Item recommendation method, computing device, electronic device, and storage medium

Abstract

This application discloses a method, computing device, electronic device, and storage medium for item recommendation, relating to the fields of artificial intelligence and data processing. The method includes: in response to receiving an item recommendation request, extracting features from the object information of the requesting object to obtain object features, and extracting features from at least one item to be recommended to obtain initial features of at least one item to be recommended; enhancing the initial features of any item to be recommended based on the independent features of any item to be recommended to obtain target features of any item to be recommended; determining a target item from the at least one item to be recommended based on the object features and the target features of the at least one item to be recommended; and outputting the target item. This application solves the technical problem in related technologies where recommended items fail to meet user preferences.

Description

Technical Field

[0001] This application relates to artificial intelligence technology and data processing, and more specifically, to a method for recommending items, a computing device, an electronic device, and a storage medium. Background Technology

[0002] With the rapid development of the Internet and e-commerce, personalized item recommendation systems have become a key technology for improving user experience and business value. Currently, item recommendation systems can usually recommend products or content that can meet user needs by analyzing users' historical behavior, recommendation requests, and other content. However, in actual item recommendation, the items that users see can usually only meet the user's needs contained in the recommendation request, but cannot meet the user's interest in different items.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method for recommending items, a computing device, an electronic device, and a storage medium to at least solve the technical problem in related technologies that the items recommended to users cannot meet the user's preferences.

[0005] According to one aspect of the embodiments of this application, an item recommendation method is provided, comprising: in response to receiving an item recommendation request, performing feature extraction on object information of a requesting object to obtain object features, and performing feature extraction on at least one item to be recommended to obtain initial features of at least one item to be recommended, wherein the requesting object is used to characterize the object that sent the item recommendation request; performing feature enhancement on the initial features of any item to be recommended based on the independent features of any item to be recommended to obtain target features of any item to be recommended, wherein the independent features are used to characterize the interests and preferences of a search object, and the search object is used to search for any item to be recommended; determining a target item from the at least one item to be recommended based on the object features and the target features of the at least one item to be recommended; and outputting the target item.

[0006] According to one aspect of the embodiments of this application, an item recommendation method is also provided, comprising: responding to an input instruction applied to an operation interface, displaying on the operation interface initial features of at least one item to be recommended, and object features of a requesting object, wherein the requesting object is used to characterize the object sending the item recommendation request; and responding to a processing instruction applied to the operation interface, displaying on the operation interface a target item, wherein the target item is determined from at least one item to be recommended by the object features and the target features of at least one item to be recommended, the target features being obtained by feature enhancement of the initial features of any item to be recommended by an independent feature of any item to be recommended, the independent feature being used to characterize the interests and preferences of a search object, and the search object being used to search for any item to be recommended.

[0007] According to one aspect of the embodiments of this application, an item recommendation method is also provided, comprising: obtaining object features of a requesting object and initial features of at least one item to be recommended by calling a first interface, wherein the requesting object is used to characterize the object sending the item recommendation request, the first interface includes a first parameter, the parameter value of the first parameter including the object features and the initial features; performing feature enhancement on the initial features of any item to be recommended based on the independent features of any item to be recommended to obtain target features of any item to be recommended, wherein the independent features are used to characterize the interests and preferences of a search object, and the search object is used to search for any item to be recommended; determining a target item from at least one item to be recommended based on the object features and the target features of at least one item to be recommended; and outputting the target item by calling a second interface, wherein the second interface includes a second parameter, the parameter value of the second parameter including the target item.

[0008] According to one aspect of the embodiments of this application, an item recommendation device is provided, comprising: a feature extraction module, configured to, in response to receiving an item recommendation request, extract features from object information of a requesting object to obtain object features, and extract features from at least one item to be recommended to obtain initial features of at least one item to be recommended, wherein the requesting object is used to characterize the object that sent the item recommendation request; a feature enhancement module, configured to enhance the initial features of any item to be recommended based on independent features of any item to be recommended to obtain target features of any item to be recommended, wherein the independent features are used to characterize the interests and preferences of a search object, and the search object is used to search for any item to be recommended; an item determination module, configured to determine a target item from at least one item to be recommended based on the object features and the target features of at least one item to be recommended; and an item output module, configured to output the target item.

[0009] According to one aspect of the embodiments of this application, an item recommendation device is also provided, comprising: a first display module, configured to respond to an input command applied to an operation interface, display on the operation interface initial features of at least one item to be recommended, and object features of a requesting object, wherein the requesting object is used to characterize the object sending the item recommendation request; and a second display module, configured to respond to a processing command applied to the operation interface, displaying a target item on the operation interface, wherein the target item is determined from at least one item to be recommended by the object features and the target features of at least one item to be recommended, the target features are obtained by feature enhancement of the initial features of any item to be recommended by an independent feature of any item to be recommended, the independent feature being used to characterize the interests and preferences of a search object, and the search object being used to search for any item to be recommended.

[0010] According to one aspect of the embodiments of this application, an item recommendation device is also provided, comprising: a first invocation module, configured to obtain object features of a requesting object and initial features of at least one item to be recommended by invoking a first interface, wherein the requesting object is used to characterize the object sending the item recommendation request, the first interface includes a first parameter, the parameter value of the first parameter including the object features and the initial features; an enhancement module, configured to perform feature enhancement on the initial features of any item to be recommended based on independent features of any item to be recommended, to obtain target features of any item to be recommended, wherein the independent features are used to characterize the interests and preferences of a search object, and the search object is used to search for any item to be recommended; a determination module, configured to determine a target item from at least one item to be recommended based on the object features and the target features of at least one item to be recommended; and a second invocation module, configured to output the target item by invoking a second interface, wherein the second interface includes a second parameter, the parameter value of the second parameter including the target item.

[0011] According to another aspect of the embodiments of this application, a computing device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0012] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory storing an executable program; and a processor connected to the memory via a bus for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0014] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the methods in various embodiments of this application.

[0016] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0017] In this embodiment, in response to receiving an item recommendation request, feature extraction is performed on the object information of the requesting object to obtain object features, and feature extraction is performed on at least one item to be recommended to obtain initial features of at least one item to be recommended; feature enhancement is performed on the initial features of any item to be recommended based on the independent features of any item to be recommended to obtain target features of any item to be recommended; based on the object features and the target features of at least one item to be recommended, a target item is determined from at least one item to be recommended; and the target item is output. By using the independent features of the item to be recommended to enhance the initial features of the item to be recommended to obtain target features for determining the user's interest in the item to be recommended, and using the target features and the object features of the requesting object to determine the target item, the matching degree between the determined target item and the user's preferences can be greatly improved, thereby improving the user's experience of using the item recommendation system, and thus solving the technical problem in related technologies that the items recommended to the user cannot meet the user's preferences.

[0018] It is worth noting that the general description above and the detailed description that follow are merely for illustrative purposes and do not constitute a limitation on this application. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a schematic diagram illustrating an application scenario of an item recommendation method according to an embodiment of this application;

[0021] Figure 2 This is a flowchart illustrating an item recommendation method according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram illustrating an item search process according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram illustrating an item recommendation process according to an embodiment of this application;

[0024] Figure 5 This is a flowchart illustrating another method for recommending items according to an embodiment of this application;

[0025] Figure 6 This is a flowchart illustrating another method for recommending items according to an embodiment of this application;

[0026] Figure 7 This is a structural block diagram of an article recommendation device according to an embodiment of this application;

[0027] Figure 8 This is a structural block diagram of another article recommendation device according to an embodiment of this application;

[0028] Figure 9 This is a structural block diagram of another article recommendation device according to an embodiment of this application;

[0029] Figure 10 This is a structural block diagram of a computing device according to an embodiment of this application;

[0030] Figure 11 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0034] Search: In some recommendation systems, the process by which users initiate search terms or images to find items based on those search terms or images.

