Robot communication method, electronic device, storage medium and program product

Abstract

Embodiments of the present application provide a robot communication method, electronic device, storage medium, and program product. The method includes: sending authentication information to a base station via a repeater, and receiving authentication success information fed back by the base station via the repeater; after receiving the authentication success information, determining a target beam based on the communication quality parameters of each of the multiple beams sent by the repeater; connecting to the core network based on the target beam, and communicating based on the target beam; determining whether the robot is in a re-authentication state based on the robot's behavioral data and communication data, and sending re-authentication information to the base station via the repeater when the robot is in the re-authentication state. This method improves the security of the robot's access to the core network while performing tasks.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a robot communication method, electronic equipment, storage medium, and program product. Background Art

[0002] The application of robots in home, commercial and other scenarios is becoming more and more extensive. Robots are mainly used in indoor environments and need to maintain stable communication in short-distance, high-density device networks. For example, they need to communicate and interact with smart home devices and IoT devices in real time. They also need to maintain efficient data transmission and fast response in complex indoor environments (such as multiple walls and multiple interferences).

[0003] Before communicating, the robot needs to authenticate and access the core network to avoid security risks and network congestion caused by unauthorized robot access. However, due to signal attenuation and interference indoors, the robot cannot authenticate normally. In addition, the robot's position and communication quality will change during the execution of the task. Authentication before accessing the core network alone cannot avoid security risks during the robot's communication process. Summary of the Invention

[0004] Embodiments of the present application provide a robot communication method, electronic device, storage medium, and program product to improve the security of robot communication.

[0005] In a first aspect, an embodiment of the present application provides a robot communication method, comprising:

[0006] Sending authentication information to the base station through the repeater, and receiving authentication success information fed back by the base station through the repeater;

[0007] After receiving the authentication success information, determining a target beam based on a communication quality parameter of each beam among the multiple beams sent by the repeater;

[0008] connecting to a core network based on the target beam, and communicating based on the target beam;

[0009] It is determined whether the robot is in a re-authentication state based on the behavior data and communication data of the robot, and when the robot is in the re-authentication state, re-authentication information is sent to the base station through the repeater.

[0010] In a possible implementation, determining the target beam based on the communication quality parameter of each beam in the multiple beams sent by the repeater includes:

[0011] Inputting the communication quality parameters of each beam into a pre-trained prediction model to determine the predicted communication quality parameters corresponding to each beam;

[0012] Averaging the communication quality parameters and predicted communication quality parameters of each beam to determine a target communication quality parameter for each beam, wherein the target communication quality parameter includes a plurality of target communication quality indicators;

[0013] Performing multi-indicator fusion processing on multiple target communication quality indicators in the target communication quality parameters of each beam to determine the communication quality value of each beam;

[0014] The target beam is determined from among the plurality of beams based on the magnitude of the communication quality values ​​of the beams.

[0015] In one possible implementation, determining whether the robot is in a re-authentication state based on the robot's behavior data and communication data includes:

[0016] Inputting the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value;

[0017] Determine whether the robot is in the re-authentication state based on the first state parameter value and a first preset threshold.

[0018] In one possible implementation, inputting the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value includes:

[0019] Inputting the behavior data and the communication data into a pre-trained gradient boosting machine to obtain predicted data output by the pre-trained gradient boosting machine, wherein the predicted data includes predicted behavior data and predicted communication data;

[0020] The distance value between the observed data and the predicted data is determined as the first state parameter value, wherein the observed data includes observed behavior data and observed communication data.

[0021] In one possible implementation, determining whether the robot is in the re-authentication state based on the first state parameter value and a first preset threshold includes:

[0022] If the first state parameter value is less than the first preset threshold, it is determined that the robot is not in the re-authentication state;

[0023] If the first state parameter value is greater than or equal to the first preset threshold, inputting the behavior data and the communication data into a pre-trained isolation forest to obtain a second state parameter value;

[0024] Determine whether the robot is in the re-authentication state based on the first state parameter value and the second state parameter value.

[0025] In one possible implementation, determining whether the robot is in the re-authentication state based on the first state parameter value and the second state parameter value includes:

[0026] Assigning corresponding first weight value and second weight value to the first state parameter value and the second state parameter value respectively;

[0027] Determining a first product of the first state parameter value and the first weight value, and determining a second product of the second state parameter value and the second weight value;

[0028] If the sum of the first product and the second product is less than a second preset threshold, determining that the robot is not in the re-authentication state;

[0029] If the sum of the first product and the second product is greater than or equal to a second preset threshold, it is determined that the robot is in the re-authentication state.

