Interaction control method and system of intelligent robot

Abstract

The invention relates to the technical field of intelligent robots, in particular to an interaction control method and system for intelligent robots, and the method comprises the following steps: obtaining a plurality of intelligent robots to be controlled, each intelligent robot having a unique identity label; interaction control rules are set for the multiple to-be-controlled intelligent robots; acquiring a voice control instruction input by a user; obtaining voice information collected by the intelligent robot, and processing the voice information to determine a target voice control instruction; based on the interaction control rule, according to a target voice control instruction, determining a target intelligent robot and a task which should be executed by the target intelligent robot, generating a corresponding control signal and sending the control signal to the target intelligent robot so as to control the target intelligent robot to execute the corresponding voice control instruction; the problem of cooperative control among a plurality of intelligent robots can be solved, and the efficiency and accuracy of controlling the intelligent robot by a user through a voice instruction are also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent robots, and in particular to an interactive control method and system of an intelligent robot. Background Art

[0002] The application of smart devices has a significant impact on people's lives and work. For example, smart speakers have gone beyond the scope of traditional speakers. They not only have the voice playback function of traditional speakers, but can also be linked with smart homes to control furniture, and can interact with users through voice to assist users in work and study.

[0003] Intelligent robots are typical intelligent devices. Traditional control methods often rely on preset programs or fixed control logic, which is difficult to adapt to the flexible needs in different scenarios. With the rapid development of voice interaction technology, users increasingly expect to control intelligent robots through natural language commands, rather than relying solely on traditional interaction methods such as physical buttons or touch screens. However, most existing voice control systems can only process simple commands for a single robot and cannot effectively handle the collaborative relationship between multiple robots, resulting in low efficiency in robot interaction control.

[0004] To this end, we propose an interactive control method and system for an intelligent robot to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an interactive control method and system for an intelligent robot to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an interactive control method and system for an intelligent robot, the method comprising the following steps:

[0007] Acquire multiple intelligent robots to be controlled, each intelligent robot having a unique identity;

[0008] Setting interactive control rules for multiple intelligent robots to be controlled, wherein the interactive control rules define the cooperation mode, priority relationship and executable task types of different intelligent robots;

[0009] Acquire a voice control instruction input by a user, wherein the voice control instruction includes an operation requirement for at least one intelligent robot;

[0010] Acquire voice information collected by the intelligent robot, process the voice information to determine the target voice control instruction; determine the target intelligent robot and the task it should perform based on the interactive control rule and the target voice control instruction, and generate a corresponding control signal to send to the target intelligent robot to control it to execute the corresponding voice control instruction, wherein the voice control instruction includes a first voice control instruction and a second voice control instruction;

[0011] Receive feedback information on the intelligent robot's execution of tasks, and adjust the interactive control rules or optimize the subsequent processing and execution of voice information based on the feedback information.

[0012] Preferably, the step of obtaining a plurality of intelligent robots to be controlled, each intelligent robot having a unique identity, comprises:

[0013] Acquire multiple intelligent robots and user information, wherein the user information includes at least a voice timbre of a user;

[0014] Bind the intelligent robot to the user information. One intelligent robot must be bound to at least one user information.

[0015] Multiple intelligent robots bound to the user are used as intelligent robots to be controlled, and a unique identity is set for each intelligent robot to be controlled.

[0016] Preferably, the step of setting interactive control rules for a plurality of intelligent robots to be controlled comprises:

[0017] Trigger keywords are set corresponding to multiple intelligent robots, and each trigger keyword corresponds to the identity of the intelligent robot;

[0018] Obtaining a first voice control instruction and a time point when the first voice control instruction is issued, and controlling a corresponding intelligent robot to execute the first voice control instruction based on a trigger keyword;

[0019] Acquire a second voice control instruction and a time point at which the second voice control instruction is issued, and calculate an interval time between the first voice control instruction and the second voice control instruction based on the time point at which the first voice control instruction is issued and the time point at which the second voice control instruction is issued;

[0020] Determine a first interaction rule based on the interval time, wherein the first interaction rule is an interaction rule between the user and the intelligent robot;

[0021] Obtain multiple behavior information of each intelligent robot, and set behavior keywords corresponding to each behavior information;

[0022] Obtaining behavior keywords corresponding to current behavior information of each intelligent robot and keyword feature information of the second voice control instruction, and determining a second interaction rule based on the behavior keywords corresponding to the current behavior information of the intelligent robot and the keyword feature information of the second voice control instruction, wherein the second interaction rule is an interaction rule between multiple intelligent robots;

[0023] The first interaction rule and the second interaction rule are used as interaction control rules.

