CN114758747B - Remote rehabilitation guidance system and method based on big data - Google Patents
Remote rehabilitation guidance system and method based on big data Download PDFInfo
- Publication number
- CN114758747B CN114758747B CN202210323813.9A CN202210323813A CN114758747B CN 114758747 B CN114758747 B CN 114758747B CN 202210323813 A CN202210323813 A CN 202210323813A CN 114758747 B CN114758747 B CN 114758747B
- Authority
- CN
- China
- Prior art keywords
- rehabilitation
- training
- guidance
- guiding
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 195
- 238000012544 monitoring process Methods 0.000 claims description 88
- 238000011156 evaluation Methods 0.000 claims description 76
- 238000004458 analytical method Methods 0.000 claims description 54
- 238000012545 processing Methods 0.000 claims description 35
- 230000006399 behavior Effects 0.000 claims description 34
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 238000011084 recovery Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 26
- 238000010191 image analysis Methods 0.000 abstract description 2
- 208000034657 Convalescence Diseases 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 208000027205 Congenital disease Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Physical Education & Sports Medicine (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a remote rehabilitation guidance system and a method based on big data; belongs to the technical field of remote rehabilitation guidance; the method comprises the steps that different directors and rehabilitation persons are respectively imaged in the early stage, so that the directors with different capacities can conduct image analysis on the rehabilitation persons with different states to obtain guide coefficients and rehabilitation coefficients, the guide effects of the directors can be evaluated and graded based on the guide coefficients, the different-level directors can conduct corresponding rehabilitation training on the rehabilitation persons with different severity degrees, the initial states of the rehabilitation persons during training can be evaluated and graded based on the rehabilitation coefficients, and the different-level rehabilitation persons can be matched with the directors with different guide capacities; the invention solves the technical problem that the integral guiding rehabilitation effect between the instructor and the rehabilitation person is poor because the guiding of the instructor and the training of the rehabilitation person cannot be dynamically adjusted according to the guiding condition of the instructor and the training condition of the rehabilitation person in the existing scheme.
Description
Technical Field
The invention relates to the technical field of remote rehabilitation guidance, in particular to a remote rehabilitation guidance system and a remote rehabilitation guidance method based on big data.
Background
The rehabilitation guidance is used for accelerating the recovery process after the injury of the human body, preventing and relieving the degree of the functional disorder of the human body, and enabling the sick and disabled to participate in the society again to the greatest extent.
When the existing remote rehabilitation guidance scheme is implemented, different instructors and rehabilitation persons are not portrayed in the early stage, and the guiding effects of the instructors are not evaluated and graded, so that the instructors with different grades cannot perform corresponding rehabilitation training on the rehabilitation persons with different severity degrees; and the technical problem that the overall guiding rehabilitation effect between the instructor and the rehabilitation person is poor is solved because the guiding of the instructor and the training of the rehabilitation person are not dynamically adjusted according to the guiding condition of the instructor and the training condition of the rehabilitation person.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a remote rehabilitation guidance system and a remote rehabilitation guidance method based on big data, which are used for solving the technical problem that the overall rehabilitation guidance effect between a mentor and a rehabilitation person is poor because the guidance of the mentor and the training of the rehabilitation person cannot be dynamically adjusted according to the guidance condition of the mentor and the training condition of the rehabilitation person in the prior art.
The aim of the invention can be achieved by the following technical scheme:
the remote rehabilitation guidance system based on big data comprises a personnel statistics module, a monitoring analysis module and an adjustment module;
The personnel statistics module is used for counting first information of a director implementing the remote rehabilitation guidance and second information of a rehabilitation person needing the remote rehabilitation guidance; the first information comprises the guiding type, the number of the guiding people, the guiding time and the good score of the guiding people; the second information includes an age, a rehabilitation type, and a training level of the rehabilitee;
the monitoring analysis module comprises a personnel analysis unit and a behavior analysis unit;
the personnel analysis unit is used for carrying out data processing and training on the collected first information of the instructor and the second information of the rehabilitee to obtain a guiding analysis set containing guiding coefficients and a rehabilitation analysis set containing rehabilitation coefficients;
The behavior analysis unit is used for monitoring and evaluating the guiding behaviors of the instructor and the rehabilitation training of the rehabilitee to obtain a guiding monitoring set containing guiding evaluation values and a rehabilitation monitoring set containing rehabilitation evaluation values;
The adjusting module is used for dynamically adjusting the guidance of the instructor and the training of the rehabilitee in a preset monitoring period according to the combination of the guidance analysis set and the rehabilitation analysis set and the guidance monitoring set and the rehabilitation monitoring set.
Further, the specific steps of processing and training the collected first information of the instructor include:
acquiring a guidance type, a guidance number, a guidance duration and a good score of a guidance person in the first information;
Matching the guide type with the guide type table to obtain corresponding guide weights and marking the values as A1; the guide type table consists of a plurality of guide types and corresponding guide weights, and different guide types are preset with different guide weights;
Respectively extracting the number of the guide persons, the guide duration and the number of the good scores and marking the number as A2, A3 and A4; wherein, the unit of the guiding time length is hours;
the marked guiding weight, the number of the guiding people, the guiding time length and the good score form guiding processing information;
Carrying out normalization processing on each item of data marked in the guiding processing information, and carrying out training on the value through a guiding function to obtain a guiding coefficient ZDX;
Marking the instructor corresponding to the instruction coefficient smaller than the instruction threshold as a first instructor; marking the instructor corresponding to the instruction coefficient not smaller than the instruction threshold as a second instructor; the guiding effect of the second guiding person is higher than that of the first guiding person;
The tutorial coefficients form a tutorial analysis set with the first tutor and the second tutor.
