WO2018000208A1

WO2018000208A1 - Method and system for searching for and positioning skill packet, and robot

Info

Publication number: WO2018000208A1
Application number: PCT/CN2016/087527
Authority: WO
Inventors: 王昊奋; 邱楠; 杨新宇
Original assignee: 深圳狗尾草智能科技有限公司
Priority date: 2016-06-28
Filing date: 2016-06-28
Publication date: 2018-01-04
Also published as: CN106663160A; CN106663160B

Abstract

A method for searching for and positioning a skill packet, comprising: obtaining user voice information and a user portrait (S101); recognizing a user intent according to the obtained voice information and user portrait (S102); obtaining weights of skill packets according to the frequencies at which the user uses the skill packets (S103); and obtaining the skill packet having the maximum weight value according to the user intent and the weights of the skill packets (S104). According to the method, after the user intent is recognized according to the user voice information and the user portrait, the skill packet having the maximum weight value can be determined in combination with the frequencies at which the user uses skill packets, and then a skill packet having the function closest to the function that the user desires to enable can be found, so that the system can enable the function of the skill packet more quickly and accurately. The method is based on voice information input and user portrait input, so that the intent can be recognized more accurately, and positioning and searching of the skill packet can be more user-friendly and precise. Moreover, by means of the weights of use frequencies, functions commonly used by the user can be found more easily, and the system response time is shortened.

Description

Method and system for searching and locating a skill package

Technical field

The invention relates to the field of robot interaction technology, in particular to a method and system for searching and locating a skill package and a robot.

Background technique

As an interactive tool with humans, robots are used more and more. For example, some elderly people and children can interact with robots, including dialogue and entertainment. Robots generally have many clock functions. These functions are called skill packs in robot systems. Generally, a skill pack corresponds to a function of the robot. For example, singing is a skill pack, and playing music is also a skill pack. The robot usually knows the skill package that the human wants the robot to perform by recognizing the human voice or the like, and the robot searches for the corresponding skill package according to the voice and then executes.

However, the skills management and search efficiency of the existing robots are low, which causes the robot to react slowly during the interaction process. Usually, the robot will respond after receiving the command for a few seconds, which greatly reduces the comfort of the user. And good feelings.

Therefore, how to provide a skill packet search method, system and robot with faster response speed and improve the human-computer interaction experience become a technical problem that needs to be solved.

Summary of the invention

The object of the present invention is to provide a skill packet search method, system and robot with faster response speed, and improve the human-computer interaction experience.

The object of the present invention is achieved by the following technical solutions:

A method for searching and locating a skill package, including:

Obtaining the user's voice information and user portraits;

Identifying user intent based on acquired voice information and user portraits;

The skill package weight is obtained according to the frequency of the user using the skill package;

A skill package having the highest weight value is obtained according to the user intention and the skill package weight.

Preferably, after the step of obtaining the skill package with the highest weight value according to the user intention and the skill package weight, the method further includes:

Obtain the multimodal parameters of the user;

Determining, according to the multimodal parameter, whether the user has the right to access the skill package with the highest weight value, and if so, the skill package port registration information is located to the skill package.

Preferably, the method further comprises: after the skill pack port registration information searches for the skill package, sending the skill package to the interaction module, and performing the function of the skill package.

Preferably, the method further includes: if the user does not have the right to access the skill package with the highest weight value, prompting the user whether to open the skill package, and if the user obtains the instruction to open the skill package, the user has access to the skill package. The permissions of the skills package.

Preferably, the multi-modal parameter includes at least one of a scene parameter, an image parameter, a video parameter, a face parameter, a pupil iris parameter, a light sensing parameter, and a fingerprint parameter.

A skill pack search and location system, including:

An acquisition module, configured to acquire voice information and a user image of the user;

An intention identification module, configured to identify a user intention according to the acquired voice information and the user portrait;

The weight module is configured to obtain the skill package weight according to the frequency of the user using the skill package;

The processing module is configured to obtain the skill package with the highest weight value according to the user intent and the skill package weight.

Preferably, the system further comprises:

a charging module for acquiring a multimodal parameter of the user;

The permission determining module is configured to determine, according to the multimodal parameter, whether the user has the right to access the skill package with the highest weight value, and if so, search for the skill package in the skill package port registration information.

Preferably, the system further comprises: a sending execution module, configured to send the skill package to the interaction module after the skill package port registration information searches for the skill package, and execute the function of the skill package.

