Rehabilitation measure determination method and device, terminal equipment and storage medium

Abstract

The invention provides a rehabilitation measure determination method and device, terminal equipment and a storage medium, and the method comprises the steps: obtaining the rehabilitation related information of a to-be-rehabilitated object in multiple dimensions, generating the rehabilitation measure information of the to-be-rehabilitated object according to the rehabilitation related information, and indicating the to-be-rehabilitated object to carry out rehabilitation training according to the rehabilitation measure information. And detecting an updated rehabilitation result after the rehabilitation training of the to-be-rehabilitated object, and replacing the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result reaches the standard. By standardizing the steps of generating the rehabilitation measure information, decision errors caused by insufficient experience or other subjective factors of doctors are avoided, and reasonable and accurate rehabilitation measure information is provided. Appropriate rehabilitation measure information is continuously generated in the rehabilitation process to indicate the to-be-rehabilitated object to perform rehabilitation training in a circulation mode of'rehabilitation measure information generation-to-be-rehabilitated object training-rehabilitation result detection ', and rehabilitation of the to-be-rehabilitated object is completed until the rehabilitation result reaches the standard.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and particularly relates to a method, device, terminal device and storage medium for determining rehabilitation measures. Background Art

[0002] Rehabilitation training refers to physical activities that are beneficial to the recovery or improvement of functions after injury. Except for severe injuries that require rest and treatment, general injuries do not necessarily require complete cessation of physical exercises. Appropriate and scientific physical exercises play a positive role in the rapid healing of injuries and the promotion of functional recovery.

[0003] In the related art, the rehabilitation training measures are usually designed and supervised by doctors to meet the specific rehabilitation needs of the object to be rehabilitated. However, doctors may have problems such as lack of experience or other subjective factors, resulting in poor effects after the object to be rehabilitated implements the rehabilitation measures. Summary of the Invention

[0004] The embodiments of this application provide a method, device, terminal device and storage medium for determining rehabilitation measures, which can solve the problem that doctors may have problems such as lack of experience or other subjective factors when designing rehabilitation measures, resulting in poor effects after the object to be rehabilitated implements the rehabilitation measures.

[0005] The first aspect of the embodiments of this application provides a method for determining rehabilitation measures, including: obtaining rehabilitation-related information of multiple dimensions of the object to be rehabilitated; generating rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information; instructing the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information; detecting the updated rehabilitation result after the object to be rehabilitated performs rehabilitation training, and replacing the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard.

[0006] Optionally, in a possible implementation manner of the first aspect, the above-mentioned rehabilitation-related information includes the physical state information and historical rehabilitation information of the object to be rehabilitated, the physical state information includes physical state characteristics of multiple dimensions, and the historical rehabilitation information includes historical rehabilitation characteristics of multiple dimensions. The above-mentioned generating rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information includes:

[0007] Performing feature extraction on the physical state information and the historical rehabilitation information respectively to determine the feature values of each physical state feature and the feature values of each historical rehabilitation feature;

[0008] Generating rehabilitation measure information according to the feature values of each physical state feature and the feature values of each historical rehabilitation feature.

[0009] Optionally, in another possible implementation manner of the first aspect, the above-mentioned rehabilitation-related information further includes the rehabilitation target information and rehabilitation device information of the object to be rehabilitated;

[0010] The generation of rehabilitation measure information for the object to be rehabilitated based on the above-mentioned rehabilitation-related information further includes: respectively extracting features from the rehabilitation target information and the rehabilitation equipment information to determine the feature values of each rehabilitation target and rehabilitation equipment;

[0011] Generate rehabilitation measure information based on the feature values of each physical state feature and the feature values of each historical rehabilitation feature, including: generating rehabilitation measure information based on the feature values of each physical state feature, each historical rehabilitation feature, each rehabilitation target, and the rehabilitation equipment.

[0012] Optionally, in another possible implementation manner of the first aspect, the above-mentioned extraction of features from the physical state information and the historical rehabilitation information respectively to determine the feature values of each physical state feature and the feature values of each historical rehabilitation feature information includes:

[0013] Using a feature extraction algorithm, identify the physical state features in each dimension of the physical state information, the historical rehabilitation features in each dimension of the historical rehabilitation information, and the corresponding feature expression content;

[0014] Quantify the feature expression content of each dimension to generate the feature values of each physical state feature and the feature values of each historical rehabilitation feature.

[0015] Optionally, in another possible implementation manner of the first aspect, the above-mentioned generation of rehabilitation measure information based on the feature values of each physical state feature and the feature values of each historical rehabilitation feature includes:

[0016] Generate a rehabilitation feature vector based on the feature values of each physical state feature and the feature values of each historical rehabilitation feature;

[0017] Input the rehabilitation feature vector into a preset rehabilitation measure evaluation model, and the rehabilitation measure evaluation model outputs the rehabilitation measure information.

[0018] Optionally, in another possible implementation manner of the first aspect, the above-mentioned generation of rehabilitation measure information based on the feature values of each physical state feature and the feature values of each historical rehabilitation feature includes:

[0019] Based on the feature values of each physical state feature and the feature values of each historical rehabilitation feature, find at least one piece of candidate measure information from a preset rehabilitation database;

[0020] Determine the rehabilitation measure information from all the candidate measure information according to at least one dimension of preset rehabilitation targets and the importance degree of each preset rehabilitation target.