Further, the guiding function is ZDX =a1 [ (a1×a2+a2×a3+a3×a4)/(a1+a2+a3) ], and A1, A2 and A3 are different scaling coefficients and the range of values is (0, 1).
Further, the specific steps of data processing and training the collected second information of the rehabilitee include:
acquiring the age, rehabilitation type and training grade of the rehabilitation person in the second information;
Matching the rehabilitation type with the guide type table to obtain corresponding rehabilitation weight and marking the value as B1;
Extracting the value of age and marking as B2;
acquiring training weights associated with the training grades and marking the training weights as B3;
the marked rehabilitation weight, age and training weight form rehabilitation processing information;
Carrying out normalization processing on each item of data marked in the rehabilitation processing information, and carrying out training on the value through a rehabilitation function to obtain a rehabilitation coefficient KFX;
Marking a rehabilitating person corresponding to a rehabilitation coefficient smaller than a rehabilitation threshold as a first rehabilitating person; marking the rehabilitating person corresponding to the rehabilitation coefficient not smaller than the rehabilitation coefficient as a second rehabilitating person; the training difficulty of the second rehabilitation person is higher than that of the first rehabilitation person;
the rehabilitation coefficients and the first rehabilitee and the second rehabilitee form a rehabilitation analysis set.
Further, the rehabilitation function is KFX =b1+b2+b2+b3, B1, B2 and B3 are different scaling factors and the values are (0, 10).
Further, the specific steps of monitoring and evaluating the guiding behavior of the instructor include:
recording the whole voice guidance process of the instructor to obtain instruction recording data;
Text conversion is carried out on the guiding record data to obtain guiding text data;
matching the guiding text data with a pre-constructed project guiding table and a behavior evaluation table to obtain project matching data and behavior evaluation data; the item matching data and the behavior evaluation data form a guiding matching set of a guiding person;
Extracting the total number of item matching in the item matching data and the total number of behavior evaluation in the behavior evaluation data, and respectively marking the values as XP and YP;
Carrying out normalization processing on each item of marked data and training through a guidance evaluation function to obtain a guidance evaluation value ZP; the guide evaluation function is zp=a1×c1× (XP/XP 0) +c2× (YP/YP 0) ]; c1 and c2 are different proportional coefficients and the value ranges are all (0, 5); XP0 is the total number of item phrases in the item guidance table; YP0 is the total number of estimated phrases in the behavior estimation table;
Setting the guidance corresponding to the guidance evaluation value which is not more than the guidance evaluation threshold value as the unqualified guidance, and adding one to the number of unqualified guidance;
Setting the guidance corresponding to the guidance evaluation value smaller than the guidance evaluation threshold as standard-reaching guidance, and adding one to the number of times of standard-reaching guidance;
counting the total number of unqualified guide times and the total number of qualified guide times in the monitoring period to obtain guide statistical data; the guidance evaluation value and the guidance statistics form a guidance monitoring set.
Further, the specific steps of monitoring and evaluating the rehabilitation training of the rehabilitation person include:
Recording the whole action training process of the rehabilitation person to obtain training video data;
acquiring frame images in training video data and arranging and combining the frame images according to time sequence to obtain video split data;
extracting action characteristics of frame images in video split data based on an image recognition algorithm;
Matching the action features with a pre-constructed sample action table, obtaining the maximum overlapping area of the action features and the sample action features in a sample action set, and marking the maximum overlapping area as CMi, i=1, 2,3, & n; n is the total number of training actions; n is a positive integer;
acquiring the training time length and marking the value as XSi; the training time is in minutes;
carrying out normalization processing on each marked data and training through a rehabilitation evaluation function to obtain Kang Fuping estimated value PG; the rehabilitation evaluation function is that
D1 and d2 are different proportional coefficients and the value ranges are all (0, 10); CMi0 is the standard overlapping area corresponding to different training items, XSi0 is the standard training duration corresponding to different training items, and the unit is minutes;
setting the rehabilitation training corresponding to the rehabilitation evaluation value which is not more than the rehabilitation evaluation threshold value as the substandard training, and adding one to the times of the substandard training;
setting the rehabilitation training corresponding to the rehabilitation evaluation value larger than the rehabilitation evaluation threshold value as standard-reaching training, and adding one to the number of times of the standard-reaching training;
Counting the total number of times of substandard training and the total number of times of substandard training in a monitoring period to obtain rehabilitation statistical data; the recovery reexamine estimated values and the recovery statistical data form a recovery monitoring set.
Further, the specific steps of dynamically adjusting the guidance of the instructor include:
The overall evaluation is carried out on the guidance of the instructor according to the guidance analysis set and the guidance monitoring set in the monitoring period; acquiring and analyzing the ratio of the total number of unqualified instructions in the instruction monitoring set to the total number of qualified instructions, and if the ratio is larger than k, judging that the instruction effect of the instructor is excellent and generating a first maintenance instruction; k is a real number greater than zero;
if the ratio is not greater than k, judging that the guiding effect of the instructor is poor and generating a first adjustment instruction;
when the first instructor and the second instructor of the instructor corresponding to the instruction monitoring set correspond to the first maintenance instruction, the instruction identity of the instructor is kept unchanged;
When the instructor corresponds to the first instructor and the second instructor corresponds to the first adjustment instruction of the instruction monitoring set, stopping the instruction of the first instructor and training, and adjusting the second instructor to be the first instructor.
