Cross-platform medical information integration and intelligent interaction system and method

Abstract

The invention discloses a cross-platform medical information integration and intelligent interaction system and method, and relates to the field of medical information.The system comprises a basic action setting module, an action information analysis module and an action effect updating module.The method includes the steps that firstly, medical information integration is conducted through the basic action setting module; the method comprises the following steps: collecting and analyzing rehabilitation action use data of a patient on each platform, generating a basic rehabilitation action group set, then analyzing basic exercise data of the patient through an action information analysis module, obtaining basic correction actions and normal use actions of the patient, further generating an initial correction action set, and finally updating the action effect through an action effect updating module. The lumbar vertebra rehabilitation data of the patient is analyzed, the basic rehabilitation action group set of the low-quality rehabilitation patient is automatically replaced according to the analysis result, the intelligent interaction design can help the patient to complete rehabilitation training more efficiently, the rehabilitation time is shortened, and the rehabilitation quality is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical information, and in particular to a cross-platform medical information integration and intelligent interaction system and method. Background Art

[0002] With the rapid development of information technology, the informatization process of the medical industry is constantly advancing, and various medical information systems are widely used in hospitals, clinics and other medical institutions. Patients with lumbar disc herniation will generate complex and diverse medical information during the rehabilitation process. In order to improve the accuracy and timeliness of rehabilitation work, a cross-platform medical information integration and intelligent interaction system and method is needed.

[0003] Prior art, such as the invention patent application with announcement number CN114999631A, discloses an Internet-based smart medical system, including a user terminal, a multi-channel data management module and a training program recommendation module, characterized in that: the user terminal is used to manage users of different roles in the smart medical system, the multi-channel data management module is used to manage the registration data and appointment data memory function in registration and appointment triage, the training program recommendation module is used to obtain a training program after performing big data analysis and matching based on the patient's personal data through a deep learning algorithm and perform the next step of training evaluation, the user terminal is electrically connected to the multi-channel data management module, and the multi-channel data management module is electrically connected to the training program recommendation module, and by utilizing the personal physiological data of the patient user during the rehabilitation process, a more accurate and reliable training program is provided for the patient's rehabilitation treatment. This invention has the characteristics of reducing the workload of doctors during rehabilitation training and improving the effect of rehabilitation training.

[0004] The above scheme has at least the following shortcomings: 1. Although the above scheme uses a deep learning algorithm to generate a rehabilitation training plan, it does not use the patient's personalized data to generate a highly customized plan. Patients have different abilities to perform various movements according to their habits. The effect of rehabilitation training movements is not only related to the rehabilitation ability of the movement itself, but also to the degree of completion of the movement. Without detailed analysis and adjustment of the movements, patients cannot complete the whole set of movements, which will not only reduce the effect of rehabilitation training, but also reduce patients' satisfaction with the system due to their inability to complete the training plan.

[0005] 2. Although the invention mentions the use of deep learning algorithms and the introduction of collaborative filtering algorithms and LSTM recurrent neural networks, it does not provide specific model details, and is unable to regulate rehabilitation training movements according to specific physical data. It is also unable to adjust the patient's rehabilitation training plan in a timely manner when the patient's rehabilitation effect is low, which reduces the efficiency of rehabilitation training, prolongs the patient's rehabilitation time, and reduces the patient's satisfaction. Summary of the invention

[0006] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a cross-platform medical information integration and intelligent interaction system and method.

[0007] In order to solve the above-mentioned technical problems, the present invention adopts the following technical solutions: The present invention provides a cross-platform medical information integration and intelligent interaction system, comprising the following modules: a basic action setting module, which is used to collect the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient through each lumbar rehabilitation platform, and analyze the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient based on the platform usage model to obtain a set of basic rehabilitation action groups for each lumbar disc herniation patient.

[0008] The motion information analysis module is used to recommend a corresponding set of basic rehabilitation motion groups to each lumbar disc herniation patient, and then collect the basic exercise data of each lumbar disc herniation patient, analyze the basic exercise data of each lumbar disc herniation patient based on the patient exercise model, obtain the movements that need to be corrected for each lumbar disc herniation patient, and then obtain the usage data of each type of movement for each lumbar disc herniation patient. According to the usage data of each movement of each lumbar disc herniation patient, set the correction multiplier of each movement that needs to be corrected for each lumbar disc herniation patient, so as to generate an initial correction motion set for each lumbar disc herniation patient.

[0009] The action effect update module is used to collect the lumbar rehabilitation data of each lumbar disc herniation patient after each lumbar disc herniation patient uses the initial correction action set, analyze the lumbar rehabilitation data of each lumbar disc herniation patient based on the rehabilitation quality model, obtain each low-quality rehabilitation patient, and replace the basic rehabilitation action group set of each low-quality rehabilitation patient.

