A robot massage method and device based on vision, and electronic equipment

Abstract

The present invention discloses a vision-based robot massage method and device, and electronic equipment, which belongs to the field of intelligent hardware technology. The method includes: obtaining user first information and user demand information; obtaining user second information through a preset visual perception device; calculating the user first information and the user second information through two different algorithms to obtain a first user back acupuncture point position distribution map and a second user back acupuncture point position distribution map; fusing the first user back acupuncture point position distribution map and the second user back acupuncture point position distribution map to generate a third user back acupuncture point position distribution map; generating a robot arm control scheme according to the user demand information and the third user back acupuncture point position distribution map; and controlling the robot arm to move on the user's back according to the robot arm control scheme. Through the vision-based robot massage method disclosed by the present invention, a high-precision user back acupuncture point position distribution map can be generated.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent hardware, and in particular to a vision-based robot massage method and device, and electronic equipment. Background Art

[0002] Machine vision is a rapidly developing branch of artificial intelligence. The machine vision system converts the photographed target into an image signal through a shooting device, transmits it to a dedicated image processing system, obtains the morphological information of the photographed target, and then converts it into a digital signal based on pixel distribution, brightness, color and other information. The image system calculates these digital signals to extract the characteristics of the photographed target, and then controls the action of the on-site equipment based on the judgment results.

[0003] Massage is an important part of Chinese medicine. It is guided by Chinese medical theory, based on the theory of meridians and acupoints, and mainly uses massage of acupoints as a means of relieving fatigue, preventing and curing diseases.

[0004] With the development of robot technology, service robots are being used more and more widely. At present, there are related solutions that use robots to achieve human body massage. However, these solutions have the following defects: due to the differences in human body morphology, it is difficult for robots to accurately find the user's acupuncture points, resulting in a significant reduction in the massage effect and a poor user experience. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a vision-based robot massage method and device, and electronic equipment, which can solve the problem in the prior art that it is difficult for robots to accurately find the user's acupuncture points.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] An embodiment of the present invention provides a vision-based robot massage method, which is applied to a robot, wherein the method comprises: obtaining first user information, wherein the first user information is used to characterize user attributes;

[0008] Obtain user demand information;

[0009] Acquire the second information of the user through a preset visual perception device, wherein the second information of the user includes: at least one of a laser point cloud, a depth image or an identification code for representing the user's posture;

[0010] The first information of the user and the second information of the user are calculated by two different algorithms to obtain a distribution map of acupuncture points on the back of the first user and a distribution map of acupuncture points on the back of the second user;

[0011] Merging the acupuncture point position distribution map on the back of the first user and the acupuncture point position distribution map on the back of the second user to generate a third acupuncture point position distribution map on the back of the user;

[0012] Generate a robotic arm control plan according to the user demand information and the acupuncture point position distribution map on the back of the third user;

[0013] According to the robot arm control scheme, the robot arm is controlled to move on the user's back.

[0014] Optionally, the step of obtaining the first user information includes:

[0015] Collecting first voice information input by a user through a voice interaction device, and identifying the first user information from the first voice information, wherein the first user information includes: at least one of the user's gender, height, and weight;

[0016] or,

[0017] The first user information input by the user is received through the electronic input device.

[0018] Optionally, the step of obtaining the second information of the user through a preset visual perception device includes:

[0019] Through the depth camera, the depth image, shoulder width information, the widest distance of the spine, and the narrowest distance of the spine representing the user's body shape are collected;

[0020] Through laser radar, laser point cloud representing the user's body posture is collected.

[0021] Optionally, the step of calculating the first user information and the second user information by two different algorithms to obtain the acupuncture point position distribution map on the back of the first user and the acupuncture point position distribution map on the back of the second user includes:

[0022] The first information of the user and the second information of the user are calculated through a preset database to obtain a distribution map of acupuncture points on the back of the first user;

[0023] The first user information and the second user information are calculated by a preset neural network detection algorithm to obtain a distribution map of acupuncture point positions on the back of the second user.

