Rehabilitation suggestion generation method, equipment and medium

Abstract

The invention relates to the technical field of computer assistance, and discloses a rehabilitation suggestion generation method and device and a medium, and the method comprises the steps: sending initial integrated data of a patient to a rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates an initial rehabilitation suggestion based on the initial integrated data; acquiring feedback data of the patient; performing multi-source integration according to the patient feedback data and the initial integration data to obtain target integration data; and sending the target integrated data to rehabilitation suggestion prediction equipment, so that the rehabilitation suggestion prediction equipment generates a target rehabilitation suggestion based on the target integrated data. Compared with the prior art, the method has the advantages that the feedback data of the patient is acquired and is subjected to multi-source integration with the related data of the patient in multiple preset dimensions, so that the comprehensiveness of the target integrated data is remarkably improved, the pertinence of the target rehabilitation suggestions to the patient is improved, the target rehabilitation suggestions are more matched with the change of the illness state of the patient, and the patient experience is improved. And doctors are effectively assisted in making more accurate rehabilitation suggestions.

Description

Technical Field

[0001] The present application relates to the field of computer-aided technology, and in particular to a method, device, and medium for generating rehabilitation suggestions. Background Art

[0002] In related technologies, doctors regularly diagnose patients during their recovery and develop appropriate rehabilitation recommendations based on changes in their condition. For patients with respiratory diseases, rehabilitation recommendations typically include environmental adjustments and treatment recommendations to help patients recover from various aspects. However, the method used to generate rehabilitation recommendations in related technologies needs to be improved, leading to the urgent need for a method that can assist doctors in developing rehabilitation recommendations. Summary of the Invention

[0003] The present application provides a method, device and medium for generating rehabilitation suggestions, which obtains patient feedback data and integrates it with relevant data of the patient in multiple preset dimensions through multi-source integration, thereby significantly improving the comprehensiveness of the target integrated data, thereby improving the targetedness of the target rehabilitation suggestions to the patient, better matching the changes in the patient's condition, and effectively assisting doctors in formulating more accurate rehabilitation suggestions.

[0004] In order to achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, an embodiment of the present application provides a method for generating rehabilitation advice, the method comprising: Sending the patient's initial integrated data to a rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates an initial rehabilitation suggestion based on the initial integrated data; wherein the initial integrated data is obtained by multi-dimensionally integrating relevant data of the patient in multiple preset dimensions; Acquiring patient feedback data; wherein the patient feedback data is obtained in response to a feedback operation on the patient side regarding the initial rehabilitation suggestion; Performing multi-source integration based on the patient feedback data and the initial integrated data to obtain target integrated data; The target integrated data is sent to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates a target rehabilitation suggestion based on the target integrated data.

[0005] The rehabilitation suggestion generation method proposed in the embodiment of the present application generates corresponding initial rehabilitation suggestions through a rehabilitation suggestion prediction device based on the initial integrated data obtained by multi-dimensionally integrating the patient's relevant data on multiple preset dimensions; and obtains patient feedback data, and performs multi-source integration based on the initial integrated data combined with the patient feedback data to obtain target integrated data, so that the rehabilitation suggestion prediction device can generate target rehabilitation suggestions for the patient based on the target integrated data. Compared with related technologies, this application also integrates patient feedback data representing the patient's status and feelings on the basis of the patient's multi-dimensional relevant data, improves the degree of fit between the target integrated data and the patient's condition changes, optimizes the rehabilitation suggestion prediction device's understanding of the patient's condition changes, thereby improving the accuracy of the target rehabilitation suggestions and their pertinence to the patient, and effectively assisting doctors in formulating more accurate rehabilitation suggestions.

[0006] Optionally, the patient feedback data includes questionnaire response data and the patient's real-time response data to the initial rehabilitation suggestions; the questionnaire response data is obtained in response to a response operation on the patient's side regarding the questionnaire on changes in the condition; and the multi-source integration based on the patient feedback data and the initial integrated data to obtain the target integrated data includes: performing multi-source dynamic integration based on the questionnaire response data, the real-time response data and the initial integrated data to obtain the target integrated data.

[0007] Optionally, the method further includes: receiving the real-time response data; The initial integrated data and the real-time echo data are aggregated in real time to obtain the real-time aggregated data of the patient; and the real-time aggregated data is sent to the rehabilitation advice prediction device so that the rehabilitation advice prediction device generates the condition change questionnaire based on the real-time aggregated data.

[0008] Optionally, the initial integrated data is obtained by: Acquiring current air condition data of the patient's environment, current physiological condition data of the patient, and current doctor's diagnosis data of the patient; The current air state data, the current physiological state data and the current doctor's diagnosis data are simultaneously and sequentially integrated in multiple dimensions to obtain the initial integrated data.

[0009] Optionally, the initial integrated data is obtained by: Obtaining targeted rehabilitation advice and targeted integrated data associated with changes in the patient's condition; Acquiring current air condition data of the patient's environment, current physiological condition data of the patient, and current doctor's diagnosis data of the patient; The targeted rehabilitation suggestions, the targeted integrated data, the current air state data, the current physiological state data and the current doctor's diagnosis data are integrated in a time-series collaborative multi-dimensional manner to obtain the initial integrated data.

[0010] Optionally, the method further includes: Acquiring current air condition data of the patient's environment, current physiological condition data of the patient, and current doctor's diagnosis data of the patient; Performing time-series collaborative multi-dimensional integration on the target integration data, the target rehabilitation suggestion, the current air state data, the current physiological state data, and the current doctor's diagnosis data to obtain time-series collaborative integration data; The time series collaborative integration data is sent to the rehabilitation advice prediction device, so that the rehabilitation advice prediction device generates new rehabilitation advice based on the time series collaborative integration data.

[0011] Optionally, the target rehabilitation suggestion includes a suggestion for adjusting parameters of the patient's environment; the patient's environment is equipped with air conditioning equipment; and the method further includes: The parameter adjustment suggestion is sent to the control device of the air conditioning equipment; wherein the parameter adjustment suggestion is used to instruct the control device to adjust the operating parameters of the air conditioning equipment, so as to provide a rehabilitation environment matching the patient's condition through the air conditioning equipment after the parameter adjustment.

[0012] In a second aspect, an embodiment of the present application provides a method for generating rehabilitation advice, the method comprising: Receiving initial integrated data of a patient; wherein the initial integrated data is obtained by multi-dimensionally integrating relevant data of the patient in multiple preset dimensions; generating an initial rehabilitation suggestion based on the initial integrated data; wherein the initial rehabilitation suggestion is used to indicate a feedback operation performed by the patient in response to the initial rehabilitation suggestion, so as to obtain patient feedback data; Generate target rehabilitation suggestions based on target integrated data; wherein the target integrated data is obtained by multi-source integration of the patient feedback data and the initial integrated data.

