Big data self-learning intelligent analysis system for reminding verification

Abstract

The invention relates to the technical field of big data intelligent analysis, in particular to a big data self-learning intelligent analysis system for reminding verification, which comprises a shell, a storage module, an identification module, a reminding module, a data receiving module, a data processing module, an information construction module, a recording module and a data analysis module, the data analysis module is arranged to determine whether the medicine in the storage bin is matched with the reminding plan according to the quality change condition of the medicine in the storage bin after the reminding plan is determined, whether implementation of the reminding plan meets the expectation or not can be effectively determined, and therefore the analysis efficiency for the obtained quality change data is effectively improved, and meanwhile, the analysis accuracy is improved. According to the method, monitoring parameters are improved step by step in a self-learning mode, and the accuracy of analyzed data can be effectively ensured, so that the analysis efficiency for the obtained quality change data is further improved while the precision of subsequent reminding plan verification is effectively ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of big data intelligent analysis, and particularly relates to a big data self-learning intelligent analysis system for reminder verification. Background Art

[0002] According to modern pharmacological knowledge, the time and interval of taking medicine depend on the needs of the condition and the metabolic rate of the medicine in the body. Only by scientifically arranging the time of taking medicine and taking medicine at intervals can the blood drug concentration in the patient's body be maintained at an appropriate level, and the efficacy of the medicine can be normally exerted to achieve the purpose of treating and saving lives. However, it is not easy for patients to take medicine on time. Especially nowadays, people often forget to take medicine on time due to busy work or other reasons. Therefore, various medicine-taking reminder devices have been developed.

[0003] Chinese Patent Application No.: CN202310640652.0 discloses a medicine-taking reminder system and method based on big data analysis. The system includes a medicine-taking reminder management platform, a hospital data center, and a cloud database. The method includes the following steps: initializing the medicine-taking reminder system; receiving medical diagnosis information; using a disease prediction model to predict diseases; performing medicine-taking analysis based on a medical diagnosis knowledge graph; reviewing the medicine-taking reminder information, and if the review is passed, sending the medicine-taking reminder information and health advice information to the patient terminal device; retrieving the medical diagnosis information, medicine-taking reminder information, and health advice information of the target patient according to the query information, and returning them to the corresponding patient / medical staff terminal device for display.

[0004] It can be seen that although the above solution can customize the corresponding reminder plan, it cannot effectively analyze the actual implementation progress of the reminder plan, so it is impossible to determine whether the customized reminder information is effective, resulting in low analysis efficiency for the obtained data. Summary of the Invention

[0005] Therefore, the present invention provides a big data self-learning intelligent analysis system for reminder verification to overcome the problem of low analysis efficiency for the obtained data caused by the inability to determine whether the formulated reminder information is effective based on actual data in the prior art.

[0006] To achieve the above object, the present invention provides a big data self-learning intelligent analysis system for reminder verification, including:

[0007] A housing;

[0008] A storage module, which is arranged inside the housing and includes a storage bin for storing medicines;

[0009] An identification module, which is arranged at the bottom of the storage module and includes a quality detector for detecting the quality of the medicines in the storage bin;

[0010] A reminder module, which is arranged at the bottom of the storage module and is used to emit a reminder signal;

[0011] A data receiving module, which is used to receive input data;

[0012] A data processing module, which is connected to the data receiving module and is used to screen and identify the input data received by the data receiving module;

[0013] An information construction module, which is connected to the data processing module and is used to construct a reminder algorithm according to the input data processed by the data processing module;

[0014] A recording module, which is connected to the information construction module and the reminder module, is used to record time, and send a reminder instruction to the reminder module based on the marked time node of the reminder algorithm;

[0015] A data analysis module, which is connected to the identification module, the reminder module and the recording module, is used to determine whether the reminder is qualified based on the change in the quality of the drug measured by the quality detector, and, when it is determined that the reminder is unqualified, generate a corresponding processing method according to the analyzed unqualified reason, including the volume of the reminder module, the number of reminder times for a single reminder and the preset monitoring duration, wherein the preset monitoring duration is obtained through the input data.

[0016] Further, the reminder module emits a reminder at the corresponding time node, and the data analysis module is also used to determine whether the reminder is qualified according to the first-level difference, and, based on the determination result, determine the reason for the reminder being unqualified according to the change in the drug quality measured within the preset monitoring duration or the quality of the drug measured this time, wherein the first-level difference is the difference between the quality of the drug in the corresponding storage bin obtained at the current reminder moment and the quality of the drug at the previous reminder moment.

[0017] Further, the data analysis module is also used to determine the reason for the reminder being unqualified according to the time interval when it is determined that the reason for the reminder being unqualified is determined according to the change in the drug quality measured within the preset monitoring duration, including re-taking the drug in case of drug damage and taking too much medicine; when the data analysis module determines that the reason for the reminder being unqualified is taking too much medicine, it controls the reminder module to emit a signal of taking too much medicine and marks this situation as a first-level event;

[0018] Wherein, the time interval is the interval between the time node when the quality measured by the quality detector changes corresponding to the quality and the previous time node.

[0019] Further, when the data analysis module determines that the reason for the reminder being unqualified is excessive medication taking, it initially determines the reason for the reminder being unqualified based on the secondary difference, including quality detector failure, user not taking the medicine, and user taking the medicine late; when the data analysis module initially determines that the medicine is taken late, it marks this situation as a secondary event;

[0020] The secondary difference is the difference between the quality of the medicine measured at the next reminder time point and the quality of the medicine measured this time recorded.

