A positron drug storage management system and method based on artificial intelligence

Abstract

The present invention discloses a positron drug storage management system and method based on artificial intelligence, which belongs to the field of data analysis technology. The system includes a personnel information recording module, an appointment management module, a demand intelligent prediction module, a risk alarm module and a storage quantity display module; the personnel information recording module is used to verify the identity information of the technician and collect the usage data of the technician's positron drug; the appointment management module is used to collect the patient's online appointment information data; the demand intelligent prediction module is used to monitor the storage volume change of the positron drug and predict the number of days of use of the current storage volume of the positron drug; the risk alarm module is used to send a goods shortage alarm to the management personnel; the storage volume display module is used to provide a human-computer interaction interface for the management personnel, and digitally represent the storage volume of the positron drug and the predicted number of days of use of the current storage volume of the positron drug.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a positron drug storage management system and method based on artificial intelligence. Background Art

[0002] Positron drugs refer to drugs containing radioactive isotopes that emit positrons. These drugs are mainly used in positron emission tomography imaging technology. By detecting the photons produced by the annihilation of positrons and surrounding negative electrons, the PET scanner can generate three-dimensional images of the inside of the body, helping doctors diagnose diseases and evaluate the efficacy of treatment.

[0003] The storage management of positron drugs requires accurate forecasting of demand to avoid surpluses and shortages. However, in the configuration of positron drugs, due to the short half-life of their radioactive nuclides, the preparation process must be rapid and must be strictly carried out in accordance with the operating procedures. Therefore, in actual operations, technicians often make operational errors and irregular behaviors during configuration, resulting in drug waste and shortages of positron drugs. The storage supervision of positron drugs is not yet perfect, and it is difficult to analyze the use of positron drugs through existing data. Summary of the invention

[0004] The purpose of the present invention is to provide a positron drug storage management system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a positron drug storage management method based on artificial intelligence, the method comprising the following steps:

[0006] S10. Verify the identity information of the technician and collect the usage data of the technician's positron drugs; generate a schedule for the technician's working hours and monitor the changes in the storage volume of the positron drugs;

[0007] S20. Based on the historical usage data of positron drugs, a regression model for predicting the usage of positron drugs is established; the online appointment information data of patients is collected, and the required usage of positron drugs is predicted based on the number of online appointments and the patient's condition;

[0008] S30, predicting the number of days for the current storage of positron drugs to be used based on the order table of the technicians' working hours and the technicians' positron drug usage data in historical data;

[0009] S40. Determine whether the current storage of positron drugs is sufficient based on the supply efficiency of the positron drugs and the number of days the current storage of the positron drugs can be used; when the storage of the positron drugs is insufficient, send a shortage alarm to the management personnel.

[0010] Furthermore, the technician's identity information is managed and the technician's working days are recorded; when the technician uses positron drugs, the required amount and actual amount of positron drugs used by the technician are recorded; the required amount represents the amount of positron drugs needed based on the patient's specific situation; the actual amount represents the amount of positron drugs used after the increase in usage due to errors in the technician's drug configuration process.

[0011] Furthermore, the specific implementation process of step S20 includes:

[0012] S201. Establish a regression model for predicting the use of positron drugs. Based on the historical use data of positron drugs, analyze the impact of different number of patients and conditions on the amount of positron drugs required each day. According to the calculation formula:

[0013] Y=N 1 γ 1 +N 2 γ 2 +...+N n γ n +ε;

[0014] Among them, γ i N represents the required amount of positron-emitting drug corresponding to the i-th patient's condition; i represents the number of patients who see a doctor on the day corresponding to the i-th patient condition; i represents different patient conditions; i = 1, 2, ..., n; n represents the number of patient conditions; ε represents the error term, which represents the amount of positron drug usage caused by some emergencies and failure to make online reservations; Y represents the predicted amount of positron drug usage on different days;

[0015] The regression model is trained by taking the different number of patients analyzed each day and the corresponding patient conditions as input and the required daily usage of positron drugs as output;

[0016] S202, predicting the required usage of positron drugs on different days according to the number of online appointments and the corresponding patient conditions;

[0017] By establishing a regression model, we can analyze the usage of positron drugs for patients with different conditions, thereby predicting the daily usage of positron drugs and improving our ability to analyze data.