[0013] Optionally, the method further includes: receiving real-time summary data; wherein the real-time summary data is obtained by summarizing the initial integrated data and the patient's real-time response data to the initial rehabilitation suggestion in real time; generating a condition change questionnaire based on the real-time aggregated data; The condition change questionnaire is sent to the patient end, so that the patient end responds to the reply operation for the condition change questionnaire and obtains the questionnaire reply data.

[0014] Optionally, the target integrated data is obtained by performing multi-source dynamic integration based on the questionnaire response data, the real-time response data and the initial integrated data.

[0015] In a third aspect, an embodiment of the present application provides a computer device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the method described in any one of the above embodiments by executing the computer instructions.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute any one of the methods in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A structural diagram of a rehabilitation advice generation system provided in an embodiment of the present application; Figure 2 A step diagram of the method for generating rehabilitation suggestions provided in an embodiment of the present application; Figure 3 A diagram showing the steps for generating a questionnaire on condition changes in an embodiment of the present application; Figure 4 A diagram showing the steps for obtaining initial integrated data in an embodiment of the present application; Figure 5 A diagram showing the steps for obtaining initial integrated data in an embodiment of the present application; Figure 6 A diagram of steps for generating new rehabilitation suggestions in an embodiment of the present application; Figure 7 A step diagram of the method for generating rehabilitation suggestions provided in an embodiment of the present application; Figure 8 A diagram showing the steps for generating a questionnaire on condition changes in an embodiment of the present application; Figure 9 A timing diagram of the rehabilitation advice generation method provided in an embodiment of the present application; Figure 10 A module diagram of a rehabilitation advice generating device provided in an embodiment of the present application; Figure 11 A module diagram of a rehabilitation advice generating device provided in an embodiment of the present application; Figure 12 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0020] Some patients, especially those with respiratory illnesses, often require home rehabilitation. During the recovery process, doctors regularly diagnose patients and provide appropriate rehabilitation advice based on their condition. For patients with respiratory illnesses, rehabilitation advice often includes environmental adjustments and treatment options to help them recover from various aspects of their condition.

[0021] However, in related technologies, doctors are unable to obtain relevant patient data in real time, including environmental data of the patient's environment and physiological data reflecting changes in the patient's condition. As a result, doctors are unable to accurately understand the correlation between environmental data and changes in the condition when making a diagnosis, resulting in the rehabilitation advice given being too one-sided and less consistent with the patient, slowing down the patient's recovery process.

[0022] Furthermore, doctors base their diagnoses on their clinical experience and existing diagnostic rules and medical guidelines. However, physiological differences may exist between patients, and the same diagnostic rules and medical guidelines may not be fully applicable to every patient. Similarly, patients may not be able to fully and accurately express their feelings about rehabilitation recommendations and the treatment process during their consultations, making it difficult for doctors to provide targeted rehabilitation advice based on these physiological differences.

[0023] Based on the above problems, this application provides a rehabilitation suggestion generation system. Figure 1 As shown, the system includes a first server, a second server, a first terminal, a second terminal and a third terminal.

[0024] The first server, which serves as a data integration device and can be a cloud server, is connected to multiple data acquisition devices to obtain patient data on multiple preset dimensions and perform multi-dimensional integration. The first server is connected to the second server, the first terminal, the second terminal, and the third terminal, respectively, to send initial or target integrated data to the second server and receive patient feedback and suggestions from the first terminal.

[0025] The second server, which serves as a rehabilitation recommendation prediction device, is equipped with a large model for generating appropriate rehabilitation recommendations based on the integrated data. The second server is connected to the first server, the first terminal, and the second terminal, respectively. The second server receives the initial integrated data or target integrated data from the first server and sends initial rehabilitation recommendations to the second terminal or a condition change questionnaire to the first terminal.

[0026] The first terminal may be a patient terminal, and is in communication with the first server and the second server, respectively. The first terminal is configured to receive initial rehabilitation advice from the first server and present it to the patient. The first terminal is also configured to receive a condition change questionnaire from the second server and transmit patient feedback data to the first server.

[0027] The second terminal may be a doctor's terminal, and is connected to the first server and the second server respectively. The second terminal is configured to receive the initial rehabilitation suggestion sent by the second server, and send the initial rehabilitation suggestion reviewed by the doctor to the first server.

[0028] The third terminal may be a control device, which is in communication with the first server and is configured to receive parameter adjustment suggestions sent by the first server to adjust operating parameters of the air conditioning device.

[0029] Based on the above system, the present application provides a method for generating rehabilitation advice, which can be applied to a data integration device configured in the rehabilitation advice generation system. The method includes: sending the patient's initial integrated data to the rehabilitation advice prediction device, so that the rehabilitation advice prediction device generates an initial rehabilitation advice based on the initial integrated data; wherein the initial integrated data is obtained by multi-dimensional integration of the patient's relevant data on multiple preset dimensions; obtaining patient feedback data; wherein the patient feedback data is obtained in response to a feedback operation on the patient side regarding the initial rehabilitation advice; performing multi-source integration based on the patient feedback data and the initial integrated data to obtain target integrated data; and sending the target integrated data to the rehabilitation advice prediction device, so that the rehabilitation advice prediction device generates a target rehabilitation advice based on the target integrated data.

[0030] The rehabilitation advice generation method proposed in this application is based on the initial integrated data obtained by multi-dimensional integration of the patient's relevant data on multiple preset dimensions, and generates corresponding initial rehabilitation advice through a rehabilitation advice prediction device; and obtains patient feedback data, and performs multi-source integration on the initial integrated data combined with the patient feedback data to obtain target integrated data, so that the rehabilitation advice prediction device can generate target rehabilitation advice for the patient based on the target integrated data.

[0031] Compared with related technologies, this application integrates patient feedback data representing the patient's status and feelings on the basis of the patient's multi-dimensional related data, improves the fit between the target integrated data and the patient's condition changes, and optimizes the rehabilitation advice prediction device's understanding of the patient's condition changes, thereby improving the accuracy of the target rehabilitation advice and its pertinence to the patient, and effectively assisting doctors in formulating more accurate rehabilitation advice.

[0032] According to an embodiment of the present application, an embodiment of a method for generating rehabilitation advice is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] In this embodiment, a method for generating rehabilitation suggestions is provided, which can be used in the above-mentioned data integration device. Figure 2 As shown, the method includes: S210. Send the patient's initial integrated data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates initial rehabilitation suggestions based on the initial integrated data; wherein the initial integrated data is obtained by multi-dimensional integration of relevant data of the patient in multiple preset dimensions.

[0034] S220. Obtain patient feedback data; wherein the patient feedback data is obtained in response to a feedback operation on the patient side regarding the initial rehabilitation suggestion.