Preferably, the authority determining module is further configured to: if the user does not have the right to access the skill package with the highest weight value, prompt the user whether to open the skill package, and if the user obtains the instruction to open the skill package, the user Have access to the skills package.

Preferably, the multimodal parameter includes at least one of an expression parameter, a scene parameter, an image parameter, a video parameter, a face parameter, a pupil iris parameter, a light sensitivity parameter, and a fingerprint parameter.

A robot comprising a search and location system for a skill package as described above.

The invention discloses a robot comprising a search and positioning system for a skill package as described above.

Compared with the prior art, the present invention has the following advantages: the method of the present invention includes: acquiring voice information of a user and a user portrait; identifying user intention according to the acquired voice information and user portrait; acquiring skill according to frequency of using the skill pack by the user The weight of the package; the skill package with the highest weight value is obtained according to the user intention and the skill package weight. After the user's voice information and the user's portrait are used to identify the user's intention, the skill pack with the highest weight value is determined by combining the frequency of the skill pack, and then the skill pack closest to the function that the user wants to enable can be found. Therefore, the system can start the function of the skill package more quickly and accurately. The method of the invention adopts the input based on the voice information and the input of the user portrait, so that the intention recognition is more accurate, and the positioning search of the skill package is more humanized and more precise. Moreover, by using the weight of the frequency, it is easier to search for functions commonly used by the user, and the response time of the system is reduced.

DRAWINGS

1 is a flowchart of a method for searching and locating a skill package according to a first mode of the first embodiment of the present invention;

2 is a flowchart of a method for searching and locating a skill package according to a second mode of the first embodiment of the present invention;

3 is a schematic diagram of a search and location system for a skill package according to a second embodiment of the present invention.

detailed description

Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. The order of the operations can be rearranged. Processing may be terminated when its operation is completed, but may also have additional steps not included in the figures. Processing can correspond to methods, functions, procedures, subroutines, subroutines, and the like.

Computer devices include user devices and network devices. The user equipment or the client includes but is not limited to a computer, a smart phone, a PDA, etc.; the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing-based computer or network server. cloud. The computer device can operate alone to carry out the invention, and can also access the network and implement the invention through interoperation with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

The terms "first," "second," and the like may be used herein to describe the various elements, but the elements should not be limited by these terms, and the terms are used only to distinguish one element from another. The term "and/or" as used herein includes one or more of Any and all combinations of associated items listed. When a unit is referred to as being "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or an intermediate unit can be present.

The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It is also to be understood that the terms "comprising" and """ Other features, integers, steps, operations, units, components, and/or combinations thereof.

The invention will now be further described with reference to the drawings and preferred embodiments.

Embodiment 1

As shown in FIG. 1 , a search and location method for a skill package is disclosed in the embodiment, including:

S101. Acquire user's voice information 300 and user portrait 400;

S102. Identify the user intention according to the acquired voice information and the user portrait.

S103. Acquire a skill package weight according to the frequency 302 of the user using the skill package.

S104. Obtain a skill package with the highest weight value according to the user intention and the skill package weight.

The method of the present invention includes: S101 acquiring the voice information of the user and the user portrait; S102 identifying the user intention according to the acquired voice information and the user portrait; S103 acquiring the skill package weight according to the frequency of the user using the skill package; S104 according to the user intention And skill pack weights get the skill pack with the highest weight value. After the user's voice information and the user's portrait are used to identify the user's intention, the skill pack with the highest weight value is determined by combining the frequency of the skill pack, and then the skill pack closest to the function that the user wants to enable can be found. Therefore, the system can start the function of the skill package more quickly and accurately. The method of the invention adopts the input based on the voice information and the input of the user portrait, so that the intention recognition is more accurate, and the positioning search of the skill package is more humanized and more precise. Moreover, by using the weight of the frequency, it is easier to search for functions commonly used by the user, and the response time of the system is reduced.

The invention adopts a new skill package method to manage the function modules in the robot, etc., and facilitates the robot to realize the function startup faster and more conveniently, and improves the efficiency of the interaction between the robot and the user and the user's good feeling.

The user portrait is a virtual representation of the real user, a target user model built on top of a series of real data. Through user research to understand users, according to their differences in goals, behaviors and opinions, they are divided into different types, and then each type extracts typical features, gives names, The description of the photo, some demographic elements, scenes, etc., forms a prototype of the character. User portraits may include name, photo, age, family status, income, work, user scenarios or activities, computer skills or knowledge, goals or motivations, preferences, attitudes to life, and the like. In this way, the user's voice and the user's portrait can be comprehensively judged to more accurately understand the user's intention.

