An intelligent training shoe for lower limb fracture rehabilitation after surgery and its control method

Abstract

Multiple embodiments of this specification relate to rehabilitation assistance devices, and more particularly to an intelligent training shoe for lower limb fracture rehabilitation after surgery and its control method. The intelligent training shoe includes: a shoe body, the shoe body is provided with an adjustable fixing strap and a load-bearing panel; a pressure sensing module, arranged in the front area and the rear area of the load-bearing panel, for detecting pressure and obtaining pressure data; a data processing module, connected to the pressure sensing module, periodically collecting and storing the pressure data, and dynamically tracking the weighing result to generate gait analysis data; a terminal analysis module, located outside the shoe body, establishing a communication connection with the data processing unit and receiving the gait analysis data reported by the data processing module, and generating training instruction data according to the gait analysis data.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to rehabilitation assistance devices, and specifically to an intelligent training shoe for lower limb fracture rehabilitation after surgery and its control method. Background Art

[0002] The intelligent training shoe for lower limb fracture rehabilitation after surgery is a rehabilitation device used to help patients recover their walking ability. It is mainly applied in hospital rehabilitation centers and home rehabilitation environments. In a hospital rehabilitation center, patients can use the rehabilitation shoe for training under the professional guidance of a doctor or physiotherapist, and the doctor can adjust the treatment plan according to the real-time monitored data. In a home environment, patients can independently complete the training through the rehabilitation shoe connected to a mobile application, and at the same time synchronize the rehabilitation data to the medical team to achieve remote monitoring and guidance. The rehabilitation shoe adopts a variety of advanced technologies. For example, the pressure sensing technology monitors the pressure distribution of each part of the foot through sensors integrated in the sole, so as to evaluate whether the patient's gait is normal. The data analysis and feedback system can process the collected data and provide real-time feedback according to the analysis results, such as adjusting the support strength or correcting the gait through vibration prompts. Although the current rehabilitation training shoes have relatively perfect data collection capabilities, they cannot restore complex gait data. Gait data includes the sagittal plane dorsiflexion / plantar flexion angle, the coronal plane varus / valgus angle, and the horizontal plane internal / external rotation angle. Only detecting data through the pressure sensors on the sole cannot accurately restore the gait. Therefore, further research on the rehabilitation training shoe is needed. Summary of the Invention

[0003] Multiple embodiments of this specification describe an intelligent training shoe for lower limb fracture rehabilitation after surgery and its control method.

[0004] In a first aspect, an embodiment of this specification provides an intelligent training shoe for lower limb fracture rehabilitation after surgery, including:

[0005] A shoe body, where the shoe body is provided with an adjustable fixing strap and a load-bearing panel;

[0006] A pressure sensing module, arranged in the front area and the rear area of the load-bearing panel, for detecting pressure and obtaining pressure data;

[0007] A data processing module, connected to the pressure sensing module, periodically collecting and storing the pressure data, and dynamically tracking the weighing result to generate gait analysis data;

[0008] A terminal analysis module, located outside the shoe body, establishing a communication connection with the data processing unit and receiving the gait analysis data reported by the data processing module, and generating training instruction data according to the gait analysis data.

[0009] Second aspect, an embodiment of this specification provides a control method for the intelligent training shoe for postoperative rehabilitation of lower limb fractures described above, including the steps:

[0010] The data processing module periodically reads the detection values of the pressure sensing module;

[0011] The data processing module periodically collects and stores the pressure data, dynamically tracks the weighing result, and generates gait analysis data;

[0012] The data processing module obtains the body weight according to the pressure data, and obtains the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period;

[0013] After aligning the plantar equivalent body weight distribution sequence data along the time axis, the data processing module uses it as gait analysis data;

[0014] The terminal analysis module performs three-dimensional gait reconstruction according to the gait analysis data to obtain three-dimensional gait data, and generates a training result report according to the three-dimensional gait data.

[0015] The beneficial effects brought by the technical solutions provided by some embodiments of this specification at least include:

[0016] In multiple embodiments of this specification, the intelligent training shoe for postoperative rehabilitation of lower limb fractures provided can obtain a more accurate weighing result with the help of the pressure sensing module and the data processing module, helping patients and medical staff to more accurately master the force condition of the affected limb of the patient, helping to carry out rehabilitation training more effectively, and protecting the affected limb. With the help of the three-dimensional gait model, gait reconstruction is realized according to the gait analysis data, and more accurate tracking of the gait is achieved, which helps to more clearly master the rehabilitation status of the patient. Through further improvement in restoring the gait of the three-dimensional gait model and by processing the correlation of the gait within a preset time period, the accuracy of gait reconstruction can be more effectively improved. By analyzing the plantar force with reference to the reference point set and further processing the detection values of the pressure sensors through filtering, it helps to filter out the interference of the plantar force to a certain extent and improve the accuracy of gait recognition.

