Cross-scene dynamic authority control method based on human-type health care robot and medium

Abstract

The invention discloses a cross-scene dynamic authority control method based on a human-type health care robot and a medium. The method comprises the steps that when it is detected that a target human-type health care robot is in an open state, current position information and a current scene picture are obtained; inputting the current scene picture into a preset scene determination model, and determining a current position scene in combination with the current position information; obtaining multi-mode identity authentication information of a target person; according to the current position scene and the multi-mode identity authentication information, dynamic authority control over the target human-type health care robot is achieved. The problems that scene selection cannot be accurately carried out and different permissions cannot be selected according to different scenes are solved, the accuracy of scene selection is improved, and the flexibility and accuracy of cross-scene dynamic permission control of the human-type health care robot are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot permission control, and particularly to a cross-scene dynamic permission control method and medium based on a humanoid health care robot. Background Art

[0002] Traditional health care models rely on human labor, suffering from problems such as low efficiency, high costs, and insufficient emotional companionship, and there is an urgent need for intelligent solutions. In recent years, with the rapid development of the Internet and technology, humanoid health care robots can better solve safety problems that occur in people's daily lives.

[0003] In the process of implementing the present invention, the inventor found that the existing technology has the following defects: At present, as humanoid health care robots gradually cover multi-dimensional scenarios such as families, hospitals, and communities, the single pre-set permission division method of humanoid health care robots cannot better meet people's needs. Additionally, it cannot better select scenarios; and for the obtained user privacy data, the security is relatively low, and there is a risk of leakage. Summary of the Invention

[0004] The present invention provides a cross-scene dynamic permission control method and medium based on a humanoid health care robot to improve the accuracy of scene selection and the flexibility and accuracy of cross-scene dynamic permission control of the humanoid health care robot.

[0005] According to one aspect of the present invention, there is provided a cross-scene dynamic permission control method based on a humanoid health care robot, which includes:

[0006] When it is detected that the target humanoid health care robot is in an on state, obtain the current location information and the current scene picture;

[0007] Input the current scene picture into a pre-set scene determination model, and combine the current location information to determine the current location scene; wherein, the scene determination model is trained based on a federated learning framework;

[0008] Obtain multi-modal identity authentication information of the target person;

[0009] Based on the current location scene and the multi-modal identity authentication information, implement dynamic permission control of the target humanoid health care robot.

[0010] According to another aspect of the present invention, there is provided a cross-scene dynamic permission control device based on a humanoid health care robot, which includes:

[0011] The current location information and current scene image acquisition module is used to acquire the current location information and current scene image when it is detected that the target humanoid health care robot is in an on state;

[0012] The current location scene determination module is used to input the current scene image into a pre-set scene determination model and combine the current location information to determine the current location scene; wherein, the scene determination model is trained based on a federated learning framework;

[0013] The multi-modal identity authentication information acquisition module is used to acquire the multi-modal identity authentication information of the target person;

[0014] The dynamic permission control module is used to implement dynamic permission control of the target humanoid health care robot according to the current location scene and the multi-modal identity authentication information.

[0015] According to another aspect of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, it implements the cross-scene dynamic permission control method based on a humanoid health care robot according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the cross-scene dynamic permission control method based on a humanoid health care robot according to any embodiment of the present invention when executed.

[0017] The technical solution of the embodiment of the present invention, by acquiring the current location information and current scene image when it is detected that the target humanoid health care robot is in an on state; inputting the current scene image into a pre-set scene determination model and combining the current location information to determine the current location scene; acquiring the multi-modal identity authentication information of the target person; and implementing dynamic permission control of the target humanoid health care robot according to the current location scene and the multi-modal identity authentication information. It solves the problems of inaccurate scene selection and different permission selections according to different scenes, improves the accuracy of scene selection, as well as the flexibility and accuracy of cross-scene dynamic permission control of the humanoid health care robot, and improves the security of user privacy data.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0020] Figure 1 is a flowchart of a cross-scenario dynamic permission control method based on a humanoid health care robot according to Embodiment 1 of the present invention;