[0024] Preferably, the step of determining the first interaction rule based on the interval time includes:

[0025] Calculating the interval time between the first voice control instruction and the second voice control instruction based on the issuance time point of the first voice control instruction and the issuance time point of the second voice control instruction;

[0026] Determine whether the interval time exceeds a preset threshold;

[0027] If it is determined that the interval time does not exceed the preset threshold, the timbre of the first voice control instruction is obtained and marked to obtain a memory timbre, and a second voice control instruction is obtained based on the memory timbre to control the intelligent robot, thereby obtaining a first interaction rule;

[0028] If it is determined that the interval time exceeds the preset threshold, the trigger keyword and the first voice control instruction are re-acquired to control the intelligent robot to obtain the first interaction rule.

[0029] Preferably, the step of determining the second interaction rule based on the keyword corresponding to the current behavior information of the intelligent robot and the keyword feature information of the second voice control instruction includes:

[0030] Obtain keywords corresponding to current behavior information of each intelligent robot and keyword feature information of the second voice control instruction, and extract intelligent robots whose behavior keywords corresponding to the current behavior information are consistent with the keyword feature information of the second voice control instruction as standby intelligent robots;

[0031] Obtain the number of standby intelligent robots, and determine whether the number of standby intelligent robots is greater than 1;

[0032] If it is determined that the number of the standby intelligent robots is equal to 1, directly executing the second voice control instruction on the standby intelligent robots to obtain the second interaction rule;

[0033] If it is determined that the number of standby intelligent robots is greater than 1, the position information of each standby intelligent robot and the position information of the corresponding second voice control instruction sound source are obtained, the distance value between each standby intelligent robot and the second voice control instruction sound source is calculated, and the standby intelligent robot corresponding to the minimum distance value executes the second voice control instruction to obtain the second interaction rule.

[0034] Preferably, the step of acquiring voice information collected by the intelligent robot and processing the voice information to determine the target voice control instruction includes:

[0035] Acquiring voice information collected by the intelligent robot, wherein the voice information includes at least one voice control instruction;

[0036] Extracting timbre features corresponding to each voice control command, calculating the timbre feature vector of the wake-up keyword, and calculating the similarity between the timbre feature vector of each voice command and the timbre feature vector of the wake-up keyword;

[0037] A similarity threshold is preset. When the similarity between the timbre feature vector of the voice command and the wake-up keyword exceeds the threshold, it is determined that the voice command and the wake-up keyword have the same timbre, and the target voice control command is obtained;

[0038] The target voice control command is amplified and other voice control commands are reduced.

[0039] Preferably, the step of determining the target intelligent robot and the task to be performed by the target intelligent robot based on the interactive control rule according to the target voice control instruction comprises:

[0040] After waking up the corresponding intelligent robot based on the trigger keyword, the target voice control instruction is obtained, and the target intelligent robot is determined based on the interactive control rule;

[0041] Based on the target, the intelligent robot performs the corresponding task according to the target voice control instructions.

[0042] An interactive control system for an intelligent robot, applied to any one of the interactive control methods described above, comprising:

[0043] An intelligent robot acquisition module is used to acquire multiple intelligent robots to be controlled, each intelligent robot having a unique identity;

[0044] An interaction rule setting module, used to set interaction control rules for multiple intelligent robots to be controlled, wherein the interaction control rules define the cooperation mode, priority relationship and executable task types of different intelligent robots;

[0045] An instruction acquisition module, used to acquire a voice control instruction input by a user, wherein the voice control instruction includes an operation requirement for at least one intelligent robot;

[0046] The intelligent robot control module is used to obtain the voice information collected by the intelligent robot, process the voice information to determine the target voice control instruction; determine the target intelligent robot and the task to be performed according to the target voice control instruction based on the interactive control rule, and generate a corresponding control signal to send to the target intelligent robot to control it to execute the corresponding voice control instruction, wherein the voice control instruction includes a first voice control instruction and a second voice control instruction;

