Drug production control method and system based on Internet of Things

Abstract

The present invention relates to the field of data processing technology, and to a drug production control method and system based on the Internet of Things. The method comprises: collecting temperature and humidity; calculating the fluctuation index of data at time i; calculating the fluctuation difference index at time i, which is positively correlated with the sum of the differences between the fluctuation indexes at time i and multiple adjacent moments; calculating the abnormal index at time i; if the ratio of the total number of abnormal moments to the total number of all moments is greater than the alarm threshold, and the abnormal index at the abnormal moment is greater than the preset threshold, an alarm is issued. The present invention solves the problem that abnormal situations in the production process may not be discovered in time.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology. The present invention relates to a drug production control method and system based on the Internet of Things. Background Art

[0002] During the pharmaceutical production process, the temperature and humidity inside the pharmaceutical container can be collected through sensors, and the data generated during the production process, such as the above-mentioned temperature and humidity data, can be recorded through the Internet of Things system.

[0003] The temperature and humidity in the pharmaceutical container have a certain impact on the quality of the produced drugs. In order to ensure the quality of the drugs, the temperature and humidity in the container need to be monitored.

[0004] Temperature is one of the key factors that affect the rate and direction of chemical reactions. For most chemical reactions, changes in temperature will directly affect the movement speed and collision frequency of the reactant molecules, thereby affecting the reaction rate. In the pharmaceutical production process, at the right temperature, the formation of by-products can be avoided or reduced to improve the purity of the product. In addition, some reactions are sensitive to temperature, and too high or too low temperatures may lead to reaction failure or more impurities.

[0005] Secondly, the temperature and humidity in the container are interrelated. As the temperature rises, the saturated water vapor pressure of the air increases, resulting in a decrease in relative humidity. Furthermore, after the drug is produced, some solid drugs in the pharmaceutical container are sensitive to humidity. Excessive humidity may cause the drug to absorb moisture, agglomerate, deteriorate, and even cause adverse reactions such as hydrolysis, affecting the stability and effectiveness of the product.

[0006] In the related prior art, for example, the patent application document with application publication number CN104266304A, entitled "A technology for regulating temperature and humidity of amoxicillin sodium and clavulanate potassium for injection", discloses that: when the ambient temperature is within the set range and the ambient humidity is within the set range, the ambient temperature and ambient humidity are considered normal. For example, the patent application document with application publication number CN108844195A, entitled "A temperature and humidity set value control device and control method", discloses that: in the production workshop, by monitoring the ambient temperature and ambient humidity, the temperature and humidity can be controlled within the required range to meet the production requirements.

[0007] In the production process of medicines, if the requirements are met as long as the temperature and humidity data are within the set range, abnormal situations in the production process may not be discovered in time. Summary of the invention

[0008] In order to solve the above-mentioned technical problem that abnormal situations in the production process may not be discovered in time, the present invention proposes a drug production control method and system based on the Internet of Things.

[0009] In a first aspect of an embodiment of the present invention, a drug production control method based on the Internet of Things is provided, comprising:

[0010] Collect the temperature and humidity inside the pharmaceutical container during the drug production process;

[0011] For time i: calculate the fluctuation index at time i, where the fluctuation index is positively correlated with the absolute value of the temperature difference data and the absolute value of the humidity difference data;

[0012] Calculate the sum of the differences between the volatility index at the moment i and the volatility indexes at multiple adjacent moments, and then calculate the volatility difference index at the moment i, wherein the volatility difference index is positively correlated with the sum of the differences;

[0013] Calculate the abnormal index at the time i :

[0014]

[0015] The value of j ranges from 1 to n. represents the function for calculating the variance, represents the volatility difference index at the time i, represents the volatility index at the time i, represents the volatility difference index of the jth moment among the moment i and its adjacent n-1 moments; is the volatility index at the jth moment, express The next volatility indicator, is the positive correlation normalization function, is the absolute value, "-" is the minus sign;

[0016] The moment corresponding to the abnormal index greater than the preset threshold is taken as the abnormal moment. If the ratio of the total number of the abnormal moments to the total number of all moments is greater than the alarm threshold, an alarm signal is issued.

[0017] The fluctuation index at time i represents the degree of fluctuation of the data at time i and its adjacent multiple moments. The greater the sum of the differences between the fluctuation index at time i and the fluctuation indexes at its adjacent multiple moments, the greater the possibility that the fluctuation of the data at time i and its adjacent multiple moments is abnormal.