[0030] In a second aspect, an embodiment of the present application provides a robot communication device, comprising: an initial authentication module, configured to send authentication information to a base station via a repeater, and receive authentication success information fed back by the base station via the repeater;

[0031] a beam determination module, configured to determine a target beam based on a communication quality parameter of each beam in the plurality of beams transmitted by the repeater;

[0032] a communication connection module, configured to connect to a core network based on the target beam and to communicate based on the target beam;

[0033] The re-authentication module is used to determine the re-authentication state of the robot based on the robot's behavior data and communication data, and send re-authentication information to the base station through the repeater when the robot is in the re-authentication state.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0039] The robot communication method, electronic device, storage medium and program product provided in the embodiments of the present application use a repeater to expand signal coverage and optimize network performance, so that the robot can be authenticated through the repeater and access the core network; at the same time, the repeater also provides the robot with a beam for accessing the core network. When selecting a target beam, a target beam with better quality is selected through the communication quality parameters of the beam, thereby improving the quality of the robot's communication; after the robot accesses the core network for communication, it can be determined in real time based on the robot's behavior data and communication data whether the robot needs to be authenticated again, thereby improving the security of the robot's access to the core network during the execution of the task. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] Figure 1 A schematic diagram of a robot communication system provided for this application;

[0042] Figure 2 Schematic diagram of the robot communication method provided in this application Figure 1 ;

[0043] Figure 3 Schematic diagram of the robot communication method provided in this application Figure 2 ;

[0044] Figure 4 Schematic diagram of the robot communication method provided in this application Figure 3 ;

[0045] Figure 5 A schematic diagram of the structure of the robot communication device provided in this application;

[0046] Figure 6 This is a schematic diagram of the structure of the electronic device provided in this application.

[0047] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0049] Robots are becoming increasingly common in homes, businesses, and other service environments. These robots primarily operate in indoor environments, requiring stable communication within short-range, high-density device networks. These robots not only need to interact with smart home and IoT devices in real time, but also maintain efficient data transmission and rapid response in complex indoor environments, such as those with multiple walls and interference.

[0050] When robots connect using communication technologies such as 5G (fifth generation mobile communication technology), Wi-Fi (wireless Fidelity), or ZigBee (a short-range wireless network protocol), signal attenuation and interference indoors often require extended signal coverage and optimized network performance. Furthermore, the robot's access to the core network requires an efficient authentication mechanism to prevent security risks and network congestion caused by unauthorized device access.

[0051] Based on this, the present application provides a robot communication method, electronic device, storage medium and program product to solve the above problems.

[0052] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0053] Figure 1 A schematic diagram of a robot communication system provided for this application, such as Figure 1 As shown, the application scenario of the present application includes at least one robot 100, a repeater 200, a base station 300 and a core network 400.

[0054] Understandably, Figure 1 Two robots 100 are shown in the figure. In other embodiments, there may be other numbers of robots 100, which is not specifically limited here.

[0055] In some embodiments, the robot 100 needs to access the core network for communication, and must be authenticated before accessing the core network.

[0056] In some embodiments, the robot 100 can be communicatively connected to the repeater 200 to expand signal coverage and optimize network performance through the repeater 200.

[0057] In some embodiments, the robot 100 sends authentication information to the base station 300 through the repeater 200, and receives authentication success information fed back by the base station 300 through the repeater 200; after receiving the authentication success information, the robot 100 determines the target beam based on the communication quality parameters of each beam in the multiple beams sent by the repeater; the robot 100 connects to the core network 400 based on the target beam, and communicates based on the target beam; the robot 100 determines whether the robot is in a re-authentication state based on its behavior data and communication data, and when the robot 100 is in the re-authentication state, sends re-authentication information to the base station 300 through the repeater 200.

[0058] It is understandable that a control module is provided inside the robot 100, and robot communication can be achieved through the control module.

[0059] In some embodiments, the control module may be a server, a processor, a server cluster, or other device capable of performing data processing and business processing.

[0060] In some embodiments, the robot 100 includes a movement unit and a communication unit.

[0061] In this embodiment, the mobile unit is used to move the robot 100. It is understood that the mobile unit can be single-wheel drive, dual-wheel drive, or multi-wheel drive, depending on the drive mode, and this application does not limit this. The communication unit is used to connect the robot 100 to the repeater 200 for communication.

[0062] In some embodiments, the communication unit may be a part of the structure of the control module, or the control module is connected to the communication unit and is in communication connection with the repeater 200 via the communication unit.

[0063] It can be understood that a SIM (Subscriber Identity Module) card interface is provided in the communication unit, and a SIM card can be inserted into or removed from the SIM card interface to achieve contact and separation with the robot 100.

[0064] The robot 100 can support one or more SIM card interfaces. The SIM card interface can support NanoSIM (fourth form factor integrated circuit) cards, MicroSIM (simple SIM card) cards, SIM cards, and the like. Multiple cards can be inserted into the same SIM card interface simultaneously. The cards can be of the same or different types. The SIM card interface can also be compatible with different types of SIM cards. The SIM card interface can also be compatible with external memory cards. The robot 100 interacts with the core network 400 through the SIM card to implement functions such as call and data communications.

