Medical rehabilitation data intelligent processing method based on monitoring sensor

Abstract

The invention relates to the technical field of data compression and storage, in particular to a medical rehabilitation data intelligent processing method based on a monitoring sensor, which comprises the following steps of: acquiring rehabilitation data of a patient, obtaining a character type sequence, and further obtaining the frequency of a character string spliced by each character and any character in the rehabilitation data of the patient; the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data is obtained; the method comprises the following steps: acquiring a coded character sequence of each character, further obtaining the number of character strings spliced by each character and each character in the coded character sequence of each character and the number of intervals of each character, further obtaining the probability that each character is the next character of each character in patient rehabilitation data, and combining arithmetic coding to obtain the probability of the next character of each character in the patient rehabilitation data. According to the method, the target interval is iteratively divided on the basis of the predicted probability that each character is the next character of each character in the patient rehabilitation data, so that the compression efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data compression and storage, and in particular to a method for intelligently processing medical rehabilitation data based on monitoring sensors. Background Art

[0002] The intelligent processing method of medical rehabilitation data based on monitoring sensors is to use sensor technology to collect the patient's physiological, movement, posture and other data during the rehabilitation process, and to intelligently process and analyze these rehabilitation data to help rehabilitation experts evaluate and detect the patient's rehabilitation progress and provide guiding opinions. Therefore, it is necessary to compress and store the patient's rehabilitation data collected by the sensor.

[0003] Arithmetic coding is a lossless data compression algorithm that divides the target interval based on the frequency of characters in the patient rehabilitation data. The patient rehabilitation data is compressed into a decimal in the final target interval by continuously iteratively dividing the initial target interval. The compression efficiency depends on the range of the target interval in each iteration. If the range of the target interval is smaller in each iteration, the smaller the range of the final target interval, the longer the code length after encoding the patient rehabilitation data using any decimal selected in the final target area, the larger the storage space required, and the lower the compression efficiency of the patient rehabilitation data. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a medical rehabilitation data intelligent processing method based on monitoring sensors.

[0005] The medical rehabilitation data intelligent processing method based on monitoring sensors of the present invention adopts the following technical solutions: An embodiment of the present invention provides a method for intelligently processing medical rehabilitation data based on monitoring sensors, the method comprising the following steps: Collect patient recovery data; According to the patient rehabilitation data, a character type sequence is obtained; according to the character type sequence, the frequency of a character string concatenated with each character and any character in the patient rehabilitation data is obtained; According to the frequency of the character string concatenated with any character in the patient rehabilitation data, obtaining the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data; Obtain the encoded character sequence of each character in the patient rehabilitation data; obtain the number of strings of each character in the patient rehabilitation data and each type of character in the encoded character sequence of each character; obtain the number of each type of interval of each character in the patient rehabilitation data according to the encoded character sequence of each character in the patient rehabilitation data; obtain the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data according to the number of each type of interval of each character in the patient rehabilitation data, the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data, and the number of strings of each character in the encoded character sequence of each character; According to the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data, the patient rehabilitation data is compressed by using arithmetic coding to obtain compressed data; When viewing the patient rehabilitation data, the decompressed data is obtained based on the compressed data and the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data.

[0006] Preferably, the method of obtaining the frequency of a character string composed of each character and any character in the patient rehabilitation data according to the character type sequence includes the following specific steps: Get the number of characters in the character type sequence, recorded as , establish a For the first character in the character type sequence, count the frequency of the string of the first character and the first character in the character type sequence appearing in the patient rehabilitation data, and fill the frequency into the first row and first column of the empty matrix; count the frequency of the string of the first character and the second character in the character type sequence appearing in the patient rehabilitation data, and fill the frequency into the first row and second column of the empty matrix, and so on, until the first row in the empty matrix is ​​filled with data; For the second character in the character type sequence, count the frequency of occurrence of the string of the second character and the first character in the character type sequence in the patient rehabilitation data, and fill the frequency into the second row and first column of the empty matrix. Count the frequency of occurrence of the string of the second character and the second character in the character type sequence in the patient rehabilitation data, and fill the frequency into the second row and second column of the empty matrix, and so on until the second row in the matrix is ​​filled with data; And so on, until every character in the character type sequence is traversed and stops, each element in the obtained matrix is ​​the frequency of the string of each character spliced ​​with any character in the patient rehabilitation data.