[0047] The feedback module is used to receive feedback information about the intelligent robot's execution of tasks, and adjust the interactive control rules or optimize the subsequent processing and execution of voice information based on the feedback information.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] By introducing voice control commands, users can control multiple intelligent robots in a more natural and intuitive way, without relying on complex physical operations or preset programs, thereby significantly improving control efficiency; by defining the collaboration mode, priority relationship and executable task types between different intelligent robots through interactive control rules, multiple robots can work together in complex scenarios to complete complex tasks together; interactive control rules can be flexibly adjusted according to actual needs to adapt to changes in needs in different scenarios. At the same time, the system can receive feedback information from the intelligent robot's execution of tasks, and continuously optimize the subsequent processing and execution of voice information based on this information, so that it can understand the user's intention more accurately and respond to the user's instructions quickly, thereby improving user satisfaction and enhancing the user's trust and dependence on the intelligent robot system. It not only solves the problem of collaborative control between multiple intelligent robots, but also improves the efficiency and accuracy of users controlling intelligent robots through voice commands. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0052] Figure 2 It is a system structure block diagram of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example

[0055] See also Figure 1 to Figure 2 The present invention provides an interactive control method and system technical solution for an intelligent robot: an interactive control method for an intelligent robot, comprising the following steps:

[0056] S1: Acquire multiple intelligent robots to be controlled, each intelligent robot having a unique identity;

[0057] The step of obtaining multiple intelligent robots to be controlled, each intelligent robot having a unique identity includes: obtaining multiple intelligent robots and user information, wherein the user information includes at least a voice timbre of a user; binding the intelligent robots to the user information, wherein one intelligent robot is bound to at least one user information; using the multiple intelligent robots bound to the user as intelligent robots to be controlled, and setting a unique identity for each intelligent robot to be controlled;

[0058] Specifically, multiple intelligent robots are obtained, and the intelligent robots are associated with users. The multiple intelligent robots associated with users are used as intelligent robots to be controlled. If the voices of multiple users are bound, one intelligent robot will correspond to the voice tones of multiple different users. The user bound to the intelligent robot can directly issue voice control instructions to the intelligent robot. If the user binds several robots, it means that the user corresponds to several robots to be controlled. These robots to be controlled are used as multiple robots to be controlled by the user. One intelligent robot is bound to at least one user, thereby obtaining multiple intelligent robots to be controlled, which is convenient for users to assign different tasks to intelligent robots and for different people to control intelligent robots, thereby improving the intelligence of robots and improving the efficiency and accuracy of interaction.

[0059] S2: setting interaction control rules for the multiple intelligent robots to be controlled, wherein the interaction control rules define the cooperation mode, priority relationship and executable task types of different intelligent robots;

[0060] The step of setting interactive control rules for the plurality of intelligent robots to be controlled comprises:

[0061] Setting trigger keywords corresponding to multiple intelligent robots, each trigger keyword corresponding to the identity of the intelligent robot; obtaining a first voice control instruction and the time point of issuing the first voice control instruction, and controlling the corresponding intelligent robot to execute the first voice control instruction based on the trigger keyword; obtaining a second voice control instruction and the time point of issuing the second voice control instruction; calculating the interval time between the first voice control instruction and the second voice control instruction based on the time point of issuing the first voice control instruction and the time point of issuing the second voice control instruction; determining a first interaction rule based on the interval time, wherein the first interaction rule is an interaction rule between a user and an intelligent robot; obtaining multiple behavior information of each intelligent robot, and setting a behavior keyword corresponding to each behavior information; obtaining the behavior keyword corresponding to the current behavior information of each intelligent robot and the keyword feature information of the second voice control instruction, and determining a second interaction rule based on the behavior keyword corresponding to the current behavior information of the intelligent robot and the keyword feature information of the second voice control instruction, wherein the second interaction rule is an interaction rule between multiple intelligent robots; using the first interaction rule and the second interaction rule as interaction control rules;