[0021] Optionally, in another possible implementation manner of the first aspect, each piece of candidate measure information corresponds to multiple reference feature vectors clustered into a classification cluster. The above method for finding at least one piece of candidate measure information from a preset rehabilitation database according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature includes:

[0022] Generating a rehabilitation feature vector according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature;

[0023] Performing clustering processing on the rehabilitation feature vector and the multiple reference feature vectors corresponding to each piece of candidate measure information in the rehabilitation database to determine the classification cluster to which the rehabilitation feature vector belongs;

[0024] Finding at least one piece of corresponding candidate measure information from the rehabilitation database according to the determined classification cluster.

[0025] Optionally, in another possible implementation manner of the first aspect, each piece of candidate measure information corresponds to an estimated feature improvement vector. The above method for determining rehabilitation measure information from all candidate measure information according to the preset rehabilitation goals in at least one dimension and the importance degree of each preset rehabilitation goal includes:

[0026] Generating a target effect vector according to the target feature improvement value of each feature dimension in the preset rehabilitation goal;

[0027] Comparing the target effect vector with the estimated feature improvement vectors of each piece of candidate measure information to determine the estimated feature improvement vector with the highest similarity to the target effect vector;

[0028] Determining the candidate measure information corresponding to the determined estimated feature improvement vector as the rehabilitation measure information.

[0029] Optionally, in another possible implementation manner of the first aspect, the above rehabilitation goal information is unstructured information. Before respectively performing feature extraction on the rehabilitation goal information and the rehabilitation device information to determine the eigenvalues of each rehabilitation goal and rehabilitation device, it includes:

[0030] Obtaining historical reference information corresponding to the rehabilitation goal information;

[0031] Determining structured information corresponding to the rehabilitation goal information according to the historical reference information;

[0032] Respectively performing feature extraction on the rehabilitation goal information and the rehabilitation device information to determine the eigenvalues of each rehabilitation goal and rehabilitation device, including:

[0033] Performing feature extraction on the structured information corresponding to the rehabilitation goal information to determine the eigenvalue of each rehabilitation goal.

[0034] The second aspect of the embodiments of the present application provides a rehabilitation measure determination device, including:

[0035] A requirements module, configured to obtain rehabilitation-related information of a plurality of dimensions of an object to be rehabilitated;

[0036] An evaluation module, configured to generate rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information;

[0037] An execution module, configured to instruct the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information;

[0038] A planning module, configured to detect an updated rehabilitation result after the object to be rehabilitated performs rehabilitation training, and replace the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard.

[0039] The third aspect of the embodiments of the present application provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the rehabilitation measure determination method of the first aspect is implemented.

[0040] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the rehabilitation measure determination method of the first aspect is implemented.

[0041] The fifth aspect of the embodiments of the present application provides a computer program product, where when the computer program product runs on a terminal device, the terminal device is enabled to execute the rehabilitation measure determination method of the first aspect.

[0042] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: The embodiments of the present application disclose a rehabilitation measure determination method, device, terminal device, and storage medium. Among them, the method first obtains rehabilitation-related information of a plurality of dimensions of an object to be rehabilitated, then generates rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information, then instructs the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information, and finally detects an updated rehabilitation result after the object to be rehabilitated performs rehabilitation training, and replaces the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard. Thus, by standardizing the steps for generating rehabilitation measure information, it avoids decision-making errors caused by doctors' lack of experience or other subjective factors, and provides reasonable and accurate rehabilitation measure information for the object to be rehabilitated. In addition, the present application continuously uses a cyclic manner of "generating rehabilitation measure information - training the object to be rehabilitated - detecting the rehabilitation result" to continuously generate appropriate rehabilitation measure information during the rehabilitation process of the object to be rehabilitated to instruct the object to be rehabilitated to perform rehabilitation training until the rehabilitation result of the object to be rehabilitated meets the standard, completing the rehabilitation of the object to be rehabilitated. Description of the Drawings

[0043] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0044] Figure 1 It is a schematic flowchart of a method for determining a rehabilitation measure provided by an embodiment of the present application;

[0045] Figure 2 It is a schematic flowchart of some steps in a method for determining a rehabilitation measure provided by an embodiment of the present application;

[0046] Figure 3 It is a schematic structural diagram of a device for determining a rehabilitation measure provided by an embodiment of the present application;

[0047] Figure 4 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0048] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0049] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0050] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0051] As used in the specification of this application and the appended claims, the term "if" may be construed contextually as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed contextually to mean "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]".

[0052] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0053] The reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0054] It should be understood that the magnitude of the sequence numbers of the steps in this embodiment does not mean the sequence of execution. The execution sequence of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0055] In the related art, the measures for rehabilitation training are usually designed and supervised by doctors to meet the specific rehabilitation needs of the object to be rehabilitated. However, doctors may have problems such as lack of experience or other subjective factors, resulting in poor effects after the object to be rehabilitated implements the rehabilitation measures.

[0056] In view of this, the embodiments of this application provide a method, device, terminal device, and storage medium for determining rehabilitation measures. By standardizing the steps for generating rehabilitation measure information, it avoids decision-making errors caused by doctors' lack of experience or other subjective factors, and provides reasonable and accurate rehabilitation measure information for the object to be rehabilitated. In addition, this application continuously uses a cyclic manner of "generating rehabilitation measure information - training the object to be rehabilitated - detecting the rehabilitation result" to continuously generate appropriate rehabilitation measure information during the rehabilitation process of the object to be rehabilitated to instruct the object to be rehabilitated to perform rehabilitation training until the rehabilitation result of the object to be rehabilitated reaches the standard, completing the rehabilitation of the object to be rehabilitated.

[0057] To illustrate the technical solution of the present application, specific embodiments will be used for illustration below.