[0065] In some embodiments, the robot 100 uses an eSIM, or embedded SIM card. The eSIM card can be embedded in the intelligent robot 100 and cannot be separated from the robot 100.

[0066] In some embodiments, the robot 100 sends authentication information to the repeater through the communication unit, and the repeater 200 sends the authentication information to the base station 300 .

[0067] In some embodiments, the robot 100 sends an access request to the base station 300 through the repeater 200, and the access request carries the authentication information.

[0068] The base station 300 is used to authenticate the robot 100 according to the authentication information, and when the robot 100 passes the authentication, it sends an authentication success message to the repeater 200 , and the repeater 200 can send the authentication success message to the robot 100 .

[0069] The repeater 200 may also provide multiple beams, and the robot 100 is connected to the core network 400 via the beams provided by the repeater 200 , thereby enabling communication of the robot 100 .

[0070] Figure 2 Schematic diagram of the robot communication process provided for this application Figure 1 ,like Figure 2 As shown, this method can be executed in Figure 1 The robot 100 shown, such as a control module within the robot 100, the method includes:

[0071] S201. Send authentication information to a base station via a repeater, and receive authentication success information fed back by the base station via the repeater.

[0072] In some embodiments, the robot needs to communicate and sends authentication information to the base station through a repeater. The authentication information may include one or more of the robot's identity, authentication credentials, network and protocol information, or additional security information.

[0073] After receiving the authentication information, the base station performs authentication processing on the robot. After the authentication is passed, the base station sends an authentication success message to the robot through the repeater.

[0074] In some embodiments, if the base station fails in authentication, it may also send an authentication failure message to the robot through a repeater. At this time, the robot may resend the authentication information for authentication.

[0075] S202: After receiving the authentication success information, determine the target beam based on the communication quality parameters of each beam in the multiple beams sent by the repeater.

[0076] After receiving the authentication success information, the robot can determine a target beam from the multiple beams sent by the repeater as the beam for the robot to access the core network.

[0077] In some embodiments, the repeater is also used to provide the intelligent robot with multiple beams that can be used for communication, and the robot can obtain the communication quality parameters of the beams provided by the repeater according to its current position.

[0078] It is understandable that the communication quality parameters of the acquired beams are different depending on the position of the robot.

[0079] In some embodiments, the signal quality parameter includes at least one indicator, such as one or more indicators such as Reference Signal Receiving Power (RSRP) or Synchronization Signal and PBCH Block (SSB), Channel Quality Indicator (CQI), Signal-to-Noise Ratio (SNR), delay, etc.

[0080] In some embodiments, based on the communication quality parameters of the beams, a beam with the best communication quality parameter is selected as the target beam.

[0081] It can be understood that when the repeater is in working state, it will generate multiple beams with different directions to completely cover the entire cell. The robot will select the one with the best communication effect as the target beam from multiple different beams. After the robot is connected to the repeater, the repeater uses beams with different directions to transmit wireless signals in turn. This process is called beam scanning (BS). At the same time, the robot measures the wireless signals emitted by different beams (Beam Measurement, BM) and reports relevant information to the base station (Beam Reporting, BR). The repeater determines the best transmission beam (Beam Determination, BD) based on the user report, which is the target beam.

[0082] S203: Connect to the core network based on the target beam, and communicate based on the target beam.

[0083] In some embodiments, after the target beam is determined, the core network can be accessed through the target beam, and interaction with the core network can be performed to achieve communication of the robot.

[0084] In some embodiments, the communication quality parameters of the beam may change during the movement of the robot. Therefore, a communication quality parameter threshold can be set. When the beam currently used by the robot is lower than the communication quality parameter threshold, a new target beam can be selected based on the communication quality parameters of the current multiple beams to perform beam switching.

[0085] In some embodiments, the communication quality parameter threshold can be set according to the communication quality parameter. Different communication quality parameters correspond to different communication quality parameter thresholds. For example, when the communication quality parameter is RSRP, the fault threshold can be set to -95dbm (decibel milliwatts), 100dbm, 102dbm, etc., which is not limited here. When the communication quality parameter also includes SSB, the corresponding communication quality parameter threshold is also set for SSB, that is, the specific communication quality parameter threshold can be set according to the type of communication quality parameter, and this application does not limit this.

[0086] In some embodiments, the repeater may actively obtain the communication quality parameters of the beam, or actively perform beam switching.

[0087] For example, the repeater determines the target beam based on the communication quality parameters of each beam among multiple beams, and sends the target beam to the robot, so that the robot is connected to the core network through the target beam; for another example, the repeater actively obtains the communication quality parameters of the beam to which the robot is currently connected. If the communication quality parameters of the beam to which the robot is currently connected are lower than the communication quality parameter threshold, the repeater sends a beam switching signaling to the robot. The robot receives the beam switching signaling and switches the beam.

