CN-121980076-A - Resource recommendation method, device, equipment, medium and product

Abstract

The disclosure provides a resource recommendation method, a device, equipment, a medium and a product, relates to the technical field of artificial intelligence, and particularly relates to the technical fields of intelligent recommendation, deep learning, large models and the like. The resource recommendation method comprises the steps of obtaining object side characteristics of a target object, wherein the object side characteristics comprise behavior characteristics of the target object on a target page, obtaining resource side characteristics of each candidate resource in a plurality of candidate resources, the resource side characteristics comprise resource characteristics, item characteristics of a current play item and entity characteristics of associated entities, obtaining target indexes based on the object side characteristics and the resource side characteristics, determining target resources in the plurality of candidate resources based on the target indexes, and recommending the target resources to the target object. The resource recommendation accuracy can be improved.

Inventors

• WANG JIANQIANG
• GAO YUAN
• LI MEIFANG
• XU PEIZHI

Assignees

• 北京百度网讯科技有限公司

Dates

Publication Date

20260505

Application Date

20251216

Claims (10)

1. 1. A resource recommendation method, comprising: the method comprises the steps of obtaining object side characteristics of a target object, wherein the object side characteristics comprise behavior characteristics of the target object on a target page; Acquiring resource side characteristics of each candidate resource in a plurality of candidate resources, wherein the resource side characteristics comprise resource characteristics, item characteristics of a current play item and entity characteristics of an associated entity; acquiring a target index based on the object side characteristic and the resource side characteristic; determining a target resource among the plurality of candidate resources based on the target indicator; recommending the target resource to the target object.
2. 2. The method of claim 1, wherein obtaining the resource signature comprises: slicing each candidate resource to obtain a plurality of resource segments, wherein the plurality of resource segments comprise current resource segments; Determining style labels of the candidate resources based on the plurality of resource segments; Determining resource semantic identifications of the candidate resources based on the current resource segment; And converting the style tag into style characteristics, and combining the style characteristics and the resource semantic identification to form the resource characteristics.
3. 3. The method of claim 2, wherein the determining style tags for the respective candidate resources based on the plurality of resource segments comprises: obtaining text fragments corresponding to each resource fragment, and processing the text fragments by adopting a large model to obtain style labels corresponding to the text fragments; And determining the style label of each candidate resource based on the style label corresponding to the text segment.
4. 4. The method of claim 2, wherein, The current resource segment is a multi-modal segment; The determining, based on the current resource segment, a resource semantic identification of the respective candidate resource includes: processing the multi-modal fragments by adopting a first multi-modal large model to obtain first multi-modal characteristics; and processing the first multi-mode features by adopting a self-coding model to obtain the resource semantic identification.
5. 5. The method of claim 1, wherein obtaining the item feature comprises: Acquiring multi-modal item data corresponding to the current play item, wherein the multi-modal item data comprises an item text; extracting core words in the project text; Acquiring the item semantic identifier of the current play item based on the multi-mode item data; and converting the core word into a core word feature, and identifying the core word feature and the project semantics to form the project feature.
6. 6. The method of claim 5, wherein the obtaining, based on the multimodal item data, an item semantic identification of the current play item comprises: Processing the multi-modal item data by adopting a second multi-modal large model to obtain a second multi-modal feature; and processing the second multi-modal feature by adopting a self-coding model to obtain the item semantic identification.
7. 7. A resource recommendation device, comprising: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring object side characteristics of a target object, and the object side characteristics comprise behavior characteristics of the target object on a target page; the second acquisition module is used for acquiring resource side characteristics of each candidate resource in the plurality of candidate resources, wherein the resource side characteristics comprise resource characteristics, item characteristics of a current play item and entity characteristics of an associated entity; The processing module is used for acquiring a target index based on the object side characteristic and the resource side characteristic; a determining module, configured to determine a target resource among the plurality of candidate resources based on the target indicator; and the recommending module is used for recommending the target resource to the target object.
8. 8. An electronic device, comprising: at least one processor, and A memory communicatively coupled 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 method of any one of claims 1-6.
9. 9. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-6.
10. 10. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-6.

Description

Resource recommendation method, device, equipment, medium and product Technical Field The disclosure relates to the technical field of artificial intelligence, in particular to the technical fields of intelligent recommendation, deep learning, large models and the like, and particularly relates to a resource recommendation method, device, equipment, medium and product. Background The resource recommendation refers to a process of precisely pushing resources meeting potential requirements of a target object to the target in a mode of an algorithm model or a rule strategy and the like based on relevant characteristics such as basic properties and behaviors of the target object. Through the accurate matching of the target object and the resource, the screening cost of the target object is reduced, and the exposure and utilization efficiency of the resource are improved. Disclosure of Invention The disclosure provides a resource recommendation method, a device, equipment, a medium and a product. According to one aspect of the disclosure, a resource recommendation method is provided, and the resource recommendation method comprises the steps of obtaining object side characteristics of a target object, wherein the object side characteristics comprise behavior characteristics of the target object on a target page, obtaining resource side characteristics of each candidate resource in a plurality of candidate resources, the resource side characteristics comprise resource characteristics, item characteristics of a current play item and entity characteristics of associated entities, obtaining target indexes based on the object side characteristics and the resource side characteristics, determining target resources in the plurality of candidate resources based on the target indexes, and recommending the target resources to the target object. According to another aspect of the disclosure, a resource recommendation device is provided, and the resource recommendation device comprises a first acquisition module, a second acquisition module and a processing module, wherein the first acquisition module is used for acquiring object side characteristics of a target object, the object side characteristics comprise behavior characteristics of the target object on a target page, the second acquisition module is used for acquiring resource side characteristics of each candidate resource in a plurality of candidate resources, the resource side characteristics comprise resource characteristics, item characteristics of a current play item and entity characteristics of associated entities, the processing module is used for acquiring target indexes based on the object side characteristics and the resource side characteristics, the determining module is used for determining target resources in the plurality of candidate resources based on the target indexes, and the recommendation module is used for recommending the target resources to the target object. According to another aspect of the present disclosure there is provided an electronic device comprising at least one processor and a memory communicatively coupled 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 method of any one of the above aspects. According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method according to any one of the above aspects. According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method according to any of the above aspects. According to the embodiment of the disclosure, the resource recommendation accuracy can be improved. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification. Drawings The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein: FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure; FIG. 2 is a schematic diagram of a resource feature acquisition process provided in accordance with an embodiment of the present disclosure; FIG. 3 is a schematic diagram of an acquisition process of project features provided in accordance with an embodiment of the present disclosure; FIG. 4 is a schematic diagram according to a second embodiment of the present disclosure; FIG. 5 is a schematic diagram according to a third embodiment of the present disclosure; Fig. 6 is a schematic diagram of an electronic device for implem