[0007] Preferably, the method of obtaining the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data according to the frequency of the character string concatenated with any character in the patient rehabilitation data includes the following specific steps: Get any character in the rehabilitation patient data, record it as the current coded character, get the frequency of the string that is the current coded character and each character in the character type sequence, and divide it by the sum of the frequencies of all the strings in the matrix to get the initial probability that each character in the character type sequence is the next character of the current coded character.

[0008] Preferably, the step of obtaining the encoded character sequence of each character in the patient rehabilitation data comprises the following specific steps: Get all characters before the current coded character to form the coded character sequence of the current coded character.

[0009] Preferably, the step of obtaining the number of each character in the patient rehabilitation data and the string concatenated with each character in the encoded character sequence of each character includes the following specific steps: Get the number of strings that are the concatenation of the current encoding character and each character in the encoded character sequence of the current encoding character.

[0010] Preferably, the method of obtaining the number of each type of intervals of each character in the patient rehabilitation data according to the encoded character sequence of each character in the patient rehabilitation data comprises the following specific steps: In the encoded character sequence of the current encoded character, get the current encoded character and the first The number of characters between each string of characters concatenated in this way and the current coded character, and the smallest number of characters is used as the first character of the current coded character in the patient rehabilitation data. The number of intervals.

[0011] Preferably, the step of obtaining the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data includes the following specific steps: In the formula, Represents the first character in the character type sequence The probability that this character is the next character of the current encoding character; The first character in the character type sequence The initial probability that this character is the next character of the current coded character; The current encoding character and The number of characters in the string concatenated by this character in the encoded sequence of the current encoding character; Represents the current encoding character Number of intervals; Represents an exponential function with a natural constant as base.

[0012] Preferably, the method of compressing the patient rehabilitation data by arithmetic coding according to the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data to obtain compressed data includes the following specific steps: Obtain the frequency of each character in the patient rehabilitation data, divide the initial target interval into multiple sub-intervals according to the frequency of each character in the patient rehabilitation data, obtain the first character in the patient rehabilitation data, and record the sub-interval corresponding to the first character in the initial target interval as the first character target interval; Divide the first character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the first character in the patient rehabilitation data, obtain the second character in the patient rehabilitation data, and record the sub-interval corresponding to the second character in the first character target interval as the second character target interval; According to the probability that each character in the character type sequence is the next character of the second character in the patient's rehabilitation data, the second character target interval is divided into multiple sub-intervals, and the third character in the patient's rehabilitation data is obtained. The sub-interval corresponding to the third character in the second character target interval is obtained, which is recorded as the third character target interval; and so on, the process stops after the last character in the patient's rehabilitation data is obtained, and the last character target interval is obtained. Any decimal is obtained in the range of the last character target interval as compressed data.

[0013] Preferably, the method of obtaining the decompressed data according to the compressed data and the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data comprises the following specific steps: The initial target interval is divided into a plurality of sub-intervals according to the frequency of each character in the patient rehabilitation data, each character corresponds to a sub-interval, the sub-interval in which the compressed data is located is taken as the first character target interval, and the character corresponding to the first character target interval is the first character in the patient rehabilitation data; Divide the first character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the first character in the patient rehabilitation data, each character corresponds to one sub-interval, and use the sub-interval in which the compressed data is located as the second character target interval, and the character corresponding to the second character target interval is the second character in the patient rehabilitation data; Divide the second character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the second character in the patient rehabilitation data, each character corresponds to one sub-interval, and use the sub-interval in which the compressed data is located as the third character target interval, and the character corresponding to the third character target interval is the third character in the patient rehabilitation data; And so on, and the number of decimal places in the two boundaries of each character target interval is obtained in turn. If the number of decimal places of the compressed data is consistent with the number of decimal places in the two boundaries of any character target interval, the iteration is stopped, and the obtained characters are concatenated in order to obtain the decompressed data.

[0014] Preferably, the step of obtaining the character type sequence according to the patient rehabilitation data includes the following specific steps: Different types of characters in the patient rehabilitation data are obtained to form a character type sequence.

