Hammer management system and method for a hammering extension rehabilitation machine

Abstract

The application discloses a hammer management system and method of a hammer stretching physical therapy rehabilitation machine, relates to the technical field of physical therapy massage machine control, and solves the technical problem that the massage machine in the prior art is difficult to adaptively adjust the strength or frequency of a massage hammer according to the state of a user, thereby reducing the experience of the user; a description voice of a user is acquired, the description voice is preprocessed and then input into a language recognition model, and a massage part and a massage scheme are obtained; the massage scheme comprises massage strength and massage frequency; an adjusted massage scheme is generated based on real-time acquired performance data or physiological monitoring data in a massage process, and the massage scheme is adjusted based on the adjusted massage scheme; the performance data comprises voice data and image data of the user, and the physiological monitoring data comprises electromyographic signals, muscle pressure and muscle temperature of the massage part; and the experience of a person being massaged is greatly improved.

Description

Technical Field

[0001] This application belongs to the field of physiotherapy and massage machine control technology, specifically a hammering management system and method for a hammering and stretching physiotherapy rehabilitation machine. Background Technology

[0002] With the continuous improvement of science and technology and the increasing maturity of robotics, service robots have emerged as the best solution to this social contradiction. While intelligent robots can currently replace manual operations, they have not yet entered the traditional Chinese medicine physiotherapy industry, such as fascia massage. Furthermore, intelligent robots, based on their safety, stability, and reliability, can be used in the personal health and wellness industry.

[0003] Existing massage machines allow users to adjust the hammering force and frequency of the massage hammers according to their needs. If adjustments to the force and frequency are required during a massage, the user must control the machine or have someone else adjust it. However, manually adjusting the hammer force often relies on the user's or the person adjusting the machine's controls to ensure precise control. Adjusting the force and frequency based on the person's subjective feeling can lead to excessive or insufficient force, thus reducing the user's experience. Therefore, a hammering management system and method are needed for hammering stretching therapy and rehabilitation machines. Summary of the Invention

[0004] This application provides a hammer management system and method for a hammer-based stretching and rehabilitation therapy machine, which solves the technical problem that existing massage machines are unable to adaptively adjust the intensity or frequency of the massage hammer according to the user's state, resulting in a reduced user experience.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a hammering management method for a hammering stretching physiotherapy rehabilitation machine is provided, including:

[0007] The system acquires the user's descriptive speech, preprocesses the speech, and inputs it into a language recognition model. The preprocessing of the speech includes recognizing the speech and converting it into descriptive text. The system then obtains the massage areas and massage plan, including massage intensity and frequency.

[0008] Massage the massage areas according to the massage plan;

[0009] During the massage, an adjustment massage plan is generated based on real-time acquired performance data or physiological monitoring data, and the massage plan is adjusted accordingly. The performance data includes the user's voice data and image data. The physiological monitoring data includes electromyographic signals, muscle pressure, and muscle temperature at the massage site. The electromyographic signals are acquired through electrode pads set at the massage site, the muscle pressure signals are acquired through pressure sensors installed on the massage head, and the muscle temperature is acquired through temperature sensors installed on the massage head.

[0010] Based on the above technical solution, in the hammering management system and method of the hammering stretching physiotherapy rehabilitation machine provided in this application, the user's descriptive speech is acquired, preprocessed, and then input into a language recognition model to obtain the massage area and massage plan; the massage hammer of the massage machine is controlled to massage the corresponding massage area; during the massage, the massage plan is generated and adjusted based on real-time acquired performance data or physiological monitoring data, and the massage plan is adjusted accordingly; the intensity and frequency of the massage are adjusted in real time based on the subjective and physiological performance of the person being massaged; thereby greatly improving the experience of the person being massaged.

[0011] In conjunction with the first aspect above, in one possible implementation, one training method for the language recognition model includes:

[0012] The process involves acquiring voice descriptions from several users, converting them into text descriptions, extracting keywords from the text descriptions, and identifying the corresponding massage areas and massage plans. These massage areas and plans are selections made by experts based on the users' voice descriptions or the keywords. The voice descriptions, keywords, and corresponding massage areas and plans are then integrated into training data. Finally, the voice descriptions and corresponding massage areas and plans are integrated into validation data.

[0013] The training data is used to train the artificial intelligence model, and the test data is used to test the trained artificial intelligence model. The final input is the descriptive text, and the output is the massage area and massage plan corresponding to the descriptive text. The artificial intelligence model includes recurrent neural network models, etc. It can be understood that the training data in the training method provided in this embodiment includes keywords of the descriptive text, and the model execution process includes extracting keywords, analyzing keywords, and matching massage areas and massage plans. It does not require analysis based on the full text of the descriptive text, which greatly reduces the amount of data processing and facilitates the increase of model processing efficiency.

