Mechanical arm massage control method, system and equipment and storage medium

Abstract

The invention provides a mechanical arm massage control method and system, and the method comprises the steps: determining a massage target region based on a preset visual sensor; establishing a hardness and strength mapping model; in the massage process, the massage position of the target area and muscle hardness information of the corresponding position are obtained, and the massage position and the muscle hardness information of the corresponding position are associated and bound; in the massage process, when the mechanical arm moves to a new massage position, muscle hardness data and a position identifier of the position are obtained, a muscle hardness value under the position identifier is input into the hardness and strength mapping model, and a predicted muscle hardness value of the position identifier is obtained; the predicted muscle hardness value under the obtained position identifier is compared with the strength actually applied by the mechanical arm at present, and the strength difference value of the predicted muscle hardness value and the strength actually applied by the mechanical arm is obtained; when the force difference value exceeds the preset threshold value, the predicted massage force value corresponding to the muscle hardness serves as the massage force after the mechanical arm is adjusted, the corresponding massage force is provided according to the muscle hardness characteristics, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of robotic arm rehabilitation massage, and specifically to a robotic arm massage control method, system, device and storage medium. Background Art

[0002] Although the current robotic arm massage technology can provide automated massage services to a certain extent, its inherent limitations make it difficult to meet the diverse needs of users in practical applications. The core problem of this technology is that it over-relies on preset paths and fixed forces, lacks sufficient flexibility and adaptability, thus affecting the massage effect and user experience.

[0003] First of all, the problem with the preset path is that it cannot fully take into account the differences between individuals and the changing needs of the same individual in different states. Everyone's body structure, muscle distribution and sensitivity are different. Even for the same person, the demand for massage position and intensity will change under different physiological and psychological states. For example, when a person feels particularly nervous or tired, he may need a deeper massage and greater force to relieve muscle tension; while in a relaxed state, he may prefer a gentle massage and moderate force. However, existing robotic arm massage systems can usually only perform massages according to pre-set paths and cannot be flexibly adjusted according to the user's real-time needs.

[0004] Secondly, the problem of fixed force is equally significant. Robotic arm massage systems usually provide several fixed force levels for users to choose from, but these levels often cannot accurately match the actual needs of users. On the one hand, due to individual differences, even the same force level may produce completely different feelings for different people. On the other hand, even on the same person, the demand for force may change as the massage progresses and the body reacts. However, existing robotic arm massage systems can usually only provide fixed force output and cannot automatically adjust based on real-time feedback from users.

[0005] This lack of flexibility and adaptability of the robotic arm massage system often results in poor massage effects and may even cause discomfort to the user in some cases. When users feel that the massage force is too strong or too weak, and the system does not provide suitable adjustment options, they can only be forced to accept this uncomfortable massage experience or manually adjust the massage force. However, due to the fixed strength level, it is often difficult for users to find a strength that fully meets their needs. In this case, users may feel disappointed and dissatisfied, and their overall evaluation of the robotic arm massage system will also be reduced.

[0006] In addition, for certain user groups, such as the elderly, the disabled, or people with special physical needs, they may have more refined and personalized requirements for the strength and position of massage. However, due to the limitations of existing robotic arm massage systems, these users often find it difficult to get massage services that meet their needs, further limiting the widespread application and popularization of robotic arm massage technology.

[0007] In summary, the current robotic arm massage technology has the problem of fixing the force on the preset path, which not only affects the massage effect and user experience, but also limits the further development and application of the technology. Therefore, it is necessary to conduct in-depth research and improvement on these issues to improve the flexibility and adaptability of robotic arm massage technology and better meet the diverse needs of users. Summary of the invention

[0008] In order to overcome the problem of fixing the force on a preset path in the prior art, which affects the massage effect and user experience, the present application provides a robotic arm massage control method and system, which adopts the following technical solutions:

[0009] In a first aspect, the present application provides a robotic arm massage control method, comprising:

[0010] Determine the target area for massage based on the preset visual sensor;