[0018] The larger it is, the more likely the data at time i is “outlier data” and the more likely the data at time i is abnormal.

[0019] The present invention determines the abnormality of the data at each moment through the discrete degree of the difference between the fluctuation indicators, the discrete degree of the fluctuation indicators, the fluctuation indicators and the fluctuation difference indicators. If the ratio of the total number of abnormal moments to the total number of all moments is greater than the alarm threshold, the relevant equipment may be abnormal and an alarm signal is issued.

[0020] Optionally, the calculation formula for the volatility difference indicator is:

[0021]

[0022] in, is the volatility difference index at the time i, is the volatility index at the time i, is the volatility index of the jth moment in the moment i and its adjacent m-1 moments, It is the fluctuation index of the first moment among the moment i and its adjacent m-1 moments.

[0023] The bigger and The larger the value is, the greater the possibility that the fluctuation of the data at time i and the data at the adjacent m-1 times is abnormal.

[0024] Optionally, the calculation formula for the volatility difference indicator is:

[0025]

[0026] in, is the volatility difference index at the time i, is the volatility index at the time i, It is the fluctuation index of the jth moment among the moment i and its adjacent m-1 moments.

[0027] The larger the value is, the greater the possibility that the fluctuation of the data at time i and the data at the adjacent m-1 times is abnormal.

[0028] Optionally, the volatility indicator is calculated as:

[0029]

[0030] in, is the volatility index at the time i, is the temperature at the time i, is the temperature at time i-1, is the temperature at time i+1, is the humidity at the time i, is the humidity at time i-1, is the humidity at time i+1.

[0031] The bigger and The larger it is, the greater the fluctuation of the data at time i and its adjacent times.

[0032] Optionally, the volatility indicator is calculated as:

[0033]

[0034]

[0035]

[0036] in, is the volatility index at the time i, is the index of the temperature data at the time i, is the index of humidity data at the time i, , , , , are the temperatures at time i-2, i-1, i, i+1, and i+2 respectively, , , , , They are the humidity at time i-2, i-1, i, i+1, and i+2 respectively.

[0037] Optionally, after obtaining each abnormal moment, for any two adjacent abnormal moments, the temperature data between the adjacent abnormal moments is replaced by the average of the temperature data between the adjacent abnormal moments; the humidity data between the adjacent abnormal moments is replaced by the average of the humidity data; and the processed data is compressed using a run-length encoding algorithm to obtain compressed data.

[0038] Compared with analyzing and processing the original data, analyzing and processing the compressed data can increase the speed of analyzing and processing.

[0039] Optionally, the value of n is 5.

[0040] In the second aspect of the embodiment of the present invention, a drug production control system based on the Internet of Things is provided, including: a processor and a memory, the memory storing computer program instructions, and when the computer program instructions are executed by the processor, the drug production control method based on the Internet of Things according to any one of the first aspects of the embodiment of the present invention is implemented.

[0041] Beneficial effects of the present invention:

[0042] The present invention determines the fluctuation index at each moment through temperature differential data and humidity differential data, which reflects the degree of fluctuation of the data at each moment. The fluctuation difference index at each moment is determined by the difference between the fluctuation indexes, which reflects the possibility of abnormal fluctuation of the data at each moment. The degree of abnormality of the data at each moment is determined by the discrete degree of the difference between the fluctuation indexes, the discrete degree of the fluctuation index, the fluctuation index and the fluctuation difference index, so that the accuracy of the abnormal data is higher. If the ratio of the total number of the abnormal moments to the total number of all moments is greater than the alarm threshold, the relevant equipment may be abnormal, and an alarm signal is issued to timely discover the abnormal situation in the production process.

[0043] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0045] Figure 1 is a flowchart schematically showing a drug production control method based on the Internet of Things according to an embodiment of the present invention;

[0046] Figure 2 is a schematic diagram schematically showing a structural block diagram of a medicine production control system based on the Internet of Things according to an embodiment of the present invention;

[0047] Figure 3 is a diagram schematically illustrating “outlier data” according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0049] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0050] In general, in order to improve the accuracy of judging abnormalities in the drug production process, a drug production control method based on the Internet of Things is proposed. Specifically, according to the stability of the temperature and humidity in the pharmaceutical container collected during the drug production process, it is determined whether the production process is abnormal. If an abnormality occurs, an alarm is issued. The following is a detailed description:

[0051] Figure 1 FIG. 1 is a flowchart schematically showing a method for controlling drug production based on the Internet of Things according to an embodiment of the present invention. Figure 1 The specific instructions are as follows:

[0052] S1: Collect the temperature and humidity inside the pharmaceutical container during the drug production process.