[0010] Preferably, the basic rehabilitation action group set for each low-quality rehabilitation patient is replaced, and the specific replacement process is as follows: the number of low-quality rehabilitation patients and lumbar disc herniation patients in each set of rehabilitation action groups is counted to obtain the normal recovery rate of each set of rehabilitation action groups, and at the same time, the usage level of each set of rehabilitation action groups for each lumbar disc herniation patient is obtained, and the usage index corresponding to each usage level is obtained from the database to obtain the usage index corresponding to the usage level of each set of rehabilitation action groups for each low-quality rehabilitation patient, and the usage level of each set of rehabilitation action groups for each lumbar disc herniation patient and each set are substituted into the treatment efficiency evaluation index calculation formula to obtain the treatment efficiency evaluation index of each set of rehabilitation action groups for each lumbar disc herniation patient.

[0011] The types of rehabilitation action groups for each lumbar disc herniation patient are obtained from the database. The types of rehabilitation action groups are divided into non-demand rehabilitation action groups and demand rehabilitation action groups, so as to obtain the treatment efficiency evaluation index of the demand rehabilitation action group and the treatment efficiency evaluation index of the non-demand rehabilitation action group for each lumbar disc herniation patient. The demand rehabilitation action group with the lowest treatment efficiency evaluation index in the basic rehabilitation action group set is replaced with a non-demand rehabilitation action group with the highest treatment efficiency evaluation index, so as to obtain the replaced basic rehabilitation action group set.

[0012] On the other hand, the present invention provides a cross-platform medical information integration and intelligent interaction method, comprising the following steps: Step 1, basic action setting: through each lumbar rehabilitation platform, the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient is collected, and based on the platform usage model, the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient is analyzed to obtain a set of basic rehabilitation action groups for each lumbar disc herniation patient.

[0013] Step 2. Action information analysis: recommend a corresponding set of basic rehabilitation action groups to each lumbar disc herniation patient, and then collect the basic exercise data of each lumbar disc herniation patient; based on the patient exercise model, analyze the basic exercise data of each lumbar disc herniation patient to obtain the actions that need to be corrected for each lumbar disc herniation patient; and then obtain the usage data of each action of each lumbar disc herniation patient; according to the usage data of each action of each lumbar disc herniation patient, set the correction multiples of each action that needs to be corrected for each type of lumbar disc herniation patient, so as to generate an initial correction action set for each lumbar disc herniation patient.

[0014] Step three, updating the action effect: after each lumbar disc herniation patient uses the initial correction action set, collect the lumbar rehabilitation data of each lumbar disc herniation patient, analyze the lumbar rehabilitation data of each lumbar disc herniation patient based on the rehabilitation quality model, obtain each low-quality rehabilitation patient, and replace the basic rehabilitation action group set of each low-quality rehabilitation patient.

[0015] The beneficial effects of the present invention are: 1. The present invention first integrates medical information through a basic action setting module, collects and analyzes the rehabilitation action usage data of patients on various platforms, and generates a basic rehabilitation action group set. Then, through the action information analysis module, the patient's basic exercise data is analyzed to obtain the patient's basic correction actions and normal usage actions, and then an initial correction action set is generated. Finally, through the action effect update module, the patient's lumbar rehabilitation data is analyzed, and the basic rehabilitation action group set of low-quality rehabilitation patients is automatically replaced according to the analysis results. The intelligent interactive design of the present invention can help patients complete rehabilitation training more efficiently, shorten rehabilitation time, and improve rehabilitation quality.

[0016] 2. The present invention generates an initial set of corrective movements for each lumbar disc herniation patient through multi-dimensional analysis of the patient's rehabilitation movement usage data, basic exercise data, etc., thereby improving the personalization of rehabilitation exercises and increasing patient satisfaction. At the same time, there is a complete set of movement management processes for rehabilitation movements, from basic movement setting, analysis of movements that need to be corrected to movement correction and effect updating, which increases the rehabilitation effect and efficiency, thereby reducing the time required for rehabilitation and reducing time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is a schematic diagram of the connection of the system modules of the present invention.

[0019] Figure 2 The present invention is a schematic flow chart of the steps for implementing the method. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] according to Figure 1 As shown, the present invention provides a cross-platform medical information integration and intelligent interaction system, including the following modules: a basic action setting module, an action information analysis module, an action effect update module and a database.

[0022] The basic action setting module is connected to the action information analysis module and the database respectively, and the action effect updating module is connected to the action information analysis module and the database respectively.

[0023] The basic movement setting module is used to collect the usage data of each set of rehabilitation movement groups of each lumbar disc herniation patient through each lumbar rehabilitation platform, and analyze the usage data of each set of rehabilitation movement groups of each lumbar disc herniation patient based on the platform usage model to obtain the basic rehabilitation movement group set of each lumbar disc herniation patient.

