JP-7855737-B2 - Parameter acquisition system

JP7855737B2JP 7855737 B2JP7855737 B2JP 7855737B2JP-7855737-B2

Inventors

島田颯己
勝丸徳浩
辰巳守祐

Assignees

株式会社ＮＴＴドコモ

Dates

Publication Date: 20260508
Application Date: 20231027
Priority Date: 20230131

Claims (7)

A parameter acquisition system that acquires parameters to be set for a character that operates in a virtual space, A topic acquisition unit acquires at least one topic whose proximity to a user embedding representation, which is an embedding representation of a user as a real number vector, and a topic embedding representation, which is an embedding representation of a topic as a real number vector, satisfies a predetermined condition. A hobby acquisition unit acquires hobbies corresponding to topics acquired by the topic acquisition unit, based on correspondence information that represents the relationship between topics and hobbies. A setting information output unit outputs the hobbies acquired by the hobby acquisition unit as hobby information for setting as parameters of the character corresponding to the user, A parameter acquisition system equipped with the following features.
The hobby acquisition unit refers to a thesaurus as correspondence information that defines the relationships between multiple words, including hobby terms representing hobbies and topic terms representing topics, and acquires hobbies corresponding to hobby terms associated with topic terms corresponding to topics acquired by the topic acquisition unit. The parameter acquisition system according to claim 1.
The hobby acquisition unit refers to a given hobby list containing multiple hobby terms that represent hobbies, calculates the similarity between each topic term representing a topic acquired by the topic acquisition unit and a hobby term included in the hobby list as correspondence information, and acquires hobbies corresponding to hobby terms whose calculated similarity is equal to or greater than a given threshold. The parameter acquisition system according to claim 1.
The hobby acquisition unit calculates the similarity between the topic word and the hobby word using Word2Vec. The parameter acquisition system according to claim 3.
The system further includes an attribute acquisition unit that references a given attribute list that associates hobbies with a person's attribute information, and acquires attribute information associated with hobbies acquired by the hobby acquisition unit, The setting information output unit outputs the attribute information obtained from the attribute information as information for setting the parameters of the character corresponding to the user. The parameter acquisition system according to claim 1.
The aforementioned topic acquisition unit, The user embedding representation of the user and the topic embedding representation of the topic are obtained in order of proximity, or The user embedding representation of the user and the topic embedding representation of the topic are to be acquired if the distance between them is less than or equal to a predetermined amount. The parameter acquisition system according to claim 1.
The system further comprises an embedded expression input unit that acquires the user embedded expression and the topic embedded expression from an embedded expression generation device that generates at least user and topic embedded expressions, The embedded representation generation device is A language understanding unit that learns a language model composed of an encoder-decoder model including an embedding unit and a decoding unit, The aforementioned embedding unit outputs an embedding representation that shows the characteristics of the input text. The decoding unit decodes the embedded representation which includes at least the output from the embedding unit. By inputting a first user utterance text representing the content of one user's utterance from among the utterance texts representing the content of the user's utterance into the embedding unit, a user utterance embedding representation output from the embedding unit is obtained; by inputting a composite embedding representation obtained by combining the user utterance embedding representation and the user embedding representation of the one user into the decoding unit, a decoded text output from the decoding unit is obtained; and machine learning is performed to adjust the language model and the user embedding representation so that the error between the second user utterance text following the first user utterance text and the decoded text in the utterance text is reduced. The user embedding representation is an initial user embedding representation before learning or a user embedding representation during the learning process, and is a language comprehension unit. A topic extraction unit extracts topic words, which are words or phrases that represent the topic of the user's utterance, from the aforementioned utterance text. An embedding expression acquisition unit that inputs the aforementioned topic word into the embedding unit which has already learned the topic word and acquires the topic embedding expression output from the embedding unit, A relationship extraction unit generates a relationship graph based on the user's utterance history and action history, in which at least the user and the topic are nodes, the history of dialogue between users are edges connecting the users, and the history of the user uttering the topic word is an edge connecting the user and the topic. A relational learning unit obtains a learned embedding representation for each node by training a graph neural network that uses the learned user embedding representation and the topic embedding representation, respectively, as features of the user and topic nodes in the relational graph. The system includes an embedding representation output unit that outputs the learned embedding representation of each node to the embedding representation input unit. The parameter acquisition system according to claim 1.

