Alarm method, device and equipment for robot and storage medium

Abstract

The present disclosure provides a warning method, device, equipment and storage medium for a robot. The method comprises: receiving abnormal information from a first robot, the abnormal information indicating that the first robot has an abnormal event. Based on the abnormal information, reference information related to the abnormal event is obtained, the reference information indicating at least one of the following: a cause of the abnormal event or a processing strategy for the abnormal event. A warning information about the first robot having the abnormal event is presented, the warning information being generated based on the reference information and running information of the first robot using a first machine learning model. In this way, relevant warning information related to the cause of the abnormal event or the processing strategy can be provided for the user, so as to facilitate the user to maintain the robot according to the reference information. Thus, the efficiency of maintaining the robot is improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to alarm methods, apparatuses, devices, and computer-readable storage media for robots. Background Technology

[0002] In recent years, robotics technology has developed rapidly and has been widely used in various technical fields. For example, on factory production lines, robots can perform various tasks such as sorting and handling. To ensure the normal operation of robots, maintenance is necessary. However, current robot maintenance methods still have some problems that affect their working efficiency. Summary of the Invention

[0003] In a first aspect of this disclosure, an alarm method for a robot is provided. The method includes: receiving abnormal information from a first robot, the abnormal information indicating that an abnormal event has occurred on the first robot; based on the abnormal information, obtaining reference information related to the abnormal event, the reference information indicating at least one of the following: the cause of the abnormal event or a handling strategy for the abnormal event; and presenting alarm information regarding the abnormal event occurring on the first robot, the alarm information being generated using a first machine learning model based on the reference information and the operating information of the first robot.

[0004] In a second aspect of this disclosure, an apparatus for alarming a robot is provided. The apparatus includes: a receiving module configured to receive abnormal information from a first robot, the abnormal information indicating an abnormal event has occurred in the first robot; an acquiring module configured to acquire reference information related to the abnormal event based on the abnormal information, the reference information indicating at least one of the following: the cause of the abnormal event or a handling strategy for the abnormal event; and a presenting module configured to present alarm information regarding the abnormal event occurring in the first robot, the alarm information being generated using a first machine learning model based on the reference information and the operating information of the first robot.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram is shown of an example environment in which embodiments of the present disclosure may be implemented;

[0011] Figure 2 Example exception information according to some embodiments of this disclosure is shown;

[0012] Figures 3A to 3C A schematic diagram of a first example interface for presenting alarm information according to some embodiments of the present disclosure is shown;

[0013] Figures 4A to 4B A schematic diagram of a second example interface for presenting alarm information according to some embodiments of the present disclosure is shown;

[0014] Figures 5A to 5B A schematic diagram of an example interface for presenting abnormal statistics information according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A flowchart illustrating an example process for issuing alarms to a robot according to some embodiments of this disclosure is shown;

[0016] Figure 7 A schematic structural block diagram of an example device for alarming robots according to some embodiments of the present disclosure is shown; and

[0017] Figure 8 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0020] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0021] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0022] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0023] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require the acquisition and use of the user's information. This allows the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein, based on the prompt message.

[0024] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0025] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure. The activation of digital assistant-related functions, the acquisition of data, the processing and storage of data, etc., in the embodiments of this disclosure shall all require prior authorization from the user and other rights holders associated with the user, and shall comply with the agreements and rules between relevant laws and regulations and rights holders.

[0026] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0027] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Multiple robots are deployed in environment 100, such as a first robot 110-1, a second robot 110-2, and a third robot 110-3, etc. The first robot 110-1, the second robot 110-2, and the third robot 110-3 may also be collectively referred to as robot 110 or individually. Hereinafter, an example embodiment of path planning will be described using the first robot 110-1 as an example. Each robot 110 may be deployed with a control device to control the operation of that robot. For example, such as... Figure 1 As shown, control devices 120-1, 120-2, and 120-3 are respectively deployed at the first robot 110-1, the second robot 110-2, and the third robot 110-3. They can also be collectively referred to as control device 120 or individually. Figure 1 The number of robots and control devices shown are merely illustrative and are not intended to be any limitation.