[0053] In the process of drug production, a temperature sensor is used to collect the temperature in the pharmaceutical container, and a humidity sensor is used to collect the humidity of the air in the pharmaceutical container. It should be noted that the temperature of the solution in the pharmaceutical container is basically the same as the temperature of the air in the pharmaceutical container, or the difference is small, or the temperature of the solution in the pharmaceutical container is positively correlated with the temperature of the air in the pharmaceutical container. Therefore, in one embodiment, the temperature of the air in the pharmaceutical container can be directly collected; in another embodiment, the temperature of the solution in the pharmaceutical container can be directly collected; when there is only solid in the pharmaceutical container, only the temperature of the air in the pharmaceutical container can be collected. For ease of understanding, the present invention collects the temperature of the air in the pharmaceutical container.

[0054] In one embodiment, the implementer can set the collection time interval according to the specific implementation scenario. For example, the collection time interval can be 9 seconds.

[0055] In one embodiment, for the temperature and humidity collection process, the temperature and humidity are collected synchronously. The implementer can set the total number of data in the collected temperature sequence and the total number of data in the humidity sequence. The total number of data in the temperature sequence is equal to the total number of data in the humidity sequence. For example, the collected temperature sequence is (W1, W2, W3, ..., W80), and the collected humidity sequence is (R1, R2, R3, ..., R80), where W1 represents the temperature collected at a certain moment, R1 represents the humidity collected at a certain moment, and the collection time of W1 and R1 is the same. The time interval corresponding to W1 and W2 is equal to the time interval corresponding to R1 and R2. It should be noted that the present invention can perform real-time alarms. For example, it is considered that W81 and W82 are stored in the system, and R81 and R82 are stored, and W82 and R82 are data at the current moment. It is mainly considered that the fluctuation index at the corresponding moment of W80 can be calculated using the calculation formula of the fluctuation index, but the fluctuation index at the corresponding moment of W82 cannot be calculated. It is assumed that there are data of at least two moments before the moment corresponding to W1, and the moment corresponding to W1 is continuous with the at least two moments, in order to enable the fluctuation index of the moment corresponding to W1 to be calculated by the calculation formula of the fluctuation index.

[0056] In another embodiment, for example, the collected temperature sequence is (W1, W2, W3, ..., W80), the collected humidity sequence is (R1, R2, R3, ..., R80), the moment corresponding to W80 is the current moment, and only the fluctuation index of each moment in (W3, W4, W5, ..., W78) is calculated, and the fluctuation index of the moments corresponding to W1 and W2 is set as the fluctuation index of the moment corresponding to W3, and the fluctuation index of the moments corresponding to W79 and W80 is set as the fluctuation index of the moment corresponding to W78.

[0057] For ease of explanation, the moments in this article all represent collection moments, and the time intervals between adjacent moments are equal.

[0058] S2: Calculate the volatility index at each moment.

[0059] The following is an analysis of a moment: For the i-th moment: calculate the fluctuation index of the data at moment i, which is positively correlated with the absolute value of the temperature difference data and the absolute value of the humidity difference data. The calculation process of the fluctuation index of the data at other moments is similar and will not be repeated.

[0060] For ease of explanation, the temperature herein refers to the temperature inside the pharmaceutical container, and the humidity herein refers to the humidity of the air inside the pharmaceutical container, unless otherwise specified.

[0061] In one embodiment, the calculation formula of the volatility index is:

[0062]

[0063] in, is the volatility index of the data at time i, is the temperature at the time i, is the temperature at the i-1th moment, is the temperature at the i+1th moment, is the humidity at the time i, is the humidity at the i-1th moment, is the humidity at the i+1th moment. The functions are all positive correlation normalization functions. In one embodiment, the positive correlation normalization function may be a positive correlation maximum and minimum normalization function, which is a prior art. For example, As the temperature difference G1 at time i, the temperature difference G1 at each time is calculated, the maximum value of the temperature difference G1 at all times is taken as the maximum value in the maximum-minimum normalization function, and the minimum value of the temperature difference G1 at all times is taken as the minimum value in the maximum-minimum normalization function. The other positive correlation normalization processes are similar and will not be repeated unless otherwise specified.