[0035] S230. Perform multi-source integration based on the patient feedback data and the initial integrated data to obtain target integrated data.

[0036] S240 . Send the target integrated data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates a target rehabilitation suggestion based on the target integrated data.

[0037] The patient's relevant data in multiple preset dimensions includes, but is not limited to, data on the air quality of the patient's environment, data on the patient's physiological status, and data from the doctor's diagnosis. The air quality data of the patient's environment may be collected by air data acquisition equipment located in the patient's environment, and may include, but is not limited to, data on air temperature, humidity, and air quality. Air quality may include, for example, particulate matter concentration, carbon dioxide content, and negative oxygen ion concentration in the air.

[0038] The patient's physiological status data can be obtained by physiological data collection devices deployed around the patient, including but not limited to the patient's cough-related data, body movement-related data, and sleep quality-related data. Cough-related data may include the loudness, frequency, duration, urgency, and timbre of the patient's cough; body movement-related data may include the number, duration, and amplitude of body movements during sleep; and sleep quality-related data may be obtained by identifying the patient's body movement-related data during sleep.

[0039] It is understood that the preset dimensions can be determined based on the type of illness a patient suffers from, in order to obtain relevant data that accurately reflects the patient's condition changes. The patient's relevant data on multiple preset dimensions can also be used to manage the patient's recovery process and ensure that the patient's recovery process is under control.

[0040] Initial integrated data is generated by multi-dimensionally integrating the aforementioned relevant data. This initial integrated data can be the patient's comprehensive health status data, which is used to form a comprehensive profile of the patient's rehabilitation process at the corresponding time period. This allows the rehabilitation recommendation prediction device to fully understand the patient's own physiological state, as well as the correlation and impact of the patient's environment and the doctor's diagnosis on the patient's condition changes, thereby generating corresponding initial rehabilitation recommendations.

[0041] Initial rehabilitation recommendations can be a preliminary comprehensive rehabilitation plan generated based on the initial integrated data. Implementing these recommendations can improve the patient's condition from multiple perspectives. These recommendations include, but are not limited to, lifestyle recommendations, medication recommendations, dietary recommendations, rehabilitation training recommendations, and personal protective equipment recommendations.

[0042] Patient feedback data can be the differential feedback data given by patients based on their own feelings regarding the initial rehabilitation recommendations. It should be noted that different patients have physiological differences and different historical treatment processes. For the same disease, different patients may have different clinical manifestations, and even if patients have the same clinical manifestations, their specific conditions may also be different. Therefore, by obtaining patient feedback data, we can understand the physiological characteristics of patients and thus understand the differences in how different patients adapt to rehabilitation recommendations.

[0043] Targeted integrated data integrates patient feedback data based on the initial integrated data. Through targeted integrated data, it is possible to determine the patient's response to the initial rehabilitation recommendations and the actual impact of the initial rehabilitation recommendations on the patient's condition changes, thereby achieving personalized management of the patient's rehabilitation process.

[0044] Target rehabilitation recommendations can be personalized rehabilitation plans generated based on target integrated data. Since the target integrated data integrates patient feedback data, when generating target rehabilitation recommendations, the patient's response and the actual impact of the initial rehabilitation recommendations can be considered simultaneously on the basis of the initial integrated data, thereby proposing new rehabilitation plans to patients, improving the targeted nature of target rehabilitation recommendations for patients, and effectively assisting doctors in formulating more accurate rehabilitation recommendations.

[0045] Specifically, the data integration device obtains relevant data of the patient across multiple preset dimensions and performs multi-dimensional integration on the relevant data to obtain initial integrated data. Multi-dimensional integration can be a unified and standardized processing of the relevant data of the patient across multiple preset dimensions, ensuring the uniformity and standardization of the relevant data and improving the comprehensive learning ability of the rehabilitation advice prediction device for the relevant data. Exemplarily, multi-dimensional integration can include operations such as formatting and association identification of the relevant data of the patient across multiple preset dimensions, where the association identification can include adding a timestamp to the relevant data and adding corresponding identification based on the source of the relevant data.

[0046] Furthermore, the initial integrated data is sent to the rehabilitation suggestion prediction device to generate an initial rehabilitation suggestion. This initial rehabilitation suggestion is then sent to the doctor, who can review the accuracy and rationality of the initial rehabilitation suggestion to confirm whether the values in the initial rehabilitation suggestion are consistent with medical common sense and whether the initial rehabilitation suggestion is reasonable and feasible. If the initial rehabilitation suggestion does not meet the requirements, the plan will be adjusted and supplemented to ensure its accuracy and rationality.

[0047] Furthermore, after review by the physician, the physician sends the initial rehabilitation recommendations to the data integration device, which then sends them to the patient, who then receives and implements them. It's understandable that patients may have different responses to the initial rehabilitation recommendations due to their own physiological differences and varying historical treatment experiences. In some cases, a patient may have previously undergone the same treatment method as the initial rehabilitation recommendation, but this treatment method wasn't well-suited to the patient's prior treatment and was unable to effectively improve their condition. In other cases, due to their physiological state, the patient may be unable to complete parts of the initial rehabilitation recommendations, thereby hindering the progress of their rehabilitation. Therefore, patients can provide feedback based on their own experiences at multiple points before or after implementing the initial rehabilitation recommendations to generate patient feedback data, providing feedback on their actual situation and specific experiences. This patient feedback data is received by the data integration device to help the rehabilitation recommendation prediction device generate rehabilitation recommendations that better suit the patient's actual situation.

[0048] Furthermore, after receiving the patient feedback data, the data integration device performs multi-source integration on the patient feedback data and the initial integrated data based on the initial integrated data to obtain target integrated data. It should be noted that during the multi-source integration process, integration weights can be set for the patient feedback data and the initial integrated data, with the patient feedback data being assigned a higher integration weight to increase the importance of the patient's differential feedback in the target integrated data. This allows the patient's actual situation to be fully and accurately reflected in the target integrated data, thereby enabling more targeted rehabilitation recommendations to be provided to the patient.

[0049] Furthermore, the target integrated data is sent to a rehabilitation recommendation prediction device, which generates a target rehabilitation recommendation based on the target integrated data. It is understood that the target rehabilitation recommendation comprehensively considers the patient's relevant data across multiple preset dimensions as well as the patient's actual situation, ensuring that the rehabilitation plan included in the target rehabilitation recommendation is not only scientifically sound but also targeted to the patient, thereby effectively assisting doctors in formulating more accurate rehabilitation recommendations, significantly improving the accuracy of rehabilitation plans and promoting the patient's recovery process.

[0050] The rehabilitation advice generation method provided in this embodiment generates corresponding initial rehabilitation advice through a rehabilitation advice prediction device based on initial integrated data obtained by multi-dimensionally integrating relevant data of the patient in multiple preset dimensions; and obtains patient feedback data, and performs multi-source integration on the initial integrated data in combination with the patient feedback data to obtain target integrated data, so that the rehabilitation advice prediction device can generate target rehabilitation advice for the patient based on the target integrated data.

[0051] Compared with related technologies, this application integrates patient feedback data representing the patient's status and feelings on the basis of the patient's multi-dimensional related data, improves the fit between the target integrated data and the patient's condition changes, and optimizes the rehabilitation advice prediction device's understanding of the patient's condition changes, thereby improving the accuracy of the target rehabilitation advice and its pertinence to the patient, and effectively assisting doctors in formulating more accurate rehabilitation advice.

[0052] In one embodiment of the present application, patient feedback data includes questionnaire response data and real-time patient response data to initial rehabilitation recommendations; the questionnaire response data is obtained in response to a patient response to a questionnaire on condition changes; multi-source integration is performed based on the patient feedback data and the initial integrated data to obtain target integrated data, including: S232. Perform multi-source dynamic integration based on the questionnaire response data, real-time response data, and initial integrated data to obtain target integrated data.

[0053] Among them, the real-time response data can be the patient's feedback data on the initial rehabilitation recommendations based on their own situation, including but not limited to the patient's questions and understanding of the initial rehabilitation recommendations, their own actual situation, and adjustment and optimization suggestions. Among them, the patient's questions and understanding of the initial rehabilitation recommendations can be the patient's questions about the doubts in the initial rehabilitation recommendations. For example, for the medication recommendations in the initial rehabilitation recommendations, the patient has doubts about the specific details of the medication time or frequency. The actual situation can be the patient's feedback based on his or her own symptoms or life factors. For example, the patient has tried the treatment methods in the initial rehabilitation recommendations, or the patient is unable to perform the treatment methods in the initial rehabilitation recommendations due to specific reasons. Adjustment and optimization suggestions can be the optimization direction proposed by the patient for the initial rehabilitation recommendations based on the actual situation and his or her own experience. For example, if the patient has suffered from a similar disease in the past, the initial rehabilitation recommendations can be improved based on the treatment methods used in the historical rehabilitation process.

[0054] Specifically, in addition to passively receiving real-time response data generated by patients' feedback on initial rehabilitation recommendations, this application also involves proactively sending a condition change questionnaire to the patient and receiving their responses. By sending the condition change questionnaire to the patient, the patient can learn about data associations they haven't yet discovered, helping them provide more accurate and authentic feedback.

[0055] It is understandable that the content of the condition change questionnaire can be adjusted according to the actual scenario, such as using templated questionnaire content, or generating corresponding questions based on the patient's actual situation to form a condition change questionnaire.

[0056] Reference Figure 3 As shown, as an embodiment of the present application, the method further includes: S222. Receive real-time response data.

[0057] S224. Perform real-time aggregation of the initial integrated data and the real-time response data to obtain the patient's real-time aggregated data.

[0058] S226. Send the real-time summary data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates a condition change questionnaire based on the real-time summary data.

[0059] Among them, in the real-time aggregation process, the weight of real-time response data is higher than that of initial integrated data, that is, real-time summary data pays more attention to the difference between the actual needs of patients reflected by real-time response data and initial rehabilitation suggestions, so when using the condition change questionnaire to obtain questionnaire response data, further data about the actual situation of the patient can be obtained.

[0060] Specifically, in some cases, patients may lack in-depth understanding of their actual conditions. For example, patients may not be able to establish a connection between air status data and their own physiological status data, resulting in patients not understanding the impact of air status on their condition. Similar situations will lead to one-sided problems in patient feedback data, thereby affecting the comprehensiveness and accuracy of the target integrated data.

[0061] It's important to note that initial integrated data focuses on reflecting changes in a patient's condition based on their objective, relevant data, while real-time response data focuses on reflecting changes in their condition based on their actual conditions and specific experiences. Generating a condition change questionnaire based on initial integrated data and real-time response data can explore factors related to a patient's condition change from multiple perspectives, helping patients understand their condition changes and providing more comprehensive and accurate feedback. This improves the accuracy of targeted rehabilitation recommendations and effectively assists physicians in developing more precise rehabilitation recommendations.

[0062] Reference Figure 4 As shown, as an embodiment of the present application, the initial integrated data is obtained in the following manner: S201. Obtain the current air state data of the patient's environment, the patient's current physiological state data, and the patient's current doctor's diagnosis data.

[0063] S203. Perform simultaneous multi-dimensional integration of the current air state data, the current physiological state data, and the current doctor's diagnosis data to obtain initial integrated data.

[0064] Specifically, for patients who have just begun their rehabilitation process, data related to the patient across multiple preset dimensions is first obtained, including data on the current air quality of the patient's environment, the patient's current physiological state, and the doctor's current diagnosis. It is understood that this data is obtained at the same point in time and reflects the patient's relevant state at that point in time from multiple dimensions.

[0065] Furthermore, the aforementioned relevant data is subjected to simultaneous, multi-dimensional integration to generate initial integrated data. This simultaneous, multi-dimensional integration process includes time-aligning the relevant data, converting the relevant data into a common format, and adding identifiers to the relevant data of different dimensions. It is understood that the initial integrated data reflects the patient's comprehensive health status at that point in time, thereby enabling the generation of initial rehabilitation recommendations for the patient.

[0066] Reference Figure 5 As shown, as an embodiment of the present application, the initial integrated data is obtained in the following manner: S205. Obtain targeted rehabilitation advice and targeted integrated data associated with changes in the patient's condition.

[0067] S207. Obtain the current air state data of the patient's environment, the patient's current physiological state data, and the patient's current doctor's diagnosis data.

[0068] S209. Perform time-series collaborative multi-dimensional integration of targeted rehabilitation suggestions, targeted integrated data, current air status data, current physiological status data, and current doctor diagnosis data to obtain initial integrated data.

[0069] Specifically, for patients in the rehabilitation process who have received multiple rehabilitation recommendations, in addition to the patient's relevant data across multiple preset dimensions, selected data from the patient's historical rehabilitation recommendations and historical integrated data can be integrated to obtain targeted rehabilitation recommendations and integrated data. Targeted rehabilitation recommendations and integrated data are tailored to the patient's current condition, improving the comprehensiveness and accuracy of the initial integrated data and assisting in providing initial rehabilitation recommendations.

[0070] In some embodiments, the method for obtaining targeted rehabilitation suggestions and targeted integrated data may include: determining the air state historical data and physiological state historical data corresponding to any historical rehabilitation suggestion and its corresponding historical integrated data based on the air state time series data and physiological state time series data during the rehabilitation process, and determining the corresponding doctor's diagnosis historical data; calculating the similarity of the disease state between the above historical data and the current air state data, current physiological state data and current doctor's diagnosis data based on the air state historical data, physiological state historical data and doctor's diagnosis historical data; obtaining historical data whose disease state similarity exceeds the similarity threshold as historical data to be screened; performing trend calculation based on the patient's physiological state time series data during the rehabilitation process to obtain the patient's disease state change trend during the rehabilitation process; determining the disease state change trend at the time point corresponding to the historical data to be screened by comparing with the disease state change trend, wherein a positive disease state change trend indicates that the patient's condition has improved, and a negative disease state change trend indicates that the patient's condition has worsened; extracting the historical data to be screened with a positive disease state change trend to obtain targeted rehabilitation suggestions and targeted integrated data.

[0071] It is understandable that similar medical conditions may recur during a patient's recovery, and the same treatment methods may have the same impact on similar medical conditions. Therefore, by calculating the similarity between historical data and current air state data, current physiological state data, and current doctor's diagnosis data, the similarity of the medical conditions between the current time point and historical time points can be determined. From these, historical time points where historical rehabilitation recommendations successfully improved the patient's condition can be selected, thereby obtaining targeted rehabilitation recommendations and targeted integrated data. This can then provide a reference for generating rehabilitation recommendations at the current time point, improving the accuracy of initial rehabilitation recommendations.

[0072] Furthermore, the time series collaborative multi-dimensional integration may include: obtaining corresponding relevant historical data for the time point corresponding to the historical data to be screened, including air state data, physiological state data, and doctor's diagnosis data; determining the patient's historical condition at the corresponding time point based on the relevant historical data, and counting the number of times the historical condition appears during the patient's rehabilitation process to obtain the number of disease repetitions; setting a number threshold based on the number of disease repetitions, treating the historical condition with a number of disease repetitions higher than the number threshold as a high-frequency disease state, and treating the historical condition with a number of disease repetitions lower than the number threshold as a low-frequency disease state; comparing the high-frequency disease state, extracting high-frequency targeted data from the targeted rehabilitation suggestions and the targeted integrated data, and the disease state corresponding to the high-frequency targeted data is the high-frequency disease state; comparing the low-frequency disease state, extracting low-frequency targeted data from the targeted rehabilitation suggestions and the targeted integrated data, and the disease state corresponding to the low-frequency targeted data is the low-frequency disease state; arranging the data in the order of low-frequency targeted data, current relevant data, and high-frequency targeted data, and performing multi-dimensional integration on the arranged data to obtain initial integrated data; wherein the current relevant data includes current air state data, current physiological state data, and current doctor's diagnosis data.

[0073] It's important to note that the rehabilitation recommendation prediction device is equipped with a large model, which suffers from information attenuation for parameter inputs. Earlier parameter inputs experience greater information attenuation, while later parameter inputs retain more feature information. Furthermore, intermediate parameter inputs combine the features of both preceding and subsequent parameter inputs, providing collaborative guidance for more accurate input to the large model.

[0074] Therefore, in this embodiment, the current air state data, current physiological state data, and current doctor's diagnosis data representing the patient's current condition are used as core parameters and placed in the middle of the initial integrated data; although the condition corresponding to the low-frequency targeted data is close to the current condition, it occurs less frequently and can be considered a rare case, with a low reference value for the current condition; the condition corresponding to the high-frequency targeted data can be considered a common condition for patients. If there is historical data of multiple successful treatments during the rehabilitation process, it can be used as a reference for rehabilitation recommendations for the current condition. Through time-series collaborative multi-dimensional integration, the rehabilitation recommendation prediction device's ability to learn different targeted rehabilitation recommendations and targeted integrated data is improved, the accuracy and comprehensiveness of the resulting initial rehabilitation recommendations are improved, and doctors are effectively assisted in formulating more accurate rehabilitation recommendations.

[0075] Reference Figure 6 As shown, as an embodiment of the present application, the method further includes: S252. Obtain the current air state data of the patient's environment, the patient's current physiological state data, and the patient's current doctor's diagnosis data.

[0076] S254. Perform time-series collaborative multi-dimensional integration on the target integration data, target rehabilitation suggestions, current air state data, current physiological state data, and current doctor diagnosis data to obtain time-series collaborative integration data.

[0077] S256. Send the time series collaborative integration data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates new rehabilitation suggestions based on the time series collaborative integration data.

[0078] Specifically, this application can be repeatedly executed during the patient's rehabilitation process, and each time the application is executed, the current air state data of the patient's environment and the patient's current physiological state data are re-acquired, and the doctor diagnoses the patient to obtain the current doctor's diagnosis data. At this time, the target integration data and target rehabilitation suggestions obtained in the previous cycle can be used as historical data in the rehabilitation process, integrated with the above-mentioned current data to obtain time-series collaborative integration data, and the time-series collaborative integration data is sent to the rehabilitation suggestion prediction device as the basis for generating rehabilitation suggestions.

[0079] Furthermore, the rehabilitation advice prediction device receives the time-series collaborative integration data and generates new rehabilitation advice based on the time-series collaborative integration data, which can be used to update the target rehabilitation advice. It is understood that the steps of this embodiment can also be repeated during the patient's rehabilitation process until the patient's rehabilitation process is completed.

[0080] It should be noted that in the process of repeatedly executing the above steps, the target integrated data includes all air status data, physiological status data, doctor's diagnosis data, rehabilitation suggestions and patient feedback data before the current time point, and as the rehabilitation process progresses, the proportion of patient feedback data in the time-series collaborative integration data gradually increases, which significantly improves the matching degree between the time-series collaborative integration data and the patient, thereby improving the targetedness of the rehabilitation suggestions to the patient.

[0081] As an embodiment of the present application, the target rehabilitation suggestion includes a parameter adjustment suggestion for the patient's environment; the patient's environment is equipped with air conditioning equipment; the method further includes: S242. Send parameter adjustment suggestions to the control device of the air conditioning equipment; wherein the parameter adjustment suggestions are used to instruct the control device to adjust the operating parameters of the air conditioning equipment so as to provide a rehabilitation environment that matches the patient's condition through the air conditioning equipment after parameter adjustment.

[0082] Targeted rehabilitation recommendations also include recommended treatment behaviors for the patient to perform. These recommendations are sent by the data integration device to the patient for display, enabling direct treatment. These recommendations include, but are not limited to, lifestyle recommendations, medication use recommendations, dietary recommendations, rehabilitation training recommendations, and personal protection recommendations.

[0083] Specifically, the control device is configured on the third terminal and is in communication connection with the air conditioning equipment configured in the patient's environment, and is used to control the working state of the air conditioning equipment. After receiving the target rehabilitation suggestion, the data integration device sends the parameter adjustment suggestion to the control device. The control device instructs the corresponding air conditioning equipment according to the type of air conditioning equipment contained in the parameter adjustment suggestion and the corresponding parameter adjustment operation, and adjusts the patient's environment by adjusting the operating parameters of the air conditioning equipment. It is understandable that the air state data of the patient's environment will affect the changes in the patient's condition. By sending parameter adjustment suggestions to adjust the patient's environment, the patient can be provided with a rehabilitation environment that matches his or her condition, thereby improving the patient's rehabilitation process.

[0084] In this embodiment, a method for generating rehabilitation advice is provided, which can be used in the above-mentioned rehabilitation advice prediction device. Figure 7 As shown, the method includes: S710. Receive initial integrated data of the patient; wherein the initial integrated data is obtained by multi-dimensionally integrating relevant data of the patient in multiple preset dimensions.

[0085] S720. Generate an initial rehabilitation suggestion based on the initial integrated data; wherein the initial rehabilitation suggestion is used to indicate the patient's feedback operation on the initial rehabilitation suggestion to obtain patient feedback data.

[0086] S730. Generate target rehabilitation suggestions based on the target integrated data; wherein the target integrated data is obtained by multi-source integration based on the patient feedback data and the initial integrated data.

[0087] Specifically, after receiving the initial integrated data, the rehabilitation advice prediction device invokes the large model configured within the device to perform associative reasoning on the initial integrated data to generate initial rehabilitation advice. The associative reasoning process is illustrated as follows: The patient's condition progression is predicted based on the physiological state data in the initial integrated data to obtain predicted condition data; associated features are extracted between the air state data and the predicted condition data to obtain environmental association features between the air state data and the predicted condition data; associated features are extracted between the doctor's diagnosis data and the predicted condition data to obtain diagnostic association features between the two data; and based on the environmental association features and diagnostic association features, the large model, using pre-acquired medical expertise, performs inference and prediction to generate initial rehabilitation advice.

[0088] Furthermore, the steps of generating target rehabilitation recommendations based on target integrated data and initial rehabilitation recommendations based on initial integrated data are described. It should be noted that the target integrated data includes patient feedback data. In the process of generating target rehabilitation recommendations, the target rehabilitation recommendations are generated by performing inference and prediction based on the large model based on the environmental association features, diagnosis association features, and patient feedback data.

[0089] It should be noted that pre-acquired medical expertise includes, but is not limited to, historical case data for the same disease as the patient, along with corresponding air-related data and condition change data. The air-related data represents the correlation between air status data and changes in the patient's condition, while the condition change data represents changes in the patient's condition during recovery. This data is collected in advance and annotated and interpreted by experts in the corresponding disease field to generate a specialized knowledge training set. This specialized knowledge training set is used to train the large model deployed in the rehabilitation recommendation prediction device, enabling the large model to acquire relevant medical knowledge.

[0090] Compared to related technologies, the large model in this application can comprehensively consider relevant patient data across multiple preset dimensions, while also incorporating patient feedback data to generate targeted rehabilitation recommendations using pre-acquired medical expertise. By assisting doctors in generating rehabilitation recommendations through the large model, doctors avoid making labeling diagnoses based solely on their own knowledge or experience, and can more fully consider patients' physiological differences and personal experiences, significantly improving the specificity of the resulting rehabilitation recommendations for patients.

[0091] Reference Figure 8 As shown, as an embodiment of the present application, the method further includes: S722. Receive real-time summary data; wherein the real-time summary data is obtained by summarizing the initial integrated data and the patient's real-time response data to the initial rehabilitation suggestions in real time.

[0092] S724. Generate a questionnaire on changes in condition based on real-time summary data.

[0093] S726. Send the condition change questionnaire to the patient side, so that the patient side responds to the reply operation on the condition change questionnaire and obtains the questionnaire reply data.

[0094] Specifically, the rehabilitation advice prediction device receives the real-time aggregated data sent by the data integration device and uses the big model to generate a questionnaire on changes in the condition based on the real-time aggregated data. The process of generating a questionnaire on changes in the condition is illustrated as follows: using the big model to extract correlation features from the initial integrated data to obtain data correlation features, including environmental correlation features and diagnosis correlation features; constructing correlation questions based on the obtained data correlation features to obtain correlation feature questions. The correlation feature questions are used to ask patients questions based on the data correlation features to help them understand changes in their condition and the impact of air conditions and doctor's diagnosis on their condition changes; constructing difference questions based on the real-time echo data to obtain difference feature questions. The difference feature questions are used to ask patients questions based on the difference between the real-time echo data and the initial integrated data to further understand the patient's true feelings during the rehabilitation process; and generating a questionnaire on changes in the condition based on the correlation feature questions and difference feature questions.

[0095] It should be noted that by generating a condition change questionnaire based on the initial integrated data and real-time response data, the relevant factors of the patient's condition change can be explored from multiple angles to help patients understand their own condition changes and provide more comprehensive and accurate feedback data, thereby improving the accuracy of target rehabilitation recommendations.

[0096] It is understood that during the rehabilitation process, as the target integrated data is continuously updated, the content of the condition change questionnaire is also updated accordingly. In some embodiments, the content of the condition change questionnaire can also be updated by using a large model to predict the patient's problems or needs that may arise during the patient's future rehabilitation process based on the patient's target integrated data, and generating corresponding questionnaire questions based on the predicted results for use in updating the condition change questionnaire.

[0097] As an embodiment of the present application, the target integrated data is obtained by dynamically integrating multiple sources based on questionnaire response data, real-time response data, and initial integrated data.

[0098] Specifically, the target integrated data can be obtained by dynamically integrating multiple sources based on the initial integrated data and combined with patient feedback data, so as to predict the patient's condition from multiple perspectives and confirm the patient's comprehensive health status. Based on the patient's multi-dimensional related data, this application also integrates patient feedback data that represents the patient's status and feelings, thereby improving the degree of fit between the target integrated data and the patient's condition changes, optimizing the rehabilitation advice prediction device's understanding of the patient's condition changes, thereby improving the accuracy of the target rehabilitation advice and its pertinence to the patient, and effectively assisting doctors in formulating more accurate rehabilitation advice.

[0099] In some embodiments, the target integrated data also includes historical correlation features, which can be data correlation features before the current moment in the rehabilitation process. The historical correlation features are evaluated using a large model based on the current air state data, the current physiological state data, the current doctor's diagnosis data, and the patient's feedback data to determine whether the historical correlation features are consistent with the correlation between the current air state data, the current physiological state data, the current doctor's diagnosis data, and the patient's feedback data and the patient's condition changes. If there is a discrepancy between the two, the historical correlation features are updated based on the current air state data, the current physiological state data, the current doctor's diagnosis data, and the patient's feedback data to obtain the current correlation features.

[0100] Furthermore, using a backpropagation algorithm, the model parameters of the large model are adjusted based on the error between the current correlation features and the historical correlation features, making the rehabilitation recommendations generated by the large model more closely aligned with the patient's actual situation. Through iterative updates to the large model, the model's ability to reflect the patient's actual situation is gradually improved, thereby making the rehabilitation recommendations more targeted to the patient.

[0101] Reference Figure 9 As shown, the rehabilitation advice generation method provided in the present application includes a data integration device, a rehabilitation advice prediction device, a doctor side, a patient side and a control device. The data integration device is connected to a data acquisition device configured in the patient's environment to collect relevant data of the patient in multiple preset dimensions.

[0102] At the beginning of the rehabilitation process, the data integration device uses the data acquisition device to obtain relevant patient data across multiple pre-defined dimensions and integrates the data across these dimensions to generate initial integrated data. The data integration device then sends this initial integrated data to the rehabilitation advice prediction device, which generates initial rehabilitation recommendations based on the initial integrated data and sends them to the physician. The physician reviews the initial rehabilitation recommendations and, if they do not meet the requirements, adjusts them and sends the adjusted recommendations back to the data integration device. The data integration device then sends the received initial rehabilitation recommendations according to their specific type, including treatment action recommendations to the patient and parameter adjustment recommendations to the control device. The control device then adjusts the air conditioning system based on the parameter adjustment recommendations. After receiving the treatment action recommendations, the patient implements them and provides feedback based on the initial rehabilitation recommendations, generating real-time feedback data that is sent to the data integration device. The data integration device aggregates the real-time feedback data with the initial integrated data in real time to generate the patient's real-time aggregated data and sends it to the rehabilitation advice prediction device. The rehabilitation recommendation prediction device generates a condition change questionnaire based on real-time aggregated data and sends it to the patient. The patient responds to the questionnaire, generating response data that is then sent to the data integration device. The data integration device dynamically integrates the initial integrated data, real-time response data, and questionnaire response data to generate target integrated data. The rehabilitation recommendation prediction device receives the target integrated data and generates targeted rehabilitation recommendations based on it.

[0103] It is understandable that in the subsequent stages of the rehabilitation process, data can also be collected from the patient regularly to obtain the current air state data of the patient's environment, the patient's current physiological state data, and the current doctor's diagnosis data, and the target integrated data, target rehabilitation suggestions, current air state data, current physiological state data, and current doctor's diagnosis data are time-series collaborative multi-dimensionally integrated to obtain time-series collaborative integration data. After receiving the time-series collaborative integration data, the rehabilitation suggestion prediction device generates new rehabilitation suggestions based on the time-series collaborative integration data for further treatment of the patient. The above process of generating new rehabilitation suggestions can be repeated multiple times until the patient's rehabilitation process is completed.

[0104] Accordingly, please refer to Figure 10 The present invention provides a rehabilitation suggestion generating device, which is provided in a data integration device. The device includes: The initial data sending module 1010 is used to send the patient's initial integrated data to the rehabilitation advice prediction device, so that the rehabilitation advice prediction device generates initial rehabilitation advice based on the initial integrated data; wherein the initial integrated data is obtained by multi-dimensional integration of the patient's relevant data in multiple preset dimensions.

[0105] The feedback data acquisition module 1020 is used to acquire patient feedback data; wherein the patient feedback data is obtained in response to the feedback operation on the patient side regarding the initial rehabilitation suggestion.

[0106] The multi-source data integration module 1030 is used to perform multi-source integration based on the patient feedback data and the initial integrated data to obtain target integrated data.

[0107] The target data sending module 1040 is configured to send the target integrated data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates target rehabilitation suggestions based on the target integrated data.

[0108] In some optional embodiments, the patient feedback data includes questionnaire response data and real-time patient responses to initial rehabilitation recommendations; the questionnaire response data is obtained in response to a patient response to a condition change questionnaire; and the multi-source data integration module 1030 includes: The multi-source dynamic integration unit is used to perform multi-source dynamic integration based on questionnaire response data, real-time response data and initial integration data to obtain target integrated data.

[0109] In some optional implementations, the feedback data acquisition module 1020 includes: The real-time data receiving unit is used to receive real-time response data.

[0110] The real-time data aggregation unit is used to aggregate the initial integrated data and the real-time response data in real time to obtain the real-time aggregated data of the patient.

[0111] The real-time data sending unit is used to send the real-time summary data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates a condition change questionnaire based on the real-time summary data.

[0112] In some optional embodiments, the device further includes an initial data integration module, including: The current multi-dimensional parameter acquisition unit is used to obtain the current air state data of the patient's environment, the patient's current physiological state data and the patient's current doctor's diagnosis data.

[0113] The simultaneous multi-dimensional integration unit is used to perform simultaneous multi-dimensional integration on the current air state data, the current physiological state data and the current doctor's diagnosis data to obtain initial integrated data.

[0114] In some optional implementations, the initial data integration module further includes: The targeted data acquisition unit is used to obtain targeted rehabilitation suggestions and targeted integrated data associated with changes in the patient's condition.

[0115] The current multi-dimensional parameter acquisition unit is used to obtain the current air state data of the patient's environment, the patient's current physiological state data and the patient's current doctor's diagnosis data.

[0116] The time-series collaborative multi-dimensional integration unit is used to perform time-series collaborative multi-dimensional integration of targeted rehabilitation suggestions, targeted integrated data, current air state data, current physiological state data and current doctor's diagnosis data to obtain initial integrated data.

[0117] In some optional embodiments, the apparatus further includes a time-series collaborative iteration integration module, including: The current multi-dimensional parameter acquisition unit is used to obtain the current air state data of the patient's environment, the patient's current physiological state data and the patient's current doctor's diagnosis data.

[0118] The time series collaborative multi-dimensional integration unit is used to perform time series collaborative multi-dimensional integration on the target integration data, target rehabilitation suggestions, current air state data, current physiological state data and current doctor diagnosis data to obtain time series collaborative integration data.

[0119] The time series collaborative integration data sending unit is used to send the time series collaborative integration data to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates new rehabilitation suggestions based on the time series collaborative integration data.

[0120] In some optional embodiments, the target rehabilitation suggestion includes a parameter adjustment suggestion for the patient's environment; the patient's environment is equipped with air conditioning equipment; the target data sending module 1040 includes: An environmental parameter adjustment unit is used to send parameter adjustment suggestions to the control device of the air conditioning equipment; wherein the parameter adjustment suggestions are used to instruct the control device to adjust the operating parameters of the air conditioning equipment so as to provide a rehabilitation environment that matches the patient's condition through the air conditioning equipment after parameter adjustment.

[0121] Accordingly, please refer to Figure 11 The present invention provides a rehabilitation suggestion generating device, which is provided in a rehabilitation suggestion prediction device. The device includes: The initial data receiving module 1110 is used to receive the initial integrated data of the patient; wherein the initial integrated data is obtained by multi-dimensionally integrating the relevant data of the patient in multiple preset dimensions.

[0122] The initial advice generating module 1120 is configured to generate an initial rehabilitation advice based on the initial integrated data; wherein the initial rehabilitation advice is used to indicate the patient's feedback operation on the initial rehabilitation advice, so as to obtain patient feedback data.

[0123] The target suggestion generating module 1130 is used to generate target rehabilitation suggestions based on the target integrated data; wherein the target integrated data is obtained by multi-source integration of the patient feedback data and the initial integrated data.

[0124] In some optional implementations, the initial suggestion generating module 1120 includes: The real-time data receiving unit is used to receive real-time summary data; wherein the real-time summary data is obtained by real-time summary of the initial integrated data and the patient's real-time response data to the initial rehabilitation suggestions.

[0125] The condition questionnaire generating unit is used to generate a condition change questionnaire based on real-time summary data.

[0126] The condition questionnaire sending unit is used to send the condition change questionnaire to the patient end, so that the patient end responds to the reply operation for the condition change questionnaire and obtains the questionnaire reply data.

[0127] In some optional implementations, the target integrated data in the target suggestion generation module 1130 is obtained by dynamically integrating multiple sources based on questionnaire response data, real-time response data, and initial integrated data.

[0128] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0129] The rehabilitation advice generating device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0130] See also Figure 12 , Figure 121 is a structural diagram of a computer device provided by an embodiment of the present application. As shown in the figure, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 12 A processor 10 is taken as an example.

[0131] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0132] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0133] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0134] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0135] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0136] The embodiments of the present application also provide a computer-readable storage medium. The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0137] An embodiment of the present application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a method according to any embodiment of the present application.

[0138] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

[0139] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0140] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0141] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0142] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0143] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0144] It is understandable that in the specific implementation of this application, related data such as user information, location information, navigation data, etc. are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0145] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0146] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0147] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0148] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0151] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0152] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0153] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

[0154] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

Claims

1. A method for generating rehabilitation advice, characterized in that: The method comprises: Sending the patient's initial integrated data to a rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates an initial rehabilitation suggestion based on the initial integrated data; wherein the initial integrated data is obtained by multi-dimensionally integrating relevant data of the patient in multiple preset dimensions; Acquiring patient feedback data; wherein the patient feedback data is obtained in response to a feedback operation on the patient side regarding the initial rehabilitation suggestion; Performing multi-source integration based on the patient feedback data and the initial integrated data to obtain target integrated data; The target integrated data is sent to the rehabilitation suggestion prediction device, so that the rehabilitation suggestion prediction device generates a target rehabilitation suggestion based on the target integrated data.

2. The method according to claim 1, characterized in that The patient feedback data includes questionnaire response data and real-time response data of the patient to the initial rehabilitation suggestions; the questionnaire response data is obtained in response to the patient's response operation to the condition change questionnaire; The performing multi-source integration based on the patient feedback data and the initial integrated data to obtain target integrated data includes: Multi-source dynamic integration is performed based on the questionnaire response data, the real-time response data, and the initial integrated data to obtain the target integrated data.

3. The method according to claim 2, characterized in that The method further comprises: receiving the real-time response data; The initial integrated data and the real-time echo data are aggregated in real time to obtain the real-time aggregated data of the patient; and the real-time aggregated data is sent to the rehabilitation advice prediction device so that the rehabilitation advice prediction device generates the condition change questionnaire based on the real-time aggregated data.

4. The method according to claim 1, wherein The initial integration data is obtained by: Acquiring current air condition data of the patient's environment, current physiological condition data of the patient, and current doctor's diagnosis data of the patient; The current air state data, the current physiological state data and the current doctor's diagnosis data are simultaneously and sequentially integrated in multiple dimensions to obtain the initial integrated data.

5. The method according to claim 1, wherein The initial integration data is obtained by: Obtaining targeted rehabilitation advice and targeted integrated data associated with changes in the patient's condition; Acquiring current air condition data of the patient's environment, current physiological condition data of the patient, and current doctor's diagnosis data of the patient; The targeted rehabilitation suggestions, the targeted integrated data, the current air state data, the current physiological state data and the current doctor's diagnosis data are integrated in a time-series collaborative multi-dimensional manner to obtain the initial integrated data.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Acquiring current air condition data of the patient's environment, current physiological condition data of the patient, and current doctor's diagnosis data of the patient; Performing time-series collaborative multi-dimensional integration on the target integration data, the target rehabilitation suggestion, the current air state data, the current physiological state data, and the current doctor's diagnosis data to obtain time-series collaborative integration data; The time series collaborative integration data is sent to the rehabilitation advice prediction device, so that the rehabilitation advice prediction device generates new rehabilitation advice based on the time series collaborative integration data.

7. The method according to any one of claims 1 to 5, characterized in that The target rehabilitation suggestions include suggestions for adjusting parameters of the patient's environment; The patient's environment is equipped with air conditioning equipment; the method further includes: The parameter adjustment suggestion is sent to the control device of the air conditioning equipment; wherein the parameter adjustment suggestion is used to instruct the control device to adjust the operating parameters of the air conditioning equipment, so as to provide a rehabilitation environment matching the patient's condition through the air conditioning equipment after the parameter adjustment.

8. A method for generating rehabilitation advice, characterized in that: The method comprises: Receiving initial integrated data of a patient; wherein the initial integrated data is obtained by multi-dimensionally integrating relevant data of the patient in multiple preset dimensions; generating an initial rehabilitation suggestion based on the initial integrated data; wherein the initial rehabilitation suggestion is used to indicate a feedback operation performed by the patient in response to the initial rehabilitation suggestion, so as to obtain patient feedback data; Generate target rehabilitation suggestions based on target integrated data; wherein the target integrated data is obtained by multi-source integration of the patient feedback data and the initial integrated data.

9. The method according to claim 8, characterized in that The method further comprises: receiving real-time summary data; wherein the real-time summary data is obtained by summarizing the initial integrated data and the patient's real-time response data to the initial rehabilitation suggestion in real time; generating a condition change questionnaire based on the real-time aggregated data; The condition change questionnaire is sent to the patient end, so that the patient end responds to the reply operation for the condition change questionnaire and obtains the questionnaire reply data.

10. The method according to claim 9, characterized in that The target integrated data is obtained by dynamically integrating multiple sources based on the questionnaire response data, the real-time response data, and the initial integrated data.

11. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 10 by executing the computer instructions.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 10.

Images