[0017] Other features and advantages of multiple embodiments of this specification will be further revealed in the following specific implementation manners and drawings. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 Schematic diagram of the rehabilitation intelligent training shoes provided by the embodiments of this specification.

[0020] Figure 2 Schematic diagram of the control architecture of the rehabilitation intelligent training shoes provided by the embodiments of this specification.

[0021] Figure 3 Schematic diagram of the weighing circuit provided by the embodiments of this specification.

[0022] Figure 4 Schematic diagram of the method flow for dynamically tracking weighing results provided by the embodiments of this specification.

[0023] Figure 5 Schematic diagram of the method for obtaining the sequence data of the plantar equivalent weight distribution provided by the embodiments of this specification.

[0024] Figure 6 Schematic diagram of the plantar reference points provided by the embodiments of this specification.

[0025] Figure 7 Schematic diagram of the method flow for obtaining the equivalent pressure of the plantar reference points provided by the embodiments of this specification.

[0026] Figure 8 Schematic diagram of the method flow for three-dimensional gait reconstruction provided by the embodiments of this specification. Detailed implementation manners

[0027] The technical solutions of the embodiments of this specification will be explained and illustrated below with reference to the accompanying drawings of the embodiments of this specification. However, the following embodiments are only the preferred embodiments of this specification, not all of them. Based on the embodiments in the implementation manners, other embodiments obtained by those skilled in the art without creative efforts all fall within the protection scope of this specification.

[0028] The terms "first", "second", "third", etc. in the specification, claims and the above accompanying drawings of this specification are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0029] In the following description, terms such as "inner", "outer", "upper", "lower", "left", "right", etc., which indicate orientation or positional relationship, are only for the convenience of describing embodiments and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this specification.

[0030] The data involved in this application are all information and data authorized by users or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0031] Before introducing the technical solutions described in this specification, the application scenarios of the technical solutions and related technologies are introduced.

[0032] The intelligent training shoe for lower limb fracture postoperative rehabilitation is a rehabilitation device integrating modern technology, which is used to help patients recover their walking ability. Its main application scenarios include hospital rehabilitation centers and home rehabilitation environments. In a hospital rehabilitation center, this intelligent training shoe can provide professional rehabilitation guidance and support for patients. Doctors or physiotherapists can use the sensor technology in the training shoe to monitor the patient's gait and plantar pressure distribution in real time, and accurately evaluate the patient's rehabilitation progress. Based on these data, the medical team can customize personalized rehabilitation plans and dynamically adjust the training intensity and content according to the patient's recovery status. For example, in the early stage of rehabilitation, more attention may be paid to reducing the burden on the affected limb and preventing the formation of incorrect gaits; while in the later stage of rehabilitation, it may focus on strengthening muscle strength and improving joint mobility. In addition, by connecting to the hospital information system, doctors can also remotely track the patient's daily training situation to ensure the effective implementation of the treatment plan.

[0033] For the home environment, the intelligent training shoe for lower limb fracture postoperative rehabilitation greatly improves the convenience and flexibility of rehabilitation training. Patients do not need to go to the hospital frequently and can carry out effective self-training at home. By connecting with a mobile application, patients can easily record and view their rehabilitation progress, such as the number of daily walking steps, gait analysis results, etc. The application usually also provides a series of rehabilitation training suggestions and goal-setting functions to encourage patients to complete the training tasks. When encountering problems, patients can also send relevant data to doctors or physiotherapists through the application to seek help, realizing remote consultation and guidance. This way not only saves the time and energy of traveling to and from the hospital, but also enables patients to carry out rehabilitation training more relaxedly in a familiar environment, which helps to improve the overall rehabilitation effect.

[0034] However, the current rehabilitation training shoes only rely on the sensors on the sole and cannot well restore the gait of patients. Therefore, this specification provides a method that uses historical relevant data to provide a relatively accurate three-dimensional gait restoration by establishing a model, so as to more accurately grasp the rehabilitation training status of patients and help improve the rehabilitation training effect. Please refer to the appendix Figure 1 The intelligent rehabilitation training shoes for lower limb fractures after surgery provided in this specification include a shoe body. The shoe body is provided with a wrapping lining 10 and an adjustable fixing strap 11. A front baffle 12 is arranged at the front end of the shoe body, and a training shoe shell 13 is arranged at the bottom of the shoe body. A load-bearing panel 14 is arranged inside the training shoe shell 13; a pressure sensing module is arranged in the front area and the rear area of the sole for detecting pressure and obtaining pressure data;

[0035] A data processing module is connected to the pressure sensing module, periodically collects and stores the pressure data, and dynamically tracks the weighing result to generate gait analysis data;

[0036] A terminal analysis module is located outside the shoe body, establishes a communication connection with the data processing unit, and receives the gait analysis data reported by the data processing module, and generates training instruction data according to the gait analysis data.

[0037] The method provided in this application is applied to the system architecture as Figure 2 shown. As Figure 2 shown, the system architecture includes a terminal analysis module and a terminal device 30. An interaction interface is set on the terminal device 30. Among them, the interaction interface can run on the terminal device 30 in the form of a browser, or can run on the terminal device 30 in the form of an independent application (APP), etc. For the specific display form of the interaction interface, no limitation is made here. The terminal analysis module involved in this application can be an independent physical server 20, or a server cluster or distributed system composed of multiple physical servers 20, or can also be a server 20 that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms, as the terminal analysis module. The terminal device 30 can be a smart phone, a tablet computer, a notebook computer, a palm computer, a personal computer, a smart speaker, a smart TV, a smart watch, a vehicle-mounted device, a wearable device, etc., but is not limited thereto. The terminal device 30 and the terminal analysis module can be directly or indirectly connected through wired or wireless communication methods, and no limitation is made in this application. The number of the terminal analysis module and the terminal device 30 is also not limited.

[0038] Please refer to the appendixFigure 3 The pressure sensor module includes a pressure sensor and a weighing circuit respectively disposed in the front area and the rear area of the load-bearing panel. The weighing circuit includes a signal input terminal SIG- and a signal input terminal SIG+. The signal input terminal SIG- and the signal input terminal SIG+ are respectively grounded through a capacitor C40 and a capacitor C47. A capacitor C44 is connected between the signal input terminal SIG- and the signal input terminal SIG+. The anodes of a voltage stabilizing diode D24 and a voltage stabilizing diode D25 are respectively connected to the signal input terminal SIG- and the signal input terminal SIG+. The cathodes of the voltage stabilizing diode D24 and the voltage stabilizing diode D25 are both grounded. The signal input terminal SIG- is connected to the first input pin of a weighing chip U17 through a resistor R72. The signal input terminal SIG+ is connected to the second input pin of the weighing chip U17 through a resistor R77. A capacitor C45 and a capacitor C46 are connected between the first input pin and the second input pin of the weighing chip U17. The first input pin and the second input pin of the weighing chip U17 are respectively grounded through a capacitor C41 and a capacitor C48. The CS pin, SCLK pin, DIN pin, DOUT / DRDY pin, and DRDY pin of the weighing chip U17 are respectively connected to designated signal terminals through resistors.

[0039] Please refer to the appendix Figure 4 When the data processing module dynamically tracks the weighing result, the following steps are executed:

[0040] Step S101) Periodically read the pressure data, judge the effective weighing time according to the pressure data, and eliminate the pressure data outside the effective weighing time;

[0041] Step S102) Convert the pressure data into percentage data according to the latest weight calibration data;

[0042] Step S103) Filter the percentage data using a filter;

[0043] Step S104) Obtain the weighing result according to the filtered percentage data and the weight calibration data.

[0044] Among them, the method of converting the pressure data into percentage data according to the latest weight calibration data includes:

[0045] Calculate the percentage value according to the following formula:

[0046] Percentage value = (percentage change amount / pressure detection value change amount) × pressure detection value + non-linear compensation value, where the percentage change amount is the change amount of the percentage value between loading a preset weight and no load, the pressure detection value change amount is the change amount of the pressure detection value between loading a preset weight and no load, and the pressure detection value is the pressure detection value in the pressure data to be converted;

[0047] The non-linear compensation value is calculated by the following formula:

[0048] Non-linear compensation value = (no-load percentage value / pressure detection value of the loaded preset weights - percentage value of the loaded preset weights / no-load pressure detection value) × pressure detection value change amount.

[0049] The pressure sensing module includes a plurality of pressure sensors disposed in the front and rear regions of the sole. The data processing module generates gait analysis data based on the pressure data. The terminal analysis module performs three-dimensional gait reconstruction based on the gait analysis data to obtain three-dimensional gait data, and generates a training result report based on the three-dimensional gait data.

[0050] When the data processing module generates gait analysis data, the following steps are executed:

[0051] Obtain the body weight based on the pressure data, and obtain the sole equivalent body weight distribution sequence data based on the pressure data and the body weight within a preset time period;

[0052] After aligning the sole equivalent body weight distribution sequence data and the inertial data along the time axis, use them as gait analysis data.

[0053] Please refer to the appendix Figure 5 , and the method for obtaining the sole equivalent body weight distribution sequence data based on the pressure data and the body weight within a preset time period includes:

[0054] Step S201) Read the pre-established reference point set. Please refer to the appendix Figure 6 , and the reference point set is a set of 16 pre-set sole reference points.

[0055] Step S202) Obtain the equivalent pressure of the sole reference point 16 based on the positional relationship between the pressure sensor 15 and the reference point set, and the pressure data.

[0056] Among them, please refer to the appendix Figure 7 , and the method for obtaining the equivalent pressure of the sole reference point 16 based on the positional relationship between the pressure sensor 15 and the reference point set, and the pressure data includes:

[0057] Step S301) Read the pressure data within a preset time period. Read a fixed time length (exemplarily, such as several seconds) of the pressure data from the data buffer or memory. Efficient data reading can be achieved through a circular queue or other suitable data structures.

[0058] Step S302) Extract the amplitude of the frequency components above the preset frequency of the pressure data, denoted as the high-frequency amplitude. Use the Fast Fourier Transform (FFT) or other frequency-domain analysis methods to transform the pressure data in the time domain to the frequency domain, and then extract the amplitudes of all frequency components above a certain preset frequency as the "high-frequency amplitude".

[0059] Step S303) Multiply the high-frequency amplitude by a preset magnification factor and then superimpose it on the frequency components below the preset frequency to obtain the secondary pressure data. Operate in the frequency domain, find all the frequency components below the preset frequency, and group the lower frequencies and higher frequencies. The combination pairing method is as follows: Obtain multiple harmonic frequencies for each lower frequency (frequency component below the preset frequency), find the closest harmonic frequency for each higher frequency (frequency component above the preset frequency), and incorporate the higher frequency component and the lower frequency component corresponding to the harmonic frequency into the same group. Each group has one lower frequency component and zero or several higher frequency components. After reducing the amplitude of the higher frequency in each group by the preset magnification factor, superimpose it on the lower frequency component in the same group. Then, perform the inverse Fourier transform to convert the data back to the time domain to obtain the secondary corrected pressure data.

[0060] Step S304) According to the positional relationship between the pressure sensor 15 and the reference point set, establish a force relationship model. The input of the force relationship model is the pressure value at the position of the pressure sensor 15, and the output is the pressure value of the plantar reference point 16. The force relationship model can predict the pressure distribution at specific plantar reference points based on the pressure value at the position of the pressure sensor 15. Exemplarily, a linear interpolation or a machine learning algorithm (such as a neural network) can be used to establish the force relationship model. In this embodiment, the force relationship model is established in the form of a neural network model.

[0061] Step S305) After training the force relationship model using the manually labeled samples, obtain the equivalent pressure of the plantar reference point 16 according to the response of the force relationship model to the secondary pressure data. First, collect sufficient manually labeled samples, that is, the known inputs (measurement values of each pressure sensor 15) and the expected outputs (true pressures of the plantar reference points 16). Use these data to train the above-mentioned force relationship model (exemplarily, train the neural network through a supervised learning algorithm). After training, use the force relationship model to predict the new secondary pressure data, thereby obtaining the equivalent pressure at the plantar reference point 16.

[0062] Step S203) Convert the equivalent pressure into a percentage of body weight, and obtain the plantar equivalent body weight distribution sequence data according to the percentage. The body weight actually refers to the weight of the patient, their clothing, and any items the patient may be holding in their hands. Therefore, the body weight of the patient is different each time. Considering that the patient may be holding a cane or using a handrail, etc., since the supporting forces provided by the cane and the handrail are dynamically changing, it will be impossible to correctly exclude the influence of the cane and the handrail on the body weight using the techniques known in the art. In this embodiment, it is considered that the supporting forces provided by the cane and the handrail have a certain periodic regularity. By using the prior filtering and the method of frequency grouping and superposition, the periodic regular supporting forces generated by the cane and the handrail can be taken into account to a certain extent, and the situations of using a cane and a handrail are uniformly mapped into the force representation of the reference point set by using the equivalent pressure method. Then, by converting the equivalent pressure into a percentage of body weight, the absolute value of the influence on the body weight when holding a cane or using a handrail is basically excluded. As long as the use of a cane or a handrail does not cause a significant change in the distribution law of the plantar force percentage, it will not have an obvious impact on the result. Of course, on the other hand, when the use of a cane or a handrail causes a significant change in the plantar force law during walking, the final effect of this embodiment will be partially affected. However, in the subsequent steps, this influence will be compensated by comparing with the gait library and probability judgment.

[0063] Step S103) After aligning the plantar equivalent body weight distribution sequence data along the time axis, use it as gait analysis data.

[0064] After the gait analysis data, the reconstruction of three-dimensional gait can be carried out. Please refer to the appendix Figure 8 , and the method for reconstructing three-dimensional gait according to the gait analysis data includes:

[0065] Step S401) Establish a three-dimensional gait model. The input of the three-dimensional gait model is the gait analysis data, and the output is a number of values and their probabilities of the sagittal plane flexion angle, the coronal plane rotation angle, and the horizontal plane rotation angle. The three-dimensional gait model is a neural network model or other machine learning models. Although there is a strong correlation between the plantar force condition and the three-dimensional gait, there is a lack of a mathematical derivation relationship. In this embodiment, a neural network model is used to fit this correlation relationship. The three-dimensional gait model includes the sagittal plane flexion angle, the coronal plane rotation angle, and the horizontal plane rotation angle. When the sagittal plane flexion angle is positive, it is the sagittal plane dorsiflexion angle; when the sagittal plane flexion angle is negative, it is the sagittal plane plantar flexion angle. The absolute value ranges of both the sagittal plane dorsiflexion angle and the sagittal plane plantar flexion angle are 0° to 45°. When the coronal plane rotation angle is positive, it is the coronal plane varus angle, and when the coronal plane rotation angle is negative, it is the coronal plane valgus angle. The absolute value ranges of both the coronal plane varus angle and the coronal plane valgus angle are 0° to 20°. When the value of the horizontal plane rotation angle is positive, it is the horizontal plane internal rotation angle, and when the value of the horizontal plane rotation angle is negative, it is the horizontal plane external rotation angle. The absolute value ranges of both the horizontal plane internal rotation angle and the horizontal plane external rotation angle are 0° to 15°.

[0066] Step S402) Use the gait analysis data with manually labeled sagittal plane flexion angle, coronal plane rotation angle, and horizontal plane rotation angle as sample data to train the three-dimensional gait model. Train the three-dimensional gait model using the labeled sample data, and the training can be completed when the preset accuracy rate is achieved.

[0067] Step S403) Read a number of the gait analysis data within a preset time period according to the time axis, input them into the three-dimensional gait model, and obtain a number of sagittal plane flexion angles, coronal plane rotation angles, horizontal plane rotation angles and their probabilities at each time point on the time axis.

[0068] Relying solely on the three-dimensional gait results obtained by the three-dimensional gait model based on the gait analysis data, the three-dimensional gait results include the sagittal plane flexion angle, the coronal plane rotation angle, and the horizontal plane rotation angle, there is still room for improvement in accuracy. In this embodiment, multiple three-dimensional gaits within a preset time period are compared to obtain the three-dimensional gait with the highest credibility as the final gait recognition result, which has higher accuracy. Moreover, with the results identified by multiple three-dimensional gait models within the preset time period, mutual verification can be carried out to suppress the inaccuracy of the three-dimensional gait model itself.

[0069] Step S404) Obtain multiple combinations of the sagittal plane flexion angle, the coronal plane rotation angle, and the horizontal plane rotation angle along the time axis, and calculate the total probability of each combination.

[0070] Step S405) Compare each combination with a preset gait library to obtain the closest gait and the similarity.

[0071] Step S406) Select a gait as the recognized gait based on the maximum weighted sum of the total probability and the similarity, and use the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle of the recognized gait as the three-dimensional gait reconstruction result within the preset duration. By using the weighted sum of the total probability and the similarity of the gait closest to the gait in the gait library as the final judgment index, it has higher accuracy. It can effectively ensure the reliability of the gait recognition result and provide a basis for the generation of subsequent training result reports.

[0072] Among them, the method for presetting the gait library includes:

[0073] Obtain the historical combination, manually label the gait and its confidence level to obtain the gait library;

[0074] After obtaining the gait closest to the combination and the similarity, use the confidence level to correct the similarity.

[0075] On the other hand, in another embodiment, the method for presetting the gait library includes:

[0076] Extra install sensors for measuring the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle to obtain gait analysis data when the patient is walking within the preset duration, and the corresponding sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle;

[0077] Correlate the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle with the corresponding gait analysis data to obtain the gait, and then obtain the gait library.

[0078] On the other hand, in another embodiment, the intelligent rehabilitation training shoe for lower limb fractures after surgery further includes a feedback module. The feedback module is arranged on the side of the shoe body. The feedback module includes a vibration motor and an LED indicator light. The feedback module is connected to the data processing module. When it is judged that the abnormal plantar pressure distribution lasts for more than the preset time threshold according to the plantar equivalent body weight distribution sequence data, the vibration motor and the LED indicator light emit vibration and light alarms. The vibration motor is arranged on the side of the shoe body and can generate vibration when receiving an instruction. Vibration, as a form of tactile feedback, can immediately attract the user's attention and is suitable for providing immediate feedback when the user is focused on other activities (such as walking or performing rehabilitation training). When the vibration motor vibrates, it will have a weak impact on the acceleration sensor and the pressure sensor 15. These data can be removed according to the vibration time of the vibration motor and obtained by filtering through the frequency of the vibration motor. The LED indicator light is also located on the side of the shoe body and can prompt the user by emitting light when an alarm is needed. Different colors of lights can be used to represent different states or severities. For example, red represents an emergency or high risk, and yellow represents a warning, etc.

[0079] On the other hand, in another embodiment, the data processing module also calculates the differences in the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle between two consecutive recognized gaits. When any of the differences in the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle is greater than a preset threshold, the vibration motor and the LED indicator emit vibration and light alarms. The data processing module processes the input gait analysis data based on the method described above to identify the gait pattern at the current time point and its sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle. For each newly recognized gait, the data processing module compares its sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle with the corresponding three angle values of the previous gait and calculates the differences. One or more thresholds (corresponding to the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle respectively) are preset, and these thresholds represent the boundaries of the normal gait change range. Once it is detected that any angle difference exceeds its preset threshold, the vibration motor and the LED indicator will emit vibration and light alarms.

[0080] On the other hand, in another embodiment, the data processing module also receives a reference gait. When the differences in the sagittal plane flexion angle, frontal plane roll angle, and horizontal plane rotation angle between the recognized gait and the reference gait exceed a preset threshold, the vibration motor and the LED indicator emit vibration and light alarms. By introducing a reference gait and comparing it with the recognized gait in real time, it can not only help the patient better master the correct gait, but also effectively prevent potential risks caused by abnormal gait, thus accelerating the rehabilitation process.

[0081] On the other hand, this specification provides a control method for an intelligent training shoe for lower limb fracture rehabilitation after surgery, including the steps:

[0082] The data processing module periodically reads the detection values of the pressure sensing module;

[0083] The data processing module periodically collects and stores the pressure data, dynamically tracks the weighing results, and generates gait analysis data;

[0084] The data processing module obtains the body weight according to the pressure data, and obtains the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period;

[0085] The data processing module aligns the plantar equivalent body weight distribution sequence data and the inertial data along the time axis and uses them as gait analysis data;

[0086] The terminal analysis module performs three-dimensional gait reconstruction based on the gait analysis data to obtain three-dimensional gait data, and generates a training result report according to the three-dimensional gait data.

[0087] Among them, the method by which the data processing module obtains the plantar equivalent body weight distribution sequence data according to the pressure data and body weight within a preset time period includes:

[0088] Read the pre-established reference point set, where the reference point set is a set of pre-set plantar reference points 16;

[0089] According to the positional relationship between the pressure sensor 15 and the reference point set, and the pressure data, obtain the equivalent pressure of the plantar reference point 16;

[0090] Convert the equivalent pressure into a proportion of body weight, and obtain the plantar equivalent body weight distribution sequence data according to the proportion.

[0091] The method by which the data processing module obtains the equivalent pressure of the plantar reference point 16 according to the positional relationship between the pressure sensor 15 and the reference point set, and the pressure data includes:

[0092] Extract the amplitude of the frequency component above the preset frequency of the pressure data, denoted as the high-frequency amplitude;

[0093] Multiply the high-frequency amplitude by a preset magnification factor and superimpose it on the frequency component below the preset frequency to obtain secondary pressure data;

[0094] According to the positional relationship between the pressure sensor 15 and the reference point set, establish a force relationship model, where the input of the force relationship model is the pressure value at the position of the pressure sensor 15, and the output is the pressure value of the plantar reference point 16;

[0095] After training the force relationship model with the manually labeled samples, obtain the equivalent pressure of the plantar reference point 16 according to the response of the force relationship model to the secondary pressure data.

Claims

1. An intelligent training shoe for postoperative rehabilitation of lower limb fractures, characterized in that, Comprising: A shoe body, wherein the shoe body is provided with an adjustable fixing strap and a load-bearing panel; A pressure sensing module, arranged in the front area and the rear area of the load-bearing panel, for detecting pressure and obtaining pressure data; A data processing module, connected to the pressure sensing module, periodically collecting and storing the pressure data, and dynamically tracking the weighing result to generate gait analysis data; A terminal analysis module, located outside the shoe body, establishing a communication connection with the data processing module and receiving the gait analysis data reported by the data processing module, and generating training instruction data according to the gait analysis data; The pressure sensing module includes a plurality of pressure sensors arranged in the front area and the rear area of the sole, and the data processing module generates gait analysis data according to the pressure data. The terminal analysis module performs three-dimensional gait reconstruction according to the gait analysis data to obtain three-dimensional gait data, and generates a training result report according to the three-dimensional gait data; When the data processing module generates gait analysis data, the following steps are executed: Obtain the body weight according to the pressure data, and obtain the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period; After aligning the plantar equivalent body weight distribution sequence data along the time axis, use it as the gait analysis data; The method for obtaining the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period includes: Read a pre-established reference point set, where the reference point set is a set of preset plantar reference points; Obtain the equivalent pressure of the plantar reference points according to the positional relationship between the pressure sensors and the reference point set and the pressure data; Convert the equivalent pressure into a proportion of the body weight, and obtain the plantar equivalent body weight distribution sequence data according to the proportion; The method for obtaining the equivalent pressure of the plantar reference points according to the positional relationship between the pressure sensors and the reference point set and the pressure data includes: Read the pressure data within a preset time period; Extract the amplitude of the frequency component with a frequency above a preset frequency in the pressure data, and denote it as the amplitude of the higher frequency component; Multiply the amplitude of the higher frequency component by a preset magnification factor and superimpose it on the amplitude of the frequency component below the preset frequency to obtain secondary pressure data; Specifically including: Group the lower frequency components and the higher frequency components. The lower frequency components refer to the frequency components below the preset frequency, and the higher frequency components refer to the frequency components above the preset frequency. The grouping method is as follows: respectively obtain multiple harmonic frequencies of the frequency of each lower frequency component, find the harmonic frequency closest to its frequency for each higher frequency component, incorporate the higher frequency component and the lower frequency component corresponding to the closest harmonic frequency into the same group. Each group has one lower frequency component and zero or several higher frequency components. After reducing the amplitude of the higher frequency components in each group by a preset magnification factor, superimpose it on the amplitude of the lower frequency component in the same group, and perform an inverse Fourier transform to convert the data back to the time domain to obtain the secondary pressure data. Establish a force relationship model based on the positional relationship between the pressure sensor and the reference point set. The input of the force relationship model is the pressure value at the position of the pressure sensor, and the output is the pressure value of the sole reference point; After training the force relationship model with manually labeled samples, obtain the equivalent pressure of the sole reference point according to the response of the force relationship model to the secondary pressure data.

2. The intelligent training shoe for postoperative rehabilitation of lower limb fractures according to claim 1, wherein The pressure sensing module includes pressure sensors and weighing circuits respectively arranged in the front area and the rear area of the load-bearing panel. The weighing circuit includes a signal input terminal SIG- and a signal input terminal SIG+. The signal input terminal SIG- and the signal input terminal SIG+ are respectively grounded through a capacitor C40 and a capacitor C47. A capacitor C44 is connected between the signal input terminal SIG- and the signal input terminal SIG+. The anodes of the voltage stabilizing diodes D24 and D25 are respectively connected to the signal input terminal SIG- and the signal input terminal SIG+, and the cathodes of the voltage stabilizing diodes D24 and D25 are both grounded. The signal input terminal SIG- is connected to the first input pin of the weighing chip U17 through a resistor R72. The signal input terminal SIG+ is connected to the second input pin of the weighing chip U17 through a resistor R77. A capacitor C45 and a capacitor C46 are connected between the first input pin and the second input pin of the weighing chip U17. The first input pin and the second input pin of the weighing chip U17 are respectively grounded through a capacitor C41 and a capacitor C48. The CS pin, SCLK pin, DIN pin, DOUT / DRDY pin, and DRDY pin of the weighing chip U17 are respectively connected to designated signal terminals through resistors.

3. The intelligent training shoe for postoperative rehabilitation of lower limb fractures according to claim 1 or 2, wherein When the data processing module dynamically tracks the weighing result, the following steps are executed: Periodically read the pressure data, judge the effective weighing time according to the pressure data, and eliminate the pressure data outside the effective weighing time; Convert the pressure data into percentage data according to the latest weight calibration data; Filter the percentage data using a filter; Obtain the weighing result according to the filtered percentage data and the weight calibration data.

4. The intelligent training shoe for postoperative rehabilitation of lower limb fractures according to claim 3, wherein The method for converting the pressure data into percentage data according to the latest weight calibration data includes: Calculate the percentage value according to the following formula: Percentage value = (percentage change amount / pressure detection value change amount) × pressure detection value + non-linear compensation value, where the percentage change amount is the change amount of the percentage value between loading a preset weight and no load, the pressure detection value change amount is the change amount of the pressure detection value between loading a preset weight and no load, and the pressure detection value is the pressure detection value in the pressure data to be converted; The non-linear compensation value is calculated by the following formula: Nonlinear compensation value = (no-load percentage value / pressure detection value of loaded preset weights - loaded preset weights percentage value / no-load pressure detection value) × pressure detection value change amount.

5. The intelligent rehabilitation training shoe for lower limb fractures after surgery according to claim 1, wherein The method for three-dimensional gait reconstruction based on the gait analysis data includes: Establish a three-dimensional gait model, the input of the three-dimensional gait model is the gait analysis data, and the output is several values and their probabilities of the sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle; Use the gait analysis data with manually marked sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle as sample data to train the three-dimensional gait model; Read several pieces of the gait analysis data within a preset time period according to the time axis, input them into the three-dimensional gait model, and obtain several sagittal plane flexion angles, coronal plane valgus angles, horizontal plane rotation angles and their probabilities at each time point on the time axis; Obtain multiple groups of combinations of sagittal plane flexion angles, coronal plane valgus angles, and horizontal plane rotation angles along the time axis, and calculate the total probability of each combination; Compare each combination with a preset gait library to obtain the closest gait and similarity; Select a gait as the recognized gait according to the maximum weighted sum of the total probability and the similarity, and use the sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle of the recognized gait as the three-dimensional gait reconstruction result within the preset time period.

6. The intelligent rehabilitation training shoe for lower limb fractures after surgery according to claim 5, wherein The method for presetting the gait library includes: Obtain the historical combinations, manually mark the gait and its confidence level to obtain the gait library; After obtaining the gait closest to the combination and the similarity, use the confidence level to correct the similarity; Or, The method for presetting the gait library includes: Additional sensors for measuring the sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle are installed to obtain the gait analysis data and the corresponding sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle when the patient is walking within a preset time period; Associate the sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle with the corresponding gait analysis data to obtain the gait, and then obtain the gait library.

7. The intelligent rehabilitation training shoe for lower limb fractures after surgery according to claim 1, wherein The data processing module also receives a reference gait. When the difference between the recognized gait and the reference gait in the sagittal plane flexion angle, coronal plane valgus angle, and horizontal plane rotation angle exceeds a preset threshold, a vibration and light alarm are issued through the vibration motor and the LED indicator.

8. A control method for an intelligent training shoe for lower limb fracture rehabilitation after surgery according to any one of claims 1 to 7, characterized in that, Including the steps: The data processing module periodically reads the detection value of the pressure sensing module; The data processing module periodically collects and stores the pressure data, dynamically tracks the weighing result, and generates gait analysis data; The data processing module obtains the body weight according to the pressure data, and obtains the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period; The data processing module aligns the plantar equivalent body weight distribution sequence data along the time axis and uses it as the gait analysis data. The terminal analysis module performs three-dimensional gait reconstruction based on the gait analysis data to obtain three-dimensional gait data, and generates a training result report according to the three-dimensional gait data; The pressure sensing module includes a plurality of pressure sensors disposed in the front area and the rear area of the sole, and the data processing module generates gait analysis data according to the pressure data. When the data processing module generates gait analysis data, the following steps are performed: Obtain the body weight according to the pressure data, and obtain the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period; After aligning the plantar equivalent body weight distribution sequence data along the time axis, it is used as gait analysis data; The method for obtaining the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period includes: Read a pre-established reference point set, where the reference point set is a set of preset plantar reference points; Obtain the equivalent pressure of the plantar reference points according to the positional relationship between the pressure sensors and the reference point set, and the pressure data; Convert the equivalent pressure into a proportion of the body weight, and obtain the plantar equivalent body weight distribution sequence data according to the proportion; The method for obtaining the equivalent pressure of the plantar reference points according to the positional relationship between the pressure sensors and the reference point set, and the pressure data includes: Read the pressure data within a preset time period; Extract the amplitude of the frequency component with a frequency above a preset frequency in the pressure data, and record it as the amplitude of the higher frequency component; Multiply the amplitude of the higher frequency component by a preset magnification factor and superimpose it on the amplitude of the frequency component below the preset frequency to obtain secondary pressure data; Specifically includes: Group the lower frequency components and the higher frequency components. The lower frequency components refer to the frequency components below the preset frequency, and the higher frequency components refer to the frequency components above the preset frequency. The grouping method is: respectively obtain multiple multiples of the frequency of each lower frequency component, find the multiple frequency closest to its frequency for each higher frequency component, and incorporate the higher frequency component and the lower frequency component corresponding to the closest multiple frequency into the same group. Each group has one lower frequency component and zero or several higher frequency components. After reducing the amplitude of the higher frequency components in each group by a preset magnification factor, superimpose it on the amplitude of the lower frequency component in the same group, and perform an inverse Fourier transform to convert the data back to the time domain to obtain the secondary pressure data; Establish a force relationship model according to the positional relationship between the pressure sensors and the reference point set. The input of the force relationship model is the pressure value at the position of the pressure sensor, and the output is the pressure value of the plantar reference point; After training the force relationship model with artificial annotation samples, obtain the equivalent pressure of the plantar reference points according to the response of the force relationship model to the secondary pressure data.

9. According to the control method described in claim 8, wherein The method for the data processing module to obtain the plantar equivalent body weight distribution sequence data according to the pressure data and the body weight within a preset time period includes: Read a pre-established reference point set, where the reference point set is a set of preset plantar reference points; Obtain the equivalent pressure of the plantar reference points according to the positional relationship between the pressure sensor and the reference point set, as well as the pressure data; Convert the equivalent pressure into a percentage of body weight, and obtain the plantar equivalent body weight distribution sequence data according to the percentage.

10. The control method according to claim 9, wherein The method by which the data processing module obtains the equivalent pressure of the plantar reference points according to the positional relationship between the pressure sensor and the reference point set, as well as the pressure data, includes: Extract the amplitude of the frequency components above a preset frequency of the pressure data, denoted as the high-frequency amplitude; Multiply the high-frequency amplitude by a preset magnification factor and superimpose it on the frequency components below the preset frequency to obtain secondary pressure data; Establish a force relationship model according to the positional relationship between the pressure sensor and the reference point set, where the input of the force relationship model is the pressure value at the position of the pressure sensor, and the output is the pressure value of the plantar reference point; After training the force relationship model with manually labeled samples, obtain the equivalent pressure of the plantar reference points according to the response of the force relationship model to the secondary pressure data.

Images