[0024] In a specific embodiment, the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient is collected, and the specific collection process is as follows: the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient includes the browsing rate, usage rate and maximum single usage time of each set of rehabilitation action groups corresponding to each lumbar disc herniation patient, and the browsing time of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform is collected from the browsing records of each platform, and the maximum single usage time of each set of rehabilitation action groups of each lumbar disc herniation patient is obtained therefrom, and at the same time, the browsing time of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform is counted to obtain the total browsing time and total number of browsing times of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform, and the total browsing time and total number of browsing times of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform are counted to obtain the total browsing time and total number of browsing times of each lumbar disc herniation patient on each platform;

[0025] Divide the total browsing time of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform by the total browsing time of the corresponding platform to obtain the browsing rate of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform; divide the total browsing times of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform by the total browsing times of the corresponding platform to obtain the utilization rate of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform; set the weight of each platform according to the number of lumbar disc herniation patients on each platform; perform weighted calculation on the browsing rate and utilization rate of each set of rehabilitation action groups of each lumbar disc herniation patient on each platform according to the weight of the corresponding platform to obtain the browsing rate and utilization rate of each set of rehabilitation action groups corresponding to each lumbar disc herniation patient.

[0026] In a specific embodiment, the usage data of each set of rehabilitation action groups for each lumbar disc herniation patient is analyzed, and the specific analysis process is as follows: the browsing rate, usage rate and maximum single usage time of each set of rehabilitation action groups corresponding to each lumbar disc herniation patient are input into the platform usage model to obtain the output results of each set of rehabilitation action groups for each lumbar disc herniation patient, and the output results have numerical values ​​of 0 and 1.

[0027] If the output result of a set of rehabilitation action groups for a patient with lumbar disc herniation is 0, it indicates that the set of rehabilitation action groups is a set of required rehabilitation action groups for the patient with lumbar disc herniation. If the output result of a set of rehabilitation action groups for a patient with lumbar disc herniation is 1, it indicates that the set of rehabilitation action groups is a set of non-required rehabilitation action groups for the patient with lumbar disc herniation. In this way, each set of non-required rehabilitation action groups and each set of required rehabilitation action groups for each patient with lumbar disc herniation are obtained. The actions in each set of required rehabilitation action groups are summarized to obtain a basic rehabilitation action group set, thereby obtaining a basic rehabilitation action group set for each patient with lumbar disc herniation.

[0028] In a specific embodiment, the platform usage model expression is:

[0029] Among them, A abis the output result of the bth set of rehabilitation action groups for the ath lumbar disc herniation patient, a is the number of the lumbar disc herniation patient, the value of a is a positive integer, b is the number of each set of rehabilitation action groups, the value of b is a positive integer, f′ ab , f″ ab and T′ ab are the browsing rate, usage rate and maximum duration of single use of the bth set of rehabilitation exercises for the ath lumbar disc herniation patient, respectively; f′, f″ and T′ are the preset standard browsing rate, standard usage rate and standard usage duration, respectively; ε 1 and ε 2 are the weight factors of the preset usage time and the number of usages, ε 1 >0,ε 2 >0,ε 1 +ε 2 =1, M is the preset standard platform usage index.

[0030] It should be noted that the standard parameter f′ is the threshold of the browsing rate of the rehabilitation action group. When the browsing rate of a lumbar disc herniation patient for a set of rehabilitation action groups is greater than f′, it indicates that the lumbar disc herniation patient has watched a certain set of rehabilitation action groups for a longer time, and is more likely to choose the rehabilitation action group. The specific data is set by the staff, and is generally set to the average browsing rate. The calculation process of the average browsing rate is: the browsing rate of each lumbar disc herniation patient for each set of rehabilitation action groups is averaged to obtain the average browsing rate, and the weight factor ε 1 and ε 2 The setting of is related to the viewing completion rate of the average rehabilitation action group. The higher the viewing completion rate of the average rehabilitation action group, the higher the ε 2 The larger the value, the lower the viewing completion rate of the average rehabilitation action group. 1 The larger the value, the specific value is set by the staff. The calculation process of the average rehabilitation action group's viewing completion rate is: divide the length of each viewing by the total length of the corresponding video to obtain the completion rate of each viewing, and calculate the average value of the completion rate of each viewing to obtain the average rehabilitation action group's viewing completion rate.

[0031] The setting process of the standard parameters f″ and T′ is the same as that of f′, for example, f″ is 0.6 and T′ is 1.3.

[0032] The motion information analysis module is used to recommend a corresponding set of basic rehabilitation motion groups to each lumbar disc herniation patient, and then collect the basic exercise data of each lumbar disc herniation patient, analyze the basic exercise data of each lumbar disc herniation patient based on the patient exercise model, obtain the movements that need to be corrected for each lumbar disc herniation patient, and then obtain the usage data of each type of movement for each lumbar disc herniation patient. According to the usage data of each movement of each lumbar disc herniation patient, set the correction multiplier of each movement that needs to be corrected for each lumbar disc herniation patient, so as to generate an initial correction motion set for each lumbar disc herniation patient.

