Method, apparatus, electronic device, and computer-readable medium for manufacturing a spinal orthosis

Abstract

Embodiments of the present disclosure disclose a method, apparatus, electronic device, and computer-readable medium for manufacturing a spinal orthosis. A specific implementation of the method includes: obtaining patient diagnosis information; generating a three-dimensional human body model based on three-dimensional human body data; updating the patient body surface data according to the three-dimensional human body model to obtain the updated patient body surface data as the patient body surface data; classifying and processing the patient diagnosis information to obtain case type information; generating a patient treatment information set according to the case type information; controlling an associated display device to display the patient treatment information set for a target user to view; in response to receiving a modification operation on the three-dimensional human body model by the target user according to the patient treatment information set, generating a modified three-dimensional human body model; and controlling an associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the modified three-dimensional human body model. This implementation can shorten the waiting time of patients, improve the correction effect of spinal orthoses, and further enhance the experience of patients.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to methods, devices, electronic devices, and computer-readable media for manufacturing spinal orthoses. Background Art

[0002] A scoliosis orthosis is an effective non-surgical treatment for early scoliosis. Patients need to make personalized scoliosis orthoses according to the shape of their spines. Currently, when making personalized scoliosis orthoses, the commonly used method is as follows: manually measure the dimensions and make a plaster model, then, according to the orthotist's experience, modify the plaster model, and finally, obtain the scoliosis orthosis by thermoforming a sheet.

[0003] However, the inventors found that when making personalized scoliosis orthoses in the above manner, the following technical problems often exist:

[0004] First, by manually measuring the dimensions and modifying them, the operation is cumbersome, the dimensional accuracy of the obtained plaster model is low, and the deviation between the size of the produced scoliosis orthosis and the actual size of the patient is large, resulting in a long waiting time for the patient, a poor correction effect of the spinal orthosis, and thus a poor experience for the patient.

[0005] Second, when treating patients, the relevant treatment plans are completely subjectively determined according to the orthotist's experience, without quantifying the degree of fit between the patient's actual situation and previous cases, resulting in a poor correction effect of the spinal orthosis designed according to the treatment plan, and thus a poor experience for scoliosis orthosis patients.

[0006] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0007] This content section of the present disclosure is used to briefly introduce concepts that will be described in detail in the subsequent detailed implementation section. This content section of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0008] Some embodiments of the present disclosure propose methods, devices, electronic devices, and computer-readable media for manufacturing spinal orthoses to solve one or more of the technical problems mentioned in the above background art section.

[0009] In a first aspect, some embodiments of the present disclosure provide a method for manufacturing a spinal orthosis. The method includes: obtaining patient diagnosis information of a target patient, where the patient diagnosis information includes patient body surface data, and the patient body surface data includes three-dimensional human data; generating a three-dimensional human model based on the three-dimensional human data; updating the patient body surface data based on the three-dimensional human model to obtain updated patient body surface data as the patient body surface data; classifying the patient diagnosis information to obtain case type information; generating a patient treatment information set based on the case type information; controlling an associated display device to display the patient treatment information set for a target user to view; generating a modified three-dimensional human model in response to receiving a modification operation on the three-dimensional human model by the target user according to the patient treatment information set; and controlling an associated spinal orthosis manufacturing device to manufacture a spinal orthosis based on the modified three-dimensional human model.