[0011] Establish a hardness-force mapping model;

[0012] During the massage process, the massage position of the target area and the muscle hardness information of the corresponding position are obtained, and the massage position and the muscle hardness information of the corresponding position are associated and bound;

[0013] During the massage process, when the robotic arm moves to a new massage position, the muscle hardness data and position identifier of the position are obtained, the muscle hardness value under the position identifier is input into the hardness force mapping model, and the predicted muscle hardness value of the position identifier is obtained;

[0014] Compare the predicted muscle hardness value obtained under the position identifier with the actual force currently applied by the robotic arm to obtain the force difference between the two;

[0015] When the force difference exceeds a preset threshold, the predicted massage force value corresponding to the muscle hardness is used as the massage force adjusted by the robotic arm.

[0016] Furthermore, the step of determining the target area for massage based on a preset visual sensor specifically includes:

[0017] Converting the visual data into a grayscale image and performing denoising filtering to obtain preprocessed visual data;

[0018] Based on the preset massage area, obtaining anatomical landmarks related to the massage area, identifying the positions of the anatomical landmarks in the pre-processed visual data based on feature point detection, and determining the initial massage area;

[0019] Extracting texture features of the initial massage area using a gray-level co-occurrence matrix, calculating shape features of the initial massage area, and performing weighted average fusion of the texture features and the shape features to generate comprehensive features;

[0020] The massage area that meets the preset threshold in the comprehensive features is selected as the target area for massage.

[0021] Furthermore, the establishment of the hardness force mapping model specifically includes:

[0022] Obtain the user's muscle hardness type, and based on the user's muscle hardness type, obtain a historical massage data set of the same muscle hardness type, wherein the historical massage data set includes a muscle hardness value and a massage strength value, wherein different muscle hardness values ​​correspond to appropriate massage strength values;

[0023] Based on the historical massage dataset, we obtain information entropy. Assume that there are n different massage intensity categories in the historical massage dataset D, and the frequency of each category i is p. i , then the information entropy is Based on the preset muscle hardness threshold, different muscle hardness values ​​are divided into different nodes to obtain sub-datasets; based on the muscle hardness features, the information gain corresponding to the sub-datasets is obtained; assuming that the muscle hardness feature A has v different values, the historical massage dataset D is divided into v subsets D1, D2, ..., D according to feature A. v , then the gain of feature A is Where |D i |It is D i is the number of samples, |D| is the number of samples of D, and the feature with the largest information gain is selected as the root node;

[0024] For each subset after the root node is divided, the above information gain calculation process is repeated to find the muscle hardness division point that can minimize the information entropy again as a new internal node, thereby generating a new branch, and continue to recursively perform until all muscle hardness related features are divided, stop dividing, and take the current node as a leaf node;

[0025] The leaf node stores the massage intensity value. A leaf node contains the massage intensity of multiple samples, and the massage intensity of the samples is y1, y2, ..., y n , get the average value of all massage intensity values ​​corresponding to the leaf nodes as the massage intensity value stored in the current leaf node, the massage intensity value stored in the leaf node is

[0026] Furthermore, during the massage process, the massage position of the target area and the muscle hardness information of the corresponding position are obtained, and the massage position and the muscle hardness information of the corresponding position are associated and bound, specifically including:

[0027] Obtaining position information of the robotic arm massage head during the massage of the target area, and matching the position information of the massage head with a position identifier identified by the visual sensor;

[0028] The muscle hardness data is acquired through a tactile sensor, and the muscle hardness data is bound to its corresponding position identifier.

[0029] Furthermore, the step of acquiring muscle hardness data through a tactile sensor and binding the muscle hardness data to a corresponding position identifier includes:

[0030] The position identifiers are associated with the muscle stiffness values ​​based on a dictionary digital structure, where the keys are the position identifiers and the values ​​correspond to the muscle stiffness values.