[0021] Figure 2 is a flowchart of security protection processing operations in the method according to Embodiment 2 of the present invention;

[0022] Figure 3 is a schematic structural diagram of a cross-scenario dynamic permission control device based on a humanoid health care robot according to Embodiment 3 of the present invention;

[0023] Figure 4 is a schematic structural diagram of an electronic device according to Embodiment 4 of the present invention. Detailed Embodiments

[0024] To enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "target", "current", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment 1

[0027] Figure 1FIG. 0 is a flowchart of a cross-scenario dynamic permission control method based on a humanoid health care robot according to Embodiment 1 of the present invention. This embodiment is applicable to the situation of determining the scenario of a humanoid health care robot and performing dynamic permission control according to different scenarios. This method can be executed by a cross-scenario dynamic permission control device based on a humanoid health care robot, and the cross-scenario dynamic permission control device based on a humanoid health care robot can be implemented in the form of hardware and / or software.

[0028] Correspondingly, as Figure 1 shown, the method includes:

[0029] S110. When it is detected that the target humanoid health care robot is in an on state, obtain the current location information and the current scene picture.

[0030] Among them, the current location information can be obtained by obtaining the location information of the current target humanoid health care robot, and the location can be obtained through a location sensor or a lidar in the target humanoid health care robot.

[0031] Among them, the current scene picture can be a picture obtained by image measurement through an infrared camera in the target humanoid health care robot.

[0032] In this embodiment, when it is detected that the target humanoid health care robot is in an on state, the current location information and the current scene picture can be obtained. For the target humanoid health care robot to be turned on, it can be turned on by the user for the target humanoid health care robot, or it can be turned on through remote control. For example, when the hospital receives the emergency information of a patient, it can select the humanoid health care robot closest to the patient according to the location of the patient, and perform the turn-on and remote control processing operations on it.

[0033] S120. Input the current scene picture into a pre-set scene determination model, and combine the current location information to determine the current location scene.

[0034] Among them, the scene determination model is trained based on a federated learning framework.

[0035] In this embodiment, the scene determination model is trained based on the federated learning framework. For the federated learning framework, it mainly includes local training, federated aggregation, and transfer testing. Specifically, local training is to optimize the parameters of the MobileNetV3 model on NVIDIA Jetson AGX Xavier. Federated aggregation is to encrypt and transmit the model parameters by adopting the Google Secure Aggregation protocol to ensure that the original data does not leave the local. Additionally, transfer testing is verified by the CASIA IRIS V4 dataset, and the cross-scenario permission policy transfer accuracy is relatively high.

[0036] Optionally, the step of inputting the current scene picture into a pre-set scene determination model and combining the current location information to determine the current location scene includes: inputting the current scene picture into a pre-set scene determination model for picture matching operation to determine the target location scene; matching the current location information with a pre-set three-dimensional semantic map, and determining the current location scene according to the target location scene.

[0037] Among them, the three-dimensional semantic map can be a map constructed by a lidar.

[0038] In this embodiment, inputting the current scene picture into the scene determination model for picture matching operation can obtain the target location scene. Suppose multiple target location scenes are obtained. Further, the current location information can be matched with a pre-set three-dimensional semantic map, and a selection and determination processing operation is performed among multiple target location scenes to obtain the current location scene.

[0039] S130. Obtain the multi-modal identity authentication information of the target person.

[0040] Optionally, the multi-modal identity authentication information includes at least one of the following: fused iris feature information, voiceprint feature information, and gait feature information.

[0041] In this embodiment, the processing of the fused iris feature information can extract 256-dimensional feature vectors by adopting the UNet segmentation algorithm, and the misidentification rate is relatively low. The processing of the voiceprint feature information can be based on the Mel spectrogram and the ResNet34 model for rapid voice verification. The processing of the gait feature information can collect the step frequency or step amplitude data through an IMU sensor and use a long short-term memory network to generate a behavior fingerprint.