[0010] In a second aspect, some embodiments of the present disclosure provide a spinal orthosis manufacturing apparatus. The apparatus includes: an obtaining unit configured to obtain patient diagnosis information of a target patient, where the patient diagnosis information includes patient body surface data, and the patient body surface data includes three-dimensional human data; a first generating unit configured to generate a three-dimensional human model based on the three-dimensional human data; an updating unit configured to update the patient body surface data based on the three-dimensional human model to obtain updated patient body surface data as the patient body surface data; a classifying unit configured to classify the patient diagnosis information to obtain case type information; a second generating unit configured to generate a patient treatment information set based on the case type information; a first control unit configured to control an associated display device to display the patient treatment information set for a target user; a third generating unit configured to generate a modified three-dimensional human model in response to receiving a modification operation on the three-dimensional human model by the target user according to the patient treatment information set; and a second control unit configured to control an associated spinal orthosis manufacturing device to manufacture a spinal orthosis based on the modified three-dimensional human model.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, where the computer program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0013] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the method for manufacturing a spinal orthosis according to some embodiments of the present disclosure, the waiting time of patients can be shortened, the correction effect of the spinal orthosis can be improved, and the patient experience can be further enhanced. Specifically, the reasons for the poor patient experience are as follows: By manually measuring the dimensions and making modifications, the operation is cumbersome, the dimensional accuracy of the plaster model obtained is low, and the deviation between the dimensions of the scoliosis orthosis produced and the actual dimensions of the patient is large, resulting in a longer waiting time for the patient, a poor correction effect of the spinal orthosis, and thus a poor patient experience. Based on this, in the method for manufacturing a spinal orthosis according to some embodiments of the present disclosure, first, obtain the patient diagnosis information of the target patient. Among them, the above-mentioned patient diagnosis information includes patient body surface data, and the above-mentioned patient body surface data includes human three-dimensional data. Thus, the basic information of the patient can be obtained, which can be used to determine the case type information of the patient. Secondly, generate a human three-dimensional model according to the above-mentioned human three-dimensional data. Thus, a human three-dimensional model can be automatically generated by computer software for manufacturing a spinal orthosis, so that it is not necessary to manually measure the dimensions to construct a model based on the human three-dimensional model, shortening the waiting time of the patient. Then, update the above-mentioned patient body surface data according to the above-mentioned human three-dimensional model to obtain the updated patient body surface data as the patient body surface data. Thus, the human three-dimensional model can also be used as a basis for determining the case type information of the patient, which can be used to determine the case type information of the patient. After that, classify and process the above-mentioned patient diagnosis information to obtain case type information. Thus, the case type information of the patient can be obtained, which can be used to determine the treatment plan of the patient. Next, generate a patient treatment information set according to the above-mentioned case type information. Thus, the treatment plan of the patient can be determined through the case type, which can be used to adjust the human three-dimensional model. Immediately afterwards, control the associated display device to display the above-mentioned patient treatment information set for the target user to view. Thus, the orthotist treating the patient can view the treatment plan, so that the orthotist has certain data basis when adjusting the human three-dimensional model, rather than making judgments solely based on subjective awareness. Subsequently, in response to receiving the modification operation of the target user on the above-mentioned human three-dimensional model according to the above-mentioned patient treatment information set, generate a modified human three-dimensional model. Thus, a human three-dimensional model modified by the orthotist can be obtained, which can be used to manufacture a spinal orthosis. Finally, control the associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the above-mentioned modified human three-dimensional model. Thus, a spinal orthosis can be obtained, which can be used to correct the scoliosis of the patient.Also, when manufacturing a spinal orthosis, a three-dimensional human model that is more fitted to the actual size of the patient is automatically generated by computer software, and there is a certain data basis for adjusting the three-dimensional human model, thereby reducing the deviation between the three-dimensional human model and the actual body size of the patient, shortening the waiting time of the patient. Therefore, the waiting time of the patient can be shortened, the manufactured spinal orthosis can be more fitted to the size of the patient, the correction effect of the spinal orthosis can be improved, and thus the patient experience can be enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flowchart of some embodiments of a method for manufacturing a spinal orthosis according to the present disclosure;

[0016] Figure 2 is a schematic structural diagram of some embodiments of a device for manufacturing a spinal orthosis according to the present disclosure;

[0017] Figure 3 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0019] It should be further noted that, for the sake of convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0021] It should be noted that the modifications of "one" and "plural" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are for illustrative purposes only and are not used to limit the scope of these messages or information.

[0023] Figure 1 Flow 100 of some embodiments of a spinal orthosis manufacturing method according to the present disclosure is shown. The spinal orthosis manufacturing method includes the following steps:

[0024] Step 101, obtaining patient diagnosis information of a target patient.

[0025] In some embodiments, the execution subject (such as a computing device) of the spinal orthosis manufacturing method may obtain the patient diagnosis information of the target patient. Among them, the above-mentioned target patient may be a patient who needs spinal curvature correction. The patient diagnosis information in the above-mentioned patient diagnosis information set may be information on the results of diagnosing the patient. Among them, the above-mentioned patient diagnosis information may include patient body surface data. The above-mentioned patient diagnosis information may further include a patient identifier, patient gender, patient age, patient flexibility, and patient body surface data. The above-mentioned patient identifier may be a unique identifier for the patient. For example, the above-mentioned patient identifier may be the patient's name or the patient's ID number. Patient flexibility may be the flexibility of the patient's body. The above-mentioned patient body surface data may include human three-dimensional data. The above-mentioned human three-dimensional data may be the point cloud data of the human body output by a human three-dimensional scanner and the dimensions of each body part of the human body. In practice, the above-mentioned execution subject may obtain the patient diagnosis information of the target patient from the server through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future-developed wireless connection methods.

[0026] Step 102, generating a human three-dimensional model according to the human three-dimensional data.

[0027] In some embodiments, the above-mentioned execution subject may generate a human three-dimensional model according to the above-mentioned human three-dimensional data. In practice, the above-mentioned execution subject may generate a human three-dimensional model according to the above-mentioned human three-dimensional data through open-source three-dimensional graphics and image software. For example, the above-mentioned three-dimensional graphics and image software may be Blender software.

[0028] Step 103, updating the patient body surface data according to the human three-dimensional model to obtain the updated patient body surface data as the patient body surface data;

[0029] In some embodiments, the above-mentioned execution entity may update the above-mentioned patient body surface data according to the above-mentioned three-dimensional human body model, and obtain the updated patient body surface data as the patient body surface data. In practice, the above-mentioned execution entity may store the above-mentioned three-dimensional human body model into the above-mentioned patient body surface data to obtain the updated patient body surface data as the patient body surface data.

[0030] Step 104: Classify the patient diagnosis information to obtain case type information.