According to one of the examples, after the step of obtaining the skill package having the highest weight value according to the user intent and the skill package weight, the method further includes:

Obtain the multimodal parameters of the user;

In this way, after the name of the skill package is determined, the multi-modal parameters of the user are obtained, and then the obtained multi-modal parameters are compared with the parameters of the pre-stored user. If the data is consistent or consistent, the user is determined. Have the right to access the skill package, and then determine the specific location of the skill package in the system, so as to specifically locate the skill package and find the skill package.

In this embodiment, the multi-modal parameter includes at least one of a scene parameter, an image parameter, a video parameter, a face parameter, a pupil iris parameter, a light sensing parameter, and a fingerprint parameter. The acquisition of multimodal parameters can be obtained by a camera, or other such as a light sensor, a fingerprint recognition module, or the like. In the embodiment, the multi-modal parameters generally refer to other parameters than the voice, and the multi-modal parameters are used to verify the identity and authority of the user, and the speed is fast, the efficiency is high, and the accuracy is also very high.

For example, if the user's voice information is "moving times", then the robot can determine that the user's intention should be the closest to playing music. Then, after determining the user's intention, the skill package with the highest weight value can be determined in combination with the weight of the frequency of the user using the skill package. For example, if a skill package commonly used by a user is to play music, then the robot will determine that the skill package for playing music is the skill package with the highest weight value. If the skill package commonly used by the user is a robot movement, the robot determines that the skill package of the robot movement is the skill package with the highest weight value. Then, obtaining multi-modal parameters of the user, such as image information or face information, and comparing the acquired image information and face information with the information of the user pre-existing in the cloud or the local user of the robot, and if they are consistent, it can be determined. The user has the right to access the skill pack for playing music or the skill pack for the azimuth robot movement, thereby continuing to locate and query the position of the skill package.

In this embodiment, the method further includes: after the skill pack port registration information searches for the skill package, sending the skill package to the interaction module, and performing the function of the skill package.

In this way, after the corresponding skill package is found, the skill package is executed, thereby allowing the machine The person reflects the function corresponding to the skill package.

According to one example, the method further includes: if the user does not have the right to access the skill package with the highest weight value, prompting the user whether to open the skill package, and if the user obtains the instruction to open the skill package, the user has Access to the skills package.

In this way, when the user does not have the right to access the skill package with the highest weight value, the user is prompted to open the function to obtain the user's will, thereby selecting whether to open the permission according to the user's will, and if the user is willing to open the skill package, Then the user has the right to access the skill package, so that the user can access the skill package and perform the function of the skill package.

As shown in FIG. 2, in a more detailed description in this embodiment, a method for searching and locating a skill package disclosed includes:

S101. Acquire user's voice information 300 and user portrait 400;

S103. Acquire a skill package weight according to the frequency 500 of the user using the skill package.

S105. Acquire a multimodal parameter of the user.

S106. Determine, according to the multimodal parameter, whether the user has the right to access the skill package with the highest weight value, and if so, locate the skill package in the skill package port registration information.

S107. Send the skill package to the interaction module, and execute the function of the skill package.

Embodiment 2

As shown in FIG. 2, in this embodiment, a search and location system for a skill package is disclosed, including:

The obtaining module 201 is configured to acquire the voice information of the user and the user portrait, wherein the voice information can be obtained by the voice module 301, and the user portrait can be obtained by the user portrait module 401;

The intent identification module 202 is configured to identify the user's intention according to the acquired voice information and the user image;

The weight module 203 is configured to obtain the skill package weight according to the frequency of the user using the skill package, wherein the frequency of the user using the skill package can be obtained by the skill packet frequency module 501;

The processing module 204 is configured to obtain the skill package with the highest weight value according to the user intent and the skill package weight.

After the user's voice information and the user's portrait are used to identify the user's intention, the skill pack with the highest weight value is determined by combining the frequency of the skill pack, and then the skill pack closest to the function that the user wants to enable can be found. So that the system can start the skill faster and more accurately. The function of the package, the method of the invention adopts the input based on the voice information and the input of the user image, so that the intention recognition is more accurate, the positioning search of the skill package is more humanized, more precise, and the use of the frequency weight makes the search easier. The functions commonly used by users reduce the response time of the system.

According to one of the examples, the system further comprises:

a charging module for acquiring a multi-modal parameter of the user, and the multi-modal parameter can be obtained by the multi-modal module;

In this embodiment, the multi-modal parameter includes at least one of a scene parameter, an image parameter, a video parameter, a face parameter, a pupil iris parameter, a light sensing parameter, and a fingerprint parameter. The acquisition of multimodal parameters can be obtained by a camera, or other such as a light sensor, a fingerprint recognition module, or the like. The multimodal parameters in this embodiment generally refer to other parameters than speech. Verification of user identities and permissions using multimodal parameters is fast, efficient, and very accurate.

For example, the user's voice information is “moving times”, and then the multi-modal parameter is recognized as an image parameter indicating that the user is performing a dance, or the scene parameter indicates that the user is in a wide environment, then the robot can Determining the user's intent should be the closest to playing music. Then, after determining the user's intention, the skill package with the highest weight value can be determined in combination with the weight of the frequency of the user using the skill package. Then, obtaining multi-modal parameters of the user, such as image information or face information, and comparing the acquired image information and face information with the information of the user pre-existing in the cloud or the local user of the robot, and if they are consistent, it can be determined. The user has the right to access the skill pack for playing music or the skill pack for the azimuth robot movement, thereby continuing to locate and query the position of the skill package.

In this embodiment, the system further includes: a sending execution module, configured to send the skill package to the interaction module after the skill package port registration information searches for the skill package, and execute the function of the skill package.

In this way, after the corresponding skill package is found, the skill package is executed, so that the robot reflects the function corresponding to the skill package.

According to an example, the permission determination module is further configured to: if the user does not have the right to access the skill package with the highest weight value, prompt the user whether to open the skill package, and if the user obtains the instruction to open the skill package, This user has access to the skills package.

In addition, in this embodiment, a robot is further disclosed, comprising a search and positioning system of a skill package according to any of the above.

The above is a further detailed description of the present invention in connection with the specific preferred embodiments, and the specific embodiments of the present invention are not limited to the description. It will be apparent to those skilled in the art that the present invention may be made without departing from the spirit and scope of the invention.

Claims

A method for searching and locating a skill package, comprising:

Obtaining the user's voice information and user portraits;

Identifying user intent based on acquired voice information and user portraits;

The skill package weight is obtained according to the frequency of the user using the skill package;

A skill package having the highest weight value is obtained according to the user intention and the skill package weight.
The search and location method according to claim 1, further comprising: after the step of obtaining the skill package having the highest weight value according to the user intention and the skill package weight, further comprising:

Obtain the multimodal parameters of the user;

Determining, according to the multimodal parameter, whether the user has the right to access the skill package with the highest weight value, and if so, the skill package port registration information is located to the skill package.
The search and location method according to claim 2, wherein the method further comprises: after the skill pack port registration information searches for the skill package, sending the skill package to the interaction module, and executing the skill package Features.
The method for searching and locating according to claim 2, wherein the method further comprises: if the user does not have the right to access the skill package with the highest weight value, prompting the user whether to open the skill package, if the user is obtained When the instruction of the skill package is opened, the user has the right to access the skill package.
The search and positioning method according to claim 2, wherein the multimodal parameter comprises at least a scene parameter, an image parameter, a video parameter, a face parameter, a pupil iris parameter, a light sensing parameter, and a fingerprint parameter. One or several.
A skill pack search and positioning system, characterized in that it comprises:

An acquisition module, configured to acquire voice information and a user image of the user;

An intention identification module, configured to identify a user intention according to the acquired voice information and the user portrait;

The weight module is configured to obtain the skill package weight according to the frequency of the user using the skill package;

The processing module is configured to obtain the skill package with the highest weight value according to the user intent and the skill package weight.
The search and location system of claim 6 wherein the system further comprises:

a charging module for acquiring a multimodal parameter of the user;

a permission determination module, configured to determine, according to the multimodal parameter, whether the user has the right to access the skill package with the highest weight value, and if so, search for the skill in the skill package port registration information. package.
The search and location system according to claim 7, wherein the system further comprises: a sending execution module, configured to send the skill package to the interaction module after the skill pack port registration information searches for the skill package, And perform the function of the skill package.
The search and location system according to claim 7, wherein the authority determining module is further configured to: if the user does not have the right to access the skill package with the highest weight value, prompt the user whether to open the skill package, if When the user is given an instruction to open the skill package, the user has the right to access the skill package.
The search and positioning system according to claim 7, wherein the multimodal parameter comprises at least a scene parameter, an image parameter, a video parameter, a face parameter, a pupil iris parameter, a light sensing parameter, and a fingerprint parameter. One or more of them.
A robot characterized by comprising a search and positioning system of a skill package according to any one of claims 6 to 10.