[0021] Further, when the data analysis module determines that the reason for the reminder being unqualified is quality detector failure, it determines whether the operation status of the quality detector is qualified based on the secondary ratio,

[0022] When the data analysis module determines that the operation status of the quality detector is qualified, it determines that the reason for the reminder being unqualified is that the patient forgot to take the medicine, and the data analysis module records this situation as a tertiary event; when the data analysis module determines that the operation status of the quality detector is unqualified, it controls the reminder module to send a maintenance prompt signal;

[0023] The primary ratio is the ratio of the first preset secondary difference preset in the data analysis module to the secondary difference.

[0024] Further, when the data analysis module determines that the user has not taken the medicine at the current reminder time node, it determines whether the drug storage capacity in the storage bin is qualified based on the tertiary difference, and when it determines that the drug storage capacity in the storage bin is unqualified, it controls the reminder module to send a signal of insufficient drug quantity;

[0025] Wherein, the tertiary difference is the difference between the quality of the medicine measured at the second reminder time node and the third reminder time node after the current time point.

[0026] Further, when the data analysis module completes the marking of each level of events, it counts the number of each level of events and generates corresponding processing methods according to the proportion of each level of events. The processing methods include: adjusting the preset monitoring duration to the corresponding value, and adjusting the volume of the reminder module to the corresponding value.

[0027] Further, when the data analysis module determines to adjust the preset monitoring duration to the corresponding value, it records the difference between the proportion of the secondary events and the preset secondary proportion preset in the analysis module as the quaternary difference, and sets several adjustment methods for the preset monitoring duration according to the quaternary difference, and the adjustment ranges of each adjustment method for the preset monitoring duration are all different.

[0028] Further, when the data analysis module determines to adjust the volume of the reminder module to the corresponding value, it records the difference between the proportion of the tertiary event and the preset tertiary proportion in the data analysis module as the fifth-level difference, and sets several adjustment methods for the volume of the reminder module according to the fifth-level difference, and the adjustment ranges of the volume for each adjustment method are different.

[0029] Further, after the data analysis module completes the adjustment of the volume of the reminder module, it sets several correction methods for the reminder times of a single reminder according to the adjusted volume of the reminder module, and the correction ranges of the reminder times for each correction method are different.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows. After determining the reminder plan, the present invention sets a data analysis module to determine whether the drugs in the storage bin match the reminder plan according to the quality change of the drugs in the storage bin. By analyzing the acquired data based on the determination benchmark determined by big data, it can effectively determine whether the implementation of the reminder plan meets the expectations, thereby effectively improving the analysis efficiency of the acquired quality change data. At the same time, when the data analysis module determines a mismatch, it can also determine the corresponding reason and generate a corresponding processing method based on the corresponding reason. By using a self-learning method to gradually improve the monitoring parameters, it can effectively ensure the accuracy of the analyzed data, thereby effectively ensuring the accuracy of the subsequent reminder plan verification while further improving the analysis efficiency of the acquired quality change data.

[0031] Further, the present invention uses the data analysis module to take the collected drug quality change amount as the reference data for analysis, and determines the reason for the reminder failure by the time interval between the time nodes when the quality of the drug changes and the quality inspection. It can effectively improve the detection accuracy of the reminder plan set in the system of the present invention, thereby effectively ensuring the accuracy of the analyzed data while effectively improving the accuracy of the subsequent reminder plan verification and further improving the analysis efficiency of the acquired quality change data.

[0032] Further, in the present invention, the data analysis module determines the reason for the reminder failure according to the difference between the drug quality measured at the next reminder time point and the drug quality measured this time and recorded. By using the time interval to determine the reason for the unqualified quality change, it can effectively avoid the situation that the detection accuracy of the subsequent reminder plan is deviated due to drug damage or excessive single-dose drug taking. While further ensuring the accuracy of the analyzed data, it further improves the accuracy of the subsequent reminder plan verification and further improves the analysis efficiency of the acquired quality change data.

[0033] Further, the present invention also determines whether the user delays taking medicine by the difference between the quality of the medicine measured at the next reminder time point and the quality of the medicine measured this time and recorded. By accurately determining the reason, the accuracy of verifying the subsequent reminder plan can be further improved, and the analysis efficiency of the obtained quality change data can be further improved.

[0034] Further, the present invention also determines whether the quality detector fails by the ratio of a first preset secondary difference preset in the data analysis module to the secondary difference. By verifying the quality detector, the situation of misjudgment caused by incorrect quality detection can be effectively avoided. While further ensuring the accuracy of the analyzed data, the accuracy of verifying the subsequent reminder plan is further improved, and the analysis efficiency of the obtained quality change data is further improved.

[0035] Further, the present invention also classifies and marks various events, and generates corresponding processing methods by counting the proportion of the number of events at each level within a preset time interval. It can effectively eliminate the problems that occur in the actual implementation of the reminder plan in a step-by-step improvement manner, effectively improve the detection accuracy of the reminder plan set in the system of the present invention, thereby effectively ensuring the accuracy of the analyzed data while effectively improving the accuracy of verifying the subsequent reminder plan, and further improving the analysis efficiency of the obtained quality change data.