[0028] In embodiments of this disclosure, robot 110 can be used for various suitable purposes, such as a transport robot for delivering goods, and control device 120 can be used to control robot 110 to perform tasks. For example, robot 110 can perform parcel delivery services. In this case, control device 120 can obtain information such as the parcel's origin, destination, recipient, and recipient's contact information. In some embodiments, control device 120 can control robot 110 based on control commands it generates. In some embodiments, control device 120 can control the operation of robot 110 based on control commands sent by server 130.

[0029] Server 130 can be used to implement or deploy a robot management platform 150 for managing robot 110. Robot management platform 150 can acquire operational information of each robot (such as robot status, tasks performed by the robot, etc.) and assign tasks to the robots. For example, robot management platform 150 can receive relevant data for each task and remotely control the operation of robot 110. Control device 120 collects data from robot 110 (including robot 110 operational data or robot 110 fault information) and communicates with robot management platform 150 via a network to send the data to robot management platform 150. Robot management platform 150 determines control commands for robot 110 based on the acquired data and sends the control commands to control device 120.

[0030] In some embodiments, robot 110 can connect to and communicate with server 130 via a network. Robot 110 can send relevant data about the various tasks it performs to server 130 in real time. Server 130 can then present the acquired data to a user. Figure 1In environment 100, terminal device 140 can present alarm information for robot 110 (such as robot malfunction, robot task failure, etc.) through an application or webpage. In some embodiments, terminal device 140 communicates with server 130 to obtain alarm information for robot 110. Terminal device 140 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 140 can also support any type of user-facing interface (such as "wearable" circuitry).

[0031] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide background services for applications or web pages in terminal device 140 that support displaying alarm information. A communication connection can be established between server 130 and terminal device 140. The communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth connections, mobile network connections, Universal Serial Bus (USB) connections, Wireless Fidelity (WiFi) connections, etc., and the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and terminal device 140 can achieve signaling interaction through the communication connection between them.

[0032] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0033] As briefly described above, robots are widely used in various technical fields. If an anomaly occurs during robot operation (such as robot malfunction or task failure), the robot will report a corresponding exception code. Maintenance personnel need to determine maintenance strategies for these anomalies based on their experience and the exception codes to ensure the robot's normal operation. However, this approach requires significant manpower and is relatively inefficient. In some scenarios (e.g., those with a large number of robots), insufficient maintenance personnel may prevent timely robot maintenance, impacting the normal operation of the robots in the scenario.

[0034] In view of this, embodiments of the present disclosure propose a scheme for alarming a robot. The scheme includes: receiving abnormal information from a first robot, the abnormal information indicating that an abnormal event has occurred in the first robot; based on the abnormal information, obtaining reference information related to the abnormal event, the reference information indicating at least one of the following: the cause of the abnormal event or a handling strategy for the abnormal event; and presenting alarm information regarding the abnormal event occurring in the first robot, the alarm information being generated using a first machine learning model based on the reference information and the operating information of the first robot.

[0035] As will be more clearly understood from the following description, according to the scheme disclosed herein, by utilizing a machine learning model, alarm information can be generated and presented to the user based on the cause of an anomaly or the handling strategy for the anomaly. In this way, alarm information related to the cause of the anomaly or the handling strategy can be provided to the user, facilitating the robot's maintenance based on the reference information. This improves the efficiency of the maintenance robot.

[0036] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0037] Example Interaction

[0038] The robot management platform 150 can receive information from multiple robots 110. For a specific robot among the multiple robots (e.g., the first robot 110-1), the first robot 110-1 sends an exception message to the robot management platform 150 in the event of an abnormal event. In some embodiments, the abnormal event can be a malfunction of the first robot 110-1 (e.g., low battery, abnormal communication module status), or a failure to perform a task (e.g., prolonged lingering at an elevator entrance, prolonged picking time). The exception message indicates the abnormal event that occurred in the first robot 110-1. For example, the exception message may include an exception code. The first robot 110-1 determines the exception code corresponding to its own abnormal event based on the correspondence between multiple abnormal events and multiple predetermined exception codes. In some embodiments, the first robot 110-1 can generate an exception code by encoding its own abnormal event. Abnormal information may also include robot operation information related to the abnormal event, in order to more accurately identify the abnormal event that has occurred.

