Robot abnormality processing method, apparatus, computer device and storage medium

Abstract

The invention discloses a robot exception handling method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: performing voice recognition on sound information collected by a robot to obtain a recognition result; when the recognition result shows that the sound information is the first abnormal sound and the sound information is obtained by collecting the sound information in the cleaning process of the robot, a first adjustment parameter is obtained according to the recognition result; the first abnormal sound is the abnormal sound emitted by a target object under the condition that the robot damages the target object in the cleaning process; one of the cleaning mode and the motion mode of the robot is adjusted according to the first adjusting parameter, by means of the method, the robot can be prevented from hurting the living object in the cleaning process, and therefore the cleaning efficiency can be improved.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202511881381.3 (22) Application Date 2023.05.18 (62) Divisional Application Data 202310565396.3 2023.05.18 (71) Applicant: Chase Innovation Technology (Suzhou) Co., Ltd. Address: Units 1, 2, and 3, Building 8, No. 1688, Songwei Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province, 215000 (72) Inventors: Sun Jiajia, Luo Shaohan, Geng Wenfeng (74) Patent Agency: Beijing Runping Intellectual Property Agency Co., Ltd. 11283 Patent Attorney: Li Hong (51) Int.Cl. A47L 11 / 24 (2006.01) A47L 11 / 40 (2006.01) (54) Invention Title: Method, Apparatus, Computer Equipment, and Storage Medium for Handling Abnormalities in a Robot (57) Abstract: This invention discloses a method, apparatus, computer equipment, storage medium, and computer program product for handling abnormalities in a robot. The method includes: performing speech recognition on sound information collected by the robot to obtain a recognition result; when the recognition result indicates that the sound information is a first abnormal sound and the sound information is collected by the robot during the cleaning process, obtaining a first adjustment parameter based on the recognition result; the first abnormal sound refers to an abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process; adjusting one of the robot's cleaning mode and movement mode according to the first adjustment parameter. This method can avoid the robot causing damage to living objects during the cleaning process, thereby improving cleaning efficiency. Claims 2 pages, Description 11 pages, Drawings 3 pages, CN 121512385 A 2026.02.13 CN 1 21 51 23 85 A 1. A method for handling abnormalities in a robot, characterized in that the method includes: performing speech recognition on sound information collected by the robot to obtain a recognition result; when the recognition result indicates that the sound information is a second abnormal sound, performing position tracking on the target object that emitted the sound information to obtain the location of the target object; the second abnormal sound is an abnormal sound emitted by the target object when the robot does not cause harm to the target object during the cleaning process; sending a reminder message carrying the location to a terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera. 2. The method according to claim 1, characterized in that, performing position tracking on the target object that emitted the sound information to obtain the location of the target object includes:3. The method according to claim 2, wherein sending a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera, comprises: sending the relative direction of the target object and the current position of the robot to the terminal corresponding to the monitored object, so that the terminal corresponding to the monitored object controls the home camera or the robot's camera to aim at the target object based on the relative direction of the target object and the current position of the robot, and the monitored object interacts with the target object through the home camera or the robot's camera. 4. The method according to claim 1, wherein the method further comprises: collecting sound information during the cleaning process to obtain the sound information; or, collecting sound information when the robot is stationary at the robot base station to obtain the sound information; or, collecting sound information when the robot is placed at a target position to obtain the sound information; or, collecting sound information when the robot moves to a designated position to obtain the sound information. 5. The method according to claim 1, wherein the step of performing speech recognition on the sound information collected by the robot to obtain a recognition result includes: comparing the collected sound information with a pre-constructed sound information set to determine whether the collected sound information belongs to a second abnormal sound. 6. The method according to claim 1, wherein the step of performing speech recognition on the sound information collected by the robot to obtain a recognition result includes: performing speech recognition on the sound information collected by the robot using a speech recognition model to obtain a recognition result. 7. An anomaly handling device for a robot, wherein the device comprises: a recognition module, used to perform speech recognition on the sound information collected by the robot to obtain a recognition result; an interaction module, used to, when the recognition result indicates that the sound information is a second abnormal sound, track the location of the target object emitting the sound information to obtain the location of the target object; the second abnormal sound is an abnormal sound emitted by the target object when the robot does not cause harm to the target object during the cleaning process; and sending a reminder message carrying the location to a terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera. 8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 6. Claims 1 / 2 page 2 CN 121512385 A9. A computer-readable storage medium storing a computer program thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6. 10. A computer program product comprising a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6. Claims 2 / 2 Page 3 CN 121512385 A Method, Apparatus, Computer Equipment and Storage Medium for Handling Abnormalities of a Robot

