligent recommendation.

In the prior art, the correlation degree between the commodity recommended by the current shopping recommendation system and the client is low, and the method can accurately position the purchase demand of the client and intelligently recommend the commodity.

Disclosure of Invention

In order to overcome the problem that the correlation degree between commodities recommended by the current shopping recommendation system and clients is low to at least a certain extent in the related technology, and the purchasing demands of the clients are accurately positioned and intelligent recommendation is carried out, the application provides a shopping recommendation method, a shopping recommendation system, a shopping recommendation device and a storage medium.

The scheme of the application is as follows:

in a first aspect, the present application provides a method of shopping recommendation, the method comprising:

acquiring user related data information;

obtaining behavior feature vector information by utilizing the user related data information;

constructing an engine recommendation model by utilizing the behavior feature vector information;

and generating recommendation information by using the engine recommendation model, and sending the recommendation information to related users.

Further, the user-related data information includes:

user basic attribute information and user behavior data information.

Further, the obtaining behavior feature vector information by using the user related data information includes:

and extracting the behaviors of the user behavior data information by using the related data information through a behavior event analysis method to obtain behavior feature vector information.

Further, the constructing an engine recommendation model by using the behavior feature vector information includes:

searching content information of interest of a user through a collaborative filtering algorithm by utilizing behavior feature vector information, and acquiring a first interest region collection;

searching content information of interest of a user by using the behavior feature vector information through a content-based recommendation algorithm, and acquiring a second interest region collection;

and combining the first region of interest collection and the second region of interest collection based on a background setting rule to obtain the region of interest information of the user.

In a second aspect, the present application provides a shopping recommendation system, the system comprising:

the acquisition module is used for acquiring the related data information of the user;

the feature extraction module is used for obtaining behavior feature vector information by utilizing the user related data information;

the model construction module is used for constructing an engine recommendation model by utilizing the behavior feature vector information;

and the recommending module is used for generating recommending information by utilizing the engine recommending model and sending the recommending information to related users.

In a third aspect, the present application provides an apparatus for shopping recommendation, the apparatus comprising:

a memory having an executable program stored thereon;

a processor for executing the executable program in the memory to implement the steps of any of the methods described above.

In a fourth aspect, the present application provides a computer readable storage medium storing computer instructions for causing a computer to perform the steps of any one of the methods described above.

The technical scheme that this application provided can include following beneficial effect:

the method and the device acquire the relevant data information of the user; obtaining behavior feature vector information by utilizing the user related data information; constructing an engine recommendation model by utilizing the behavior feature vector information; and generating recommendation information by using the engine recommendation model, and sending the recommendation information to related users. By utilizing the engine recommendation model, recommendation information is generated and sent to related users, so that the purchasing requirements of customers can be accurately positioned, and intelligent recommendation can be realized.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

FIG. 1 is a flow diagram of a method for shopping recommendation provided in one embodiment of the present application;

FIG. 2 is a schematic diagram of a shopping recommendation system according to another embodiment of the present application;

FIG. 3 is a schematic diagram of the apparatus composition of a shopping recommendation according to another embodiment of the present application.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.

Example 1

Referring to fig. 1, fig. 1 is a flowchart of a method for recommending shopping according to an embodiment of the present application, where the method includes:

s1, acquiring relevant data information of a user;

s2, obtaining behavior feature vector information by utilizing the user related data information;

s3, constructing an engine recommendation model by utilizing behavior feature vector information;

s4, generating recommendation information by using the engine recommendation model, and sending the recommendation information to related users.

In one embodiment, as described in step S1, the acquiring the user related data information includes: user basic attribute information and user behavior data information.

In particular, the main basis for how to determine whether a user is interested is derived from known user data, essentially based on statistical data inference. It is important that what is described herein is of possible interest. While referring to user data, it is necessary to mention the main types of user data that facilitate subsequent understanding and expansion:

user basic attributes: here, mainly user geographical information, user social attribute data (gender, age, etc.), and the like.

User behavior data: here, mainly the mail, the receipt data, etc. of the user. Of course, considering the results of human behavioral dynamics studies (in most cases, human attention to a matter can last only a short time), there is also a need to do resolution, i.e. historical behavioral data and real-time behavioral data.

In one embodiment, as described in step S2, the obtaining the behavior feature vector information by using the user-related data information includes:

In the embodiment of the application, the behavior event analysis method is mainly used for extracting behaviors of the user behavior data information, and for the specific behaviors, people (white), time (white), places (white), interactions (How) and interaction content (What) are firstly defined and aggregated to form a complete user behavior event.

Wherein, who is the participation subject of the event, such as user id, equipment id and the like; when, time of event occurrence; where, the place Where the event happens, such as through ip address resolution, GPS acquisition; how the user engages in behavior, such as the equipment used, app version, channel, etc.; what is specific to What the user does in the event, such as for a purchase event, may include purchasing commodity name, type, quantity, amount, payment means, etc.

After the definition is completed, multidimensional drill-down analysis is needed to be performed, subdivision is performed, the reason for the behavior is confirmed, and the behavior generating the phenomenon is found out for the existing phenomenon. Such as what the behavior of a new user clicking on the login and skipping the login differs under the login page. The reasons are found by defining the user behavior events and then splitting the events in multiple dimensions (such as location, event, app version, etc.).

In particular implementations, user behavior causes an association to be made between a user and a commodity. Because of one interaction, a contact is made. Thus, there is an association relationship. This "interaction" is in fact: item type, times, clicks, orders, etc. And the user can analyze a large amount of historical behavior data according to the user through an event analysis method to obtain behavior characteristic vector information.