[0031] In a second aspect, the present application also provides a robotic arm massage control system, comprising:

[0032] A target area determination module, used to determine a target area for massage based on a preset visual sensor;

[0033] A hardness force mapping model building module is used to build a hardness force mapping model;

[0034] An associated information binding module is used to obtain the massage position of the target area and the muscle hardness information of the corresponding position during the massage process, and associate and bind the massage position with the muscle hardness information of the corresponding position;

[0035] A predicted muscle hardness value acquisition module is used to obtain the muscle hardness data and position identifier of a new massage position when the robotic arm moves to the position during massage, input the muscle hardness value under the position identifier into the hardness force mapping model, and obtain the predicted muscle hardness value of the position identifier;

[0036] A force difference acquisition module is used to compare the predicted muscle hardness value obtained under the position identifier with the actual force currently applied by the robotic arm to obtain the force difference between the two;

[0037] The robot arm massage force adjustment module is used to use the predicted massage force value corresponding to the muscle hardness as the massage force after the robot arm is adjusted when the force difference exceeds a preset threshold.

[0038] In a third aspect, the present application provides an electronic device, including:

[0039] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0041] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0042] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0043] This application has the following beneficial effects:

[0044] 1. The present application determines the target area for massage based on a preset visual sensor. By determining the target area for massage through a preset visual sensor, the body part that needs massage can be accurately located, which helps to avoid deviation in the massage position, especially for complex human anatomical structures, such as between different muscle groups on the back of the human body. The target muscles can be accurately found for massage, thereby improving the accuracy and effectiveness of the massage.

[0045] 2. This application adjusts the massage intensity by combining the muscle hardness information of different positions, fully considering individual differences and the characteristics of different parts of the body. During the massage process, the massage position and the corresponding muscle hardness information are obtained in real time, and they are associated and bound, so that the massage strategy can be adjusted in time according to the current physical condition.

[0046] 3. When the robotic arm in this application moves to a new position, it can obtain the muscle hardness data of that position and predict the appropriate massage strength, and then compare it with the current actual strength. When the strength difference exceeds the threshold, it will be adjusted. This application uses a dynamic adjustment mechanism to ensure that the massage strength always remains within the appropriate range. This application can not only improve the comfort of the massage, but also optimize the massage effect according to the real-time state of the muscles. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0048] Figure 2This is a flow chart of the robotic arm massage control method according to an embodiment of the present application;

[0049] Figure 3 A flow chart for determining a massage target area according to an embodiment of the present application;

[0050] Figure 4 A flow chart for establishing a hardness force mapping model for an embodiment of the present application;

[0051] Figure 5 A flowchart of associating and binding massage positions with muscle hardness information of corresponding positions according to an embodiment of the present application;

[0052] Figure 6 This is a system flow chart of an embodiment of the present application;

[0053] Figure 7 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0055] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0057] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0058] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant terminal devices 101, 102, 103 can be communication tools with display screens and support web browsing, email clients, social platform software, etc.

[0059] Various electronic devices, including but not limited to smartphones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptop computers and desktop computers, etc.

[0060] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0061] It should be noted that the robotic arm massage control method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the robotic arm massage control system is generally arranged in the server / terminal device.

[0062] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0063] Continue to refer Figure 2 , the figure shows a flow chart of a mechanical arm massage control method of the present application, the method comprising the following steps:

[0064] Step 201, determining a massage target area based on a preset visual sensor.

[0065] In a possible implementation, the target area of ​​massage is determined based on a preset visual sensor. Figure 3 , the specific contents include:

[0066] Step 31, converting the visual data into a grayscale image and performing denoising filtering to obtain pre-processed visual data;

[0067] Step 32, based on the preset massage area, obtaining anatomical landmarks related to the massage area, identifying the positions of the anatomical landmarks in the pre-processed visual data based on feature point detection, and determining the initial massage area;

[0068] For example, different massage areas involve different anatomical landmarks; for example, the back massage area is usually related to landmarks such as the spine and shoulder blades; the shoulder massage area is related to landmarks such as the clavicle and scapula; the leg massage area may be related to landmarks such as the hip joint and knee joint.