[0001] This application is a divisional application of the invention patent with application number 202310565396.3, application date 2023.05.18, and invention title "Method, Apparatus, Computer Equipment and Storage Medium for Handling Abnormalities of a Robot". Technical Field

[0002] This invention belongs to the field of artificial intelligence technology, specifically relating to a method, apparatus, computer equipment and storage medium for handling abnormalities of a robot. Background Art

[0003] Currently, sweeping robots can act as robot butlers in the home, possessing vision and voice systems. As a mobile platform, they can do more work in monitoring and abnormality recognition. Existing robotic vacuum cleaners may cause harm to living objects during the cleaning process, resulting in low cleaning efficiency.

[0004] Therefore, the technical problem to be solved by this invention is how to avoid causing harm to pets during the cleaning process, thus preventing low cleaning efficiency.

[0005] To solve the above technical problem, this invention provides a method, apparatus, computer device, and storage medium for handling abnormalities in a robot.

[0006] In a first aspect, this invention provides a method for handling abnormalities in a robot. The method includes: performing speech recognition on sound information collected by the robot to obtain a recognition result; when the recognition result indicates that the sound information is a first abnormal sound, and the sound information is obtained by the robot during the cleaning process, obtaining a first adjustment parameter based on the recognition result; the first abnormal sound refers to an abnormal sound emitted by the target object when the robot causes harm to the target object during the cleaning process; adjusting one of the robot's cleaning mode and movement mode according to the first adjustment parameter. Secondly, the present invention also provides an anomaly handling device for a machine, the device comprising: a recognition module, configured to perform speech recognition on sound information collected by the robot to obtain a recognition result; and an acquisition module, configured to acquire a first adjustment parameter based on the recognition result when the recognition result indicates that the sound information is a first abnormal sound and the sound information is collected by the robot during the cleaning process; the first abnormal sound refers to an abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process;An adjustment module is used to adjust one of the cleaning mode and the movement mode of the robot according to the first adjustment parameter. In one embodiment, the adjustment module is also used to control the robot to decelerate, pause movement, or change the direction of movement according to the first adjustment parameter.

[0007] In one embodiment, the acquisition module is also used to detect the operating parameters of the robot and obtain a detection result when the recognition result indicates that the sound information is a first abnormal sound and the sound information is obtained by the robot during the cleaning process; and to acquire the first adjustment parameter according to the recognition result when the detection result indicates that the robot has caused damage to the target object that emitted the sound information during the cleaning process.

[0008] In one embodiment, the acquisition module is also used to include at least one of the robot's brush current and the robot's posture in the operating parameters.

[0009] In one embodiment, the acquisition module is also used to perform the step of detecting the operating parameters of the robot when it is determined that the target object is in contact with the robot.

[0010] In one embodiment, the device further includes: a control module, configured to control the robot to reduce the brush speed if the robot does not cause damage to the target object emitting the sound information during the cleaning process.

[0011] A determination module, configured to compare the robot posture with each sample posture in a preset posture sample set; wherein the sample posture is a robot posture in which the probability of the robot causing damage to the target object during the cleaning process is greater than a preset value; and to determine whether the robot caused damage to the target object emitting the sound information during the cleaning process based on the comparison result.

[0012] An interaction module, configured to perform position tracking on the target object emitting the sound information when the recognition result indicates that the sound information is a second abnormal sound, and to obtain the location of the target object; the second abnormal sound is an abnormal sound emitted by the target object when the robot does not cause damage to the target object during the cleaning process; and to send a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera.

[0013] In one embodiment, the interaction module is further configured to determine the relative direction of the target object emitting the sound information, the relative direction being the direction of the target object relative to the robot.

[0014] In one embodiment, the interaction module is further configured to send the relative direction of the target object and the current position of the robot to the terminal corresponding to the monitored object, so that the terminal corresponding to the monitored object controls the home camera or the robot's camera to be aimed based on the relative direction of the target object and the current position of the robot.The target object, the monitored object interacts with the target object through the home camera or the robot's camera.