[0058] Referring to Figure 1 , a schematic flowchart of a rehabilitation measure determination method provided by an embodiment of the present application is shown. This method can be executed by a rehabilitation measure determination device, which can be implemented in software and / or hardware, and the device can be implemented as a terminal or a server. As Figure 1 shown, the rehabilitation measure determination method may include the following steps:

[0059] Step 101, obtain rehabilitation-related information of the object to be rehabilitated in multiple dimensions.

[0060] Among them, the rehabilitation-related information may include the physical state information, historical rehabilitation information, rehabilitation target information, rehabilitation equipment information, etc. of the object to be rehabilitated.

[0061] For example, the physical state information may include information such as gender, height, weight, age, and physical fitness; the historical rehabilitation information may include information such as historical rehabilitation conditions and historical rehabilitation times; the rehabilitation target information may include information such as target rehabilitation cycles, target rehabilitation effects, and target rehabilitation budgets; the rehabilitation equipment information may include information such as rehabilitation equipment types and rehabilitation equipment quantities.

[0062] It should be noted that during the rehabilitation process of the object to be rehabilitated, the above-mentioned rehabilitation-related information in each dimension can be updated in real time to ensure the timeliness and accuracy of subsequent analysis.

[0063] Step 102, generate rehabilitation measure information for the object to be rehabilitated according to the rehabilitation-related information.

[0064] Among them, the rehabilitation measure information may include adjustments in aspects such as diet, sleep, and exercise, aiming to analyze the current physiological phenomena of the object to be rehabilitated according to the rehabilitation-related information, and then conduct targeted training on the object to be rehabilitated.

[0065] In an embodiment of the present application, a rehabilitation database may be pre-constructed, and the rehabilitation database may include multiple pieces of rehabilitation measure information, and each piece of rehabilitation measure information corresponds to at least one physiological phenomenon, such as fractures, joint surgeries, heart problems, lung problems, nervous system problems, etc., indicating which physiological phenomenon the rehabilitation measure information can be used for rehabilitation.

[0066] It should be noted that, in order to better understand and analyze the rehabilitation-related information of the object to be rehabilitated, the rehabilitation-related information can be quantified first to convert the complex rehabilitation-related information of the object to be rehabilitated into numerical values or operable features. That is, as a possible implementation manner of the embodiments of the present application, when the rehabilitation-related information includes physical state information and historical rehabilitation information, the above step 102 may include: respectively extracting features from the physical state information and the historical rehabilitation information to determine the feature values of each physical state feature and each historical rehabilitation feature; generating rehabilitation measure information according to the feature values of each physical state feature and each historical rehabilitation feature.

[0067] Among them, feature extraction is a process of extracting useful information for solving problems or describing specific attributes from the original data. Feature extraction can convert the rich and complex rehabilitation-related information of the object to be rehabilitated into numerical values or operable features, so as to better understand the condition of the object to be rehabilitated, and then generate accurate and reasonable rehabilitation measure information.

[0068] As another possible implementation manner of the embodiments of the present application, when the rehabilitation-related information further includes rehabilitation target information and rehabilitation device information, the above step 102 may further include: respectively extracting features from the rehabilitation target information and the rehabilitation device information to determine the feature values of each rehabilitation target and each rehabilitation device; correspondingly, the above generating rehabilitation measure information according to the feature values of each physical state feature and each historical rehabilitation feature may include: generating rehabilitation measure information according to the feature values of each physical state feature, each historical rehabilitation feature, each rehabilitation target and each rehabilitation device.

[0069] In a possible implementation manner, a feature extraction algorithm can be used to identify the physical state features of each dimension in the physical state information, the historical rehabilitation features of each dimension in the historical rehabilitation information, and the corresponding feature expression content; quantify the feature expression content of each dimension to generate the feature values of each physical state feature and each historical rehabilitation feature.

[0070] Among them, the feature extraction algorithm can be the TF-IDF (Term Frequency-Inverse Document Frequency) text feature extraction algorithm. The TF-IDF text feature extraction algorithm takes into account the frequency of a word in a document and its importance in the entire text set, and can highlight the words that appear frequently in a specific document but are relatively rare in the entire text set, so as to better capture the differences between documents.

[0071] It should be noted that after extracting the features and the corresponding feature description content using the feature extraction algorithm, the next step is to quantify these feature description contents. These feature description contents may have various types, such as numerical data, degree data, categorical data, etc., and the quantification methods for different types of feature description contents are also different.

[0072] For example, assume that the object to be rehabilitated suffers from arthritis, and the features and the corresponding feature description content obtained through the feature extraction algorithm are: degree of joint pain: unbearable pain; joint movement condition: limited joint range of motion, unable to complete some basic activities in daily life; weight: 75 kg; gender: male. Next, quantify the feature description content. For the feature description content of weight, the current weight value of 75 of the object to be rehabilitated can be directly determined as the corresponding feature value; for the feature description content of the degree of joint pain and joint movement condition, since a numerical value cannot be directly obtained, a scoring standard can be set in combination with the actual application scenario, such as 0 - 10, and the degree of joint pain and joint movement condition of the object to be rehabilitated are scored according to the feature description content, so as to obtain the feature value of this type of feature description content. For example, if the feature description content of the degree of joint pain is unbearable pain, the feature value corresponding to the degree of joint pain can be determined as 8; for the feature description content of gender, methods such as one-hot encoding can be used to convert it into a numerical feature. For example, gender can be encoded as 0 or 1.