[0036] Further, the present invention can also specifically improve the reminder volume, preset monitoring duration or reminder times according to the corresponding values. By adjusting the corresponding parameters to the corresponding values based on the determined reasons, the problems that occur in the actual implementation of the reminder plan can be gradually eliminated. While further improving the detection accuracy of the reminder plan set in the system of the present invention, the accuracy of the analyzed data is further ensured, and while further improving the accuracy of verifying the subsequent reminder plan, the analysis efficiency of the obtained quality change data is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is the structural block diagram of the big data self-learning intelligent analysis system for reminder verification of the present invention;

[0038] Figure 2 is the flowchart for determining whether the reminder is qualified in the present invention;

[0039] Figure 3 is the flowchart for determining the reasons for the unqualified reminder in the present invention;

[0040] Figure 4 is the flowchart for determining whether the operation status of the quality detector is qualified in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] To make the objectives and advantages of the present invention more clearly understood, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] It should be noted that the data in this embodiment are all obtained through comprehensive analysis and evaluation of the historical data in the 6 months before this determination by the system described in the present invention and the corresponding historical determination results. The system described in the present invention determines the numerical values of various preset parameter standards for this determination based on the comprehensive evaluation value of 37,393 retrieval results accumulated in the previous three months before this detection. Those skilled in the art can understand that the determination method of the system described in the present invention for a single above-mentioned parameter can be to select the value with the highest proportion according to the data distribution as the preset standard parameter, use weighted summation to take the obtained value as the preset standard parameter, substitute each historical data into a specific formula and take the value obtained by using this formula as the preset standard parameter, or other selection methods, as long as it satisfies that the system described in the present invention can clearly define different specific situations in a single determination process through the obtained values.

[0043] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0044] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0045] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0046] Please refer to Figure 1 as shown, which is a structural block diagram of the big data self-learning intelligent analysis system for reminder verification of the present invention.

[0047] The big data self-learning intelligent analysis system for reminder verification in the embodiments of the present invention includes:

[0048] A housing (not shown in the figure);

[0049] A storage module, which is arranged inside the housing and includes a storage bin for storing drugs;

[0050] An identification module, which is arranged at the bottom of the storage module and includes a quality detector for detecting the quality of drugs in the storage bin;

[0051] A reminder module, which is arranged at the bottom of the storage module and is used to send a reminder signal;

[0052] A data receiving module, which is used to receive input data;

[0053] A data processing module, which is connected to the data receiving module and is used to screen and identify the input data received by the data receiving module;

[0054] An information construction module, which is connected to the data processing module and is used to construct a reminder algorithm according to the input data processed by the data processing module;

[0055] A recording module, which is connected to the information construction module and the reminder module, is used to record time, and send a reminder instruction to the reminder module based on the marked time node of the reminder algorithm;

[0056] A data analysis module, which is connected to the identification module, the reminder module, and the recording module, is used to determine whether to send a reminder based on the instruction issued by the recording module and the current time, determine whether the reminder is qualified according to the change of the quality of the drug measured by the quality detector, and analyze the reason for unqualified when determining that the reminder is unqualified.

[0057] When the system of the present invention runs, data corresponding to the reminder plan information is input through the data receiving module, the data processing module screens and identifies the received data, the information construction module constructs a reminder algorithm for representing the reminder plan based on the identified data. After the construction of the reminder algorithm is completed, the identification module detects the quality of drugs in each storage bin of the storage module through the quality detector at the corresponding time node. The data analysis module controls the recording module to send a reminder instruction to the reminder module according to the reminder algorithm at the corresponding time node. The data analysis module determines whether the current reminder meets the expectation based on the drug quality obtained by the identification module when the recording module sends the instruction, determines whether the reminder is qualified based on whether it meets the expectation, and analyzes the reason for unqualified when determining that the reminder is unqualified; wherein, the data analysis module determines that the reminder meets the expectation and the reminder is qualified when determining that the corresponding drug quality decreases by the corresponding amount when the reminder is issued, or determines that the reminder does not meet the expectation and the reminder is unqualified when determining that the corresponding drug quality does not decrease by the corresponding amount when the reminder is issued.

[0058] In the embodiment of the present invention, the operation of the reminder module includes: initialization, data input, data processing, and obtaining the pre-execution alarm value.

[0059] Ⅰ) Initialization: Define n groups of alarm variables. Each group of variables consists of an hour variable and a minute variable, and their initial values are all zero. Each group of alarms also stores the drug information corresponding to that time, which is not given here. The alarm variable structure is as follows.

[0060] A i =(H i , M i ), i = 0, 1, 2,..., n - 1

[0061] Among them, A i is the i-th group of alarm variables, H i is the hour variable in this group of alarm variables, and M i is the minute variable in this group of alarm variables.

[0062] Ⅱ) Data input: The user inputs the information of various drugs through the touch screen, and assigns the medication time to the corresponding hour variable H i and minute variable M i . The unassigned variables remain at the initial value of zero. Considering that when the values of both the hour variable and the minute variable are 0, the corresponding time is 0:00 in the morning, and at this time the human body should be in the rest stage and will not take medicine during this period. When the alarm responds here, no event is processed.

[0063] Ⅲ) Data processing: Re-sort the n groups of variables in ascending order to obtain n groups of new alarm variables, and their structure is as follows.

[0064] A′ i =(H′ i , M′ i ), i = 0, 1, 2,..., n - 1

[0065] Among them, A′ i is the i-th group of alarm variables after re-sorting, H′ i is the hour variable in this group of alarm variables, and M′ i is the minute variable in this group of alarm variables.

[0066] Ⅳ) Obtain the pre-execution alarm value. Compare the RTC real-time system time with each group of sorted alarm variables to obtain the alarm time to be executed.