[0018] Furthermore, the specific implementation process of step S30 includes:

[0019] S301. The data on the use of positron drugs by technicians in the historical data is used as sample data to analyze the probability of errors in the drug configuration process of different technicians in the sample data; the number of working days T of the technician is used as the independent variable, and the probability of errors in the drug configuration process of the technician G is used as the dependent variable, and the relationship curve between the number of working days of the technician and the proficiency of drug configuration is fitted to obtain the functional relationship G T ;

[0020] S302: Determine the number of technicians working on different days w according to the work schedule of the technicians, and determine the number of working days T of the corresponding technicians 1 , T 2 , ..., T w , according to the predicted amount of positron drugs required for different days, the actual amount of positron drugs used for different days, H, is calculated; according to the calculation formula:

[0021]

[0022] in, Indicates that the number of working days for the corresponding technician is T j The probability of errors in drug configuration; T j represents the number of working days corresponding to the jth technician; j = 1, 2, ..., w;

[0023] By calculating the required usage of positron drugs and the drug waste caused by technicians' operational errors during drug preparation, the average error probability of different technicians is calculated every day to analyze the overall error probability, making the prediction of positron drug usage more accurate.

[0024] When the technicians make a configuration error of positron drugs, the required usage L and actual usage E of the administrator's configuration error are determined, and the actual usage of positron drugs on different days is recalculated according to the calculation formula:

[0025]

[0026] Since the technicians have made a configuration error in the positron drug, it is necessary to recalculate the actual usage of the positron drug to ensure that the data is updated in real time to prevent emergencies;

[0027] S303. At zero o'clock every day, the data is automatically updated to determine the current storage volume H of the positron drug. 总According to the collected online appointment information data of patients, the required usage of positron drugs in different days is obtained; according to the order table of the technicians' working hours, the actual usage of positron drugs in the corresponding number of days of required usage of positron drugs is predicted, and the usage days S of the current storage of positron drugs is predicted, so that S satisfies the calculation formula:

[0028]

[0029] Among them, H z It indicates the actual usage of positronic drugs on the zth day calculated after the data is automatically updated;

[0030] By predicting the number of days the current inventory of positron drugs can be used, out-of-stock warnings can be sent to managers, ensuring an adequate supply of positron drugs, avoiding delays in diagnosis due to drug shortages, and reducing supply chain uncertainty.

[0031] Furthermore, the specific implementation process of step S40 includes:

[0032] S401, based on the historical supply cycle of positron drugs, determining the maximum supply cycle days K of positron drugs;

[0033] S402, compare K with S; when S≤K, the electronic drug storage is sufficient; when S>K, there is a risk of out-of-stock of positron drugs, and send a shortage alarm to the management personnel;

[0034] By analyzing the usage data of positron drugs and mining information data, the storage and supervision capabilities of positron drugs have been improved.

[0035] An artificial intelligence-based positron drug storage management system, the system includes a personnel information recording module, an appointment management module, a demand intelligent prediction module, a risk alarm module and a storage quantity display module;

[0036] The personnel information recording module is used to verify the identity information of the technician and collect the technician's positron drug usage data; the appointment management module is used to collect patients' online appointment information data; the demand intelligent prediction module is used to monitor the changes in the storage volume of positron drugs and predict the number of days the current storage volume of positron drugs can be used; the risk alarm module is used to send goods shortage alarms to management personnel; the storage volume display module is used to provide management personnel with a human-computer interaction interface to digitally represent the storage volume of positron drugs and the predicted number of days the current storage volume of positron drugs can be used.