[0035] Features: The data input into the model can be applied to the process of recommending items using the model.

[0036] Counterfactual learning: a technique for exploring the effects of interference on a target before and after intervention and quantifying the role of the interference component.

[0037] According to an embodiment of this application, an item recommendation method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0038] Considering that the model parameters used in the above-mentioned item recommendation method may be very large, while the computing resources of mobile terminals are limited, the method provided in this application embodiment can be applied to, for example, Figure 1 The application scenarios shown are not limited to these. Figure 1 This is a schematic diagram illustrating an application scenario of an item recommendation method according to an embodiment of this application. Figure 1In the application scenario shown, the model used in the above-described item recommendation method can be deployed on server 10. Server 10 can connect to one or more client devices 20 via a local area network (LAN), wide area network (WAN), internet connection, or other types of data network. Client devices 20 may include, but are not limited to, smartphones, tablets, laptops, PDAs, personal computers, smart home devices, and in-vehicle devices. Client devices 20 can interact with users through a graphical user interface to invoke the model, thereby implementing the method provided in this application embodiment.

[0039] In this embodiment, the system consisting of a client device and a server can perform the following steps: the client device executes an input item recommendation request; and outputs the target item. The server performs feature extraction on the object information of the requested object to obtain object features, and performs feature extraction on at least one item to be recommended to obtain corresponding initial features; based on the independent features of any item to be recommended, the initial features of any item to be recommended are enhanced to obtain the target features of any item to be recommended; based on the object features and the target features of at least one item to be recommended, the target item is determined from at least one item to be recommended.

[0040] It should be noted that with the rapid development of high-performance computing units, the methods provided in this application embodiment can also be applied to model-in-machine systems in other application scenarios. In one optional embodiment, the model-in-machine system has multiple built-in models. Users can select one model to adjust as needed to obtain their own model. The high-performance computing unit built into the model-in-machine system can then directly call the adjusted model to execute the methods provided in this application embodiment. In another optional embodiment, the model-in-machine system has a pre-trained model built-in. Therefore, the high-performance computing unit built into the model-in-machine system can directly call this model to execute the methods provided in this application embodiment.

[0041] Furthermore, when users need to train their own models, they can upload their own datasets via the client. These datasets are then sent to the server, allowing the server to adjust the pre-trained model using the dataset to obtain the user's customized model, which can then be deployed to the production environment. To facilitate users' model adjustment needs, the server provides complete adjustment tools, development frameworks, and processes, supporting multiple adjustment strategies. This allows the adjusted model to better adapt to different application domains and achieve a high degree of customization.

[0042] Under the aforementioned operating environment, this application provides the following: Figure 2 Recommended methods for the items shown. Figure 2 This is a flowchart illustrating an item recommendation method according to an embodiment of this application. For example... Figure 2 As shown, the method may include the following steps:

[0043] Step S202: In response to receiving an item recommendation request, feature extraction is performed on the object information of the requesting object to obtain object features, and feature extraction is performed on at least one item to be recommended to obtain initial features of at least one item to be recommended.

[0044] The request object is used to represent the object that sends the item recommendation request.

[0045] The aforementioned request object can refer to other servers that have a communication relationship with the item recommendation system, or to the user currently using the item recommendation system. The following explanation uses the user as an example. The aforementioned items to be recommended can refer to items searched from the database based on the request object's, such as the user's, needs. These can include, but are not limited to: physical goods in real-world scenarios such as clothing, vehicles, and furniture, and virtual goods in virtual environments such as digital collectibles, accounts, and online courses.

[0046] In one optional embodiment, when recommending items to a user, the current item recommendation system can first determine the user's needs based on the user's search behavior, and then search for the aforementioned items to be recommended from a database storing different items based on the user's needs. Then, it can integrate the relevant information of the searched items to be recommended, such as the attribute characteristics of the items to be recommended and the search data generated when searching for the items to be recommended, and display the aforementioned items to be recommended to the user based on the integrated information, so that the items to be recommended displayed to the user can meet the user's needs. While item recommendation systems consider relevant user information, such as the behavioral characteristics corresponding to the user's search behavior, and present recommended items to the user based on these characteristics to ensure the final item display effect, it is important to note that when users view different items, in addition to considering their objective needs for different items, they also have certain subjective thoughts, such as their level of interest in different items. As shown above, current item recommendation systems only apply the behavioral characteristics corresponding to the user's search behavior to the item recommendation process, ignoring the difference between the user's search intent and general interests. For example, suppose a user has a need for items A and B, but is not interested in item A. When selecting items, the user may not choose item A. In this case, if the item recommendation system shows the user item A first and then item B, it may negatively affect the user's experience of using the item recommendation system.

[0047] Therefore, when actually recommending the searched items to users, the item recommendation system can additionally incorporate the user's level of interest in different items to ensure that the final item recommendations meet the user's needs while improving the user experience. In order to accurately determine the user's level of interest in different items, after receiving an item recommendation request, the item recommendation system can first obtain the object information of the requesting object and the item information of at least one item to be recommended to the user. Then, it can perform feature extraction on the obtained object information to obtain the corresponding object features of the requesting object, and simultaneously perform feature extraction on the item information to obtain the initial features of at least one item to be recommended. Based on the object features of the requesting object and the initial features of different items to be recommended, the recommendation system can determine the association between the requesting object and different items to be recommended, thereby determining the requesting object's level of interest in different items to be recommended.

[0048] Step S204: Based on the independent features of any item to be recommended, perform feature enhancement on the initial features of any item to be recommended to obtain the target features of any item to be recommended.

[0049] Among them, independent features are used to characterize the interests and preferences of the search object, which is used to search for any item to be recommended.

[0050] The search target mentioned above can refer to the object performing actions such as keyword search or item query, and can be the same as the request object, such as a user sending an item recommendation request. The independent features mentioned above can refer to features related to the user's level of interest, reflecting the user's interest preferences in the search target. By changing the independent features of an item, the user's level of interest in the item can be changed accordingly.

[0051] In one optional embodiment, considering that an item's characteristics typically consist of both dynamic and static features, dynamic features, also known as query features, refer to features related to the user's query behavior. These features can be applied to the process of searching for recommended items and have a certain degree of subjectivity and immediacy. For example, if the user inputs the keyword "metal eyeglass frames," the dynamic features could be "metal" and "eyeglass frames." If the user inputs the keyword "plastic eyeglass frames," the dynamic features could be "plastic" and "eyeglass frames." The dynamics can change with the user's query behavior. The item recommendation system can determine whether an item meets the user's needs based on its dynamic features to perform the item search. Static features can also be... The aforementioned independent features can refer to the inherent characteristics of an item itself, possessing a certain degree of objectivity. Static features do not change with changes in user query behavior. Different static features may have different levels of appeal to users, and a user's level of interest in an item will be influenced by its static features. For example, suppose a user enters the keyword "metal eyeglass frames." Based on this keyword, the item recommendation system can search for multiple eyeglass frames made of metal. However, the static features of these eyeglass frames, such as color, texture, and style, may be different, and the user's preference for these static features may also be different. Through these static features, it is possible to determine the metal eyeglass frames that the user is more likely to choose, thereby ensuring that the items ultimately recommended to the user can well meet the user's expectations.