[0015] In one embodiment, the interaction module is further used to collect sound information during the cleaning process to obtain the sound information; or, when the robot is stationary at the robot base station, collect sound information to obtain the sound information; or, when the robot is placed at the target location, collect sound information to obtain the sound information; or, when the robot moves to a designated location, collect sound information to obtain the sound information. In a third aspect, the present invention also provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the following steps: performing speech recognition on the sound information collected by the robot to obtain a recognition result; when the recognition result indicates that the sound information is a first abnormal sound and the sound information is obtained by the robot collecting sound information during the cleaning process, obtaining a first adjustment parameter based on the recognition result; the first abnormal sound refers to the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process; adjusting one of the robot's cleaning mode and movement mode according to the first adjustment parameter. Fourthly, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps: (See specification 2 / 11, page 5, CN 121512385 A) Performing speech recognition on sound information collected by the robot to obtain a recognition result; When the recognition result indicates that the sound information is a first abnormal sound, and the sound information is obtained by the robot during the cleaning process, obtaining a first adjustment parameter based on the recognition result; The first abnormal sound refers to an abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process; Adjusting one of the robot's cleaning mode and movement mode according to the first adjustment parameter. Fifthly, the present invention also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps: performing speech recognition on sound information collected by the robot to obtain a recognition result; when the recognition result indicates that the sound information is a first abnormal sound, and the sound information was collected by the robot during the cleaning process, obtaining a first adjustment parameter based on the recognition result; the first abnormal sound refers to an abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process; adjusting one of the robot's cleaning mode and movement mode according to the first adjustment parameter.The robot's abnormal handling method, device, computer equipment, storage medium, and computer program product obtain recognition results by performing speech recognition on the sound information collected by the robot; achieve accurate recognition of the collected sound information, and when the recognition result indicates that the sound information is a first abnormal sound, and the sound information is collected by the robot during the cleaning process, obtain a first adjustment parameter based on the recognition result; the first abnormal sound refers to the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process; adjust one of the robot's cleaning mode and movement mode according to the first adjustment parameter. Determine the corresponding first adjustment parameter based on the recognition result, and adjust the robot's mode according to the first adjustment parameter, so as to realize the robot's flexible response in different scenarios, thereby avoiding damage to living objects and improving cleaning efficiency. Brief Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the specific embodiments of the present invention or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 is an application environment diagram of the robot's exception handling method in one embodiment; Figure 2 is a flowchart of the robot's exception handling method in one embodiment; Figure 3 is a flowchart of obtaining the first adjustment parameter in one embodiment; Figure 4 is a structural block diagram of the robot's exception handling device in one embodiment; Figure 5 is a structural block diagram of the robot's exception handling device in another embodiment; Figure 6 is an internal structure diagram of a computer device in one embodiment. Detailed Description

[0018] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0019] It should be noted that the terms "first," "second," etc. in the specification, claims, and above-mentioned drawings of the present invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] In this invention, unless otherwise stated, directional terms such as "upper," "lower," "top," and "bottom" generally refer to the direction shown in the accompanying drawings, or to the vertical, perpendicular, or gravitational direction of the component itself; similarly, for ease of understanding and description, "inner" and "outer" refer to the inner and outer contours relative to the individual components, but these directional terms are not intended to limit the invention.

[0021] The robot anomaly handling method provided in this application embodiment can be applied to the application environment shown in Figure 1. The robot 102 performs speech recognition on the sound information collected by the robot to obtain a recognition result. When the recognition result indicates that the sound information is a first abnormal sound, and the sound information is collected by the robot during the cleaning process, a first adjustment parameter is obtained based on the recognition result. The first abnormal sound refers to the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process. The robot's cleaning mode and movement mode are adjusted according to the first adjustment parameter.

[0022] The robot 102 is a robot capable of performing cleaning tasks, including sweeping robots, mopping robots, or sweeping and mopping robots. The robot 102 is equipped with a recorder, camera, and radar, and can detect living objects through radar.

[0023] In one embodiment, as shown in Figure 2, a robot cleaning method is provided. Taking the application of this method to the robot in Figure 1 as an example, the method includes the following steps: S202, performing speech recognition on the sound information collected by the robot to obtain a recognition result.

[0024] The sound information may include the frequency, decibels, and related speech content, etc. The recognition result can refer to the recognition result of the sound information, which can be used to indicate the source of the sound or the corresponding abnormal scenario represented by the sound information. For example, the recognition result can indicate whether the sound information is a first abnormal sound or a second abnormal sound. The first abnormal sound can refer to the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process. The second abnormal sound is the abnormal sound emitted by the target object when the robot does not cause damage to the target object during the cleaning process.