[0073] Furthermore, after obtaining all the feature values included in the rehabilitation-related information, all the feature values can be integrated into a rehabilitation feature vector, and then this feature vector is input into a rehabilitation measure evaluation model, which is a machine learning model trained based on a rehabilitation database and is used to output rehabilitation measure information according to the feature vector. That is, as a possible implementation manner of the embodiment of the present application, the steps of generating rehabilitation measure information include: generating a rehabilitation feature vector according to the feature values of each physical state feature and the feature values of each historical rehabilitation feature; inputting the rehabilitation feature vector into a preset rehabilitation measure evaluation model, and the rehabilitation measure evaluation model outputs rehabilitation measure information. It should be understood that a more comprehensive rehabilitation feature vector can also be generated according to the feature values of each physical state feature, the feature values of each historical rehabilitation feature, the feature values of each rehabilitation goal, and the feature values of each rehabilitation device.

[0074] Step 103, according to the rehabilitation measure information, instruct the object to be rehabilitated to perform rehabilitation training.

[0075] Among them, after generating the rehabilitation measure information, it can be transmitted to the object to be rehabilitated in real time, and the object to be rehabilitated then performs rehabilitation training according to the received rehabilitation measure information, so as to help the object to be rehabilitated recover or improve its functional level to the greatest extent.

[0076] Step 104: Detect the updated rehabilitation result of the object to be rehabilitated after the rehabilitation training, and replace the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard.

[0077] In the embodiment of the present application, after the object to be rehabilitated undergoes rehabilitation training, the updated rehabilitation result of the latest round of rehabilitation training is detected. If the rehabilitation result does not meet the standard, the updated rehabilitation result needs to be used to replace the rehabilitation result of the previous round, and then the next round of rehabilitation training is performed. During the next round of rehabilitation training, the aforementioned steps 101-102 are re-executed. After generating new rehabilitation measure information, step 103 is executed to instruct the object to be rehabilitated to perform rehabilitation training. Among them, during the re-execution of step 102, the latest round of rehabilitation result and rehabilitation-related information can be combined to generate new rehabilitation measure information to instruct the object to be rehabilitated to perform rehabilitation training. If the updated rehabilitation result of the latest round meets the standard, it is considered that the ideal rehabilitation effect has been achieved and the rehabilitation is completed. Thus, through the cyclic manner of "generating rehabilitation measure information - the object to be rehabilitated trains - detecting the rehabilitation result" continuously, the rehabilitation measure information is continuously updated during the rehabilitation process of the object to be rehabilitated to instruct the object to be rehabilitated to perform rehabilitation training until the rehabilitation result of the object to be rehabilitated meets the standard and the rehabilitation of the object to be rehabilitated is completed.

[0078] That is to say, the rehabilitation measure information will be fed back and adjusted according to the actual rehabilitation result, which can ensure that the rehabilitation measure information can better meet the physiological changes, rehabilitation progress and special needs of the object to be rehabilitated and improve the rehabilitation effect.

[0079] The rehabilitation measure determination method disclosed in the above embodiment of the present application first obtains the rehabilitation-related information of the object to be rehabilitated in multiple dimensions, then generates the rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information, then instructs the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information, and finally detects the updated rehabilitation result of the object to be rehabilitated after the rehabilitation training, and replaces the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard. Thus, by standardizing the steps of generating the rehabilitation measure information, it avoids the decision-making errors caused by doctors due to lack of experience or other subjective factors, and provides reasonable and accurate rehabilitation measure information for the object to be rehabilitated. In addition, the present application continuously generates appropriate rehabilitation measure information to instruct the object to be rehabilitated to perform rehabilitation training during the rehabilitation process of the object to be rehabilitated through the cyclic manner of "generating rehabilitation measure information - the object to be rehabilitated trains - detecting the rehabilitation result" until the rehabilitation result of the object to be rehabilitated meets the standard and the rehabilitation of the object to be rehabilitated is completed.

[0080] See Figure 2 , which shows a schematic flowchart of a rehabilitation measure determination method provided by an embodiment of the present application. Figure 2 It can be regarded as an example of step 102. As Figure 2As shown, the method for determining the rehabilitation measure may include the following steps:

[0081] Step 201: Based on the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature, find at least one piece of candidate measure information from a preset rehabilitation database.

[0082] It should be understood that at least one piece of candidate measure information may also be found from a preset rehabilitation database based on the eigenvalue of each physical state feature, the eigenvalue of each historical rehabilitation feature, the eigenvalue of each rehabilitation goal, and the eigenvalue of each rehabilitation device.

[0083] In an embodiment of the present application, based on the eigenvalue of each feature of the object to be rehabilitated, the physiological phenomenon corresponding to the object to be rehabilitated can be analyzed. Based on this physiological phenomenon, the historical rehabilitation treatment measures taken by other rehabilitated objects when facing the same physiological phenomenon can be found from the rehabilitation database. All relevant historical rehabilitation treatment measures found in the rehabilitation database are determined as candidate measure information.

[0084] Further, the physiological phenomenon corresponding to the object to be rehabilitated can be analyzed in a clustering manner. Among them, each piece of candidate measure information in the rehabilitation database corresponds to a plurality of reference feature vectors clustered into a classification cluster. A classification cluster refers to a set of features containing similar features obtained through a clustering algorithm. In an embodiment of the present application, each classification cluster represents a physiological phenomenon. By performing clustering processing on the rehabilitation feature vector and the plurality of reference feature vectors, the classification cluster to which the rehabilitation feature vector belongs (i.e., the physiological phenomenon of the object to be rehabilitated) can be obtained, and then the relevant candidate measure information can be found. That is, as a possible implementation manner in an embodiment of the present application, the above step 201 may include: generating a rehabilitation feature vector based on the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature; performing clustering processing on the rehabilitation feature vector and the plurality of reference feature vectors corresponding to each piece of candidate measure information in the rehabilitation database to determine the classification cluster to which the rehabilitation feature vector belongs; and finding at least one piece of corresponding candidate measure information from the rehabilitation database according to the determined classification cluster.