[0052] Based on this, in order to better recommend different items to users, after extracting the initial features of different items to be recommended, the item recommendation system can further obtain the independent features of different items to be recommended, and use these independent features to enhance the extracted initial features to obtain rich and informative item representations, that is, to obtain the aforementioned target features. This allows the item recommendation system to provide users with more accurate item recommendation results based on the target features of different items to be recommended.

[0053] Step S206: Based on object features and target features of at least one item to be recommended, determine the target item from at least one item to be recommended.

[0054] In one optional embodiment, after obtaining the target features of different items to be recommended, considering that both the object features of the requesting object and the target features of the items to be recommended can reflect the user's degree of interest in different items to be recommended, in order to recommend items to the user more accurately, the item recommendation system can combine the extracted object features and the obtained target features to determine the user's degree of interest in different items to be recommended based on the object features and target features, so as to ensure the accuracy of the determined degree of interest. Then, based on the determined degree of interest, the system can determine the target items that will be liked by the user from the above-mentioned at least one item to be recommended, thereby ensuring the accuracy of the determined target items.

[0055] Step S208: Output the target item.

[0056] In one optional embodiment, after identifying the target item, the item recommendation system can display the target item in the user interface for easy viewing. To ensure a good user experience when viewing the target item, the system can first display items of high user interest in areas the target frequently browses, and items of lower user interest in other areas, as well as other items from the list of recommended items besides the target item. Alternatively, considering that the target item satisfies the user's preferences, to improve the efficiency of displaying items to the user, the system can first display the target item in the user interface, and then display other items from the list of recommended items besides the target item when the user requests further viewing.

[0057] In this embodiment, in response to receiving an item recommendation request, feature extraction is performed on the object information of the requesting object to obtain object features, and feature extraction is performed on at least one item to be recommended to obtain initial features of at least one item to be recommended; feature enhancement is performed on the initial features of any item to be recommended based on the independent features of any item to be recommended to obtain target features of any item to be recommended; based on the object features and the target features of at least one item to be recommended, a target item is determined from at least one item to be recommended; and the target item is output. By using the independent features of the item to be recommended to enhance the initial features of the item to be recommended to obtain target features for determining the user's interest in the item to be recommended, and using the target features and the object features of the requesting object to determine the target item, the matching degree between the determined target item and the user's preferences can be greatly improved, thereby improving the user's experience of using the item recommendation system, and thus solving the technical problem in related technologies that the items recommended to the user cannot meet the user's preferences.

[0058] In this embodiment of the application, before performing feature enhancement on the initial features of any item to be recommended based on the independent features of any item to be recommended, the above method further includes: extracting features from the item recommendation request to obtain the request features of the item recommendation request; constructing a feature evaluation score corresponding to any recommended item based on the initial features, request features, and object features, wherein the feature evaluation score is used to reflect the association between any item to be recommended, the item recommendation request, and the request object; inputting the initial features and feature evaluation scores into the feature evaluation model, and using the feature evaluation model to determine independent features from the initial features.

[0059] In one optional embodiment, to accurately enhance the initial features, the item recommendation system can first determine the corresponding independent features from the initial features of the item to be recommended before using independent features to enhance the initial features. Considering that the independent features of an item are generally not affected by the user's query behavior, but the user's interest in the item changes accordingly when the independent features change, the item recommendation system can establish a mapping curve between object features, initial features, and requested features for different initial features of the item. This reflects the correlation between the different initial features of the item, the item search process, and the user's interest. By controlling the changes in the initial features, the system can determine the changes in the corresponding constructed correlations, and thus determine the type of item feature, i.e., whether it belongs to an independent feature, based on the changes in the correlations. Based on this, when determining the independent features of an item to be recommended, the item recommendation system can first extract features from the item recommendation request to obtain the corresponding request features. Then, based on the extracted initial features of the item to be recommended, the object features of the request object, and the request features of the item recommendation request, the system can construct the association between any one of the items to be recommended, the item recommendation request, and the request object to obtain the feature evaluation score of any one of the items to be recommended. The constructed feature evaluation score is then input into a pre-constructed feature evaluation model to determine the corresponding independent features from the extracted initial features using the feature evaluation score.

[0060] In this embodiment of the application, the feature evaluation score includes: a first evaluation score between any item to be recommended and the requesting object, and a second evaluation score between any item to be recommended and the item recommendation request; constructing a feature evaluation score corresponding to any recommended item based on the initial features, request features, and object features includes: matching the object features with the initial features to obtain the first evaluation score; and matching the request features with the initial features to obtain the second evaluation score.

[0061] In one optional embodiment, to clearly reflect the relationship between any item to be recommended, the item recommendation request, and the requesting object, a first evaluation score can be set for each item to be recommended and the requesting object. This first evaluation score reflects the relationship between the item to be recommended and the requesting object, such as the user's level of interest in the item to be recommended. Simultaneously, a second evaluation score can be set for each item to be recommended and the item recommendation request. This second evaluation score reflects the relationship between the item to be recommended and the item recommendation request, such as whether the item to be recommended meets the user's needs. Based on this, when constructing the feature evaluation scores, the item recommendation system can match the object features of the requesting object with the initial features of different items to be recommended to obtain the first evaluation score corresponding to each item to be recommended, and match the request features of the item recommendation request with the initial features of different items to be recommended to obtain the second evaluation score corresponding to each item to be recommended.

[0062] In this embodiment of the application, initial features and feature evaluation scores are input into a feature evaluation model, and independent features are determined from the initial features using the feature evaluation model. This includes: removing any initial feature according to a preset method and obtaining the score change of the feature evaluation score; and determining independent features from the initial features based on the score change.

[0063] In one optional embodiment, as described above, considering that the independent features of an item typically influence a user's level of interest in that item, an increase in the number of independent features leads to a corresponding increase in user interest, while a decrease in the number of independent features leads to a corresponding decrease in user interest. Therefore, the feature evaluation model used to determine independent features can be a counterfactual decoupling model, which can evaluate the type of item features through counterfactual learning. The item recommendation system can change the features of an item, observe the changes in the relationship between any recommended item, the item recommendation request, and the requesting object, and determine the independent features based on these changes. Based on this, when using a feature evaluation model to determine independent features, the item recommendation system can first remove any initial feature according to a preset method, such as polling or random selection. Simultaneously, it can obtain the changes in the feature evaluation score after removing the feature. Then, based on the score changes, it can determine the type of the removed initial feature. For example, if after removing the initial feature, the feature evaluation score indicates the user's level of interest in the recommended item, such as the first evaluation score not changing, it can be initially determined that the feature does not affect the user's level of interest and is not an independent feature. If after removing the initial feature, the feature evaluation score indicates the user's level of interest in the recommended item, such as the first evaluation score changing, it can be initially determined that the feature affects the user's level of interest and is an independent feature.

[0064] In this embodiment of the application, removing any initial feature according to a preset method and obtaining the score change of the feature evaluation score includes: selecting a feature to be removed from the initial features according to a preset method; removing the feature to be removed from the initial features, and constructing a test evaluation score corresponding to any item to be recommended based on other features, request features, and object features, wherein other features are used to characterize the features remaining in the initial features after removing the feature to be removed; and determining the score change based on the test evaluation score and the feature evaluation score.