[0015] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the frequency of the string of each character spliced ​​with any character in the patient rehabilitation data, thereby obtaining the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data; obtains the encoded character sequence of each character in the patient rehabilitation data, thereby obtaining the number of the string of each character in the patient rehabilitation data spliced ​​with each character in the encoded character sequence of each character and the number of each interval of each character in the patient rehabilitation data; according to the number of each interval of each character in the patient rehabilitation data, the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data, and the character sequence of each character spliced ​​with each character The number of strings in the encoded character sequence of each character is obtained, and the initial probability of each character in the character type sequence being the next character of the current encoded character is obtained, and then the patient rehabilitation data is compressed to obtain compressed data. The present invention divides the target interval of each character by predicting the initial probability of each character in the character type sequence being the next character of each character, and then obtains the target interval of the next character of each character. In this way, the target interval range of each character in the patient rehabilitation data can be as large as possible, so that the range of the final target interval is larger, and any decimal in the final target area range is obtained to encode the patient rehabilitation data. The storage space occupied by the obtained encoding result is smaller, thereby improving the compression efficiency of the patient rehabilitation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Figure 1 The present invention is a flowchart of the steps of the intelligent processing method of medical rehabilitation data based on monitoring sensors. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of the intelligent processing method of medical rehabilitation data based on monitoring sensors proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the intelligent processing method of medical rehabilitation data based on monitoring sensors provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flowchart of a method for intelligently processing medical rehabilitation data based on monitoring sensors provided by an embodiment of the present invention, the method comprising the following steps: S001. Collect patient rehabilitation data.

[0022] It should be noted that sensors are increasingly used in the field of medical care. They are medical devices used to monitor patients' rehabilitation exercises. For example, heart rate sensors, blood pressure sensors, and blood glucose sensors are used to monitor patients' physiological parameters to help rehabilitation experts evaluate and detect patients' rehabilitation progress. In an embodiment of the present invention, a heart rate sensor is prepared and fixed to the heart area of ​​the patient's chest, the heart rate sensor is started to collect the patient's heart rate data, and the collected patient's heart rate data is recorded as the patient's rehabilitation data.

[0023] S002. Obtain the frequency of each character in the patient rehabilitation data and the string concatenated with any character in the patient rehabilitation data.

[0024] It should be noted that arithmetic coding is a lossless data compression algorithm. It divides the target interval based on the frequency of characters in the data, and compresses the data into a decimal in the final target interval by continuously iteratively dividing the initial target interval. The compression efficiency depends on the range of the target interval in each iteration. If the range of the target interval can be made larger in each iteration, the range of the final target interval will be larger, the code length after encoding any number selected in the final target area will be shorter, the required storage space will be smaller, and the compression efficiency will be higher.

[0025] When arithmetic coding is used to compress patient rehabilitation data, when the target interval is iteratively divided based on the frequency of each character in the patient rehabilitation data, for any character in the patient rehabilitation data, the size of its target interval depends on the frequency of the character. If the frequency of the character is large, the range of the target interval corresponding to the character is large. If the frequency of the character is small, the range of the target interval corresponding to the character is small, resulting in a smaller range of the final target interval and lower compression efficiency. Since there is continuity between the characters in the patient rehabilitation data, in an embodiment of the present invention, a method is proposed to predict the probability of each character in the character type sequence being the next character of the current encoded character based on the current encoded character, and then divide the target interval of the current encoded character based on the probability of each character in the predicted character type sequence being the next character of the current encoded character to obtain the target interval of the next character. In this way, the target interval range of each character in the patient rehabilitation data can be as large as possible, so that the range of the final target interval is large, and the compression efficiency is improved.

[0026] It should be further explained that, since the collected patient rehabilitation data is the patient's heart rate data, the heart rate data is continuous in the time series, so there is continuity between the characters in the patient rehabilitation data. Therefore, the probability of each character in the character type sequence being the next character of the current coded character can be predicted based on the current coded character. If the frequency of the string of the current coded character and any character spliced ​​in the patient rehabilitation data is greater, it means that the next character of the current coded character is more likely to be this character, and the probability that the next character of the current coded character is more likely to be this character is greater; if the frequency of the string of the current coded character and any character spliced ​​in the patient rehabilitation data is smaller, it means that the next character of the current coded character is less likely to be this character, and the probability that the next character of the current coded character is more likely to be this character is smaller. Therefore, in order to facilitate the subsequent compression of the patient rehabilitation data, it is first necessary to obtain the frequency of the string of each character in the patient rehabilitation data and any character spliced ​​in the patient rehabilitation data.