[0067] K n+1 =(A′0, A′1,..., A′ j-1 , C, A′ j ,..., A′ n-1 ) C=(C h, C i )

[0068] Wherein, C is the system time, C h is its hour value, C i is its minute value, then A' j is the alarm value to be executed. After triggering the alarm, repeat the above steps to obtain the next set of alarm values to be executed.

[0069] Please refer to Figure 2 shown, which is a flowchart for determining whether a reminder is qualified.

[0070] Specifically, the reminder module issues a reminder at the corresponding time node. The data analysis module calculates the difference between the quality of the drug in the storage bin corresponding to the current reminder time of the quality detector and the quality of the drug at the previous reminder time, and records this difference as the first-level difference. The data analysis module determines the determination method for whether the reminder is qualified according to the first-level difference, where:

[0071] The first determination method is that the data analysis module determines that the reminder is unqualified and determines the reason for its unqualified according to the change in the quality of the drug measured within the preset monitoring duration; the first determination method satisfies that the first-level difference is greater than or equal to the first preset first-level difference in the data analysis module;

[0072] The second determination method is that the data analysis module determines that the reminder is qualified and marks it as a qualified event; the second determination method satisfies that the first-level difference is less than the first preset first-level difference and greater than or equal to the second preset first-level difference in the data analysis module;

[0073] The third determination method is that the data analysis module determines that the reminder is unqualified and preliminarily determines that the drug has not been taken, and records the quality of the drug measured this time; the third determination method satisfies that the first-level difference is less than the second preset first-level difference.

[0074] In the embodiment of the present invention, the first preset first-level difference is 800 mg, and the second preset first-level difference is 100 mg.

[0075] In the present invention, the data analysis module determines whether the medication reminder is qualified according to the change in the quality of the drug measured by the quality detector, and analyzes the reason for its unqualified according to the change in the quality of the drug when determining its unqualified, improving the control accuracy of the patient's medication situation and the control accuracy of the patient's treatment process.

[0076] Please refer to Figure 3 shown, which is a flowchart for determining the reason for the unqualified reminder.

[0077] Specifically, the data analysis module marks the time node when the quality measured by the quality detector changes under the first determination method, and calculates the time interval between this time node and the time node when the previous quality change occurred. The data analysis module determines the cause determination method for reminding of unqualified according to this time interval, including:

[0078] The first cause determination method is that the data analysis module determines that the reason for the reminder of unqualified is drug damage, and re - takes the drug, marking it as a qualified event; the first cause determination method satisfies that the time interval is greater than or equal to the preset time interval in the data analysis module;

[0079] The second cause determination method is that the data analysis module determines that the reason for the reminder of unqualified is taking too much medicine, and controls the reminder module to send a signal of taking too much medicine, and marks this situation as a first - level event; the second cause determination method satisfies that the time interval is less than the preset time interval.

[0080] In the embodiment of the present invention, the preset quantity is 4, and the preset time interval is 3.5h.

[0081] In the present invention, the data analysis module determines the reason for the reminder of unqualified according to the time interval of quality inspection at the time node when the quality of the drug changes, and when the time interval is too large, analyzes and determines that the reason for the reminder of unqualified is drug dropping, and re - takes the drug to avoid misjudgment caused by drug damage during the medication process.

[0082] Specifically, the data analysis module records the quality of the drug measured this time under the third determination method, and records the difference between the quality of the drug measured this time and the quality of the drug measured at the next reminder time node as the second - level difference. The data analysis module determines the preliminary determination method for the cause of the reminder of unqualified according to the second - level difference, where:

[0083] The first cause preliminary determination method is that the data analysis module preliminarily determines that the reason for the reminder of unqualified is a quality detector failure, and makes a secondary determination on whether the quality detector fails according to the second - level difference; the first cause preliminary determination method satisfies that the second - level difference is greater than or equal to the first preset second - level difference in the data analysis module;

[0084] The second cause preliminary determination method is that the data analysis module preliminarily determines delayed medication and marks this situation as a second - level event; the second cause preliminary determination method satisfies that the second - level difference is less than the first preset second - level difference and greater than or equal to the second preset second - level difference in the data analysis module;

[0085] The preliminary determination method for the third reason is that the data analysis module preliminarily determines that the medicine has not been taken at the current reminder time node; the preliminary determination method for the third reason satisfies that the secondary difference is less than the second preset secondary difference.

[0086] In the embodiment of the present invention, the first preset secondary difference is 900 mg, and the second preset secondary difference is 400 mg.

[0087] In the present invention, the data analysis module determines the reason for the unqualified reminder according to the difference between the quality of the medicine measured this time and the quality of the medicine measured at the next reminder time point recorded, and determines that the quality detector is faulty when the difference is greater than the preset value, avoiding misjudgment caused by detector failure and improving the accuracy of the analysis result.

[0088] Please refer to Figure 4 as shown, which is a flowchart for determining whether the operation status of the quality detector is qualified.

[0089] Specifically, in the first reason preliminary determination method, the data analysis module records the ratio of the first preset secondary difference to the secondary difference as the primary ratio, and determines whether the operation status of the quality detector is qualified according to the secondary ratio, where:

[0090] The first qualified determination method is that the data analysis module determines that the operation status of the quality detector is qualified, and determines that the reason for the unqualified reminder is that the patient forgot to take the medicine. The data analysis module records this situation as a third-level event; the first qualified determination method satisfies that the secondary ratio is less than or equal to the preset secondary ratio preset in the data analysis module;

[0091] The second qualified determination method is that the data analysis module determines that the operation status of the quality detector is unqualified, and controls the reminder module to send a maintenance reminder signal; the second qualified determination method satisfies that the secondary ratio is greater than the preset secondary ratio.

