Recommendation method and device, equipment and medium

Abstract

The invention provides a recommendation method and device, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of recommendation. According to the implementation scheme, in response to a received recommendation request, recommendation information is determined based on user features of a target user, category features of multiple object categories and object features of candidate objects included in each object category, and the recommendation information comprises at least one recommendation category and at least one recommendation object corresponding to each recommendation category; and based on the recommendation information, determining a recommendation sequence comprising a plurality of recommendation objects for the target user.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of recommendation technology, and specifically to a recommendation method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] With the development of computer technology and big data technology, people's consumption, entertainment, learning, travel and other behaviors in life are closely related to big data. In the operation process of business platforms, it is usually necessary to actively recommend content to users in order to improve corresponding business performance.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0006] According to one aspect of the present disclosure, a recommendation method is provided, comprising: in response to receiving a recommendation request, determining recommendation information based on user characteristics of a target user, category characteristics of multiple object categories, and object characteristics of candidate objects included in each object category, wherein the recommendation information includes at least one recommendation category and at least one recommended object corresponding to each recommendation category; and determining a recommendation sequence including multiple recommended objects for the target user based on the recommendation information.

[0007] According to one aspect of the present disclosure, a method for training a recommendation model is provided, comprising: inputting user features of sample users, category features of multiple object categories, and object features of candidate objects included in each object category into the recommendation model to obtain predicted recommendation information output by the recommendation model, wherein the predicted recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; based on the predicted recommendation information, determining a predicted recommendation sequence including multiple recommended objects; determining a training score for the predicted recommendation sequence; and adjusting parameters of the recommendation model based on the training score of the predicted recommendation sequence.

[0008] According to one aspect of the present disclosure, a recommendation device is provided, comprising: a first determination unit, configured to determine, in response to receiving a recommendation request, recommendation information based on user characteristics of a target user, category characteristics of multiple object categories, and object characteristics of candidate objects included in each object category, wherein the recommendation information includes at least one recommendation category and at least one recommended object corresponding to each recommendation category; and a second determination unit, configured to determine, based on the recommendation information, a recommendation sequence including multiple recommended objects for the target user.

[0009] According to one aspect of the present disclosure, a training device for a recommendation model is provided, comprising: an input unit, configured to input user features of a sample user, category features of multiple object categories, and object features of candidate objects included in each object category into the recommendation model to obtain predicted recommendation information output by the recommendation model, wherein the predicted recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; a fifth determination unit, configured to determine a predicted recommendation sequence including multiple recommended objects based on the predicted recommendation information; a scoring unit, configured to determine a training score for the predicted recommendation sequence; and a second adjustment unit, configured to adjust parameters of the recommendation model based on the training score of the predicted recommendation sequence.

[0010] According to one aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned recommendation method or the training method of the recommendation model.

[0011] According to one aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned recommendation method or recommendation model training method.

[0012] According to one aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program can implement the above-mentioned recommendation method or the training method of the recommendation model when executed by a processor.

[0013] According to one or more embodiments of the present disclosure, the recommendation accuracy and recommendation efficiency can be improved.

[0014] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0016] Figure 1 shows in which various methods described herein may be implemented according to exemplary embodiments of the present disclosure;

[0017] Figure 2 A flowchart of a recommendation method according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 3 A schematic diagram showing a recommendation model according to an exemplary embodiment of the present disclosure is shown;

[0019] Figure 4 A flowchart of a training method for a recommendation model according to an exemplary embodiment of the present disclosure is shown;

[0020] Figure 5 A structural block diagram of a recommendation device according to an exemplary embodiment of the present disclosure is shown;

[0021] Figure 6 A structural block diagram of a training device for a recommendation model according to an exemplary embodiment of the present disclosure is shown;

[0022] Figure 7 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0023] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0024] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0025] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0026] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0028] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable the recommended method to be performed.

[0029] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0030] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0031] The user may send a recommendation request using client devices 101, 102, 103, 104, 105, and / or 106. The client device may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0032] Client devices 101, 102, 103, 104, 105 and / or 106 may include various categories of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various categories and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (eg, email applications), short message service (SMS) applications, and may use various communication protocols.

[0033] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0034] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0035] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0036] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0037] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0038] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different categories. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0039] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different categories of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0040] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0041] In the related art, when the object to be recommended involves an object category, the recommended category is usually determined first, and then the recommended object is further determined based on the recommended category. In this case, the characteristics of the recommended object are not taken into account in the step of determining the recommended category, and the accuracy is limited.

[0042] Based on this, the present disclosure provides a recommendation method, which outputs information including recommended categories and recommended objects under the recommended categories end-to-end based on category features and specific object features for a candidate object library involving object category information to improve recommendation accuracy.

[0043] Figure 2 FIG. 2 shows a flow chart of a recommendation method 200 according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the method 200 includes:

[0044] Step S201, in response to receiving a recommendation request, determining recommendation information based on a user feature of a target user, category features of a plurality of object categories, and object features of candidate objects included in each object category, wherein the recommendation information includes at least one recommendation category and at least one recommended object corresponding to each recommendation category; and

[0045] Step S202: Based on the recommendation information, determine a recommendation sequence including multiple recommendation objects for the target user.

[0046] By applying the above-mentioned recommendation method 200, object category features and object features can be considered simultaneously in the recommendation process, and information including recommended categories and recommended objects under the recommended categories can be output end-to-end based on the category features and the specific object features to improve the recommendation accuracy.

[0047] In some examples, the recommended objects may be various types of objects in a variety of application scenarios, and the object categories may be determined by classification based on various attributes of the recommended objects. For example, when method 200 is applied to the field of e-commerce, the recommended objects may be different types of goods, and the object categories may be the category information of the goods. Alternatively, the recommended objects may be different styles of product advertisements, and the corresponding categories may be the goods corresponding to the product advertisements. For another example, when method 200 is applied to the operation scenarios of Internet platforms such as video playback and e-book reading, the recommended objects may include various videos, e-books, etc. to be recommended, and the object categories may be the content categories of the recommended objects.

[0048] In some examples, method 200 can be applied to a recommendation platform. In this case, pushing a recommendation sequence to a target user can bring certain marketing benefits to the recommendation platform. For example, a recommendation sequence can include multiple product advertisements. After the recommendation platform pushes the product advertisements to the target user, the advertiser can be charged based on the target user's interactive behavior with respect to the product advertisements. In this case, the object category of the candidate object can be determined based on the advertiser corresponding to the candidate advertising content, so that it is convenient to take into account both the advertiser information and the advertising content information in the recommendation process, and then the advertiser or advertising content of the recommendation sequence can be controlled by adjusting the parameters or means that can affect the recommendation information in step S201 to meet the needs of actual application scenarios.

[0049] As mentioned above, the object category can be determined by classification based on various attributes of the recommended object. In this case, each candidate object can correspond to multiple object categories under different dimensions, so that the object category characteristics of various dimensions can be comprehensively considered in step S201 to improve the recommendation accuracy.

[0050] In some examples, the object categories and the information of the candidate objects included in each object category can be determined based on an object library having a hierarchical tree classification structure. In one example, when the method 200 is applied to the field of advertising recommendation, the object library can include multiple first-level classifications corresponding to multiple advertisers, each first-level classification can further include multiple second-level classifications corresponding to multiple products, and each second-level classification can include multiple product advertisements corresponding to different advertising styles.

[0051] In one example, the category features of the object category in step S201 may be the above-mentioned classification features of the first-level classification or the classification features of the second-level classification. The object features may be used to indicate the features of the advertising style of the product advertisement, thereby being able to directly determine the product advertisement for recommendation to the user based on the recommendation information.

[0052] In one example, the category features of the object category in step S201 may be the classification features of the above-mentioned first-level classification, and the object features may be the classification features of the above-mentioned second-level classification, so that the first-level recommendation classification and the second-level recommendation classification for recommendation to the target user can be determined based on the classification features at different levels. On this basis, the recommended advertisement styles under the first-level recommendation classification and the second-level recommendation classification can be further determined to obtain the product advertisements for recommendation to the user.

[0053] In some examples, the object features of a candidate object may be encoded based on the content of the candidate object (e.g., product information of the candidate object, video content of a candidate video), and the category features of an object category may be encoded based on the object features of each candidate object under the object category, thereby enabling recommendations to be made based on the object category and the specific content of the candidate object.

[0054] In some examples, when the recommended object is related to the marketing revenue of the recommendation platform or the business revenue of the business platform, the object features of the candidate object and the category features of the object category can also indicate the corresponding revenue information. For example, when the recommendation platform can obtain certain marketing revenue by recommending product advertisements, by using object features and category features to indicate the revenue that different candidate objects and object categories can bring to the platform, it can select recommended categories and recommended objects with higher revenue based on this, so as to more efficiently meet the business goals of the recommendation platform and meet the needs of actual application scenarios.

[0055] According to some embodiments, the recommendation information includes a plurality of information pairs arranged in sequence, each of the plurality of information pairs including a recommendation category and a recommended object corresponding to the recommendation category. Thus, the object category and the specific object information can be explicitly output, which facilitates the retrieval of the recommended object and the evaluation of the recommendation effect.

[0056] In some examples, the recommendation information may be in the following form: recommendation category A-recommended object A1-recommended category B-recommended object B2-recommended category A-recommended object A2. By using an information pair including category information and object information to indicate a recommended object, it is possible to more easily and accurately indicate the category features and specific object features corresponding to the recommended object, making it easier to select a recommended object based on the category features and object features during the recommendation process.

[0057] In some examples, when the object categories and the information of the candidate objects included in each object category are determined based on an object library with different classification dimensions. In this case, the recommendation information may only include multiple recommendation categories of the first dimension and multiple recommendation categories of the second dimension, and then the recommended object can be determined in step S202 by combining the recommendation classification information of different dimensions. For example, when method 200 is applied to the field of advertising recommendation, the classification information of the first dimension can be used to indicate the product corresponding to the advertisement, and the classification information of the second dimension can be used to indicate the type of advertisement, such as pop-up ads and page sidebar ads. In this case, the recommended object can be determined by combining the recommendation classification information of different dimensions.

[0058] According to some embodiments, determining the recommendation information based on the user features of the target user, the category features of multiple object categories, and the object features of the candidate objects included in each object category in step S201 includes: inputting the user features, the category features of the multiple object categories, and the object features of the candidate objects included in each object category into a recommendation model to obtain the recommendation information output by the recommendation model, wherein the training process of the recommendation model includes: determining a predicted recommendation sequence based on the predicted recommendation information output by the recommendation model; determining a training score for the predicted recommendation sequence; and adjusting the parameters of the recommendation model based on the training score of the predicted recommendation sequence. By training the recommendation model based on the training score in the training process, the recommendation model can be tuned by reinforcement learning to improve the prediction performance of the recommendation model to obtain more accurate recommendation information.

[0059] In some examples, other methods may be used to train the recommendation model, for example, supervised training may be performed using sample data labeled with reference recommendation information to improve the prediction accuracy of the recommendation model.

[0060] In some examples, the training score can be determined based on one or more evaluation objectives. For example, the training score can be determined based on the target user's selection probability of the recommended object (such as the user's click-through rate on the recommended advertisement, the user's purchase rate on the recommended product). For another example, the training score can also be determined based on the marketing revenue that the recommendation sequence can bring to the recommendation platform.

[0061] According to some embodiments, determining the training score for the predicted recommendation sequence includes: inputting the predicted recommendation sequence into a scoring model to obtain the training score output by the scoring model, wherein the scoring model is trained using a sample recommendation sequence annotated with reference scoring information, and wherein the reference scoring information is determined based on the user's real interaction information for the sample recommendation sequence. By using the scoring model to learn the reference scoring results in a real interaction environment, that is, when there are fewer real samples, the scoring model can be used to expand the training sample data set and improve the model training effect.

[0062] According to some embodiments, the user characteristics of the target user include historical interaction information of the target user for the historical recommendation sequence. By combining the historical interaction behavior of the user for recommendation, it is possible to determine the recommendation object that better meets the user's preference, so as to improve the recommendation accuracy.

[0063] In some examples, the historical interaction information of the target user for the historical recommendation sequence may include time information, behavior type information, etc. of various historical interaction behaviors of the user. For example, when the method 200 is applied to an e-commerce scenario, the historical interaction information of the target user for the historical recommendation sequence may indicate the following: the target user's browsing behavior, click behavior, consultation behavior, purchase behavior, etc. for the historically recommended products. For another example, when the method 200 is applied to a video playback scenario, the historical interaction information of the target user for the historical recommendation sequence may indicate the following: the target user's click behavior, playback and viewing behavior, etc. for the historically recommended videos.

[0064] As described above, method 200 according to an exemplary embodiment of the present disclosure determines a recommendation sequence based on feature information at two levels: category features of the object category and specific object features. In this case, the historical interaction information of the target user for the historical recommendation sequence may include the target user's interaction information for different object categories, thereby indicating the user's preference for different object categories, thereby achieving more accurate recommendations.

[0065] In some examples, the user characteristics of the target user may also include more content, such as a user portrait of the target user. In one example, the user portrait may include the age group information, consumption capacity information, etc. of the target user after desensitization processing, as long as it can affect the target user's preference for the recommended object in the current application scenario, and the present disclosure does not limit this.

[0066] In one example, method 200 is applied to a scenario where a specific display page is used to make recommendations to a user. In this case, the display page may include a certain number of recommendation slots, and by applying method 200 to determine the recommendation sequence, the recommended objects for filling each recommendation slot can be obtained.

[0067] In some examples, the recommendation request may be automatically generated based on the user's behavior of opening the display page. In this case, the recommendation request may include information indicating the number of recommendation positions in the display page, and the method 200 may be used to obtain a recommendation sequence including a certain number of recommendation objects.

[0068] In some examples, the aforementioned display page may be a search page for displaying search results to the user, and the recommendation request may be generated in response to the search request of the target user. In this case, in step S201, the recommendation information may also be determined based on the user's search request, so that the recommendation sequence can be related to the user's search request, thereby increasing the probability of the user clicking or viewing the recommendation sequence and improving the accuracy of the recommendation.

[0069] Figure 3 FIG. 2 shows a schematic diagram of a structure of a recommendation model according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the recommendation model includes an encoding network 310 and a prediction network 320. In this example, the encoding network may include a search feature encoding layer 311, a user feature encoding layer 312, a category feature encoding layer 313, and an object feature encoding layer 314, and different types of input features are encoded by applying multiple independent encoding layers, that is, the input features can be mapped to a high-dimensional feature space, and the high-dimensional feature encoding results are used to indicate input features of different dimensions.

[0070] In some examples, the prediction network 320 may be built based on a Transformer network structure. In this case, the prediction network 320 may include an attention layer, and the attention layer may be used to implement multi-head attention calculation to obtain recommendation information more accurately and efficiently.

[0071] In some examples, the prediction network 320 may further include network structures such as an activation layer and an output layer to output explicit recommendation information.

[0072] According to one aspect of the present disclosure, a training method for a recommendation model is also provided. Figure 4 FIG. 4 is a flow chart of a training method 400 for a recommendation model according to an exemplary embodiment of the present disclosure. Figure 4 As shown, the method 400 includes:

[0073] Step S401: inputting user features of sample users, category features of multiple object categories, and object features of candidate objects included in each object category into a recommendation model to obtain predicted recommendation information output by the recommendation model, wherein the predicted recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category;

[0074] Step S402: determining a predicted recommendation sequence including a plurality of recommended objects based on the predicted recommendation information;

[0075] Step S403: determining a training score for the predicted recommendation sequence; and

[0076] Step S404: Adjust the parameters of the recommendation model based on the training score of the predicted recommendation sequence.

[0077] By applying the above method 400, a recommendation model that can determine recommendation information based on object category can be obtained, and then when a candidate object has certain object category information, the recommendation model can be used to generate recommendation information including recommendation categories and specific recommended objects. In the recommendation process, both object category features and object features are taken into account, thereby improving the recommendation accuracy.

[0078] According to one aspect of the present disclosure, a recommendation device is also provided. Figure 5 FIG. 5 shows a structural block diagram of a recommendation device 500 according to an exemplary embodiment of the present disclosure. Figure 5 As shown, the device 500 includes:

[0079] A first determining unit 501 is configured to determine, in response to receiving a recommendation request, recommendation information based on a user feature of a target user, category features of a plurality of object categories, and object features of candidate objects included in each object category, wherein the recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; and

[0080] The second determining unit 502 is configured to determine a recommendation sequence including a plurality of recommendation objects for the target user based on the recommendation information.

[0081] According to some embodiments, the recommendation information includes a plurality of information pairs arranged in sequence, and each of the plurality of information pairs includes a recommendation category and a recommendation object corresponding to the recommendation category.

[0082] According to some embodiments, the first determination unit 501 is configured to: input the user features, the category features of the multiple object categories, and the object features of the candidate objects included in each object category into a recommendation model to obtain recommendation information output by the recommendation model, wherein the recommendation model is trained using a model training device, and the model training device includes: a third determination unit, configured to determine a predicted recommendation sequence based on the predicted recommendation information output by the recommendation model; a fourth determination unit, configured to determine a training score for the predicted recommendation sequence; and a first adjustment unit, configured to adjust the parameters of the recommendation model based on the training score of the predicted recommendation sequence.

[0083] According to some embodiments, the fourth determination unit is configured to: input the predicted recommendation sequence into a scoring model to obtain the training score output by the scoring model, wherein the scoring model is trained using a sample recommendation sequence annotated with reference scoring information, and wherein the reference scoring information is determined based on actual interaction information of the user for the sample recommendation sequence.

[0084] According to some embodiments, the user characteristics of the target user include historical interaction information of the target user for historical recommendation sequences.

[0085] According to one aspect of the present disclosure, a training device for a recommendation model is also provided. Figure 6 FIG. 6 shows a structural block diagram of a training device 600 for a recommendation model according to an exemplary embodiment of the present disclosure. Figure 6 As shown, the device 600 includes:

[0086] An input unit 601 is configured to input user features of sample users, category features of multiple object categories, and object features of candidate objects included in each object category into a recommendation model to obtain predicted recommendation information output by the recommendation model, wherein the predicted recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category;

[0087] A fifth determining unit 602 is configured to determine a predicted recommendation sequence including a plurality of recommended objects based on the predicted recommendation information;

[0088] A scoring unit 603 is configured to determine a training score for the predicted recommendation sequence; and

[0089] The second adjusting unit 604 is configured to adjust the parameters of the recommendation model based on the training score of the predicted recommendation sequence.

[0090] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0091] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned recommendation method or recommendation model training method.

[0092] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned recommendation method or recommendation model training method.

[0093] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, wherein the computer program implements the above-mentioned recommendation method or recommendation model training method when executed by a processor.

[0094] refer to Figure 7 , a block diagram of an electronic device 700 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0095] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0096] Multiple components in the device 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 can be any type of device that can input information to the device 700. The input unit 706 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 707 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 708 can include but is not limited to a disk, an optical disk. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0097] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as a recommendation method or a training method for a recommendation model. For example, in some embodiments, the recommendation method or the training method for a recommendation model may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the recommendation method or the training method for the recommendation model described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the recommendation method or the training method of the recommendation model in any other appropriate manner (for example, by means of firmware).

[0098] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0100] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0103] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0105] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples. Various elements in the embodiments or examples may be omitted or may be replaced by their equivalent elements. In addition, each step may be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. It is important that with the evolution of technology, many elements described herein may be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A recommendation method, comprising: In response to receiving the recommendation request, determining recommendation information based on a user feature of a target user, category features of a plurality of object categories, and object features of candidate objects included in each object category, wherein the recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; and Based on the recommendation information, a recommendation sequence including a plurality of recommendation objects for the target user is determined.

2. The method of claim 1, wherein: The recommendation information includes a plurality of information pairs arranged in sequence, and each of the plurality of information pairs includes a recommendation category and a recommendation object corresponding to the recommendation category.

3. The method according to claim 1 or 2, wherein: The determining of the recommendation information based on the user characteristics of the target user, the category characteristics of the plurality of object categories, and the object characteristics of the candidate objects included in each object category comprises: Inputting the user features, the category features of the multiple object categories, and the object features of the candidate objects included in each object category into a recommendation model to obtain recommendation information output by the recommendation model, wherein the training process of the recommendation model includes: Determining a prediction recommendation sequence based on the prediction recommendation information output by the recommendation model; Determining a training score for the predicted recommendation sequence; and Based on the training score of the predicted recommendation sequence, the parameters of the recommendation model are adjusted.

4. The method of claim 3, wherein: The determining of a training score for the predicted recommendation sequence includes: The predicted recommendation sequence is input into a scoring model to obtain the training score output by the scoring model, wherein the scoring model is trained using a sample recommendation sequence annotated with reference score information, and wherein the reference score information is determined based on actual interaction information of the user for the sample recommendation sequence.

5. The method according to any one of claims 1 to 4, wherein: The user characteristics of the target user include historical interaction information of the target user for historical recommendation sequences.

6. A training method for a recommendation model, comprising: Inputting user features of sample users, category features of multiple object categories, and object features of candidate objects included in each object category into a recommendation model to obtain predicted recommendation information output by the recommendation model, wherein the predicted recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; Based on the predicted recommendation information, determining a predicted recommendation sequence including a plurality of recommended objects; Determining a training score for the predicted recommendation sequence; and Based on the training score of the predicted recommendation sequence, the parameters of the recommendation model are adjusted.

7. A recommendation device, comprising: a first determining unit configured to, in response to receiving a recommendation request, determine recommendation information based on a user feature of a target user, category features of a plurality of object categories, and object features of candidate objects included in each object category, wherein the recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; and The second determining unit is configured to determine a recommendation sequence including a plurality of recommendation objects for the target user based on the recommendation information.

8. The device according to claim 7, wherein: The recommendation information includes a plurality of information pairs arranged in sequence, and each of the plurality of information pairs includes a recommendation category and a recommendation object corresponding to the recommendation category.

9. The device according to claim 7 or 8, wherein: The first determining unit is configured to: The user features, the category features of the multiple object categories, and the object features of the candidate objects included in each object category are input into a recommendation model to obtain recommendation information output by the recommendation model, wherein the recommendation model is trained by a model training device, and the model training device includes: A third determining unit is configured to determine a predicted recommendation sequence based on the predicted recommendation information output by the recommendation model; a fourth determining unit, configured to determine a training score for the predicted recommendation sequence; and The first adjustment unit is configured to adjust the parameters of the recommendation model based on the training score of the predicted recommendation sequence.

10. The device of claim 9, wherein: The fourth determining unit is configured to: The predicted recommendation sequence is input into a scoring model to obtain the training score output by the scoring model, wherein the scoring model is trained using a sample recommendation sequence annotated with reference score information, and wherein the reference score information is determined based on actual interaction information of the user for the sample recommendation sequence.

11. The device according to any one of claims 7 to 10, wherein: The user characteristics of the target user include historical interaction information of the target user for historical recommendation sequences.

12. A training device for a recommendation model, comprising: an input unit configured to input user features of sample users, category features of multiple object categories, and object features of candidate objects included in each object category into a recommendation model to obtain predicted recommendation information output by the recommendation model, wherein the predicted recommendation information includes at least one recommended category and at least one recommended object corresponding to each recommended category; A fifth determining unit is configured to determine a predicted recommendation sequence including a plurality of recommended objects based on the predicted recommendation information; a scoring unit configured to determine a training score for the predicted recommendation sequence; and The second adjustment unit is configured to adjust the parameters of the recommendation model based on the training score of the predicted recommendation sequence.

13. An electronic device, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-6.

15. A computer program product comprising a computer program, wherein: The computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images