[0085] As an example, the clustering processing can be implemented by clustering algorithms such as K-means and Mean Shift. Among them, K-means is a partitioning clustering method, and its basic idea is to divide the data set into K different clusters, and each cluster contains the data points closest to its mean; Mean Shift is a density-based clustering method, and its goal is to find the region with the highest data point density and determine the clustering center based on this.

[0086] It should be understood that the steps for generating the rehabilitation feature vector can refer to the relevant descriptions in the foregoing step 102 and will not be elaborated here.

[0087] Step 202: Determine the rehabilitation measure information from all the candidate measure information according to the preset rehabilitation goals in at least one dimension and the importance degree of each preset rehabilitation goal.

[0088] It should be noted that since clustering is essentially an unsupervised learning method that divides data only based on the similarity between feature vectors, some key information may be ignored. That is to say, relying solely on the clustering results is not sufficient to provide the optimal rehabilitation measure information. In response to this situation, at least one rehabilitation goal can be determined in combination with the actual rehabilitation needs of the object to be rehabilitated. The rehabilitation goal can be given by a doctor and is used to match the most relevant rehabilitation measure information from the candidate measure information to ensure that the rehabilitation plan is more tailored to the individual needs of the object to be rehabilitated and improve the rationality and accuracy of the rehabilitation measure information.

[0089] In the embodiments of the present application, each rehabilitation goal corresponds to an importance degree. For example, the importance degree of each rehabilitation goal can be represented by a weight. The higher the importance, the higher the weight. In the process of determining the rehabilitation measure information from all the candidate measure information, it is necessary to give priority to the candidate measure information corresponding to the rehabilitation goal with a higher importance degree.

[0090] For example, the rehabilitation goal A is to control the body temperature between 36.5 and 37.5 degrees Celsius, and the rehabilitation goal B is to control the heart rate between 60 and 100 beats per minute. The importance of rehabilitation goal A is less than that of rehabilitation goal B, which means that more attention should be paid to the heart rate during the rehabilitation of the object to be rehabilitated. Therefore, when determining the rehabilitation measure information, the candidate measure information with a better rehabilitation effect on the heart rate is preferentially selected.

[0091] In a possible implementation manner, each candidate measure information in the rehabilitation database may also correspond to the estimated feature improvement in at least one dimension, and the estimated feature improvement can be represented in the form of a feature vector.

[0092] For example, suppose there is candidate measure information K in the rehabilitation database, and this candidate measure information K can be used for physiological phenomenon a. Combining historical data, when the rehabilitation object implements candidate measure information K in the face of physiological phenomenon a, each feature in the body state information will change accordingly. For example, the body temperature drops by 0.5 degrees Celsius, the heart rate decreases by 10 beats per minute, the weight drops by 2 kg... This change is the estimated feature improvement corresponding to candidate measure information K and can be represented in the form of a feature vector as (-0.5, -10, -2,...).

[0093] Further, corresponding target effect vectors can be generated according to each rehabilitation goal, that is, the expected changes in the physical state characteristics of the target to be rehabilitated. Then, the target effect vectors are compared with the estimated feature improvement vectors corresponding to each candidate measure information in the rehabilitation database, and then the most suitable rehabilitation measure information is determined. That is, as a possible implementation manner of the embodiment of the present application, the above step 202 may include: generating corresponding target effect vectors according to the target feature improvement values of each feature dimension in the preset rehabilitation goal; comparing the target effect vectors with the estimated feature improvement vectors of each candidate measure information, and determining the estimated feature improvement vector with the highest similarity to the target effect vector; determining the candidate measure information corresponding to the determined estimated feature improvement vector as the rehabilitation measure information.

[0094] For example, the doctor believes that the two physical state characteristics of the body temperature and weight of the object to be rehabilitated are very important. Among them, the body temperature needs to be reduced by 0.5 degrees Celsius, and the weight needs to be reduced by 2 kg. Then, the target feature improvement value corresponding to the body temperature is -0.5, and the target feature improvement value corresponding to the weight is -10. The target effect vector obtained according to the two target feature improvement values is (-0.5, 0, -2,...). Then, the target effect vector (-0.5, 0, -2,...) is compared with the estimated feature improvement vectors of each candidate measure information. Finally, it is found that the estimated feature improvement vector (-0.5, -10, -2,...) corresponding to the candidate measure information K is the most matched with the target effect vector. Then, the candidate measure information K can be determined as the rehabilitation measure information.

[0095] It should be noted that if one or more of the estimated feature improvement situations in the matched candidate measure information violate the rehabilitation goal information. For example, two candidate measure information are matched, namely candidate measure information K and candidate measure information L. Among them, the estimated feature improvement vector corresponding to candidate measure information K is (-0.5, -10, -2,...), and the estimated feature improvement vector corresponding to candidate measure information K is (-0.5, 0, -2,...). It can be seen that both candidate measure information K and candidate measure information L are matched with the target effect vector (-0.5, 0, -2,...). However, if the rehabilitation goal information is: the body temperature drops by 0.5 degrees Celsius, and while the weight drops by 2 kg, the heart rate cannot change. That is to say, the candidate measure information K does not meet the rehabilitation goal information, and the candidate measure information K needs to be abandoned, and the candidate measure information L is selected as the rehabilitation measure information.