Further, the specific steps of dynamically adjusting the training of the rehabilitation person include:
The overall evaluation is carried out on the training of the rehabilitation person according to the rehabilitation analysis set and the rehabilitation monitoring set in the monitoring period; acquiring and analyzing the ratio of the total number of times of the substandard training in the rehabilitation monitoring set to the total number of times of the substandard training, and if the ratio is larger than p, judging that the training effect of the rehabilitation person is excellent and generating a second maintenance instruction; p is a real number greater than zero;
if the ratio is not greater than p, judging that the training effect of the rehabilitation person is poor and generating a second adjustment instruction;
When the first rehabilitator and the second rehabilitator corresponding to the rehabilitation monitoring set both correspond to the second maintenance instruction, the training intensity of the rehabilitator is kept unchanged;
When the first convalescence person and the second convalescence person corresponding to the convalescence monitoring set both correspond to the second adjusting instruction, stopping the remote convalescence training of the first convalescence person based on the big data technology and performing text guidance, and adjusting the second convalescence person to the first convalescence person to perform low-difficulty training.
The remote rehabilitation guidance method based on big data comprises the following steps:
Step one: counting first information of a mentor who implements the remote rehabilitation guidance and second information of a rehabilitation person who needs the remote rehabilitation guidance; the first information comprises the guiding type, the number of the guiding people, the guiding time and the good score of the guiding people; the second information includes an age, a rehabilitation type, and a training level of the rehabilitee;
Step two: performing data processing and training on the collected first information of the instructor and the second information of the rehabilitee to obtain a guiding analysis set containing guiding coefficients and a rehabilitation analysis set containing rehabilitation coefficients;
Step three: monitoring and evaluating the guiding behaviors of the instructor and the rehabilitation training of the rehabilitee to obtain a guiding monitoring set containing guiding evaluation values and a rehabilitation monitoring set containing rehabilitation evaluation values;
step four: and dynamically adjusting the guidance of the instructor and the training of the rehabilitee in a preset monitoring period by combining the guidance monitoring set and the rehabilitation monitoring set according to the guidance analysis set and the rehabilitation analysis set.
Compared with the prior art, the invention has the beneficial effects that:
According to the invention, different directors and rehabilitation persons are respectively imaged in the early stage, so that the directors with different capacities can carry out image analysis on the rehabilitation persons with different states to obtain the guidance coefficients and the rehabilitation coefficients, the guidance effects of the directors can be evaluated and graded based on the guidance coefficients, the different-level directors can carry out corresponding rehabilitation training on the rehabilitation persons with different severity degrees, the initial states of the rehabilitation persons during training can be evaluated and graded based on the rehabilitation coefficients, and the rehabilitation persons with different levels can be matched with the directors with different guidance capacities; meanwhile, through data acquisition and analysis of the guiding process of the instructor and the training process of the rehabilitation person, whether the guiding state of the instructor is qualified or not can be judged, and the function of monitoring and evaluating the guiding of the instructor is achieved; the training states of the rehabilitation persons are evaluated so as to dynamically adjust the training intensity, and the training states can be matched with corresponding directors to conduct guidance, so that different directors conduct differentiated guidance training on different rehabilitation persons, and the overall effect of remote rehabilitation guidance based on big data is effectively improved.
Drawings
Fig. 1 is a schematic block diagram of the big data based remote rehabilitation guidance system of the present invention.
Fig. 2 is a flow chart of the remote rehabilitation guidance method based on big data.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used herein is for the purpose of describing embodiments and is not intended to limit and/or restrict the disclosure; it should be noted that the singular forms "a", "an" and "the" include plural forms as well, unless the context clearly indicates otherwise; moreover, although the terms "first," "second," etc. may be used herein to describe various elements, the elements are not limited by these terms, and these terms are merely used to distinguish one element from another element.
Referring to fig. 1, a schematic block diagram of a remote rehabilitation guidance system based on big data according to an embodiment of the present invention is shown. In the embodiment of the invention, big data is also called huge amount of data, which means that the data is huge in size and cannot be retrieved, managed, processed and tidied in a reasonable time through a main stream software tool, so that the information is more positive for helping users.
According to the embodiment of the invention, the guidance of the instructor and the training of the rehabilitation person are monitored and analyzed based on the big data, and the guiding progress of the instructor and the training progress of the rehabilitation person are adjusted by personnel, so that the instructors with different guiding effects are dynamically matched with the rehabilitation person with different rehabilitation degrees, and the overall effects of remote rehabilitation and guidance are improved.