[0037] Further, the personnel information recording module includes an identity authentication unit and a usage data collection unit;

[0038] The identity verification unit is used to manage the technician's identity information and record the technician's working days;

[0039] The usage data collection unit is used to record the required amount and actual usage of positron drugs when the technician uses the positron drugs; the required amount represents the required amount of positron drugs required according to the specific situation of the patient; the actual amount represents the amount of positron drugs used after the increase in usage caused by errors in the technician's drug configuration process.

[0040] Further, the appointment management module includes a patient appointment management unit and an appointment information recording unit;

[0041] The patient appointment management unit is used to provide an online appointment platform for patients and collect online appointment information data of patients;

[0042] The reservation information recording unit is used to determine the number of online reservations and the patient's condition.

[0043] Furthermore, the demand intelligent prediction module includes a model training unit, an inventory monitoring unit, an order list management unit and a positron drug prediction unit;

[0044] The model training unit is used to establish a regression model for predicting the usage of positron drugs, and analyze the impact of different patient numbers and conditions on the required usage of positron drugs based on historical positron drug usage data;

[0045] The inventory monitoring unit is used to monitor the change in the storage amount of the positron drug and determine the current storage amount of the positron drug;

[0046] The order table management unit is used to generate an order table for the working hours of technicians on different days, determine the number of technicians working on different days, and determine the working days of the corresponding technicians;

[0047] The positron drug prediction unit is used to obtain the required usage of positron drugs on different days based on the collected patient online reservation information data; according to the order scheduling table of the technicians' working hours, predict the actual usage of positron drugs in the corresponding number of days of required usage of positron drugs, and predict the usage days of the current storage of positron drugs.

[0048] Further, the risk alarm module includes a supply cycle determination unit, a risk judgment unit and an alarm management unit;

[0049] The supply cycle determination unit is used to determine the maximum supply cycle days of the positron drug based on the historical supply cycle of the positron drug;

[0050] The risk judgment unit is used to judge whether the current storage of positron drugs is sufficient according to the supply efficiency of positron drugs and the number of days of use of the current storage of positron drugs;

[0051] The alarm management unit is used to send a shortage alarm to the management personnel when the storage amount of the positron medicine is insufficient.

[0052] Compared with the prior art, the beneficial effects achieved by the present invention are: providing an artificial intelligence-based positron drug storage management system and method, which supervises the stored positron drugs, predicts the demand for positron drug use by analyzing the usage data of positron drugs, reduces inventory backlogs, thereby saving storage space and avoiding waste caused by expired drugs; at the same time, sending goods shortage alerts to managers to ensure sufficient supply of positron drugs, avoid delayed diagnosis due to drug shortages, and reduce supply chain uncertainty. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0054] Figure 1 It is a structural schematic diagram of an artificial intelligence-based positron drug storage management system of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] See also Figure 1 The present invention provides a technical solution: a positron drug storage management method based on artificial intelligence, the method comprising the following steps:

[0057] S10. Verify the identity information of the technician and collect the usage data of the technician's positron drugs; generate a schedule for the technician's working hours and monitor the changes in the storage volume of the positron drugs;

[0058] S20. Based on the historical usage data of positron drugs, a regression model for predicting the usage of positron drugs is established; the online appointment information data of patients is collected, and the required usage of positron drugs is predicted based on the number of online appointments and the patient's condition;

[0059] S30, predicting the number of days for the current storage of positron drugs to be used based on the order table of the technicians' working hours and the technicians' positron drug usage data in historical data;

[0060] S40. Determine whether the current storage of positron drugs is sufficient based on the supply efficiency of the positron drugs and the number of days the current storage of the positron drugs can be used; when the storage of the positron drugs is insufficient, send a shortage alarm to the management personnel.

[0061] Manage the technician's identity information and record the technician's working days; when the technician uses positron drugs, record the required amount and actual amount of positron drugs used by the technician; the required amount represents the amount of positron drugs needed based on the patient's specific situation; the actual amount represents the amount of positron drugs used after the increase in usage due to errors in the technician's drug configuration process.