Description

This invention relates to a parameter acquisition system. For example, in a virtual space known as the metaverse, characters communicate with each other by engaging in activities such as roaming and interacting. Furthermore, regarding the behavior of avatars in virtual spaces, there are known technologies that allow avatars to learn from user input and then act autonomously to a certain extent based on that learning (see, for example, Patent Document 1). Japanese Patent Publication No. 2010-101950 This is a block diagram showing the functional configuration of the parameter acquisition device of this embodiment.This is a hard block diagram of the parameter acquisition device and the embedded representation generation device.This diagram provides a schematic explanation of the process for obtaining embedded representations.This figure shows an example of a topic obtained based on the distance between the user-embedded representation and the topic-embedded representation.This figure shows an example of a given list of hobbies, including hobby-related terms.This figure shows an example of correspondence information that defines the relationship between hobbies and topics.As an example of correspondence information, this figure shows an example of a thesaurus that is hierarchically structured, including topical terms and hobby-related terms.As an example of correspondence information, the figure shows an example of calculating the similarity between topic words and hobby-related words.This diagram schematically illustrates the output of hobby information for setting as character parameters.This figure shows an example of an attribute list that associates hobbies with attribute information.This diagram schematically illustrates the output of hobby information and attribute information for setting as character parameters.This is a flowchart showing the processing steps for parameter acquisition in a parameter acquisition device.This diagram shows the configuration of the parameter acquisition program.This is a block diagram showing the functional configuration of the embedded representation generation device of this embodiment.This diagram provides a schematic explanation of the process for acquiring spoken text.This figure shows an example of the structure of a language model and the machine learning processing of the language model.This figure shows an example of the process of obtaining an embedded representation using the embedded part of a pre-trained language model.This figure shows an example of edge acquisition for generating a relational graph.This figure shows an example of a relationship graph and an example of extracting positive and negative examples from the relationship graph.This figure shows an example of an embedding representation of each entity obtained by training a graph neural network that constitutes a relational graph.This flowchart shows the processing details of the embedded representation generation method in the embedded representation generation device.This flowchart shows the processing steps involved in machine learning for language models.This diagram shows the configuration of the embedded representation generation program. Embodiments of the parameter acquisition system according to the present invention will be described with reference to the drawings. Where possible, the same parts are denoted by the same reference numerals, and redundant descriptions are omitted. Figure 1 shows the functional configuration of the parameter acquisition system according to this embodiment. The parameter acquisition system 1 of this embodiment is a system for acquiring parameters to be set for a character that operates in a virtual space, and is configured, for example, by a parameter acquisition device 30. The parameter acquisition system 1 may further include an embedded representation generation device 10. The parameter acquisition device 30 is a device that acquires parameters to be set for a character that operates in a virtual space. Functionally, as shown in Figure 1, it comprises an embedded expression input unit 31, a topic acquisition unit 32, a hobby acquisition unit 33, an attribute acquisition unit 34, and a setting information output unit 35. These functional units 31 to 35 may be configured in a single device as illustrated in Figure 1, or they may be distributed across multiple devices. The embedded expression generation device 10 is a device that generates embedded expressions of at least the user and the topic. In the example shown in Figure 1, the embedded expression generation device 10 is shown as a separate device from the parameter acquisition device 30, but it may be configured integrally with the parameter acquisition device 30. The functions of the embedded expression generation device 10 will be described later. The block diagram shown in Figure 1 represents functional units. These functional blocks (components) are realized by any combination of at least one of hardwa