Method, apparatus, device, storage medium and program product for object determination
According to the embodiments of the present disclosure, a method, an apparatus, a device, a storage medium and a program product for object determination are provided. The method includes: recalling, from a set of objects, a plurality of candidate objects for a target promoter, the promoter being capable of publishing a guidance content for guiding a user to acquire a corresponding object; determining, based on a first feature of the target promoter and second features of the plurality of candidate objects, priority levels of the plurality of candidate objects; and determining, based on the priority levels, a target object for the target promoter from the plurality of candidate objects.
1 . A computer-implemented method for object determination in a content promotion platform, comprising:
recalling, from a set of objects, a plurality of candidate objects for a target promoter, the promoter being capable of publishing a live streaming guidance content for guiding a user to acquire a corresponding object;
determining, based on a first feature of the target promoter and second features of the plurality of candidate objects, priority levels of the plurality of candidate objects, wherein the priority levels are determined by a machine learning priority model trained to predict suitability of each candidate object for promotion by the target promoter based on the first feature and the second feature;
determining, based on the priority levels, a target object for the target promoter from the plurality of candidate objects; and
presenting, via a user interface, a ranked list of information associated with one or more target objects for the target promoter to select for inclusion in the live streaming guidance content.
2 . The method of claim 1 , wherein recalling, from the set of objects, the plurality of candidate objects for the target promoter comprises:
determining, from the set of objects, a plurality groups of candidate objects corresponding to a plurality of recall policies; and
selecting, from the plurality groups of candidate objects, the plurality of candidate objects.
3 . The method of claim 2 , wherein the plurality of recall policies comprises a collaborative recall policy, and determining the plurality groups of candidate objects corresponding to the plurality of recall policies comprises:
determining, based on a historical guidance content published by the target promoter, a historical object associated with the target promoter; and
acquiring, from the set of objects, a group of candidate objects whose differences from the historical object are less than a predetermined threshold,
wherein a difference between the historical object and a specific object in the set of objects is determined based on the number of users that acquired both the historical object and the specific object within a predetermined period of time.
4 . The method of claim 2 , wherein selecting, from the plurality groups of candidate objects, the plurality of candidate objects comprises:
acquiring the plurality of candidate objects by excluding an abnormal object from the plurality groups of candidate objects,
wherein the abnormal object comprises at least one of the following:
an object that is currently unavailable to a user,
an object with an acquisition cost deviating from a predetermined scope,
an object with an evaluation that is below a predetermined level,
an object that has been acquired for a number of times that is below a predetermined threshold, and
an object provided by a provider that has been in violation.
5 . The method of claim 1 , wherein the first feature represents a user attribute of a first group of associated users associated with the target promoter, the second feature represents a user attribute of a second group of associated users associated with the candidate object, the second group of associated users have acquired the candidate object within a predetermined period of time.
6 . The method of claim 1 , wherein the first feature represents first statistical information associated with the target promoter, the second feature represents second statistical information associated with the candidate object, at least one of the first statistical information and the second statistical information is updated in real-time or periodically in response to a user operation.
7 . The method of claim 1 , wherein the first feature represents a first attribute of a historical object acquired by a user through being guided by the target promoter within a first period of time, the second feature represents a second attribute of a historical promoter that published a guidance content for guiding to acquire the candidate object within a second period of time.
8 . The method of claim 1 , wherein determining the target object for the target promoter from the plurality of candidate objects comprises:
adjusting the priority level of at least one of the plurality of candidate objects; and
determining, based on the adjusted priority level, the target object.
9 . The method of claim 8 , wherein adjusting the priority level of at least one of the plurality of candidate objects comprises:
adjusting, based on an expected promotional benefit of the at least one candidate object, the priority level of the at least one candidate object.
10 . The method of claim 8 , wherein adjusting the priority level of at least one of the plurality of candidate objects comprises:
adjusting, based on popularity of the at least one candidate object, the priority level of the at least one candidate object, the popularity indicating a degree to which the at least one candidate object is concerned by a user.