[0065] In one optional embodiment, when determining the change in feature evaluation scores, the item recommendation system can first select features to be removed from the initial features according to the preset method described above. After removing the features to be removed, the system can reconstruct the relationship between the item recommendation request, the item to be recommended, and the requested object based on the remaining features in the initial features, the request features of the item recommendation request, and the object features of the requested object. This will yield the corresponding test evaluation score, which will determine whether the user's interest in the recommended item and the satisfaction of the item recommendation request will change without the features to be removed. Based on the test evaluation score and the feature evaluation score, the item recommendation system can determine the aforementioned score changes.

[0066] In this embodiment of the application, the test evaluation score includes: a first test score between any recommended item and the requesting object when removing the feature to be removed, and a second test score between any recommended item and the item recommendation request; determining independent features from the initial features based on score changes includes: determining a first comparison result between the first evaluation score and the first test score, and a second comparison result between the second evaluation score and the second test score based on score changes; in response to the first comparison result being that the first test score is greater than the first evaluation score, and the second comparison result being that the second test score is less than the second evaluation score, determining the feature to be removed as an independent feature.

[0067] Corresponding to the feature evaluation score, the test evaluation score can include: a first test score between any recommended item and the request object, and a second test score between any recommended item and the item recommendation request, assuming the feature to be removed is removed. When determining independent features from the initial features based on score changes, the item recommendation system can first determine the change between the first evaluation score and the first test score (i.e., determine the first comparison result mentioned above), and simultaneously determine the change between the second evaluation score and the second current score (i.e., determine the second comparison result mentioned above). Then, it can determine whether the feature to be removed is an independent feature based on these two comparison results. For example, if the first comparison result is that the first test score is greater than the first evaluation score, and the second comparison result is that the second current score is less than the second evaluation score, then the item recommendation system can determine that the feature to be removed is an independent feature of the recommended item; otherwise, it can determine that the feature to be removed is a query feature of the recommended item.

[0068] In this embodiment of the application, the method further includes: obtaining the training evaluation score corresponding to the training item, wherein the training evaluation score is used to reflect the association between the training item, the training item recommendation request, and the test request object; inputting multiple training features and the training evaluation score of the training item into an initial evaluation model, and using the initial evaluation model to determine initial independent features from the training features; matching the initial independent features and the target independent features corresponding to the training item to construct a feature loss function, wherein the feature loss function includes: a first loss function between the training item and the test request object, and a second loss function between the training item and the training item recommendation request; and adjusting the initial evaluation model based on the feature loss function to obtain a feature evaluation model.

[0069] In one optional embodiment, in order to accurately determine independent features from the initial features of the items to be recommended, the item recommendation system can pre-acquire a large number of training items and construct corresponding training evaluation scores for different training items. For example, following the aforementioned process of determining feature evaluation scores, the training evaluation scores are constructed to reflect the relationship between the training items, the training item recommendation requests, and the test request objects, based on the item features of the training items, the request features of the training item recommendation requests, and the test request objects, so as to obtain the corresponding training evaluation scores. Then, multiple training features of the training items and the corresponding training evaluation scores are input into the initial evaluation model to determine the initial independent features from the training features of different training items using the initial evaluation model. Then, for the initial independent features and the target independent features corresponding to the training items, a corresponding feature loss function is constructed. The feature loss function corresponds to the feature evaluation score and may include a first loss function between the training items and the test request objects, i.e., the loss function corresponding to the first evaluation score, and a second loss function between the training items and the training item recommendation requests, i.e., the loss function corresponding to the second evaluation score. After constructing the feature loss function, the item recommendation system can use the feature loss function to adjust the initial evaluation model, thereby obtaining a feature evaluation model with higher accuracy.

[0070] In this embodiment of the application, feature enhancement is performed on the initial features of any item to be recommended based on the independent features of any item to be recommended, so as to obtain the target features of any item to be recommended. This includes: concatenating the independent features and the initial features according to the initial weights to obtain the concatenated features; inputting the concatenated features into a multilayer perceptron, and using the multilayer perceptron to adjust the initial weights to obtain the target weights; and concatenating the independent features and the initial features based on the target weights to obtain the target features.

[0071] In one optional embodiment, to accurately determine the target item based on the target features, when constructing target features corresponding to different recommended items, the item recommendation system can first concatenate the independent features and the initial features according to a preset initial weight to obtain the concatenated features. This increases the proportion of independent features in the target features, enabling the item recommendation system to more accurately determine the user's interest in different recommended items based on the target features. Considering that the attractiveness of independent features to users may differ among different recommended items, simple initial weights may not reflect this. Therefore, after constructing the concatenated features, the item recommendation system can further input the concatenated features into the multilayer perceptron to adjust the initial weights, obtaining target weights that better reflect the independent features of the recommended items. Then, the target weights are used to concatenate the independent features and the initial features to obtain more accurate target features.

[0072] In this embodiment of the application, feature extraction is performed on at least one item to be recommended to obtain initial features of at least one item to be recommended, including: obtaining item identifiers and item attributes of at least one item to be recommended; concatenating the item identifiers and item attributes to obtain first concatenation information; and encoding the first concatenation information based on a recommendation domain item encoder to obtain initial features of at least one item to be recommended, wherein the recommendation domain item encoder is used to characterize the encoder used to encode the features of at least one item to be recommended when recommending items to a requesting object.

[0073] The aforementioned recommendation domain item encoder refers to an encoder used during item recommendation to encode initial features. Considering that item features are needed in both item search and recommendation processes, at least one item encoder should be set up in the item recommendation system to encode item features. In the recommendation domain, the item encoder primarily learns item features to predict user preferences for items, thereby achieving personalized recommendations. In the search domain, the item encoder primarily understands the relationship between items and user queries, improving the relevance and accuracy of search results. Since their focuses differ, to ensure accuracy in item search and recommendation, corresponding recommendation domain item encoders and search domain item encoders can be set up separately for the recommendation domain and search domain, respectively.

[0074] In one optional embodiment, in order to accurately and richly represent the features of the items to be recommended during the item recommendation process, when extracting the aforementioned initial features, the item recommendation system can first obtain at least one item identifier of the item to be recommended, such as item ID (Identification), SKU (Stock Keeping Unit), etc., as well as the item attributes of the item to be recommended. Then, the item identifier and item attributes are concatenated to obtain the aforementioned first concatenation information. The first concatenation information is then encoded using a pre-configured recommendation domain item encoder to obtain the initial features of the item to be recommended during item recommendation.

[0075] In this embodiment, feature extraction is performed on the object information of the requesting object to obtain object features, including: obtaining the identity identifier of the requesting object, the object attributes of the requesting object, and the request type of the item recommendation request; concatenating the identity identifier and the object attributes to obtain second concatenated information; and encoding the second concatenated information using a recommendation domain requesting object encoder based on the request type of the item recommendation request to obtain object features, wherein the recommendation domain requesting object encoder is used to characterize the encoder used to encode the features of the requesting object when recommending items to the requesting object.