[0033] In a specific embodiment, the basic exercise data of each lumbar disc herniation patient is collected, and the specific collection process is as follows: the basic exercise data of each lumbar disc herniation patient includes the average completion rate, average accuracy rate, maximum completion rate and maximum completion rate of each action of each lumbar disc herniation patient, key nodes of the patient's body are set, and videos of each action of each lumbar disc herniation patient are collected by a camera, and the positions and movement vectors of each key node collected each time for each action are identified by machine vision. If the position of a key node collected at a certain time for a certain action belongs to the corresponding standard position interval, it indicates that the key node of the action collected at that time is a correct node, and the number of correct nodes collected at that time for the action is obtained by statistics, and the number of correct nodes collected at that time for the action is divided by the total number of nodes to obtain the accuracy of the action collected at that time, thereby obtaining the accuracy of each action collected at each time for each lumbar disc herniation patient, and the average value is calculated to obtain the average accuracy of each action of each lumbar disc herniation patient, and at the same time, the maximum accuracy is obtained from the accuracy of each action collected at each time for each lumbar disc herniation patient, thereby obtaining the maximum accuracy of each action of each lumbar disc herniation patient.

[0034] If the moving vector of a key node collected at a certain time for a certain action belongs to the corresponding standard moving vector interval, it indicates that the key node collected at this time for the action is a mobile node. The number of mobile nodes collected at this time for the action is obtained. The number of mobile nodes collected at this time for the action is divided by the total number of nodes to obtain the completion rate of the collection of this action. The completion rate of each collection of each action of each lumbar disc herniation patient is obtained. The average value is calculated to obtain the average completion rate of each action of each lumbar disc herniation patient. The maximum completion rate is obtained from the completion rate of each collection of each action of each lumbar disc herniation patient to obtain the maximum completion rate of each action of each lumbar disc herniation patient.

[0035] In a specific embodiment, the basic exercise data of each lumbar disc herniation patient is analyzed, and the specific analysis process is as follows: the average completion rate, average accuracy rate, maximum completion rate and maximum completion rate of each action of each lumbar disc herniation patient are input into the patient exercise model to obtain the output results of each action of each lumbar disc herniation patient, and the output results have numerical values ​​of 0 and 1.

[0036] If the output result of a certain action of a patient with lumbar disc herniation is 0, it indicates that the action of the patient with lumbar disc herniation is an action that needs to be corrected, thereby obtaining the actions that need to be corrected for each patient with lumbar disc herniation. If the output result of a certain action of a patient with lumbar disc herniation is 1, it indicates that the action of the patient with lumbar disc herniation is a normal action, thereby obtaining the normal actions of each patient with lumbar disc herniation.

[0037] In a specific embodiment, the patient exercise model expression is:

[0038] Among them, B ac is the output result of the cth action of the ath lumbar disc herniation patient, c is the number of each action, and the value of c is a positive integer. E′ac , E″ ac , F′ ac and F″ ac are the average completion rate, average accuracy rate, maximum completion rate and maximum completion rate of the cth action of the ath lumbar disc herniation patient, E′ and F′ are the preset standard completion rate and standard accuracy, respectively. 1 and φ 2 are the preset completion rate weight factor and accuracy weight factor, φ 1 >0,φ 2 >0,φ 1 +φ 2 =1, N is the preset exercise evaluation quality index.

[0039] It should be noted that the setting process of the standard parameters E′ and F′ is the same as the setting process of the standard parameter f′. For example, E′ is 0.56 and F′ is 7.8, and the weight factor φ 1 and φ 2 The setting process and weight factor ε 1 The setting process is the same as for 1 is 0.45 and φ 2 is 0.55.

[0040] In a specific embodiment, the initial set of corrective actions for each patient is generated, and the specific generation process is as follows: the usage data of each action of each lumbar disc herniation patient includes the correction required rate, completion fluctuation rate and accuracy fluctuation rate of each type of action of each lumbar disc herniation patient, and statistics are performed according to the normal usage actions and the actions that need to be corrected of each lumbar disc herniation patient, and the correction required rate, accuracy rate and completion rate of each action of each lumbar disc herniation patient are obtained, and then the accuracy rate and completion rate of each action of each lumbar disc herniation patient are calculated to obtain the completion fluctuation rate and accuracy fluctuation rate of each type of action of each lumbar disc herniation patient.

[0041] It should be noted that the accuracy fluctuation rate is calculated as the difference between the maximum movement accuracy rate and the minimum accuracy rate of each type of movement for each lumbar disc herniation patient, divided by the sum of the maximum movement accuracy rate and the minimum accuracy rate. The completion fluctuation rate is calculated as the difference between the maximum movement completion rate and the minimum completion rate of each type of movement for each lumbar disc herniation patient, divided by the sum of the maximum movement completion rate and the minimum completion rate.

[0042] Substitute the correction rate, completion fluctuation rate and accuracy fluctuation rate of each type of action of each lumbar disc herniation patient into the correction index calculation formula

[0043] The correction index C of the d-type action of the a-th lumbar disc herniation patient is obtained. ad , d is the number of each action, the value of d is a positive integer, G′ ad , G″ad and G″′ ad are the correction rate, completion fluctuation rate and accuracy fluctuation rate of the dth action of the ath lumbar disc herniation patient, G′, G″ and G″′ are the preset standard correction rate, standard completion fluctuation rate and standard accuracy fluctuation rate, respectively. 1 ,δ 2 and δ 3 They are the preset weight factors of the required correction rate, the completed volatility and the accurate volatility, δ 1 >0,δ 2 >0,δ 3 >0.