[0062] The specific implementation process of step S20 includes:

[0063] S201. Establish a regression model for predicting the use of positron drugs. Based on the historical use data of positron drugs, analyze the impact of different number of patients and conditions on the amount of positron drugs required each day. According to the calculation formula:

[0064] Y=N 1 γ 1 +N 2 γ 2 +...+N n γ n +ε;

[0065] Among them, γ i N represents the required amount of positron-emitting drug corresponding to the i-th patient's condition; i represents the number of patients who see a doctor on the day corresponding to the i-th patient condition; i represents different patient conditions; i = 1, 2, ..., n; n represents the number of patient conditions; ε represents the error term; Y represents the predicted amount of positron drug required for different days;

[0066] The regression model is trained by taking the different number of patients analyzed each day and the corresponding patient conditions as input and the required daily usage of positron drugs as output;

[0067] S202. Predict the required usage of positron drugs on different days based on the number of online reservations and the corresponding patient conditions.

[0068] The specific implementation process of step S30 includes:

[0069] S301. The data on the use of positron drugs by technicians in the historical data is used as sample data to analyze the probability of errors in the drug configuration process of different technicians in the sample data; the number of working days T of the technician is used as the independent variable, and the probability of errors in the drug configuration process of the technician G is used as the dependent variable, and the relationship curve between the number of working days of the technician and the proficiency of drug configuration is fitted to obtain the functional relationship G T ;

[0070] S302: Determine the number of technicians working on different days w according to the work schedule of the technicians, and determine the number of working days T of the corresponding technicians 1 , T 2 , ..., T w , according to the predicted amount of positron drugs required for different days, the actual amount of positron drugs used for different days, H, is calculated; according to the calculation formula:

[0071]

[0072] in, Indicates that the number of working days for the corresponding technician is T j The probability of errors in drug configuration; T j represents the number of working days corresponding to the jth technician; j = 1, 2, ..., w;

[0073] S303. At zero o'clock every day, the data is automatically updated to determine the current storage volume H of the positron drug. 总 According to the collected online appointment information data of patients, the required usage of positron drugs in different days is obtained; according to the order table of the technicians' working hours, the actual usage of positron drugs in the corresponding number of days of required usage of positron drugs is predicted, and the usage days S of the current storage of positron drugs is predicted, so that S satisfies the calculation formula:

[0074]

[0075] Among them, H z It indicates the actual usage of positronic drugs on the zth day calculated after the data is automatically updated.

[0076] The specific implementation process of step S40 includes:

[0077] S401, based on the historical supply cycle of positron drugs, determining the maximum supply cycle days K of positron drugs;

[0078] S402, compare K with S; when S≤K, the storage of electronic drugs is sufficient; when S>K, there is a risk of out-of-stock of positron drugs, and a shortage alert is sent to the management personnel.

[0079] An artificial intelligence-based positron drug storage management system, the system includes a personnel information recording module, an appointment management module, a demand intelligent prediction module, a risk alarm module and a storage quantity display module;

[0080] The personnel information recording module is used to verify the identity information of the technician and collect the technician's positron drug usage data; the appointment management module is used to collect patients' online appointment information data; the demand intelligent prediction module is used to monitor the changes in the storage volume of positron drugs and predict the number of days the current storage volume of positron drugs can be used; the risk alarm module is used to send goods shortage alarms to management personnel; the storage volume display module is used to provide management personnel with a human-computer interaction interface to digitally represent the storage volume of positron drugs and the predicted number of days the current storage volume of positron drugs can be used.

[0081] The personnel information recording module includes an identity authentication unit and a usage data collection unit;

[0082] The identity verification unit is used to manage the technician's identity information and record the technician's working days;

[0083] The usage data collection unit is used to record the required amount and actual usage of positron drugs when the technician uses the positron drugs; the required amount represents the required amount of positron drugs required according to the specific situation of the patient; the actual amount represents the amount of positron drugs used after the increase in usage caused by errors in the technician's drug configuration process.