[0027] It is known that the co-occurrence matrix is ​​formed based on the co-occurrence frequency of each character and its surrounding neighborhood characters. Each element in the co-occurrence matrix represents the frequency of occurrence of a specific character pair. Therefore, combining the idea of ​​the co-occurrence matrix, the frequency of each character in the patient rehabilitation data and the string spliced ​​with any character in the patient rehabilitation data is counted.

[0028] In the embodiment of the present invention, different types of characters in the patient rehabilitation data are obtained to form a character type sequence, which is recorded as ,in Indicates the first character in a sequence of character types. Type of characters, Representative patient recovery data different kinds of characters, so generate a An empty matrix of size, traversing the first character in the character type sequence , count the first character The first character in the character type sequence The number of times the concatenated string appears in the patient's rehabilitation data is filled in the first row and first column of the empty matrix to count the first character and the second character in the character type sequence The number of times the concatenated string appears in the patient's rehabilitation data is filled in the first row and second column of the empty matrix, and so on until the first row of the empty matrix is ​​filled with data; Traverse the second character in the character type sequence , count the second character The first character in the character type sequence The number of times the concatenated string appears in the patient's rehabilitation data is filled in the second row and first column of the empty matrix to count the second character and the second character in the character type sequence The number of times the concatenated string appears in the patient's rehabilitation data is filled into the second row and second column of the empty matrix, and so on until the second row of the matrix is ​​filled with data; And so on, until every character in the character type sequence is traversed, the process stops, and a matrix and the frequency of a string of each character concatenated with any other character in the patient's rehabilitation data are obtained.

[0029] So far, the frequency of character strings composed of each character and any other character in the patient rehabilitation data has been obtained.

[0030] S003. According to the frequency of the character string concatenated with any character in the patient rehabilitation data, obtain the probability that each character in the character type sequence is the next character of the current encoding character.

[0031] It should be noted that, when the frequency of the string of the known current coded character and any character is greater in the patient rehabilitation data, it means that the next character of the current coded character is more likely to be this character, and the probability that the next character of the current coded character is more likely to be this character is greater; if the frequency of the string of the known current coded character and any character is smaller in the patient rehabilitation data, it means that the next character of the current coded character is less likely to be this character, and the probability that the next character of the current coded character is more likely to be this character is smaller. Therefore, according to the frequency of the string of the known current coded character and any character, the initial probability of each character in the character type sequence being the next character of the current coded character is obtained.

[0032] It should be further explained that, for the first character of the patient's rehabilitation data, it is impossible to predict the probability of the first character being each character based on the previous character. Therefore, in an embodiment of the present invention, when encoding the first character of the patient's rehabilitation data, the initial target interval is divided based on the frequency of each character in the patient's rehabilitation data to obtain the target interval of the first character.

[0033] In the embodiment of the present invention, any character in the rehabilitation patient data is traversed and recorded as the current coded character, and the current coded character and the first character in the character type sequence are obtained in the matrix. The frequency of the string of characters concatenated by the matrix is ​​divided by the sum of the frequencies of all the strings in the matrix to get the character type sequence. The initial probability that the character is the next character of the current coded character is obtained.