[0044] It should be noted that the setting process of the standard parameters G′, G″ and G″′ is the same as the setting process of the standard parameter f′, for example, G′ is 0.3, G″ is 0.4 and G″′ is 0.35, and the weight factor δ 1 ,δ 2 and δ 3 The setting process of is the same as that of the weight factor ε1, for example, δ 1 =0.3,δ 2 is 0.3 and δ 3 is 0.3.

[0045] The correction plan corresponding to each correction index is obtained from the database to obtain the correction plan for each type of movement of each lumbar disc herniation patient. Then, according to the type of movement of each lumbar disc herniation patient, the correction plan for each movement of each lumbar disc herniation patient is obtained. Each movement to be corrected in the basic rehabilitation movement group set of each lumbar disc herniation patient is corrected according to the corresponding correction plan to obtain the initial correction movement set of each patient.

[0046] It should be noted that the correction plan includes but is not limited to the change in exercise duration, the change in rest duration between the previous movement, and the change in rest duration between the next movement. Correction according to the correction plan can effectively reduce the difficulty of exercise and reduce the phenomenon of low efficiency of the patient's entire exercise set due to difficulty in some movements.

[0047] The action effect update module is used to collect the lumbar rehabilitation data of each lumbar disc herniation patient after each lumbar disc herniation patient uses the initial correction action set, analyze the lumbar rehabilitation data of each lumbar disc herniation patient based on the rehabilitation quality model, obtain each low-quality rehabilitation patient, and replace the basic rehabilitation action group set of each low-quality rehabilitation patient.

[0048] In a specific embodiment, the lumbar rehabilitation data of each lumbar disc herniation patient is collected, and the specific collection process is as follows: the lumbar rehabilitation data of each lumbar disc herniation patient includes the muscle recovery index, pain recovery index and lumbar physiological recovery index of each lumbar disc herniation patient, the strength of each lower limb related muscle of each lumbar disc herniation patient is collected by a handgrip dynamometer, and the electrical signal strength of each lower limb related muscle of each lumbar disc herniation patient is collected by an electromyograph, and substituted into the muscle recovery index calculation formula

[0049] The muscle recovery index α of the patient with lumbar disc herniation No. a is obtained a , d is the number of the lower limb related muscles, the value of d is a positive integer, n is the maximum number of the lower limb related muscles, K′ ad and K″ ad are the strength and electrical signal intensity of the lower limb related muscles of each lumbar disc herniation patient, K′ and K″ are the preset standard strength and standard electrical signal intensity, respectively, 1 and λ 2 are the weight factors of force and electrical signal strength, respectively, 1 >0,λ 2 >0,λ 1 +λ 2 =1.

[0050] It should be noted that the setting process of the standard parameters K′ and K″ is the same as the setting process of the standard parameter f′. For example, K′ is 1.6 and K″ is 1.3, and the weight factor λ 1 and λ 2 The setting process and weight factor ε 1 The setting process is the same as for 1 is 0.4 and λ 2 is 0.6.

[0051] The physiological curvature and intervertebral height of the lumbar spine of each patient with lumbar disc herniation were collected through X-ray images and substituted into the calculation formula of the lumbar physiological recovery index. The lumbar physiological recovery index β of the patient with lumbar disc herniation No. a is obtained a , Q′ a and Q″ a are the physiological curvature of the lumbar spine and the intervertebral disc height of the patient with lumbar disc herniation No. a, Q′ and Q″ are the preset standard physiological curvature of the lumbar spine and the standard intervertebral disc height, and They are the preset weight factors of the lumbar physiological curvature and the intervertebral disc height.

[0052] It should be noted that the setting process of the standard parameters Q′ and Q″ is the same as the setting process of the standard parameter f′. For example, Q′ is 0.3 and Q″ is 0.4, and the weight factor and The setting process and weight factor ε 1 The setup process is the same as is 0.3 and is 0.7.

[0053] The pain level of each lumbar disc herniation patient was collected by visual analogue scoring method, and the pain frequency of each lumbar disc herniation patient was recorded. The pain level and pain frequency of each lumbar disc herniation patient were substituted into the pain recovery index calculation formula The pain recovery index γ of the patient with lumbar disc herniation No. a is obtained a , P′ a and P″ a are the physiological curvature and intervertebral disc height of the lumbar disc of the patient with lumbar disc herniation No. a, P′ and P″ are the preset standard physiological curvature and intervertebral disc height of the lumbar disc, θ 1 and θ 2 are the weight factors of the preset lumbar physiological curvature and intervertebral disc height, θ 1 >0,θ 2 >0,θ 1 +θ 2 =1.

[0054] It should be noted that the process of setting the standard parameters P′ and P″ is the same as the process of setting the standard parameter f′. For example, P′ is 0.15 and P″ is 0.24, and the weight factor θ 1 and θ 2 The setting process and weight factor ε 1 The setting process is the same as that of 1 is 0.45 and is 0.55.