[0084] The appointment management module includes a patient appointment management unit and an appointment information recording unit;

[0085] The patient appointment management unit is used to provide an online appointment platform for patients and collect online appointment information data of patients;

[0086] The reservation information recording unit is used to determine the number of online reservations and the patient's condition.

[0087] The demand intelligent prediction module includes a model training unit, an inventory monitoring unit, an order list management unit and a positron drug prediction unit;

[0088] The model training unit is used to establish a regression model for predicting the usage of positron drugs, and analyze the impact of different patient numbers and conditions on the required usage of positron drugs based on historical positron drug usage data;

[0089] The inventory monitoring unit is used to monitor the change in the storage amount of the positron drug and determine the current storage amount of the positron drug;

[0090] The order table management unit is used to generate an order table for the working hours of technicians on different days, determine the number of technicians working on different days, and determine the working days of the corresponding technicians;

[0091] The positron drug prediction unit is used to obtain the required usage of positron drugs on different days based on the collected patient online reservation information data; according to the order scheduling table of the technicians' working hours, predict the actual usage of positron drugs in the corresponding number of days of required usage of positron drugs, and predict the usage days of the current storage of positron drugs.

[0092] The risk alarm module includes a supply cycle determination unit, a risk judgment unit and an alarm management unit;

[0093] The supply cycle determination unit is used to determine the maximum supply cycle days of the positron drug based on the historical supply cycle of the positron drug;

[0094] The risk judgment unit is used to judge whether the current storage of positron drugs is sufficient according to the supply efficiency of positron drugs and the number of days of use of the current storage of positron drugs;

[0095] The alarm management unit is used to send a shortage alarm to the management personnel when the storage amount of the positron medicine is insufficient.

[0096] In this embodiment:

[0097] The system is specifically a positron drug storage monitoring and management system for medical institutions; in the system, the use of positron drugs is supervised, and when the storage of positron drugs is insufficient, a shortage alarm is sent to the management personnel;

[0098] Based on the historical data of positron drug usage, a regression model for predicting the amount of positron drug usage is established; the impact of the number of patients and the amount of positron drug required for each disease condition is analyzed, and the calculation formula is as follows:

[0099] Y=N 1 γ 1 +N 2 γ 2 +...+N n γ n +ε;

[0100] The number of patients analyzed each day and the corresponding patient conditions are used as input, and the required daily usage of positron drugs is used as output to train the regression model;

[0101] The 200 types of positron drug usage data of technicians in the historical data were used as sample data, and the probability of errors in the drug configuration process of different technicians in the 1000 sample data was analyzed; the number of technician working days T was taken as the independent variable, and the probability of errors in the drug configuration process of technicians G was taken as the dependent variable, and the relationship curve between the number of technician working days and the proficiency of drug configuration was fitted to obtain the functional relationship G T for:

[0102] G T =ae -bT ;

[0103] Where a and b represent constants;

[0104] At a certain zero o'clock, the data is automatically updated. According to the collected online appointment information of patients, the number of online appointments and the patient's condition in the next five days are obtained. The number of patients analyzed in the next five days and the corresponding patient's condition are used as input to the regression model to obtain the required usage of positron drugs in the next five days Y. 1 , Y 2 , Y 3 , Y 4 and Y 5 They are 100, 150, 200, 120 and 100 respectively;

[0105] Among them, Y m Indicates the amount of positron drug required for the mth day in the future; m = 1, 2, 3, 4, 5;

[0106] According to the work schedule of technicians, the number of technicians working in the next five days is determined to be 2, 3, 3, 2, and 2 respectively; the number of working days of the corresponding technicians is determined, and the actual usage of positron drugs in the next five days is calculated; according to the calculation formula:

[0107]

[0108] Get H 1 , H 2 , H 3 , H 4 and H 5 The values ​​of are 102, 155, 206, 124 and 101 respectively;

[0109] Among them, H c represents the actual usage of positron drugs on the cth day in the future; c = 1, 2, 3, 4, 5;