[0034] It should be noted that the initial probability of each character in the character type sequence being the next character of the current coded character is obtained based on the frequency of the string of characters spliced ​​together with each character in the global rehabilitation patient data. The influence of the coded character sequence before the current coded character on the initial probability is not taken into account. If, in the coded character sequence before the current coded character, there is a string of characters spliced ​​together with the current coded character, then the initial probability of the next character of the current coded character being the character is inaccurate and needs to be adjusted to appropriately lower the initial probability. If the number of strings of characters spliced ​​together with the current coded character is larger in the coded character sequence, the degree to which the initial probability needs to be adjusted will be greater. If the number of strings of characters spliced ​​together with the current coded character is smaller in the coded character sequence, the initial probability will be adjusted to a greater extent. The smaller the number of sequences, the less the initial probability needs to be adjusted. Since the collected patient rehabilitation data is the patient's heart rate data, the heart rate data has continuity in the time series. Therefore, when the position of the string of the current coded character and the character is close to the current coded character in the coded character sequence, the probability that the next character of the current coded character is the character is greater. Therefore, in the embodiment of the present invention, according to the number of strings of the current coded character and any character in the coded character sequence, the initial probability of each character in the character type sequence being the next character of the current coded character is adjusted, and then combined with the position of the string of the current coded character and the character in the coded character sequence, the probability of each character in the character type sequence being the next character of the current coded character is obtained. If the current coded character is close to the first coded character, the probability of each character in the character type sequence being the next character of the current coded character is adjusted. When the number of characters in the encoded sequence is 0, it means that the next character of the current encoded character is The initial probabilities of these characters are accurate and do not need to be adjusted.

[0035] In an embodiment of the present invention, any character in the rehabilitation patient data is obtained, recorded as the current coded character, and all characters before the current coded character are obtained to form a coded character sequence of the current coded character; the number of strings of the current coded character and each character concatenated in the coded character sequence of the current coded character is obtained; in the coded character sequence of the current coded character, the number of characters before the current coded character and each character concatenated in the coded character sequence of the current coded character is obtained; The number of characters between each string of characters concatenated in this way and the current coded character, and the smallest number of characters is used as the first character of the current coded character in the patient rehabilitation data. Similarly, the number of each interval of the current coded character in the patient's rehabilitation data is obtained.

[0036] Get the first character in the character type sequence The probability that this character is the next character of the current encoding character: In the formula, Represents the first character in the character type sequence The probability that this character is the next character of the current encoding character; The larger the value, the more likely the next character of the current coded character is. Type of characters; The first character in the character type sequence The initial probability that this character is the next character of the current coded character; The current encoding character and The number of characters in the string concatenated by the current encoding character in the encoded sequence. The current encoding character is The more characters in the coded character sequence the string is, the more the initial probability needs to be reduced. If the number of characters in the coded character sequence is smaller, the smaller the initial probability needs to be reduced. Represents the first character in the current encoding The number of intervals, the first The smaller the number of intervals, the closer the current coded character is to the first If the position of the string of characters concatenated in the encoded character sequence is close to the current encoded character, then the character type sequence The greater the probability that this character is the next character of the current coded character; it should be noted that when When it is 0, it means that there is no current encoding character in the encoded sequence. A string of characters concatenated together, The value of is the length of the encoded sequence.

[0037] Similarly, the probability of each character in the character type sequence being the next character of the current coded character is obtained. It should be noted that when the target interval of the current coded character is divided according to the probability of each character in the character type sequence being the next character of the current coded character to obtain the target interval of the next character, the probability of each character in the character type sequence being the next character of the current coded character needs to be normalized. Therefore, in the embodiment of the present invention, the probability of each character in the character type sequence being the next character of the current coded character is used. The normalization method processes the probability that each character in the character type sequence is the next character of the current encoded character.

[0038] At this point, the probability that the next character of each character in the rehabilitation patient data is each character is obtained, and then the target interval of each character is divided according to the probability that the next character of each character is each character to obtain the target interval of the next character. In this way, the target interval range of each character in the patient rehabilitation data can be as large as possible, making the final target interval range larger, thereby improving the compression efficiency of arithmetic coding.

[0039] S004. Compress the patient rehabilitation data according to the probability that each character in the character type sequence is the next character of the current encoding character to obtain compressed data.

[0040] Arithmetic coding is used to compress patient rehabilitation data. The process of obtaining compressed data is as follows: Obtain the frequency of each character in the patient rehabilitation data, divide the initial target interval into multiple sub-intervals according to the frequency of each character in the patient rehabilitation data, obtain the first character in the patient rehabilitation data, and record the sub-interval corresponding to the first character in the initial target interval as the first character target interval; Divide the first character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the first character in the patient rehabilitation data, obtain the second character in the patient rehabilitation data, and record the sub-interval corresponding to the second character in the first character target interval as the second character target interval; According to the probability that each character in the character type sequence is the next character of the second character in the patient's rehabilitation data, the second character target interval is divided into multiple sub-intervals, and the third character in the patient's rehabilitation data is obtained. The sub-interval corresponding to the third character in the second character target interval is obtained, which is recorded as the third character target interval; and so on, the process stops after the last character in the patient's rehabilitation data is obtained, and the last character target interval is obtained. Any decimal is obtained in the range of the last character target interval as compressed data.