[0055] In a specific embodiment, the lumbar rehabilitation data of each lumbar disc herniation patient is analyzed, and the specific analysis process is as follows: the muscle recovery index, pain recovery index and lumbar physiological recovery index of each lumbar disc herniation patient are input into the rehabilitation quality model to obtain the output results of each lumbar disc herniation patient, and the output results have numerical values ​​of 0 and 1.

[0056] If the output result of a patient with lumbar disc herniation is 0, it indicates that the patient is a low-quality rehabilitation patient and needs to replace the basic rehabilitation action group set. If the output result of a patient with lumbar disc herniation is 1, it indicates that the patient is a normal rehabilitation patient and does not need to replace the basic rehabilitation action group set.

[0057] In a specific embodiment, the rehabilitation quality model expression is:

[0058] Among them, D a is the output result for the patient with lumbar disc herniation No. a, H a ,Ia and J a are the muscle recovery index, pain recovery index and lumbar physiological recovery index of the patient with lumbar disc herniation No. a, respectively. H′, I′ and J′ are the expected muscle recovery index, expected pain recovery index and expected lumbar physiological recovery index of the patient with lumbar disc herniation No. a, respectively.

[0059] It should be noted that the setting process of the standard parameters H′, I′ and J′ is the same as the setting process of the standard parameter f′, for example, H′ is 0.13, I′ is 0.16 and J′ is 0.7.

[0060] In a specific embodiment, the basic rehabilitation action group set for each low-quality rehabilitation patient is replaced, and the specific replacement process is as follows: the number of low-quality rehabilitation patients and lumbar disc herniation patients in each set of rehabilitation action groups are counted to obtain the normal recovery rate of each set of rehabilitation action groups, and at the same time, the usage level of each set of rehabilitation action groups for each lumbar disc herniation patient is obtained, and the usage index corresponding to each usage level is obtained from the database to obtain the usage index corresponding to the usage level of each set of rehabilitation action groups for each low-quality rehabilitation patient, and the usage level of each set of rehabilitation action groups for each lumbar disc herniation patient and each set are substituted into the treatment efficiency evaluation index calculation formula to obtain the treatment efficiency evaluation index of each set of rehabilitation action groups for each lumbar disc herniation patient.

[0061] The types of rehabilitation action groups for each lumbar disc herniation patient are obtained from the database. The types of rehabilitation action groups are divided into non-demand rehabilitation action groups and demand rehabilitation action groups, so as to obtain the treatment efficiency evaluation index of the demand rehabilitation action group and the treatment efficiency evaluation index of the non-demand rehabilitation action group for each lumbar disc herniation patient. The demand rehabilitation action group with the lowest treatment efficiency evaluation index in the basic rehabilitation action group set is replaced with a non-demand rehabilitation action group with the highest treatment efficiency evaluation index, so as to obtain the replaced basic rehabilitation action group set.

[0062] The database is used to store the correction scheme corresponding to each correction index, the usage index corresponding to each usage level and the type of each set of rehabilitation action groups for each lumbar disc herniation patient.

[0063] according to Figure 2 As shown, the present invention provides a cross-platform medical information integration and intelligent interaction method, comprising the following steps: Step 1, basic action setting: through each lumbar rehabilitation platform, the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient is collected, and based on the platform usage model, the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient is analyzed to obtain a set of basic rehabilitation action groups for each lumbar disc herniation patient.

[0064] Step 2. Action information analysis: recommend a corresponding set of basic rehabilitation action groups to each lumbar disc herniation patient, and then collect the basic exercise data of each lumbar disc herniation patient; based on the patient exercise model, analyze the basic exercise data of each lumbar disc herniation patient to obtain the actions that need to be corrected for each lumbar disc herniation patient; and then obtain the usage data of each action of each lumbar disc herniation patient; according to the usage data of each action of each lumbar disc herniation patient, set the correction multiples of each action that needs to be corrected for each type of lumbar disc herniation patient, so as to generate an initial correction action set for each lumbar disc herniation patient.

[0065] Step three, updating the action effect: after each lumbar disc herniation patient uses the initial correction action set, collect the lumbar rehabilitation data of each lumbar disc herniation patient, analyze the lumbar rehabilitation data of each lumbar disc herniation patient based on the rehabilitation quality model, obtain each low-quality rehabilitation patient, and replace the basic rehabilitation action group set of each low-quality rehabilitation patient.

[0066] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they shall all fall within the protection scope of the present invention.

Claims

1. A cross-platform medical information integration and intelligent interaction system, characterized in that: Includes the following modules: The basic action setting module is used to collect the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient through each lumbar vertebra rehabilitation platform, analyze the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient based on the platform usage model, and obtain the basic rehabilitation action group set of each lumbar disc herniation patient; The motion information analysis module is used to recommend a corresponding basic rehabilitation motion group set to each lumbar disc herniation patient, and then collect the basic exercise data of each lumbar disc herniation patient, analyze the basic exercise data of each lumbar disc herniation patient based on the patient exercise model, obtain the motions that need to be corrected of each lumbar disc herniation patient, and then obtain the usage data of various motions of each lumbar disc herniation patient by statistics, and set the correction multiples of each motion that needs to be corrected of each lumbar disc herniation patient according to the usage data of each motion of each lumbar disc herniation patient, so as to generate the initial correction motion set of each lumbar disc herniation patient; The action effect update module is used to collect the lumbar rehabilitation data of each lumbar disc herniation patient after each lumbar disc herniation patient uses the initial correction action set, analyze the lumbar rehabilitation data of each lumbar disc herniation patient based on the rehabilitation quality model, obtain each low-quality rehabilitation patient, and replace the basic rehabilitation action group set of each low-quality rehabilitation patient.