11 . The method of claim 8 , wherein adjusting the priority level of at least one of the plurality of candidate objects comprises:
adjusting, based on evaluation information of the at least one candidate object, the priority level of the at least one candidate object.
12 . The method of claim 8 , wherein adjusting the priority level of at least one of the plurality of candidate objects comprises:
reducing the priority level of the at least one candidate object, if the at least one candidate object is provided to the target promoter within a predetermined period of time and is not selected by the target promoter.
13 . The method of claim 12 , wherein a degree by which the priority level is reduced is determined based on viewing information of the at least one candidate object, the viewing information comprises viewing times or viewing duration.
14 . The method of claim 1 ,
wherein the target object comprises a first object and a second object, the priority level of the first object is higher than the priority level of the second object, and first information associated with the first object has a higher presentation priority than second information associated with the second object.
15 . The method of claim 14 ,
wherein the target object comprises a plurality of target objects, the information of the plurality of target objects is presented as a plurality of information items in an object information list, the plurality of information items are ranked in the object information list according to the priority levels.
16 . The method of claim 15 , further comprising:
determining, from the object information list, a group of information items in consecutive positions, the group of information items corresponding to a first category of objects, and a number of information items contained in the group of information items being greater than a threshold; and
replacing at least one information item in the group of information items with an information item corresponding to a second category of object in the object information list, the first category being different from the second category.
17 . An electronic device, comprising:
a memory and a processor;
wherein the memory is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement a computer-implemented method for object determination in a content promotion platform, the method comprising:
recalling, from a set of objects, a plurality of candidate objects for a target promoter, the promoter being capable of publishing a live streaming guidance content for guiding a user to acquire a corresponding object;
determining, based on a first feature of the target promoter and second features of the plurality of candidate objects, priority levels of the plurality of candidate objects, wherein the priority levels are determined by a machine learning priority model trained to predict suitability of each candidate object for promotion by the target promoter based on the first feature and the second feature;
determining, based on the priority levels, a target object for the target promoter from the plurality of candidate objects; and
presenting, via a user interface, a ranked list of information associated with one or more target objects for the target promoter to select for inclusion in the live streaming guidance content.
18 . The electronic device of claim 17 , wherein recalling, from the set of objects, the plurality of candidate objects for the target promoter comprises:
determining, from the set of objects, a plurality groups of candidate objects corresponding to a plurality of recall policies; and
selecting, from the plurality groups of candidate objects, the plurality of candidate objects.
19 . The electronic device of claim 18 , wherein the plurality of recall policies comprises a collaborative recall policy, and determining the plurality groups of candidate objects corresponding to the plurality of recall policies comprises:
determining, based on a historical guidance content published by the target promoter, a historical object associated with the target promoter; and
acquiring, from the set of objects, a group of candidate objects whose differences from the historical object are less than a predetermined threshold,
wherein a difference between the historical object and a specific object in the set of objects is determined based on the number of users that acquired both the historical object and the specific object within a predetermined period of time.
20 . A non-transitory computer-readable storage medium, storing thereon one or more computer instructions, wherein the one more computer instructions are executed by a processor to implement a computer-implemented method for object determination in a content promotion platform, the method comprising:
recalling, from a set of objects, a plurality of candidate objects for a target promoter, the promoter being capable of publishing a live streaming guidance content for guiding a user to acquire a corresponding object;
determining, based on a first feature of the target promoter and second features of the plurality of candidate objects, priority levels of the plurality of candidate objects, wherein the priority levels are determined by a machine learning priority model trained to predict suitability of each candidate object for promotion by the target promoter based on the first feature and the second feature; determining, based on the priority levels, a target object for the target promoter from the plurality of candidate objects; and
presenting, via a user interface, a ranked list of information associated with one or more target objects for the target promoter to select for inclusion in the live streaming guidance content.