The remote rehabilitation guidance system based on big data comprises a personnel statistics module, a monitoring analysis module and an adjustment module;
the personnel statistics module is used for counting first information of a director implementing the remote rehabilitation guidance and second information of a rehabilitation person needing the remote rehabilitation guidance;
The first information comprises the guiding type, the number of the guiding people, the guiding time and the good score of the guiding people; the second information includes an age, a rehabilitation type, and a training level of the rehabilitee;
the monitoring analysis module comprises a personnel analysis unit and a behavior analysis unit;
the personnel analysis unit is used for carrying out data processing and training on the collected first information of the instructor and the second information of the rehabilitee to obtain a guiding analysis set containing guiding coefficients and a rehabilitation analysis set containing rehabilitation coefficients;
The specific steps of processing and training the collected first information of the instructor include:
acquiring a guidance type, a guidance number, a guidance duration and a good score of a guidance person in the first information;
matching the guide type with the guide type table to obtain corresponding guide weights and marking the values as A1; it should be noted that the instruction type table is composed of a plurality of instruction types and corresponding instruction weights, and different instruction types are preset with different instruction weights;
It should be noted that the purpose of presetting different instruction weights is to digitally process the areas and instruction types of different instructors, so as to combine the data of different aspects to carry out overall evaluation on the instructors; the instruction type can be acquired based on the existing instruction big data; the guidance types include, but are not limited to, postoperative action guidance and congenital disease action guidance, and the guidance difficulty of different guidance types is different, so that digital processing is needed;
Respectively extracting the number of the guide persons, the guide duration and the number of the good scores and marking the number as A2, A3 and A4; wherein, the unit of the guiding time length is hours;
the marked guiding weight, the number of the guiding people, the guiding time length and the good score form guiding processing information;
Carrying out normalization processing on each item of data marked in the guiding processing information, and carrying out training on the value through a guiding function to obtain a guiding coefficient ZDX;
the guiding function is ZDX =a1 [ (a1 a2+a2 a3+a3 a4)/(a1+a2+a3) ];
a1, a2 and a3 are different proportionality coefficients, a1 can take on a value of 0.352, a2 can take on a value of 0.684, and a3 can take on a value of 0.973;
matching and analyzing the guide coefficient with a preset guide threshold value; the coaching threshold may be set based on big data that all coaches have directed;
marking the instructor corresponding to the instruction coefficient smaller than the instruction threshold as a first instructor;
marking the instructor corresponding to the instruction coefficient not smaller than the instruction threshold as a second instructor; wherein the guiding effect of the second guiding person is higher than the guiding effect of the first guiding person;
The tutorial coefficients form a tutorial analysis set with the first tutor and the second tutor.
It should be noted that the guidance coefficient is a numerical value for integrally evaluating the guidance ability of the guidance person by combining the data guided by the guidance person; the guiding effect of the instructor is evaluated and graded based on the guiding coefficient, so that the instructors with different grades can perform corresponding rehabilitation training on rehabilitation persons with different severity degrees; different from indiscriminate guidance and training in the existing scheme, the embodiment of the invention can realize a more efficient rehabilitation training effect;
the specific steps of data processing and training the collected second information of the rehabilitee include:
acquiring the age, rehabilitation type and training grade of the rehabilitation person in the second information;
Matching the rehabilitation type with the guide type table to obtain corresponding rehabilitation weight and marking the value as B1; it should be noted that, the instruction type table is composed of a plurality of instruction types and corresponding rehabilitation weights, and different instruction types preset a corresponding rehabilitation weight so as to perform training calculation on different instruction types;
Extracting the value of age and marking as B2;
acquiring training weights associated with the training grades and marking the training weights as B3;
the training grades can comprise three grades, namely a first training grade, a second training grade and a third training grade, corresponding training weight values are sequentially increased, and the training requirements of the training grades are increased; training weights corresponding to the training grades can be preset;
the marked rehabilitation weight, age and training weight form rehabilitation processing information;
It should be noted that, the training receiving capacities of different ages and the recovery speeds of rehabilitation are different, and different rehabilitation types need to be matched with corresponding training types, the training grades are used for training to different degrees, and the rehabilitation states of the rehabilitation person can be represented;
Carrying out normalization processing on each item of data marked in the rehabilitation processing information, and carrying out training on the value through a rehabilitation function to obtain a rehabilitation coefficient KFX;
the rehabilitation function is KFX =b1×b1+b2×b2+b3×b3;
b1, b2 and b3 are different proportionality coefficients, a1 can take on a value of 3.625, a2 can take on a value of 2.351, and a3 can take on a value of 1.967;
matching and analyzing the rehabilitation coefficient with a preset rehabilitation threshold value;
Marking a rehabilitating person corresponding to a rehabilitation coefficient smaller than a rehabilitation threshold as a first rehabilitating person; marking the rehabilitating person corresponding to the rehabilitation coefficient not smaller than the rehabilitation coefficient as a second rehabilitating person; the training difficulty of the second rehabilitation person is higher than that of the first rehabilitation person;
the rehabilitation coefficients and the first rehabilitee and the second rehabilitee form a rehabilitation analysis set.
It should be noted that the rehabilitation coefficient is a numerical value for integrally evaluating the initial state of the rehabilitation person during rehabilitation training by combining training data of the rehabilitation person; based on the rehabilitation coefficient, the initial state of the rehabilitation person during training can be evaluated and graded, so that the rehabilitation persons with different grades can be matched with the directors with different guiding capacities, the targeted training can be performed on different rehabilitation persons, and the training effect of the directors with different capacities can be improved.
