Resource recommendation method and device, equipment and storage medium

Abstract

This disclosure provides a resource recommendation method, apparatus, device, storage medium, and program product, relating to the field of computer technology, and particularly to the fields of artificial intelligence and information recommendation. The specific implementation scheme includes: obtaining a recommendation sequence, wherein the recommendation sequence includes at least one resource to be recommended; determining the probability of continuing browsing corresponding to each resource to be recommended in the recommendation sequence; determining a target step size based on the probability of continuing browsing corresponding to each resource to be recommended; and recommending the resources to be recommended in the recommendation sequence according to the target step size.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of artificial intelligence and information recommendation. Background Technology

[0002] With the development of mobile internet, recommendation systems have penetrated into many application areas, effectively solving the problem of information overload. To provide users with a better recommendation experience, recommendation systems can create immersive browsing scenarios, such as immersive video browsing scenarios and immersive text and image browsing scenarios. In immersive browsing scenarios, the step size of immersive browsing is an important indicator. Summary of the Invention

[0003] This disclosure provides a resource recommendation method, apparatus, device, storage medium, and program product.

[0004] According to one aspect of this disclosure, a resource recommendation method is provided, comprising: obtaining a recommendation sequence, wherein the recommendation sequence includes at least one resource to be recommended; determining a continued browsing probability corresponding to each resource to be recommended in the recommendation sequence; determining a target step size based on the continued browsing probability corresponding to each resource to be recommended; and recommending the resources to be recommended in the recommendation sequence based on the target step size.

[0005] According to another aspect of this disclosure, a resource recommendation apparatus is provided, comprising: a sequence acquisition module for acquiring a recommendation sequence, wherein the recommendation sequence includes at least one resource to be recommended; a probability determination module for determining a continued browsing probability corresponding to each resource to be recommended in the recommendation sequence; a step size determination module for determining a target step size based on the continued browsing probability corresponding to each resource to be recommended; and a recommendation module for recommending the resources to be recommended in the recommendation sequence based on the target step size.

[0006] Another aspect of this disclosure provides an electronic device including: 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 to enable the at least one processor to perform the methods shown in embodiments of this disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the methods shown in the embodiments of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instructions, characterized in that, when the computer program / instructions are executed by a processor, they implement the steps of the method shown in the embodiments of the present disclosure.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This illustration schematically shows an exemplary system architecture to which resource recommendation methods and apparatus can be applied according to embodiments of this disclosure;

[0012] Figure 2 A flowchart illustrating a resource recommendation method according to an embodiment of the present disclosure is shown schematically;

[0013] Figure 3 A flowchart illustrating a method for determining the probability of continuing browsing for each resource to be recommended, according to an embodiment of the present disclosure, is shown.

[0014] Figure 4 A flowchart illustrating a method for determining a target step size according to an embodiment of the present disclosure is shown schematically.

[0015] Figure 5 A flowchart illustrating a resource recommendation method according to another embodiment of this disclosure is shown schematically;

[0016] Figure 6 A schematic diagram illustrating the determination of a target step size according to another embodiment of the present disclosure is shown.

[0017] Figure 7 A block diagram of a resource recommendation apparatus according to embodiments of the present disclosure is schematically shown; and

[0018] Figure 8 A block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is illustrated schematically. Detailed Implementation

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] The following will combine Figure 1 An exemplary system architecture for which resource recommendation methods and apparatus can be applied, as provided in this disclosure, is described.

[0021] Figure 1 This illustration schematically depicts an exemplary system architecture to which resource recommendation methods and apparatus can be applied according to embodiments of this disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0022] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0023] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0024] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0025] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103. The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0026] Server 105 can be a cloud server, also known as a cloud computing server or cloud host. It is a host product in the cloud computing service system, which solves the shortcomings of traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"), such as high management difficulty and weak business scalability. Server 105 can also be a server for a distributed system or a server combined with blockchain.

[0027] It should be noted that the resource recommendation method provided in this embodiment can generally be executed by server 105. Correspondingly, the resource recommendation device provided in this embodiment can generally be located in server 105. The resource recommendation method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the resource recommendation device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0028] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0029] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0030] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0031] The following will combine Figure 2 The resource recommendation method provided in this disclosure is described.

[0032] Figure 2 A flowchart illustrating a resource recommendation method according to an embodiment of the present disclosure is shown.