[0039] In some embodiments, reference information related to the anomaly information can be obtained based on the anomaly information. The reference information includes at least the cause of the anomaly or a handling strategy for the anomaly. In some embodiments, the reference information can be presented to the user through the terminal device 140 so that the user can maintain the robot according to the reference information.

[0040] In some embodiments, the received anomaly information can be processed using a machine learning model (e.g., a language model) to determine reference information corresponding to the anomaly information. In some embodiments, a predetermined database can be used to determine the reference information corresponding to the anomaly information. The database includes at least a number of predetermined reference information related to historical failures of the robot; for example, the predetermined reference information may include the cause or solution of a failure in a historical failure of the first robot 110-1. If the received anomaly information includes an anomaly code, the predetermined reference information corresponding to that anomaly code (i.e., the anomaly code included in the anomaly information) can be determined from the multiple predetermined reference information based on the correspondence between the multiple predetermined reference information and the multiple anomaly codes. In this way, reference information related to the anomaly event can be accurately determined.

[0041] Since multiple robots exist in the scenario, different robots may experience the same abnormal events. For example, if an elevator malfunctions, multiple robots may exhibit the "elevator waiting time is too long" abnormal event. The robot management platform 150 may receive multiple identical exception codes from different robots. Furthermore, during the user's maintenance of the first robot 110-1, the first robot 110-1 may frequently send the same abnormal information, resulting in a waste of computing resources. Therefore, the received abnormal information can be filtered. In some embodiments, abnormal information can be filtered based on the source of the abnormal information. For example, identical abnormal information from the same robot can be filtered. In some embodiments, multiple abnormal information received within a certain period (e.g., 3 minutes) can be stored as historical abnormal information. If an abnormal information sent by a robot is detected, it is first determined whether the multiple historical abnormal information includes an abnormal information that matches the abnormal information. If no historical abnormal information matching the abnormal information is detected, reference information corresponding to the abnormal information is obtained.

[0042] If, after receiving an anomaly message from the first robot and displaying an alarm message for the first robot, it is detected that a second robot (one of multiple robots) sends the same anomaly message as the first robot (i.e., the second robot experiences the same anomaly event as the first robot), an indication that the second robot experienced the anomaly message can be added to the alarm message corresponding to the first robot 110-1, without executing the alarm message generation step again. This prevents the platform from processing the same anomaly message from robots multiple times, reducing the waste of computing resources.

[0043] In some embodiments, alarm information is generated using a first machine learning model (e.g., a language model) based on reference information and the operational information of the first robot 110-1. Subsequently, alarm information regarding an abnormal event occurring in the first robot 110-1 is presented. The operational information of the first robot 110-1 includes the task performed by the first robot 110, the location of the first robot 110-1, and the state of the first robot 110-1. Based on the reference information and the operational information of the first robot 110-1, a second prompt message is generated for the first machine learning model to obtain the output of the first machine learning model. Based on the output of the first machine learning model, alarm information is generated and presented.

[0044] Different types of abnormal events have varying impacts on the robot, and their maintenance difficulty also differs. During robot operation, some abnormal events may have minor impacts or be self-recoverable; these types of abnormal events do not require alarm notifications. In some embodiments, a first machine learning model can determine whether to present alarm notifications. For a given abnormal event, content related to "not presenting alarm notifications" can be added to predetermined reference information (e.g., processing strategy) corresponding to that abnormal event. In this case, the generated second prompt message can instruct the first machine learning model to determine whether to issue an alarm for the abnormal event based on the processing strategy. If it is detected that an alarm notification can be determined from the output of the first machine learning model, then an alarm notification is presented.