[0024] Optionally, the step of fusing the first user's back acupuncture point location distribution map and the second user's back acupuncture point location distribution map to generate a third user's back acupuncture point location distribution map includes:

[0025] Inputting the acupuncture point position distribution map of the first user's back, the acupuncture point position distribution map of the second user's back, and the first information of the user into a pre-trained fusion model, and determining the output of the fusion model as the acupuncture point position distribution map of the third user's back;

[0026] The fusion model is generated by training based on multiple groups of user first information, a distribution map of user back acupuncture points before fusion, and a distribution map of user back acupuncture points after fusion.

[0027] Optionally, the step of generating a robot arm control solution according to the user demand information and the acupuncture point position distribution map on the back of the third user includes:

[0028] Determine the massage points, massage duration and massage intensity according to the user demand information;

[0029] Determining a movement trajectory of the robotic arm based on the massage acupuncture points and the acupuncture point position distribution map of the third user's back;

[0030] A robotic arm control plan is generated based on the movement trajectory of the robotic arm, the massage duration and the massage intensity.

[0031] An embodiment of the present invention provides a vision-based robot massage device, which is applied to a robot, wherein the device comprises:

[0032] A first acquisition module, used to acquire first information of a user, wherein the first information is used to characterize user attributes;

[0033] The second acquisition module is used to acquire user demand information;

[0034] A third acquisition module is used to acquire the second information of the user through a preset visual perception device, wherein the second information of the user includes: at least one of a laser point cloud, a depth image or an identification code for representing the user's body shape;

[0035] A calculation module, used to calculate the first user information and the second user information by using two different algorithms to obtain a distribution map of acupuncture points on the back of the first user and a distribution map of acupuncture points on the back of the second user;

[0036] A fusion module, configured to fuse the acupuncture point position distribution map on the back of the first user and the acupuncture point position distribution map on the back of the second user to generate a acupuncture point position distribution map on the back of a third user;

[0037] A generating module, configured to generate a robot arm control scheme according to the user demand information and the acupuncture point position distribution map on the back of the third user;

[0038] The control module is used to control the robot's mechanical arm to move on the user's back according to the mechanical arm control scheme.

[0039] Optionally, the first acquisition module includes:

[0040] A first calling submodule, configured to collect first voice information input by a user through a voice interaction device, and identify the first user information from the first voice information, wherein the first user information includes: at least one of the user's gender, height, and weight;

[0041] The second calling submodule is used to receive first user information input by the user through an electronic input device.

[0042] Optionally, the third acquisition module includes:

[0043] The third calling submodule is used to collect a depth image representing the user's body shape, shoulder width information, the widest distance of the middle spine, and the narrowest distance of the middle spine through a depth camera;

[0044] The fourth calling submodule is used to collect laser point clouds representing the user's body posture through laser radar.

[0045] Optionally, the calculation module includes:

[0046] A first calculation submodule, configured to calculate the first information of the user and the second information of the user through a preset database to obtain a distribution map of acupuncture points on the back of the first user;

[0047] The second calculation submodule is used to calculate the first information of the user and the second information of the user through a preset neural network detection algorithm to obtain a distribution map of acupuncture points on the back of the second user.

[0048] Optionally, the fusion module is specifically used for:

[0049] Inputting the acupuncture point position distribution map of the first user's back, the acupuncture point position distribution map of the second user's back, and the first information of the user into a pre-trained fusion model, and determining the output of the fusion model as the acupuncture point position distribution map of the third user's back;

[0050] The fusion model is generated by training based on multiple groups of user first information, a distribution map of user back acupuncture points before fusion, and a distribution map of user back acupuncture points after fusion.

[0051] Optionally, the generating module includes:

[0052] A first determination submodule is used to determine massage points, massage duration and massage intensity according to the user demand information;

[0053] A first determination submodule, configured to determine a movement trajectory of the robotic arm based on the massage acupuncture points and the acupuncture point position distribution map of the third user's back;

[0054] A generation submodule is used to generate a robotic arm control plan based on the movement trajectory of the robotic arm, the massage duration and the massage intensity.