[0031] In some embodiments, the above-mentioned execution entity may classify the above-mentioned patient diagnosis information to obtain case type information. Among them, the above-mentioned case type information may characterize the case type of the above-mentioned target patient. The above-mentioned case type may be, but is not limited to, one of the following: right chest and left waist, right chest and left neck and shoulder, right chest and left pelvis, left waist and right chest, left waist, right chest and right pelvis, left waist and right pelvis. The above-mentioned right chest and left waist may mean that the Cobb angle of the patient's chest scoliosis is greater than the Cobb angle of the waist scoliosis, and the thoracic vertebrae are translated to the right and the lumbar vertebrae are translated to the left. The above-mentioned thoracic vertebrae may be the vertebrae between the upper end vertebra and the lower end vertebra of the chest. The above-mentioned lumbar vertebrae may be the vertebrae between the upper end vertebra and the lower end vertebra of the patient's waist. The above-mentioned right chest and left neck and shoulder may mean that the thoracic vertebrae are translated to the right and the patient's neck and shoulder are translated to the left. The above-mentioned right chest and left pelvis may mean that the thoracic vertebrae are translated to the right and the pelvis is translated to the left. The above-mentioned left waist and right chest may mean that the Cobb angle of the patient's chest scoliosis is less than the Cobb angle of the waist scoliosis, and the lumbar vertebrae are translated to the left and the thoracic vertebrae are translated to the right. The above-mentioned left waist, right chest and right pelvis may mean that the lumbar vertebrae are translated to the left, and the thoracic vertebrae and the pelvis are both translated to the right. The above-mentioned left waist and right pelvis may mean that the lumbar vertebrae are translated to the left and the pelvis is translated to the right. In practice, the above-mentioned execution entity may classify the above-mentioned patient diagnosis information in various ways to obtain case type information.

[0032] Optionally, the above patient diagnosis information may further include patient foot diagnosis data and patient spinal diagnosis data. The above patient foot diagnosis data may be data of the patient's foot. The above patient foot diagnosis data may include, but is not limited to, at least one of the following: past medical history of the foot, foot imaging information, foot diagnosis information. The above past medical history of the foot may be the past medical history of the patient's foot. The above foot imaging information may include, but is not limited to, X-ray films, CT films, etc. of the foot. The above foot diagnosis information may include, but is not limited to, foot pressure values, gait analysis, etc. The above foot pressure values may be the pressure values output by a plantar pressure sensor. The above patient spinal diagnosis data may be data of the patient's spine. The above patient spinal diagnosis data may include, but is not limited to, at least one of the following: past medical history of the spine, spinal imaging information, spinal diagnosis information. The above past medical history of the spine may be the past medical history of the patient's spine. The above spinal imaging information may include, but is not limited to, X-ray films, CT films, MRI films, etc. of the foot. The above spinal diagnosis information may include, but is not limited to, at least one of the following: scoliosis type, pathological type, abnormal vertebral body information. The above scoliosis type may be, but is not limited to, one of the following: thoracic curve type and lumbar curve type. The above pathological type may be congenital scoliosis and idiopathic scoliosis. The above abnormal vertebral body information may include, but is not limited to, at least one of the following: body part identifier of the abnormal spine vertebra, Cobb angle value of the spine. The above body part identifier may uniquely identify a body part.

[0033] In some alternative implementation manners of some embodiments, the above execution subject may classify the above patient diagnosis information through the following steps to obtain case type information:

[0034] First step: Input the patient's body surface data included in the above patient diagnosis information into a preset body surface case type information generation model to obtain body surface case type information. Among them, the above preset body surface case type information generation model is a pre-trained body surface case type information generation model. The above body surface case type information generation model can be a classification model with the patient's body surface data as the input and the body surface case type information as the output. For example, the above body surface case type information generation model can include an input layer, a first classification model, a second classification model, a third classification model, and an output layer. The above input layer can be used to extract features from the patient's body surface data. The first classification model, the second classification model, and the third classification model can be different types of classification models for generating body surface case type information. The above output layer can be used to output the body surface case type information based on the body surface case types generated by the first classification model, the second classification model, and the third classification model. When any two of the body surface case types generated by the first classification model, the second classification model, and the third classification model are the same, the output layer can determine the same body surface case type as the body surface case type information for output. The above input layer is respectively connected to the above first classification model, the above second classification model, and the above third classification model. The above first classification model, the above second classification model, and the above third classification model are connected to the above output layer. The above body surface case type information can be, but is not limited to, one of the following: right chest left waist, right chest left neck and shoulder, right chest left pelvis, left waist right chest, left waist chest and right pelvis, left waist right pelvis.

[0035] Second step: Input the patient's foot diagnosis data included in the above patient diagnosis information into a preset foot case type information generation model to obtain foot case type information. Among them, the above preset foot case type information generation model is a pre-trained foot case type information generation model. The above foot case type information generation model can be a neural network with the patient's foot diagnosis data as the input and the foot case type information as the output. The above neural network can be a convolutional neural network or a recurrent neural network. The above foot case type information can be, but is not limited to, one of the following: right chest left waist, right chest left neck and shoulder, right chest left pelvis, left waist right chest, left waist chest and right pelvis, left waist right pelvis.

[0036] Step 3: Input the patient's spinal diagnosis data included in the above patient diagnosis information into a preset spinal case type information generation model to obtain spinal case type information. Among them, the above preset spinal case type information generation model is a spinal case type information generation model that has been pre-trained. The above spinal case type information generation model can be a neural network that takes the patient's spinal diagnosis data as input and the spinal case type information as output. The above neural network can be a convolutional neural network or a recurrent neural network. The above spinal case type information can be, but is not limited to, one of the following: right chest and left waist, right chest and left neck and shoulder, right chest and left pelvis, left waist and right chest, left waist, chest and right pelvis, left waist and right pelvis.