[0042] In this embodiment, one or more types of identity authentication information can be collected. For example, voiceprint feature information can be collected; or fused iris feature information and voiceprint feature information can be collected; or fused iris feature information, voiceprint feature information, and gait feature information can be collected.

[0043] S140. Implement dynamic permission control for the target humanoid health care robot according to the current location scenario and the multimodal identity authentication information.

[0044] Optionally, the implementing dynamic permission control for the target humanoid health care robot according to the current location scenario and the multimodal identity authentication information includes: obtaining the current combined environmental parameters, and combining the current location scenario to determine the target identity authentication information adjustment coefficient; wherein, the current combined environmental parameters include the current environmental light intensity and the current noise decibel value; the target identity authentication information adjustment coefficient includes: the fused iris feature information adjustment coefficient, the voiceprint feature information adjustment coefficient, and the gait feature information adjustment coefficient; performing a weight distribution processing operation on the multimodal identity authentication information respectively through the fused iris feature information adjustment coefficient, the voiceprint feature information adjustment coefficient, and the gait feature information adjustment coefficient, and matching the weight distribution result with a pre-constructed permission level query table to obtain the target level permission control, and implementing dynamic permission control for the target humanoid health care robot according to the target level permission control.

[0045] Among them, the target identity authentication information adjustment coefficient can be a coefficient for weighting the multimodal identity authentication information. The current environmental light intensity can be a parameter describing the light intensity in the current environment. The current noise decibel value can be a parameter describing the noise level in the current environment.

[0046] Among them, the fused iris feature information adjustment coefficient can be a parameter for adjusting the fused iris feature information. The voiceprint feature information adjustment coefficient can be a parameter for adjusting the voiceprint feature information. The gait feature information adjustment coefficient can be a parameter for adjusting the gait feature information.

[0047] Optionally, the obtaining the current combined environmental parameters and combining the current location scenario to determine the target identity authentication information adjustment coefficient includes: obtaining the current combined environmental parameters, wherein the current combined environmental parameters include the current environmental light intensity and the current noise decibel value; according to the current location scenario, and combining the current environmental light intensity and the current noise decibel value, performing a query operation through a pre-constructed adjustment parameter query table to determine the target identity authentication information adjustment coefficient.

[0048] Among them, the adjustment parameter query table can be a table that obtains different target identity authentication information adjustment coefficients according to different scenarios and different ambient light intensities and noise decibel values in different scenarios.

[0049] Exemplarily, it is assumed that in a home scenario, when the ambient light intensity is greater than 80 lux and the noise decibel value is less than 40 dB, it can be determined that α≥0.6 (where α is the adjustment coefficient of the fused iris feature information); it can be determined that γ≤0.5 (where γ is the adjustment coefficient of the gait feature information). Additionally, when the noise decibel value is greater than 60 dB, it can be determined that β≥0.7 (where β is the adjustment coefficient of the voiceprint feature information). In a specific example, when the currently collected ambient light intensity is 100 lux and the current noise decibel value is 30 dB, by querying with the adjustment parameter query table, the target identity authentication information adjustment coefficients can be determined as the adjustment coefficient of the fused iris feature information is 0.7, the adjustment coefficient of the voiceprint feature information is 0.2, and the adjustment coefficient of the gait feature information is 0.1.

[0050] Optionally, the multi-modal identity authentication information is weighted by the adjustment coefficient of the fused iris feature information, the adjustment coefficient of the voiceprint feature information, and the adjustment coefficient of the gait feature information respectively, and the weight distribution result is matched with a pre-constructed permission level query table to obtain the target level permission control, and the dynamic permission control of the target humanoid healthcare robot is realized according to the target level permission control, including: if the multi-modal identity authentication information is the voiceprint feature information, the voiceprint feature information is weighted by the adjustment coefficient of the voiceprint feature information to obtain the first weight distribution result, and the first weight distribution result is matched with the pre-constructed permission level query table to obtain the first-level permission control, and the target humanoid healthcare robot is processed according to the first-level permission control;

[0051] If the multi-modal identity authentication information is the fused iris feature information and the voiceprint feature information, the fused iris feature information and the voiceprint feature information are weighted by the adjustment coefficient of the fused iris feature information and the adjustment coefficient of the voiceprint feature information respectively to obtain the second weight distribution result, and the second weight distribution result is matched with the pre-constructed permission level query table to obtain the second-level permission control, and the target humanoid healthcare robot is processed according to the second-level permission control;

[0052] If the multimodal identity authentication information is the fused iris feature information, voiceprint feature information, and gait feature information, weight assignment processing operations are respectively performed on the fused iris feature information, voiceprint feature information, and gait feature information by the target identity authentication information adjustment coefficient to obtain a third weight assignment result, and the third weight assignment result is used to match with a pre-constructed permission level query table to obtain a third-level permission control, and the target humanoid health care robot is processed according to the third-level permission control.

[0053] Among them, the weight assignment result can be the assignment result obtained by respectively performing weight processing on different feature information by the target identity authentication information adjustment coefficient. The target level permission control can be permission controls of different levels. The permission controls of different levels can correspond to different operation types.

[0054] Exemplarily, it is assumed that the first-level permission control can instruct the target humanoid health care robot to perform processing operations of voice interaction and information query. The second-level permission control can instruct the target humanoid health care robot to perform processing operations of item delivery and assisted walking. The third-level permission control can instruct the target humanoid health care robot to perform processing operations of drug injection and first aid operations.

[0055] Specifically, if the multimodal identity authentication information is voiceprint feature information, weight assignment processing operations are performed on the voiceprint feature information by the voiceprint feature information adjustment coefficient to obtain a first weight assignment result, and the first weight assignment result is used to match with a pre-constructed permission level query table to obtain a first-level permission control, and the target humanoid health care robot is processed according to the first-level permission control.

[0056] Continuing the previous example, if the multimodal identity authentication information is voiceprint feature information and the voiceprint feature information adjustment coefficient is 0.2, then according to the formula W = αW iris +βW voice +γW gait (where W iris is the fused iris feature information; W voice is the voiceprint feature information; W gait is the gait feature information; W is the weight assignment result). Through calculation, the first weight assignment result can be obtained as 0.2W voice .

[0057] Furthermore, the first weight assignment result is used to match with the permission level query table to obtain a first-level permission control, and the target humanoid health care robot is processed according to the first-level permission control.

[0058] Among them, the permission level query table can determine the specific permission level according to the weight assignment result.

[0059] Continuing from the previous example, assume 0.2W voice Match with the permission level query table to obtain the first-level permission control. Since the first-level permission control can instruct the target humanoid health care robot to perform voice interaction and information query processing operations, the target humanoid health care robot can be instructed to perform voice interaction and information query.

[0060] Similarly, whether the multi-modal identity authentication information is the fusion of iris feature information and voiceprint feature information, or the multi-modal identity authentication information is the fusion of iris feature information, voiceprint feature information and gait feature information, the corresponding weight distribution result can be calculated, and then matched with the permission level query table to obtain the specific permission control level, and the target humanoid health care robot can be processed according to different permission control levels.

[0061] The technical solution of the embodiment of the present invention, by when detecting that the target humanoid health care robot is in an open state, obtaining the current location information and the current scene picture; inputting the current scene picture into a pre-set scene determination model, and combining the current location information to determine the current location scene; obtaining the multi-modal identity authentication information of the target person; realizing the dynamic permission control of the target humanoid health care robot according to the current location scene and the multi-modal identity authentication information. Solve the problems of inaccurate scene selection and different permission selections according to different scenes, improve the accuracy of scene selection, as well as the flexibility and accuracy of the cross-scene dynamic permission control of the humanoid health care robot, and improve the security of user privacy data.

[0062] Embodiment 2

[0063] Figure 2 This is a flowchart of the security protection processing operation in a cross-scene dynamic permission control method based on a humanoid health care robot provided by the second embodiment of the present invention. This embodiment is optimized based on the above-mentioned embodiments. In this embodiment, after implementing the dynamic permission control of the target humanoid health care robot according to the target level permission control, it further includes performing a security protection processing operation on the humanoid health care robot.

[0064] Correspondingly, as Figure 2 shown, the method includes:

[0065] S210. When detecting that the target humanoid health care robot is in an open state, obtain the current location information and the current scene picture.

[0066] S220. Input the current scene picture into a pre-set scene determination model, and combine the current location information to determine the current location scene.

[0067] S230. Obtain the multi-modal identity authentication information of the target person.

[0068] S240. Implement dynamic permission control over the target humanoid healthcare robot according to the current location scenario and the multi-modal identity authentication information.

[0069] S250. After the target humanoid healthcare robot receives the target level permission control, obtain the operation response time.

[0070] Among them, the operation response time can be the magnitude of the response time for counting the actions of the target humanoid healthcare robot.

[0071] S260. Obtain the preset operation response time threshold.

[0072] Among them, the operation response time threshold can be the minimum response time of the preset actions.

[0073] S270. If the operation response time is less than or equal to the operation response time threshold, instruct the electronic fuse to perform a safety protection processing operation.

[0074] Exemplarily, assume that the operation response time threshold of the target humanoid healthcare robot is 0.5 ms, and the obtained operation response time is 0.2 ms. Since 0.2 ms is less than 0.5 ms, it indicates that the target humanoid healthcare robot moves in advance, rather than a normal response action, and this corresponding action is dangerous. Therefore, it is necessary to instruct the electronic fuse to perform a safety protection processing operation to cut off the motor power supply in time to prevent mechanical injuries.

[0075] In addition, it is also necessary to preset the CAN bus instruction lock of the target humanoid healthcare robot, so as to disable unauthorized function modules. For example, the robotic arm grasping operation of the target humanoid healthcare robot.

[0076] In the technical solution of the embodiment of the present invention, when it is detected that the target humanoid health care robot is in an on state, the current location information and the current scene picture are obtained; the current scene picture is input into a pre-set scene determination model, and combined with the current location information, the current location scene is determined; the multi-modal identity authentication information of the target person is obtained; according to the current location scene and the multi-modal identity authentication information, the dynamic permission control of the target humanoid health care robot is realized; after the target humanoid health care robot receives the target level permission control, the operation response time is obtained; the pre-set operation response time threshold is obtained; if the operation response time is less than or equal to the operation response time threshold, the electronic fuse is instructed to perform a safety protection processing operation. By obtaining the operation response time, the standardization of the operation of the target humanoid health care robot can be improved, and the safety of the user can be guaranteed.

[0077] Embodiment III

[0078] Figure 3 FIG. 7 is a schematic structural diagram of a cross-scene dynamic permission control device based on a humanoid health care robot provided in Embodiment III of the present invention. The cross-scene dynamic permission control device provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device to implement a cross-scene dynamic permission control method based on a humanoid health care robot in the embodiment of the present invention. As Figure 3 shown, the device includes: a current location information and current scene picture acquisition module 310, a current location scene determination module 320, a multi-modal identity authentication information acquisition module 330, and a dynamic permission control module 340.

[0079] Among them, the current location information and current scene picture acquisition module 310 is used to obtain the current location information and the current scene picture when it is detected that the target humanoid health care robot is in an on state;

[0080] The current location scene determination module 320 is used to input the current scene picture into a pre-set scene determination model, and combine the current location information to determine the current location scene; among them, the scene determination model is trained based on a federated learning framework;

[0081] The multi-modal identity authentication information acquisition module 330 is used to obtain the multi-modal identity authentication information of the target person;

[0082] The dynamic permission control module 340 is used to implement the dynamic permission control of the target humanoid health care robot according to the current location scene and the multi-modal identity authentication information.

[0083] The technical solution of the embodiment of the present invention is as follows: when it is detected that the target humanoid health care robot is in an on state, the current position information and the current scene picture are obtained; the current scene picture is input into a pre-set scene determination model, and combined with the current position information, the current position scene is determined; the multi-modal identity authentication information of the target person is obtained; according to the current position scene and the multi-modal identity authentication information, dynamic permission control of the target humanoid health care robot is realized. This solves the problems of inaccurate scene selection and different permission selections according to different scenes, improves the accuracy of scene selection, as well as the flexibility and accuracy of cross-scene dynamic permission control of the humanoid health care robot, and improves the security of user privacy data.

[0084] Based on the above embodiments, the current position scene determination module 320 may specifically be used for: inputting the current scene picture into a pre-set scene determination model for picture matching operation to determine the target position scene; matching the current position information with a pre-set three-dimensional semantic map, and determining the current position scene according to the target position scene.

[0085] Based on the above embodiments, the multi-modal identity authentication information includes at least one of the following: integrated iris feature information, voiceprint feature information, and gait feature information.

[0086] Based on the above embodiments, the dynamic permission control module 340 may specifically include: a target identity authentication information adjustment coefficient determination unit, which may specifically be used for: obtaining the current combined environment parameters, and combining the current position scene to determine the target identity authentication information adjustment coefficient; wherein, the current combined environment parameters include the current environmental light intensity and the current noise decibel value; the target identity authentication information adjustment coefficient includes: integrated iris feature information adjustment coefficient, voiceprint feature information adjustment coefficient, and gait feature information adjustment coefficient; a dynamic permission control unit, which may specifically be used for: performing weight distribution processing on the multi-modal identity authentication information respectively through the integrated iris feature information adjustment coefficient, the voiceprint feature information adjustment coefficient, and the gait feature information adjustment coefficient, and matching the weight distribution result with a pre-constructed permission level query table to obtain the target level permission control, and realizing dynamic permission control of the target humanoid health care robot according to the target level permission control.

[0087] Based on the above embodiments, the target identity authentication information adjustment coefficient determination unit may specifically be further configured to: obtain current combined environmental parameters, where the current combined environmental parameters include the current environmental light intensity and the current noise decibel value; according to the current location scene, and in combination with the current environmental light intensity and the current noise decibel value, perform a query operation through a pre-constructed adjustment parameter query table to determine the target identity authentication information adjustment coefficient.

[0088] Based on the above embodiments, the dynamic permission control unit may specifically be further configured to: if the multi-modal identity authentication information is voiceprint feature information, perform a weight assignment processing operation on the voiceprint feature information through the voiceprint feature information adjustment coefficient to obtain a first weight assignment result, and match the first weight assignment result with a pre-constructed permission level query table to obtain a first-level permission control, and perform a processing operation on the target humanoid healthcare robot according to the first-level permission control; if the multi-modal identity authentication information is a combination of iris feature information and voiceprint feature information, perform weight assignment processing operations on the iris feature information and the voiceprint feature information respectively through the iris feature information adjustment coefficient and the voiceprint feature information adjustment coefficient to obtain a second weight assignment result, and match the second weight assignment result with a pre-constructed permission level query table to obtain a second-level permission control, and perform a processing operation on the target humanoid healthcare robot according to the second-level permission control; if the multi-modal identity authentication information is a combination of iris feature information, voiceprint feature information and gait feature information, perform weight assignment processing operations on the iris feature information, the voiceprint feature information and the gait feature information respectively through the target identity authentication information adjustment coefficient to obtain a third weight assignment result, and match the third weight assignment result with a pre-constructed permission level query table to obtain a third-level permission control, and perform a processing operation on the target humanoid healthcare robot according to the third-level permission control.

[0089] Based on the above embodiments, it further includes a dynamic permission control module, which may specifically be configured to: after implementing the dynamic permission control of the target humanoid healthcare robot according to the target level permission control, after the target humanoid healthcare robot receives the target level permission control, obtain the operation response time; obtain a pre-set operation response time threshold; if the operation response time is less than or equal to the operation response time threshold, instruct the electronic fuse to perform a safety protection processing operation.

[0090] The dynamic permission control device based on a humanoid health care robot provided by an embodiment of the present invention can execute the dynamic permission control method based on a humanoid health care robot provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution of the method.

[0091] Embodiment 4

[0092] Figure 4 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0093] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0094] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0095] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the cross-scenario dynamic permission control method based on the humanoid healthcare robot.

[0096] In some embodiments, the cross-scenario dynamic permission control method based on the humanoid healthcare robot may be implemented as a computer program, which is tangibly included in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the cross-scenario dynamic permission control method based on the humanoid healthcare robot described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the cross-scenario dynamic permission control method based on the humanoid healthcare robot in any other suitable manner (e.g., by means of firmware).

[0097] The method includes: when it is detected that the target humanoid healthcare robot is in an on state, obtaining the current location information and the current scene picture; inputting the current scene picture into a pre-set scene determination model, and combining the current location information to determine the current location scene; wherein, the scene determination model is trained based on a federated learning framework; obtaining multi-modal identity authentication information of the target person; and implementing dynamic permission control of the target humanoid healthcare robot according to the current location scene and the multi-modal identity authentication information.

[0098] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0099] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0100] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0103] A computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0104] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0105] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0106] Example 5

[0107] Example 5 of the present invention further provides a computer-readable storage medium, and the computer-readable instructions are used to execute a cross-scenario dynamic permission control method based on a humanoid healthcare robot when executed by a computer processor. The method includes: when it is detected that the target humanoid healthcare robot is in an on state, obtaining the current location information and the current scene picture; inputting the current scene picture into a pre-set scene determination model, and combining the current location information to determine the current location scene; wherein, the scene determination model is trained based on a federated learning framework; obtaining multi-modal identity authentication information of the target person; and implementing dynamic permission control of the target humanoid healthcare robot according to the current location scene and the multi-modal identity authentication information.

[0108] Certainly, the computer-executable instructions of a computer-readable storage medium provided by the embodiments of the present invention are not limited to the method operations described above, and can also execute related operations in the cross-scenario dynamic permission control based on a humanoid healthcare robot provided by any embodiment of the present invention.

[0109] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0110] It should be noted that in the above embodiments of the cross-scenario dynamic permission control based on a humanoid healthcare robot, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0111] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A cross-scenario dynamic permission control method based on a humanoid health care robot, characterized in that Including: When it is detected that the target humanoid health care robot is in an on state, obtain the current location information and the current scene picture; Input the current scene picture into a pre-set scene determination model, and combine the current location information to determine the current location scene; wherein, the scene determination model is trained based on a federated learning framework; Obtain the multi-modal identity authentication information of the target person; Based on the current location scene and the multi-modal identity authentication information, implement dynamic permission control over the target humanoid health care robot.

2. The method according to claim 1, characterized in that, The step of inputting the current scene picture into a pre-set scene determination model and combining the current location information to determine the current location scene includes: Input the current scene picture into a pre-set scene determination model for picture matching operation to determine the target location scene; Match the current location information with a pre-set three-dimensional semantic map, and based on the target location scene, determine the current location scene.

3. The method according to claim 2, wherein The multi-modal identity authentication information includes at least one of the following: fused iris feature information, voiceprint feature information, and gait feature information.

4. The method according to claim 3, wherein The step of implementing dynamic permission control over the target humanoid health care robot based on the current location scene and the multi-modal identity authentication information includes: Obtain the current combined environment parameters, and combine the current location scene to determine the target identity authentication information adjustment coefficient; Wherein, the current combined environment parameters include the current environmental light intensity and the current noise decibel value; The target identity authentication information adjustment coefficient includes: fused iris feature information adjustment coefficient, voiceprint feature information adjustment coefficient, and gait feature information adjustment coefficient; Perform weight assignment processing operations on the multi-modal identity authentication information respectively through the fused iris feature information adjustment coefficient, the voiceprint feature information adjustment coefficient, and the gait feature information adjustment coefficient, and match the weight assignment result with a pre-constructed permission level query table to obtain the target level permission control, and implement dynamic permission control over the target humanoid health care robot according to the target level permission control.

5. The method according to claim 4, wherein The step of obtaining the current combined environment parameters and combining the current location scene to determine the target identity authentication information adjustment coefficient includes: Obtain the current combined environment parameters, wherein the current combined environment parameters include the current environmental light intensity and the current noise decibel value; Based on the current location scene, and in combination with the current environmental light intensity and the current noise decibel value, perform a query operation through a pre-constructed adjustment parameter query table to determine the target identity authentication information adjustment coefficient.

6. The method according to claim 5, wherein The step of performing weight assignment processing operations on the multi-modal identity authentication information respectively through the fused iris feature information adjustment coefficient, the voiceprint feature information adjustment coefficient, and the gait feature information adjustment coefficient, and match the weight assignment result with a pre-constructed permission level query table to obtain the target level permission control, and implement dynamic permission control over the target humanoid health care robot according to the target level permission control includes: If the multimodal identity authentication information is voiceprint feature information, perform a weight assignment processing operation on the voiceprint feature information through the voiceprint feature information adjustment coefficient to obtain a first weight assignment result, and match the first weight assignment result with a pre-constructed permission level query table to obtain a first-level permission control, and perform a processing operation on the target humanoid health care robot according to the first-level permission control; If the multimodal identity authentication information is fused iris feature information and voiceprint feature information, perform weight assignment processing operations on the fused iris feature information and the voiceprint feature information respectively through the fused iris feature information adjustment coefficient and the voiceprint feature information adjustment coefficient to obtain a second weight assignment result, and match the second weight assignment result with a pre-constructed permission level query table to obtain a second-level permission control, and perform a processing operation on the target humanoid health care robot according to the second-level permission control; If the multimodal identity authentication information is fused iris feature information, voiceprint feature information and gait feature information, perform weight assignment processing operations on the fused iris feature information, the voiceprint feature information and the gait feature information respectively through the target identity authentication information adjustment coefficient to obtain a third weight assignment result, and match the third weight assignment result with a pre-constructed permission level query table to obtain a third-level permission control, and perform a processing operation on the target humanoid health care robot according to the third-level permission control.

7. The method according to claim 6, wherein After implementing the dynamic permission control of the target humanoid health care robot according to the target level permission control, it further includes: After the target humanoid health care robot receives the target level permission control, obtain the operation response time; Obtain a pre-set operation response time threshold; If the operation response time is less than or equal to the operation response time threshold, instruct the electronic fuse to perform a safety protection processing operation.

8. A cross-scenario dynamic permission control device based on a humanoid health care robot, characterized in that, It includes: A current position information and current scene picture acquisition module, configured to acquire current position information and a current scene picture when it is detected that the target humanoid health care robot is in an on state; A current position scene determination module, configured to input the current scene picture into a pre-set scene determination model and combine the current position information to determine the current position scene; wherein, the scene determination model is trained based on a federated learning framework; A multimodal identity authentication information acquisition module, configured to acquire multimodal identity authentication information of a target person; A dynamic permission control module, configured to implement dynamic permission control of the target humanoid health care robot according to the current position scene and the multimodal identity authentication information.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a cross-scene dynamic permission control method for a humanoid health care robot according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the processor to implement a cross-scene dynamic permission control method for a humanoid health care robot according to any one of claims 1-7 when executed.

Images