[0045] In some embodiments, alarm information may include text. Figure 2 Example exception information according to some embodiments of this disclosure is shown. Figure 2 As shown, the abnormal information may include abnormal information (e.g., an abnormal code) and reference information 220. Reference information 220 may include the cause of the abnormal event occurring on the robot, historical processing methods related to the abnormal event, etc. In some embodiments, if the abnormal information received from the first robot 110-1 includes the abnormal code "0X5204XXXX", indicating that the first robot 110-1 has experienced an abnormal event "waiting too long for the elevator", then the abnormal cause corresponding to the abnormal code is determined as "XXX has occupied the elevator for too long, which may cause an abnormality", and the solution corresponding to the abnormal event is determined as "confirm whether the elevator is faulty; if the elevator is not faulty, the algorithm needs to restart the elevator". In this way, the abnormal cause or solution for the abnormal event occurring on the first robot is presented in the second area, so that the user can quickly and accurately determine the operation that needs to be performed on the first robot for maintenance.

[0046] In some embodiments, there may be situations where the cause or solution to the anomaly related to the abnormal information cannot be determined, or the user cannot maintain the first robot 110-1 based on the presented reference information. Therefore, a robot maintenance platform (e.g., the name of the robot maintenance platform, internet link, etc.) can be presented. The user can obtain maintenance solutions for the first robot 110-1 by accessing the robot maintenance platform. For example, it can be presented as "Requires redirection to XXX platform for processing, platform address: XXXX".

[0047] In some embodiments, alarm information may include structured cards. Structured cards may include anomaly information, reference information, and robot operation information, etc. In some embodiments, different types of structured cards may be presented for different types of anomaly events. For example, anomaly events may be classified based on their severity; for example, anomaly events may include regular anomalies, emergency anomalies, etc. In this case, structured cards of different colors may be used to present alarm information. For example, anomaly events may be classified based on the object in which the anomaly event occurs; for example, robot hardware failure, robot task execution failure, etc. In some embodiments, firstly, based on the type of anomaly event, a target card type is determined from multiple card types according to the correspondence between multiple card types and multiple anomaly event types. Subsequently, structured cards may be generated using a first machine learning model based on reference information, operation information, and the target card type. For example, descriptive information related to the target card type (or a card template corresponding to the target card type) may be determined first. The descriptive information, reference information, and operation information of the target card type are provided to the first machine learning model to obtain the output of the first machine learning model. Subsequently, structured cards are determined based on the output of the first machine learning model.

[0048] Figures 3A to 3C Schematic diagrams are shown of first example interfaces 300A to 300C for presenting alarm information according to some embodiments of the present disclosure. Figure 3AAs shown, interface 300A illustrates a first example interface for presenting alarm information indicating a robot malfunction. Interface 300A includes a first alarm area 310 and a second alarm area 320. The first alarm area 310 may present summary information about the abnormal event, such as "excessive dwell time," "elevator resource occupancy," or "inconsistent picking status." The second alarm area 320 may present details of the alarm information. For example, the second alarm area may include the name, location, and identification code of the robot (e.g., the first robot 110-1) where the abnormal event occurred, so that the user can identify the robot with the abnormal event from among multiple robots in the scene based on the alarm information. The second alarm area may include the operating information of the first robot 110-1, such as the task identification code of the first robot 110-1, the system information of the first robot 110-1 (e.g., system version), and the task information that the first robot 110-1 is performing. The second alarm area 320 may include solutions for the abnormal information of the first robot 110-1, so that the user can maintain the robot according to the solutions. For example, the second alarm area 320 may include messages such as "Please check and process this order" or "Please confirm whether the elevator is online or malfunctioning. If the elevator is not malfunctioning, the algorithm needs to be restarted." In some embodiments, the second alarm area 320 may include annotation information for abnormal events. The annotation information may include the occurrence time of the abnormal event, the severity of the abnormal event, etc. For example, the annotation information may include "Delivery order XXXX95 has been in an order-in-delay state for 60 minutes," etc. Users can determine the resolution strategy and processing time for the corresponding abnormal events based on the annotation information, thereby ensuring the normal operation of the robot.