In this embodiment of the present application, the behavior of the user behavior data information is extracted by a behavior event analysis method, and after obtaining behavior feature vector information, the method further includes:

and acquiring association information between the user and the commodity, wherein the commodity characteristics are specifically derived from descriptions of different dimensions of the commodity. Here replaced by commodity attributes. The more commodity attributes, the more commodity features are enriched. Attributes are the basic elements that make up a feature. The same is true for the user features. The inherent characteristics (usually described by user labels) of the user are established through the user attributes, and the user and the commodity are associated through active actions (such as geographic positions, mobile phone numbers, number of delivery, number of signing and receiving, signing and receiving duration and the like), so that the connection between the user and the commodity is established, and a foundation is laid for commodity recommendation.

In one embodiment, as described in step S3, the building an engine recommendation model using the behavior feature vector information includes:

In this embodiment of the present application, the combination processing is performed based on a background setting rule to obtain the information of the region of interest of the user, by combining a collaborative filtering algorithm and a recommendation algorithm based on content, after obtaining respective region of interest sets, that is, prediction result sets, the optimal combination result set is obtained based on a rule set by a system background or based on manual processing, and the optimal combination result set is a set that avoids defects of the two algorithms to the greatest extent, and intelligent recommendation is performed by using the optimal combination result set.

Specifically, the collaborative filtering algorithm (Collaborative Filtering) is a relatively classical and commonly used recommendation algorithm, which is a recommendation algorithm that relies entirely on the behavioral relationship between the user and the item. From its name "collaborative filtering", we can snoop on the principle behind it, namely "collaborative feedback, evaluation and opinion," together filter massive information, and screen out information that may be of interest to the user. Collaborative filtering algorithms are mainly divided into two categories:

collaborative filtering algorithm based on articles: the user is recommended items similar to the items he liked before.

Collaborative filtering algorithm based on user: the user is recommended what the user likes similar to his interests.

In the embodiment of the application, we choose a collaborative filtering algorithm based on users: such an algorithm that recommends the user the items that the user likes that are similar to his interests.

Specifically, the theoretical basis of the content-based information recommendation method mainly comes from information retrieval and information filtering, and the content-based recommendation method recommends recommended items to the user that the user has not contacted according to the browsing records in the past of the user. Content-based recommendation methods, heuristic methods and model-based methods, are described primarily from two approaches.

The heuristic method is that a user defines a related calculation formula by experience, then verifies according to the calculation result and the actual result of the formula, and then continuously modifies the formula to achieve the final purpose. The method for model is to take the past data as the data set and learn a model according to the data set.

In particular, content-based recommendation (CB for short) is based on Content information of an item, and does not need to rely on evaluation opinion of the item by a user, and more interest materials of the user need to be obtained from the feature description cases of the Content by a machine learning method. The simple understanding is that according to the attribute of the recommended items, the relevance among the items is calculated, and then according to the preference record of the user, the items with high similarity are recommended to the user.

In the embodiment of the application, when the system is established, enough user information is not collected yet, the collaborative filtering algorithm cannot find a suitable neighbor for a specified user, so that recommendation prediction cannot be provided for the user. For newly registered users, the collaborative filtering algorithm cannot recommend goods for the new users because the system has no historical data information. For cold products, such as newly added products or relatively small products, they may not be recommended to the user. To overcome the above drawbacks, embodiments of the present application generally use multiple recommendation strategies for complementation, rather than just using a single recommendation strategy. The common thinking is:

if the recommended varieties are less, the predicted values of various recommendation algorithms including, but not limited to, content-based recommendation algorithms, association rule-based recommendation algorithms, utility-based association algorithms, knowledge-based recommendation algorithms may be weighted to obtain final predicted values for ranking recommendation.

Example two

Referring to fig. 2, fig. 2 is a schematic diagram illustrating a system composition of shopping recommendation according to another embodiment of the present application, where the system includes:

an acquisition module 101, configured to acquire user related data information;

the feature extraction module 102 is configured to obtain behavior feature vector information by using the user related data information;

the model construction module 103 is used for constructing an engine recommendation model by utilizing the behavior feature vector information;

and the recommendation module 104 is used for generating recommendation information by utilizing the engine recommendation model and sending the recommendation information to related users.

Example III

Referring to fig. 3, fig. 3 is a schematic view illustrating an apparatus for recommending shopping according to another embodiment of the present application, where the apparatus includes:

a memory 31 on which an executable program is stored;

a processor 32 for executing the executable program in the memory 31, with the steps of the method as claimed in any one of the preceding claims.

Furthermore, the present application provides a computer readable storage medium storing computer instructions for causing a computer to perform the steps of any one of the methods described above. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.

It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.

It should be noted that in the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present application, unless otherwise indicated, the meaning of "plurality" means at least two.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims

1. A method of shopping recommendation, the method comprising:

acquiring user related data information;

2. The method of claim 1, wherein the user-related data information comprises:

user basic attribute information and user behavior data information.

3. The method of claim 1, wherein the obtaining behavior feature vector information using the user-related data information comprises:

4. The method of claim 1, wherein constructing an engine recommendation model using behavior feature vector information comprises:

5. A system for shopping recommendation, the system comprising:

6. An apparatus for shopping recommendation, the apparatus comprising:

a memory having an executable program stored thereon;

a processor for executing the executable program in the memory to implement the steps of the method of any one of claims 1-4.

7. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the steps of the method according to any one of claims 1-4.