[0064] Here's the explanation: In the pharmaceutical manufacturing process, temperature and humidity are usually interrelated, and rising temperatures cause relative humidity to drop because warm air can hold more water vapor. In other words, as the temperature rises, the saturated water vapor pressure of the air increases, causing relative humidity to drop. Conversely, when the temperature drops, the amount of water vapor that the air can hold decreases, and relative humidity rises. When the temperature changes, the humidity usually changes with it. Therefore, the stability of the environment inside the pharmaceutical container can be judged based on the stability of temperature and humidity. When the stability of the environment inside the pharmaceutical container is poor, there is a greater possibility of problems in the pharmaceutical production process.

[0065] The larger the value is, the greater the fluctuation of the temperature at time i and the temperatures at the two adjacent time points is, that is, the greater the difference is. The larger it is, the greater the fluctuation of the humidity at time i and the humidity at the two adjacent moments, that is, the greater the difference.

[0066] The bigger and The larger it is, the greater the fluctuation of the data at time i and its adjacent times.

[0067] In another embodiment, the calculation formula of the volatility index is:

[0068]

[0069]

[0070]

[0071] in, is the volatility index at the time i, is the index of the temperature data at the time i, is the index of humidity data at the time i, , , , , are the temperatures at the i-2th, i-1th, i, i+1th, and i+2th moments respectively, , , , , They are the humidity at the i-2th, i-1th, i, i+1th, and i+2th moments respectively.

[0072] So far, the volatility index at each moment is obtained

[0073] S3: Calculate the volatility difference index at each moment.

[0074] Specifically, the sum of the differences between the volatility index at the moment i and the volatility indexes at the preset number of adjacent moments is calculated, and then the volatility difference index at the moment i is calculated, and the volatility difference index is positively correlated with the sum of the differences. The implementer can set the preset number by himself. The calculation process of the volatility difference index at other moments is similar and will not be repeated.

[0075] In one embodiment, the calculation formula of the volatility difference index is:

[0076]

[0077] in, is the volatility difference index at the time i, is the volatility index at the time i, is the fluctuation index of the jth moment among all moments Q1, and the moment Q1 is the moment i and its adjacent m-1 moments. The implementer can set the value of m by himself. In one embodiment, m can be 5. For example, (E1, E2, E3, E4, E5, E6, ..., W80), where E1 represents the first moment, for E4, E4 and its adjacent 4 moments are (E2, E3, E4, E5, E6), and the second moment among E4 and its adjacent 4 moments is E3.

[0078] For example, the normalization process can be: As the index Z1 at time i, the index Z1 at each time is calculated, the maximum value of the index Z1 at all times is taken as the maximum value in the maximum-minimum normalization function, and the minimum value of the index Z1 at all times is taken as the minimum value in the maximum-minimum normalization function.

[0079] The instructions are as follows: The larger it is, the greater the difference between the volatility index at moment i and the volatility index at its adjacent m-1 moments, which further indicates that the possibility of abnormal fluctuations in the data at moment i and the data at its adjacent m-1 moments is greater.

[0080] In another embodiment, the sum of the differences between the volatility index at the time i and a preset number of adjacent moments and any volatility index except the volatility index at the time i is calculated, and then the volatility difference index at the time i is calculated; the volatility difference index is also positively correlated with the sum of the differences. The implementer can set the preset number by himself.

[0081] Specifically, in one embodiment, the calculation formula of the volatility difference index is:

[0082]

[0083] in, is the volatility difference index at the time i, is the volatility index at the time i, is the volatility index of the jth moment among all moments Q1, where the moment Q1 is the moment i and its adjacent m-1 moments, is the volatility index of the first moment among all moments Q1. m can be 5.

[0084] The instructions are as follows: The bigger and The larger the value is, the greater the possibility that the fluctuation of the data at time i and the data at the adjacent m-1 times is abnormal.

[0085] In combination with the concept of the present invention, a modified embodiment is provided: In another embodiment, the calculation formula of the volatility difference index is:

[0086]

[0087] At this point, the volatility difference index at each moment is obtained.

[0088] S4: Calculate the abnormal index at each moment.

[0089] In one embodiment, the abnormal index at time i is The calculation formula is:

[0090]

[0091] The value range of j is from 1 to n. represents the function for calculating the variance, represents the volatility difference index at the time i, represents the volatility index at the time i, represents the volatility difference index of the jth moment among all moments Q2, where the moment Q2 is the moment i and its adjacent n-1 moments, is the volatility index at the jth moment, express The next volatility indicator, is the positive correlation normalization function. The “-” in this article is a minus sign, " denotes an absolute value. The implementer may set the value of n. In one embodiment, n is 5. For example, (E1, E2, E3, E4, E5, E6, ..., W80), where for E3, E3 and its adjacent 4 moments are (E1, E2, E3, E4, E5).