[0014] In conjunction with the first aspect above, in one possible implementation, generating the adjustment massage plan based on real-time acquired performance data includes:

[0015] Extract voice data and image data from the performance data; the image data is a facial image of the user; convert the voice data into descriptive text;

[0016] The descriptive text and facial image are input into a trained hybrid recognition model to obtain adjustment intensity and adjustment frequency. The adjustment intensity and adjustment frequency are integrated into an adjustment massage plan. The adjustment intensity includes adjustment direction and adjustment intensity value. The adjustment direction includes positive and negative directions, where positive direction indicates increasing intensity and negative direction indicates decreasing intensity. The adjustment frequency includes adjustment direction and adjustment frequency value. The adjustment direction includes positive and negative directions, where positive direction indicates increasing frequency and negative direction indicates decreasing frequency.

[0017] In conjunction with the first aspect above, in one possible implementation, one training method for the hybrid recognition model includes:

[0018] Acquire several descriptive texts and facial images; as well as the adjustment intensity and adjustment frequency corresponding to the descriptive texts and facial images; integrate the several descriptive texts and facial images, as well as the adjustment intensity and adjustment frequency corresponding to the descriptive texts and facial images, into several training data and test data;

[0019] The artificial intelligence model is trained using training data and tested using a testing model. The final input consists of descriptive text and facial images, and the output consists of the adjustment intensity and adjustment frequency corresponding to the descriptive text and facial images. The artificial intelligence model includes a recurrent neural network model.

[0020] In conjunction with the first aspect above, in one possible implementation, the adjustment massage plan is generated based on real-time acquired physiological monitoring data, including:

[0021] Extract electromyographic signals, muscle pressure, and muscle temperature from physiological monitoring data; generate a muscle relaxation score based on electromyographic signals, muscle pressure, and muscle temperature;

[0022] When the muscle relaxation score is greater than the set relaxation threshold, it means that the massage has achieved the desired effect, and a stop massage signal is generated.

[0023] When the muscle relaxation score is less than the set relaxation threshold, it means that the massage has not yet achieved the desired effect; an adjustment massage plan is generated based on the muscle relaxation score.

[0024] In conjunction with the first aspect above, in one possible implementation, the method for generating the muscle relaxation score includes:

[0025] Acquire several physiological monitoring data within a set time period; fit the electromyographic signals in each physiological monitoring data into an electromyographic signal change curve according to the corresponding acquisition time sequence; extract the average amplitude (EMGP) of the electromyographic signal change curve;

[0026] Muscle pressure characteristic change curve MP(n) is generated based on muscle pressure data from various physiological monitoring data.

[0027] Muscle temperature change curve MT(t) is generated based on muscle temperature data from various physiological monitoring data.

[0028] Substituting the average amplitude EMGP, the muscle pressure characteristic change curve MP(n), and the muscle temperature change curve MT(t) into the muscle relaxation evaluation function yields the muscle relaxation score SP; the muscle relaxation evaluation function is:

[0029]

[0030] Where SP is the muscle relaxation score, H1() is the set quantization function of muscle temperature and muscle pressure, H2() is the set quantization function of electromyography (EMG) signal; δ1 is the weighting coefficient of the effect of muscle temperature and muscle pressure on muscle relaxation, δ2 is the weighting coefficient of the effect of EMG signal on muscle relaxation, δ1+δ2=1, δ1<δ2; the specific values ​​are set according to experience.

[0031] In conjunction with the first aspect above, in one possible implementation, generating a muscle temperature change curve based on muscle temperature from various physiological monitoring data includes:

[0032] Acquire muscle temperature data from several physiological monitoring data points, and sort each muscle temperature according to its corresponding acquisition time to obtain a muscle temperature array.

[0033] Obtain the movement cycle corresponding to the massage frequency of the massage hammer, obtain all muscle temperatures in the first movement cycle of the muscle temperature data group, and mark the number of muscle temperatures as K. Then, take each muscle temperature as the starting point and the cycle as the step size and continuously select several muscle temperatures in the muscle temperature data group to divide the muscle temperature group into K muscle temperature change groups.

[0034] The muscle temperatures in the muscle temperature change groups are sequentially fitted into muscle temperature change curves MTi(t) according to their corresponding collection times; where i is the number corresponding to the muscle temperature change group; i=1,2,…,K;

[0035] Through formula The muscle temperature change curve is selected as the final muscle temperature change curve MT(t); where T is the duration of the set time, i.e. the time length for collecting several physiological monitoring data.