[0062] Specifically, by setting a trigger keyword for the intelligent robot, and the keyword corresponds to the identity of the intelligent robot, it can be ensured that the first voice control instruction is issued to which intelligent robot, thereby determining which intelligent robot implements the first voice control instruction, and judging whether the intelligent robot continues to execute the second voice instruction by the interval time between voice control qualities. If the time is exceeded, but the intelligent robot needs to continue to execute the second voice control instruction, it is necessary to re-trigger the keyword to start the intelligent robot; if the interval time is not exceeded, but there are multiple first voice control instructions, the timbre corresponding to the trigger keyword closest to the current time period is used as the standard according to the output time of the first voice instruction, and the voice control instruction corresponding to the timbre is collected as For the first voice control instruction, even if it is within the interval time threshold, the previous first voice control instruction at this time is also invalid, and the voice control instruction corresponding to the timbre corresponding to the trigger keyword closest to the current time period is used as the first voice control instruction, so as to complete the update of the intelligent robot when multiple sources issue voice control instructions to the intelligent robot; by determining the keyword feature information of the second voice control instruction consistent with the behavior keyword, the corresponding standby intelligent robot is determined, and the interaction rules between multiple intelligent robots are determined according to the behavior keyword and the keyword feature information, so as to complete the formulation of the interaction rules, and the interaction rules between the user and the intelligent robot and the interaction rules between multiple intelligent robots are integrated to obtain the interaction control rules, thereby improving the interaction control effect of the intelligent robot;

[0063] The step of determining the first interaction rule based on the interval time includes: calculating the interval time between the first voice control instruction and the second voice control instruction based on the issuance time point of the first voice control instruction and the issuance time point of the second voice control instruction, judging whether the interval time exceeds a preset threshold, if it is judged that the interval time does not exceed the preset threshold, obtaining the timbre of the first voice control instruction and marking it to obtain a memory timbre, obtaining the second voice control instruction based on the memory timbre to control the intelligent robot, and obtaining the first interaction rule; if it is judged that the interval time exceeds the preset threshold, re-obtaining the trigger keyword and the first voice control instruction to control the intelligent robot, and obtaining the first interaction rule;

[0064] Specifically, the preset threshold refers to a preset time threshold, which is used to control that if a second voice control instruction appears within the time period, there is no need to start the trigger key again, and the standby robot that executes the first voice control instruction can be directly controlled for the second time, so that it can directly execute the second voice control instruction; by calculating the interval time of continuous voice control instructions and deciding whether to use the memory tone for control according to the time interval, not only the continuity and accuracy of user interaction are improved;

[0065] The step of determining the second interaction rule based on the keywords corresponding to the current behavior information of the intelligent robot and the keyword feature information of the second voice control instruction includes: obtaining the keywords corresponding to the current behavior information of each intelligent robot and the keyword feature information of the second voice control instruction, extracting the intelligent robots whose behavior keywords corresponding to the current behavior information are consistent with the keyword feature information of the second voice control instruction as standby intelligent robots, obtaining the number of standby intelligent robots, judging whether the number of standby intelligent robots is greater than 1, and if it is judged that the number of standby intelligent robots is equal to 1, directly executing the second voice control instruction on the standby intelligent robots to obtain the second interaction rule; if it is judged that the number of standby intelligent robots is greater than 1, obtaining the position information of each standby intelligent robot and the position information of the sound source of the second voice control instruction, calculating the distance value between each standby intelligent robot and the sound source of the second voice control instruction, and executing the second voice control instruction on the standby intelligent robot corresponding to the minimum distance value to obtain the second interaction rule;

[0066] It should be noted that when the number of standby intelligent robots is less than 1, it means that there is no standby intelligent robot. At this time, it is necessary to re-enter the trigger keyword and the first voice control instruction to restart the intelligent robot to execute the voice control instruction, which is equivalent to returning to the initial step;