[0110] The current storage volume of positron drugs is 685. The predicted number of days of use of the current storage volume of positron drugs is calculated according to the formula:

[0111]

[0112] The value of S is 4; the maximum supply cycle of positron drugs is K = 3 days. At this time, S>K, there is a risk of positron drugs being out of stock, and a shortage alert is sent to the management personnel;

[0113] In another embodiment:

[0114] Determine the working days of the corresponding technicians and calculate the actual usage of positron drugs in the next five days; when the technicians make a configuration error of positron drugs, determine the required usage L and actual usage E of the manager's incorrect configuration, and recalculate the actual usage of positron drugs in the next five days according to the calculation formula:

[0115]

[0116] Get H 1 , H 2 , H 3 , H 4 and H 5 The values ​​are 107, 160, 211, 129 and 106 respectively.

[0117] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0118] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A positron drug storage management method based on artificial intelligence, characterized in that: The method comprises the following steps: S10. Verify the identity information of the technician and collect the usage data of the technician's positron drugs; generate a schedule for the technician's working hours and monitor the changes in the storage volume of the positron drugs; S20. Based on the historical usage data of positron drugs, a regression model for predicting the usage of positron drugs is established; the online appointment information data of patients is collected, and the required usage of positron drugs is predicted based on the number of online appointments and the patient's condition; The specific implementation process of step S20 includes: S201. Establish a regression model for predicting the use of positron drugs. Based on the historical use data of positron drugs, analyze the impact of different number of patients and conditions on the amount of positron drugs required each day. According to the calculation formula: Y=N1γ1+N2γ2+...+N n c n +e; Among them, γ i N represents the required amount of positron-emitting drug corresponding to the i-th patient's condition; i represents the number of patients who see a doctor on the day corresponding to the i-th patient condition; i represents different patient conditions; i = 1, 2, ..., n; n represents the number of patient conditions; ε represents the error term; Y represents the predicted amount of positron drug required for different days; The regression model is trained by taking the different number of patients analyzed each day and the corresponding patient conditions as input and the required daily usage of positron drugs as output; S202, predicting the required usage of positron drugs on different days according to the number of online appointments and the corresponding patient conditions; S30, predicting the number of days for the current storage of positron drugs to be used based on the order table of the technicians' working hours and the technicians' positron drug usage data in historical data; The specific implementation process of step S30 includes: S301. The data on the use of positron drugs by technicians in the historical data is used as sample data to analyze the probability of errors in the drug configuration process of different technicians in the sample data; the number of working days T of the technician is used as the independent variable, and the probability of errors in the drug configuration process of the technician G is used as the dependent variable, and the relationship curve between the number of working days of the technician and the proficiency of drug configuration is fitted to obtain the functional relationship G T ; S302: According to the work schedule of technicians, determine the number of technicians working on different days, and determine the corresponding working days T1, T2, ..., T w , according to the predicted amount of positron drugs required for different days, the actual amount of positron drugs used for different days, H, is calculated; according to the calculation formula: in, Indicates that the number of working days for the corresponding technician is T j The probability of errors in drug configuration; T j represents the number of working days corresponding to the jth technician; j = 1, 2, ..., w; S303. At zero o'clock every day, the data is automatically updated to determine the current storage volume H of the positron drug. 总 According to the collected online appointment information data of patients, the required usage of positron drugs in different days is obtained; according to the order table of the technicians' working hours, the actual usage of positron drugs in the corresponding number of days of required usage of positron drugs is predicted, and the usage days S of the current storage of positron drugs is predicted, so that S satisfies the calculation formula: Among them, H z It indicates the actual usage of positronic drugs on the zth day calculated after the data is automatically updated; S40. Determine whether the current storage of positron drugs is sufficient based on the supply efficiency of the positron drugs and the number of days the current storage of the positron drugs can be used; when the storage of the positron drugs is insufficient, send a shortage alarm to the management personnel.