The behavior analysis unit is used for monitoring and evaluating the guiding behaviors of the instructor and the rehabilitation training of the rehabilitee to obtain a guiding monitoring set containing guiding evaluation values and a rehabilitation monitoring set containing rehabilitation evaluation values;
the specific steps of monitoring and evaluating the guiding behavior of the instructor include:
recording the whole voice guidance process of the instructor to obtain instruction recording data;
text conversion is carried out on the guiding record data to obtain guiding text data; the technology of converting the text by voice is the conventional technology means, and specific steps are not repeated here;
matching the guiding text data with a pre-constructed project guiding table and a behavior evaluation table to obtain project matching data and behavior evaluation data; the item matching data and the behavior evaluation data form a guiding matching set of a guiding person;
It is worth noting that the project guidance table is composed of a plurality of training contents corresponding to different training types, the different training types correspond to a complete training process, and the project guidance table plays a role in monitoring and evaluating guidance steps of a mentor; the project guidance table and the behavior evaluation table can be obtained based on the existing guidance big data; the behavior evaluation table is composed of a plurality of word groups of personal care, including but not limited to 'true stick', 'you are the most stick', 'fueling', 'continuing to strive' and the like, and plays a role in monitoring and evaluating the personal care aspect of a director;
Extracting the total number of item matching in the item matching data and the total number of behavior evaluation in the behavior evaluation data, and respectively marking the values as XP and YP;
Carrying out normalization processing on each item of marked data and training through a guidance evaluation function to obtain a guidance evaluation value ZP; the guide evaluation function is zp=a1×c1× (XP/XP 0) +c2× (YP/YP 0) ];
c1 and c2 are different proportionality coefficients, c1 can take on a value of 0.467, and c2 can take on a value of 0.533; XP0 is the total number of item phrases in the item guidance table; YP0 is the total number of estimated phrases in the behavior estimation table;
Setting the guidance corresponding to the guidance evaluation value which is not more than the guidance evaluation threshold value as the unqualified guidance, and adding one to the number of unqualified guidance;
Setting the guidance corresponding to the guidance evaluation value smaller than the guidance evaluation threshold as standard-reaching guidance, and adding one to the number of times of standard-reaching guidance;
counting the total number of unqualified guide times and the total number of qualified guide times in the monitoring period to obtain guide statistical data; the guidance evaluation value and the guidance statistics form a guidance monitoring set.
It should be noted that, in the embodiment of the present invention, the instruction evaluation value is a value for evaluating the instruction state of the instructor by combining various data of the instructor during training; based on the instruction evaluation value, whether the instruction state of the instructor is qualified or not can be judged, and the function of monitoring and evaluating the instruction of the instructor is achieved.
The specific steps of monitoring and evaluating the rehabilitation training of the rehabilitation person include:
Recording the whole action training process of the rehabilitation person to obtain training video data;
acquiring frame images in training video data and arranging and combining the frame images according to time sequence to obtain video split data;
extracting action characteristics of frame images in video split data based on an image recognition algorithm;
Matching the action features with a pre-constructed sample action table, obtaining the maximum overlapping area of the action features and the sample action features in a sample action set, and marking the maximum overlapping area as CMi, i=1, 2,3, & n; n is the total number of training actions; n is a positive integer;
acquiring the training time length and marking the value as XSi; the training time is in minutes;
It should be noted that, the rehabilitation guidance in the embodiment of the present invention refers to guidance in terms of motion, which is used for recovering the motion capability of the patient, the image recognition algorithm may be a HOG feature algorithm, the pre-constructed sample motion table is composed of a plurality of standard character contours corresponding to training items, when the motion of the rehabilitation person is matched with the standard character contours of the corresponding items, the training motion standard of the rehabilitation person is determined, the matched basis is that the overlapping area of the motion feature of the rehabilitation person and the standard character contours is acquired, and the maximum overlapping area in the motion matching of the rehabilitation person is subjected to matching analysis.
Carrying out normalization processing on each marked data and training through a rehabilitation evaluation function to obtain Kang Fuping estimated value PG; the rehabilitation evaluation function is that
D1 and d2 are different proportionality coefficients, d1 can take on a value of 1.268, and d2 can take on a value of 0.634; CMi0 is the standard overlapping area corresponding to different training items, XSi0 is the standard training duration corresponding to different training items, and the unit is minutes.
It should be noted that the rehabilitation evaluation value is a value for integrally evaluating the training state of a rehabilitation person by correlating the action characteristic data of the rehabilitation person during training with the training time period; based on the estimated value of the rehabilitation reexamine, the training state of the rehabilitation person can be evaluated so as to dynamically adjust the training intensity, and meanwhile, the training state can be matched with a corresponding director to conduct guidance, so that different directors conduct differentiated guidance training on different rehabilitation persons, and the training device is different from indifferent guidance and non-dynamic adjustment in the existing scheme, and can achieve more efficient guidance effect and training effect;
The formulas in the embodiment of the invention are all formulas with dimensions removed and numerical calculation thereof, a formula closest to the actual situation is obtained by collecting a large amount of data and performing software simulation, and the proportionality coefficient and the preset threshold value in the formulas are set by a person skilled in the art according to the actual situation or are obtained by large amount of data simulation;
Acquiring Kang Fuping a rehabilitation evaluation threshold corresponding to the evaluation value;
setting the rehabilitation training corresponding to the rehabilitation evaluation value which is not more than the rehabilitation evaluation threshold value as the substandard training, and adding one to the times of the substandard training;
setting the rehabilitation training corresponding to the rehabilitation evaluation value larger than the rehabilitation evaluation threshold value as standard-reaching training, and adding one to the number of times of the standard-reaching training;
Counting the total number of times of substandard training and the total number of times of substandard training in a monitoring period to obtain rehabilitation statistical data; the recovery reexamine estimated values and the recovery statistical data form a recovery monitoring set.