2. A cross-platform medical information integration and intelligent interaction system and method according to claim 1, characterized in that: The usage data of each set of rehabilitation action groups of each lumbar disc herniation patient are analyzed, and the specific analysis process is as follows: The usage data of each set of rehabilitation action groups of each lumbar disc herniation patient include the browsing rate, usage rate and maximum single usage duration of each set of rehabilitation action groups corresponding to each lumbar disc herniation patient. The browsing rate, usage rate and maximum single usage duration of each set of rehabilitation action groups corresponding to each lumbar disc herniation patient are input into the platform usage model to obtain the output results of each set of rehabilitation action groups of each lumbar disc herniation patient, and the output result values ​​are 0 and 1; If the output result of a set of rehabilitation action groups for a patient with lumbar disc herniation is 0, it indicates that the set of rehabilitation action groups is a set of required rehabilitation action groups for the patient with lumbar disc herniation. If the output result of a set of rehabilitation action groups for a patient with lumbar disc herniation is 1, it indicates that the set of rehabilitation action groups is a set of non-required rehabilitation action groups for the patient with lumbar disc herniation. In this way, each set of non-required rehabilitation action groups and each set of required rehabilitation action groups for each patient with lumbar disc herniation are obtained. The actions in each set of required rehabilitation action groups are summarized to obtain a basic rehabilitation action group set, thereby obtaining a basic rehabilitation action group set for each patient with lumbar disc herniation.

3. A cross-platform medical information integration and intelligent interaction system and method according to claim 1, characterized in that: The platform usage model expression is: ， Among them, Aab is the output result of the bth set of rehabilitation action groups for the ath lumbar disc herniation patient, a is the number of the lumbar disc herniation patient, the value of a is a positive integer, b is the number of each set of rehabilitation action groups, the value of b is a positive integer, fa′b, fa″b and Ta′b are the browsing rate, usage rate and maximum single usage time of the bth set of rehabilitation action groups for the ath lumbar disc herniation patient, f′, f″ and T′ are the preset standard browsing rate, standard usage rate and standard usage time, ε1 and ε2 are the preset weight factors of usage time and number of uses, ε1>0, ε2>0, ε1+ε2=1, and M is the preset standard platform usage index.

4. A cross-platform medical information integration and intelligent interaction system and method according to claim 1, characterized in that: The basic exercise data of each lumbar disc herniation patient is analyzed, and the specific analysis process is as follows: The basic exercise data of each lumbar disc herniation patient includes the average completion rate, average accuracy rate, maximum completion rate and maximum completion rate of each action of each lumbar disc herniation patient. The average completion rate, average accuracy rate, maximum completion rate and maximum completion rate of each action of each lumbar disc herniation patient are input into the patient exercise model to obtain the output results of each action of each lumbar disc herniation patient, and the values ​​of the output results are 0 and 1; If the output result of a certain action of a patient with lumbar disc herniation is 0, it indicates that the action of the patient with lumbar disc herniation is an action that needs to be corrected, thereby obtaining the actions that need to be corrected for each patient with lumbar disc herniation. If the output result of a certain action of a patient with lumbar disc herniation is 1, it indicates that the action of the patient with lumbar disc herniation is a normal action, thereby obtaining the normal actions of each patient with lumbar disc herniation.

5. A cross-platform medical information integration and intelligent interaction system and method according to claim 4, characterized in that: The patient exercise model expression is: Among them, Bac is the output result of the cth action of the ath lumbar disc herniation patient, c is the number of each action, the value of c is a positive integer, E′ac, E′a′c, Fa′c and Fa″c are the average completion rate, average accuracy, maximum completion rate and maximum completion rate of the cth action of the ath lumbar disc herniation patient, respectively, E′ and F′ are the preset standard completion rate and standard accuracy rate, respectively, φ1 and φ2 are the preset weight factors of the completion rate and the accuracy rate, respectively, φ1>0, φ2>0, φ1+φ2=1, and N is the preset exercise evaluation quality index.