[0096] In a possible implementation, since the rehabilitation target information given by a doctor may be unquantifiable directly, that is, unstructured information. Therefore, through big data analysis, the unstructured rehabilitation target information can be mapped to a set of related features, so as to convert the unstructured information into feature values that can be searched in the database. That is, as a possible implementation in the embodiments of the present application, historical reference information corresponding to the rehabilitation target information can be obtained; according to the historical reference information, the structured information corresponding to the rehabilitation target information can be determined; correspondingly, when extracting features from the rehabilitation target information, the structured information corresponding to the rehabilitation target information can be extracted to determine the feature values of each rehabilitation target.

[0097] For example, if the rehabilitation target information given by a doctor is to control blood pressure within the normal range and control body temperature within the normal range, by analyzing the data of multiple historical rehabilitation targets in combination with the historical reference information, the rehabilitation target information includes the rehabilitation target of controlling blood pressure within the normal range. After the rehabilitation is completed, the blood pressure is almost all controlled within the range of systolic blood pressure of 120-130 and diastolic blood pressure of 80-90; the rehabilitation target information includes the rehabilitation target of controlling body temperature within the normal range. After the rehabilitation is completed, the body temperature is almost all controlled within the range of 36.5-37.5 degrees Celsius. Therefore, the structured information corresponding to the rehabilitation target information can be determined according to the data after the above analysis.

[0098] As an example, the method of analyzing the data of multiple historical rehabilitation targets in combination with the historical reference information can be analyzed using Natural Language Processing (NLP) technology. NLP technology is a branch in the fields of artificial intelligence and computer science, focusing on enabling computers to understand, parse, and generate human natural language. NLP technology involves using computer algorithms and technologies to process, analyze, and handle various forms of human language, including text, speech, and dialogue. The goal is to enable computers to process and understand the meaning, grammar, semantics, and context of human language and extract useful information from it.

[0099] In the embodiments of the present application, assume that the rehabilitation target information given by a doctor is an abstract state characteristic, such as a moist and red tongue coating. This state characteristic does not match any of the features in the rehabilitation database at all, and this state characteristic cannot be quantified either. It is very difficult to match accurate rehabilitation measure information according to the state characteristic.

[0100] Based on this, the historical reference information corresponding to the moist and red tongue coating can be used for big data analysis, collecting the physical state information of the rehabilitation objects including this situation, and analyzing the correlation between the physical state information and other features.

[0101] Exemplarily, a correlation analysis method, such as the Pearson correlation coefficient, can be used to calculate the linear correlation between the state characteristics and the existing features in the database (such as age, gender, body temperature, weight, blood pressure, etc.). The value range is from -1 to 1, where a positive value indicates a positive correlation, a negative value indicates a negative correlation, and 0 indicates no correlation. Assuming that the correlation coefficient between the state characteristic and the body temperature is positive, it means that as the body temperature increases, the possibility of the tongue coating being moist and red also increases.

[0102] Furthermore, machine learning algorithms can also be used to perform association analysis on the state characteristics and the existing features in the database, explore the potential relationships between the abstract state characteristics and other features, and find out which physical characteristics of the rehabilitation goal may change when the state feature appears. In this way, the structured features and corresponding feature values related to the state characteristics can be found, and then the rehabilitation measure information can be matched.

[0103] The rehabilitation measure determination method disclosed in the above embodiments of the present application first searches for at least one candidate measure information from a preset rehabilitation database according to the feature values of each body state feature and the feature values of each historical rehabilitation feature, and then determines the rehabilitation measure information from all the candidate measure information according to the preset rehabilitation goals of at least one dimension and the importance degree of each preset rehabilitation goal. Thus, by combining the rehabilitation-related information of multiple dimensions of the object to be rehabilitated, multiple candidate measure information is searched from the rehabilitation database, and further combined with the important rehabilitation goals given by the doctor, the candidate measure information is screened, so as to obtain more accurate rehabilitation measure information.

[0104] Referring to Figure 3 , a schematic structural diagram of a rehabilitation measure determination device provided by an embodiment of the present application is shown. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown.

[0105] The rehabilitation measure determination device may specifically include the following modules:

[0106] A requirement module 301, configured to obtain the rehabilitation-related information of multiple dimensions of the object to be rehabilitated.

[0107] An evaluation module 302, configured to generate the rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information.

[0108] An execution module 303, configured to instruct the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information.

[0109] A plan module 304, configured to detect the updated rehabilitation result after the object to be rehabilitated performs rehabilitation training, and replace the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result reaches the standard.

[0110] The rehabilitation measure determination device disclosed in the above embodiments of the present application first obtains rehabilitation-related information of a plurality of dimensions of the object to be rehabilitated, then generates rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information, and then instructs the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information. Finally, it detects the updated rehabilitation result after the object to be rehabilitated performs rehabilitation training, and replaces the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result reaches the standard. Thus, by standardizing the steps of generating rehabilitation measure information, it avoids decision-making errors caused by doctors' lack of experience or other subjective factors, and provides reasonable and accurate rehabilitation measure information for the object to be rehabilitated. In addition, the present application continuously generates appropriate rehabilitation measure information to instruct the object to be rehabilitated to perform rehabilitation training during the rehabilitation process of the object to be rehabilitated in a cyclic manner of "generating rehabilitation measure information - the object to be rehabilitated trains - detecting the rehabilitation result" until the rehabilitation result of the object to be rehabilitated reaches the standard, and completes the rehabilitation of the object to be rehabilitated.

[0111] Optionally, in a possible implementation manner of the embodiment of the present application, the above evaluation module 302 may specifically include the following sub-modules:

[0112] The first determination sub-module is used to respectively extract features from the physical state information and the historical rehabilitation information, and determine the feature values of each physical state feature and the feature values of each historical rehabilitation feature.