[0076] The aforementioned recommendation domain request object encoder refers to an encoder used to encode the features of an object during item recommendation. Similar to configuring the recommendation domain item encoder, considering that the features of the request object are needed in both item search and item recommendation processes, at least one request object encoder should be set up in the item recommendation system to encode the features of the item. In the recommendation domain, the request object encoder primarily determines the relationship between the item to be recommended and the request object, thus determining the request object's level of interest in the recommended item. In the search domain, the request object encoder mainly ensures the matching degree between the request object and different items, determining whether different items can meet the request object's needs. Since their focuses differ, to ensure accuracy in item search and item recommendation, corresponding recommendation domain request object encoders and search domain request object encoders can be set up separately for the recommendation domain and search domain.

[0077] In one optional embodiment, to accurately describe the object characteristics of the requesting object during the item recommendation process, the item recommendation system can first obtain the identity identifier and object attributes of the requesting object. Simultaneously, the obtained identity identifier and object attributes are concatenated to obtain the aforementioned second concatenated information. Then, the second concatenated information is encoded using a recommendation domain requesting object encoder to obtain the object characteristics of the requesting object during item recommendation. Considering that users' needs and levels of interest in different items may vary under different recommendation requests, the item recommendation system can also introduce the request type of the item recommendation request when actually determining the object characteristics of the requesting object, so as to determine the aforementioned object characteristics based on the request type of the item recommendation request.

[0078] In this embodiment, the request types include collaborative filtering and sequence recommendation. Based on the request type of the item recommendation request, the second concatenation information is encoded using a recommendation domain request object encoder to obtain object features, including: in response to the request type being collaborative filtering, encoding the second concatenation information based on the recommendation domain request object encoder to obtain object features; in response to the request type being sequence recommendation, obtaining the historical interaction sequence of the request object, and encoding the historical interaction sequence and the second concatenation information based on the recommendation domain request object encoder to obtain object features, wherein the historical interaction sequence is used to characterize the sequence of items that interacted with the request object within a historical time period.

[0079] The aforementioned collaborative filtering types refer to recommendation methods that recommend items to a requesting user based on other objects or items. This can be divided into two parts: user-based collaborative filtering and item-based collaborative filtering. User-based collaborative filtering can be understood as determining the requesting user's interest in different items based on the interest levels of other similar users. Item-based collaborative filtering can be understood as recommending an item to other users similar to a given user based on their interest level in that item. The aforementioned sequence recommendation type refers to a recommendation technique that considers user behavior sequences. By analyzing a user's historical behavior sequences, it can predict the content a user might be interested in next.

[0080] In one optional embodiment, in order to accurately extract the object features of the requested object, the item recommendation system can directly encode the second concatenation information using the recommendation domain request object to obtain the corresponding object features when the request type of the item recommendation request is determined to be the collaborative filtering type mentioned above. When the request type of the item recommendation request is determined to be the sequence recommendation type mentioned above, the system first obtains the historical interaction sequence of the requested object, such as the item sequence corresponding to the items that the user clicked or viewed within a historical time period. Then, the system uses the recommendation domain request object encoder to encode the historical interaction sequence and the second concatenation information to obtain object features that can further reflect the user's preferences.

[0081] In this embodiment of the application, determining a target item from at least one item to be recommended based on object features and target features of at least one item to be recommended includes: obtaining an object feature vector corresponding to the object features and a target feature vector corresponding to the target features; obtaining a target value based on the inner product of the object feature vector and the target feature vector; constructing an item preference score corresponding to different recommended items based on the target value, wherein the item preference score is used to reflect the degree of preference of the requesting object for different items to be recommended; and selecting a target item from at least one item to be recommended based on the item preference score.

[0082] In one optional embodiment, in order to accurately determine the target item from at least one item to be recommended, the item recommendation system can first obtain the object feature vector corresponding to the object feature and the target feature vector corresponding to the target feature. Then, based on the inner product of these two vectors, i.e. the target value, the system determines the degree of preference of the requesting object for different items to be recommended, i.e., determines the item preference score. Finally, based on the item preference score, the item recommendation system can filter out the target item from the items to be recommended.

[0083] For ease of understanding, the item recommendation process proposed in this application can be divided into two parts: one part is the process by which the search object obtains at least one of the aforementioned items to be recommended through the search system, and the other part is the process by which the requesting object displays the target item to the user through the recommendation system. Figure 3 This is a schematic diagram illustrating an item search process according to an embodiment of this application. Figure 4 This is a schematic diagram illustrating an item recommendation process according to an embodiment of this application. First, as... Figure 3As shown, during the item search process, the item recommendation system can first obtain the user embedding, such as user ID and attributes; the item embedding, such as item ID and attributes; and the request embedding of the item recommendation request. Then, the search domain user encoder, search domain item encoder, and search domain request encoder are used to encode these three embeddings respectively to obtain the corresponding first user feature, first item feature, and first request feature. Considering that item features can be divided into query features and independent features, the item embeddings can be processed before using the search domain item encoder to initially separate information related to the query features and independent features of the item, so as to ensure the accuracy of the first item feature obtained by the search domain item encoder. After obtaining the corresponding first user features, first item features, and first request features, the item recommendation system can combine the first item features and the first user features to determine the first association between the item and the user. At the same time, it can combine the first item features and the first request features to determine the second association between the item and the query request. Based on these two associations, the item recommendation system can further determine the query features and independent features of the item from the item features. In addition, the item recommendation system can also search the database for items that can meet the user's needs based on these two associations.

[0084] After the search results for items to be recommended, such as Figure 4As shown, the item recommendation system can use a recommendation domain user encoder and a recommendation domain item encoder to encode the user embedding and item embedding respectively to obtain corresponding second user features and second item features. After obtaining the second item features, the item recommendation system can introduce the first item features encoded by the search domain item encoder in the aforementioned search process, as well as the independent features of the determined items, and use these two features to enhance the second item features to obtain the corresponding target features. After constructing the target features, the item recommendation system can determine the user's level of interest in different items to be recommended based on the target features and the second user features, and then determine the target items from the items to be recommended based on the determined level of interest to display to the user. To ensure the accuracy of the determined level of interest, the item recommendation system can additionally configure a score determination model to determine the user's preference score for different items to be recommended based on the target features and the second user features, thereby determining the user's level of interest in different items to be recommended based on this preference score. Both the aforementioned feature evaluation model and the score determination model mentioned here can employ an end-to-end training strategy during model training. This allows for the simultaneous optimization of both the recommendation and search assistance tasks using a joint learning approach with balanced parameter control. During training, the item recommendation system can use user-item preference scores and recommendation request-item matching scores as supervision signals. These signals provide the model with rich semantic information, helping it better understand user behavior and preferences. Furthermore, the model's accuracy can be improved through joint optimization using multiple loss functions.

[0085] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0086] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0087] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0088] According to an embodiment of this application, a method for recommending items is also provided. Figure 5 This is a flowchart illustrating another item recommendation method according to an embodiment of this application, such as... Figure 5 As shown, the method may include the following steps:

[0089] Step S502: In response to the input command applied to the operation interface, display at least one initial feature of the item to be recommended and the object feature of the requested object on the operation interface.

[0090] The request object is used to represent the object that sends the item recommendation request.

[0091] Step S504: In response to the processing command applied to the operation interface, the target item is displayed on the operation interface.

[0092] The target item is determined from at least one item to be recommended, based on the object features and the target features of at least one item to be recommended. The target features are obtained by enhancing the initial features of any item to be recommended with the independent features of any item to be recommended. The independent features are used to characterize the interests and preferences of the search object, and the search object is used to search for any item to be recommended.