[0069] Step 33, extracting texture features of the initial massage area using a gray level co-occurrence matrix, calculating shape features of the initial massage area, and performing weighted average fusion of the texture features and the shape features to generate comprehensive features;

[0070] Explanation: Within the massage area, changes in texture features can help identify different sub-areas. For example, in a back massage, the skin texture near the spine is different from the skin texture near the shoulder. Extracting texture features helps to accurately locate and distinguish the massage areas corresponding to different muscle groups. Shape features can accurately define the boundaries of the massage area. Shape features help match the massage area with the human anatomy; accurate shape features can ensure that the massage area is consistent with the actual anatomical structure such as muscles and bones, thereby improving the effectiveness and safety of the massage. For example, in a leg massage, shape features are used to determine whether the massage area accurately covers the thigh muscle group or the calf muscle group to avoid unnecessary pressure on joints and other parts.

[0071] Step 34, selecting massage areas that meet a preset threshold in the comprehensive features as massage target areas.

[0072] Step 202, establishing a hardness strength mapping model;

[0073] In a possible implementation, the hardness force mapping model is established. Please refer to Figure 4 , the specific contents include:

[0074] Step 41, obtain the user's muscle hardness type, and obtain a historical massage data set of the same muscle hardness type based on the user's muscle hardness type, wherein the historical massage data set includes muscle hardness values ​​and massage strength values, wherein different muscle hardness values ​​correspond to appropriate massage strength values; for example, the muscle hardness of sprinters is mainly concentrated in a higher range, and the corresponding massage strength is larger; while the muscle hardness of yoga athletes is relatively low, and the massage strength is also smaller; there seem to be different rules between the muscle hardness and massage strength of different people.

[0075] Step 42, obtain the root node: obtain information entropy based on the historical massage data set. Assume that there are n different massage intensity categories in the historical massage data set D, and the frequency of each category i is p i , then the information entropy is Based on the preset muscle hardness threshold, different muscle hardness values ​​are divided into different nodes to obtain sub-datasets; based on the muscle hardness features, the information gain corresponding to the sub-datasets is obtained; assuming that the muscle hardness feature A has v different values, the historical massage dataset D is divided into v subsets D1, D2, ..., D according to feature A. v , then the gain of feature A is Where |D i |It is D i is the number of samples, |D| is the number of samples of D, and the feature with the largest information gain is selected as the root node; for example, if it is found that when the muscle hardness is divided by a certain value x0, the information gain is the largest, then the division condition of the root node is "whether the muscle hardness is greater than x0".

[0076] Step 43, obtaining child nodes: for each subset after the root node is divided, repeat the above information gain calculation process, and find the muscle hardness division point that can minimize the information entropy again as a new internal node, thereby generating a new branch, and continue to recursively perform until all muscle hardness related features are divided, stop the division, and use the current node as a leaf node. For example, in the subset of "muscle hardness greater than x0" after the root node is divided, continue to find a new division point x1 so that the information gain is maximized when divided by x1, so as to construct the internal nodes and branches of the next layer.

[0077] Step 44: the leaf node stores the massage intensity value. A leaf node contains the massage intensity of multiple samples, and the massage intensity of the samples is y1, y2, ..., y n , get the average value of all massage intensity values ​​corresponding to the leaf nodes as the massage intensity value stored in the current leaf node, the massage intensity value stored in the leaf node is

[0078] Step 203, during the massage process, obtaining massage positions of the target area and muscle hardness information of corresponding positions, and associating and binding the massage positions with the muscle hardness information of corresponding positions;

[0079] In a possible implementation, during the massage process, the massage position of the target area and the muscle hardness information of the corresponding position are obtained, and the massage position and the muscle hardness information of the corresponding position are associated and bound. Please refer to Figure 5 , specifically:

[0080] Step 51, obtaining the position information of the massage head of the robotic arm during the massage of the target area, and making the position information of the massage head correspond to the position identifier recognized by the visual sensor;

[0081] Step 52, obtaining muscle hardness data through a tactile sensor, and binding the muscle hardness data to its corresponding position identifier.