6. A cross-platform medical information integration and intelligent interaction system and method according to claim 4, characterized in that: The initial correction action set for each patient is generated, and the specific generation process is as follows: The usage data of each action of each lumbar disc herniation patient includes the correction-needed rate, completion fluctuation rate and accuracy fluctuation rate of each action of each lumbar disc herniation patient. According to each normally used action and each correction-needed action of each lumbar disc herniation patient, statistics are performed according to the type of each action to obtain the correction-needed rate, accuracy rate and completion rate of each action of each lumbar disc herniation patient. Then, the fluctuation rate of each action accuracy rate and completion rate of each action of each lumbar disc herniation patient is calculated to obtain the completion fluctuation rate and accuracy fluctuation rate of each action of each lumbar disc herniation patient. The correction rate, completion fluctuation rate and accuracy fluctuation rate of various movements of each lumbar disc herniation patient are substituted into the correction index calculation formula to obtain the correction index of various movements of each lumbar disc herniation patient, and the correction plan corresponding to each correction index is obtained from the database to obtain the correction plan for various movements of each lumbar disc herniation patient. Furthermore, according to the type of each movement of each lumbar disc herniation patient, a correction plan for each movement of each lumbar disc herniation patient is obtained, and each movement that needs to be corrected in the basic rehabilitation movement group set of each lumbar disc herniation patient is corrected according to the corresponding correction plan to obtain the initial correction movement set of each patient.

7. A cross-platform medical information integration and intelligent interaction system and method according to claim 1, characterized in that: The lumbar rehabilitation data of each lumbar disc herniation patient is analyzed, and the specific analysis process is as follows: The lumbar rehabilitation data of each lumbar herniation patient include the muscle recovery index, pain recovery index and lumbar physiological recovery index of each lumbar herniation patient. The muscle recovery index, pain recovery index and lumbar physiological recovery index of each lumbar herniation patient are input into the rehabilitation quality model to obtain the output results of each lumbar herniation patient, and the values ​​of the output results are 0 and 1; If the output result of a patient with lumbar disc herniation is 0, it indicates that the patient is a low-quality rehabilitation patient and needs to replace the basic rehabilitation action group set. If the output result of a patient with lumbar disc herniation is 1, it indicates that the patient is a normal rehabilitation patient and does not need to replace the basic rehabilitation action group set.

8. A cross-platform medical information integration and intelligent interaction system and method according to claim 7, characterized in that: The rehabilitation quality model expression is: Among them, Da is the output result of the patient with lumbar disc herniation No. a, Ha, Ia and Ja are the muscle recovery index, pain recovery index and lumbar physiological recovery index of the patient with lumbar disc herniation No. a, respectively, and H′, I′ and J′ are the expected muscle recovery index, expected pain recovery index and expected lumbar physiological recovery index of the patient with lumbar disc herniation No. a, respectively.

9. A cross-platform medical information integration and intelligent interaction system and method according to claim 7, characterized in that: The specific replacement process of the basic rehabilitation action set set for each low-quality rehabilitation patient is as follows: The number of low-quality rehabilitation patients and lumbar disc herniation patients who are normal rehabilitation patients in each rehabilitation action group is counted to obtain the normal rehabilitation rate of each rehabilitation action group, and at the same time, the usage level of each rehabilitation action group for each lumbar disc herniation patient is obtained, and the usage index corresponding to each usage level is obtained from the database, so as to obtain the usage index corresponding to the usage level of each rehabilitation action group for each low-quality rehabilitation patient, and the usage level and each set of each rehabilitation action group for each lumbar disc herniation patient are substituted into the treatment efficiency evaluation index calculation formula to obtain the treatment efficiency evaluation index of each rehabilitation action group for each lumbar disc herniation patient; The types of rehabilitation action groups for each lumbar disc herniation patient are obtained from the database. The types of rehabilitation action groups are divided into non-demand rehabilitation action groups and demand rehabilitation action groups, so as to obtain the treatment efficiency evaluation index of the demand rehabilitation action group and the treatment efficiency evaluation index of the non-demand rehabilitation action group for each lumbar disc herniation patient. The demand rehabilitation action group with the lowest treatment efficiency evaluation index in the basic rehabilitation action group set is replaced with a non-demand rehabilitation action group with the highest treatment efficiency evaluation index, so as to obtain the replaced basic rehabilitation action group set.

10. A medical information integration and intelligent interaction method using the cross-platform medical information integration and intelligent interaction system according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Basic action setting: Through each lumbar rehabilitation platform, collect the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient, analyze the usage data of each set of rehabilitation action groups of each lumbar disc herniation patient based on the platform usage model, and obtain the basic rehabilitation action group set of each lumbar disc herniation patient; Step 2, motion information analysis: recommend a corresponding basic rehabilitation motion group set to each lumbar disc herniation patient, and then collect the basic exercise data of each lumbar disc herniation patient, analyze the basic exercise data of each lumbar disc herniation patient based on the patient exercise model, obtain the motions that need to be corrected for each lumbar disc herniation patient, and then obtain the usage data of each motion of each lumbar disc herniation patient by statistics, and according to the usage data of each motion of each lumbar disc herniation patient, set the correction multiples of each motion that needs to be corrected for each type of lumbar disc herniation patient, so as to generate the initial correction motion set for each lumbar disc herniation patient; Step three, updating the action effect: after each lumbar disc herniation patient uses the initial correction action set, collect the lumbar rehabilitation data of each lumbar disc herniation patient, analyze the lumbar rehabilitation data of each lumbar disc herniation patient based on the rehabilitation quality model, obtain each low-quality rehabilitation patient, and replace the basic rehabilitation action group set of each low-quality rehabilitation patient.

Images