WO2019148491A1 - Human-computer interaction method and device, robot, and computer readable storage medium - Google Patents

Abstract

The present application relates to the technical field of robots and discloses a human-computer interaction method and device, a robot, and a computer readable storage medium. In the present application, the human-computer interaction method is applied to a robot, and comprises: extracting biometric information of at least one recognized object, the biometric information comprising physiological feature information and/or behavior feature information; determining, from the at least one object and according to the biometric information, a target interaction object requiring interaction; and controlling a robot to execute a response matched to the target interaction object. The human-computer interaction method enables a robot to respond only to an object requiring interaction, thereby avoiding false response operations, and greatly improving the user experience.

Description

Human-computer interaction method, device, robot and computer readable storage medium Technical field

The present application relates to the field of robot technology, and in particular, to a human-computer interaction method, device, robot, and computer readable storage medium.

Background technique

Human-computer interaction or Human-Machine Interaction (HCI or HMI) is a study of the interaction between systems and users. The system can be a wide variety of machines or computerized systems and software. Taking interactive robots placed in public places such as bank business halls, large shopping malls, airports, etc. as an example, the robot can respond to the computer system and provide services for users, such as actively initiating greetings, answering user questions, guiding users to handle business, etc. .

However, the inventors have found that at least the following problems exist in the prior art: since the traffic volume in a public place is large and there are various kinds of sound disturbances, such as broadcasted music and music, the existing robot cannot be shielded at all. These interference factors will continue to respond, which not only seriously occupies the processing resources of the robot, but also makes the robot unable to provide effective services for users who really need help, seriously affecting the user experience.

Summary of the invention

One technical problem to be solved by some embodiments of the present application is to provide a human-computer interaction method, apparatus, robot, and computer readable storage medium to solve the above technical problems.

An embodiment of the present application provides a human-computer interaction method, the human-computer interaction method being applied to a robot, comprising: extracting biometric information of the identified at least one object; wherein the biometric information includes physiological characteristic information and/or Behavior characteristic information; determining, according to the biometric information, a target interaction object that needs to interact from at least one object; and controlling the robot to make a response that matches the target interaction object.

An embodiment of the present application provides a human-machine interaction device, which is applied to a robot, including: an extraction module, a determination module, and a control module; and an extraction module, configured to extract biometric characteristics of the identified at least one object Information; wherein the biometric information includes physiological characteristic information and/or behavior characteristic information; and a determining module, configured to determine, from the at least one object, a target interactive object that needs to interact according to the biometric information; and a control module, configured to control the robot to make The response that matches the target interaction object.

An embodiment of the present application provides a robot including 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, the instructions being at least one The processor executes to enable the at least one processor to perform the human-computer interaction method involved in any of the method embodiments of the present application.

An embodiment of the present application provides a computer readable storage medium storing computer instructions for causing a computer to execute the human-computer interaction method involved in any of the method embodiments of the present application.

Compared with the prior art, the robot detects the object by extracting the biometric information of the recognized object, and determines the object that really needs to be interacted according to the biometric information, and determines that the interaction is really needed. The object is only made to respond to the object. Through this human-computer interaction mode, the robot can respond only to the objects that need to interact, thereby effectively avoiding the false response operation and greatly improving the user experience.

DRAWINGS

The one or more embodiments are exemplified by the accompanying drawings in the accompanying drawings, and FIG. The figures in the drawings do not constitute a scale limitation unless otherwise stated.

1 is a flowchart of a human-computer interaction method in a first embodiment of the present application;

2 is a schematic diagram of a robot determining a target interaction object in the first embodiment of the present application;

3 is a flowchart of a human-computer interaction method in a second embodiment of the present application;

4 is a schematic diagram of a robot determining a target interaction object in a second embodiment of the present application;

5 is a flowchart of a human-computer interaction method in a third embodiment of the present application;

6 is a block diagram showing a human-machine interaction apparatus in a fourth embodiment of the present application;

Fig. 7 is a block diagram showing the robot in the fifth embodiment of the present application.

Detailed ways

In order to make the objects, the technical solutions and the advantages of the present application more clear, some embodiments of the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The first embodiment of the present application relates to a human-computer interaction method, and the human-computer interaction method is applied to a robot. The specific process is shown in FIG. 1 .

It should be noted that the robot referred to in this embodiment is a common name for automatic control of a machine, including all machines that simulate human behavior or thoughts and simulate other creatures (such as robot dogs, robot cats, etc.).

In step 101, biometric information of the identified at least one object is extracted.

Specifically, in the embodiment, the operation of extracting the biometric information of the identified at least one object may be, at least, detecting at least one within a preset range (eg, 5 meters) centered on the position of the robot. Triggered when the object is close, this detection method enables the robot to perceive objects within 360 degrees of its position.

It is worth mentioning that, in this embodiment, the robot determines the operation of identifying the object, specifically by using a proximity sensor installed on the robot, for example, after placing the robot in a public place and starting it, the proximity sensor is It is possible to perceive whether there is an object approaching within 5 meters of the center of the robot. If the movement information or presence information of the object is sensed, the sensed information is converted into an electrical signal, and the robot's processor controls the biological characteristics of the robot. The collecting device extracts biometric information of the identified at least one object.

In order to facilitate the understanding of the specific implementation of extracting biometric information, several specific extraction methods are listed below, as follows:

Method 1: Control the robot to perform image acquisition, and extract biometric features of at least one object from the collected images to obtain biometric information of at least one object.

Method 2: Control the robot to perform voice collection, and extract biometric features of at least one object from the collected voices to obtain biometric information of at least one object.

Manner 3: controlling the robot to perform image acquisition and voice collection, and extracting biometric features of at least one object from the acquired image, obtaining biometric information of at least one object, and extracting biometric characteristics of at least one object from the collected speech. Obtaining biometric information of at least one object.

In addition, when the biometric information is extracted by using the third method, the biometric information of the object obtained from the image and the biometric information of the object obtained from the speech may be further analyzed to determine the biometric information belonging to the same object. In the operation of subsequently determining the target interaction object, the biometric information of the object in the image and the biometric information from the object in the speech can be comprehensively analyzed according to the same object, thereby improving the accuracy of determining the target interaction object.

It should be noted that, in this embodiment, the extracted biometric information specifically includes physiological characteristic information and/or behavior characteristic information.

The physiological characteristic information may specifically be any one or any combination of the facial information, the eye information, and the voiceprint information (specifically, information indicating who the sound is from the voice), and the behavior characteristic information is specific. It may be any one or any combination of the displacement information of the recognized object, the related information such as the voice content information (specifically, the information capable of identifying the content) in the utterance.

For example, when extracting biometrics of at least one object from the acquired image, physiological feature information such as facial information and/or eye information of the subject, and behavior characteristic information such as displacement information may be extracted.

For example, when the biometrics of at least one object are extracted from the collected speech, physiological characteristic information such as voiceprint information of the object, and behavior characteristic information such as voice content information may be extracted.

In addition, the above-mentioned control robot performs image acquisition, specifically, an image acquisition device that controls the robot itself, such as a camera for image acquisition, or an external image acquisition device that is connected to the robot, such as a monitoring device installed in a shopping mall, or Two ways to cooperate with the acquisition.

Similarly, the above control robot performs voice collection, and may also be acquired by using the robot's own voice acquisition device and/or an external voice collection device connected thereto.

In addition, it is worth mentioning that, after determining the object to be recognized, before controlling the robot to perform image acquisition and/or voice collection, the robot can be controlled to rotate to the direction of the object to be recognized according to the direction information of the object, and then The robot is controlled to perform image and/or voice acquisition operations, thereby ensuring that the captured image and the voice have recognized objects, so that the biometric information of the subsequently extracted object is more complete, thereby ensuring that the final target interaction object is more accurate. .

In addition, the collected image in the embodiment is not limited to image information such as a photo, and may be image information in the video, which is not limited herein.

It should be noted that the above is only an example. In practical applications, those skilled in the art may reasonably set according to the technical means they master, as long as they can determine from the identified at least one object according to the extracted biometric information. The target interaction object can be.

In step 102, a target interaction object that needs to be interacted is determined from at least one object according to the biometric information.

In this embodiment, the operation of the target interaction object that needs to be interacted is determined from the at least one object according to the biometric information, which may be implemented by:

First, according to the biometric information, at least one object is determined to be an object to be interacted. For convenience of description, the present embodiment specifically describes the object to be interacted with.

Specifically, because in practical applications, objects close to the robot are not necessarily objects that need to be interacted, such as small animals or other terminal devices that are close to the robot, not human. Therefore, the non-human object can be excluded by comparing the extracted biometric information with the sample information of the pre-stored person, thereby ensuring the accuracy of the subsequent operation.

In addition, when it is determined that there are a plurality of people in the identified object, it is further possible to determine each person's biometrics, such as the direction of displacement (whether it is toward robot motion, etc.), eye information (whether or not the robot is watching, etc.) Are you looking for help to identify those who really seek help as objects to be interacted with?

Then, from the determined objects to be interacted, select a matching interactive object as the target interactive object, that is, the object selected by the robot for human-computer interaction.

Specifically, if the number of the objects to be interacted is equal to 1, the object to be interacted is directly determined as the target interaction object. If the number of the objects to be interacted is greater than 1, the condition is set according to the preset priority, and each of the objects to be interacted The object sets the priority, and then determines that the object with the highest priority is the target interaction object.

For ease of understanding, the following is specifically described in conjunction with FIG. 2.

As shown in Fig. 2, three objects appear in the range that can be recognized by the robot, namely A, B, and C, and after determining according to the biometric information, all three objects meet the interactive conditions, that is, The object to be interacted with. In this case, the way to determine the target interaction object can be determined by the priority level, for example, according to the location information of the object to be interacted.

可以计算出待交互对象A、B、C分别距离机器人的距离为d0、d1、d2。假如d2<d0<d1，则根据预设的优先级设置条件(距离机器人越近，优先级越高，距离机器人越远，优先级越低)，为待交互对象A、B、C设置优先级，设置的优先级分别为：待交互对象C(优先级最高)、待交互对象B(优先级最低)，待交互对象A(优先级位于待交互对象C和待交互对象B之间)，此时就可以确定待交互对象C为目标交互对象。 Specifically, as shown in FIG. 2, the obtained location information of the object A to be interacted is (x0, y0), the location information of the object B to be interacted with (x1, y1), and the location information of the object C to be interacted with ( X2, y2), formula according to distance

It can be calculated that the distances of the objects A, B, and C to be interacted with each other are d0, d1, and d2, respectively. If d2<d0<d1, the conditions are set according to the preset priority (the closer to the robot, the higher the priority, the farther from the robot, the lower the priority), and the priority is set for the objects A, B, and C to be interacted with. The priority of the setting is: the object to be interacted with C (the highest priority), the object to be interacted with B (the lowest priority), and the object to be interacted with A (the priority is between the object to be interacted and the object to be interacted with B). It can be determined that the object C to be interacted with is the target interactive object.

In addition, it is worth mentioning that in practical applications, there may be multiple situations where the object to be interacted is the same as the position of the robot. In this case, the angle at which the robot needs to be rotated when moving to which object to be interacted The principle of minimum makes priority judgment.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. In practical applications, those skilled in the art can appropriately set according to actual needs, and no limitation is made herein.

In step 103, location information of the target interactive object is obtained.

In step 104, the robot is controlled to move toward the target interactive object based on the location information.

Specifically, after the target interaction object is determined, the robot can be moved toward the target interaction object according to the acquired location information of the target interaction object, so that the robot can actively perform the interaction operation and improve the user experience.

Compared with the prior art, the human-computer interaction method provided in the embodiment can enable the robot to respond only to the object that needs to interact, thereby effectively avoiding the error response operation and greatly improving the user experience.

A second embodiment of the present application relates to a human-computer interaction method. The embodiment is further improved on the basis of the first embodiment, and the specific improvement is: in the process of controlling the response of the robot to match the target interaction object, the identity information of the target interaction object is also acquired, and the robot is After moving to the area where the target interaction object is located, a response matching the target interaction object is made according to the identity information. For convenience of description, the following specifically describes FIG. 3 and FIG.

Specifically, in this embodiment, step 301 to step 305 are included, wherein step 301 and step 302 and step 304 are substantially the same as step 101 and step 102 and step 104 in the first embodiment, respectively. For details, the following is a description of the differences. For details of the technical details that are not described in detail in this embodiment, refer to the human-computer interaction method provided in the first embodiment, and details are not described herein again.

In step 303, location information and identity information of the target interaction object are obtained.

Taking the target interaction object as an example, the identity information of the target interaction object obtained in this embodiment may include any one or any combination of name, gender, age, whether it is a VIP client or the like.

It should be noted that the above various identity information may specifically be the person stored in the face database of the user who has processed the business recorded by the face recognition technology and the location of the robot (such as the bank business hall). The face data is matched. After the matching is successful, the related identity information of the recorded user who has processed the service can be directly obtained. If there is no match, the gender and approximate age range are first determined according to the face recognition technology, and then the identity information of the target interactive object is further improved through the Internet search.

In addition, it is worth mentioning that, in the actual application, when the target interaction object is determined, the identity information of the object to be interacted may also be determined, for example, the priority of the object to be interacted is set according to the VIP parameter carried in the identity information, and The target interaction object is determined by considering factors such as distance, and is specifically described below in conjunction with FIG. 4 for ease of understanding.

Specifically, there are three objects to be interacted with A, B, and C in the range that the robot can recognize, and the location information and identity information of each object to be interacted are marked as shown in FIG. 4, wherein the objects A, B, and C to be interacted are respectively The distance from the robot is d0, d1, d2, and d2 < d0 < d1.

In this case, the method of determining the target interaction object may be to prioritize the distance factor, and select the object C to be the target interaction object; or preferentially consider the VIP factor, and select the object A to be interacted as the target interaction object; The age factor prioritizes the older objects to be interacted with as the target interaction object.

It should be noted that the above is only a description of the distance, and does not limit the technical solution of the present application and the scope to be protected. In practical applications, those skilled in the art can appropriately set according to actual needs, and no limitation is made herein.

In step 305, after moving to the area where the target interaction object is located, a response matching the target interaction object is made according to the identity information.

For example, the target interaction object is C in Figure 4. After moving to the area where the target interaction object C is located (such as one meter away from the target interaction object), the robot can actively perform service inquiry or business guidance, such as "Zhang Yi Hello, sir, what business do you need to do?".

Further, in order to improve the user experience, after the query to the target interactive object C, while waiting for the target interactive object C to make an answer, the object to be interacted with the object A to be interacted with and the object to be interacted with B may be made. Patience waiting!" voice prompts.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. In practical applications, those skilled in the art can appropriately set according to actual needs, and no limitation is made herein.

Compared with the prior art, the human-computer interaction method provided in this embodiment can further acquire the identity information of the target interaction object when acquiring the location information of the target interaction object, so that the robot can move according to the location information of the target interaction object. After the target interaction object is located, the response to the target interaction object can be made according to the identity information, thereby further improving the user experience.

A third embodiment of the present application relates to a human-computer interaction method. The embodiment is further improved on the basis of the first embodiment or the second embodiment, and the specific improvement is: after the control robot makes a response that matches the target interaction object, and then re-determines the target interaction object that needs to be interacted. It is necessary to first determine whether there is a new object approaching the robot at present. The specific process is shown in Figure 5.

Specifically, in this embodiment, step 501 to step 508 are included, where steps 501 to 504 are substantially the same as steps 101 to 104 in the first embodiment, and details are not described herein again. For the technical details that are not described in detail in this embodiment, refer to the human-computer interaction method provided in the first embodiment or the second embodiment, and details are not described herein again.

In step 505, it is determined whether a new object is approaching the robot. If it is determined that a new object is close to the robot, go to step 506; otherwise, go directly to step 507 to re-select a target object to be interacted from the remaining objects to be interacted in the last human-computer interaction process to make the target interaction object.

Specifically, in this embodiment, the manner of judging whether a new object approaches the robot may be adopted as in the first embodiment, if the preset range (eg, 5 meters) is centered on the current position of the robot. If it is detected that a new object is approaching, it is determined that a new object is close to the robot, and the specific judgment operation will not be described here.

In addition, it should be noted that, in this embodiment, the new object approaching the robot may be one, or may be greater than 1, and is not limited herein.

In step 506, biometric information of the new object is extracted.

In step 507, the target interaction object that needs to interact is re-determined.

Specifically, the target object that needs to be interacted in the embodiment is specifically selected from the new object and the object other than the target interaction object of the last interaction operation.

For ease of understanding, the following is specifically explained:

In practical applications, especially in public places with large traffic, there may be multiple objects that need to interact with the robot at the same time (ie, according to the biometric information of the identified objects, it is determined that more than one object is needed) Interactive interaction objects) However, at the same time, during the human-computer interaction, the robot can only respond to an object to be interacted (that is, the target interaction object needs to be selected for interaction), and after completing an interaction, Other objects to be interacted with each other. However, after completing an interaction, the robot may wait for the robot to respond in addition to the previously determined object to be interacted, and there may be new objects to be interacted with, so in this case, it is necessary to re-determine the interaction. For the operation of the target interactive object, it is necessary to reselect a target to be interacted with the newly confirmed object to be interacted and the remaining objects to be interacted in the last human-computer interaction process to make the target interactive object.

In addition, it should be noted that, in this embodiment, the manner of re-determining the target interaction object that needs to be interacted is substantially the same as the determination manner in the first embodiment, and it is determined that the identified object is determined according to the biometric information. Interacting objects, and then selecting the target interaction objects that need to be interacted with from the objects to be interacted. The specific implementation details are not described here.

In addition, regarding the selection of the target interaction object, in this embodiment, the priority of each object to be interacted can still be selected. Of course, the new target interaction object can be determined according to other selection methods, and no limitation is made here.

In step 508, the control robot is made to respond to the re-determined target interaction object.

Specifically, the control robot makes a response that matches the re-determined target interaction object, and the response process may be: moving toward the target interaction object, and moving to the area where the target interaction object is located, actively conducting service consultation or service guidance, specifically The response mode can be set according to the information about the re-determined target interaction object, and no limitation is made here.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. In practical applications, those skilled in the art can appropriately set according to actual needs, and no limitation is made herein.

Compared with the prior art, the human-computer interaction method provided in this embodiment extracts a new one by monitoring whether a new object approaches the robot after completing a human-computer interaction operation, and when it is determined that a new object approaches the robot. The biometric information of the object that appears and whether the newly appearing object is the object to be interacted. If the newly appearing object is the object to be interacted, the object to be interacted with in the newly confirmed object to be interacted and the last human-computer interaction process Re-select an object to be interacted to make the target interaction object, and then perform human-computer interaction; if the newly appearing object is not the object to be interacted, then directly select an object to be interacted in the remaining objects to be interacted in the last human-computer interaction process. Make the target interaction object and then perform human-computer interaction.

It is not difficult to find through the above description that the human-computer interaction method provided in this embodiment enables the robot to dynamically update the state of the object during the work process, thereby accurately making a response conforming to the current scene, reducing misoperation, and further Improved user experience.

A fourth embodiment of the present application relates to a human-machine interaction device, which is applied to a robot, and the specific structure is as shown in FIG. 6.

As shown in FIG. 6, the human-machine interaction device includes an extraction module 601, a determination module 602, and a control module 603.

The extraction module 601 is configured to extract biometric information of the identified at least one object.

The determining module 602 is configured to determine, from the at least one object, the target interactive object that needs to interact according to the biometric information.

The control module 603 is configured to control the robot to make a response that matches the target interaction object.

Specifically, in the embodiment, the biometric information of the identified at least one object extracted by the extraction module 601 may be any one of physiological characteristic information and behavior characteristic information or a combination of the two.

In addition, it is worth mentioning that the physiological feature information extracted by the extraction module 601 in this embodiment may be any one or any combination of facial information, eye information, voiceprint information, and the like of the object. The behavior characteristic information extracted by the extraction module 601 may specifically be any one of a displacement information of the object, voice content information, or a combination thereof.

The determining module 602 may determine, when determining the target interactive object that needs to be interacted from the at least one object, according to the foregoing various biometric information, first: determining, according to the foregoing various biometric information, that the identified object is the object to be interacted with ( An object that needs to be interacted with, such as analyzing the eye gaze of the object based on the ocular information of the recognized object, and the displacement information of the object to determine whether it is currently seeking help to determine whether it is the object to be interacted; After determining the objects to be interacted with, select an object that meets the requirements from the objects to be interacted as the target interaction object (the object that needs to be interacted eventually).

In addition, in the embodiment, the control module 603 controls the robot to make a response that matches the target interaction object, and specifically may control the robot to move toward the target interaction object.

Further, after the robot moves to the area where the target interaction object is located, the robot can be controlled to make a response matching the identity information of the object, such as active service inquiry, service guidance, etc., specifically: "Hello, may I ask? What business do you want to handle?"

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. In practical applications, those skilled in the art can appropriately set according to actual needs, and no limitation is made herein.

In addition, for the technical details that are not described in detail in this embodiment, refer to the human-computer interaction method provided in any embodiment of the present application, and details are not described herein again.

It is not difficult to find that the human-machine interaction device provided in this embodiment uses the extraction module to extract the biometric information of the identified at least one object, and the determining module determines that the interaction needs to be performed from the at least one object according to the biometric information. The target interaction object, and then the control module is used to control the robot to make a response matching the target interaction object, and the direct cooperation of the above modules enables the robot equipped with the human-machine interaction device to respond only to the object that needs to interact. Thereby effectively avoiding the false response operation and greatly improving the user experience.

The device embodiments described above are merely illustrative and do not limit the scope of the application. In practical applications, those skilled in the art may select some or all of the modules according to actual needs to implement the embodiment. The purpose of the program is not limited here.

A fifth embodiment of the present application relates to a robot, and the specific structure is as shown in FIG.

The robot can be a smart machine located in a public place such as a bank business hall, a large shopping mall, an airport, or the like. The internal one specifically includes one or more processors 701 and a memory 702. One processor 701 is taken as an example in FIG.

In this embodiment, each functional module in the human-machine interaction device involved in the foregoing embodiment is deployed on the processor 701, and the processor 701 and the memory 702 can be connected through a bus or other manner, and the bus is used in FIG. Connection is an example.

The memory 702 is a computer readable storage medium, and can be used to store a software program, a computer executable program, and a module, such as a program instruction/module corresponding to the human-computer interaction method involved in any method embodiment of the present application. The processor 701 executes various functional applications and data processing of the server by executing software programs, instructions, and modules stored in the memory 702, that is, implementing the human-computer interaction method involved in any method embodiment of the present application.

The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may establish a history database, store priority setting conditions, and the like. In addition, the memory 702 may include a high speed random access memory, and may also include a readable and writable memory (RAM). In some embodiments, memory 702 can optionally include memory remotely located relative to processor 701 that can be connected to the terminal device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

In an actual application, the memory 702 can store the instructions executed by the at least one processor 701, and the instructions are executed by the at least one processor 701, so that the at least one processor 701 can perform the human-computer interaction method involved in any method embodiment of the present application. For the details of the technical operations in the human-computer interaction method, the human-computer interaction method provided in any embodiment of the present application can be referred to.

A sixth embodiment of the present application is directed to a computer readable storage medium having stored therein computer instructions that enable a computer to perform the human-computer interaction method involved in any of the method embodiments of the present application.

A person skilled in the art can understand that the above embodiments are specific embodiments of the present application, and various changes can be made in the form and details without departing from the spirit and scope of the application. range.

Claims (10)

A human-computer interaction method is applied to a robot, and the human-computer interaction method includes: Extracting biometric information of the identified at least one object; wherein the biometric information includes physiological characteristic information and/or behavior characteristic information; Determining, from the at least one object, a target interaction object that needs to be interacted according to the biometric information; Controlling the robot to make a response that matches the target interaction object. The human-computer interaction method according to claim 1, wherein the extracting the biometric information of the at least one object that is identified includes: In a preset range centered on the position where the robot is located, it is detected that at least one object approaches the robot, and biometric information of the at least one object is extracted. The human-computer interaction method according to claim 1 or 2, wherein the extracting the biometric information of the identified at least one object comprises: Controlling the robot to perform image acquisition, and extracting biometric features of the at least one object from the collected image to obtain physiological characteristic information and/or behavior characteristic information of the at least one object; wherein the physiological characteristic information includes Facial information and/or eye information, the behavior characteristic information including displacement information; And/or controlling the robot to perform voice collection, and extracting biometric features of the at least one object from the collected voices to obtain physiological feature information and/or behavior feature information of the at least one object; wherein The physiological feature information includes voiceprint information, and the behavior feature information includes voice content information. The human-computer interaction method according to any one of claims 1 to 3, wherein the determining, according to the biometric information, the target interaction object that needs to be interacted from the at least one object, specifically includes: Determining, according to the biometric information, that the at least one object is an object to be interacted with; If the number of the objects to be interacted is equal to 1, determining that the object to be interacted is the target interaction object; If the number of the objects to be interacted is greater than 1, the priority is set for each object to be interacted according to the preset priority setting condition, and the object to be interacted with the highest priority is determined as the target interaction object. The human-computer interaction method according to any one of claims 1 to 4, wherein the controlling the robot to make a response that matches the target interaction object includes: Obtaining location information of the target interaction object; Controlling the robot to move toward the target interactive object according to the location information. The human-computer interaction method according to claim 5, wherein the controlling the robot to make a response that matches the target interaction object comprises: Obtaining identity information of the target interaction object; After the robot moves to the area where the target interaction object is located, a response matching the target interaction object is made according to the identity information. The human-computer interaction method according to claim 6, wherein after the controlling the robot to make a response that matches the target interaction object, the human-computer interaction method further comprises: Determining that a new object is in proximity to the robot; Extracting biometric information of the new object, and re-determining a target interactive object that needs to be interacted from the object other than the target interaction object among the new object and the at least one object; The robot is controlled to make a response that matches the re-determined target interaction object. A human-machine interaction device is applied to a robot, and the human-machine interaction device comprises: an extraction module, a determination module and a control module; The extraction module is configured to extract biometric information of the identified at least one object, where the biometric information includes physiological characteristic information and/or behavior characteristic information; The determining module is configured to determine, from the at least one object, a target interaction object that needs to be interacted according to the biometric information; The control module is configured to control the robot to make a response that matches the target interaction object. A robot that includes: 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7. Human-computer interaction method. A computer readable storage medium storing computer instructions for causing the computer to perform the human-computer interaction method of any one of claims 1 to 7.

Images