2. According to claim 1, a positron drug storage management method based on artificial intelligence is characterized in that: Manage the technician's identity information and record the technician's working days; when the technician uses positron drugs, record the required amount and actual amount of positron drugs used by the technician; the required amount represents the amount of positron drugs needed based on the patient's specific situation; the actual amount represents the amount of positron drugs used after the increase in usage due to errors in the technician's drug configuration process.

3. The method for storage and management of positron drugs based on artificial intelligence according to claim 2, characterized in that: The specific implementation process of step S40 includes: S401, based on the historical supply cycle of positron drugs, determining the maximum supply cycle days K of positron drugs; S402, compare K with S; when S≤K, the storage of electronic drugs is sufficient; when S>K, there is a risk of out-of-stock of positron drugs, and a shortage alert is sent to the management personnel.

4. A positron drug storage management system based on artificial intelligence, using a positron drug storage management method based on artificial intelligence as claimed in any one of claims 1 to 3, characterized in that: The system includes a personnel information recording module, an appointment management module, a demand intelligent prediction module, a risk alarm module and a storage capacity display module; The personnel information recording module is used to verify the identity information of the technicians and collect the usage data of the technicians' positronic drugs; the reservation management module is used to collect the online reservation information data of the patients; The demand intelligent prediction module is used to monitor the changes in the storage volume of positron drugs and predict the number of days the current storage volume of positron drugs can be used; the risk alarm module is used to send goods shortage alarms to management personnel; the storage volume display module is used to provide management personnel with a human-computer interaction interface to digitally represent the storage volume of positron drugs and the predicted number of days the current storage volume of positron drugs can be used.

5. According to claim 4, the positron drug storage management system based on artificial intelligence is characterized in that: The personnel information recording module includes an identity authentication unit and a usage data collection unit; The identity verification unit is used to manage the technician's identity information and record the technician's working days; The usage data collection unit is used to record the required amount and actual usage of positron drugs when the technician uses the positron drugs; the required amount represents the required amount of positron drugs required according to the specific situation of the patient; the actual amount represents the amount of positron drugs used after the increase in usage caused by errors in the technician's drug configuration process.

6. The artificial intelligence-based positron drug storage management system according to claim 5 is characterized in that: The appointment management module includes a patient appointment management unit and an appointment information recording unit; The patient appointment management unit is used to provide an online appointment platform for patients and collect online appointment information data of patients; The reservation information recording unit is used to determine the number of online reservations and the patient's condition.

7. The artificial intelligence-based positron drug storage management system according to claim 6 is characterized by: The demand intelligent prediction module includes a model training unit, an inventory monitoring unit, an order list management unit and a positron drug prediction unit; The model training unit is used to establish a regression model for predicting the usage of positron drugs, and analyze the impact of different patient numbers and conditions on the required usage of positron drugs based on historical positron drug usage data; The inventory monitoring unit is used to monitor the change in the storage amount of the positron drug and determine the current storage amount of the positron drug; The order table management unit is used to generate an order table for the working hours of technicians on different days, determine the number of technicians working on different days, and determine the working days of the corresponding technicians; The positron drug prediction unit is used to obtain the required usage of positron drugs on different days based on the collected patient online reservation information data; according to the order scheduling table of the technicians' working hours, predict the actual usage of positron drugs in the corresponding number of days of required usage of positron drugs, and predict the usage days of the current storage of positron drugs.

8. The artificial intelligence-based positron drug storage management system according to claim 6 is characterized by: The risk alarm module includes a supply cycle determination unit, a risk judgment unit and an alarm management unit; The supply cycle determination unit is used to determine the maximum supply cycle days of the positron drug based on the historical supply cycle of the positron drug; The risk judgment unit is used to judge whether the current storage of positron drugs is sufficient according to the supply efficiency of positron drugs and the number of days of use of the current storage of positron drugs; The alarm management unit is used to send a shortage alarm to the management personnel when the storage amount of the positron medicine is insufficient.

Images