[0113] The first generation sub-module is used to generate rehabilitation measure information according to the feature values of each physical state feature and the feature values of each historical rehabilitation feature.

[0114] Optionally, in another possible implementation manner of the embodiment of the present application, the above evaluation module 302 may specifically include the following sub-modules:

[0115] The second determination sub-module is used to respectively extract features from the rehabilitation target information and the rehabilitation equipment information, and determine the feature values of each rehabilitation target and rehabilitation equipment.

[0116] The above first generation sub-module may specifically include the following units:

[0117] The first generation unit is used to generate rehabilitation measure information according to the feature values of each physical state feature, each historical rehabilitation feature, each rehabilitation target and rehabilitation equipment.

[0118] Optionally, in yet another possible implementation manner of the embodiment of the present application, the above first determination sub-module may specifically include the following units:

[0119] The first recognition unit is used to use a feature extraction algorithm to recognize the physical state features of each dimension in the physical state information, the historical rehabilitation features of each dimension in the historical rehabilitation information, and the corresponding feature expression content.

[0120] A second generation unit, configured to quantify the feature expression content of each dimension to generate an eigenvalue of each physical state feature and an eigenvalue of each historical rehabilitation feature.

[0121] Optionally, in another possible implementation manner of the embodiment of the present application, the above first generation sub-module may specifically include the following units:

[0122] A third generation unit, configured to generate a rehabilitation feature vector according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature.

[0123] A first input unit, configured to input the rehabilitation feature vector into a preset rehabilitation measure evaluation model, and the rehabilitation measure evaluation model outputs rehabilitation measure information.

[0124] Optionally, in another possible implementation manner of the embodiment of the present application, the above first generation sub-module may specifically include the following units:

[0125] A first search unit, configured to search for at least one piece of candidate measure information from a preset rehabilitation database according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature.

[0126] A first determination unit, configured to determine rehabilitation measure information from all candidate measure information according to at least one dimension of preset rehabilitation goals and the importance degree of each preset rehabilitation goal.

[0127] Optionally, in another possible implementation manner of the embodiment of the present application, the above first search unit is specifically configured to: generate a rehabilitation feature vector according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature; perform clustering processing on the rehabilitation feature vector and multiple reference feature vectors corresponding to each candidate measure information in the rehabilitation database to determine the classification cluster to which the rehabilitation feature vector belongs; and search for at least one piece of corresponding candidate measure information from the rehabilitation database according to the determined classification cluster.

[0128] Optionally, in another possible implementation manner of the embodiment of the present application, the above first determination unit is specifically configured to: generate a corresponding target effect vector according to the target feature improvement value of each feature dimension in the preset rehabilitation goal; compare the target effect vector with the estimated feature improvement vector of each candidate measure information to determine the estimated feature improvement vector with the highest similarity to the target effect vector; and determine the candidate measure information corresponding to the determined estimated feature improvement vector as the rehabilitation measure information.

[0129] Optionally, in another possible implementation manner of the embodiment of the present application, the above evaluation module 302 may specifically include the following sub-modules:

[0130] The first acquisition sub-module is used to acquire historical reference information corresponding to the rehabilitation target information.

[0131] The third determination sub-module is used to determine the structured information corresponding to the rehabilitation target information according to the historical reference information.

[0132] The above-mentioned second determination sub-module may specifically include the following units:

[0133] The second determination unit is used to perform feature extraction on the structured information corresponding to the rehabilitation target information to determine the feature values of each rehabilitation target.

[0134] The rehabilitation measure determination device disclosed in the above embodiments of the present application first finds at least one candidate measure information from a preset rehabilitation database according to the feature values of each physical state feature and the feature values of each historical rehabilitation feature, and then determines the rehabilitation measure information from all the candidate measure information according to the preset rehabilitation targets of at least one dimension and the importance degree of each preset rehabilitation target. Thus, by combining the rehabilitation-related information of multiple dimensions of the object to be rehabilitated, multiple candidate measure information is found from the rehabilitation database, and further combined with the important rehabilitation targets given by the doctor, the candidate measure information is screened, so as to obtain more accurate rehabilitation measure information.

[0135] The rehabilitation measure determination device provided by the embodiments of the present application can be applied in the foregoing method embodiments. For details, please refer to the description of the foregoing method embodiments, which will not be repeated here.

[0136] Figure 4 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 4 shown, the terminal device 400 of this embodiment includes: at least one processor 410 ( Figure 4 only one processor is shown in the figure), a memory 420, and a computer program 421 stored in the memory 420 and operable on the at least one processor 410. When the processor 410 executes the computer program 421, the steps in the above-mentioned rehabilitation measure determination method embodiment are implemented.

[0137] The terminal device 400 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 410 and a memory 420. Those skilled in the art can understand that Figure 4 merely an example of the terminal device 400, which does not constitute a limitation on the terminal device 400, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0138] The so-called processor 410 may be a Central Processing Unit (CPU), and the processor 410 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0139] In some embodiments, the memory 420 may be an internal storage unit of the terminal device 400, such as the hard disk or memory of the terminal device 400. In other embodiments, the memory 420 may also be an external storage device of the terminal device 400, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the terminal device 400. Further, the memory 420 may also include both the internal storage unit of the terminal device 400 and the external storage device. The memory 420 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as the program code of the computer program, etc. The memory 420 may also be used to temporarily store data that has been output or is to be output.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0141] In the above embodiments, the descriptions of the various embodiments each have their own focuses. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0142] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0143] In the embodiments provided in this application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0144] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] In addition, the functional units in the various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0146] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0147] To implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by a computer program product. When the computer program product runs on a terminal device, the terminal device can execute the steps in the above-described method embodiments.