[0082] In one possible implementation, the location identifier is associated with the muscle hardness value based on a dictionary digital structure, wherein the key is the location identifier and the value corresponds to the muscle hardness value.

[0083] Step 204, during the massage process, when the robotic arm moves to a new massage position, the muscle hardness data and position identifier of the position are obtained, the muscle hardness value under the position identifier is input into the hardness force mapping model, and the predicted muscle hardness value of the position identifier is obtained.

[0084] Step 205, comparing the predicted muscle hardness value obtained under the position identifier with the actual force currently applied by the robotic arm to obtain the force difference between the two;

[0085] Step 206, when the force difference exceeds a preset threshold, the predicted massage force value corresponding to the muscle hardness is used as the massage force adjusted by the robotic arm.

[0086] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0087] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0088] Continue to refer Figure 6, the robotic arm massage control system described in this embodiment includes:

[0089] The target area determination module 601 is used to determine the target area of ​​massage based on a preset visual sensor;

[0090] A hardness strength mapping model establishing module 602 is used to establish a hardness strength mapping model;

[0091] The associated information binding module 603 is used to obtain the massage position of the target area and the muscle hardness information of the corresponding position during the massage process, and associate and bind the massage position with the muscle hardness information of the corresponding position;

[0092] The predicted muscle hardness value acquisition module 604 is used to acquire the muscle hardness data and position identifier of a new massage position when the robotic arm moves to the position during the massage process, input the muscle hardness value under the position identifier into the hardness force mapping model, and acquire the predicted muscle hardness value of the position identifier;

[0093] A force difference acquisition module 605 is used to compare the predicted muscle hardness value obtained under the position identifier with the actual force currently applied by the robot arm to obtain the force difference between the two;

[0094] The robot arm massage force adjustment module 606 is used to use the predicted massage force value corresponding to the muscle hardness as the massage force after the robot arm is adjusted when the force difference exceeds a preset threshold.

[0095] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0096] The computer device 7 includes a memory 7a, a processor 7b, and a network interface 7c that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 7 with components 7a-7c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0097] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0098] The memory 7a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 7a can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 7a can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 7. Of course, the memory 7a can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 7a is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the robot arm massage control method, etc. In addition, the memory 7a can also be used to temporarily store various types of data that have been output or are to be output.

[0099] The processor 7b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 7b is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 7b is used to run the program code stored in the memory 7a or process data, such as running the program code of the robotic arm massage control method.

[0100] The network interface 7c may include a wireless network interface or a wired network interface. The network interface 7c is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0101] The present application also provides another embodiment, namely, providing a non-volatile computer-readable storage medium, which stores a program of a robotic arm massage control method, and the robotic arm massage control can be executed by at least one processor so that the at least one processor performs the steps of the robotic arm massage control method as described above.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0103] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A robotic arm massage control method, characterized in that: include: Determine the target area for massage based on the preset visual sensor; Establish a hardness-force mapping model; During the massage process, the massage position of the target area and the muscle hardness information of the corresponding position are obtained, and the massage position and the muscle hardness information of the corresponding position are associated and bound; During the massage process, when the robotic arm moves to a new massage position, the muscle hardness data and position identifier of the position are obtained, the muscle hardness value under the position identifier is input into the hardness force mapping model, and the predicted muscle hardness value of the position identifier is obtained; Compare the predicted muscle hardness value obtained under the position identifier with the actual force currently applied by the robotic arm to obtain the force difference between the two; When the force difference exceeds a preset threshold, the predicted massage force value corresponding to the muscle hardness is used as the massage force adjusted by the robotic arm.