[0067] Specifically, the distance value between each standby intelligent robot and the user is calculated. The distance here can be a straight-line distance, a Euclidean distance, or other appropriate measurement methods. The standby intelligent robot closest to the user (i.e., the smallest distance value) is selected as the execution object. After determining the execution object, the system will send a second voice control instruction to the intelligent robot and record this interaction rule. The intelligent robot will perform the corresponding operation according to the instruction; obtain the keywords corresponding to the current behavior information of each intelligent robot and the keyword feature information of the second voice control instruction, for example, the keyword corresponding to the behavior information of intelligent robot A is "grab items", and the keyword feature information of the second voice control instruction is "put down items". According to the keyword matching, determine the intelligent robot whose behavior keyword corresponding to the current behavior information is consistent with the keyword feature information of the second voice control instruction, that is, the standby intelligent robot. Assuming that the behavior keyword of intelligent robot A is "grab items", the standby intelligent robot may be intelligent robot B or C. Obtain the number of standby intelligent robots, for example, there may be three standby intelligent robots in the system. Determine whether the number of standby intelligent robots is greater than 1. If there is only one standby intelligent robot, the second voice control instruction is directly executed on the intelligent robot to obtain the second interaction rule; if there are two or more standby intelligent robots, proceed to the next step. If the number of standby intelligent robots is greater than 1, the position information of each standby intelligent robot and the position information of the corresponding second voice control instruction sound source are obtained. Assuming that the sound source of the second voice control instruction is robot D, and its location is (x, y), it is necessary to calculate the distance value between each standby intelligent robot and robot D. Assuming that the standby intelligent robots A, B, and C are located at positions (a, b), (c, d), and (e, f), respectively, their distances from robot D are |AD|, |BD|, and |CD|, respectively. The standby intelligent robot corresponding to the minimum distance value executes the second voice control instruction to obtain the second interaction rule. At this time, assuming that the standby intelligent robot corresponding to the shortest distance is intelligent robot A, the intelligent robot A will be executed with the second voice control instruction to obtain a new interaction rule; the intelligent robot control system can dynamically select a suitable intelligent robot to execute the second voice control instruction based on the current behavior information and the keyword feature information of the second voice control instruction, thereby achieving more efficient task allocation and collaboration;

[0068] S3: Acquire a voice control instruction input by a user, wherein the voice control instruction includes an operation requirement for at least one intelligent robot;

[0069] S4: Acquire the voice information collected by the intelligent robot, process the voice information to determine the target voice control instruction; determine the target intelligent robot and the task it should perform based on the interactive control rule and the target voice control instruction, and generate a corresponding control signal to send to the target intelligent robot to control it to execute the corresponding voice control instruction, wherein the voice control instruction includes a first voice control instruction and a second voice control instruction;

[0070] The steps of obtaining voice information collected by the intelligent robot and processing the voice information to determine the target voice control instruction include: obtaining voice information collected by the intelligent robot, wherein the voice information includes at least one voice control instruction; extracting timbre features corresponding to each voice control instruction, calculating the timbre feature vector of the wake-up keyword, and performing similarity calculation between the timbre feature vector of each voice instruction and the timbre feature vector of the wake-up keyword; presetting a similarity threshold, when the similarity between the timbre feature vector of the voice instruction and the wake-up keyword exceeds the threshold, determining that the voice instruction has the same timbre as the wake-up keyword, obtaining the target voice control instruction, amplifying the target voice control instruction, and reducing other voice control instructions;

[0071] It should be noted that when the similarity between the timbre feature vector of the voice command and the wake-up keyword does not exceed the threshold, they are all regarded as other voice control commands and are reduced in size;

[0072] The similarity between the timbre feature vector of each voice command and the timbre feature vector of the wake-up keyword can be calculated using cosine similarity. Given two timbre feature vectors A and B, the corresponding similarity calculation formula is: Among them, A·B is the dot product of the vectors, ||A|| and ||B|| represent the norms of A and B respectively; extract timbre features for each voice command, including fundamental frequency, resonance peak, MFCC, etc.; for amplifying the voice command with the same timbre as the wake-up keyword, linear gain or nonlinear gain adjustment can be used. Assuming that the amplitude of the original voice signal is x(t), the amplitude of the amplified voice signal is y(t), and the amplification factor is G, then: y(t) = G·x(t) (for voice commands with the same timbre as the wake-up keyword); for other voice commands, a smaller gain coefficient g (g<G) can be used for reduction processing: y′(t) = g·x′(t) (for other voice commands), and the above preprocessing, voice recognition, timbre matching and enhancement modules are integrated into a system. Test the system to ensure that it can accurately recognize voice control commands, amplify voice commands with the same timbre as the wake-up keyword, and reduce other voice commands;

