US-12619671-B2 - Resource list recommendation method, terminal device, and server

US12619671B2US 12619671 B2US12619671 B2US 12619671B2US-12619671-B2

Abstract

Disclosed are method for recommending a resource list, a terminal device, and a server. The method may include: acquiring current running information in response to detecting that the interface is invoked; inputting the running information into the local recommendation model to obtain recommendation probabilities of resources in the resource list; and selecting a to-be-recommended resource according to the recommendation probabilities and displaying the to-be-recommended resource.

Inventors

Xing Wang

Assignees

ZTE CORPORATION

Dates

Publication Date: 20260505
Application Date: 20230116
Priority Date: 20220516

Claims (10)

1 . A method for recommending a resource list, applied to a terminal device, wherein the terminal device provides an interface for acquiring the resource list, and the terminal device comprises a built-in local recommendation model and updates the local recommendation model based on an online learning algorithm, the method comprising: acquiring current running information in response to detecting that the interface is invoked; inputting the running information into the local recommendation model to obtain recommendation probabilities of resources in the resource list; and selecting a to-be-recommended resource according to the recommendation probabilities and displaying the to-be-recommended resource; wherein updating the local recommendation model based on the online learning algorithm comprises: acquiring current feature information in response to an invocation of a resource in the resource list; obtaining a feature vector corresponding to the resource invocation according to the feature information; and updating a parameter of the local recommendation model according to the feature vector; wherein the feature vector is stored in a local database of the terminal device, and the method further comprises: after inputting the running information into the local recommendation model to obtain recommendation probabilities of resources in the resource list, adjusting a length of the resource list and a number of feature vectors stored in the local database according to the recommendation probabilities, comprising: in response to the recommendation probability corresponding to a resource in the resource list being less than a preset probability threshold, monitoring a variance of the recommendation probabilities of the resource in latest N times and subsequent N times, and in response to the variance being less than a third preset value, deleting the resource from the resource list and deleting the feature vector related to the resource from the local database, wherein N is a positive integer.
2 . The method for recommending the resource list of claim 1 , wherein after detecting that the interface is invoked, the method further comprises: determining whether the interface invocation satisfies a model recommendation condition; and in response to the interface invocation not satisfying the model recommendation condition, performing resource recommendation according to an order of most recent usage of the resources in the resource list and selecting and displaying the to-be-recommended resource.
3 . The method for recommending the resource list of claim 2 , wherein the feature vector is stored in a local database of the terminal device, and the model recommendation condition comprises one of the following two conditions: a number of resources contained in the resource list is greater than or equal to a first preset value; or a number of feature vectors stored in the local database is greater than a second preset value.
4 . The method for recommending the resource list of claim 1 , wherein adjusting a length of the resource list and a number of feature vectors stored in the local database according to the recommendation probabilities further comprises: in response to the length of the resource list reaching a fourth preset value, deleting the resource corresponding to a minimum recommendation probability from the resource list and deleting the feature vector related to the resource from the local database.
5 . The method for recommending the resource list of claim 1 , wherein the local recommendation model is initially a basic recommendation model, the basic recommendation model is obtained through training by a server, and the method further comprises: performing update detection on the basic recommendation model in the server; and in response to detecting that the server provides an updated basic recommendation model, sending a local model parameter to the server such that the server fuses the local model parameter with a parameter of the updated basic recommendation model in the server, and receiving the fused model parameters from the server.
6 . The method for recommending the resource list of claim 1 , wherein the feature information comprises one or more of: current location information, a time period in which the resource is invoked, usage frequency of the resource, a category of the resource, an average invocation duration of the resource, a running status of a resource associated with the resource, or a search keyword.
7 . The method for recommending the resource list of claim 1 , further comprising: presetting a default resource, and in response to the interface for acquiring the resource list being invoked for the first time, displaying the default resource.
8 . A terminal device, comprising at least one control processor and a memory communicatively connected to the at least one control processor, wherein the memory stores instructions executable by the at least one control processor which, when executed by the at least one control processor, cause the at least one control processor to carry out a method for recommending a resource list, applied to a terminal device, wherein the terminal device provides an interface for acquiring the resource list, and the terminal device comprises a built-in local recommendation model and updates the local recommendation model based on an online learning algorithm, the method comprising: acquiring current running information in response to detecting that the interface is invoked; inputting the running information into the local recommendation model to obtain recommendation probabilities of resources in the resource list; and selecting a to-be-recommended resource according to the recommendation probabilities and displaying the to-be-recommended resource; wherein updating the local recommendation model based on the online learning algorithm comprises: acquiring current feature information in response to an invocation of a resource in the resource list; obtaining a feature vector corresponding to the resource invocation