[0036] In conjunction with the first aspect above, in one possible implementation, the generation of muscle pressure characteristic change curves based on muscle pressure from various physiological monitoring data includes:

[0037] The muscle pressure data from each physiological monitoring data point were fitted into an original pressure change curve YP(t) according to the time sequence of their corresponding collection.

[0038] Through formula The pressure characteristics MPn of the muscle pressure of the massage hammer during the nth movement cycle are calculated; where n is the number of the movement cycle and f is the massage frequency of the massage hammer.

[0039] Each pressure feature is fitted into a pressure feature change curve MP(n) according to the numbering order of the motion cycle.

[0040] In conjunction with the first aspect above, in one possible implementation, the generation of adjustment intensity and adjustment frequency based on several muscle relaxation scores includes:

[0041] Obtain the muscle relaxation score generated this time, as well as the muscle relaxation score and muscle relaxation threshold generated last time, and label them as DSP, XSP, and SPY, respectively; using the formula:

[0042]

[0043] The adjustment ratio TB is calculated; where μ is a set adjustment coefficient used to adjust the distribution of the adjustment ratio TB.

[0044] When the adjustment ratio TB is less than zero, the adjustment direction in the adjustment intensity and adjustment frequency is set to negative, the adjustment intensity value is set to 1+TB times the original intensity value, and the adjustment frequency value is set to 1+TB times the original frequency value.

[0045] When the adjustment ratio TB is greater than zero, the adjustment direction in the adjustment intensity and adjustment frequency is set to positive, the adjustment intensity value is set to 1 + TB times the original intensity value, and the adjustment frequency value is set to 1 + TB times the original frequency value.

[0046] Secondly, this application provides a hammer management device for a hammer stretching physiotherapy rehabilitation machine, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the method described in the first aspect and any possible implementation thereof. The hammer management device for the hammer stretching physiotherapy rehabilitation machine can be an electronic device or a chip within an electronic device.

[0047] Thirdly, this application provides a hammering management system for a hammering stretching physiotherapy rehabilitation machine, including: a data acquisition module, a data analysis module, and a massage adjustment module;

[0048] The data acquisition module includes an image acquisition unit, a voice acquisition unit, and a physiological data acquisition unit;

[0049] The image acquisition unit is used to acquire facial images of the user, and the facial images are integrated into image data;

[0050] The voice acquisition unit is used to collect the user's descriptive voice and voice data;

[0051] The physiological data acquisition unit is used to collect the user's physiological monitoring data, which includes electromyographic signals, muscle pressure, and muscle temperature at the massage site.

[0052] The data analysis module is used to acquire the user's descriptive speech, preprocess the descriptive speech and input it into the language recognition model to obtain the massage area and massage plan; and generate and adjust the massage plan based on the real-time acquired performance data or physiological monitoring data during the massage; the performance data includes the user's voice data and image data;

[0053] The massage adjustment module is used to perform massage based on a massage plan, and to adjust the massage plan based on the adjusted massage plan.

[0054] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a hammer management device of a hammer stretching physiotherapy rehabilitation machine, cause the hammer management device of the hammer stretching physiotherapy rehabilitation machine to perform the method described in the first aspect and any possible implementation thereof.

[0055] Fifthly, this application provides a computer program product containing instructions that, when the computer program product is run on the hammer management device of a hammer stretching physiotherapy rehabilitation machine, cause the hammer management device of the hammer stretching physiotherapy rehabilitation machine to perform the method as described in the first aspect and any possible implementation thereof.

[0056] This application provides a hammering management system and method for a hammering stretching physiotherapy rehabilitation machine. It can acquire the user's descriptive speech, preprocess the speech, and input it into a speech recognition model to obtain massage areas and massage plans; control the massage hammers of the massage machine to massage the corresponding areas; generate and adjust the massage plan based on real-time acquired performance data or physiological monitoring data during the massage process; and adjust the massage plan accordingly. Furthermore, it adjusts the intensity and frequency of the massage in real time based on the subjective and physiological performance of the person being massaged, thereby greatly enhancing the user's experience.

[0057] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic diagram illustrating the steps of a hammer management method for a hammer-assisted stretching physiotherapy rehabilitation machine according to this application.