[0088] S204: Determine whether the robot is in a re-authentication state based on the robot's behavior data and communication data, and send re-authentication information to the base station through the repeater when the robot is in the re-authentication state.

[0089] In some embodiments, the robot has corresponding tasks to perform. When the robot is connected to the core network for communication, the robot's position changes according to the task being performed, and its communication data may change. When the robot's behavior data indicates that the robot deviates from the behavior of the preset task and / or the robot's communication data changes dramatically, the robot's current state may be abnormal. At this time, if no intervention is made, there may be communication risks. Therefore, after the robot is connected to the core network, the robot's behavior data and communication data can be obtained in real time to determine whether the robot is in a re-authentication state. When the robot is in the re-authentication state, the re-authentication information is sent to the base station through the repeater. The re-authentication information is the authentication information of the robot in the current state. If the re-authentication information corresponds to the feedback authentication success information, the robot can continue to perform the corresponding activities. Otherwise, the robot stops running and waits for manual inspection.

[0090] In some embodiments, the behavior data and the communication data are input into a pre-trained gradient boosting machine to determine a first state parameter value; and based on the first state parameter value and a first preset threshold, it is determined whether the robot is in a re-authentication state.

[0091] The robot communication method provided in the embodiment of the present application uses a repeater to expand signal coverage and optimize network performance, so that the robot can be authenticated through the repeater and access the core network; at the same time, the repeater also provides the robot with a beam for accessing the core network. When selecting a target beam, a target beam with better quality is selected through the communication quality parameters of the beam, thereby improving the quality of the robot's communication; after the robot accesses the core network for communication, it can be determined in real time based on the robot's behavior data and communication data whether the robot needs to be authenticated again, thereby improving the security of the robot's access to the core network during the execution of the task.

[0092] Figure 3 Schematic diagram of the robot communication process provided for this application Figure 2 ,like Figure 3 As shown, this embodiment Figure 2 Based on the embodiment, step S202 is described in detail. The method includes:

[0093] S301: Input the communication quality parameter of each beam into a pre-trained prediction model to determine the predicted communication quality parameter corresponding to each beam.

[0094] In some intelligence systems, the prediction model can be trained through the historical communication quality parameters of the beam, and the label data of the historical communication quality parameters are the communication quality parameters within the next time period (such as 1 hour, 2 hours, etc.) of the historical communication quality parameters.

[0095] By inputting historical communication quality parameters into the prediction model, the prediction model is trained using the output of the prediction model and the label data of the historical communication quality parameters to obtain a pre-trained prediction model. The pre-trained prediction model can predict the communication quality parameters of the input communication quality parameters in the next time period, that is, predict the communication quality parameters.

[0096] In some embodiments, the prediction model may be a deep neural network, which is not specifically limited here.

[0097] S302: Perform averaging processing on the communication quality parameters and predicted communication quality parameters of each beam to determine a target communication quality parameter of each beam, where the target communication quality parameter includes a plurality of target communication quality indicators.

[0098] In an embodiment of the present application, the communication quality parameters and the predicted communication quality parameters can be averaged. It can be understood that if the communication quality parameters include multiple indicators, the average processing is performed separately for different types of indicators. For example, if the communication quality parameters include RSRP, SSB and CQI, the RSRP in the communication quality parameters and the RSRP in the predicted communication quality parameters can be averaged to obtain the RSRP in the target communication quality parameters; the SSB in the communication quality parameters and the SSB in the predicted communication quality parameters can be averaged to obtain the SSB in the target communication quality parameters; the CQI in the communication quality parameters and the CQI in the predicted communication quality parameters can be averaged to obtain the CQI in the target communication quality parameters.

[0099] The indicator of the communication quality parameter corresponds to the target communication quality indicator of the target communication quality parameter. The number of types of indicators of the communication quality parameter is equal to the number of target communication quality indicators of the corresponding type of the target communication quality parameter obtained. For example, if the communication quality parameters include RSRP, SSB and CQI, RSRP, SSB and CQI are the target communication quality indicators of the target communication quality parameter.

[0100] S303: Perform multi-indicator fusion processing on multiple target communication quality indicators in the target communication quality parameters of each beam to determine the communication quality value of each beam.

[0101] In some embodiments, the multi-indicator fusion is to assign respective weights to different target communication quality indicators, and determine the sum of the products of each target communication quality indicator and the weight as the communication quality value.

[0102] The sum of the weights assigned to different target communication quality indicators is 1. The weights can be dynamically adjusted according to the specific application scenario. For example, the target communication quality indicators include RSRP, SNR, CQI, and latency. In the scenario of high-speed robot movement, latency and CQI indicators may be more important than RSRP and are assigned larger weights. In static or low-speed scenarios, signal reception power may play a decisive role and is assigned a larger weight.