according to the feature information; and updating a parameter of the local recommendation model according to the feature vector; wherein the feature vector is stored in a local database of the terminal device, and the method further comprises: after inputting the running information into the local recommendation model to obtain recommendation probabilities of resources in the resource list, adjusting a length of the resource list and a number of feature vectors stored in the local database according to the recommendation probabilities, comprising: in response to the recommendation probability corresponding to a resource in the resource list being less than a preset probability threshold, monitoring a variance of the recommendation probabilities of the resource in latest N times and subsequent N times, and in response to the variance being less than a third preset value, deleting the resource from the resource list and deleting the feature vector related to the resource from the local database, wherein N is a positive integer.
9 . The terminal device of claim 8 , wherein after detecting that the interface is invoked, the method further comprises: determining whether the interface invocation satisfies a model recommendation condition; and in response to the interface invocation not satisfying the model recommendation condition, performing resource recommendation according to an order of most recent usage of the resources in the resource list and selecting and displaying the to-be-recommended resource.
10 . The terminal device of claim 9 , wherein the feature vector is stored in a local database of the terminal device, and the model recommendation condition comprises one of the following two conditions: a number of resources contained in the resource list is greater than or equal to a first preset value; or a number of feature vectors stored in the local database is greater than a second preset value.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is a national stage filing under 35 U.S.C. § 371 of international application number PCT/CN2023/072451, filed Jan. 16, 2023, which claims priority to Chinese patent application No. 202210529658.6 filed May 16, 2022. The contents of these applications are incorporated herein by reference in their entirety. TECHNICAL FIELD The present disclosure relates to the field of intelligent recommendation, and more particularly, to a method for recommending a resource list, a terminal device, and a server. BACKGROUND Currently, most resources recommendation lists in terminal devices are sorted by the most recent usage time. However, when there are too many historical usage records, the number of recommended resources in the list increases accordingly, requiring the user to further search or browse through numerous resources in the list for a particular resource. SUMMARY The present disclosure provides a method for recommending a resource list, a terminal device, and a server. In accordance with a first aspect of the present disclosure, an embodiment provides a method for recommending a resource list, which is applied to a terminal device. The terminal device provides an interface for acquiring the resource list, and the terminal device includes a built-in local recommendation model and updates the local recommendation model based on an online learning algorithm. The method includes: acquiring current running information in response to detecting that the interface is invoked; inputting the running information into the local recommendation model to obtain recommendation probabilities of resources in the resource list; and selecting a to-be-recommended resource according to the recommendation probabilities and displaying the to-be-recommended resource. In accordance with a second aspect of the present disclosure, an embodiment provides a method for recommending a resource list, which is applied to a server. The server stores background operation data of resources. The method includes: training a basic recommendation model according to the background operation data; and presetting the basic recommendation model in a terminal device as an initial local recommendation model of the terminal device, such that the terminal device recommends the resource list according to the local recommendation model and an online learning algorithm. In accordance with a third aspect of the present disclosure, an embodiment provides a terminal device, including at least one control processor and a memory communicatively connected to the at least one control processor, where the memory stores instructions executable by the at least one control processor which, when executed by the at least one control processor, cause the at least one control processor to carry out the method for recommending a resource list according to the embodiment of the first aspect of the present disclosure. In accordance with a fourth aspect of the present disclosure, an embodiment provides a server, including at least one control processor and a memory communicatively connected to the at least one control processor, wherein the memory stores instructions executable by the at least one control processor which, when executed by the at least one control processor, causes the at least one control processor to carry out the method for recommending a resource list according to the embodiment of the second aspect of the present disclosure. Additional features and advantages of the present disclosure will be outlined in the following description and will, in part, become apparent from the description, or may be learned through the practice of the present disclosure. The purposes and other advantages of the present disclosure can be realized and obtained through the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS The drawings are provided for a further understanding of the technical schemes of the present disclosure, and form part of the description. The drawings and the embodiments of the present disclosure are used to illustrate the technical schemes of the present disclosure, and are not intended to limit them. The present disclosure is further described below in conjunction with the accompanying drawings and embodiments. FIG. 1 is a flowchart of steps of a method for recommending a resource list according to an embodiment of the present disclosure; FIG. 2 is a flowchart of part of steps of another method for recommending a resource list according to an embodiment of the present disclosure; FIG. 3 is a flowchart of part of steps of another method for recommending a resource list according to an embodiment of the present disclosure; FIG. 4 is a detailed flowchart of part of steps of another method for recommending a resource list according to an embodiment of the present disclosure; FIG. 5 is a detailed flowchart of part of steps of another method for recommendin