[0060] Figure 2 This is a schematic diagram of the module connection of the hammer management system of a hammer-stretching physiotherapy rehabilitation machine according to this application. Detailed Implementation

[0061] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0062] Please see Figure 1 Firstly, a method for managing the percussion of a percussion stretching physiotherapy rehabilitation machine is provided, comprising:

[0063] The process involves acquiring the user's descriptive speech, preprocessing the speech, and inputting it into a speech recognition model. The preprocessing includes recognizing the speech and converting it into descriptive text. The process also involves obtaining the massage areas and massage plan, which includes massage intensity and frequency. Finally, the process involves massaging the areas identified through speech recognition as the muscle groups requiring massage.

[0064] During the massage, an adjustment massage plan is generated based on real-time acquired performance data or physiological monitoring data, and the massage plan is adjusted accordingly. The performance data includes the user's voice data and image data; the physiological monitoring data includes electromyographic signals, muscle pressure, and muscle temperature at the massage site; the electromyographic signals are acquired through electrode pads set at the massage site, the muscle pressure signals are acquired through pressure sensors installed on the massage head, and the muscle temperature is acquired through temperature sensors installed on the massage head; it is understood that the massage machine includes at least a robotic arm and a massage hammer head.

[0065] Based on the above technical solution, in the hammering management system and method of the hammering stretching physiotherapy rehabilitation machine provided in this application, the user's descriptive speech is acquired, preprocessed, and then input into a language recognition model to obtain the massage area and massage plan; the massage hammer of the massage machine is controlled to massage the corresponding massage area; during the massage, the massage plan is generated and adjusted based on real-time acquired performance data or physiological monitoring data, and the massage plan is adjusted accordingly; the intensity and frequency of the massage are adjusted in real time based on the subjective and physiological performance of the person being massaged; thereby greatly improving the experience of the person being massaged.

[0066] In one possible implementation, one training method for the language recognition model includes:

[0067] The process involves acquiring voice descriptions from several users, converting them into text descriptions, extracting keywords from the text descriptions, and identifying the corresponding massage areas and massage plans. These massage areas and plans are selections made by experts based on the users' voice descriptions or the keywords. The voice descriptions, keywords, and corresponding massage areas and plans are then integrated into training data. Finally, the voice descriptions and corresponding massage areas and plans are integrated into validation data.

[0068] The AI ​​model is trained using training data and then validated using validation data. Specifically, the descriptive text from the validation data is input into the trained AI model, which outputs corresponding massage areas and massage plans. If the output massage areas match those in the validation data, and the difference between the output and validation plans is within an acceptable range, the validation data passes. Otherwise, the relevant parameters of the AI ​​model need to be adjusted. This process continues until a set percentage of the validation data passes, with a minimum of 80%. The final result is input descriptive text and output corresponding massage areas and plans. The AI ​​model includes recurrent neural network models, etc. It is understood that the training data in this embodiment includes keywords from the descriptive text, and the model execution process includes keyword extraction, keyword analysis, and matching massage areas and plans. This eliminates the need for analysis of the full descriptive text, significantly reducing data processing volume and increasing model processing efficiency.

[0069] In one possible implementation, the adjustment massage plan is generated based on real-time acquired performance data, including: extracting voice data and image data from the performance data; the image data being a facial image of the user; and converting the voice data into descriptive text.

[0070] The descriptive text and facial image are input into a trained hybrid recognition model to obtain adjustment intensity and adjustment frequency. The adjustment intensity and adjustment frequency are integrated into an adjustment massage plan. The adjustment intensity includes adjustment direction and adjustment intensity value. The adjustment direction includes positive and negative directions, where positive direction indicates increasing intensity and negative direction indicates decreasing intensity. The adjustment frequency includes adjustment direction and adjustment frequency value. The adjustment direction includes positive and negative directions, where positive direction indicates increasing frequency and negative direction indicates decreasing frequency.

[0071] In one possible implementation, one training method for the hybrid recognition model includes:

[0072] Acquire several descriptive texts and facial images; as well as the corresponding adjustment intensity and frequency for the descriptive texts and facial images; the adjustment intensity and frequency are set by experts based on the descriptive texts and facial images; for example, when keywords such as pain, ache, or ah appear in the descriptive text, the adjustment intensity needs to be set lower than the current intensity; the adjustment frequency also needs to be set lower than the current frequency; when the facial image recognition shows an expression of pain, the adjustment intensity needs to be set lower than the current intensity; the adjustment frequency also needs to be set lower than the current frequency; integrate the several descriptive texts and facial images, as well as the corresponding adjustment intensity and frequency for the descriptive texts and facial images, into several training data and validation data;

[0073] The artificial intelligence model is trained using training data and validated using a validation model. The final input consists of descriptive text and a facial image, and the output consists of the adjustment intensity and frequency corresponding to the descriptive text and facial image. The artificial intelligence model includes a recurrent neural network model. The training process for the text and image recognition models follows existing artificial intelligence training procedures and will not be described in detail here. This embodiment uses adjustment intensity and direction, and adjustment frequency and direction to allow for mutual verification between adjustment direction and intensity, as well as adjustment direction and frequency, thus preventing errors in intensity or frequency adjustment.

[0074] In one possible implementation, the adjustment massage plan is generated based on real-time acquired physiological monitoring data, including: extracting electromyographic signals, muscle pressure, and muscle temperature from the physiological monitoring data; generating a muscle relaxation score based on the electromyographic signals, muscle pressure, and muscle temperature; the muscle relaxation score is a score that evaluates whether the muscles are relaxed, and the larger the value of the muscle relaxation score, the closer the muscles are to being relaxed.

[0075] When the muscle relaxation score is greater than the set relaxation threshold, it means that the massage has achieved the desired effect, and a stop massage signal is generated. The stop massage signal is used to control the massage to stop. The muscle relaxation threshold is a value set by experts. When it is greater than the value, it means that the muscles are in a good relaxed state. When it is less than the value, it means that the muscles are in a stiff or poor relaxed state. The smaller the relaxation score, the closer the muscles are to a stiff state.

[0076] When the muscle relaxation score is less than the set relaxation threshold, it means that the massage has not yet achieved the desired effect; an adjustment massage plan is generated based on the muscle relaxation score.

[0077] In one possible implementation, one way to generate the muscle relaxation score includes:

[0078] Acquire several physiological monitoring data within a set time period; fit the electromyographic signals in each physiological monitoring data into an electromyographic signal change curve according to the corresponding acquisition time sequence; extract the average amplitude (EMGP) of the electromyographic signal change curve;

[0079] Muscle pressure characteristic change curve MP(n) is generated based on muscle pressure data from various physiological monitoring data.

[0080] Muscle temperature change curve MT(t) is generated based on muscle temperature data from various physiological monitoring data.

[0081] Substituting the average amplitude EMGP, the muscle pressure characteristic change curve MP(n), and the muscle temperature change curve MT(t) into the muscle relaxation evaluation function yields the muscle relaxation score SP; the muscle relaxation evaluation function is:

[0082]

[0083] Where SP is the muscle relaxation score, H1() is the set quantization function of muscle temperature and muscle pressure, H2() is the set quantization function of electromyography (EMG) signal; δ1 is the weighting coefficient of the effect of muscle temperature and muscle pressure on muscle relaxation, δ2 is the weighting coefficient of the effect of EMG signal on muscle relaxation, δ1+δ2=1, δ1<δ2; the specific values ​​are set according to experience.

[0084] For example, the quantization functions for muscle temperature and muscle pressure are:

[0085]

[0086] Wherein, MT(T) is the final value of the muscle temperature change curve, and MT(0) is the initial value of the muscle temperature change curve; MP(N) is the final value of the muscle pressure characteristic change curve, and MP(0) is the initial value of the muscle pressure characteristic change curve; In this embodiment, the influence of muscle temperature and muscle pressure on muscle relaxation score is quantified by the above formula. When the muscle goes from stiff to relaxed, both muscle temperature and muscle pressure tend to stabilize. When muscle temperature or muscle pressure tends to stabilize, it indicates that the muscle has reached a good state of relaxation. The more relaxed the muscle is, the larger the corresponding quantification result value.

[0087] The quantization function for electromyographic signals is:

[0088]

[0089] WEMG is the set standard value for electromyographic signal relaxation, which is the average value of electromyographic signal when the muscle is in a relaxed state. As the muscle relaxes from stiffness, the value of the electromyographic signal will increase due to the increased activity inside the muscle, eventually approaching or exceeding the standard value for electromyographic signal relaxation. The larger the value of the electromyographic signal, the larger the value of its corresponding quantitative result will also be.

[0090] In one possible implementation, generating a muscle temperature change curve based on muscle temperature from various physiological monitoring data includes: acquiring muscle temperature from several physiological monitoring data, and sorting each muscle temperature according to its corresponding acquisition time order to obtain a muscle temperature array.

[0091] Obtain the movement cycle corresponding to the massage frequency of the massage hammer, obtain all muscle temperatures in the first movement cycle of the muscle temperature data group, and mark the number of muscle temperatures as K. Then, take each muscle temperature as the starting point and the cycle as the step size and continuously select several muscle temperatures in the muscle temperature data group to divide the muscle temperature group into K muscle temperature change groups.

[0092] The muscle temperatures in the muscle temperature change groups are sequentially fitted into muscle temperature change curves MTi(t) according to their corresponding collection times; where i is the number corresponding to the muscle temperature change group; i=1,2,…,K;

[0093] Through formula The muscle temperature change curve is selected as the final muscle temperature change curve MT(t); where T is the duration of the set time, i.e. the time length for collecting several physiological monitoring data.

[0094] Because the degree of contact between the massage hammer and the skin varies during massage, the muscle temperature collected by the temperature sensor on the massage hammer may fluctuate slightly. In this embodiment, the muscle temperature measured by the massage hammer at the same location is divided into the same muscle temperature change group, and the group with the highest overall temperature is selected to generate the muscle temperature change curve used for subsequent analysis. That is, the muscle temperature change data of the group with the closest contact between the massage hammer and the skin is selected as the muscle temperature reference for thickness analysis. This avoids inaccurate muscle temperature measurements due to substances such as air between the massage hammer and the skin, and the muscle temperature in the group with the closest contact between the massage hammer and the skin is more accurate, thus ensuring the accuracy of subsequent analysis.

[0095] In one possible implementation, generating a muscle pressure characteristic change curve based on muscle pressure from various physiological monitoring data includes:

[0096] The muscle pressure data from each physiological monitoring data point were fitted into an original pressure change curve YP(t) according to the time sequence of their corresponding collection.

[0097] Through formula The pressure characteristics MPn of the muscle pressure of the massage hammer during the nth movement cycle are calculated; where n is the number of the movement cycle and f is the massage frequency of the massage hammer.

[0098] Each pressure feature is fitted into a pressure feature change curve MP(n) according to the numbering order of the motion cycle.

[0099] For example, during a massage, the massage hammer contacts the skin until it reaches the deepest point and then leaves the skin, which is a complete massage hammer movement cycle. The force collected by the pressure sensor on the massage hammer will first increase from small to large, and then decrease from large to small. When the muscle is in a stiff state, the muscle's cushioning effect is weaker, so the rate of change of muscle pressure is faster, and the final maximum value of muscle pressure will be larger. When the muscle is in a relaxed state, the muscle's cushioning effect is stronger, so the rate of change of muscle pressure is slower, and the final maximum value of muscle pressure will be smaller.

[0100] This embodiment analyzes the presentation of muscle pressure during different exercise cycles, that is, it dynamically evaluates the effect of massage by observing changes in muscle condition, making the evaluation results more accurate.

[0101] In one possible implementation, generating adjustment intensity and adjustment frequency based on several muscle relaxation scores includes:

[0102] Obtain the muscle relaxation score generated this time, as well as the muscle relaxation score and muscle relaxation threshold generated last time, and label them as DSP, XSP, and SPY, respectively; using the formula:

[0103]

[0104] The adjustment ratio TB is calculated. It can be understood that the adjustment ratio TB calculated by the above formula is within (-1, 1). The range of the adjustment ratio can be limited by controlling the adjustment coefficient μ. Here, μ is the set adjustment coefficient used to adjust the distribution of the adjustment ratio TB. The specific value is set according to expert experience. In this embodiment, μ=0.2, and the adjustment ratio TB is within (-0.1, 0.1).

[0105] When the adjustment ratio TB is less than zero, the adjustment direction in the adjustment intensity and adjustment frequency is set to negative, the adjustment intensity value is set to 1+TB times the original intensity value, and the adjustment frequency value is set to 1+TB times the original frequency value.

[0106] When the adjustment ratio TB is greater than zero, the adjustment direction in the adjustment intensity and adjustment frequency is set to positive, the adjustment intensity value is set to 1 + TB times the original intensity value, and the adjustment frequency value is set to 1 + TB times the original frequency value.

[0107] In this embodiment, when the current muscle relaxation score is higher than the previous muscle relaxation score, it indicates that the massage effect is better, and the massage intensity and frequency can be appropriately reduced to avoid muscle damage caused by continuous high-intensity massage. Conversely, the massage intensity and frequency need to be appropriately increased. When the current muscle relaxation score is closer to the muscle relaxation score threshold, the reduction in massage intensity and frequency needs to be increased to avoid muscle damage caused by over-massage. Conversely, the massage intensity and frequency need to be appropriately increased.

[0108] Secondly, this application provides a hammer management device for a hammer stretching physiotherapy rehabilitation machine, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the method described in the first aspect and any possible implementation thereof. The hammer management device for the hammer stretching physiotherapy rehabilitation machine can be an electronic device or a chip within an electronic device.

[0109] Please see Figure 2 Thirdly, this application provides a hammering management system for a hammering stretching physiotherapy rehabilitation machine, including: a data acquisition module, a data analysis module, and a massage adjustment module;

[0110] The data acquisition module includes an image acquisition unit, a voice acquisition unit, and a physiological data acquisition unit;

[0111] The image acquisition unit is used to acquire facial images of the user, and the facial images are integrated into image data;

[0112] The voice acquisition unit is used to collect the user's descriptive voice and voice data;

[0113] The physiological data acquisition unit is used to collect the user's physiological monitoring data, which includes electromyographic signals, muscle pressure, and muscle temperature at the massage site.

[0114] The data analysis module is used to acquire the user's descriptive speech, preprocess the descriptive speech and input it into the language recognition model to obtain the massage area and massage plan, and generate and adjust the massage plan based on the real-time acquired performance data or physiological monitoring data during the massage process; the performance data includes the user's voice data and image data;

[0115] The massage adjustment module is used to perform massage based on a massage plan, and to adjust the massage plan based on the adjusted massage plan.

[0116] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a hammer management device of a hammer stretching physiotherapy rehabilitation machine, cause the hammer management device of the hammer stretching physiotherapy rehabilitation machine to perform the method described in the first aspect and any possible implementation thereof.

[0117] Fifthly, this application provides a computer program product containing instructions that, when the computer program product is run on the hammer management device of a hammer stretching physiotherapy rehabilitation machine, cause the hammer management device of the hammer stretching physiotherapy rehabilitation machine to perform the method as described in the first aspect and any possible implementation thereof.

[0118] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0119] How this application works:

[0120] By acquiring the user's descriptive speech, preprocessing the speech, and inputting it into a language recognition model, the massage areas and massage plan are obtained. The massage hammers of the massage machine are controlled to massage the corresponding areas. During the massage, the massage plan is adjusted based on real-time acquired performance data or physiological monitoring data, and the massage plan is adjusted accordingly. The intensity and frequency of the massage are adjusted in real time based on the subjective and physiological performance of the person being massaged, thereby greatly improving the experience of the person being massaged.

[0121] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A hammering management system for a hammering stretching physiotherapy rehabilitation machine, characterized in that, include: Data acquisition module, data analysis module, and massage adjustment module; The data acquisition module includes an image acquisition unit, a voice acquisition unit, and a physiological data acquisition unit; The image acquisition unit is used to acquire facial images of the user, and the facial images are integrated into image data; The voice acquisition unit is used to collect the user's descriptive voice and voice data; The physiological data acquisition unit is used to collect the user's physiological monitoring data, which includes electromyographic signals, muscle pressure, and muscle temperature at the massage site. The data analysis module is used to acquire the user's descriptive speech, preprocess the descriptive speech and input it into the language recognition model to obtain the massage area and massage plan, and generate and adjust the massage plan based on the real-time acquired performance data or physiological monitoring data during the massage process. The performance data includes the user's voice data and image data; The adjusted massage plan is generated based on real-time acquired physiological monitoring data, including: Extract electromyographic signals, muscle pressure, and muscle temperature from physiological monitoring data; generate a muscle relaxation score based on electromyographic signals, muscle pressure, and muscle temperature; When the muscle relaxation score is greater than the set relaxation threshold, a stop massage signal is generated; When the muscle relaxation score is less than the set relaxation threshold, the adjustment intensity and frequency are generated based on the muscle relaxation score; the adjustment intensity and frequency are then integrated into a fine-tuning massage plan. The adjustment of the massage program includes a stop massage signal or a fine-tuning of the massage program. One method for generating the muscle relaxation score includes: Acquire several physiological monitoring data within a set time period; fit the electromyographic signals in each physiological monitoring data into an electromyographic signal change curve according to the corresponding acquisition time sequence; extract the average amplitude (EMGP) of the electromyographic signal change curve; Muscle pressure characteristic change curve MP(n) is generated based on muscle pressure data from various physiological monitoring data. Muscle temperature change curve MT(t) is generated based on muscle temperature data from various physiological monitoring data. Substituting the average amplitude EMGP, the muscle pressure characteristic change curve MP(n), and the muscle temperature change curve MT(t) into the muscle relaxation evaluation function yields the muscle relaxation score SP; the muscle relaxation evaluation function is: Where SP is the muscle relaxation score, H1() is the set quantization function of muscle temperature and muscle pressure, H2() is the set quantization function of electromyography signal; δ1 is the weighting coefficient of the effect of muscle temperature and muscle pressure on muscle relaxation, δ2 is the weighting coefficient of the effect of electromyography signal on muscle relaxation, δ1+δ2=1, δ1<δ2. The massage adjustment module is used to perform massage based on a massage plan, and to adjust the massage plan based on the adjusted massage plan.

2. The hammering management system of the hammering stretching physiotherapy rehabilitation machine according to claim 1, characterized in that, The generation of the muscle temperature change curve MT(t) based on muscle temperature from various physiological monitoring data includes: Acquire muscle temperature data from several physiological monitoring data points, and sort each muscle temperature according to its corresponding acquisition time to obtain a muscle temperature array. Obtain the movement cycle corresponding to the massage frequency of the massage hammer, obtain all muscle temperatures in the first movement cycle of the muscle temperature data group, and mark the number of muscle temperatures as K. Then, take each muscle temperature as the starting point and the cycle as the step size and continuously select several muscle temperatures in the muscle temperature data group to divide the muscle temperature group into K muscle temperature change groups. The muscle temperatures in the muscle temperature change groups are sequentially fitted into muscle temperature change curves MTi(t) according to their corresponding collection times; where i is the number corresponding to the muscle temperature change group; i=1,2,…,K; Through formula Select the muscle temperature change curve as the final muscle temperature change curve MT(t); where T is the duration of the set time.

3. The hammering management system of the hammering stretching physiotherapy rehabilitation machine according to claim 1, characterized in that, The muscle pressure characteristic change curve is generated based on muscle pressure from various physiological monitoring data. ,include: The muscle pressure data from each physiological monitoring data point were fitted into an original pressure change curve YP(t) according to the time sequence of their corresponding collection. Through formula The pressure characteristics MPn of the muscle pressure of the massage hammer during the nth movement cycle are calculated; where n is the number of the movement cycle and f is the massage frequency of the massage hammer. Each pressure feature is fitted into a pressure feature change curve MP(n) according to the numbering order of the motion cycle.

4. The hammering management system of the hammering stretching physiotherapy rehabilitation machine according to claim 1, characterized in that, The generation of adjustment intensity and frequency based on muscle relaxation scores includes: Obtain the muscle relaxation score generated this time, as well as the muscle relaxation score and muscle relaxation threshold generated last time, and label them as DSP, XSP, and SPY, respectively; using the formula: The adjustment ratio TB is calculated; where μ is a set adjustment coefficient used to adjust the distribution of the adjustment ratio TB. When the adjustment ratio TB is less than zero, the adjustment direction in the adjustment intensity and adjustment frequency is set to negative, the adjustment intensity value is set to 1+TB times the original intensity value, and the adjustment frequency value is set to 1+TB times the original frequency value. When the adjustment ratio TB is greater than zero, the adjustment direction in the adjustment intensity and adjustment frequency is set to positive, the adjustment intensity value is set to 1 + TB times the original intensity value, and the adjustment frequency value is set to 1 + TB times the original frequency value.

5. The hammering management system of the hammering stretching physiotherapy rehabilitation machine according to claim 1, characterized in that, One training method for the language recognition model includes: Acquire the voice descriptions of several users, convert the voice descriptions into text descriptions, extract several keywords from the text descriptions, as well as the corresponding massage areas and massage plans; integrate the text descriptions, the corresponding keywords, the corresponding massage areas and massage plans into training data; integrate the text descriptions, the corresponding massage areas and massage plans into test data. The AI ​​model is trained using training data and tested using validation data. The final input is descriptive text, and the output is the massage area and massage plan corresponding to the descriptive text.

6. The hammering management system of the hammering stretching physiotherapy rehabilitation machine according to claim 1, characterized in that, The adjusted massage plan is generated based on real-time acquired performance data, including: Extract voice data and image data from the performance data; the image data is a facial image of the user; convert the voice data into descriptive text; The descriptive text and facial image are input into a trained hybrid recognition model to obtain adjustment intensity and adjustment frequency; the adjustment intensity and adjustment frequency are integrated into an adjustment massage scheme; the adjustment intensity includes adjustment direction and adjustment intensity value, and the adjustment direction includes positive and negative directions; the adjustment frequency includes adjustment direction and adjustment frequency value, and the adjustment direction includes positive and negative directions.

7. The hammering management system of the hammering stretching physiotherapy rehabilitation machine according to claim 6, characterized in that, One training method for the hybrid recognition model includes: Acquire several descriptive texts and facial images; as well as the adjustment intensity and adjustment frequency corresponding to the descriptive texts and facial images; integrate the several descriptive texts and facial images, as well as the adjustment intensity and adjustment frequency corresponding to the descriptive texts and facial images, into several training data and test data; The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using a testing model. The final result is that the input is descriptive text and facial image, and the output is the adjustment intensity and adjustment frequency corresponding to the descriptive text and facial image.

Images