[0093] The input instruction mentioned above could refer to an instruction to retrieve items to be recommended. The processing instruction mentioned above could refer to an item recommendation request input by the requesting object.

[0094] In one optional embodiment, when the item recommendation system receives an input instruction, it can display at least one initial characteristic of the item to be recommended and the object characteristics of the requested object on the aforementioned operation interface. When it receives a processing instruction, the item recommendation system can determine the target item based on the initial characteristics and object characteristics, and display the target item on the operation interface for user convenience. The specific process of determining the target item can be as described above and will not be repeated here.

[0095] According to an embodiment of this application, a method for recommending items is also provided. Figure 6This is a flowchart illustrating another item recommendation method according to an embodiment of this application, such as... Figure 6 As shown, the method may include the following steps:

[0096] Step S602: Obtain the object characteristics of the request object and at least one initial characteristic of the item to be recommended by calling the first interface.

[0097] The request object is used to represent the object that sends the item recommendation request. The first interface includes a first parameter, the value of which includes object characteristics and initial characteristics.

[0098] Step S604: Based on the independent features of any item to be recommended, perform feature enhancement on the initial features of any item to be recommended to obtain the target features of any item to be recommended.

[0099] Among them, independent features are used to characterize the interests and preferences of the search object, which is used to search for any item to be recommended.

[0100] Step S606: Based on object features and target features of at least one item to be recommended, determine the target item from at least one item to be recommended.

[0101] Step S608: Output the target item by calling the second interface.

[0102] The second interface includes a second parameter, the value of which includes the target item.

[0103] In one optional embodiment, when recommending items to a user, the item recommendation system can first obtain a first parameter through a first interface, namely, the object features of the request object and the initial features of the item to be recommended. Then, it can use an independent feature of any item to be recommended to enhance the initial features of that item, thereby obtaining the target features of the item to be recommended. Next, it can use the object features and the target features to determine the target item from the list of items to be recommended. Finally, it can output a second parameter, i.e., output the target item, through a second interface for the user's convenience. The specific process for determining the target item can be as described above and will not be repeated here.

[0104] According to an embodiment of this application, an item recommendation apparatus for implementing the above-described item recommendation method is also provided. Figure 7 This is a structural block diagram of an article recommendation device according to an embodiment of this application, such as... Figure 7 As shown, the device includes: a feature extraction module 702, a feature enhancement module 704, an item determination module 706, and an item output module 708.

[0105] The feature extraction module 702 is used to extract features from the object information of the requesting object in response to receiving an item recommendation request, to obtain object features, and to extract features from at least one item to be recommended, to obtain initial features of at least one item to be recommended, wherein the requesting object is used to represent the object that sent the item recommendation request; the feature enhancement module 704 is used to enhance the initial features of any item to be recommended based on the independent features of any item to be recommended, to obtain the target features of any item to be recommended, wherein the independent features are used to represent the interests and preferences of the search object, and the search object is used to search for any item to be recommended; the item determination module 706 is used to determine the target item from at least one item to be recommended based on the object features and the target features of at least one item to be recommended; and the item output module 708 is used to output the target item.

[0106] In this embodiment of the application, the above-mentioned apparatus further includes: a request feature extraction unit, used to extract features from the item recommendation request to obtain the request features of the item recommendation request; an evaluation score construction unit, used to construct a feature evaluation score corresponding to any recommended item based on the initial features, request features, and object features, wherein the feature evaluation score is used to reflect the association between any item to be recommended, the item recommendation request, and the request object; and an independent feature determination unit, used to input the initial features and the feature evaluation score into the feature evaluation model, and use the feature evaluation model to determine independent features from the initial features.

[0107] In this embodiment of the application, the feature evaluation score includes: a first evaluation score between any item to be recommended and the requesting object, and a second evaluation score between any item to be recommended and the item recommendation request; the evaluation score construction unit is further used to match the object features with the initial features to obtain the first evaluation score; and to match the request features with the initial features to obtain the second evaluation score.

[0108] In this embodiment of the application, the independent feature determination unit is further configured to: remove any initial feature according to a preset method and obtain the score change of the feature evaluation score; and determine independent features from the initial features based on the score change.

[0109] In this embodiment of the application, the independent feature determination unit is further configured to: select features to be removed from the initial features according to a preset method; remove the features to be removed from the initial features, and construct a test evaluation score corresponding to any item to be recommended based on other features, request features, and object features, wherein other features are used to characterize the features remaining in the initial features after removing the features to be removed; and determine the score change based on the test evaluation score and the feature evaluation score.

[0110] In this embodiment of the application, the test evaluation score includes: a first test score between any recommended item and the request object when the feature to be removed is removed, and a second test score between any recommended item and the item recommendation request; the independent feature determination unit is further configured to: determine a first comparison result between the first evaluation score and the first test score, and a second comparison result between the second evaluation score and the second test score based on the score change; in response to the first comparison result being that the first test score is greater than the first evaluation score, and the second comparison result being that the second test score is less than the second evaluation score, determine the feature to be removed as an independent feature.

[0111] In this embodiment, the apparatus further includes: a score acquisition module for acquiring training evaluation scores corresponding to training items, wherein the training evaluation scores reflect the association between training items, training item recommendation requests, and test request objects; a feature determination module for inputting multiple training features and training evaluation scores of training items into an initial evaluation model, and using the initial evaluation model to determine initial independent features from the training features; a function construction module for matching the initial independent features and target independent features corresponding to training items to construct a feature loss function, wherein the feature loss function includes: a first loss function between training items and test request objects, and a second loss function between training items and training item recommendation requests; and a model adjustment module for adjusting the initial evaluation model based on the feature loss function to obtain a feature evaluation model.

[0112] In this embodiment, the feature enhancement module 704 includes: a first splicing unit, used to splice independent features and initial features according to initial weights to obtain spliced ​​features; a weight adjustment unit, used to input the spliced ​​features into a multilayer perceptron and use the multilayer perceptron to adjust the initial weights to obtain target weights; and a second splicing unit, used to splice independent features and initial features based on the target weights to obtain target features.

[0113] In this embodiment, the feature extraction module 702 includes: an attribute acquisition unit, used to acquire at least one item identifier and at least one item attribute of the item to be recommended; a third splicing unit, used to splice the item identifier and the item attribute to obtain first splicing information; and a first encoding unit, used to encode the first splicing information based on the recommendation domain item encoder to obtain initial features of at least one item to be recommended, wherein the recommendation domain item encoder is used to characterize the encoder used to encode the features of at least one item to be recommended when recommending items to the requesting object.

[0114] In this embodiment, the feature extraction module 702 includes: a parameter acquisition unit, used to acquire the identity identifier of the request object, the object attributes of the request object, and the request type of the item recommendation request; a fourth splicing unit, used to splice the identity identifier and object attributes to obtain second splicing information; and a second encoding unit, used to encode the second splicing information using a recommendation domain request object encoder based on the request type of the item recommendation request to obtain object features, wherein the recommendation domain request object encoder is used to characterize the encoder used to encode the features of the request object when recommending items to the request object.

[0115] In this embodiment of the application, the second encoding unit is further configured to: in response to a request type being collaborative filtering, encode the second concatenation information based on the recommendation domain request object encoder to obtain object features; in response to a request type being sequence recommendation, obtain the historical interaction sequence of the request object, and encode the historical interaction sequence and the second concatenation information based on the recommendation domain request object encoder to obtain object features, wherein the historical interaction sequence is used to characterize the sequence of items that have interacted with the request object within a historical time period.