[0049] To further improve robot maintenance efficiency, alarm information may include one or more controls corresponding to one or more instructions, which users can trigger to execute robot-related shortcut operation instructions. For example, shortcut operation instructions may include "adjust to cloud platform," "robot restart," and "order recovery," etc. If a trigger for the "robot restart" control is detected, the first robot 110-1 is restarted. In some embodiments, one or more shortcut operation instructions corresponding to the reference information can be determined from a predetermined plurality of shortcut operation instructions based on the operating information and reference information of the first robot 110-1. The controls provided to the user can be determined based on the correspondence between the solution and the plurality of shortcut operation instructions, or a machine learning model can be used to determine the controls provided to the user. For example, a first prompt message for a first machine learning model can be generated based on the reference information, descriptive information related to at least one candidate instruction (i.e., shortcut operation instruction), and operating information to obtain the output of the first machine learning model. Based on the output of the first machine learning model, one or more instructions from at least one candidate instruction are determined. The descriptive information may include the application scenario of the corresponding candidate instruction (such as the abnormal events that the candidate instruction can handle).

[0050] If a user trigger on a control is detected, one or more parameters for executing the instruction corresponding to that control are first determined. For example, a second machine learning model can be used to determine the parameters for executing the instruction based on the operational information of the first robot 110-1 (such as task information performed by the first robot 110-1). Then, based on the determined parameters, the instruction corresponding to the control is executed.

[0051] In some embodiments, the controls included in the alarm information can be presented in a structured card. For example... Figure 3B As shown, the second alarm area 320 of interface 300B includes a solution strategy of "restarting the algorithm" and a corresponding control 330-1. Control 330-1 is used to restart the robot. The second alarm area also includes a control 330-2 for redirecting to the "XX Cloud Platform". If restarting the robot fails to resolve the abnormal event of the current first robot 110-1, redirection to the "XX Cloud Platform" will be performed for further technical support. Figure 3C As shown, interface 300C includes a solution strategy of "performing a warehouse order recovery operation" and a control 330-3 for recovering orders. In some embodiments, the structured card includes controls 340-1 and 340-2 for receiving feedback information, used to obtain user feedback on whether the alarm information is effective.

[0052] Figures 4A to 4BSchematic diagrams of second example interfaces 400A and 400B for presenting alarm information according to some embodiments of the present disclosure are shown. Interfaces 400A and 400B are used to present alarm information indicating that the first robot 110-1 has failed to perform a task. The first and second example interfaces are presented in different forms (e.g., colors, graphics, etc.). Figure 4A and Figure 4B As shown, the alarm information includes the identifier and address of the first robot 110-1, the task it was performing, and the specific details of the abnormal event (i.e., the error information in interface 400A). The alarm information also includes the reason for the task failure and the solution.

[0053] In some embodiments, to more accurately determine the working status of multiple robots in a scene, abnormal events occurring in multiple robots can be statistically analyzed. For example, if a predetermined statistical period is detected, or a statistical request sent by a user is received, statistical results of abnormal events occurring in multiple robots within a predetermined time period are obtained to generate abnormal statistical information for multiple robots. This abnormal statistical information is then presented in the form of structured cards. For example, the statistical period can be set to 24 hours. If the current time is detected to meet the statistical period, abnormal events occurring in robot 110 within this period (i.e., the predetermined time period of 24 hours prior to the current time) are statistically analyzed to generate abnormal statistical information for multiple robots. In some embodiments, abnormal statistical information within a user-specified time period can be obtained based on a statistical request sent by the user. For example, if the statistical request is "statistics on abnormal information from 8:00 to 22:00 in the previous period," then abnormal events occurring within the predetermined time period from 8:00 to 22:00 in the previous period are statistically analyzed. Figure 5A A schematic diagram of an example interface 500A for presenting abnormal statistical information according to some embodiments of the present disclosure is shown. Figure 5A As shown, the system counts the number of times various abnormal events (such as low battery, 4G module malfunction, etc.) occur for each robot (e.g., robot 01, robot 02, and robot 03) within a predetermined time period. This method provides a clear overview of the number of abnormal events occurring across multiple robots and the frequency of different events, facilitating robot maintenance for users. If a user's charging status query request is detected, the charging status of each robot can be displayed. Figure 5B A schematic diagram of an example interface 500B for presenting abnormal statistical information according to some embodiments of the present disclosure is shown. Figure 5B As shown, all robots except the one performing the delivery task are in a charging state. If a robot is detected that is not performing a task and is not charging, it can be manually charged. In some embodiments, options for manually controlling the robots may be provided. Figure 5BAs shown, users can click the robot's recharge control to manually control the robot's charging. For example, if robot 02 is performing a delivery task, the user can click the "Robot 02 Recharge" control to send a charging command to robot 02. After receiving the charging command, robot 02 will execute the charging task. In some embodiments, robot 02 can determine whether to execute the charging command immediately or after the current delivery task is completed, based on the information of the delivery task being performed (such as the time limit of the delivery task, the distance of the delivery task, etc.).

[0054] Example process

[0055] Figure 6 A flowchart illustrating an example process 600 of an alarm method for a robot according to some embodiments of the present disclosure is shown. Process 600 can be implemented at server 130. Reference is made below. Figure 1 To describe process 600.

[0056] like Figure 6 As shown in box 610, server 130 receives abnormal information from the first robot, indicating that an abnormal event has occurred in the first robot.

[0057] In some embodiments, the abnormal event includes at least one of the following: a malfunction of the first robot, or the failure of the first robot to perform a task.

[0058] In box 620, server 130 obtains reference information related to the abnormal event based on the abnormal information, the reference information indicating at least one of the following: the cause of the abnormal event or the handling strategy for the abnormal event.

[0059] In some embodiments, the exception information includes an exception code, and determining the reference information includes: determining, based on the correspondence between multiple predetermined reference information and multiple exception codes, predetermined reference information corresponding to the exception code included in the exception information as reference information related to the exception event.

[0060] In some embodiments, obtaining reference information related to an abnormal event includes: in response to receiving abnormal information, determining historical abnormal information matching the abnormal event from one or more historical abnormal information, wherein the historical abnormal information in one or more historical abnormal information includes abnormal information received within a predetermined time period before receiving the abnormal information; and in response to not detecting historical abnormal information matching the abnormal information, initiating the acquisition of reference information.

[0061] In box 630, server 130 presents alarm information about an abnormal event that occurred in the first robot. The alarm information is generated using a first machine learning model based on reference information and the operating information of the first robot.

[0062] In some embodiments, presenting alarm information regarding an abnormal event occurring in the first robot includes: generating a second prompt message for the first machine learning model based on reference information and operational information to obtain the output of the first machine learning model, wherein the second prompt message instructs the first machine learning model to determine whether to issue an alarm for the abnormal event based on a processing strategy; and presenting the alarm message in response to determining the alarm message from the output of the first machine learning model.

[0063] In some embodiments, the alarm information includes structured cards, and the structured cards are generated by: determining a target card type from multiple card types based on the type of the abnormal event, wherein the multiple card types correspond to multiple abnormal event types respectively; and generating structured cards using a first machine learning model based on reference information, runtime information and the target card type.

[0064] In some embodiments, process 600 further includes: generating first prompt information for a first machine learning model based on reference information, description information related to at least one candidate instruction, and operational information to obtain the output of the first machine learning model, wherein at least one candidate instruction is configured to perform a corresponding operation related to the robot; and determining one or more instructions among the at least one candidate instruction based on the output of the first machine learning model, wherein the alarm information includes one or more controls corresponding to the one or more instructions respectively.

[0065] In some embodiments, process 600 further includes, in response to triggering a control in one or more controls, using a second machine learning model to determine one or more parameters based on runtime information for an instruction corresponding to the triggered control; and executing the instruction corresponding to the triggered control based on the one or more parameters.

[0066] In some embodiments, the first robot is one of a plurality of robots, and the process 600 further includes: generating anomaly statistics for the plurality of robots, the anomaly statistics including statistical results of anomaly events occurring in the plurality of robots within a predetermined time period; and presenting the anomaly statistics in a structured card format.

[0067] In some embodiments, the first robot is one of a plurality of robots, and the process 600 further includes: in response to an abnormal event occurring in a second robot among the plurality of robots, adding an indication that an abnormal event has occurred in the second robot to an alarm message.

[0068] Example devices and equipment

[0069] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 7A schematic structural block diagram of an example device 700 for alarming robots according to certain embodiments of the present disclosure is shown. Device 700 may be implemented as or included in server 130. Various modules / components in device 700 may be implemented by hardware, software, firmware, or any combination thereof.

[0070] like Figure 7 As shown, the device 700 includes a receiving module 710 configured to receive abnormal information from a first robot, the abnormal information indicating that an abnormal event has occurred in the first robot. The device 700 also includes an acquiring module 720 configured to acquire reference information related to the abnormal event based on the abnormal information, the reference information indicating at least one of the following: the cause of the abnormal event or a handling strategy for the abnormal event. The device 700 also includes a presenting module 730 configured to present alarm information regarding the abnormal event occurring in the first robot, the alarm information being generated using a first machine learning model based on the reference information and the operating information of the first robot.

[0071] In some embodiments, the abnormal event includes at least one of the following: a malfunction of the first robot, or the failure of the first robot to perform a task.

[0072] In some embodiments, the exception information includes an exception code, and the acquisition module 720 is further configured to determine, based on the correspondence between multiple predetermined reference information and multiple exception codes, the predetermined reference information corresponding to the exception code included in the exception information as reference information related to the exception event.

[0073] In some embodiments, the acquisition module 720 is further configured to, in response to receiving abnormal information, determine historical abnormal information matching the abnormal event from one or more historical abnormal information, wherein the historical abnormal information in one or more historical abnormal information includes abnormal information received within a predetermined time period before receiving the abnormal information; and in response to not detecting historical abnormal information matching the abnormal information, initiate the acquisition of reference information.

[0074] In some embodiments, the presentation module 730 is further configured to generate a second prompt message for the first machine learning model based on reference information and runtime information, so as to obtain the output of the first machine learning model, wherein the second prompt message instructs the first machine learning model to determine whether to issue an alarm for an abnormal event based on a processing strategy; and to present the alarm message in response to determining the alarm message from the output of the first machine learning model.

[0075] In some embodiments, the alarm information includes structured cards, and the presentation module 730 is further configured to determine a target card type from multiple card types based on the type of the abnormal event, wherein the multiple card types correspond to multiple abnormal event types respectively; and to generate structured cards using a first machine learning model based on reference information, runtime information and the target card type.

[0076] In some embodiments, the apparatus 700 further includes an instruction determination module configured to generate first prompt information for a first machine learning model based on reference information, description information related to at least one candidate instruction, and operational information, to obtain the output of the first machine learning model, wherein at least one candidate instruction is configured to perform a corresponding operation related to the robot; and to determine one or more instructions from at least one candidate instruction based on the output of the first machine learning model, wherein the alarm information includes one or more controls corresponding to one or more instructions respectively.

[0077] In some embodiments, the apparatus 700 further includes an instruction execution module configured to, in response to triggering a control in one or more controls, use a second machine learning model to determine one or more parameters based on runtime information for an instruction corresponding to the triggered control; and execute the instruction corresponding to the triggered control according to the one or more parameters.

[0078] In some embodiments, the first robot is one of a plurality of robots, and the device 700 further includes a statistics module configured to generate anomaly statistics for the plurality of robots, the anomaly statistics including statistical results of anomaly events occurring in the plurality of robots within a predetermined time period; and to present the anomaly statistics in a structured card format.

[0079] In some embodiments, the first robot is one of a plurality of robots, and the apparatus 700 further includes an alarm information adding module configured to add an indication of an abnormal event to the alarm information in response to an abnormal event occurring in a second robot among the plurality of robots.

[0080] like Figure 8 As shown, electronic device 800 is in the form of a general-purpose electronic device. Components of electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 800.

[0081] Electronic device 800 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 820 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 830 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 800.