[0055] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of any one of the above-mentioned vision-based robotic massage methods.

[0056] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of any one of the above-mentioned vision-based robot massage methods are implemented.

[0057] The vision-based robot massage solution provided by the embodiment of the present invention obtains the first user information and the user demand information; obtains the second user information through a preset visual perception device; calculates the first user information and the second user information through two different algorithms to obtain the acupuncture point position distribution map of the first user's back and the acupuncture point position distribution map of the second user's back; fuses the acupuncture point position distribution map of the first user's back and the acupuncture point position distribution map of the second user's back to generate the acupuncture point position distribution map of the third user's back; calculates the acupuncture point position distribution map of the user's back through two different algorithms, and then fuses the two calculated acupuncture point position distribution maps of the user's back, which can improve the accuracy of the acupuncture point position distribution map of the third user's back generated. Then, according to the user demand information and the acupuncture point position distribution map of the third user's back, a mechanical arm control scheme is generated; according to the mechanical arm control scheme, the mechanical arm of the robot is controlled to move on the user's back. Since the acupuncture point position distribution map of the third user's back obtained has high accuracy, the acupuncture points determined based on the acupuncture point position distribution map of the third user's back and the user demand information will also be more accurate, so that the massage effect can be improved, thereby improving the user's massage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a flowchart showing the steps of a vision-based robot massage method according to an embodiment of the present application;

[0059] Figure 2 is a schematic diagram of a user's posture representing an embodiment of the present application;

[0060] Figure 3 is a structural block diagram of a vision-based robotic massage device according to an embodiment of the present application;

[0061] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0063] The following is a detailed description of the motion safety area prediction solution provided by the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0064] As attached Figure 1 As shown, the vision-based robot massage method of the embodiment of the present application includes the following steps:

[0065] Step 101: Obtain the first user information.

[0066] The first user information is used to represent the user's attributes, and includes but is not limited to: at least one of gender, height, and weight. Figure 2 As shown in the user posture diagram in , the user's first information such as the user's height and weight will affect the distribution of the acupuncture points on the back. Therefore, when the user is stationary on the massage bed, the user's first information is an important parameter when determining the distribution of the acupuncture points on the user's back.

[0067] The vision-based robot massage method of the embodiment of the present application is applied to an electronic device, which can be a server, computer or other device with analysis function that exists independently of the robot, or a control device set in the robot. The storage medium in the electronic device stores a control program of the vision-based robot massage method, and the processor of the electronic device runs the program in the storage medium to execute the robot massage process to provide a back massage for the user.

[0068] An optional way to obtain the user's first information may be: collecting the first voice information input by the user through a voice interaction device, and identifying the user's first information from the first voice information; or, receiving the user's first information input by the user through an electronic input device.

[0069] The above are only two exemplary methods of obtaining the user's first information. In the actual implementation process, the user's first information can also be obtained through other feasible methods. The specific method of obtaining the user's first information is not specifically limited in the embodiments of the present application.

[0070] Step 102: Obtain user demand information.

[0071] User demand information includes at least one of the massage point sequence, massage duration, and massage intensity. By obtaining user demand information, the user's massage needs can be understood more accurately. User demand information can be entered by the user or by the staff to assist the user in entering it. User demand information can be collected through a voice interaction device or input through an electronic input device.

[0072] Step 103: Obtain the second user information through a preset visual perception device.

[0073] The second user information may include but is not limited to: at least one of a laser point cloud, a depth image or an identification code for representing the user's posture. In the actual implementation process, the user's posture information may be entered into the background system in advance, and an identification code such as a QR code corresponding to each user's posture information may be generated. The visual perception setting device may obtain the user's posture information by identifying the QR code.