[0025] For example, the sound information of the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process can be stored in advance as the sound information set corresponding to the first abnormal sound; and the sound information of the abnormal sound emitted by the target object when the robot does not cause damage to the target object during the cleaning process can be stored as the sound information set corresponding to the second abnormal sound. In practical application scenarios, after the robot collects the sound information, the collected sound information can be compared with the pre-built sound information set to determine whether the collected sound information belongs to the first abnormal sound or the second abnormal sound.

[0026] Alternatively, the sound information corresponding to the first abnormal sound and the second abnormal sound can be collected in advance as samples to train a speech recognition model. This model can then be used to perform speech recognition on the sound information collected by the robot, obtaining the recognition result. The speech recognition model refers to a machine learning model used for speech recognition, including but not limited to models based on ASRT (Auto Speech Recognition Tool) and Deep Speech.The speech recognition model is constructed using speech recognition algorithms such as Recognition (Deep Speech Recognition, DSR), Wenet, and Whisper.

[0027] S204, when the recognition result indicates that the sound information is the first abnormal sound, and the sound information is obtained by the robot during the cleaning process, the first adjustment parameter is obtained based on the recognition result; the first abnormal sound refers to the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process. Specification 4 / 11 pages 7 CN 121512385 A

[0028] The target object refers to the object that emits the sound information, including pets, infants, minors, the elderly, and pregnant women, etc.

[0029] The cleaning process can refer to the process by which the robot performs cleaning on a designated work area. The cleaning mode is the cleaning method adopted by the robot during the cleaning process, and the motion mode can be the operating mode performed by the robot during the cleaning process. Preferably, the cleaning mode can be adjusted by adjusting the cleaning parameters, such as the rotation speed of the side brush, the vibration frequency of the mop disc, and other parameters related to the robot's cleaning work. Correspondingly, the achievable cleaning modes can be reduced side brush speed, stopped mop disc vibration, etc. The motion mode can be adjusted by adjusting the robot's motion parameters, such as the roller rotation speed, roller direction, etc. Correspondingly, the achievable motion modes can be deceleration, turning, stopping, backward movement, etc. The first adjustment parameter can at least include cleaning parameters, motion parameters, etc., to at least achieve the adjustment of the robot's cleaning mode and motion mode.

[0030] The adjustment parameters corresponding to different recognition results can be preset. For example, the adjustment parameters corresponding to the first abnormal sound and the second abnormal sound can be preset. For ease of distinction, the adjustment parameter corresponding to the first abnormal sound can be described as the first adjustment parameter, and the adjustment parameter corresponding to the second abnormal sound can be described as the second adjustment parameter. Of course, the adjustment parameters corresponding to different recognition results can also be adjusted in conjunction with other factors in the actual application scenario, which is not limited here.

[0031] The first adjustment parameter and the second adjustment parameter obtained according to the recognition result may include parameter type and parameter value or parameter adjustment method (such as increase or decrease) corresponding to the parameter type. For example, after determining that the recognition result is the first abnormal sound, the side brush speed can be reduced, the roller speed can be reduced, or the roller direction can be adjusted, etc.; correspondingly, the first adjustment parameter may be the side brush speed and the speed value to which the side brush speed is adjusted, the roller speed and the speed value to which the roller speed is adjusted, the roller direction and the direction value of the roller direction adjustment value, etc.

[0032] S206, adjust one of the robot's cleaning mode and motion mode according to the first adjustment parameter.

[0033] The above-mentioned abnormal handling method for the robot performs speech recognition on the sound information collected by the robot. After determining that the sound information used is an abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process, the robot adjusts one of its cleaning mode and movement mode according to the first adjustment parameter, such as reducing the side brush speed or changing the roller direction, to effectively reduce the possibility of the robot causing damage to the living object during the cleaning process and realize the robot's autonomous response to abnormal situations.

[0034] In one embodiment, the parameter type corresponding to the first adjustment parameter may include the robot's roller speed and the roller speed adjustment value, the roller direction and the direction value of the roller direction adjustment value. Accordingly, the robot can be controlled to decelerate, pause movement or change the direction of movement according to the first adjustment parameter. After determining that the sound information used is an abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process, timely control of the robot to decelerate, pause movement or change the direction of movement can effectively reduce the possibility of further damage to the target object.

[0035] In one embodiment, as shown in FIG3, the step of obtaining the first adjustment parameter includes: S302, when the identification result indicates that the sound information is the first abnormal sound and the sound information is obtained by the robot during the cleaning process, the robot's operating parameters are detected to obtain the detection result.

