Granted Patent B2

US 12,646,505 · App. 18/059,386 · Granted Jun 2, 2026

Inventors: Zeming Liu (Beijing, CN); Hao Liu (Beijing, CN); Zhengyu Niu (Beijing, CN); Hua Wu (Beijing, CN); Haifeng Wang (Beijing, CN); Hui Xiong (Beijing, CN)

Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.

G10L15/16G10L15/063G10L15/1815G10L15/22G10L2015/0631G10L2015/228

Abstract

Claims (57)

1 . A conversational recommendation method, comprising:

acquiring historical conversation information;

determining a target conversation object to be generated from a conversation target graph based on the historical conversation information, wherein

the conversation target graph comprises an object node,

the object node is configured to represent a conversation object, and

the target conversation object is determined based on the object node; and

generating a target conversation information for recommendation based on the target conversation object,

wherein the determining of the target conversation object to be generated from a conversation target graph based on the historical conversation information comprises:

determining, based on the historical conversation information and a target conversation guiding information, the target conversation object from the conversation target graph, wherein

the historical conversation information is information generated during a conversation, and

the target conversation guiding information is configured to guide the generation of the target conversation object to be generated during the conversation, and the target conversation guiding information comprises:

 a target conversation guiding object being of a same type as the target conversation object, and the target conversation guiding object is used as a target conversation object to be generated at a target time instant during the conversation,

wherein the determining, based on the historical conversation information and the target conversation guiding information, the target conversation object from the conversation target graph comprises:

determining a sequence of historical target conversation objects in the historical conversation information based on the historical conversation information,

wherein the sequence of historical target conversation objects is a sequence of historical target conversation objects in chronological order which are generated at different time instants during the conversation in the historical conversation information;

determining a cost parameter of a candidate object node for the conversation target graph based on the sequence of historical target conversation objects, the target conversation guiding information and the conversation target graph,

wherein a type of the candidate object node matches a type of the sequence of historical target conversation objects; and

determining the target conversation object from the candidate object node based on the cost parameter of the candidate object node.

2 . The method according to claim 1 , wherein the determining of the cost parameter of the candidate object node for the conversation target graph based on the sequence of historical target conversation objects, the target conversation guiding information and the conversation target graph comprises:

determining a transition matrix for the candidate object node based on the conversation target graph;

determining a first initial cost parameter of the candidate object node based on the sequence of historical target conversation objects and the transition matrix for the candidate object node;

determining a second initial cost parameter of the candidate object node based on the sequence of historical target conversation objects, the target conversation guiding information and the transition matrix for the candidate object node; and

determining the cost parameter of the candidate object node based on the first initial cost parameter and the second initial cost parameter.

3 . The method according to claim 2 , wherein the determining of the target conversation object from the candidate object node based on the cost parameter of the candidate object node comprises:

determining a probability of switching the target conversation object node based on the cost parameter of the candidate object node;

determining the target conversation object from the candidate object node based on the cost parameter of the candidate object node, in response to determining that the probability of switching is greater than or equal to a predetermined switching threshold; and

determining the target conversation object from the sequence of historical target conversation objects, in response to determining that the probability of switching is smaller than the predetermined switching threshold.

4 . The method according to claim 2 , wherein the determining of the target conversation object from the candidate object node based on the cost parameter of the candidate object node comprises:

determining a probability of generating the target conversation object node based on the cost parameter of the candidate object node; and

determining the target conversation object from the candidate object node based on the cost parameter of the candidate object node, in response to determining that the probability of generating is greater than or equal to a predetermined generation threshold.

5 . The method according to claim 2 , wherein the conversation target graph comprises:

a heterogeneous hierarchical conversation target graph, the heterogeneous hierarchical conversation target graph comprising:

a plurality of conversation target sub-graphs having a hierarchical relationship with each other, each conversation target sub-graph among the plurality of conversation target sub-graphs comprising:

a plurality of object nodes of a same type, wherein

a connection edge between the plurality of object nodes of the same type is configured to represent a homogeneous association relationship,

the type of object nodes of one of two adjacent conversation target sub-graphs is different from the type of object nodes of the other of the two adjacent conversation target sub-graphs, and

a connection edge between a plurality of objects nodes in the conversation target sub-graph at a current level and a plurality of objects nodes in the conversation target sub-graph at a higher level is configured to represent a heterogeneous association relationship.

6 . The method according to claim 5 ,

wherein the target conversation object comprises a plurality of target conversation objects having levels; and

wherein the determining of the transition matrix for the candidate object node based on the conversation target graph comprises:

determining a candidate object node in the conversation target sub-graph at the current level based on the heterogeneous association relationship in the heterogeneous hierarchical conversation target graph and a determined target object node in the conversation target sub-graph at the higher level, wherein

the target object node in the conversation target sub-graph at the higher level corresponds to a target conversation object at the higher level, and

the candidate object node in the conversation target sub-graph at the current level corresponds to a candidate conversation object at the current level; and

determining a transition matrix for the candidate object node at the current level based on the candidate object node for the conversation target sub-graph at the current level, and taking the transition matrix for the candidate object node at the current level as the transition matrix for the candidate object node.

7 . The method according to claim 1 , wherein the generating of the target conversation information based on the target conversation object comprises:

generating the target conversation information based on the target conversation object, the historical conversation information and the sequence of historical target conversation objects.

8 . The method according to claim 1 , wherein a type of the target conversation object node comprises at least one of a conversation type of recommendation, a conversation topic, or a topic attribute.

9 . An electronic device, 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, when executed by the at least one processor, cause the at least one processor to implement the conversational recommendation method of claim 1 .

10 . The electronic device according to claim 9 , wherein the at least one processor is further configured to:

determine a transition matrix for the candidate object node based on the conversation target graph;

determine a first initial cost parameter of the candidate object node based on the sequence of historical target conversation objects and the transition matrix for the candidate object node;

determine a second initial cost parameter of the candidate object node based on the sequence of historical target conversation objects, the target conversation guiding information and the transition matrix for the candidate object node; and

determine the cost parameter of the candidate object node based on the first initial cost parameter and the second initial cost parameter.

11 . A non-transitory computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions are configured to cause a computer to implement the conversational recommendation method of claim 1 .

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (12)