[0074] The step of obtaining the second information of the user through a preset visual perception device includes:

[0075] Through the depth camera, the depth image, shoulder width information, the widest distance of the spine, and the narrowest distance of the spine representing the user's body shape are collected;

[0076] Through laser radar, laser point cloud representing the user's body posture is collected.

[0077] It should be noted that there is no order in which step 101, step 102 and step 103 are executed, and the three steps can be executed in parallel; or any two steps can be executed in parallel.

[0078] Step 104: Calculate the first user information and the second user information by using two different algorithms to obtain a distribution map of acupuncture points on the back of the first user and a distribution map of acupuncture points on the back of the second user.

[0079] Two different algorithms are used to calculate the acupuncture point position distribution map on the user's back, and the information between the two acupuncture point position distribution maps on the user's back can be verified and supplemented with each other.

[0080] A feasible method of calculating the first user information and the second user information by two different algorithms to obtain the acupuncture point position distribution map on the back of the first user and the acupuncture point position distribution map on the back of the second user may be as follows:

[0081] The first information of the user and the second information of the user are calculated through a preset database to obtain a distribution map of acupuncture points on the back of the first user;

[0082] The user's first information and the user's second information are calculated using a preset neural network detection algorithm to obtain a distribution map of acupuncture points on the back of the second user.

[0083] The preset database can also be called an expert database. A large amount of correspondence between user's first information, user's second information and user's back acupuncture point location distribution map can be managed in the preset database. When calculating the user's back acupuncture point location distribution map based on the preset database, the back acupuncture point location distribution map can be quickly obtained by searching the correspondence based on the user's first information and the user's second information.

[0084] The preset neural network is generated by training a large number of back acupuncture point location distribution map samples, and each back acupuncture point location distribution map sample includes: the correspondence between the user's first information, the user's second information, and the user's back acupuncture point location distribution map.

[0085] A preset neural network is used to calculate the second back acupuncture point position distribution map, with high calculation efficiency.

[0086] Step 105: Fusing the acupuncture point position distribution map on the back of the first user and the acupuncture point position distribution map on the back of the second user to generate a third acupuncture point position distribution map on the back of the user.

[0087] An optional method of fusing the acupuncture point location distribution map on the back of a first user and the acupuncture point location distribution map on the back of a second user to generate a acupuncture point location distribution map on the back of a third user is as follows: inputting the acupuncture point location distribution map on the back of the first user, the acupuncture point location distribution map on the back of the second user and the first information of the user into a pre-trained fusion model, and determining the output of the fusion model as the acupuncture point location distribution map on the back of the third user.

[0088] The fusion model is generated and trained based on multiple groups of user first information, the user's back acupuncture point position distribution map before fusion, and the user's back acupuncture point position distribution map after fusion.

[0089] Specifically, construct a system based on the user's first information and the location distribution of the user's back acupuncture points. Figure 1 And the location of the acupuncture points on the user's back Figure 2 As input, and based on the acupuncture points on the user's back Figure 3 The neural network is output, and the neural network is trained to obtain a fusion model. The fusion model obtained by training is used to calculate the acupuncture point position distribution of the first user's back. Figure 1 The acupuncture point distribution on the back of the second user Figure 2 The user's first information and the acupuncture point location distribution on the user's back are integrated. Figure 1 And the location of the acupuncture points on the user's back Figure 2 Input the fusion model to obtain the acupuncture point location distribution of the third user's back Figure 3 .

[0090] Step 106: Generate a robotic arm control solution based on the user demand information and the acupuncture point location distribution map on the back of the third user.

[0091] The robotic arm control scheme may include but is not limited to: movement trajectory, massage intensity, and massage duration.

[0092] An alternative method of generating a robotic arm control solution based on the user demand information and the acupuncture point position distribution map on the back of a third user may include the following steps:

[0093] First, the massage points, massage duration and massage intensity are determined based on user demand information;

[0094] Secondly, based on the massage acupuncture points and the acupuncture point position distribution map of the third user's back, the movement trajectory of the robotic arm is determined;

[0095] Finally, a robotic arm control plan is generated based on the robotic arm movement trajectory, massage duration, and massage intensity.

[0096] This method of flexibly setting the robotic arm control scheme according to the actual needs of the user, the generated scheme is more in line with the user's personalized needs and can enhance the user's massage experience.

[0097] Step 107: According to the robotic arm control scheme, control the robotic arm of the robot to move on the back of the user.

[0098] After determining the robotic arm control plan, just move and massage the user's back according to the robotic arm control plan.

[0099] It should be noted that in the actual implementation process, the robotic arm control plan corresponding to the user's current demand can also be archived and managed. When the user has the same demand next time, he can directly call the matching robotic arm control plan in the archive, without the need to spend time calculating and formulating the robotic arm control plan.

[0100] The vision-based robot massage method provided in the embodiment of the present application calculates the acupuncture point position distribution map on the user's back through two different algorithms, and then fuses the two calculated acupuncture point position distribution maps on the user's back, which can improve the accuracy of the third user's back acupuncture point position distribution map finally generated. Then, a robotic arm control scheme is generated based on the user's demand information and the acupuncture point position distribution map on the third user's back; according to the robotic arm control scheme, the robotic arm of the robot is controlled to move on the user's back. Since the obtained acupuncture point position distribution map on the back of the third user has high accuracy, the acupuncture points subsequently determined based on the acupuncture point position distribution map on the back of the third user and the user's demand information will also be more accurate, so that the massage effect can be improved, thereby improving the user's massage experience.

[0101] Figure 3 A structural block diagram of a vision-based robotic massage device for implementing an embodiment of the present application.

[0102] The vision-based robot massage device provided in the embodiment of the present application is applied to a robot, and the device includes the following functional modules:

[0103] A first acquisition module 301 is used to acquire first information of a user, wherein the first information is used to represent user attributes;

[0104] The second acquisition module 302 is used to acquire user demand information;

[0105] The third acquisition module 303 is used to acquire the second information of the user through a preset visual perception device, wherein the second information of the user includes: at least one of a laser point cloud, a depth image or an identification code for representing the user's body shape;

[0106] A calculation module 304 is used to calculate the first user information and the second user information by using two different algorithms to obtain a distribution map of acupuncture points on the back of the first user and a distribution map of acupuncture points on the back of the second user;

[0107] A fusion module 305 is used to fuse the acupuncture point position distribution map of the first user's back and the acupuncture point position distribution map of the second user's back to generate a third user's back acupuncture point position distribution map;

[0108] A generating module 306, configured to generate a robot arm control scheme according to the user demand information and the acupuncture point position distribution map of the third user's back;

[0109] The control module 307 is used to control the robot's mechanical arm to move on the user's back according to the mechanical arm control scheme.

[0110] Optionally, the first acquisition module includes:

[0111] A first calling submodule, configured to collect first voice information input by a user through a voice interaction device, and identify the first user information from the first voice information, wherein the first user information includes: at least one of the user's gender, height, and weight;

[0112] The second calling submodule is used to receive first user information input by the user through an electronic input device.

[0113] Optionally, the third acquisition module includes:

[0114] The third calling submodule is used to collect a depth image representing the user's body shape, shoulder width information, the widest distance of the middle spine, and the narrowest distance of the middle spine through a depth camera;

[0115] The fourth calling submodule is used to collect laser point clouds representing the user's body posture through laser radar.

[0116] Optionally, the calculation module includes:

[0117] A first calculation submodule, configured to calculate the first information of the user and the second information of the user through a preset database to obtain a distribution map of acupuncture points on the back of the first user;

[0118] The second calculation submodule is used to calculate the first information of the user and the second information of the user through a preset neural network detection algorithm to obtain a distribution map of acupuncture points on the back of the second user.