[0116] In this embodiment, the item determination module 706 includes: a vector acquisition unit, used to acquire object feature vectors corresponding to object features and target feature vectors corresponding to target features; a value determination unit, used to obtain a target value based on the inner product of the object feature vector and the target feature vector; a score construction unit, used to construct item preference scores corresponding to different recommended items based on the target value, wherein the item preference scores are used to reflect the degree of preference of the requesting object for different items to be recommended; and an item selection module, used to select a target item from at least one item to be recommended based on the item preference scores.

[0117] It should be noted that the feature extraction module 702, feature enhancement module 704, item determination module 706, and item output module 708 correspond to steps S202 to S208 in the above embodiments. The four modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware or software components stored in memory and processed by one or more processors. The above modules can also run as part of the device in the server 10 provided in the above embodiments.

[0118] According to an embodiment of this application, an item recommendation apparatus for implementing the above-described item recommendation method is also provided. Figure 8 This is a structural block diagram of another article recommendation device according to an embodiment of this application, such as... Figure 8 As shown, the device includes: a first display module 802 and a second display module 804.

[0119] The first display module 802 is used to respond to input commands applied to the operation interface and display the initial features of at least one item to be recommended and the object features of the requesting object on the operation interface. The requesting object is used to represent the object that sent the item recommendation request. The second display module 804 is used to respond to processing commands applied to the operation interface and display the target item on the operation interface. The target item is determined from at least one item to be recommended by the object features and the target features of at least one item to be recommended. The target features are obtained by feature enhancement of the initial features of any item to be recommended by the independent features of any item to be recommended. The independent features are used to represent the interests and preferences of the search object. The search object is used to search for any item to be recommended.

[0120] It should be noted that the first display module 802 and the second display module 804 mentioned above correspond to steps S502 to S504 in the above embodiments. The two modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware components or software components stored in memory and processed by one or more processors. The above modules can also be part of the device and run in the server 10 provided in the above embodiments.

[0121] According to an embodiment of this application, an item recommendation apparatus for implementing the above-described item recommendation method is also provided. Figure 9 This is a structural block diagram of another article recommendation device according to an embodiment of this application, such as... Figure 9 As shown, the device includes: a first invocation module 902, an enhancement module 904, a determination module 906, and a second invocation module 908.

[0122] The first calling module 902 is used to obtain the object features of the requesting object and the initial features of at least one item to be recommended by calling a first interface. The requesting object is used to represent the object that sent the item recommendation request. The first interface includes a first parameter, the value of which includes the object features and the initial features. The enhancement module 904 is used to enhance the initial features of any item to be recommended based on the independent features of any item to be recommended, thereby obtaining the target features of any item to be recommended. The independent features are used to represent the interests and preferences of the search object, and the search object is used to search for any item to be recommended. The determination module 906 is used to determine the target item from at least one item to be recommended based on the object features and the target features of at least one item to be recommended. The second calling module 908 is used to output the target item by calling a second interface. The second interface includes a second parameter, the value of which includes the target item.

[0123] It should be noted that the first calling module 902, the enhancement module 904, the determination module 906, and the second calling module 908 mentioned above correspond to steps S602 to S608 in the above embodiments. The four modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware or software components stored in memory and processed by one or more processors. The above modules can also run as part of the device in the server 10 provided in the above embodiments.

[0124] It should be noted that the preferred embodiments involved in the above embodiments of this application are the same as the solutions, application scenarios and implementation processes provided in the above embodiments, but are not limited to the solutions provided in the above embodiments.

[0125] Embodiments of this application may provide a computing device. Figure 10 This is a structural block diagram of a computing device according to an embodiment of this application. Figure 10 As shown, the computing device 1000 may include: one or more (only one is shown in the figure) processors 1002, memory 1004, memory controller, and peripheral interfaces.

[0126] The aforementioned computing device can be understood as an integrated smart terminal, including but not limited to servers, desktop computers, PCs (Personal Computers), all-in-one model machines, etc., and the computing device may have the model in the above embodiments of this application pre-installed.

[0127] Specifically, this computing device can pre-install various types of models, including but not limited to models in natural language processing, visual processing, speech processing, code processing, and multimodal task processing, thus providing diverse model selection. In different product forms, this computing device can support one or more model usage methods, including but not limited to model training, model invocation, model fine-tuning, model deployment, model inference, and application. In some product forms, this computing device also supports model management, including but not limited to multi-type model management (supporting the management of discriminative, generative, and other model types), model version control (supporting the control of different model versions), and model evaluation (evaluating model performance and effectiveness based on model evaluation tools). In other product forms, this computing device can also create applications based on models, providing API calling capabilities, allowing models to be called into created applications through API interfaces, and providing application management tools to achieve application control.

[0128] Furthermore, the computing device may also include data management (supporting the creation and management of model tuning datasets), a training center (providing abundant training resources to help users learn and master AI technology), and basic control capabilities (providing enterprise-level basic control capabilities to ensure the security and efficient operation of the system). Through the above functions, it provides a comprehensive and integrated device for AI development, training, deployment, and application.

[0129] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0130] The processor can invoke an executable program stored in memory via a transmission device to execute any of the methods described in the above embodiments.

[0131] Embodiments of this application may provide an electronic device. Figure 11 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 11 As shown, the electronic device may include: an input / output device 1102; a memory 1104; and a processor 1106, wherein the processor 1106 is connected to the input / output device 1102 and the memory 1104 via a bus 1108.

[0132] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0133] The processor can invoke an executable program stored in memory via a transmission device to execute any of the methods described in the above embodiments.

[0134] It will be understood by those skilled in the art that the structure shown in the figure is merely illustrative, and the computing device may also be a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile internet device (MID), a PAD, or other terminal device. This figure does not limit the structure of the aforementioned computing device. For example, the computing device 1000 may also include more or fewer components (such as a network interface, a display device, etc.) than those shown in the figure, or may have a different configuration than that shown in the figure.

[0135] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0136] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the computer-readable storage medium can be used to store program code executed by the method provided in the above embodiments.

[0137] Optionally, in this embodiment, the storage medium may be located in a computing device.

[0138] Optionally, in this embodiment, the computer-readable storage medium is configured to store an executable program, which, when the executable program is running, controls the device where the computer-readable storage medium is located to execute any of the methods described in the above embodiments.

[0139] Embodiments of this application also provide a computer program product. Optionally, in this embodiment, the computer program product may include a computer program that, when executed by a processor, implements the methods provided in the embodiments described above.

[0140] Embodiments of this application also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium, which can be used to store a computer program that, when executed by a processor, implements the method provided in the above embodiments.

[0141] Embodiments of this application also provide a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it implements the method provided in the above embodiments.

[0142] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0143] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0145] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0146] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0147] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for recommending items, characterized in that, include: In response to receiving an item recommendation request, feature extraction is performed on the object information of the requesting object to obtain object features, and feature extraction is performed on at least one item to be recommended to obtain the initial features of the at least one item to be recommended, wherein the requesting object is used to characterize the object that sent the item recommendation request; Based on the independent features of any item to be recommended, feature enhancement is performed on the initial features of the item to be recommended to obtain the target features of the item to be recommended. The independent features are used to characterize the interests and preferences of the search object, which is used to search for the item to be recommended. The independent features are determined from the initial features by a feature evaluation model based on the feature evaluation score corresponding to any item to be recommended. The feature evaluation score corresponding to the item to be recommended is constructed from the initial features, the request features of the item recommendation request, and the object features. The feature evaluation score is used to reflect the association between the item to be recommended, the item recommendation request, and the request object. Based on the object characteristics and the target characteristics of the at least one item to be recommended, a target item is determined from the at least one item to be recommended; Output the target item.