[0037] Step 4: Generate case type information based on the above body surface case type information, the above foot case type information, and the above spinal case type information. In practice, first, the above execution subject can, in response to determining that the above body surface case type information is the same as the above foot case type information or the above spinal case type information, determine the above body surface case type information as the case type information. Second, in response to determining that the above body surface case type information is different from both the above foot case type information and the above spinal case type information, determine whether the above foot case type information is the same as the above spinal case type information. Then, in response to determining that the above foot case type information is the same as the above spinal case type information, determine the above foot case type information as the case type information. Finally, in response to determining that the above foot case type information is different from the above spinal case type information, determine the preset case type as the case type information. Among them, the above preset case type can be a type preset to represent that the case cannot be determined. For example, the above preset case type can be "uncertain case".

[0038] In some other alternative implementation manners of some embodiments, the above execution subject can input the above patient diagnosis information into a preset case type information generation model to obtain case type information. Among them, the above preset case type information generation model can be a classification model that has been pre-trained, taking the patient diagnosis information as input and the case type information as output.

[0039] Optionally, the above-mentioned preset case type information generation model may include an information input layer, a first information classification model, a second information classification model, a third information classification model, a fourth information classification model, and an information output layer. The above-mentioned information input layer may be used to extract features from patient diagnosis information. The first information classification model may be a classification model for generating pelvic case type information. The above-mentioned pelvic case type information may be, but is not limited to, one of the following: left pelvic deviation, right pelvic deviation, normal pelvis. The above-mentioned left pelvic deviation may be the leftward translation of the pelvis. The above-mentioned right pelvic deviation may be the rightward translation of the pelvis. The second information classification model may be a classification model for generating lumbar case type information. The above-mentioned lumbar case type information may be, but is not limited to, one of the following: left lumbar deviation, right lumbar deviation, normal lumbar. The above-mentioned left lumbar deviation may be the leftward translation of the lumbar vertebrae. The above-mentioned right lumbar deviation may be the rightward translation of the lumbar vertebrae. The third information classification model may be a classification model for generating thoracic case type information. The above-mentioned thoracic case type information may be, but is not limited to, one of the following: left thoracic deviation, right thoracic deviation, normal thorax. The above-mentioned left thoracic deviation may be the leftward translation of the thoracic vertebrae. The above-mentioned right thoracic deviation may be the rightward translation of the thoracic vertebrae. The fourth information classification model may be a classification model for generating neck and shoulder case type information. The above-mentioned neck and shoulder case type information may be, but is not limited to, one of the following: left neck and shoulder deviation, right neck and shoulder deviation, normal neck and shoulder. The above-mentioned left neck and shoulder deviation may be the leftward translation of the neck and shoulder. The above-mentioned right neck and shoulder deviation may be the rightward translation of the neck and shoulder. The above-mentioned output layer may be used to output case type information based on the pelvic case type information, lumbar case type information, thoracic case type information, and neck and shoulder case type information generated by the first information classification model, second information classification model, third information classification model, and fourth information classification model. The above-mentioned output layer may output the pelvic case type information, lumbar case type information, thoracic case type information, and neck and shoulder case type information as combined into case type information. The above-mentioned combination method may be character splicing. The above-mentioned input layer is respectively connected to the first information classification model, second information classification model, third information classification model, and fourth information classification model. The above-mentioned first information classification model, second information classification model, third information classification model, and fourth information classification model are connected to the above-mentioned output layer.

[0040] Optionally, the above-mentioned preset case type information generation model is trained according to the following steps:

[0041] In the first step, obtain a sample set. Among them, the samples in the above-mentioned sample set include sample patient diagnosis information and sample case type information corresponding to the sample patient diagnosis information.

[0042] In the second step, perform the following training steps based on the above-mentioned sample set:

[0043] The first training step is to input the sample patient diagnosis information of at least one sample in the above sample set into the initial case type information generation model respectively to obtain the case type information corresponding to each sample in the above at least one sample. In practice, first, the above execution entity can input at least one sample in the sample set into the input layer of the initial preset case type information generation model respectively to obtain the feature vector corresponding to each sample in the above at least one sample. Then, input the feature vector corresponding to each sample in the above at least one sample into the first information classification model, the second information classification model, the third information classification model and the fourth information classification model of the initial preset case type information generation model respectively to obtain the pelvic case type information, the lumbar case type information, the thoracic case type information and the neck and shoulder case type information corresponding to each sample in the above at least one sample. Finally, input the pelvic case type information, the lumbar case type information, the thoracic case type information and the neck and shoulder case type information corresponding to each sample in the above at least one sample into the output layer of the initial preset case type information generation model to obtain the case type information corresponding to each sample in the above at least one sample.

[0044] The second training step is to compare the case type information corresponding to each sample in the above at least one sample with the corresponding sample case type information.

[0045] The third training step is to determine whether the initial preset case type information generation model reaches the preset optimization goal according to the comparison result. As an example, when the case type information corresponding to a sample is the same as the corresponding sample case type information, it is considered that the case type information is accurate. At this time, the above optimization goal can refer to whether the case type information generated by the initial preset case type information generation model is the same as the sample case type information.