[0119] Optionally, the fusion module is specifically used for:

[0120] Inputting the acupuncture point position distribution map of the first user's back, the acupuncture point position distribution map of the second user's back, and the first information of the user into a pre-trained fusion model, and determining the output of the fusion model as the acupuncture point position distribution map of the third user's back;

[0121] The fusion model is generated by training based on multiple groups of user first information, a distribution map of user back acupuncture points before fusion, and a distribution map of user back acupuncture points after fusion.

[0122] Optionally, the generating module includes:

[0123] A first determination submodule is used to determine massage points, massage duration and massage intensity according to the user demand information;

[0124] A first determination submodule, configured to determine a movement trajectory of the robotic arm based on the massage acupuncture points and the acupuncture point position distribution map of the third user's back;

[0125] A generation submodule is used to generate a robotic arm control plan based on the movement trajectory of the robotic arm, the massage duration and the massage intensity.

[0126] The vision-based robot massage device provided in the embodiment of the present application calculates the acupuncture point position distribution map on the user's back through two different algorithms, and then fuses the two calculated acupuncture point position distribution maps on the user's back, which can improve the accuracy of the third user's back acupuncture point position distribution map finally generated. Then, a robotic arm control scheme is generated based on the user's demand information and the acupuncture point position distribution map on the third user's back; according to the robotic arm control scheme, the robotic arm of the robot is controlled to move on the user's back. Since the obtained acupuncture point position distribution map on the back of the third user has a high accuracy, the acupuncture points subsequently determined based on the acupuncture point position distribution map on the back of the third user and the user's demand information will also be more accurate, so that the massage effect can be improved, thereby improving the user's massage experience.

[0127] In the present application embodiment Figure 3The visual-based robotic massage device shown can be a device, or a component, integrated circuit, or chip in a server. Figure 3 The visual-based robotic massage device shown may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0128] The embodiments of the present application provide Figure 3 The vision-based robotic massage device shown can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0129] Alternatively, if Figure 4 As shown, an embodiment of the present application further provides an electronic device 400, including a processor 401, a memory 402, and a program or instruction stored in the memory 402 and executable on the processor 401. When the program or instruction is executed by the processor 401, each process of the above-mentioned vision-based robot massage method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0130] It should be noted that the electronic device in the embodiment of the present application includes the server described above.

[0131] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned vision-based robot massage method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0132] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0133] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned vision-based robot massage method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0134] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0135] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0136] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A vision-based robot massage device, applied to a robot, characterized in that: The device comprises: A first acquisition module is used to acquire first information of a user, wherein the first information of the user is used to represent user attributes; The second acquisition module is used to acquire user demand information; A third acquisition module is used to acquire the second information of the user through a preset visual perception device, wherein the second information of the user includes: at least one of a laser point cloud, a depth image or an identification code for representing the user's body shape; The third acquisition module includes: The third calling submodule is used to collect a depth image representing the user's body shape, shoulder width information, the widest distance of the middle spine, and the narrowest distance of the middle spine through a depth camera; The fourth calling submodule is used to collect a laser point cloud representing the user's body posture through a laser radar; A calculation module, used to calculate the first user information and the second user information by using two different algorithms to obtain a distribution map of acupuncture points on the back of the first user and a distribution map of acupuncture points on the back of the second user; A fusion module, configured to fuse the acupuncture point position distribution map on the back of the first user and the acupuncture point position distribution map on the back of the second user to generate a acupuncture point position distribution map on the back of a third user; A generating module, configured to generate a robot arm control scheme according to the user demand information and the acupuncture point position distribution map on the back of the third user; The control module is used to control the robot's mechanical arm to move on the user's back according to the mechanical arm control scheme.

2. The device according to claim 1, characterized in that The first acquisition module includes: A first calling submodule, configured to collect first voice information input by a user through a voice interaction device, and identify the first user information from the first voice information, wherein the first user information includes: at least one of the user's gender, height, and weight; The second calling submodule is used to receive the first user information input by the user through the electronic input device.

Images