2. The method according to claim 1, characterized in that, The feature evaluation score includes: a first evaluation score between any item to be recommended and the request object, and a second evaluation score between any item to be recommended and the item recommendation request; the step of constructing the feature evaluation score corresponding to any item to be recommended based on the initial features, the request features, and the object features includes: The object features are matched with the initial features to obtain the first evaluation score; The request features are matched with the initial features to obtain the second evaluation score.

3. The method according to claim 1, characterized in that, The method further includes: Remove any initial feature according to a preset method, and obtain the score change of the feature evaluation score; Based on the changes in the scores, the independent features are determined from the initial features.

4. The method according to claim 3, characterized in that, The step of removing any initial feature according to a preset method and obtaining the score change of the feature evaluation score includes: Features to be removed are selected from the initial features according to the preset method; The feature to be removed is removed from the initial features, and a test evaluation score is constructed for any item to be recommended based on other features, the request feature, and the object feature. The other features are used to characterize the features remaining in the initial features after the feature to be removed is removed. Based on the test evaluation score and the feature evaluation score, the score change is determined.

5. The method according to claim 4, characterized in that, The test evaluation score includes: a first test score between any item to be recommended and the request object when the feature to be removed is removed, and a second test score between any item to be recommended and the item recommendation request; determining the independent feature from the initial features based on the score changes includes: Based on the changes in the scores, a first comparison result between the first evaluation score and the first test score is determined, and a second comparison result between the second evaluation score and the second test score is determined; In response to the first comparison result being that the first test score is greater than the first evaluation score, and the second comparison result being that the second test score is less than the second evaluation score, the feature to be removed is determined to be the independent feature.

6. The method according to claim 1, characterized in that, The method further includes: Obtain the training evaluation score corresponding to the training item, wherein the training evaluation score is used to reflect the relationship between the training item, the training item recommendation request, and the test request object; Multiple training features of the training items and the training evaluation scores are input into an initial evaluation model, and the initial evaluation model is used to determine initial independent features from the training features; Matching is performed based on the initial independent features and the target independent features corresponding to the training items to construct a feature loss function, wherein the feature loss function includes: a first loss function between the training items and the test request object, and a second loss function between the training items and the training item recommendation request; The initial evaluation model is adjusted based on the feature loss function to obtain the feature evaluation model.

7. The method according to claim 1, characterized in that, The step of enhancing the initial features of any item to be recommended based on its independent features to obtain the target features of the item to be recommended includes: The independent features and the initial features are concatenated according to the initial weights to obtain the concatenated features; The spliced ​​features are input into a multilayer perceptron, and the initial weights are adjusted using the multilayer perceptron to obtain the target weights; The independent features and the initial features are concatenated based on the target weights to obtain the target features.

8. The method according to claim 1, characterized in that, The step of extracting features from at least one item to be recommended to obtain initial features of the at least one item to be recommended includes: Obtain the item identifier of the at least one item to be recommended, and the item attributes of the at least one item to be recommended; The item identifier and the item attribute are concatenated to obtain the first concatenation information; The first splicing information is encoded based on the recommendation domain item encoder to obtain the initial features of the at least one item to be recommended. The recommendation domain item encoder is used to characterize the encoder used to encode the features of the at least one item to be recommended when recommending items to the requesting object.

9. The method according to claim 1, characterized in that, The step of extracting features from the object information of the requested object to obtain object features includes: Obtain the identity identifier of the requesting object, the object attributes of the requesting object, and the request type of the item recommendation request; The identity identifier and the object attribute are concatenated to obtain the second concatenation information; Based on the request type of the item recommendation request, the second concatenation information is encoded using a recommendation domain request object encoder to obtain the object features. The recommendation domain request object encoder is used to characterize the encoder used to encode the features of the request object when recommending items to the request object.

10. The method according to claim 9, characterized in that, The request types include: collaborative filtering type and sequence recommendation type; the request type based on item recommendation uses a recommendation domain request object encoder to encode the second concatenation information to obtain the object features, including: In response to the request type being the collaborative filtering type, the second concatenation information is encoded based on the recommendation domain request object encoder to obtain the object features; In response to the request type being the sequence recommendation type, the historical interaction sequence of the request object is obtained, and the historical interaction sequence and the second splicing information are encoded based on the recommendation domain request object encoder to obtain the object features, wherein the historical interaction sequence is used to characterize the sequence of items that have interacted with the request object within a historical time period.

11. The method according to claim 1, characterized in that, Based on the object characteristics and the target characteristics of the at least one item to be recommended, determining the target item from the at least one item to be recommended includes: Obtain the object feature vector corresponding to the object feature, and the target feature vector corresponding to the target feature; The target value is obtained based on the inner product of the object feature vector and the target feature vector; Based on the target value, an item preference score is constructed for different recommended items, wherein the item preference score is used to reflect the degree of preference of the requesting object for different recommended items; The target item is selected from the at least one item to be recommended based on the item preference score.

12. A method for recommending items, characterized in that, include: In response to an input command applied to the operation interface, at least one initial feature of the item to be recommended and the object feature of the requesting object are displayed on the operation interface, wherein the requesting object is used to characterize the object that sent the item recommendation request; In response to a processing instruction applied to the operation interface, a target item is displayed on the operation interface. The target item is determined from the at least one item to be recommended by the object features and the target features of the at least one item to be recommended. The target features are obtained by enhancing the initial features of any item to be recommended by an independent feature. The independent features are used to characterize the interests and preferences of the search object, which is used to search for the item to be recommended. The independent features are determined from the initial features based on the feature evaluation score corresponding to any item to be recommended using a feature evaluation model. The feature evaluation score corresponding to the item to be recommended is constructed from the initial features, the request features of the item recommendation request, and the object features. The feature evaluation score reflects the association between the item to be recommended, the item recommendation request, and the requesting object.

13. A method for recommending items, characterized in that, include: The object characteristics of the request object and the initial characteristics of at least one item to be recommended are obtained by calling the first interface. The request object is used to represent the object that sent the item recommendation request. The first interface includes a first parameter, and the parameter value of the first parameter includes the object characteristics and the initial characteristics. Based on the independent features of any item to be recommended, feature enhancement is performed on the initial features of the item to be recommended to obtain the target features of the item to be recommended. The independent features are used to characterize the interests and preferences of the search object, which is used to search for the item to be recommended. The independent features are determined from the initial features by a feature evaluation model based on the feature evaluation score corresponding to any item to be recommended. The feature evaluation score corresponding to the item to be recommended is constructed from the initial features, the request features of the item recommendation request, and the object features. The feature evaluation score is used to reflect the association between the item to be recommended, the item recommendation request, and the request object. Based on the object characteristics and the target characteristics of the at least one item to be recommended, a target item is determined from the at least one item to be recommended; The target item is output by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter includes the target item.

14. A computing device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 12.

15. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor, connected to the memory via a bus, is used to run the program, wherein the program executes the method according to any one of claims 1 to 12.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 12.

17. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 12.

Images