[0103] For example, in one embodiment, the target communication quality indicators include signal received power (RSRP), signal-to-noise ratio (SNR), channel quality indicator (CQI), and delay (Delay), and the communication quality value is:

[0104] Score i =w1·RSRP i +w2·SNR i +w3·CQI i +w4·Delay i

[0105] Score i represents the communication quality value of the i-th beam, w1-w4 represent the weights of RSRP, SNR, CQI and delay respectively. The weight parameters can be dynamically adjusted according to the specific application scenario. The sum of w1-w4 is 1. For example, in some embodiments, w1 is 0.3, w2 is 0.2, w3 is 0.4, and w4 is 0.1.

[0106] S304: Determine a target beam from the multiple beams based on the communication quality values ​​of the beams.

[0107] In the embodiment of the present application, the beam with the largest communication quality value is determined as the target beam.

[0108] In other embodiments, other beams with higher communication quality values ​​are reserved as backup, and rapid switching can be achieved when the quality of the current connection beam decreases, thereby ensuring the continuity and stability of the communication link.

[0109] Figure 4 Schematic diagram of the robot communication method provided in this application Figure 3 ,like Figure 4 As shown, this embodiment Figure 2 Based on the embodiment, step S204 is described in detail. The method includes:

[0110] S401: Input the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value.

[0111] In some embodiments, behavioral data can be obtained through sensors or work logs set on the robot, such as visual sensors, lidar, sound sensors, etc. The behavioral data may include movement path, speed, work area, task type, interaction mode, etc.

[0112] When performing tasks, robots move along specific paths and speeds. The robot's movement patterns (e.g., route, speed changes, etc.) can be considered behavioral data. The type of task a robot performs (e.g., carrying, cleaning, inspection, etc.) affects its behavioral characteristics, and thus, the task type can also serve as behavioral data. The robot's interaction patterns with other devices (e.g., voice recognition, gesture control, etc.) can also serve as behavioral data, providing clues to whether it is in a re-authentication state. Robots typically operate within a predetermined work area. Any abnormal activity area (e.g., entering a restricted area) may indicate that the robot has been tampered with or illegally operated. Therefore, the work area can also serve as behavioral data for the robot.

[0113] If the behavioral data indicates that the robot's behavior deviates from the original preset task, it can be considered that the robot currently has a potential abnormality, which can trigger re-authentication or security measures.

[0114] Communication data may include data on the communication mode and frequency between the robot and the intelligent repeater, base station and core network. When the communication data is abnormal, such as communicating with other devices too frequently or communicating with other devices in a mode that does not conform to the normal mode, the intelligent robot may be subject to external interference, which may trigger re-authentication or take security measures.

[0115] In some embodiments, a regular behavior pattern of the robot is constructed through a gradient boosting machine (GBDT), the behavior data and communication data are input into a pre-trained gradient boosting machine, a first state parameter value is determined, and the first state parameter value is used to determine whether it is in a re-authentication state.

[0116] In this embodiment, the robot's regular behavior patterns are constructed based on its historical behavior data and historical communication data, and a gradient boosting machine (GBDT) is used for modeling. GBDT is a tree-based ensemble learning method that iteratively generates a series of weak classifiers (decision trees) and combines the outputs of these trees by weighted combination to obtain a strong classifier. Each tree corrects the prediction errors of the previous tree, greatly enhancing the accuracy and generalization ability of the model.

[0117] The gradient boosting machine is trained using historical behavior data and historical communication data. The historical behavior data and historical communication data may correspond to a first historical label. The historical behavior data and historical communication data are input into the gradient boosting machine, and the gradient boosting machine is trained using the predicted value output by the gradient boosting machine and the first historical label to obtain a pre-trained gradient boosting machine.

[0118] In some embodiments, the first historical label can be the value of the historical behavior data and the historical communication data at a later moment. The gradient boosting machine trained in this way can predict the predicted behavior data and predicted communication data of the next time period of the real-time behavior data and the real-time communication data, and the predicted behavior data and predicted communication data are the behavior data and communication data of the robot in a normal state. If the actual observed behavior data and observed communication data of the robot in the future are highly consistent with the predicted behavior data and predicted communication data, re-authentication is not required, that is, it is not in a re-authentication state.

[0119] In some embodiments, the behavior data and communication data are input into a pre-trained gradient boosting machine to obtain predicted data output by the pre-trained gradient boosting machine, the predicted data including predicted behavior data and predicted communication data, and the distance value between the observed data and the predicted data is determined as the first state parameter value, the observed data including observed behavior data and observed communication data.

[0120] In this embodiment, the behavior data and communication data are the data detected at the current moment. The behavior data and communication data are input into the pre-trained gradient boosting machine to obtain the predicted behavior data and predicted communication data at the next moment. At the same time, the observed behavior data and observed communication data are detected at the next moment, and the distance value between the observed data and the predicted data is determined as the first state parameter value.