The adjusting module is used for dynamically adjusting the guidance of a mentor and the training of a rehabilitation person in a preset monitoring period according to the combination of the guidance analysis set and the rehabilitation analysis set and the guidance monitoring set and the rehabilitation monitoring set;
The method comprises the following specific steps of dynamically adjusting the guidance of a mentor:
The overall evaluation is carried out on the guidance of the instructor according to the guidance analysis set and the guidance monitoring set in the monitoring period; acquiring and analyzing the ratio of the total number of unqualified instructions in the instruction monitoring set to the total number of qualified instructions, and if the ratio is larger than k, judging that the instruction effect of the instructor is excellent and generating a first maintenance instruction; k is a real number greater than zero; the monitoring period can be two weeks, namely, the guiding state of the instructor is analyzed and evaluated every two weeks;
if the ratio is not greater than k, judging that the guiding effect of the instructor is poor and generating a first adjustment instruction;
when the first instructor and the second instructor of the instructor corresponding to the instruction monitoring set correspond to the first maintenance instruction, the instruction identity of the instructor is kept unchanged;
When the instructor corresponds to the first instructor and the second instructor corresponds to the first adjustment instruction of the instruction monitoring set, stopping the instruction of the first instructor and training, and adjusting the second instructor to be the first instructor.
The specific steps of the dynamic adjustment of the training of the rehabilitation person comprise:
The overall evaluation is carried out on the training of the rehabilitation person according to the rehabilitation analysis set and the rehabilitation monitoring set in the monitoring period; acquiring and analyzing the ratio of the total number of times of the substandard training in the rehabilitation monitoring set to the total number of times of the substandard training, and if the ratio is larger than p, judging that the training effect of the rehabilitation person is excellent and generating a second maintenance instruction; p is a real number greater than zero;
if the ratio is not greater than p, judging that the training effect of the rehabilitation person is poor and generating a second adjustment instruction;
When the first rehabilitator and the second rehabilitator corresponding to the rehabilitation monitoring set both correspond to the second maintenance instruction, the training intensity of the rehabilitator is kept unchanged;
When the first convalescence person and the second convalescence person corresponding to the convalescence monitoring set both correspond to the second adjusting instruction, stopping the remote convalescence training of the first convalescence person based on the big data technology and performing text guidance, and adjusting the second convalescence person to the first convalescence person to perform low-difficulty training.
In the embodiment of the invention, the guiding state of the instructor and the training state of the rehabilitation person are evaluated periodically by setting a monitoring period, and the guiding of the instructor and the training of the rehabilitation person are dynamically adjusted according to the evaluation result, so that the instructors with different abilities can dynamically maintain the efficient guiding function, the rehabilitation persons with different states can also dynamically maintain the adaptive training strength, and the overall effect of the remote rehabilitation guidance is effectively improved.
Referring to fig. 2, a flow chart of a remote rehabilitation guidance method based on big data according to an embodiment of the invention is shown. In this embodiment, the method for remote rehabilitation guidance based on big data specifically includes the steps of:
Step one: counting first information of a mentor who implements the remote rehabilitation guidance and second information of a rehabilitation person who needs the remote rehabilitation guidance; the first information comprises the guiding type, the number of the guiding people, the guiding time and the good score of the guiding people; the second information includes an age, a rehabilitation type, and a training level of the rehabilitee;
Step two: performing data processing and training on the collected first information of the instructor and the second information of the rehabilitee to obtain a guiding analysis set containing guiding coefficients and a rehabilitation analysis set containing rehabilitation coefficients;
Step three: monitoring and evaluating the guiding behavior of a instructor and the rehabilitation training of a rehabilitee to obtain a guiding and monitoring set containing guiding and evaluating values and a rehabilitation and monitoring set containing a rehabilitation and reexamine evaluating value, wherein the guiding and evaluating value is a numerical value for evaluating the guiding state of the instructor by combining various data of the instructor during training, and the rehabilitation evaluating value is a numerical value for integrally evaluating the training state of the rehabilitee by combining action characteristic data of the rehabilitee during training with training time;
step four: according to the guiding analysis set and the rehabilitation analysis set, the guiding monitoring set and the rehabilitation monitoring set are combined to dynamically adjust the guiding of the instructor and the training of the rehabilitation person in a preset monitoring period, so that the instructors with different capacities can dynamically keep high-efficiency guiding function, and the rehabilitation persons with different states can dynamically keep the adaptive training intensity.