[0092] In the embodiment of the present invention, the preset secondary ratio is 0.75, and the primary ratio is the first preset secondary difference divided by the secondary difference.

[0093] In the present invention, the greater the difference between the quality of the medicine measured this time and the quality of the medicine measured at the next reminder time point, the smaller the ratio of the difference to the first preset secondary difference. The quality detector may cause the detection reading to be too large due to insufficient power or failure to clear the reading during detection. Whether the detection reading of the quality detector is qualified is determined according to this ratio, improving the control accuracy of the analysis process and further improving the control accuracy of the patient's medication situation.

[0094] Specifically, in the third preliminary determination method of the cause, the data analysis module records the difference in the quality of the drug measured at the second reminder time node and the third reminder time node after the current time point as the third-level difference, and determines whether the drug storage amount in the storage bin is qualified according to the third-level difference, where:

[0095] The first drug storage amount determination method is that the data analysis module determines that the drug storage amount in the storage bin is qualified and determines that the drug has not been taken, and marks this event as a third-level event; the first drug storage amount determination method satisfies that the third-level difference is greater than or equal to the preset third-level difference preset in the data analysis module;

[0096] The second drug storage amount determination method is that the data analysis module determines that the drug storage amount in the storage bin is unqualified, controls the reminder module to send a signal of insufficient drug amount, and marks this event as a third-level event; the second drug storage amount determination method satisfies that the third-level difference is less than the preset third-level difference.

[0097] In the embodiment of the present invention, the preset third-level difference is 300 mg, the second reminder time node is the reminder time node adjacent to the current time node after the current time point, and the third reminder time node is the reminder time node adjacent to the second reminder time node after the second reminder time node.

[0098] In the present invention, the data analysis module determines whether the drug storage amount is qualified according to the difference in the quality of the drug measured at the second reminder time node and the third reminder time node after the current time point, avoiding misjudgment caused by insufficient drugs and improving the analysis accuracy.

[0099] Specifically, when the data analysis module finishes marking each level of events, it counts the number of each level of events and generates corresponding processing methods according to the proportion of each level of events, where:

[0100] The first processing method is that the data analysis module determines to adjust the preset monitoring duration to the corresponding value; the first processing method satisfies that the proportion of the second-level events is greater than or equal to the preset second-level proportion preset in the data analysis module;

[0101] The second processing method is that the data analysis module determines to adjust the volume of the reminder module to the corresponding value; the second processing method satisfies that the proportion of the third-level events is greater than or equal to the preset third-level proportion preset in the data analysis module.

[0102] In the embodiment of the present invention, the preset second-level proportion is 0.35, and the preset third-level proportion is 0.4.

[0103] Specifically, under the first processing mode, the data analysis module records the difference between the proportion of the secondary events and the preset secondary proportion as the fourth-level difference, and determines the adjustment mode for the preset monitoring duration according to the fourth-level difference, where:

[0104] The first adjustment mode is that the data analysis module selects the first adjustment coefficient β1 to adjust the preset monitoring duration T to the corresponding value, and sets the adjusted preset monitoring duration T' = β1 × T0, where T0 is the initial preset monitoring duration before adjustment; the first adjustment mode satisfies that the fourth-level difference is less than or equal to the preset fourth-level difference preset in the data analysis module;

[0105] The second adjustment mode is that the data analysis module selects the second adjustment coefficient β2 to adjust the preset monitoring duration T to the corresponding value, and sets the adjusted preset monitoring duration T' = β2 × T0; the second adjustment mode satisfies that the fourth-level difference is greater than the preset fourth-level difference.

[0106] In the embodiment of the present invention, the first adjustment coefficient β1 is 1.5, the second adjustment coefficient β2 is 2, and the preset fourth-level difference is 0.065.

[0107] Specifically, under the second processing mode, the data analysis module records the difference between the proportion of the tertiary events and the preset tertiary proportion as the fifth-level difference, and determines the volume adjustment mode for the volume of the reminder module according to the fifth-level difference, where:

[0108] The first volume adjustment mode is that the data analysis module selects the first volume adjustment coefficient α1 to adjust the volume D of the reminder module to the corresponding value, and sets the adjusted volume D' = α1 × D0, where D0 is the initial volume before adjustment; the first volume adjustment mode satisfies that the fifth-level difference is less than or equal to the preset fifth-level difference preset in the data analysis module;

[0109] The second volume adjustment mode is that the data analysis module selects the second volume adjustment coefficient α2 to adjust the volume D of the reminder module to the corresponding value, and sets the adjusted volume D' = α2 × D0; the second volume adjustment mode satisfies that the fifth-level difference is greater than the preset fifth-level difference.

[0110] In the embodiment of the present invention, the first volume adjustment coefficient α1 is 1.5, the second volume adjustment coefficient α2 is 1.4, the preset fifth-level difference is 0.02, and the initial volume is 30%.