[0092] The explanation is as follows: In the production process of drugs, some drugs are suitable for production at lower temperatures, and some drugs are suitable for production at higher temperatures. In other words, the production of higher quality drugs has certain temperature requirements, usually requiring the temperature to be stable or the temperature to vary slightly. Specifically, many drugs are sensitive to temperature, and higher temperatures are likely to accelerate the chemical reactions of drugs, leading to degradation, failure, etc., and even produce harmful byproducts. Lower temperatures are likely to reduce the rate of chemical reactions, reduce production efficiency, and may even make the reaction impossible; and lower temperatures may change the physical state of the drug, such as changing the solubility of the drug.

[0093] Since temperature and humidity are correlated, when the humidity at a certain moment is greatly different from the humidity at multiple adjacent moments, it is highly likely that the temperature at the certain moment is greatly different from the temperature at multiple adjacent moments.

[0094] In a pharmaceutical container, when the chemical reaction is basically over, only solid drugs may remain in the pharmaceutical container. For solid drugs, when the humidity in the pharmaceutical container is too high, the drugs may absorb moisture in the air, resulting in chemical reactions such as hydrolysis and oxidation, which changes the chemical composition of the drugs, thereby reducing their efficacy or producing harmful byproducts. When the humidity in the pharmaceutical container is too low, static electricity may accumulate, which may cause the drugs to adhere, etc. Therefore, when the humidity is too high or too low, it may also have a certain impact on the quality of the drugs.

[0095] Further explanation: It represents the difference between the volatility index at the jth moment in all moments Q2 and the volatility index at the next moment.

[0096] It reflects the possibility of abnormal fluctuations in the data at the jth moment and the data at multiple adjacent moments in all moments Q2. The larger it is, the more likely the data at time i is abnormal. The reason is: The larger it is, the more likely the data at time i is "outlier data", or in other words, the greater the possibility that the data at time i is different from the adjacent data, and the greater the possibility that the data at time i suddenly increases or decreases.

[0097] The larger it is, the more likely the data at time i is “outlier data”, which means the data at time i is more likely to be abnormal.

[0098] The larger it is, the greater the possibility that the fluctuation of the data at time i and the data at the adjacent m-1 times is abnormal, the more likely the data at time i is "outlier data", and the more likely the data at time i is abnormal.

[0099] The larger it is, the greater the fluctuation of the data at time i and its adjacent times, the more likely the data at time i is “outlier data”, and the more likely the data at time i is abnormal.

[0100] In order to facilitate the understanding of "outlier data", a schematic diagram of "outlier data" is drawn here. Figure 3 Schematic diagram schematically illustrating “outlier data” according to an embodiment of the present invention. Figure 3 As shown, 301 is "outlier data" and the other data are "non-outlier data".

[0101] In one embodiment, As the index H1 of moment i, calculate the index H1 corresponding to each moment, determine the index H1 corresponding to a preset number of abnormal moments in the historical data, and the abnormal index of the abnormal moment is greater than the preset threshold. The implementer can set the preset number by himself, which can be 1. The maximum value in the maximum-minimum normalization function is the maximum value of the index H1 corresponding to each moment and the index H1 corresponding to the preset number of abnormal moments in the historical data, and the minimum value in the maximum-minimum normalization function is the minimum value of the index H1 corresponding to each moment and the index H1 corresponding to the preset number of abnormal moments in the historical data.

[0102] After the above analysis, we can know The larger it is, the more likely the data (temperature and humidity) at time i is abnormal.

[0103] In combination with the concept of the present invention, some variant embodiments are given: In another embodiment, the abnormal index at time i is The calculation formula is:

[0104] In one embodiment, the abnormal index at time i is The calculation formula is:

[0105] .

[0106] In one embodiment, the moment corresponding to the abnormal index greater than the preset threshold is taken as the abnormal moment. After each abnormal moment is obtained, for any two adjacent abnormal moments, the temperature data between the adjacent abnormal moments is replaced by the mean value of the temperature data, and the humidity data between the adjacent abnormal moments is replaced by the mean value of the humidity data, to obtain the processed data; the processed data is compressed using the run-length encoding algorithm to obtain the compressed data. For example, the collected temperature sequence is (W1, W2, W3, W4, W5, W6, ..., W80), if the moment corresponding to W2 is an abnormal moment, the moment corresponding to W5 is an abnormal moment, and there is no abnormal moment between the two abnormal moments, then the mean of W3 and W4 is calculated, and W3 and W4 are replaced by the mean.