[0073] Specifically, the voice control command is recognized, multiple voice commands in the voice control command are obtained, the voice control command with the same timbre as the wake-up keyword is obtained for amplification processing, and other voices are reduced for processing, so that the intelligent robot can more accurately recognize the voice control command, and the effect of voice recognition can be improved by adjusting the amplitude or gain of the sound signal. It can be optimized for specific sound characteristics or environmental noise to improve the clarity and accuracy of voice recognition;

[0074] The step of determining the target intelligent robot and the task to be performed by the target intelligent robot according to the target voice control instruction based on the interactive control rule includes: after waking up the corresponding intelligent robot based on the trigger keyword, obtaining the target voice control instruction, determining the target intelligent robot based on the interactive control rule; and performing the corresponding task according to the target voice control instruction based on the target intelligent robot;

[0075] Specifically, the user wakes up the intelligent robot by saying specific trigger keywords (such as "robot, wake up", etc.). After the built-in voice recognition system of the intelligent robot captures these keywords, it will be judged as a valid wake-up command, and then enter the standby state, ready to receive subsequent voice control commands. After being awakened, the intelligent robot will remain sensitive to sound and wait for the user to issue specific voice control commands. The user can say the task he wants the intelligent robot to perform. The voice recognition system of the intelligent robot will convert the voice command into text or specific control signals. In some cases, the user may have multiple intelligent robots or devices and want to specify a specific robot to perform a task. At this time, the user can explicitly specify the target robot in the voice control command, or determine the target robot through preset interaction rules (such as based on the user's location, which robot is currently interacting with, etc.). The control system of the intelligent robot will determine which robot should respond and perform the task based on this information. After determining the target intelligent robot, the robot will perform the corresponding task according to the received voice control command. After completing the task, the intelligent robot may feedback the results to the user through voice, screen display, etc.; use existing natural language processing (NLP) technology to identify and wake up keywords. It can include part-of-speech tagging, named entity recognition, etc. to improve the accuracy of keyword recognition. After identifying the keywords, the target intelligent robot is determined based on these keywords. After the target intelligent robot is determined, the intelligent robot is asked to perform the corresponding task according to the user's voice control instructions. The behavior action sequence can be pre-defined, and the behavior action can be bound to the corresponding keyword, or the behavior action sequence can be generated in real time according to the user's voice content. Through the reasonable setting of interaction rules, linkage control between multiple devices can be realized to improve the convenience of life;

[0076] S5: receiving feedback information of the intelligent robot executing the task, and adjusting the interactive control rules or optimizing the subsequent processing and execution of the voice information according to the feedback information;

[0077] Specifically, after the intelligent robot performs a task, it may provide feedback to the user through multiple channels such as voice, screen display, flashing lights, etc. It can ensure accurate capture and analysis of feedback information to ensure the integrity and accuracy of the information. Feedback information may include the results of task execution (such as queried weather information), execution status (such as task completed, in progress, execution failed, etc.) and possible error prompts. This information is parsed for subsequent processing and optimization. According to user feedback and task execution results, the interactive control rules are dynamically adjusted to improve the flexibility and adaptability of the system. For example, if the user still fails to successfully perform a task after multiple attempts, the system can automatically adjust the priority of task execution; the system can learn the user's preferences and needs by analyzing the user's feedback and behavioral habits. Based on the learning results, the system can customize more personalized interactive control rules for users to improve user experience. According to user feedback and task execution results, the system can optimize the speech recognition algorithm to improve the accuracy and efficiency of recognition. For example, if it is found that users frequently use certain specific words or phrases, special optimization training can be carried out for these words or phrases. According to the results and feedback of task execution, the task execution process can be optimized to reduce unnecessary steps or improve execution efficiency. For example, if the system finds that a task often encounters errors or delays during execution, it can reconstruct or optimize the execution process of the task. Based on user feedback and task execution results, the system can recommend more appropriate or relevant tasks or services to users. At the same time, the system can also provide intelligent tips and suggestions during the user's task execution to help users complete tasks more efficiently.

[0078] An interactive control system for an intelligent robot, applied to any one of the interactive control methods described above, comprising:

[0079] An intelligent robot acquisition module is used to acquire multiple intelligent robots to be controlled, each intelligent robot having a unique identity;

[0080] An interaction rule setting module, used to set interaction control rules for multiple intelligent robots to be controlled, wherein the interaction control rules define the cooperation mode, priority relationship and executable task types of different intelligent robots;

[0081] An instruction acquisition module, used to acquire a voice control instruction input by a user, wherein the voice control instruction includes an operation requirement for at least one intelligent robot;

[0082] The intelligent robot control module is used to obtain the voice information collected by the intelligent robot, process the voice information to determine the target voice control instruction; determine the target intelligent robot and the task to be performed according to the target voice control instruction based on the interactive control rule, and generate a corresponding control signal to send to the target intelligent robot to control it to execute the corresponding voice control instruction, wherein the voice control instruction includes a first voice control instruction and a second voice control instruction;

[0083] The feedback module is used to receive feedback information about the intelligent robot's execution of tasks, and adjust the interactive control rules or optimize the subsequent processing and execution of voice information based on the feedback information.

[0084] By introducing voice control commands, users can control multiple intelligent robots in a more natural and intuitive way, without relying on complex physical operations or preset programs, thereby significantly improving control efficiency; by defining the collaboration mode, priority relationship and executable task types between different intelligent robots through interactive control rules, multiple robots can work together in complex scenarios to complete complex tasks together; interactive control rules can be flexibly adjusted according to actual needs to adapt to changes in needs in different scenarios. At the same time, the system can receive feedback information from the intelligent robot's execution of tasks, and continuously optimize the subsequent processing and execution of voice information based on this information, so that it can understand the user's intention more accurately and respond to the user's instructions quickly, thereby improving user satisfaction and enhancing the user's trust and dependence on the intelligent robot system. It not only solves the problem of collaborative control between multiple intelligent robots, but also improves the efficiency and accuracy of users controlling intelligent robots through voice commands.

[0085] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0086] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An interactive control method for an intelligent robot, characterized in that: The following steps are involved: Acquire multiple intelligent robots to be controlled, each intelligent robot having a unique identity; Setting interactive control rules for multiple intelligent robots to be controlled, wherein the interactive control rules define the cooperation mode, priority relationship and executable task types of different intelligent robots; Acquire a voice control instruction input by a user, wherein the voice control instruction includes an operation requirement for at least one intelligent robot; Acquire voice information collected by the intelligent robot, process the voice information to determine the target voice control instruction; determine the target intelligent robot and the task it should perform based on the interactive control rule and the target voice control instruction, and generate a corresponding control signal to send to the target intelligent robot to control it to execute the corresponding voice control instruction, wherein the voice control instruction includes a first voice control instruction and a second voice control instruction; Receive feedback information on the intelligent robot's execution of tasks, and adjust the interactive control rules or optimize the subsequent processing and execution of voice information based on the feedback information.

2. The interactive control method of an intelligent robot according to claim 1, characterized in that: The step of obtaining a plurality of intelligent robots to be controlled, each intelligent robot having a unique identity, comprises: Acquire multiple intelligent robots and user information, wherein the user information includes at least a voice timbre of a user; Bind the intelligent robot to the user information. One intelligent robot must be bound to at least one user information. Multiple intelligent robots bound to the user are used as intelligent robots to be controlled, and a unique identity is set for each intelligent robot to be controlled.

3. The interactive control method of an intelligent robot according to claim 1, characterized in that: The step of setting interactive control rules for a plurality of intelligent robots to be controlled comprises: Trigger keywords are set corresponding to multiple intelligent robots, and each trigger keyword corresponds to the identity of the intelligent robot; Obtaining a first voice control instruction and a time point when the first voice control instruction is issued, and controlling a corresponding intelligent robot to execute the first voice control instruction based on a trigger keyword; Acquire a second voice control instruction and a time point at which the second voice control instruction is issued, and calculate an interval time between the first voice control instruction and the second voice control instruction based on the time point at which the first voice control instruction is issued and the time point at which the second voice control instruction is issued; Determine a first interaction rule based on the interval time, wherein the first interaction rule is an interaction rule between the user and the intelligent robot; Obtain multiple behavior information of each intelligent robot, and set behavior keywords corresponding to each behavior information; Obtaining behavior keywords corresponding to current behavior information of each intelligent robot and keyword feature information of the second voice control instruction, and determining a second interaction rule based on the behavior keywords corresponding to the current behavior information of the intelligent robot and the keyword feature information of the second voice control instruction, wherein the second interaction rule is an interaction rule between multiple intelligent robots; The first interaction rule and the second interaction rule are used as interaction control rules.

4. The interactive control method of an intelligent robot according to claim 3, characterized in that: The step of determining the first interaction rule based on the interval time comprises: Calculating the interval time between the first voice control instruction and the second voice control instruction based on the issuance time point of the first voice control instruction and the issuance time point of the second voice control instruction; Determine whether the interval time exceeds a preset threshold; If it is determined that the interval time does not exceed the preset threshold, the timbre of the first voice control instruction is obtained and marked to obtain a memory timbre, and a second voice control instruction is obtained based on the memory timbre to control the intelligent robot, thereby obtaining a first interaction rule; If it is determined that the interval time exceeds the preset threshold, the trigger keyword and the first voice control instruction are re-acquired to control the intelligent robot to obtain the first interaction rule.

5. The interactive control method of an intelligent robot according to claim 3, characterized in that: The step of determining the second interaction rule based on the keyword corresponding to the current behavior information of the intelligent robot and the keyword feature information of the second voice control instruction includes: Obtain keywords corresponding to current behavior information of each intelligent robot and keyword feature information of the second voice control instruction, and extract intelligent robots whose behavior keywords corresponding to the current behavior information are consistent with the keyword feature information of the second voice control instruction as standby intelligent robots; Obtain the number of standby intelligent robots, and determine whether the number of standby intelligent robots is greater than 1; If it is determined that the number of the standby intelligent robots is equal to 1, directly executing the second voice control instruction on the standby intelligent robots to obtain the second interaction rule; If it is determined that the number of standby intelligent robots is greater than 1, the position information of each standby intelligent robot and the position information of the corresponding second voice control instruction sound source are obtained, the distance value between each standby intelligent robot and the second voice control instruction sound source is calculated, and the standby intelligent robot corresponding to the minimum distance value executes the second voice control instruction to obtain the second interaction rule.

6. The interactive control method of an intelligent robot according to claim 1, characterized in that: The steps of acquiring voice information collected by the intelligent robot and processing the voice information to determine the target voice control instruction include: Acquiring voice information collected by the intelligent robot, wherein the voice information includes at least one voice control instruction; Extracting timbre features corresponding to each voice control command, calculating the timbre feature vector of the wake-up keyword, and calculating the similarity between the timbre feature vector of each voice command and the timbre feature vector of the wake-up keyword; A similarity threshold is preset. When the similarity between the timbre feature vector of the voice command and the wake-up keyword exceeds the threshold, it is determined that the voice command and the wake-up keyword have the same timbre, and the target voice control command is obtained; The target voice control command is amplified and other voice control commands are reduced.

7. The interactive control method of an intelligent robot according to claim 1, characterized in that: The step of determining the target intelligent robot and the task to be performed by the target intelligent robot based on the interactive control rule and the target voice control instruction comprises: After waking up the corresponding intelligent robot based on the trigger keyword, the target voice control instruction is obtained, and the target intelligent robot is determined based on the interactive control rule; Based on the target, the intelligent robot performs the corresponding task according to the target voice control instructions.

8. An interactive control system of an intelligent robot, applied to the interactive control method according to any one of claims 1 to 7, characterized in that: include: An intelligent robot acquisition module is used to acquire multiple intelligent robots to be controlled, each intelligent robot having a unique identity; An interaction rule setting module, used to set interaction control rules for multiple intelligent robots to be controlled, wherein the interaction control rules define the cooperation mode, priority relationship and executable task types of different intelligent robots; An instruction acquisition module, used to acquire a voice control instruction input by a user, wherein the voice control instruction includes an operation requirement for at least one intelligent robot; The intelligent robot control module is used to obtain the voice information collected by the intelligent robot, process the voice information to determine the target voice control instruction; determine the target intelligent robot and the task to be performed according to the target voice control instruction based on the interactive control rule, and generate a corresponding control signal to send to the target intelligent robot to control it to execute the corresponding voice control instruction, wherein the voice control instruction includes a first voice control instruction and a second voice control instruction; The feedback module is used to receive feedback information about the intelligent robot's execution of tasks, and adjust the interactive control rules or optimize the subsequent processing and execution of voice information based on the feedback information.

Images