[0033] like Figure 2 As shown, the resource recommendation method 200 includes operation S210, obtaining a recommendation sequence.

[0034] According to embodiments of this disclosure, the recommendation sequence may include at least one resource to be recommended. The resource to be recommended may include, for example, video, audio, text, images, and other resources.

[0035] Then, in operation S220, the probability of continuing to browse corresponding to each resource to be recommended in the recommendation sequence is determined.

[0036] According to embodiments of this disclosure, the probability of continuing to browse can be used to represent the probability that a user will continue browsing after browsing the recommended resources.

[0037] In operation S230, the target step size is determined based on the probability of continuing to browse for each resource to be recommended.

[0038] According to embodiments of this disclosure, the probability of continuing browsing can be used to represent the probability that a user will continue browsing the next recommended resource after browsing the previous one. The target step size can be used to represent the number of resources included in a single recommendation.

[0039] For example, users can swipe to browse the next resource. Therefore, it's possible to detect whether a swipe is triggered; if so, it indicates that the user continues browsing.

[0040] In operation S240, resources to be recommended in the recommendation sequence are recommended according to the target step size.

[0041] According to embodiments of this disclosure, for example, the resources to be recommended in the recommendation sequence can be divided into multiple batches based on a target step size. Then, the resources to be recommended in multiple batches are displayed sequentially.

[0042] The resource recommendation method according to embodiments of this disclosure can be applied to immersive browsing scenarios. In an immersive browsing scenario, m resources can be recommended to the user, allowing the user to browse these m resources in an immersive manner. After the user has browsed all m resources, a refresh operation can be triggered to continue browsing another m resources. Here, m is a positive integer, representing the step size.

[0043] When recommending related technical resources, the step size is set manually, and the step size setting is unreasonable.

[0044] According to embodiments of this disclosure, the step size is determined based on the probability of continuing to browse each resource to be recommended, which can optimize the step size, make the step size more reasonable, improve the user experience, and increase the number of users of the application.

[0045] The following is for reference. Figure 3 The method for determining the probability of continuing to browse for each resource to be recommended, as shown above, will be further explained in conjunction with specific embodiments.

[0046] Figure 3 A flowchart illustrating a method for determining the probability of continuing browsing for each resource to be recommended, according to an embodiment of the present disclosure, is shown.

[0047] like Figure 3 As shown, the method 320 for determining the probability of continuing to browse for each resource to be recommended may include, for example, operation S321, determining input features for each resource to be recommended based on at least one of the following: click-through rate estimate, duration estimate, completion rate estimate, and interaction data.

[0048] According to embodiments of this disclosure, the Click-Through-Rate (CTR) estimate can be used to estimate the probability that a resource to be recommended will be clicked. The CTR estimate may include, for example, a CTR estimate. Exemplarily, a machine learning model can be pre-trained to estimate the probability of a user clicking on the resource. The duration estimate can be used to estimate the viewing time of a user browsing the resource to be recommended. The completion rate estimate can be used to estimate the proportion of the resource viewed by a user out of the total recommended resources. For example, if a user watches 1 minute of a 10-minute video, the completion rate is 10%. Interaction data can be used to estimate the probability that a user will interact with the resource to be recommended. Interactions may include, for example, liking, commenting, and sharing.

[0049] In operation S322, the input features are fed into the machine learning model to obtain the probability of continuing to browse the resource to be recommended.

[0050] According to embodiments of this disclosure, a machine learning model can be pre-trained to determine the probability of continuing to browse a resource to be recommended. The input to this machine learning model can be at least one of the resource's click-through rate prediction, duration prediction, completion rate prediction, and interaction data. The output can be the probability of continuing to browse the resource.

[0051] The following is for reference. Figure 4 The method for determining the target step size shown above will be further explained with reference to specific embodiments.

[0052] Figure 4 A flowchart illustrating a method for determining a target step size according to an embodiment of the present disclosure is shown schematically.

[0053] like Figure 4 As shown, the method 430 for determining the probability of continuing to browse for each resource to be recommended may, for example, include operation S431, which determines multiple candidate step sizes based on the recommendation sequence.

[0054] In operation S432, the probability of continuing to browse for each resource to be recommended is used to determine the expected value of each candidate step size among multiple candidate step sizes.