[0107] The implementer may set the preset threshold value according to the specific implementation scenario. For example, the preset threshold value may be 0.8.

[0108] S5: Issue an alarm based on abnormal indicators.

[0109] The time corresponding to the abnormal index greater than the preset threshold is regarded as the abnormal time. , an alarm signal is issued, where L1 is the total number of abnormal moments, L2 is the total number of all moments, and K1 is the alarm threshold. When the stability of temperature and humidity data is poor, there may be problems with related equipment. An alarm signal should be issued to remind relevant personnel to handle it. For example, relevant personnel can inspect and repair related equipment to make the stability of temperature and humidity data meet the requirements.

[0110] Implementers can set the alarm threshold according to specific scenarios. For example, the alarm threshold can be 0.06.

[0111] Figure 2 FIG. 1 is a schematic diagram schematically showing a structural block diagram of a drug production control system based on the Internet of Things according to an embodiment of the present invention. Figure 2As shown, 01 is a communication bus. The present invention also provides a drug production control system based on the Internet of Things, the system includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the drug production control method based on the Internet of Things according to the present invention is implemented.

[0112] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0113] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0114] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0115] Additionally, the articles "a" and "an" as used in this disclosure and the appended claims are generally construed to mean "one or more" unless specified otherwise or clear from context to be directed to a singular form.

[0116] Where the terms "includes," "having," "having," "having," or variations thereof are used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term "comprising."

[0117] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations appearing in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as S1, S2, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that if descriptions such as "first", "second", "A1", "Q1", etc. appear in this article, their role is to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, do not have any technical meaning, and do not limit "A1", "Q1", "first" and "second" to different types. For example: the first feature of an image is the feature of the image. The role of adding "first" includes facilitating subsequent references to different objects, that is, facilitating indexing.

[0118] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A drug production control method based on the Internet of Things, characterized in that: include: Collect the temperature and humidity inside the pharmaceutical container during the drug production process; For time i: Calculate the volatility index at time i, the calculation formula is: ;in, is the temperature at the time i, is the temperature at time i-1, is the temperature at time i+1, is the humidity at the time i, is the humidity at time i-1, is the humidity at time i+1; the fluctuation index is positively correlated with the absolute value of the temperature difference data and the absolute value of the humidity difference data; The sum of the differences between the volatility index at the moment i and the volatility indexes at multiple adjacent moments is calculated, and then the volatility difference index at the moment i is calculated. The calculation formula is: ;in, is the volatility difference index at the time i, is the volatility index of the jth moment in the moment i and its adjacent m-1 moments, is the fluctuation index of the first moment among the moment i and its adjacent m-1 moments; the fluctuation difference index is positively correlated with the sum of the differences; Calculate the abnormal index at the time i : , the value range of j is from 1 to n, represents the function for calculating the variance, represents the volatility index at the time i, represents the volatility difference index of the jth moment among the moment i and its adjacent n-1 moments; express The next volatility indicator, is the positive correlation normalization function, is an absolute value; The time corresponding to the abnormal index greater than the preset threshold is regarded as the abnormal time. If the ratio of the total number of the abnormal time to the total number of all times is greater than the alarm threshold, an alarm signal is issued; It also includes: after obtaining each abnormal moment, for any two adjacent abnormal moments, replacing the temperature data between the adjacent abnormal moments with the average value of the temperature data between the adjacent abnormal moments; replacing the humidity data between the adjacent abnormal moments with the average value of the humidity data; and compressing the processed data using a run-length encoding algorithm to obtain compressed data.

2. The drug production control method based on the Internet of Things according to claim 1 is characterized in that: The calculation formula of the volatility difference indicator can also be replaced by: ； in, is the volatility difference index at the time i, It is the fluctuation index of the jth moment among the moment i and its adjacent m-1 moments.

3. The drug production control method based on the Internet of Things according to claim 1 is characterized in that: The calculation formula of the volatility indicator can also be replaced by: ； ； ； in, is the index of the temperature data at the time i, is the index of humidity data at the time i, , , , , are the temperatures at time i-2, i-1, i, i+1, and i+2 respectively, , , , , They are the humidity at time i-2, i-1, i, i+1, and i+2 respectively.

4. The drug production control method based on the Internet of Things according to claim 1 is characterized in that: The value of n is 5.

5. The drug production control system based on the Internet of Things is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the Internet of Things-based drug production control method according to any one of claims 1 to 4 is implemented.

Images