[0121] In some embodiments, the first state parameter value may be determined by calculating a characteristic distance between the observed data and the predicted data.

[0122] The first state parameter value reflects the gap between the current state of the robot and the normal operating state.

[0123] In some embodiments, the modeling of the gradient boosting machine can be:

[0124]

[0125] Among them, h m (x) represents the mth decision tree, r m The corresponding weight can be set by yourself. For the feature vector x of the input behavior data and communication data (such as robot motion trajectory, speed, sensor data, etc., which are input in sequence), the predicted value f(x) output by the model represents the predicted data of the feature vector x.

[0126] The first state parameter value R(x) can be expressed as:

[0127] R(x)=|yf(x)|

[0128] Among them, y represents the actual observed observation data, and the first state parameter value reflects the gap between the robot's current behavior and the normal preset behavior. When R(x) is small, it means that the robot is in a normal state; when R(x) is large, there may be risks, and it can be judged that the robot is in a re-authentication state.

[0129] S402: Determine whether the robot is in a re-authentication state based on a first state parameter value and a first preset threshold.

[0130] In some embodiments, if the first state parameter value is less than a first preset threshold, it is determined that the robot is not in a re-authentication state; otherwise, it is determined that the robot is in a re-authentication state.

[0131] In other embodiments, in order to further improve the detection accuracy of the re-authentication status, an isolation forest is introduced as a supplement to further detect and confirm those "isolated" data points in the feature space for re-authentication status detection.

[0132] When the first state parameter value corresponding to the behavior data and the communication data is greater than or equal to a first preset threshold, the behavior data and the communication data are input into a pre-trained isolation forest to obtain a second state parameter value; based on the first state parameter value and the second state parameter value, it is determined whether the robot is in a re-authentication state.

[0133] The behavioral data and communication data are input into the isolation forest model to further verify whether the behavioral data and communication data are highly abnormal. Only when both GBDT and the isolation forest confirm that the behavioral data and communication data are abnormal can it be determined that the robot is in the re-authentication state. This joint judgment method not only ensures efficient detection of known abnormal behaviors, but also can respond promptly to new, unlabeled abnormal behaviors, thereby improving the robustness and security of the re-authentication state determination.

[0134] In some embodiments, the isolation forest can be obtained by inputting historical behavior data and historical communication data into the isolation forest for training, and the historical behavior data and historical communication data trained by the isolation forest correspond to a second historical label, and the second historical label is manually labeled, that is, manually labeled according to the robot's behavior data and communication data, so as to obtain a pre-trained isolation forest by training the predicted value output by the isolation forest for the historical behavior data and historical communication data and the second historical label.

[0135] In some embodiments, the isolation forest can be abstracted as:

[0136]

[0137] Where c(x) is a normalization constant, usually H(·) represents the harmonic number, S(x) is the second state parameter value, and E(h(x)) is the average path length of behavioral data and communication data.

[0138] In some embodiments, after determining the first state parameter and the second state parameter values, a joint judgment can be made based on the first state parameter and the second state parameter values, and corresponding first weight values ​​and second weight values ​​are assigned to the first state parameter value and the second state parameter value respectively; a first product of the first state parameter value and the first weight value is determined, and a second product of the second state parameter value and the second weight value is determined; if the sum of the first product and the second product is less than a second preset threshold, it is determined that the robot is not in a re-authentication state; if the sum of the first product and the second product is greater than or equal to the second preset threshold, it is determined that the robot is in a re-authentication state.

[0139] The first weight value and the second weight value can be set by empirical parameters, and the sum of the two is 1. For example, in one embodiment, the first weight value is 0.6 and the second weight value is 0.4. Of course, other values ​​are also possible, and no specific limitation is made here.

[0140] In some embodiments, the second preset threshold can also be set by empirical parameters, such as 0.1, 0.3, etc. It can be understood that the smaller the sum of the first product and the second product, the higher the possibility of the robot operating normally.

[0141] In the embodiment of the present application, GBDT is used to capture normal behavior patterns and provide a preliminary risk assessment for real-time data. Then, isolation forest can be used to efficiently detect noise and unlabeled anomalies in behavioral data and communication data. Finally, by combining the outputs of the two, not only can the misjudgment rate that may be generated by a single model be reduced, but it can also adapt to a wider range of abnormal situations during the operation of the robot, thereby significantly improving the overall robustness and safety of the robot. The combination of gradient boosting machine (GBDT) and isolation forest can improve the prediction and detection capabilities of the robot's re-authentication state, ensure the safety and identity consistency of the robot during operation, and effectively deal with the complexity, dynamic changes and diversity that may arise in behavior recognition, thereby improving the overall safety and reliability of the system.