[0046] The fourth training step is to, in response to determining that the initial preset case type information generation model reaches the above optimization goal, use the above initial preset case type information generation model as the trained preset case type information generation model.

[0047] Optionally, the step of training to obtain the above preset case type information generation model may further include:

[0048] In the fifth training step, in response to determining that the initial preset case type information generation model fails to achieve the above optimization goal, adjust the network parameters of the initial preset case type information generation model, and use the unused samples to form a sample set. Use the adjusted initial preset case type information generation model as the initial preset case type information generation model, and execute the above training steps again. As an example, the backpropagation algorithm (BP algorithm) and the gradient descent method (such as the stochastic mini-batch gradient descent algorithm) can be used to adjust the network parameters of the above initial preset case type information generation model.

[0049] The above-mentioned preset case type information generation model and its related content are an inventive point of the embodiments of the present disclosure, which solves the second technical problem mentioned in the background art, that is, "when treating a patient, the relevant treatment plan is completely subjectively determined according to the experience of the orthotist, and the degree of fit between the actual situation of the patient and previous cases is not quantified, resulting in a poor correction effect of the spinal orthosis designed according to the treatment plan, and thus a poor experience for patients wearing the spinal orthosis." The factors that often lead to a poor experience for patients wearing spinal orthoses are as follows: when treating a patient, the relevant treatment plan is completely subjectively determined according to the experience of the orthotist, and the degree of fit between the actual situation of the patient and previous cases is not quantified, resulting in a poor correction effect of the spinal orthosis designed according to the treatment plan, and thus a poor experience for patients wearing the spinal orthosis. If the above factors are solved, the effect of improving the experience of patients wearing spinal orthoses can be achieved. To achieve this effect, the spinal orthosis manufacturing method of some embodiments of the present disclosure first obtains a sample set, wherein the samples in the sample set include sample patient diagnosis information and sample case type information corresponding to the sample patient diagnosis information. Thus, a sample set can be obtained, which can be used to train the preset case type information generation model. Secondly, the following training steps are performed based on the above sample set: the sample patient diagnosis information of at least one sample in the sample set is respectively input into the initial case type information generation model to obtain the case type information corresponding to each sample in the at least one sample; the case type information corresponding to each sample in the at least one sample is compared with the corresponding sample case type information; according to the comparison result, it is determined whether the initial case type information generation model reaches a preset optimization target; in response to determining that the initial case type information generation model reaches the optimization target, the initial case type information generation model is used as the trained case type information generation model. In response to determining that the initial case type information generation model does not reach the optimization target, the parameters of the initial case type information generation model are adjusted, and a sample set is composed of unused samples, and the adjusted initial case type information generation model is used as the initial case type information generation model, and the above training steps are performed again. Thus, by training the samples in the sample set, that is, the patient diagnosis information and case type information of previous patients, it can be determined whether the case type information generated by the initial preset case type information generation model is the same as the corresponding sample case type information, and further determine whether the initial preset case type information generation model reaches the optimization target, so as to obtain a preset case type information generation model representing the corresponding relationship between patient diagnosis information and case type information, and thus the case type information can be determined according to the patient diagnosis information.Also, since the case type information can be determined based on the patient's diagnosis information, a corresponding relationship between the patient's diagnosis information and the case type is established, quantifying the degree of fit between the actual situation of the patient and previous cases, and improving the correction effect of the spinal orthosis designed according to the treatment plan. Thus, the patient experience can be improved.

[0050] Step 105: Generate a patient treatment information set according to the case type information.

[0051] In some embodiments, the above-mentioned execution entity can generate a patient treatment information set according to the above-mentioned case type information. The patient treatment information included in the above-mentioned patient treatment information set can be information for treating the patient's scoliosis. The patient treatment information included in the above-mentioned patient treatment information set can include, but is not limited to, at least one of the following: treatment position identifier and treatment pressure. The corresponding relationship between the above-mentioned treatment position identifier and the above-mentioned treatment pressure can be one-to-one. The above-mentioned treatment position identifier can be the unique identifier of the position where the spinal orthosis needs to correct the patient. The above-mentioned treatment position identifier can be the name of the patient's bone part. For example, the above-mentioned treatment position identifier can be the apex vertebra. The above-mentioned treatment pressure can be the pressure value that the spinal orthosis needs to apply to the treatment position when correcting the patient's spine. The above-mentioned pressure value can be represented by the depth value of the patient's body depression after being subjected to the pressure. In practice, the above-mentioned execution entity can generate a patient treatment information set according to the above-mentioned case type information in various ways.

[0052] In some optional implementation manners of some embodiments, the above-mentioned execution entity can generate a patient treatment information set for the patient according to the above-mentioned case type information through the following steps:

[0053] First step: Determine whether there is a preset case type in the preset case type set that meets the preset matching condition according to the above-mentioned case type information. Among them, the preset case types included in the above-mentioned preset case type set correspond to preset treatment information sets. The preset case types included in the above-mentioned preset case type set can be preset case types. The preset case types included in the above-mentioned preset case type set can be, but are not limited to, one of the following: right chest left waist, right chest left neck and shoulder, right chest left pelvis, left waist right chest, left waist right chest and pelvis, left waist right pelvis. The above-mentioned preset matching condition can be that the preset case type is the same as the above-mentioned case type information. The preset treatment information included in the above-mentioned preset treatment information set can be preset information for treating the patient's scoliosis. The preset treatment information included in the above-mentioned preset treatment information set can include, but is not limited to, treatment position identifier and treatment pressure.