[0111] Specifically, under the first preset condition, the data analysis module determines the correction mode for the number of reminders for a single reminder according to the adjusted volume of the reminder module, where:

[0112] The first correction method is that the data analysis module selects a first correction coefficient γ1 to correct the reminder times C for a single reminder to a corresponding value, and sets the corrected reminder times C' = γ1 × C0, where C0 is the initial reminder times before correction; the first correction method satisfies that the volume of the reminder module after adjustment is less than or equal to the preset volume in the data analysis module;

[0113] The second correction method is that the data analysis module selects a second correction coefficient γ2 to correct the reminder times C for a single reminder to a corresponding value, and sets the corrected reminder times C' = γ2 × C0; the second correction method satisfies that the volume of the reminder module after adjustment is greater than the preset volume in the data analysis module;

[0114] The first preset condition is that the data analysis module completes the adjustment of the volume of the reminder module.

[0115] In the embodiment of the present invention, the first correction coefficient γ1 is 1, the second correction coefficient γ2 is 0.5, the preset volume is 50%, and the initial reminder times is 2 times.

[0116] Embodiment 1

[0117] Using the system of the present invention to monitor the medication reminder, input data: the single-dose quality is 400 mg, the medication interval is 4 h, the reminder times are 9:00, 13:00, 17:00, 24:00, and the preset monitoring duration is 39 h (9:00 on the first day - 24:00 on the second day),

[0118] The difference between the quality at 13:00 on the first day and the quality at the previous reminder time 9:00 on the first day is 500 mg. It is determined that the reminder is unqualified. According to the quality change of the medicine, the reason for its unqualified is determined. The time node when the quality measured by the quality detector changes is 11:00 on the first day, and the time interval between it and the previous quality change time node (9:00 on the first day) is 2 h, which is less than the preset time interval, so a signal of taking too much medicine is sent and it is recorded as a first-level event;

[0119] The difference between the quality at 17:00 on the first day and the quality at the previous reminder time 13:00 on the first day is 0 mg, which meets the third determination method. It is initially determined that the medicine has not been taken. The difference between the quality of the medicine measured this time and the quality of the medicine measured at the next reminder time node (24:00 on the first day) is 400 mg. It is initially determined that the medicine taking is delayed and it is marked as a second-level event;

[0120] The difference between the quality at 24:00 on the first day and the quality at the previous reminder time 17:00 on the first day is 400 mg, which meets the second determination method and is marked as a qualified event;

[0121] The difference in quality between 9:00 on the second day and 24:00 on the first day at the previous reminder time is 0 mg, which meets the third determination method. It is preliminarily determined that the drug has not been taken. The difference in the quality of the drug measured this time and the quality of the drug measured at the next reminder time point (13:00 on the second day) is 800 mg. It is preliminarily determined that the drug taking is delayed, and this situation is marked as a secondary event;

[0122] The difference in quality between 13:00 on the second day and 9:00 on the second day at the previous reminder time is 800 mg, which meets the first determination method. It is determined that the reminder is unqualified, and the reason for its unqualified is determined according to the change in the quality of the drug measured within the preset monitoring duration. The time point when the quality corresponding to the quality measured by the quality detector changes is 13:00 on the second day, and the time interval between it and the previous time point when the quality changed (19:00 on the first day) is 18 h, which is greater than the preset time interval. The reason for determining that the reminder is unqualified is drug damage. Take the medicine again and mark it as a qualified event;

[0123] The difference in quality between 17:00 on the second day and 13:00 on the second day at the previous reminder time is 0 mg, which meets the third determination method. It is preliminarily determined that the drug has not been taken. The difference in the quality of the drug measured this time and the quality of the drug measured at the next reminder time point (24:00 on the second day) is 700 mg. It is preliminarily determined that the drug taking is delayed, and this situation is marked as a secondary event;

[0124] The difference in quality between 24:00 on the second day and 17:00 on the second day at the previous reminder time is 700 mg. It is determined that the reminder is qualified and marked as a qualified event;

[0125] The marking results are as follows:

[0126]

[0127]

[0128] The above 8 times of drug taking situations are statistically as follows:

[0129] Mark Qualified event Level 1 event Level 2 event Level 3 event Quantity 4 1 3 0

[0130] After statistics, the proportion of secondary events is 0.375, which is greater than the preset secondary proportion, meeting the first processing method. The difference between the proportion of secondary events and the preset secondary proportion is 0.075, which is greater than the preset fourth-level difference. The second adjustment coefficient is selected to adjust the preset monitoring duration to eliminate the misjudgment caused by too short monitoring duration. The adjusted preset monitoring duration is 78 h. From the above data, it can be concluded that the reason for the non-compliance of this detection is affected by too little analysis data. After eliminating the influence, the analysis of the first aid kit is normal.

[0131] Embodiment 2

[0132] Using the system of the present invention to monitor the medication reminder, the input data: the mass of a single dose is 400 mg, the dosing interval is 4 h, the reminder times are 9:00, 13:00, 17:00, 24:00, and the preset monitoring duration is 28 h (from 9:00 on the first day to 13:00 on the second day).

[0133] The difference between the mass at 13:00 on the first day and the mass at the previous reminder time 9:00 on the first day is 0 mg, which meets the third determination method. The difference between the mass of the drug measured this time and the mass of the drug measured at the next reminder time node is 0 mg, which meets the third preliminary determination method for the reason. It is preliminarily determined that no medication was taken at the current reminder time node. The difference between the mass of the drug measured at the second reminder time node (17:00 on the first day) and the mass of the drug measured at the third reminder time node (24:00 on the first day) after the current time point is 400 mg. It is determined that no medication was taken, and this event is marked as a third-level event;

[0134] The difference between the mass at 17:00 on the first day and the mass at the previous reminder time 13:00 on the first day is 0 mg, which meets the third determination method. It is preliminarily determined that no drug was taken. The difference between the mass of the drug measured this time and the mass of the drug measured at the next reminder time node (24:00 on the first day) is 400 mg. It is preliminarily determined that the medication was taken late, and it is marked as a second-level event;

[0135] The difference between the mass at 24:00 on the first day and the mass at the previous reminder time 17:00 on the first day is 400 mg, which meets the second determination method, and it is marked as a qualified event;

[0136] The difference between the mass at 9:00 on the second day and the mass at the previous reminder time 24:00 on the first day is 0 mg, which meets the third determination method. It is preliminarily determined that no drug was taken. The difference between the mass of the drug measured this time and the mass of the drug measured at the next reminder time node (13:00 on the second day) is 1000 mg, which meets the first preliminary determination method for the reason. The ratio of the first preset secondary difference to the secondary difference is 0.9. It is determined that the operation status of the mass detector is qualified, and it is determined that the reason for the unqualified reminder is that the patient forgot to take the medicine. This situation is marked as a third-level event;

[0137] The marking results are as follows:

[0138]

[0139] The above 5 medication situations are statistically as follows:

[0140] Mark Qualified event Level 1 event Level 2 event Level 3 event Quantity 2 0 1 2

[0141] After statistics, the proportion of level-three events is 0.4, which is equal to the preset proportion of level three, meeting the second processing method. The difference between the proportion of level-three events and the preset proportion of level three is 0, which is less than the preset difference of level five. The first volume adjustment coefficient is selected to adjust the volume of the reminder module to eliminate the situation where the reminder is unqualified due to too low volume. The adjusted volume of the reminder module is 42%, which is less than the preset volume, and the reminder frequency is not adjusted. From the above data, it can be concluded that the reason for the unqualified detection this time is affected by the too small initial volume, and the analysis is normal after eliminating the influence.

[0142] Embodiment 3

[0143] Using the system of the present invention to monitor the medication reminder, input data: the quality of a single dose is 400 mg, the dosing interval is 4 h, and the reminder times are 9:00, 13:00, 17:00, 24:00. The preset monitoring duration is 15 h (9:00 on the second day - 24:00 on the second day).

[0144] The difference between the quality at 13:00 on the first day and the quality at the previous reminder time 9:00 on the first day is 500 mg. It is determined that the reminder is unqualified. According to the change in the quality of the drug, the reason for its unqualified is determined. The time node when the quality corresponding to the quality measured by the quality detector changes is 11:00 on the first day, and the time interval between it and the previous quality change time node (9:00 on the first day) is 2 h, which is less than the preset time interval. A signal of taking too much medicine is sent and recorded as a level-one event.

[0145] The difference between the quality at 17:00 on the first day and the quality at the previous reminder time 13:00 on the first day is 0 mg, meeting the third determination method. It is initially determined that the drug has not been taken. The difference between the quality of the drug measured this time and the quality of the drug measured at the next reminder time node (24:00 on the first day) is 400 mg. It is initially determined that the medication is delayed and marked as a level-two event.

[0146] The difference between the quality at 24:00 on the first day and the quality at the previous reminder time 17:00 on the first day is 400 mg, meeting the second determination method, and it is marked as a qualified event.

[0147] The difference between the quality at 9:00 on the second day and the quality at the previous reminder time 24:00 on the first day is 0 mg, meeting the third determination method. It is initially determined that the drug has not been taken. The difference between the quality of the drug measured this time and the quality of the drug measured at the next reminder time node (13:00 on the second day) is 800 mg. It is initially determined that the medication is delayed and this situation is marked as a level-two event.

[0148] The difference between the quality at 13:00 on the second day and the quality at 9:00 on the second day at the previous reminder time is 800 mg, which meets the first determination method. It is determined that the reminder is unqualified, and the reason for its unqualified is determined according to the change of the drug quality measured within the preset monitoring duration. The time node when the quality corresponding to the quality measured by the quality detector changes is 13:00 on the second day, and the time interval between it and the previous time node when the quality changed (19:00 on the first day) is 18 h, which is greater than the preset time interval. The reason for determining the reminder as unqualified is drug damage. Take the medicine again and mark it as a qualified event;

[0149] The difference between the quality at 17:00 on the second day and the quality at 13:00 on the second day at the previous reminder time is 0 mg, which meets the third determination method. It is initially determined that the drug has not been taken. The difference between the quality of the drug measured this time and the quality of the drug measured at the next reminder time node (24:00 on the second day) is 700 mg. It is initially determined that the drug taking is delayed, and this situation is marked as a secondary event;

[0150] The difference between the quality at 24:00 on the second day and the quality at 17:00 on the second day at the previous reminder time is 700 mg. It is determined that the reminder is qualified and marked as a qualified event;

[0151] The marking results are as follows:

[0152]

[0153]

[0154] The statistics of the 4 times of drug taking are as follows:

[0155] Mark Qualified event Level 1 event Level 2 event Level 3 event Quantity 2 0 2 0

[0156] After statistics, the proportion of secondary events is 0.5, which is greater than the preset secondary proportion, meeting the first processing method. The difference between the proportion of secondary events and the preset secondary proportion is 0.15, which is greater than the preset fourth-level difference. The second adjustment coefficient is selected to adjust the preset monitoring duration to eliminate the misjudgment caused by too short monitoring duration. The adjusted preset monitoring duration is 30 h. From the above data, it can be concluded that the reason for the non-compliance of this detection is affected by too little analysis data. After eliminating the influence, the analysis of the first aid kit is normal.