[0142] For example, in one embodiment, a robot is performing an item handling task in a warehouse. The robot is set to perform the handling task according to a fixed route and speed, interacts with the administrator through voice recognition, and maintains a connection with the smart repeater and base station.

[0143] When the robot is performing the task of moving items, the behavior data and communication data are monitored in real time. At one moment, the robot suddenly deviates from the predetermined path while performing the task. At this time, the robot can determine that the robot has illegally operated or may have an equipment failure based on the behavior data and communication data, that is, the robot has entered the re-authentication state. At this time, the robot sends authentication information to the base station through the repeater, and the base station re-authenticates the robot. After the base station returns the authentication success information, the robot operates normally. If the robot feedback authentication failure information, the robot cannot access the core network for communication, and an alarm can be issued to instruct relevant personnel to conduct inspections.

[0144] In other embodiments, the specific processing method of the robot can also be set according to the size of the sum of the first product and the second product. For example, if the sum of the first product and the second product is less than the second preset threshold, no processing is performed. If the sum of the first product and the second product is greater than or equal to the second preset threshold, re-authentication is performed; if the sum of the first product and the second product is greater than or equal to the third preset threshold, on the basis of the re-authentication, it can be set to prohibit further operation of the robot, lock the control authority of the robot, or send it back to a safe area for inspection. The sum of the first product and the second product is greater than or equal to the third preset threshold and enters a potentially dangerous state, which may involve malicious manipulation of the robot or a serious malfunction.

[0145] In some embodiments, the third preset threshold is greater than the second preset threshold.

[0146] In other embodiments, a fourth preset threshold value may also be set. If the sum of the first product and the second product is less than the second preset threshold value and greater than the fourth preset threshold value, it indicates that the current state of the robot deviates slightly, such as speed changes, unstable movements, etc. GBDT can adapt to the new behavior pattern in a weighted manner based on the existing model, and gradually incorporate the behavior data and communication data corresponding to the numerical value into the conventional behavior range, thereby improving the accuracy of obtaining the first state parameters.

[0147] In some embodiments, the first preset threshold is less than the second preset threshold.

[0148] Figure 5 A schematic diagram of the structure of the robot communication device provided in this application, such as Figure 5 As shown, the robot communication device 50 provided in this embodiment includes:

[0149] The initial authentication module 501 is used to send authentication information to the base station through the repeater and receive authentication success information fed back by the base station through the repeater;

[0150] A beam determination module 502 is configured to determine a target beam based on a communication quality parameter of each beam in a plurality of beams transmitted by the repeater;

[0151] The communication connection module 503 is configured to connect to the core network based on the target beam and communicate based on the target beam;

[0152] The re-authentication module 504 is used to determine the re-authentication state of the robot based on the robot's behavior data and communication data, and send re-authentication information to the base station through the repeater when the robot is in the re-authentication state.

[0153] In one possible implementation, the beam determination module includes:

[0154] A prediction unit, configured to input the communication quality parameter of each beam into a pre-trained prediction model to determine a predicted communication quality parameter corresponding to each beam;

[0155] a target data acquisition unit, configured to average the communication quality parameters and the predicted communication quality parameters of each beam to determine a target communication quality parameter of each beam, wherein the target communication quality parameter includes a plurality of target communication quality indicators;

[0156] a fusion unit, configured to perform multi-indicator fusion processing on multiple target communication quality indicators in the target communication quality parameters of each beam to determine a communication quality value of each beam;

[0157] The beam determination unit is configured to determine a target beam from among the plurality of beams based on the communication quality values ​​of the beams.

[0158] In one possible implementation, the re-authentication module includes:

[0159] a first value acquisition unit, configured to input the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value;

[0160] The state judgment unit is used to determine whether the robot is in a re-authentication state based on a first state parameter value and a first preset threshold.

[0161] In a possible implementation, the first value obtaining unit includes:

[0162] The prediction module is used to input the behavior data and communication data into the pre-trained gradient boosting machine to obtain the predicted data output by the pre-trained gradient boosting machine. The predicted data includes predicted behavior data and predicted communication data.

[0163] The first value acquisition module is used to determine the distance value between the observed data and the predicted data as the first state parameter value, and the observed data includes observed behavior data and observed communication data.

[0164] In one possible implementation, the state determination unit includes:

[0165] A first state judgment module is used to determine that the robot is not in a re-authentication state if the first state parameter value is less than a first preset threshold value;

[0166] a second value acquisition module, configured to input the behavior data and the communication data into a pre-trained isolation forest to obtain a second state parameter value if the first state parameter value is greater than or equal to a first preset threshold;

[0167] The second state judgment module is used to determine whether the robot is in the re-authentication state based on the first state parameter value and the second state parameter value.