[0054] In the second step, in response to determining that there is a preset case type in the above preset case type set that meets the above preset matching condition, the preset case type in the above preset case type set that meets the above preset matching condition is determined as the target preset case type.

[0055] In the third step, the preset treatment information corresponding to the above target preset case type is determined as the patient treatment information.

[0056] Optionally, the above execution entity can also perform the following steps:

[0057] In the first step, in response to determining that there is no preset case type in the above preset case type set that meets the above preset matching condition, the associated display device is controlled to display preset treatment prompt information. Among them, the above display device can be a display screen. The above preset treatment prompt information can be information preset for prompting the patient to input a treatment information set. The above treatment information can include, but is not limited to, at least one of the following: treatment position identifier and treatment pressure. For example, the above preset treatment prompt information can be "Please input the treatment plan".

[0058] In the second step, in response to receiving the input treatment information set, the above input treatment information set is determined as the patient treatment information. Among them, the input treatment information included in the above input treatment information set can be the treatment information input by the patient.

[0059] Step 106: Control the associated display device to display the patient treatment information set for the target user to view.

[0060] In some embodiments, the above execution entity can control the associated display device to display the above patient treatment information set for the target user to view. Among them, the above display device can be a display screen. The above target user can be an orthotist or a doctor treating the target patient.

[0061] Step 107: In response to receiving the shaping operation on the human body three-dimensional model by the target user according to the patient treatment information set, generate a corrected human body three-dimensional model.

[0062] In some embodiments, the above-mentioned execution entity may generate a corrected human three-dimensional model in response to receiving the modification operation performed by the above-mentioned target user on the above-mentioned human three-dimensional model according to the above-mentioned patient treatment information set. Among them, the above-mentioned modification operation may be that for each piece of patient treatment information in the patient treatment information set, the target user moves the target adjustment point by the treatment pressure value included in the patient treatment information through various deformation tools in the sculpting mode of Blender software. Among them, the above-mentioned target adjustment point may be the point corresponding to the treatment position identifier included in the patient treatment information. In practice, the above-mentioned execution entity may generate a corrected human three-dimensional model through Blender software in response to receiving the modification operation performed by the above-mentioned target user on the above-mentioned human three-dimensional model according to the above-mentioned patient treatment information set.

[0063] Step 108, according to the corrected human three-dimensional model, control the associated spinal orthosis manufacturing device to manufacture a spinal orthosis.

[0064] In some embodiments, the above-mentioned execution entity may control the associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the above-mentioned corrected human three-dimensional model. Among them, the above-mentioned spinal orthosis manufacturing device may be a device for manufacturing a spinal orthosis. For example, the above-mentioned spinal orthosis manufacturing device may be a 3D printer for printing a spinal orthosis. The above-mentioned spinal orthosis may be an orthosis for treating scoliosis. In practice, the above-mentioned execution entity may send the above-mentioned corrected human three-dimensional model to the above-mentioned spinal orthosis manufacturing device and control the associated spinal orthosis manufacturing device to manufacture a spinal orthosis.

[0065] Optionally, the above-mentioned execution entity may also store the above-mentioned patient diagnosis information, the above-mentioned case type information, and the above-mentioned patient treatment information set in the historical patient information database. Among them, the above-mentioned historical patient information database may be a database for storing the patient diagnosis information, case type information, and patient treatment information set of previous patients.

[0066] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the method for manufacturing a spinal orthosis according to some embodiments of the present disclosure, the waiting time of patients can be shortened, the correction effect of the spinal orthosis can be improved, and the patient experience can be further enhanced. Specifically, the reasons for the poor patient experience are as follows: By manually measuring the dimensions and performing shaping, the operation is cumbersome, the dimensional accuracy of the plaster model obtained is low, and the deviation between the dimensions of the scoliosis orthosis produced and the actual dimensions of the patient is large, resulting in a long waiting time for the patient, a poor correction effect of the spinal orthosis, and thus a poor patient experience. Based on this, in the method for manufacturing a spinal orthosis according to some embodiments of the present disclosure, first, obtain the patient diagnosis information of the target patient. Among them, the above-mentioned patient diagnosis information includes patient body surface data, and the above-mentioned patient body surface data includes human three-dimensional data. Thus, the basic information of the patient can be obtained, which can be used to determine the case type information of the patient. Secondly, generate a human three-dimensional model according to the above-mentioned human three-dimensional data. Thus, a human three-dimensional model can be automatically generated by computer software for manufacturing a spinal orthosis, so that it is not necessary to manually measure the dimensions to construct a model based on the human three-dimensional model, shortening the waiting time of the patient. Then, update the above-mentioned patient body surface data according to the above-mentioned human three-dimensional model to obtain the updated patient body surface data as the patient body surface data. Thus, the human three-dimensional model can also be used as a basis for determining the case type information of the patient, which can be used to determine the case type information of the patient. After that, classify and process the above-mentioned patient diagnosis information to obtain case type information. Thus, the case type information of the patient can be obtained, which can be used to determine the treatment plan of the patient. Next, generate a patient treatment information set according to the above-mentioned case type information. Thus, the treatment plan of the patient can be determined through the case type, which can be used to adjust the human three-dimensional model. Immediately afterwards, control the associated display device to display the above-mentioned patient treatment information set for the target user to view. Thus, the orthotist treating the patient can view the treatment plan, so that the orthotist has certain data basis when adjusting the human three-dimensional model, rather than making judgments solely based on subjective awareness. Subsequently, in response to receiving the shaping operation of the target user on the above-mentioned human three-dimensional model according to the above-mentioned patient treatment information set, generate a corrected human three-dimensional model. Thus, a human three-dimensional model modified by the orthotist can be obtained, which can be used to manufacture a spinal orthosis. Finally, control the associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the above-mentioned corrected human three-dimensional model. Thus, a spinal orthosis can be obtained, which can be used to correct the scoliosis of the patient.Also, when manufacturing a spinal orthosis, a three-dimensional human body model that is more fitted to the actual size of the patient is automatically generated by computer software, and when adjusting the three-dimensional human body model, there is a certain data basis, thereby reducing the deviation between the three-dimensional human body model and the actual body size of the patient, shortening the waiting time of the patient. Therefore, the waiting time of the patient can be shortened, the manufactured spinal orthosis can be more fitted to the size of the patient, the correction effect of the spinal orthosis can be improved, and the patient experience can be improved accordingly.