[0082] Electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 8 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 820 may include computer program product 825 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0083] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 800 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 800 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0084] Input device 850 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 860 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 800 can also communicate with one or more external devices (not shown) via communication unit 840 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 800, or with any device that enables electronic device 800 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0085] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0086] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0087] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0088] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0090] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An alarm method for robots, comprising: Receive abnormal information from the first robot, the abnormal information indicating that an abnormal event has occurred in the first robot; Based on the anomaly information, obtain reference information related to the anomaly event, wherein the reference information indicates at least one of the following: the cause of the anomaly event or the handling strategy for the anomaly event; as well as An alarm message is presented regarding the occurrence of the abnormal event in the first robot. The alarm message is generated using a first machine learning model based on the reference information and the operating information of the first robot.

2. The method according to claim 1, further comprising: Based on the reference information, the descriptive information related to at least one candidate instruction, and the running information, a first prompting information is generated for the first machine learning model to obtain the output of the first machine learning model, wherein the at least one candidate instruction is configured to perform a corresponding operation related to the robot. as well as Based on the output of the first machine learning model, one or more instructions from the at least one candidate instruction are determined, wherein the alarm information includes one or more controls corresponding to the one or more instructions respectively.

3. The method according to claim 2, further comprising: In response to the triggering of a control in one or more of the controls, a second machine learning model is used to determine one or more parameters for the instruction corresponding to the triggered control based on the runtime information; as well as Based on one or more parameters, execute the instruction corresponding to the triggered control.

4. The method according to claim 1, wherein the exception information includes an exception code, and determining the reference information includes: Based on the correspondence between multiple predetermined reference information and multiple exception codes, predetermined reference information corresponding to the exception codes included in the exception information is determined from the multiple predetermined reference information as the reference information related to the exception event.

5. The method of claim 1, wherein presenting alarm information regarding the occurrence of the abnormal event in the first robot includes: Based on the reference information and the running information, a second prompt message is generated for the first machine learning model to obtain the output of the first machine learning model. The second prompt message instructs the first machine learning model to determine whether to issue an alarm for the abnormal event based on the processing strategy. as well as In response to determining the alarm information from the output of the first machine learning model, the alarm information is presented.

6. The method of claim 1, wherein the first robot is one of a plurality of robots, and the method further comprises: Generate abnormal statistical information for the multiple robots, the abnormal statistical information including statistical results of abnormal events that occurred in the multiple robots within a predetermined time period; as well as The abnormal statistics are presented in a structured card format.

7. The method of claim 1, wherein the first robot is one of a plurality of robots, and the method further comprises: In response to the occurrence of the abnormal event in the second robot among the plurality of robots, an indication that the abnormal event occurred in the second robot is added to the alarm information.

8. The method according to claim 1, wherein obtaining reference information related to the abnormal event includes: In response to receiving the abnormal information, determine historical abnormal information that matches the abnormal event from one or more historical abnormal information, wherein the historical abnormal information in the one or more historical abnormal information includes abnormal information received within a predetermined time period before receiving the abnormal information; as well as In response to the absence of historical anomaly information matching the anomaly information, the acquisition of the reference information is initiated.

9. The method of claim 1, wherein the alarm information comprises a structured card, and the structured card is generated in the following manner: Based on the type of the abnormal event, a target card type is determined from multiple card types, wherein each of the multiple card types corresponds to a different abnormal event type; and Based on the reference information, the operational information, and the target card type, the structured card is generated using the first machine learning model.

10. The method of claim 1, wherein the abnormal event includes at least one of the following: The fault status of the first robot, or The first robot failed to complete the task.

11. An alarm device for a robot, comprising: The receiving module is configured to receive abnormal information from the first robot, the abnormal information indicating that an abnormal event has occurred in the first robot; The acquisition module is configured to acquire reference information related to the abnormal event based on the abnormal information, wherein the reference information indicates at least one of the following: the cause of the abnormal event or the handling strategy for the abnormal event; as well as The presentation module is configured to present alarm information regarding the occurrence of the abnormal event in the first robot, the alarm information being generated using a first machine learning model based on the reference information and the operating information of the first robot.

12. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 10.

Images