[0168] In one possible implementation, the second status determination section includes:

[0169] The weight allocation sub-module is used to allocate corresponding first weight values ​​and second weight values ​​to the first state parameter value and the second state parameter value respectively;

[0170] a calculation submodule, configured to determine a first product of a first state parameter value and a first weight value, and to determine a second product of a second state parameter value and a second weight value;

[0171] A first state judgment submodule is used to determine that the robot is not in a re-authentication state if the sum of the first product and the second product is less than a second preset threshold;

[0172] The second state judgment submodule is used to determine that the robot is in a re-authentication state if the sum of the first product and the second product is greater than or equal to a second preset threshold.

[0173] The robot communication device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and will not be described in detail in this embodiment.

[0174] Figure 6 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.

[0175] During the specific implementation process, at least one processor 601 executes the computer-executable instructions stored in the memory 602, so that the at least one processor 601 performs the above method.

[0176] The specific implementation process of the processor 601 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0177] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0178] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0179] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0180] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0181] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0182] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0183] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0184] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0185] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0186] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0187] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0188] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0189] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A robot communication method, characterized in that: include: Sending authentication information to a base station through a repeater, and receiving authentication success information fed back by the base station through the repeater; After receiving the authentication success information, determining a target beam based on a communication quality parameter of each beam in the multiple beams sent by the repeater; connecting to a core network based on the target beam, and communicating based on the target beam; Determine whether the robot is in a re-authentication state based on the robot's behavior data and communication data, and send re-authentication information to the base station through a repeater when the robot is in the re-authentication state; wherein, The determining whether the robot is in a re-authentication state based on the robot's behavior data and communication data includes: Inputting the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value, wherein the pre-trained gradient boosting machine is used to construct a regular behavior pattern of the robot, and the first state parameter value is used to indicate the difference between the current state of the robot and the normal operating state; Determine whether the robot is in the re-authentication state based on the first state parameter value and a first preset threshold.

2. The method according to claim 1, characterized in that The determining of the target beam based on the communication quality parameter of each beam in the multiple beams sent by the repeater includes: Inputting the communication quality parameters of each beam into a pre-trained prediction model to determine the predicted communication quality parameters corresponding to each beam; Averaging the communication quality parameters and predicted communication quality parameters of each beam to determine a target communication quality parameter for each beam, wherein the target communication quality parameter includes a plurality of target communication quality indicators; Performing multi-indicator fusion processing on multiple target communication quality indicators in the target communication quality parameters of each beam to determine the communication quality value of each beam; The target beam is determined from among the plurality of beams based on the magnitude of the communication quality values ​​of the beams.

3. The method according to claim 1, characterized in that Inputting the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value includes: Inputting the behavior data and the communication data into a pre-trained gradient boosting machine to obtain predicted data output by the pre-trained gradient boosting machine, wherein the predicted data includes predicted behavior data and predicted communication data; The distance value between the observed data and the predicted data is determined as the first state parameter value, wherein the observed data includes observed behavior data and observed communication data.

4. The method according to claim 1, wherein The determining whether the robot is in the re-authentication state based on the first state parameter value and a first preset threshold value includes: If the first state parameter value is less than the first preset threshold, it is determined that the robot is not in the re-authentication state; If the first state parameter value is greater than or equal to the first preset threshold, inputting the behavior data and the communication data into a pre-trained isolation forest to obtain a second state parameter value; Determine whether the robot is in the re-authentication state based on the first state parameter value and the second state parameter value.

5. The method according to claim 4, characterized in that The determining whether the robot is in the re-authentication state based on the first state parameter value and the second state parameter value includes: Assigning corresponding first weight value and second weight value to the first state parameter value and the second state parameter value respectively; Determining a first product of the first state parameter value and the first weight value, and determining a second product of the second state parameter value and the second weight value; If the sum of the first product and the second product is less than a second preset threshold, determining that the robot is not in the re-authentication state; If the sum of the first product and the second product is greater than or equal to a second preset threshold, it is determined that the robot is in the re-authentication state.

6. A robot communication device, characterized in that: include: An initial authentication module, configured to send authentication information to a base station via a repeater, and receive authentication success information fed back by the base station via the repeater; a beam determination module, configured to determine a target beam based on a communication quality parameter of each beam in the plurality of beams transmitted by the repeater; a communication connection module, configured to connect to a core network based on the target beam and to communicate based on the target beam; A re-authentication module is used to determine the re-authentication state of the robot based on the robot's behavior data and communication data, and when the robot is in the re-authentication state, send re-authentication information to the base station through the repeater; wherein, The re-authentication module includes: a first value acquisition unit, configured to input the behavior data and the communication data into a pre-trained gradient boosting machine to determine a first state parameter value, wherein the pre-trained gradient boosting machine is used to construct a regular behavior pattern of the robot, and the first state parameter value is used to indicate a difference between a current state of the robot and a normal operating state; A state judgment unit is used to determine whether the robot is in the re-authentication state based on the first state parameter value and a first preset threshold.

7. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

9. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 5 when executed by a processor.

Images