[0067] Further reference Figure 2 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a spinal orthosis manufacturing device, and these device embodiments correspond to Figure 1 the method embodiments shown, and the device can be specifically applied to various electronic devices.

[0068] As Figure 2 shown, some embodiments of the spinal orthosis manufacturing device 200 include: an acquisition unit 201, a first generation unit 202, an update unit 203, a classification unit 204, a second generation unit 205, a first control unit 206, a third generation unit 207, and a second control unit 208. Among them, the acquisition unit 201 is configured to acquire patient diagnosis information of a target patient, where the patient diagnosis information includes patient body surface data, and the patient body surface data includes three-dimensional human body data; the first generation unit 202 is configured to generate a three-dimensional human body model according to the three-dimensional human body data; the update unit 203 is configured to update the patient body surface data according to the three-dimensional human body model to obtain updated patient body surface data as the patient body surface data; the classification unit 204 is configured to classify the patient diagnosis information to obtain case type information; the second generation unit 205 is configured to generate a patient treatment information set according to the case type information; the first control unit 206 is configured to control an associated display device to display the patient treatment information set for a target user; the third generation unit 207 is configured to generate a modified three-dimensional human body model in response to receiving a modification operation on the three-dimensional human body model by the target user according to the patient treatment information set; the second control unit 208 is configured to control an associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the modified three-dimensional human body model.

[0069] It can be understood that the units described in the spinal orthosis manufacturing device 200 correspond to the respective steps in the method described with reference to Figure 1 . Thus, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units included therein, and will not be elaborated herein.

[0070] Next, reference is made to Figure 3, which shows a schematic structural diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The illustrated electronic device is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0071] As Figure 3 shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage device 308 into the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0072] Generally, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 the electronic device 300 with various devices is shown, it should be understood that it is not required to implement or include all the shown devices. More or fewer devices may be alternatively implemented or included. Figure 3 Each block shown in

[0073] Specifically, according to some embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such some embodiments, the computer program may be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0074] It should be noted that the computer-readable media described in some embodiments of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0075] In some embodiments, the client and the server may communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0076] The above computer-readable medium may be included in the above electronic device; or it may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device is caused to: obtain patient diagnosis information of a target patient, where the patient diagnosis information includes patient body surface data, and the patient body surface data includes three-dimensional human body data; generate a three-dimensional human body model according to the three-dimensional human body data; update the patient body surface data according to the three-dimensional human body model; store the three-dimensional human body model into the patient body surface data to obtain updated patient body surface data as the patient body surface data; classify the patient diagnosis information to obtain case type information; generate a patient treatment information set according to the case type information; control an associated display device to display the patient treatment information set for a target user to view; in response to receiving a modification operation on the three-dimensional human body model by the target user according to the patient treatment information set, generate a modified three-dimensional human body model; and control an associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the modified three-dimensional human body model.

[0077] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the patient computer, partially on the patient computer, executed as an independent software package, partially on the patient computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the patient computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0078] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in an order different from that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0079] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes an acquisition unit, a first generation unit, an update unit, a classification unit, a second generation unit, a first control unit, a third generation unit, and a second control unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the acquisition unit can also be described as "a unit that acquires patient diagnosis information of a target patient, where the patient diagnosis information includes patient body surface data, and the patient body surface data includes three-dimensional human body data".

[0080] The functions described above can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0081] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure.