In several embodiments provided by the present invention, it should be understood that the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Claims (4)
1. The remote rehabilitation guidance system based on big data comprises a monitoring analysis module and an adjustment module, and is characterized in that the monitoring analysis module comprises a personnel analysis unit and a behavior analysis unit;
Personnel analysis unit: performing data processing and training on the collected first information of the instructor and the second information of the rehabilitee to obtain a guiding analysis set containing guiding coefficients and a rehabilitation analysis set containing rehabilitation coefficients;
behavior analysis unit: monitoring and evaluating the guiding behaviors of the instructor and the rehabilitation training of the rehabilitee to obtain a guiding monitoring set containing guiding evaluation values and a rehabilitation monitoring set containing rehabilitation evaluation values;
And an adjustment module: dynamically adjusting the guidance of a mentor and the training of a rehabilitation person in a preset monitoring period by combining the guidance monitoring set and the rehabilitation monitoring set according to the guidance analysis set and the rehabilitation analysis set;
the specific steps of processing and training the collected first information of the instructor include:
Acquiring a guidance type, a guidance number, a guidance duration and a good score of a guidance person in the first information; acquiring corresponding guidance weights according to the guidance types and taking value marks; respectively extracting and marking the numerical values of the number of the people to be guided, the guiding time length and the number of the betting points; carrying out normalization processing and parallel training on each item of data marked in the instruction processing information to obtain an instruction coefficient; acquiring a first director and a second director according to the guiding coefficient; the guidance coefficients and the first and second directors form a guidance analysis set;
the specific steps of data processing and training the collected second information of the rehabilitee include:
Acquiring the age, rehabilitation type and training grade of the rehabilitation person in the second information; matching the rehabilitation type with the guiding type list to obtain corresponding rehabilitation weight and value marking; extracting and marking the numerical value of the age; acquiring training weights associated with training grades and marking; carrying out normalization processing and parallel training on each item of data marked in the rehabilitation processing information to obtain a rehabilitation coefficient; acquiring a first rehabilitee and a second rehabilitee according to the rehabilitation coefficient; the training difficulty of the second rehabilitation person is higher than that of the first rehabilitation person; the rehabilitation coefficients and the first rehabilitee and the second rehabilitee form a rehabilitation analysis set;
The specific steps of monitoring and evaluating the guiding behavior of the instructor include:
Recording the whole voice guidance process of the instructor to obtain instruction recording data; text conversion is carried out on the guiding record data to obtain guiding text data; matching the guiding text data with a pre-constructed project guiding table and a behavior evaluation table to obtain project matching data and behavior evaluation data; the item matching data and the behavior evaluation data form a guiding matching set of a guiding person;
extracting the total number of item matching in the item matching data and the total number of behavior evaluation in the behavior evaluation data, and respectively taking value marks; carrying out normalization processing and parallel training on each marked data to obtain a guide evaluation value; setting the guidance corresponding to the guidance evaluation value which is not more than the guidance evaluation threshold value as the unqualified guidance, and adding one to the number of unqualified guidance; setting the guidance corresponding to the guidance evaluation value smaller than the guidance evaluation threshold as standard-reaching guidance, and adding one to the number of times of standard-reaching guidance;
counting the total number of unqualified guide times and the total number of qualified guide times in the monitoring period to obtain guide statistical data; the guidance evaluation value and the guidance statistical data form a guidance monitoring set;
the specific steps of monitoring and evaluating the rehabilitation training of the rehabilitation person include:
recording the whole action training process of the rehabilitation person to obtain training video data; acquiring frame images in training video data and arranging and combining the frame images according to time sequence to obtain video split data; extracting action characteristics of frame images in video split data based on an image recognition algorithm;
Matching the action features with a pre-constructed sample action table, obtaining the maximum overlapping area of the action features and the sample action features in a sample action set, and taking a value mark; acquiring the training time length and taking a value mark; carrying out normalization processing and parallel training on each marked data to obtain Kang Fuping estimated values; setting the rehabilitation training corresponding to the rehabilitation evaluation value which is not more than the rehabilitation evaluation threshold value as the substandard training, and adding one to the times of the substandard training; setting the rehabilitation training corresponding to the rehabilitation evaluation value larger than the rehabilitation evaluation threshold value as standard-reaching training, and adding one to the number of times of the standard-reaching training;
Counting the total number of times of substandard training and the total number of times of substandard training in a monitoring period to obtain rehabilitation statistical data; the estimated value of the recovery reexamine and the recovery statistical data form a recovery monitoring set;
the specific steps of dynamically adjusting the guidance of the instructor include:
Acquiring and analyzing the ratio of the total number of unqualified instructions in the instruction monitoring set to the total number of qualified instructions to obtain a first maintenance instruction and a first adjustment instruction; and adjusting the guiding identity of the instructor according to the first maintenance instruction and the first adjustment instruction.
2. The big data based remote rehabilitation coaching system according to claim 1, characterized in that the specific step of dynamically adjusting the training of the rehabilitee comprises:
acquiring and analyzing the ratio of the total number of times of the substandard training in the rehabilitation monitoring set to the total number of times of the substandard training, and obtaining a second maintenance instruction and a second adjustment instruction; and adjusting the training intensity of the rehabilitation person according to the second maintenance instruction and the second adjustment instruction.
3. The big data based remote rehabilitation guidance system of claim 2, further comprising a personnel statistics module for counting first information of a mentor who implements the remote rehabilitation guidance and second information of a rehabilitee who needs the remote rehabilitation guidance; the first information comprises the guiding type, the number of the guiding people, the guiding time and the good score of the guiding people; the second information includes an age of the rehabilitee, a rehabilitation type, and a training level.