2. The robotic arm massage control method according to claim 1, characterized in that: The step of determining the target area for massage based on a preset visual sensor specifically includes: Converting the visual data into a grayscale image and performing denoising filtering to obtain preprocessed visual data; Based on the preset massage area, obtaining anatomical landmarks related to the massage area, identifying the positions of the anatomical landmarks in the pre-processed visual data based on feature point detection, and determining the initial massage area; Extracting texture features of the initial massage area using a gray-level co-occurrence matrix, calculating shape features of the initial massage area, and performing weighted average fusion of the texture features and the shape features to generate comprehensive features; The massage area that meets the preset threshold in the comprehensive features is selected as the target area for massage.

3. The robotic arm massage control method according to claim 1, characterized in that: The establishment of the hardness force mapping model specifically includes: Obtain the user's muscle hardness type, and based on the user's muscle hardness type, obtain a historical massage data set of the same muscle hardness type, wherein the historical massage data set includes a muscle hardness value and a massage strength value, wherein different muscle hardness values ​​correspond to appropriate massage strength values; Based on the historical massage dataset, we obtain information entropy. Assume that there are n different massage intensity categories in the historical massage dataset D, and the frequency of each category i is p. i , then the information entropy is Based on the preset muscle hardness threshold, different muscle hardness values ​​are divided into different nodes to obtain sub-datasets; based on the muscle hardness features, the information gain corresponding to the sub-datasets is obtained; assuming that the muscle hardness feature A has v different values, the historical massage dataset D is divided into v subsets D1, D2, ..., D according to feature A. v , then the gain of feature A is Where |D i |It is D i is the number of samples, |D| is the number of samples of D, and the feature with the largest information gain is selected as the root node; For each subset after the root node is divided, the above information gain calculation process is repeated to find the muscle hardness division point that can minimize the information entropy again as a new internal node, thereby generating a new branch, and continue to recursively perform until all muscle hardness related features are divided, stop dividing, and take the current node as a leaf node; The leaf node stores the massage intensity value. A leaf node contains the massage intensity of multiple samples, and the massage intensity of the samples is y1, y2, ..., y n , get the average value of all massage intensity values ​​corresponding to the leaf nodes as the massage intensity value stored in the current leaf node, the massage intensity value stored in the leaf node is 4. The robotic arm massage control method according to claim 1, characterized in that: During the massage process, the massage position of the target area and the muscle hardness information of the corresponding position are obtained, and the massage position and the muscle hardness information of the corresponding position are associated and bound, specifically including: Obtaining position information of the robotic arm massage head during the massage of the target area, and matching the position information of the massage head with a position identifier identified by the visual sensor; The muscle hardness data is acquired through a tactile sensor, and the muscle hardness data is bound to its corresponding position identifier.

5. The robotic arm massage control method according to claim 1, characterized in that: The method of acquiring muscle hardness data through a tactile sensor and binding the muscle hardness data to a corresponding position identifier includes: The position identifiers are associated with the muscle stiffness values ​​based on a dictionary digital structure, where the keys are the position identifiers and the values ​​correspond to the muscle stiffness values.

6. A robotic arm massage control system, used to implement the robotic arm massage control method of claims 1-5, characterized in that: include: A target area determination module, used to determine a target area for massage based on a preset visual sensor; A hardness force mapping model building module is used to build a hardness force mapping model; An associated information binding module is used to obtain the massage position of the target area and the muscle hardness information of the corresponding position during the massage process, and associate and bind the massage position with the muscle hardness information of the corresponding position; A predicted muscle hardness value acquisition module is used to obtain the muscle hardness data and position identifier of a new massage position when the robotic arm moves to the position during massage, input the muscle hardness value under the position identifier into the hardness force mapping model, and obtain the predicted muscle hardness value of the position identifier; A force difference acquisition module is used to compare the predicted muscle hardness value obtained under the position identifier with the actual force currently applied by the robotic arm to obtain the force difference between the two; The robot arm massage force adjustment module is used to use the predicted massage force value corresponding to the muscle hardness as the massage force after the robot arm is adjusted when the force difference exceeds a preset threshold.

7. An electronic device, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, when the instructions are executed by the device, the device performs the steps of the robotic arm massage control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the steps of the robotic arm massage control method as claimed in any one of claims 1 to 5.

Images