[0036] Wherein, the operating parameters may refer to parameters related to the robot's operation, including the robot's posture and the rotation speed of the side brush, the rotation speed of the roller brush motor, or the rotation speed of the fan motor, etc. The parameter types of the operating parameters, cleaning parameters, and motion parameters may overlap. The detection result may refer to the judgment result of whether the robot has caused damage to the target object. By analyzing the actual operating data of the robot, it is possible to more accurately confirm whether the robot has caused damage to the target object that emitted the sound information during the cleaning process. If it is determined that damage has been caused, the robot's cleaning mode or motion mode can be further adjusted, which can effectively avoid misadjustment and improve the accuracy of the robot's autonomous response to abnormal situations.

[0037] In one embodiment, the operating parameters include at least one of the robot's roller brush current or the robot's posture. Here, "brush current" refers to the current of the brush motor. "Machine posture" refers to the robot's orientation, which can be represented by the robot's coordinates and orientation on a world map; however, it can also be based on other types of map representations, which are not limited here. During the cleaning process, if pets such as cats and dogs, or infants, are squeezed or their fur gets caught, the probability of the robot's brush current changing is relatively high. Furthermore, as the pets or infants wriggle, the robot's posture changes accordingly.The probability is also relatively high. Therefore, by further combining the robot's brush current or machine posture to detect whether the robot has caused damage to the target object that emits the sound information during the cleaning process, the accuracy of determining whether damage has been caused can be further improved, effectively avoiding misadjustment, and thus improving the accuracy of the robot's autonomous response to abnormal situations.

[0038] In one embodiment, the machine posture can be compared with each sample posture in a preset posture sample set; wherein, the sample posture is the robot posture in which the probability of the robot causing damage to the target object during the cleaning process is greater than a preset value; the comparison result determines whether the robot has caused damage to the target object that emits the sound information during the cleaning process. The preset posture sample set can refer to a set of sample postures set in advance. The sample posture is the robot posture in which the probability of the robot causing damage to the target object during the cleaning process is greater than a preset value. The preset value can refer to a preset probability value. The comparison result can refer to the result obtained after comparing the machine posture with the sample posture. By using the preset robot posture in which the probability of causing damage to the target object is greater than a preset value as the sample posture, in actual scenarios, by comparing the actual machine posture with the sample posture, the accuracy and efficiency of confirming damage to the target object can be further improved.

[0039] In one embodiment, when it is determined that the target object is in contact with the robot, the step of detecting the robot's operating parameters is performed.

[0040] For example, the target object can be tracked to obtain its position. When the distance between the target object's position and the robot's position is less than a contact distance threshold, it is determined that the target object is in contact with the robot, and the step of detecting the robot's operating parameters is performed.

[0041] Wherein, the contact distance threshold can refer to a threshold used to determine whether the target object is in contact with the robot. For example, the contact distance threshold can be 5cm, 10cm, and 20cm.

[0042] Alternatively, the target object can also be detected by sensors on the robot. When the sensors on the robot detect the target object, it is determined that the target object is in contact with the robot, and the step of detecting the robot's operating parameters is performed.

[0043] In the above embodiment, by determining that the target object is in contact with the robot and then performing the step of detecting the robot's operating parameters, false detections can be reduced. For example, if the target object is far away, abnormal operating parameters may occur during the robot's cleaning process, in which case there is no risk of injury.

[0044] S304, if the detection result indicates that the robot caused damage to the target object emitting the sound information during the cleaning process, the first adjustment parameter is obtained based on the recognition result.

[0045] For example, if the current operating parameters of the robot are: mode: sweeping mode, speed: 0.05m / s, direction: southwest, and the first adjustment parameter is speed: -0.02m / s, direction: north, then the robot's operating parameters are adjusted according to the first adjustment parameter.The adjusted operating parameters are: mode: sweeping mode, speed: 0.03m / s, direction: north, thereby controlling the robot's deceleration and movement direction after the operating parameters are adjusted.

[0046] In one embodiment, S304 includes determining that the robot has caused damage to the target object emitting the sound information if the brush current is less than a first current threshold or greater than a second current threshold; or, determining that the robot has caused damage to the target object emitting the sound information if the robot posture matches the sample posture in the preset posture sample specification 6 / 11 page 9 CN 121512385 A set.

[0047] Wherein, the current threshold can be used to determine the brush current, the first current threshold and the second current threshold are different current thresholds, and the first current threshold is not greater than the second current threshold.

[0048] In one embodiment, if the robot does not cause damage to the target object emitting the sound information during the cleaning process, the robot can also be controlled to reduce the brush speed. Wherein, the brush speed can refer to the rotation speed of the brush. Although further testing showed that the robot did not harm the target object, the target object might have been too close to the robot or the high cleaning frequency of the robot might have frightened the target object. By controlling the robot to reduce the speed of the brush, it is possible to further and effectively avoid the robot from harming the target object.

[0049] In the above embodiment, when the recognition result indicates that the sound information is a first abnormal sound and the sound information is collected by the robot during the cleaning process, the robot's operating parameters are detected to obtain the detection result; when the detection result indicates that the robot has harmed the target object that emitted the sound information during the cleaning process, the first adjustment parameter is obtained based on the recognition result, thus realizing an accurate judgment of whether the robot has harmed the target object that emitted the sound information, and accurately obtaining the first adjustment parameter based on the recognition result.

[0050] In one embodiment, when the identification result indicates that the sound information is a second abnormal sound, the location of the target object emitting the sound information is tracked to obtain the location of the target object; the second abnormal sound is an abnormal sound emitted by the target object when the robot does not cause harm to the target object during the cleaning process; a reminder message carrying the location is sent to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera. By judging the abnormal sound emitted by the target object when no harm is caused to the target object, timely communication with the target object that emitted the abnormal sound can further expand the robot's autonomous response and handling capabilities for abnormal situations and improve the user experience.

[0051] Wherein, the monitored object can refer to the object that monitors the target object, including the target object's guardian, spouse, caregiver, etc. The reminder message can refer to a message used to remind the monitored object.

[0052] In one embodiment, tracking the location of the target object emitting sound information to obtain the location of the target object includes: determining the relative direction of the target object emitting sound information, where the relative direction is the direction of the target object relative to the robot.

[0053] In one embodiment, sending a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera, includes: sending the relative direction of the target object and the current position of the robot to the terminal corresponding to the monitored object, so that the terminal corresponding to the monitored object can control the home camera or the robot's camera to aim at the target object based on the relative direction of the target object and the current position of the robot, and the monitored object can interact with the target object through the home camera or the robot's camera.

[0054] In one embodiment, sound information is collected during the cleaning process to obtain sound information; or, sound information is collected when the robot is stationary at the robot base station to obtain sound information; or, sound information is collected when the robot is placed at the target position to obtain sound information; or, sound information is collected when the robot moves to the designated position to obtain sound information.

[0055] Wherein, the target position can refer to the position used to place the robot. The designated position can refer to a pre-specified position. Both the target position and the designated position can be represented by coordinates.

[0056] As an example, this embodiment is as follows: Scenario 1: Cleaning abnormality caused by the robot vacuum cleaner: When the robot vacuum cleaner detects abnormal cries from a pet during the cleaning process, and the brush current or machine posture monitoring is also in an abnormal state, it is determined that the robot has caused harm to the pet. At this time, the motion device is controlled to decelerate, pause, and change direction.

[0057] Scenario 2: Special scene recognition: Even when the robot vacuum cleaner is stationary, it can monitor target sounds, such as monitoring baby crying or elderly people calling, and track abnormal voice information to detect the target object that emits the abnormal voice information. After the target object that emits the abnormal voice information is found, a reminder can be sent to the mobile phone (the abnormal reminder may include information such as the location of the target object), so that the user can interact with the target object through the camera on the robot vacuum cleaner or the camera at home. This realizes the recognition of special scenes, assists users in abnormal monitoring, and improves the user experience. The robot can be monitored at a base station, or it can begin monitoring after being moved to a certain location, or it can begin monitoring (patrolling or stationary) after being moved to a certain location.

[0058] In this embodiment, a speech recognition system is used to recognize linguistic or non-linguistic sounds, such as cat meows, baby cries, painful groans, etc. (e.g., special sound information to be recognized can be collected in advance to build a speech recognition model, etc.; speech(The recognition algorithm is not limited here). Then, based on the recognized sound information, the abnormal working scene of the robot is determined, and the cleaning adjustment operation corresponding to the abnormal working scene is extracted, thereby completing the cleaning adjustment and reducing the damage that may be caused during the cleaning process; and it can also assist the user in completing special scene monitoring.

[0059] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, those skilled in the art can make other different forms of changes or modifications without creative labor, and all of them should fall within the scope of protection of the present invention.

[0060] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown sequentially according to the arrow indication, these steps are not necessarily executed in the order indicated by the arrow. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0061] Based on the same inventive concept, the embodiments of this application also provide a robot exception handling device for implementing the robot exception handling method involved above. The solution to the problem provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more robot exception handling device embodiments provided below can be found in the limitations of the robot exception handling method above, and will not be repeated here.

[0062] In one embodiment, as shown in FIG4, an anomaly handling device for a robot is provided, including: an identification module 402, an acquisition module 404, and an adjustment module 406, wherein: the identification module 402 is used to perform speech recognition on the sound information collected by the robot to obtain an identification result; the acquisition module 404 is used to acquire a first adjustment parameter based on the identification result when the identification result indicates that the sound information is a first abnormal sound and the sound information is collected by the robot during the cleaning process; the first abnormal sound refers to the abnormal sound emitted by the target object when the robot causes damage to the target object during the cleaning process; the adjustment module 406 is used to adjust one of the robot's cleaning mode and movement mode according to the first adjustment parameter. In one embodiment, the adjustment module 406 is also used to control the robot to decelerate, pause movement, or change the direction of movement according to the first adjustment parameter.

[0063] In one embodiment, the acquisition module 404 is also used to acquire a first adjustment parameter when the identification result indicates that the sound information is a first abnormal sound,Furthermore, when the sound information is collected by the robot during the cleaning process, the robot's operating parameters are detected to obtain the detection result (page 8 / 11, CN 121512385 A). If the detection result indicates that the robot has caused damage to the target object emitting the sound information during the cleaning process, the first adjustment parameter is obtained based on the recognition result.

[0064] In one embodiment, the acquisition module 404 is further used to include at least one of the robot's brush current and machine posture as operating parameters.

[0065] In one embodiment, the acquisition module 404 is further used to perform the step of detecting the robot's operating parameters when it is determined that the target object is in contact with the robot. In one embodiment, as shown in FIG5, the robot's abnormal handling device further includes: a control module 608, a determination module 610, and an interaction module 612, wherein: the control module 408 is used to control the robot to reduce the brush speed if the robot has not caused damage to the target object emitting the sound information during the cleaning process.

[0066] The determination module 410 is used to compare the machine posture with each sample posture in the preset posture sample set; wherein, the sample posture is the robot posture in which the probability of the robot causing damage to the target object during the cleaning process is greater than a preset value; and determines whether the robot has caused damage to the target object that emitted the sound information during the cleaning process based on the comparison result.

[0067] The interaction module 412 is used to perform position tracking on the target object that emitted the sound information when the recognition result indicates that the sound information is a second abnormal sound, and obtain the position of the target object; the second abnormal sound is the abnormal sound emitted by the target object when the robot has not caused damage to the target object during the cleaning process; and sends a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera.

[0068] In one embodiment, the interaction module 412 is also used to determine the relative direction of the target object that emitted the sound information, and the relative direction is the direction of the target object relative to the robot.

[0069] In one embodiment, the interaction module 412 is further configured to send the relative direction of the target object and the current position of the robot to the terminal corresponding to the monitored object, so that the terminal corresponding to the monitored object controls the home camera or the robot's camera to aim at the target object based on the relative direction of the target object and the current position of the robot, and the monitored object interacts with the target object through the home camera or the robot's camera.

[0070] In one embodiment, the interaction module 412 is further configured to collect sound information during the cleaning process; or, collect sound information when the robot is stationary at the robot base station; or, collect sound information when the robot is placed at the target position; or, collect sound information when the robot moves to the designated position.Sound information is collected in real time to obtain sound information. In the above embodiment, the sound information collected by the robot is subjected to speech recognition to obtain the recognition result; the collected sound information is accurately recognized, and when the recognition result indicates that the sound information is a first abnormal sound and the sound information is obtained by the robot in the cleaning process, the first adjustment parameter is obtained according to the recognition result; the first abnormal sound refers to the abnormal sound emitted by the target object when the robot causes damage to the target object in the cleaning process; the robot's cleaning mode and movement mode are adjusted according to the first adjustment parameter. The corresponding first adjustment parameter is determined according to the recognition result, and the robot's mode is adjusted according to the first adjustment parameter, so as to realize the robot's flexible response in different scenarios, thereby avoiding damage to living objects and improving cleaning efficiency.