[0041] At this point, the compression of the patient's rehabilitation data is completed and the compressed data is obtained.

[0042] S005. Decompress the compressed data.

[0043] It should be noted that the compressed data is stored in the medical rehabilitation management system. When the patient's medical data needs to be viewed or used, the compressed data stored in the medical rehabilitation management system needs to be decompressed. The specific process is as follows: The initial target interval is divided into a plurality of sub-intervals according to the frequency of each character in the patient rehabilitation data, each character corresponds to a sub-interval, the sub-interval in which the compressed data is located is taken as the first character target interval, and the character corresponding to the first character target interval is the first character in the patient rehabilitation data; Divide the first character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the first character in the patient rehabilitation data, each character corresponds to one sub-interval, and use the sub-interval in which the compressed data is located as the second character target interval, and the character corresponding to the second character target interval is the second character in the patient rehabilitation data; Divide the second character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the second character in the patient rehabilitation data, each character corresponds to one sub-interval, and use the sub-interval in which the compressed data is located as the third character target interval, and the character corresponding to the third character target interval is the third character in the patient rehabilitation data; And so on, and the number of decimal places in the two boundaries of each character target interval is obtained in turn. If the number of decimal places of the compressed data is consistent with the number of decimal places in the two boundaries of any character target interval, the iteration is stopped, and the obtained characters are concatenated in order to obtain the decompressed data.

[0044] At this point, the compressed data is decompressed to obtain the decompressed data.

[0045] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A medical rehabilitation data intelligent processing method based on monitoring sensors, characterized in that: The method comprises the following steps: Collect patient recovery data; According to the patient rehabilitation data, a character type sequence is obtained; according to the character type sequence, the frequency of a character string concatenated with each character and any character in the patient rehabilitation data is obtained; According to the frequency of the character string concatenated with any character in the patient rehabilitation data, obtaining the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data; Obtain the encoded character sequence of each character in the patient rehabilitation data; obtain the number of strings of each character in the patient rehabilitation data and each type of character in the encoded character sequence of each character; obtain the number of each type of interval of each character in the patient rehabilitation data according to the encoded character sequence of each character in the patient rehabilitation data; obtain the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data according to the number of each type of interval of each character in the patient rehabilitation data, the initial probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data, and the number of strings of each character in the encoded character sequence of each character; According to the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data, the patient rehabilitation data is compressed by using arithmetic coding to obtain compressed data; When viewing the patient rehabilitation data, the decompressed data is obtained based on the compressed data and the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data.

2. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 1 is characterized in that: The specific steps of obtaining the frequency of a character string composed of each character and any character in the patient rehabilitation data according to the character type sequence are as follows: Get the number of characters in the character type sequence, recorded as , establish a For the first character in the character type sequence, count the frequency of the string of the first character and the first character in the character type sequence appearing in the patient rehabilitation data, and fill the frequency into the first row and first column of the empty matrix; count the frequency of the string of the first character and the second character in the character type sequence appearing in the patient rehabilitation data, and fill the frequency into the first row and second column of the empty matrix, and so on, until the first row in the empty matrix is ​​filled with data; For the second character in the character type sequence, count the frequency of occurrence of the string of the second character and the first character in the character type sequence in the patient rehabilitation data, and fill the frequency into the second row and first column of the empty matrix. Count the frequency of occurrence of the string of the second character and the second character in the character type sequence in the patient rehabilitation data, and fill the frequency into the second row and second column of the empty matrix, and so on until the second row in the matrix is ​​filled with data; And so on, until every character in the character type sequence is traversed and stops, each element in the obtained matrix is ​​the frequency of the string of each character spliced ​​with any character in the patient rehabilitation data.

3. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 1 is characterized in that: The specific steps of obtaining the initial probability of each character in the character type sequence being the next character of each character in the patient rehabilitation data according to the frequency of the character string concatenated with any character in the patient rehabilitation data are as follows: Get any character in the rehabilitation patient data, record it as the current coded character, get the frequency of the string that is the current coded character and each character in the character type sequence, and divide it by the sum of the frequencies of all the strings in the matrix to get the initial probability that each character in the character type sequence is the next character of the current coded character.

4. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 3 is characterized in that: The step of obtaining the encoded character sequence of each character in the patient rehabilitation data includes the following specific steps: Get all characters before the current coded character to form the coded character sequence of the current coded character.

5. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 3 is characterized in that: The specific steps of obtaining the number of each character in the patient rehabilitation data and the string concatenated with each character in the encoded character sequence of each character include the following: Get the number of strings that are the concatenation of the current encoding character and each character in the encoded character sequence of the current encoding character.

6. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 3 is characterized in that: The method of obtaining the number of each type of interval of each character in the patient rehabilitation data according to the encoded character sequence of each character in the patient rehabilitation data includes the following specific steps: In the encoded character sequence of the current encoded character, get the current encoded character and the first The number of characters between each string of characters concatenated in this way and the current coded character, and the smallest number of characters is used as the first character of the current coded character in the patient rehabilitation data. The number of intervals.

7. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 3 is characterized in that: The specific steps of obtaining the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data are as follows: In the formula, Represents the first character in the character type sequence The probability that this character is the next character of the current encoding character; is the first character in the character type sequence The initial probability that this character is the next character of the current coded character; The current encoding character and The number of characters in the string concatenated by this character in the encoded sequence of the current encoding character; Represents the current encoding character Number of intervals; Represents an exponential function with a natural constant as base.

8. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 1 is characterized in that: The method of compressing the patient rehabilitation data by arithmetic coding according to the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data to obtain compressed data includes the following specific steps: Obtain the frequency of each character in the patient rehabilitation data, divide the initial target interval into multiple sub-intervals according to the frequency of each character in the patient rehabilitation data, obtain the first character in the patient rehabilitation data, and record the sub-interval corresponding to the first character in the initial target interval as the first character target interval; Divide the first character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the first character in the patient rehabilitation data, obtain the second character in the patient rehabilitation data, and record the sub-interval corresponding to the second character in the first character target interval as the second character target interval; According to the probability that each character in the character type sequence is the next character of the second character in the patient's rehabilitation data, the second character target interval is divided into multiple sub-intervals, and the third character in the patient's rehabilitation data is obtained. The sub-interval corresponding to the third character in the second character target interval is obtained, which is recorded as the third character target interval; and so on, the process stops after the last character in the patient's rehabilitation data is obtained, and the last character target interval is obtained. Any decimal is obtained in the range of the last character target interval as compressed data.

9. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 1, characterized in that: The specific steps of obtaining the decompressed data according to the compressed data and the probability that each character in the character type sequence is the next character of each character in the patient rehabilitation data are as follows: The initial target interval is divided into a plurality of sub-intervals according to the frequency of each character in the patient rehabilitation data, each character corresponds to a sub-interval, the sub-interval in which the compressed data is located is taken as the first character target interval, and the character corresponding to the first character target interval is the first character in the patient rehabilitation data; Divide the first character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the first character in the patient rehabilitation data, each character corresponds to one sub-interval, and use the sub-interval in which the compressed data is located as the second character target interval, and the character corresponding to the second character target interval is the second character in the patient rehabilitation data; Divide the second character target interval into a plurality of sub-intervals according to the probability that each character in the character type sequence is the next character of the second character in the patient rehabilitation data, each character corresponds to one sub-interval, and use the sub-interval in which the compressed data is located as the third character target interval, and the character corresponding to the third character target interval is the third character in the patient rehabilitation data; And so on, and the number of decimal places in the two boundaries of each character target interval is obtained in turn. If the number of decimal places of the compressed data is consistent with the number of decimal places in the two boundaries of any character target interval, the iteration is stopped, and the obtained characters are concatenated in order to obtain the decompressed data.

10. The intelligent processing method for medical rehabilitation data based on monitoring sensors according to claim 1, characterized in that: The specific steps of obtaining the character type sequence according to the patient rehabilitation data are as follows: Different types of characters in the patient rehabilitation data are obtained to form a character type sequence.

Images