[0055] In operation S433, the candidate step size with the highest mathematical expectation among multiple candidate step sizes is determined as the target step size.

[0056] According to embodiments of this disclosure, for example, the configurable step size of the recommended sequence can be enumerated to obtain candidate step sizes.

[0057] According to embodiments of this disclosure, for example, the expected value corresponding to the candidate step size can be used as reference data to measure the reasonableness of the candidate step size. The larger the expected value of the candidate step size, the more reasonable the candidate step size is.

[0058] According to embodiments of this disclosure, immersive browsing scenarios can be divided into two types: immersive browsing scenarios with entry resources and immersive browsing scenarios without entry resources.

[0059] Entry resources refer to resources used as entry points to immersive browsing scenarios. In immersive browsing scenarios with entry resources, users can enter the immersive browsing interface by clicking on the corresponding entry resource on the list page.

[0060] For example, the application interface can include a comprehensive information feed, and entry resources can be set within this feed. When a user clicks on a specific type of entry resource within the comprehensive information feed, they will enter a corresponding immersive browsing scenario. In this scenario, the recommended resources are all of the same type as the entry resource, and the user can immerse themselves in browsing these resources.

[0061] In immersive browsing scenarios without entry resources, users enter the immersive browsing interface as soon as they open the application, or they enter the immersive browsing interface through the application's function entry point, rather than through an entry resource.

[0062] For example, some short video apps allow users to enter an immersive video browsing experience as soon as they open the app, without any entry resources.

[0063] For immersive browsing scenarios with entry points, the expected value can be calculated using, for example, the following formula:

[0064] E(S(L|u,i))=E(S({d1,d2,…,d n}|u,i))=1*p(↓|u,i)*(1-p(↓|u,i,d1))+2*p(↓|u,i)*p(↓|u,i,d1)( 1-p(↓|u,i,d1,d2))+…+n*p(↓|u,i)*p(↓|u,i,d1)*…*p(↓|u,i,d1,…,d n-1 )=p(↓|u,i)*[1*(1-p(↓|u,i,d1))+2*p(↓|u,i,d1)(1-p(↓|u,i,d1,d2))+…+n*p(↓|u,i,d1)*…*p(↓|u,i,d1,…,d n-1 )]=p(↓|u,i)*V(S(L|u,i))

[0065] Where u can represent an object, such as a user. i can represent an entry resource. L is the recommendation sequence, L = {d1, d2, ..., dn}, where d1, d2, ..., dn are the resources to be recommended. (S(L|u, i)) represents the step size, and E is the expected value of (S(L|u, i)). p(↓|u, i) represents the probability that an object continues to be viewed after being viewed i. n-1 The expression represents the probability that a user will continue browsing after viewing i, d1, d2, ..., dn-1. 1, 2, ..., n correspond to the cases with step sizes of 1, 2, ..., n, respectively.

[0066] For example, in this embodiment, V(S(L|u,i)) can be denoted as:

[0067] V(S(L|u,i))=1*(1-p(↓|u,i,d1))+2*p(↓|u,i,d1)(1-p(↓|u,i,d1,d2))+…+n*p(↓|u,i,d1)*…*p(↓|u,i,d1,…,d n-1 )

[0068] When joint optimization of entry resources and step size is required, the optimization objective can be expressed as maximizing E(S(L|u,i))=p(↓|u,i)*V(S(L|u,i)), that is, choosing appropriate i and L to maximize the step size.

[0069] Given the entry resources, and only needing to optimize the step size, the optimization objective can be expressed as maximizing V(S(L|u,i)).

[0070] For immersive browsing scenarios without entry resources, the expected value can be calculated using the following formula:

[0071] E(S(L|u))=E(S({d1,d2,…,d n}|u))=1*p(↓|u)*(1-p(↓|u,d1))+2*p(↓|u)*p(↓|u,d1)(1-p(↓|u,d1,d2))+…+n*p(↓|u)*p(↓|u,d1)*…*p(↓|u,d1,…,d n-1 )=p(↓|u)*[1*(1-p(↓|u,d1))+2*p(↓|u,d1)(1-p(↓|u,d1,d2))+…+n*p(↓|u,d1)*…*p(↓|u,d1,…,d n-1 )|=p(↓|u)*V(S(L|u))

[0072] Where u can represent an object, such as a user. L is the recommendation sequence, L = {d1, d2, ..., dn}, where d1, d2, ..., dn are the resources to be recommended. (S(L|u)) represents the step size, and E is the expected value of (S(L|u)). p(↓|u) represents the probability that an object enters the immersive browsing interface. p(↓|u, i, d1, ..., dn) n-1 The expression represents the probability that a user will continue browsing after viewing i, d1, d2, ..., dn-1. 1, 2, ..., n correspond to the cases with step sizes of 1, 2, ..., n, respectively.

[0073] For example, in this embodiment, V(S(L|u)) can be denoted as:

[0074] V(S(L|u))=1*(1-p(↓|u,d1))+2*p(↓|u,d1)(1-p(↓|u,d1,d2))+…+n*p(↓|u,d1)*…*p(↓|u,d1,…,d n-1 )

[0075] The probability p(↓|u) of an object entering the immersive browsing interface is independent of the current recommended result. Therefore, when optimizing the step size, it is only necessary to maximize V(S(L|u)).

[0076] According to embodiments of this disclosure, by calculating the mathematical expectation of each candidate step size and determining the target step size based on the mathematical expectation, the target step size can be improved, thereby enhancing the user experience and increasing the number of users of the application.

[0077] Figure 5 A flowchart illustrating a resource recommendation method according to another embodiment of this disclosure is shown schematically.

[0078] like Figure 5 As shown, the resource recommendation method 500 may also include operation S550, which involves obtaining multiple candidate resources.

[0079] According to embodiments of this disclosure, candidate resources may include, for example, video, audio, text, images, and other resources.

[0080] In operation S560, each candidate resource among multiple candidate resources is evaluated to obtain an evaluation value for each candidate resource.

[0081] According to embodiments of this disclosure, the evaluation value can be used to represent a user's degree of liking for candidate resources. For example, in this embodiment, a higher evaluation value indicates a higher degree of liking for the candidate resource.

[0082] According to embodiments of this disclosure, for example, object features, resource features, and cross-features between the candidate resource and the object can be obtained for each candidate resource. Then, based on the object features, resource features, and cross-features corresponding to each candidate resource, an evaluation value for each candidate resource is determined. Object features may include user preference information, etc. Resource features may include, for example, keywords, categories, publication time, etc. Cross-features may include the matching degree between the user and the resource, etc.

[0083] According to another embodiment of this disclosure, candidate resources can be evaluated, for example, using a pre-trained machine learning model. The input to the machine learning model can be object features, resource features, and cross features of the resource. The output can be an evaluation value for the resource.

[0084] In operation S570, based on the evaluation value, at least one resource to be recommended is determined from multiple candidate resources to obtain a recommendation sequence.

[0085] According to embodiments of this disclosure, for example, the k candidate resources with the highest evaluation values ​​among multiple candidate resources can be determined as the resources to be recommended, where k is a positive integer and the value of k can be set according to actual needs.

[0086] According to another embodiment of this disclosure, for example, a beam-search algorithm can be used to select the final k candidate resources. Beam-search can be understood as a breadth-first search, a greedy algorithm for finding potentially optimal sequences. The beam-search algorithm includes a parameter beam size. When the search is performed in multiple rounds, each round retains the beam-size candidate resources with the highest scores, and then the search continues based on these beam-size candidate resources in the next round. The larger the beam size, the better the candidate results, but the greater the performance overhead. Therefore, the value of beam size can be set according to the requirements of computational performance and search effect to achieve a trade-off between computational performance and search effect. Exemplarily in this embodiment, the evaluation value can be used as the score of each round of the beam-search algorithm. Alternatively, in each round of selection, the mathematical expectation of the step size of each sequence segment can be evaluated to assist the beam-search algorithm in selecting the final k candidate resources. The beam-search algorithm...

[0087] According to embodiments of this disclosure, the quality of recommended sequences can be improved using the beam-search algorithm. The higher the quality of the recommended sequences, the better the effect of step size optimization.

[0088] The following is for reference. Figure 6The method for determining the target step size described above will be further explained with reference to specific embodiments. Those skilled in the art will understand that the following example embodiments are only for understanding this disclosure, and this disclosure is not limited thereto.

[0089] Figure 6 A schematic diagram illustrating the determination of a target step size according to another embodiment of the present disclosure is shown.

[0090] exist Figure 6 The diagram illustrates how multiple resources 602 to be recommended are determined from a plurality of candidate resources 601. These multiple resources 602 to be recommended constitute a recommendation sequence.

[0091] For example, in this embodiment, each of the multiple candidate resources 601 can be evaluated to obtain an evaluation value for each candidate resource 601. The evaluation value can be used to represent the user's degree of liking for the candidate resource. Based on the evaluation value, multiple resources 602 to be recommended are determined from the multiple candidate resources 601.

[0092] For each resource to be recommended 602, input features are determined based on the predicted click-through rate, predicted duration, predicted completion rate, and interaction data. Each input feature is then fed into the machine learning model to obtain the probability of continuing to browse 603 corresponding to each resource to be recommended 602.

[0093] Then, based on the recommendation sequence, multiple candidate step sizes 604 are determined. Based on the probability of continuing to browse 603 corresponding to each resource to be recommended, the expected value of each candidate step size 604 is determined, and the candidate step size 604 with the largest expected value among the multiple candidate step sizes 604 is determined as the target step size 605.

[0094] The following will combine Figure 7 The resource recommendation device provided in this disclosure is described.

[0095] Figure 7 A block diagram of a resource recommendation apparatus according to an embodiment of the present disclosure is shown schematically.

[0096] like Figure 7 As shown, the resource recommendation device 700 may include a sequence acquisition module 710, a probability determination module 720, a step size determination module 730, and a recommendation module 740.

[0097] The sequence acquisition module 710 can be used to acquire recommended sequences, wherein the recommended sequence includes at least one resource to be recommended.

[0098] The probability determination module 720 can be used to determine the probability of continuing to browse for each resource to be recommended in the recommendation sequence.

[0099] The step size determination module 730 can be used to determine the target step size based on the probability of continuing to browse each resource to be recommended.

[0100] The recommendation module 740 can be used to recommend resources in the recommendation sequence based on the target step size.

[0101] According to embodiments of this disclosure, the probability determination module may include a feature determination submodule and an input submodule. The feature determination submodule is used to determine input features for each resource to be recommended, based on at least one of the following: a click-through rate prediction, a duration prediction, a completion rate prediction, and interaction data. The input submodule is used to input the input features into a machine learning model to obtain the probability of continuing to browse corresponding to the resource to be recommended.

[0102] According to embodiments of this disclosure, the step size determination module may include a candidate step size determination submodule, an expected step size determination submodule, and a target step size determination submodule. The candidate step size determination submodule can be used to determine multiple candidate step sizes based on the recommendation sequence. The expected step size determination submodule can be used to determine the expected value corresponding to each candidate step size among the multiple candidate step sizes, based on the probability of continuing to browse for each resource to be recommended. The target step size determination submodule can be used to determine the candidate step size with the largest expected value among the multiple candidate step sizes, as the target step size.

[0103] According to embodiments of this disclosure, the resource recommendation device may further include a resource acquisition module, an evaluation module, and a recommendation sequence determination module. The resource acquisition module can acquire multiple candidate resources. The evaluation module can evaluate each candidate resource to obtain an evaluation value for each candidate resource. The recommendation sequence determination module can determine multiple resources to be recommended from the multiple candidate resources based on the evaluation values, thus obtaining a recommendation sequence.

[0104] According to embodiments of this disclosure, the evaluation module may include a feature acquisition submodule and an evaluation value determination submodule. The feature acquisition submodule is used to acquire object features, resource features, and cross-features between the candidate resource and the object corresponding to each candidate resource. The evaluation value determination submodule is used to determine the evaluation value of each candidate resource based on the object features, resource features, and cross-features corresponding to each candidate resource.

[0105] According to embodiments of this disclosure, the recommendation module may include a partitioning submodule and a display submodule. The partitioning submodule is used to divide the resources to be recommended in the recommendation sequence into multiple batches according to a target step size. The display submodule is used to sequentially display the resources to be recommended from multiple batches.

[0106] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0107] Figure 8 A block diagram schematically illustrates an example electronic device 800 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0108] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0109] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0110] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the resource recommendation method. For example, in some embodiments, the resource recommendation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the resource recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the resource recommendation method by any other suitable means (e.g., by means of firmware).

[0111] Various embodiments 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0115] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0116] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0117] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A resource recommendation method, comprising: Obtain a recommendation sequence, wherein the recommendation sequence includes at least one resource to be recommended; Determine the probability of continuing to browse for each resource to be recommended in the recommendation sequence; The target step size is determined based on the probability of continuing to browse corresponding to each resource to be recommended; and Based on the target step size, the resources to be recommended in the recommendation sequence are recommended. The step of determining the target step size based on the probability of continuing to browse corresponding to each resource to be recommended includes: Based on the recommended sequence, multiple candidate step sizes are determined; Based on the probability of continuing to browse corresponding to each resource to be recommended, determine the expected value corresponding to each of the plurality of candidate step sizes; and The candidate step size with the highest mathematical expectation among the multiple candidate step sizes is determined as the target step size, and... The determination of the probability of continuing browsing for each resource to be recommended in the recommendation sequence includes: For each of the resources to be recommended, Based on at least one of the following: the predicted click-through rate, predicted duration, predicted completion rate, and interaction data of the resource to be recommended, determine the input features; and The input features are fed into a machine learning model to obtain the probability of continuing to browse the resource to be recommended.

2. The resource recommendation method according to claim 1 further includes: Obtain multiple candidate resources; Each of the plurality of candidate resources is evaluated to obtain an evaluation value for each candidate resource; as well as Based on the evaluation value, at least one resource to be recommended is determined from the plurality of candidate resources, thus obtaining the recommendation sequence.

3. The resource recommendation method according to claim 2, wherein, The step of evaluating each of the plurality of candidate resources to obtain an evaluation value for each candidate resource includes: Obtain the object features, resource features, and cross-features between the candidate resources and the object corresponding to each candidate resource; and The evaluation value of each candidate resource is determined based on the object characteristics, resource characteristics, and cross-features corresponding to each candidate resource.

4. The resource recommendation method according to any one of claims 1-3, wherein, The step of recommending resources in the recommendation sequence according to the target step size includes: Based on the target step size, the resources to be recommended in the recommendation sequence are divided into multiple batches; and The multiple batches of resources to be recommended will be displayed sequentially.

5. A resource recommendation device, comprising: A sequence acquisition module is used to acquire a recommended sequence, wherein the recommended sequence includes at least one resource to be recommended; The probability determination module is used to determine the probability of continuing to browse for each resource to be recommended in the recommendation sequence. The step size determination module is used to determine the target step size based on the probability of continuing browsing corresponding to each resource to be recommended; and The recommendation module is used to recommend resources in the recommendation sequence according to the target step size. The step size determination module includes: The candidate step size determination submodule is used to determine multiple candidate step sizes based on the recommended sequence; The expectation determination submodule is used to determine the mathematical expectation corresponding to each candidate step size among the plurality of candidate step sizes based on the probability of continuing to browse corresponding to each resource to be recommended; and The target step size determination submodule is used to determine the candidate step size with the largest mathematical expectation among the multiple candidate step sizes, and use it as the target step size. The probability determination module includes: The feature determination submodule is used to determine input features for each resource to be recommended, based on at least one of the following: predicted click-through rate, predicted duration, predicted completion rate, and interaction data; and The input submodule is used to input the input features into the machine learning model to obtain the probability of continuing to browse corresponding to the resource to be recommended.

6. The resource recommendation device according to claim 5, further comprising: The resource acquisition module is used to acquire multiple candidate resources. An evaluation module is used to evaluate each of the plurality of candidate resources to obtain an evaluation value for each candidate resource; as well as The recommendation sequence determination module is used to determine at least one resource to be recommended from the plurality of candidate resources based on the evaluation value, thereby obtaining the recommendation sequence.

7. The resource recommendation device according to claim 6, wherein, The evaluation module includes: The feature acquisition submodule is used to acquire the object features, resource features, and cross features between the candidate resource and the object corresponding to each candidate resource; and The evaluation value determination submodule is used to determine the evaluation value of each candidate resource based on the object characteristics, resource characteristics, and cross characteristics corresponding to each candidate resource.

8. The resource recommendation device according to any one of claims 5-7, wherein, The recommendation module includes: A segmentation submodule is used to divide the resources to be recommended in the recommendation sequence into multiple batches according to the target step size; and The display submodule is used to sequentially display the multiple batches of resources to be recommended.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the resource recommendation method according to any one of claims 1-4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the resource recommendation method according to any one of claims 1-4.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the resource recommendation method according to any one of claims 1-4.

Images