Claims

1. A method for manufacturing a spinal orthosis, comprising: Obtaining patient diagnosis information of a target patient, wherein the patient diagnosis information includes patient body surface data, and the patient body surface data includes three-dimensional human data; Generating a three-dimensional human model according to the three-dimensional human data; Updating the patient body surface data according to the three-dimensional human model to obtain updated patient body surface data as the patient body surface data; Performing classification processing on the patient diagnosis information to obtain case type information, including: inputting the patient diagnosis information into a preset case type information generation model to obtain case type information, wherein the case type information characterizes the case type of the target patient; Generating a patient treatment information set according to the case type information; Controlling an associated display device to display the patient treatment information set for a target user to view; Responding to receiving a modification operation on the three-dimensional human model by the target user according to the patient treatment information set, and generating a modified three-dimensional human model; Controlling an associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the modified three-dimensional human model; The preset case type information generation model is trained according to the following steps: Obtaining a sample set, wherein the samples in the sample set include sample patient diagnosis information of previous patients and sample case type information corresponding to the sample patient diagnosis information; Performing the following training steps based on the sample set: Respectively inputting the sample patient diagnosis information of at least one sample in the sample set into an initial case type information generation model to obtain case type information corresponding to each sample in the at least one sample; Comparing the case type information corresponding to each sample in the at least one sample with the corresponding sample case type information; Determining whether the initial preset case type information generation model reaches a preset optimization goal according to the comparison result; Responding to determining that the initial preset case type information generation model reaches the optimization goal, and using the initial preset case type information generation model as the trained preset case type information generation model; Responding to determining that the initial preset case type information generation model does not reach the optimization goal, adjusting the network parameters of the initial preset case type information generation model, and using the unused samples to form a sample set, using the adjusted initial preset case type information generation model as the initial preset case type information generation model, and performing the training steps again.

2. The method according to claim 1, wherein The patient diagnosis information further includes patient foot diagnosis data and patient spinal diagnosis data; And The performing classification processing on the patient diagnosis information to obtain case type information includes: Inputting the patient body surface data included in the patient diagnosis information into a preset body surface case type information generation model to obtain body surface case type information; Inputting the patient foot diagnosis data included in the patient diagnosis information into a preset foot case type information generation model to obtain foot case type information; Inputting the patient spinal diagnosis data included in the patient diagnosis information into a preset spinal case type information generation model to obtain spinal case type information; Generate case type information based on the body surface case type information, the foot case type information, and the spinal case type information.

3. The method according to claim 1, wherein, Generate a patient treatment information set according to the case type information, including: Determine whether there is a preset case type in the preset case type set that meets the preset matching condition according to the case type information, where the preset case types included in the preset case type set correspond to preset treatment information sets; In response to determining that there is a preset case type in the preset case type set that meets the preset matching condition, determine the preset case type that meets the preset matching condition in the preset case type set as the target preset case type; Determine the preset treatment information set corresponding to the target preset case type as the patient treatment information set.

4. The method according to claim 3, wherein, The method further includes: In response to determining that there is no preset case type in the preset case type set that meets the preset matching condition, control the associated display device to display preset treatment prompt information; In response to receiving the input treatment information set, determine the input treatment information set as the patient treatment information set.

5. The method according to any one of claims 1 to 4, wherein The method further includes: Store the patient diagnosis information, the case type information, and the patient treatment information set in the historical patient information database.

6. The method according to claim 1, wherein The preset case type information generation model is a classification model that is pre-trained with patient diagnosis information as input and case type information as output.

7. A spinal orthosis manufacturing device, including: An acquisition unit configured to acquire patient diagnosis information of a target patient, where the patient diagnosis information includes patient body surface data, and the patient body surface data includes human three-dimensional data; A first generation unit configured to generate a human three-dimensional model based on the human three-dimensional data; An update unit configured to update the patient body surface data according to the human three-dimensional model to obtain updated patient body surface data as the patient body surface data; A classification unit configured to classify the patient diagnosis information to obtain case type information, including: inputting the patient diagnosis information into a preset case type information generation model to obtain case type information, where the case type information represents the case type of the target patient; A second generation unit configured to generate a patient treatment information set according to the case type information; A first control unit configured to control the associated display device to display the patient treatment information set for the target user to view; A third generation unit configured to generate a modified human three-dimensional model in response to receiving a modification operation on the human three-dimensional model by the target user according to the patient treatment information set; A second control unit configured to control the associated spinal orthosis manufacturing device to manufacture a spinal orthosis according to the modified human three-dimensional model; The training unit is configured such that the preset case type information generation model is obtained through the following steps: obtaining a sample set, where the samples in the sample set include the sample patient diagnosis information of previous patients and the corresponding sample case type information of the sample patient diagnosis information; performing the following training steps based on the sample set: respectively inputting the sample patient diagnosis information of at least one sample in the sample set into an initial case type information generation model to obtain the case type information corresponding to each sample in the at least one sample; comparing the case type information corresponding to each sample in the at least one sample with the corresponding sample case type information; determining whether the initial preset case type information generation model reaches a preset optimization goal according to the comparison result; in response to determining that the initial preset case type information generation model reaches the optimization goal, using the initial preset case type information generation model as the trained preset case type information generation model; in response to determining that the initial preset case type information generation model does not reach the optimization goal, adjusting the network parameters of the initial preset case type information generation model, and using the unused samples to form a sample set, using the adjusted initial preset case type information generation model as the initial preset case type information generation model, and performing the training steps again.

8. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored, When the one or more programs are executed by the one or more processors, enabling the one or more processors to implement the method according to any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, wherein, The computer program, when executed by a processor, implements the method according to any one of claims 1-6.

Images