[0157] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

[0158] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention; for those skilled in the art, various modifications and variations can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A big data self-learning intelligent analysis system for reminder verification, characterized in that, Comprising: A housing; A storage module disposed inside the housing, including a storage bin for storing drugs; An identification module disposed at the bottom of the storage module, including a quality detector for detecting the quality of the drugs in the storage bin; A reminder module disposed at the bottom of the storage module for emitting a reminder signal; A data receiving module for receiving input data; A data processing module connected to the data receiving module for screening and identifying the input data received by the data receiving module; An information construction module connected to the data processing module for constructing a reminder algorithm based on the input data processed by the data processing module; A recording module connected to the information construction module and the reminder module for recording time and sending a reminder instruction to the reminder module based on the marked time nodes of the reminder algorithm; A data analysis module connected to the identification module, the reminder module and the recording module for determining whether a reminder is qualified based on the change in the quality of the drugs measured by the quality detector, and, when determining that the reminder is unqualified, generating a corresponding processing method according to the analyzed unqualified reason, including the volume of the reminder module, the number of reminder times for a single reminder and a preset monitoring duration, wherein the preset monitoring duration is obtained through the input data.

2. The big data self-learning intelligent analysis system for reminder verification according to claim 1, characterized in that The reminder module emits a reminder at the corresponding time node, and the data analysis module is further used for determining whether the reminder is qualified according to a first-level difference, and, based on the determination result, determining the reason for the reminder being unqualified according to the change in the drug quality measured within the preset monitoring duration or the quality of the drug measured this time, wherein the first-level difference is the difference between the quality of the drug in the corresponding storage bin obtained at the current reminder moment and the quality of the drug at the previous reminder moment.

3. The big data self-learning intelligent analysis system for reminder verification according to claim 2, characterized in that, The data analysis module is further used for determining the reason for the reminder being unqualified according to a time interval when determining that the reason for the reminder being unqualified is determined according to the change in the drug quality measured within the preset monitoring duration, including re-taking drugs in case of drug damage and taking too many drugs; the data analysis module controls the reminder module to emit a signal of taking too many drugs when determining that the reason for the reminder being unqualified is taking too many drugs, and marks this situation as a first-level event; Wherein, the time interval is the interval between the time node when the quality measured by the quality detector changes corresponding to the quality and the previous time node.

4. The big data self-learning intelligent analysis system for reminder verification according to claim 3, wherein The data analysis module is further used for initially determining the reason for the reminder being unqualified according to a second-level difference when determining that the reason for the reminder being unqualified is taking too many drugs, including quality detector failure, user not taking drugs and user delaying taking drugs; The data analysis module marks this situation as a second-level event when initially determining delayed drug taking; The second-level difference is the difference between the quality of the drug measured at the next reminder time point and the quality of the drug measured this time recorded.

5. The big data self-learning intelligent analysis system for reminder verification according to claim 4, wherein The data analysis module is further used for determining whether the operation status of the quality detector is qualified according to a second-level ratio when determining that the reason for the reminder being unqualified is quality detector failure, When the data analysis module determines that the operation status of the quality detector is qualified, it determines that the reason for the unqualified reminder is that the patient forgets to take medicine, and the data analysis module records this situation as a third-level event; when the data analysis module determines that the operation status of the quality detector is unqualified, it controls the reminder module to send a maintenance prompt signal. The first ratio is the ratio of the first preset second difference preset in the data analysis module to the second difference.

6. The big data self-learning intelligent analysis system for reminder verification according to claim 5, characterized in that The data analysis module is further configured to determine whether the drug storage amount in the storage bin is qualified according to the third difference when it determines that the user has not taken medicine at the current reminder time node, and control the reminder module to send a drug shortage signal when it determines that the drug storage amount in the storage bin is unqualified. Wherein, the third difference is the difference in the quality of the drug measured at the second reminder time node and the third reminder time node after the current time point.

7. The big data self-learning intelligent analysis system for reminder verification according to claim 6, characterized in that, When the data analysis module completes the marking of each level of events, it counts the number of each level of events and generates corresponding processing methods according to the proportion of each level of events. The processing methods include: adjusting the preset monitoring duration to the corresponding value, and adjusting the volume of the reminder module to the corresponding value.

8. The big data self-learning intelligent analysis system for reminder verification according to claim 7, wherein, When the data analysis module determines to adjust the preset monitoring duration to the corresponding value, it records the difference between the proportion of the second-level events and the preset second proportion preset in the analysis module as the fourth difference, and sets several adjustment methods for the preset monitoring duration according to the fourth difference, and the adjustment ranges of each adjustment method for the preset monitoring duration are all different.

9. The big data self-learning intelligent analysis system for reminder verification according to claim 8, wherein When the data analysis module determines to adjust the volume of the reminder module to the corresponding value, it records the difference between the proportion of the third-level events and the preset third proportion preset in the data analysis module as the fifth difference, and sets several adjustment methods for the volume of the reminder module according to the fifth difference, and the adjustment ranges of each adjustment method for the volume are all different.

10. The big data self-learning intelligent analysis system for reminder verification according to claim 9, characterized in that, When the data analysis module completes the adjustment of the volume of the reminder module, it sets several correction methods for the number of reminder times for each single reminder according to the adjusted volume of the reminder module, and the correction ranges of each correction method for the reminder times are all different.

Images