[0148] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A method for determining rehabilitation measures, characterized in that, it includes: Obtain rehabilitation-related information of the object to be rehabilitated in multiple dimensions; Generate rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information; According to the rehabilitation measure information, instruct the object to be rehabilitated to carry out rehabilitation training; Detect the updated rehabilitation result after the object to be rehabilitated undergoes rehabilitation training, and replace the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard.

2. The method for determining rehabilitation measures according to claim 1, characterized in that, the rehabilitation-related information includes the physical state information and historical rehabilitation information of the object to be rehabilitated, the physical state information includes physical state characteristics in multiple dimensions, the historical rehabilitation information includes historical rehabilitation characteristics in multiple dimensions, and the generating the rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information includes: Extract features from the physical state information and historical rehabilitation information respectively to determine the feature values of each physical state feature and each historical rehabilitation feature; Generate the rehabilitation measure information according to the feature values of each physical state feature and each historical rehabilitation feature.

3. The method for determining rehabilitation measures according to claim 2, characterized in that, the rehabilitation-related information further includes the rehabilitation target information and rehabilitation equipment information of the object to be rehabilitated; the generating the rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information further includes: extracting features from the rehabilitation target information and the rehabilitation equipment information respectively to determine the feature values of each rehabilitation target and the rehabilitation equipment; Generating the rehabilitation measure information according to the feature values of each physical state feature and each historical rehabilitation feature includes: generating the rehabilitation measure information according to the feature values of each physical state feature, each historical rehabilitation feature, each rehabilitation target and the rehabilitation equipment.

4. The method for determining rehabilitation measures according to claim 3, characterized in that, the extracting features from the physical state information and historical rehabilitation information respectively to determine the feature values of each physical state feature and the feature values of each historical rehabilitation information includes: Using a feature extraction algorithm, identify the physical state features in each dimension of the physical state information, the historical rehabilitation features in each dimension of the historical rehabilitation information, and the corresponding feature expression content; Quantify the feature expression content of each dimension to generate the feature values of each physical state feature and each historical rehabilitation feature.

5. The method for determining rehabilitation measures according to claim 2, characterized in that, the generating the rehabilitation measure information according to the feature values of each physical state feature and each historical rehabilitation feature includes: Generate a rehabilitation feature vector according to the feature values of each physical state feature and each historical rehabilitation feature; Input the rehabilitation feature vector into a preset rehabilitation measure evaluation model, and the rehabilitation measure evaluation model outputs the rehabilitation measure information.

6. The method for determining rehabilitation measures according to claim 2 or 3, characterized in that, Generating the rehabilitation measure information based on the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature includes: Searching for at least one piece of candidate measure information from a preset rehabilitation database according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature; Determining the rehabilitation measure information from all the candidate measure information according to at least one dimension of preset rehabilitation goals and the importance degree of each preset rehabilitation goal.

7. The rehabilitation measure determination method according to claim 6, wherein, Each of the candidate measure information corresponds to a plurality of reference feature vectors clustered into a classification cluster. The step of searching for at least one piece of candidate measure information from a preset rehabilitation database according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature includes: Generating a rehabilitation feature vector according to the eigenvalue of each physical state feature and the eigenvalue of each historical rehabilitation feature; Performing clustering processing on the rehabilitation feature vector and the plurality of reference feature vectors corresponding to each candidate measure information in the rehabilitation database to determine the classification cluster to which the rehabilitation feature vector belongs; Searching for the corresponding at least one piece of candidate measure information from the rehabilitation database according to the determined classification cluster.

8. The rehabilitation measure determination method according to claim 6, wherein, Each of the candidate measure information corresponds to an estimated feature improvement vector. The step of determining the rehabilitation measure information from all the candidate measure information according to at least one dimension of preset rehabilitation goals and the importance degree of each preset rehabilitation goal includes: Generating a target effect vector according to the target feature improvement value of each feature dimension in the preset rehabilitation goal; Comparing the target effect vector with the estimated feature improvement vector of each candidate measure information to determine the estimated feature improvement vector with the highest similarity to the target effect vector; Determining the candidate measure information corresponding to the determined estimated feature improvement vector as the rehabilitation measure information.

9. The rehabilitation measure determination method according to claim 3, wherein, The rehabilitation goal information is unstructured information. Before respectively performing feature extraction on the rehabilitation goal information and the rehabilitation device information to determine the eigenvalue of each rehabilitation goal and the rehabilitation device, it includes: Obtaining the historical reference information corresponding to the rehabilitation goal information; Determining the structured information corresponding to the rehabilitation goal information according to the historical reference information; The step of respectively performing feature extraction on the rehabilitation goal information and the rehabilitation device information to determine the eigenvalue of each rehabilitation goal and the rehabilitation device includes: Performing feature extraction on the structured information corresponding to the rehabilitation goal information to determine the eigenvalue of each rehabilitation goal.

10. A rehabilitation measure determination device, wherein, It includes: A requirement module, configured to obtain rehabilitation-related information of a plurality of dimensions of an object to be rehabilitated; An evaluation module, configured to generate rehabilitation measure information of the object to be rehabilitated according to the rehabilitation-related information; An execution module, configured to instruct the object to be rehabilitated to perform rehabilitation training according to the rehabilitation measure information. A planning module, configured to detect an updated rehabilitation result of the rehabilitation object after rehabilitation training, and replace the current rehabilitation result with the updated rehabilitation result until the updated rehabilitation result meets the standard.

11. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, when the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium storing a computer program, wherein, when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images