[0071] Each module in the above robot's abnormal handling device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in the processor of the computer device in hardware form or independent of the processor, or stored in the memory of the computer device in software form, so that the processor can call and execute the operation corresponding to each module.

[0072] In one embodiment, a computer device is provided, which may be a robot, and its internal structure can be as shown in Figure 6. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through WIFI, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an exception handling method for the robot. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an e-ink display screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad set on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0073] Those skilled in the art will understand that the structure shown in FIG6 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0074] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0075] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the above-described method embodiments.

[0076] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0077] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0078] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Any references to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM).Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc. The databases involved in the various embodiments provided in this application may include at least one of relational databases and non-relational databases. Non-relational databases may include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited thereto.

[0079] The technical features of the above embodiments can be combined arbitrarily. In order to simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered as within the scope of this specification.

[0080] The above embodiments only express several implementation methods of this application. The descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent of this application. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims. Specification 11 / 11 pages 14 CN 121512385 A Figure 1 Figure 2 Specification Drawings 1 / 3 pages 15 CN 121512385 A Figure 3 Figure 4 Figure 5 Specification Drawings 2 / 3 pages 16 CN 121512385 A Figure 6 Specification Drawings 3 / 3 pages 17 CN 121512385 A ROBOT ABNORMALITY PROCESSING METHOD, APPARATUS, COMPUTER DEVICE AND STORAGE MEDIUM Abstract The present invention discloses an abnormality processing method and apparatus for a robot, a computer device, a storage medium, and a computer program product. The method includes: performing speech recognition on sound information collected by the robot toobtain a recognition result; acquiring a first adjustment parameter according to the recognition result when the recognition result indicates that the sound information is a first abnormal sound and the sound information is collected by the robot during a cleaning process, wherein the first abnormal sound refers to an abnormal sound emitted by a target object when the robot causes damage to the target object during the cleaning process; and adjusting one of a cleaning mode and a motion mode of the robot according to the first adjustment parameter. By adopting the method, the robot can be prevented from causing damage to a living object during the cleaning process, thereby also improving cleaning efficiency.

Claims

1. A method for handling anomalies in a robot, characterized in that, The method includes: The robot performs speech recognition on the audio information it collects, and obtains the recognition results. When the recognition result indicates that the sound information is a second abnormal sound, the target object that emitted the sound information is tracked to obtain the location of the target object; the second abnormal sound is an abnormal sound emitted by the target object when the robot does not cause damage to the target object during the cleaning process; Send a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera.

2. The method according to claim 1, characterized in that, The step of tracking the location of the target object that emitted the sound information to obtain the location of the target object includes: Determine the relative direction of the target object emitting the sound information, where the relative direction is the direction of the target object relative to the robot.

3. The method according to claim 2, characterized in that, Sending a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera, includes: The relative direction of the target object and the current position of the robot are sent to the terminal corresponding to the monitored object, so that the terminal corresponding to the monitored object controls the home camera or the robot's camera to aim at the target object based on the relative direction of the target object and the current position of the robot, and the monitored object interacts with the target object through the home camera or the robot's camera.

4. The method according to claim 1, characterized in that, The method further includes: Sound information is collected during the cleaning process to obtain the sound information; or... The sound information is collected when the robot is stationary at the robot base station; or... The robot collects sound information when it is placed at the target location; or... When the robot moves to the designated position, sound information is collected to obtain the sound information.

5. The method according to claim 1, characterized in that, The process of performing speech recognition on the sound information collected by the robot to obtain the recognition result includes: The collected sound information is compared with a pre-built sound information set to determine whether the collected sound information belongs to the second abnormal sound.

6. The method according to claim 1, characterized in that, The process of performing speech recognition on the sound information collected by the robot to obtain the recognition result includes: The robot uses a speech recognition model to perform speech recognition on the sound information it collects, and obtains the recognition results.

7. An anomaly handling device for a robot, characterized in that, The device includes: The recognition module is used to perform speech recognition on the sound information collected by the robot and obtain the recognition result. The interaction module is used to track the location of the target object that emitted the sound information when the recognition result indicates that the sound information is a second abnormal sound, and to obtain the location of the target object; the second abnormal sound is an abnormal sound emitted by the target object when the robot does not cause damage to the target object during the cleaning process; and to send a reminder message carrying the location to the terminal corresponding to the monitored object, so that the monitored object can interact with the target object through a home camera or the robot's camera.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images