4. The big data based remote rehabilitation guidance method applied to the big data based remote rehabilitation guidance system of any one of claims 1 to 3, characterized by comprising:
counting first information of a mentor who implements the remote rehabilitation guidance and second information of a rehabilitation person who needs the remote rehabilitation guidance; the first information comprises the guiding type, the number of the guiding people, the guiding time and the good score of the guiding people; the second information includes an age, a rehabilitation type, and a training level of the rehabilitee;
Performing data processing and training on the collected first information of the instructor and the second information of the rehabilitee to obtain a guiding analysis set containing guiding coefficients and a rehabilitation analysis set containing rehabilitation coefficients;
monitoring and evaluating the guiding behaviors of the instructor and the rehabilitation training of the rehabilitee to obtain a guiding monitoring set containing guiding evaluation values and a rehabilitation monitoring set containing rehabilitation evaluation values;
and dynamically adjusting the guidance of the instructor and the training of the rehabilitee in a preset monitoring period by combining the guidance monitoring set and the rehabilitation monitoring set according to the guidance analysis set and the rehabilitation analysis set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210323813.9A CN114758747B (en) | 2022-03-30 | 2022-03-30 | Remote rehabilitation guidance system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210323813.9A CN114758747B (en) | 2022-03-30 | 2022-03-30 | Remote rehabilitation guidance system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114758747A CN114758747A (en) | 2022-07-15 |
| CN114758747B true CN114758747B (en) | 2024-05-03 |
Family
ID=82327575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210323813.9A Active CN114758747B (en) | 2022-03-30 | 2022-03-30 | Remote rehabilitation guidance system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114758747B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448807A (en) * | 2018-10-12 | 2019-03-08 | 成都数联易康科技有限公司 | A kind of patient's medical treatment guiding implementation method based on doctor's medical services behavioural analysis |
| KR20190112962A (en) * | 2018-03-27 | 2019-10-08 | (주)메디즈 | Cognitive rehabilitation training system |
| CN111724879A (en) * | 2020-06-29 | 2020-09-29 | 中金育能教育科技集团有限公司 | Rehabilitation training evaluation processing method, device and equipment |
| CN113707268A (en) * | 2021-08-27 | 2021-11-26 | 温州医科大学慈溪生物医药研究院 | Rehabilitation training evaluation method and system |
| CN114203274A (en) * | 2021-12-14 | 2022-03-18 | 浙江大学 | Chronic respiratory failure patient remote rehabilitation training guidance system |
| CN114203275A (en) * | 2021-12-16 | 2022-03-18 | 江苏海洋大学 | Recovery state analysis system for rehabilitation training movement |
-
2022
- 2022-03-30 CN CN202210323813.9A patent/CN114758747B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190112962A (en) * | 2018-03-27 | 2019-10-08 | (주)메디즈 | Cognitive rehabilitation training system |
| CN109448807A (en) * | 2018-10-12 | 2019-03-08 | 成都数联易康科技有限公司 | A kind of patient's medical treatment guiding implementation method based on doctor's medical services behavioural analysis |
| CN111724879A (en) * | 2020-06-29 | 2020-09-29 | 中金育能教育科技集团有限公司 | Rehabilitation training evaluation processing method, device and equipment |
| CN113707268A (en) * | 2021-08-27 | 2021-11-26 | 温州医科大学慈溪生物医药研究院 | Rehabilitation training evaluation method and system |
| CN114203274A (en) * | 2021-12-14 | 2022-03-18 | 浙江大学 | Chronic respiratory failure patient remote rehabilitation training guidance system |
| CN114203275A (en) * | 2021-12-16 | 2022-03-18 | 江苏海洋大学 | Recovery state analysis system for rehabilitation training movement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114758747A (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035089A (en) | A kind of Online class atmosphere assessment system and method | |
| CN111915148B (en) | Classroom teaching evaluation method and system based on information technology | |
| CN109805944B (en) | Children's ability analytic system that shares feelings | |
| CN108491830A (en) | A kind of job site personnel uniform dress knowledge method for distinguishing based on deep learning | |
| CN110097283A (en) | Education Administration Information System and method based on recognition of face | |
| CN112785205A (en) | Intelligent teaching comprehensive analysis system based on education big data | |
| CN114758747B (en) | Remote rehabilitation guidance system and method based on big data | |
| Yang et al. | Research on face recognition sports intelligence training platform based on artificial intelligence | |
| CN116452071B (en) | Intelligent teaching quality evaluation system based on VR and 5G technologies | |
| CN111369140B (en) | Teaching evaluation system and method | |
| CN116747495A (en) | Action counting method and device, terminal equipment and readable storage medium | |
| CN114971425B (en) | Database information monitoring method, device, equipment and storage medium | |
| CN114068020A (en) | Intelligent health monitoring and optimizing system | |
| CN113887339A (en) | Silent voice recognition system and method fusing surface electromyogram signal and lip image | |
| Rafiee et al. | Effect of Grit on Exercise Self-Efficacy and Participatory Performance in Elite Athletes | |
| Gill et al. | Sports Game Classification and Detection Using ResNet50 Model Through Machine Learning Techniques Using Artificial Intelligence | |
| WO2022082840A1 (en) | Brain training evaluation system based on smart maze and evaluation method therefor | |
| Shen | Learn from Teachers: A Teacher Learner Yoga Pose Classification and Scoring Network | |
| Kamnardsiri et al. | Requirement analysis to design the knowledge-based system for long jump coaching | |
| CN114239724B (en) | Cuball motion recognition and skill evaluation method based on inertial sensor | |
| Zhang et al. | Intelligent Recognition System of Sports Athletes’ Wrong Actions Based on AI+ IoT | |
| CN111383747B (en) | Big data-based field rescue analysis system and method | |
| CN115798676B (en) | Interactive experience analysis management method and system based on VR technology | |
| CN117390401B (en) | Campus sports digital management system and method based on cloud platform | |
| CN117496580B (en) | Facial expression intelligent recognition robot terminal based on multi-person synchronous interaction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240408 Address after: 518000, No.310, 3rd Floor, Port Building, Ocean Shipping Center, No. 59 Linhai Avenue, Nanshan Street, Qianhai Shenzhen Hong Kong Cooperation Zone, Shenzhen, Guangdong Province - G399 Applicant after: Shenzhen Qianhai hi tech international medical management Co.,Ltd. Country or region after: China Address before: 214135 floor 7, building C1, China Sensor Network International Innovation Park, 200 Linghu Avenue, Xinwu District, Wuxi City, Jiangsu Province Applicant before: JIANGSU ZHONGKE NORTHWEST STAR INFORMATION TECHNOLOGY CO.,LTD. Country or region before: China |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |