Collaborative multi-point analysis security risk management platform

Abstract

The application discloses a multi-point cooperative analysis security risk management platform and relates to the technical field of data management.The platform comprises a storage system of interactive target drug storage warehouses, extracts drug storage distribution data, generates a plurality of drug characteristic sets, acquires a plurality of storage monitoring index sets, determines a first risk identification result, determines a second risk identification result, and takes a plurality of first risk drugs, a plurality of first risk coefficients, a plurality of risk areas and a plurality of second risk coefficients as a drug storage risk identification result.The technical problem that the prior art has the single monitoring dimension of the security risk management of drug storage, lagging risk identification and difficulty in realizing multi-source data cooperative analysis, and further leads to the inability to accurately predict potential risks in the drug storage process and insufficient drug storage safety is solved, and the technical effects of real-time dynamic monitoring of drug storage risks, multi-dimensional cooperative early warning and intelligent accurate management are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data management, in particular to a security risk management platform for multi-point collaborative analysis. BACKGROUND

[0002] The safe storage and effective management of drugs not only relates to the effectiveness and stability of the drugs, but also directly affects the safety of drug use by patients. In actual drug storage management, due to the variety of drugs, different storage conditions (such as different environmental requirements such as temperature, humidity, and light), and the problems of similar appearance and similar name of different drugs, it is easy to cause confusion, deterioration, or substandard storage environment during drug storage. Traditional drug storage management mainly relies on manual inspection and simple information recording, and it is difficult to realize real-time and accurate risk monitoring and early warning, which is easy to cause safety hazards due to human negligence or environmental fluctuations. However, the drug storage management system is often limited to single-dimensional monitoring, such as only focusing on environmental parameters or only relying on manual checking of drug information, lacking multi-dimensional and collaborative risk analysis capabilities, and it is difficult to comprehensively identify potential storage risks.

[0003] Therefore, in the current drug storage risk identification technology, there are technical problems such as single monitoring dimension of drug storage safety risk management, lagging risk identification, difficulty in realizing multi-source data collaborative analysis, and thus inability to accurately predict potential risks in the drug storage process and insufficient drug storage safety. SUMMARY

[0004] The present application provides a security risk management platform for multi-point collaborative analysis, which adopts integrated intelligent sensing array, big data analysis technology, and artificial intelligence algorithm and other technical means, solves the technical problems of single monitoring dimension of drug storage safety risk management, lagging risk identification, difficulty in realizing multi-source data collaborative analysis, and thus inability to accurately predict potential risks in the drug storage process and insufficient drug storage safety in the prior art, and achieves the technical effects of real-time dynamic monitoring of drug storage risks, multi-dimensional collaborative early warning, and intelligent and accurate management.

[0005] The application provides a safety risk management platform for multi-point collaborative analysis, which comprises: a drug storage distribution data extraction module for interacting with a storage system of a target drug storage warehouse to extract drug storage distribution data, wherein the drug storage distribution data comprises a plurality of drug sets corresponding to a plurality of drug storage areas and a plurality of drug storage location identifiers; a drug feature set generation module for performing feature extraction on the plurality of drug sets according to preset risk features to generate a plurality of drug feature sets, wherein the plurality of drug feature sets comprise a plurality of drug name sets, a plurality of outer packaging image sets and a plurality of storage environment requirement sets; a storage monitoring index set acquisition module for interacting with a plurality of intelligent sensing arrays of the plurality of drug storage areas to acquire a plurality of storage monitoring index sets, wherein the plurality of storage monitoring index sets comprise a plurality of storage temperatures, a plurality of storage humidities and a plurality of storage radiation amounts; a first risk identification result determination module for performing risk identification on the plurality of storage monitoring index sets based on the plurality of storage environment requirement sets to determine a first risk identification result, wherein the first risk identification result comprises a plurality of first risk drugs and a plurality of first risk coefficients; a second risk identification result determination module for performing regional confusion risk identification based on the plurality of drug name sets, a plurality of outer packaging image sets, the plurality of drug sets and the plurality of drug storage location identifiers to determine a second risk identification result, wherein the second risk identification result comprises a plurality of risk areas and a plurality of second risk coefficients; and a safety risk management module for performing safety risk management according to the plurality of first risk drugs, a plurality of first risk coefficients, a plurality of risk areas and the plurality of second risk coefficients.

[0006] In possible implementation manners, the drug feature set generation module further performs the following processing: the preset risk features comprise drug names, outer packaging images and storage environment requirements.

[0007] In a possible implementation, the storage monitoring index set acquisition module further performs the following processing: respectively performing data collection on the multiple intelligent sensing arrays in a preset verification window to generate multiple verification temperature sequence sets, multiple verification humidity sequence sets, and multiple verification radiation sequence sets; performing normalization processing on the multiple verification temperature sequence sets, the multiple verification humidity sequence sets, and the multiple verification radiation sequence sets respectively to obtain multiple normalized verification temperature sequence sets, multiple normalized verification humidity sequence sets, and multiple normalized verification radiation sequence sets; performing window alignment on the multiple normalized verification temperature sequence sets, the multiple normalized verification humidity sequence sets, and the multiple normalized verification radiation sequence sets, and synchronously distributing the multiple normalized verification temperature sequence sets, the multiple normalized verification humidity sequence sets, and the multiple normalized verification radiation sequence sets to multiple verification fitting branches to generate multiple verification fitting spaces, where the multiple verification fitting spaces include multiple verification fitting particle sets; performing linear fitting on the multiple verification fitting particle sets in the multiple verification fitting spaces, and performing feasibility authentication on the multiple intelligent sensing arrays according to a linear fitting result, and when the authentication passes, performing index monitoring on the multiple drug storage areas by using the multiple intelligent sensing arrays respectively to generate the multiple storage monitoring index sets, where the linear fitting result includes multiple fitting straight lines.

[0008] In a possible implementation, the storage monitoring index set acquisition module further performs the following processing: randomly generating multiple starting straight lines in the multiple verification fitting spaces respectively, counting verification fitting particle numbers that are within a preset bandwidth from the multiple starting straight lines to generate multiple starting fitting amounts, performing iterative updating on the multiple starting straight lines in the multiple verification fitting spaces according to the preset bandwidth and the multiple starting fitting amounts to obtain multiple iterative straight lines, respectively performing iteration on the multiple iterative straight lines in the multiple verification fitting spaces according to a preset angle step to obtain multiple angle iterative straight lines, and determining whether a fitting amount difference between the multiple angle iterative straight lines and the multiple iterative straight lines satisfies a preset fitting amount difference, and if yes, taking the multiple angle iterative straight lines as the multiple fitting straight lines.

[0009] In a possible implementation, the storage monitoring index set acquisition module further performs the following processing: extracting multiple slopes of the multiple fitting straight lines, determining whether the multiple slopes are less than or equal to a preset slope threshold, and if yes, passing the authentication, and if not, failing the authentication, generating a sensing risk instruction, and sending the sensing risk instruction to a worker.

[0010] In a possible implementation, the first risk identification result determination module further performs the following processing: performing demand difference calculation according to the plurality of storage environment demand sets and the plurality of storage monitoring indicator sets to obtain a plurality of storage demand difference sets; respectively determining whether the plurality of storage demand difference sets are greater than or equal to a plurality of preset tolerance difference sets, and if yes, obtaining a plurality of first risk drugs; calculating differences between the plurality of storage demand difference sets corresponding to the plurality of first risk drugs and the plurality of preset tolerance difference sets, and comparing the calculation results with the plurality of preset tolerance difference sets to obtain a plurality of first risk coefficients; and taking the plurality of first risk drugs and the plurality of first risk coefficients as the first risk identification result.

[0011] In a possible implementation, the second risk identification result determination module further performs the following processing: respectively randomly extracting one drug from a plurality of drug sets of the plurality of drug storage areas as a first near-neighbor central drug to obtain a plurality of first near-neighbor central drugs; extracting a plurality of first drug neighborhoods of the plurality of first near-neighbor central drugs based on the plurality of drug storage location identifiers; performing similarity identification on the plurality of first near-neighbor central drugs and the plurality of first drug neighborhoods according to the plurality of drug name sets and a plurality of outer packaging image sets to obtain a plurality of first near-neighbor similarity coefficients; performing near-neighbor similarity identification on the plurality of drug sets to obtain a plurality of near-neighbor similarity coefficient sets; and performing area confusion risk identification on the plurality of near-neighbor similarity coefficient sets by using a preset similarity threshold to determine the second risk identification result.

[0012] In a possible implementation, a similarity identification function is constructed, where the similarity identification function is:

[0013] ;

[0014] wherein, is a first near-neighbor similarity coefficient, is a number of drugs in the first drug neighborhood, and n is a positive integer greater than or equal to 1, is a drug name of the first near-neighbor central drug, is a drug name of an i th drug in the first drug neighborhood, is an outer packaging image of the first near-neighbor central drug, is an outer packaging image of the i th drug in the first drug neighborhood, is a weight of a similarity degree of the drug name when performing the near-neighbor similarity identification, a weight of a similarity degree of the outer package image in the neighbor similarity identification; and performing mapping matching on the plurality of first neighbor center drugs and the plurality of first drug neighborhoods based on the plurality of drug name sets and the plurality of outer package image sets to obtain a plurality of first neighbor center drug names, a plurality of first neighbor center drug outer package images, a plurality of first drug neighborhood name sets, and a plurality of first drug neighborhood outer package image sets; and inputting the plurality of first neighbor center drug names, the plurality of first neighbor center drug outer package images, the plurality of first drug neighborhood name sets, and the plurality of first drug neighborhood outer package image sets into the similarity identification function to obtain the plurality of first neighbor similarity coefficients.

[0015] The safety risk management platform for multi-point collaborative analysis provided in the present application interacts with a storage system of a target drug storage bin to extract drug storage distribution data; performs feature extraction on a plurality of drug sets according to preset risk characteristics to generate a plurality of drug feature sets; interacts with a plurality of intelligent sensing arrays of a plurality of drug storage areas to obtain a plurality of storage monitoring index sets; performs risk identification on the plurality of storage monitoring index sets based on a plurality of storage environment requirement sets to determine a first risk identification result; performs regional confusion risk identification based on a plurality of drug name sets, a plurality of outer package image sets, a plurality of drug sets, and a plurality of drug storage location identifiers to determine a second risk identification result; and takes the plurality of first risk drugs, the plurality of first risk coefficients, the plurality of risk regions, and the plurality of second risk coefficients as a drug storage risk identification result. The technical problems of single monitoring dimension, lagging risk identification, and difficulty in multi-source data collaborative analysis in the prior art are solved, and the technical effects of real-time dynamic monitoring of drug storage risks, multi-dimensional collaborative early warning, and intelligent precise management are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the platform according to the embodiments of the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or at the same time as needed. Meanwhile, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 A structural schematic diagram of the safety risk management platform for multi-point collaborative analysis provided in the embodiments of the present application;

[0018] Figure 2An execution process schematic diagram of the storage monitoring index set obtaining module in the multi-point collaborative analysis security risk management platform provided by the embodiments of the present application is shown.

[0019] The reference signs are explained as follows: a drug storage distribution data extracting module 10, a drug feature set generating module 20, a storage monitoring index set obtaining module 30, a first risk identification result determining module 40, a second risk identification result determining module 50, and a security risk management module 60. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the present application. In order to make the technical solutions of the present application more clearly understood and implemented, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the technical solutions, purposes, and advantages of the present application more clearly understood, the following will further describe the present application with reference to the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without making creative efforts fall within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The term "first\second" is only to distinguish similar objects, and does not represent a specific order of the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, platform, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide a multi-point collaborative analysis security risk management platform, as shown in Figure 1 The platform comprises:

[0024] The drug storage distribution data extraction module 10 is used for extracting drug storage distribution data of a storage system of a target drug storage warehouse, wherein the drug storage distribution data comprises a plurality of drug sets corresponding to a plurality of drug storage areas and a plurality of drug storage location identifiers. The storage system of the target drug storage warehouse is a comprehensive system integrating modern information technology, automation technology and warehouse management technology. Through reasonable planning of drug storage areas, accurate identification of drug storage locations, and utilization of intelligent means to realize automatic storage and retrieval of drugs, inventory monitoring and data analysis, etc., the drug storage distribution data mainly refers to detailed information about the distribution of drugs in the storage warehouse, including a plurality of drug sets corresponding to a plurality of drug storage areas and a plurality of drug storage location identifiers. Specifically, the storage area refers to different spatial areas in the storage warehouse divided according to drug types, uses, management requirements, etc. Each area may correspond to different environmental conditions (such as temperature, humidity), security levels or access permissions. The drug set refers to a group of drugs with similar attributes or uses stored in a specific area, for example, classified as prescription drugs, non-prescription drugs, traditional Chinese medicines, western medicines, etc. according to drug types, and classified as antibiotics, painkillers, cardiovascular drugs, etc. according to uses, as well as special management drugs such as psychotropic drugs and narcotic drugs. The storage location identifier is information used to uniquely identify the specific location of each drug in the storage warehouse, including physical locations such as shelf number, layer number, column number, bin number, etc., and electronic identifiers such as RFID tags, two-dimensional codes, etc. Drug information can be quickly read through scanning equipment. The following is an exemplary table of drug storage data:

[0025]

[0026] The drug feature set generation module 20 is configured to perform feature extraction on the plurality of drug sets according to preset risk features, and generate a plurality of drug feature sets, wherein the plurality of drug feature sets include a plurality of drug name sets, a plurality of outer packaging image sets, and a plurality of storage environment requirement sets. In the storage system of the target drug storage bin, feature extraction is performed on the plurality of drug sets according to preset risk features, and a plurality of drug feature sets are generated. Specifically, the relevant information of each drug set is extracted from the storage system, including drug name, outer packaging image, and storage environment requirement, etc. The collected information is classified, sorted and summarized to form a standardized data structure. According to the preset risk features (such as drug name, outer packaging image, storage environment requirement, etc.), the key features are extracted from the sorted information, and the corresponding feature sets are generated. The generated drug feature sets are stored in the database and managed and queried uniformly through the management system. A plurality of drug feature sets including a plurality of drug name sets, a plurality of outer packaging image sets, and a plurality of storage environment requirement sets are obtained. The drug name set refers to the set of drug names extracted from all drug sets, which contains the standard names of all drugs in the storage bin. Each drug name is unique and used to identify different drug categories. The drug name set helps to quickly identify drug categories and facilitates accurate operation during storage, retrieval, inventory, etc. The outer packaging image set refers to the set of drug outer packaging images extracted from all drug sets, which contains the outer packaging images of all drugs in the storage bin, which can be in the form of photos, scans or digital models, etc. It is used to show the outer packaging features of the drug. The outer packaging image set helps to quickly confirm the drug category and state through visual identification, especially when dealing with drugs with similar appearance or similar names, which can significantly reduce the risk of confusion. The storage environment requirement set refers to the set of drug storage environment requirements extracted from all drug sets, which contains the specific requirements of each drug for the storage environment, such as temperature range, humidity requirement, lighting condition, whether it needs to be kept away from light, etc. The storage environment requirement set is crucial for ensuring the safety and effectiveness of drugs during storage. By monitoring and adjusting the storage environment in real time, the storage needs of different drugs can be met, and the invalidation or deterioration of drugs due to improper storage can be avoided.

[0027] The storage monitoring index set acquisition module 30 is configured to interact with the plurality of intelligent sensing arrays of the plurality of drug storage areas respectively, and acquire a plurality of storage monitoring index sets, wherein the plurality of storage monitoring index sets include a plurality of storage temperatures, a plurality of storage humidities, and a plurality of storage radiation amounts. The intelligent sensing array is a device or system that integrates multiple sensors and data processing technologies, which can monitor and record various environmental parameters in the drug storage area in real time. The sensors may include temperature sensors, humidity sensors, radiation amount sensors, etc., for measuring the temperature, humidity, and radiation amount of the storage area, etc. In the storage warehouse, drugs are usually stored in different areas, which may be divided according to the type, use, management requirements, etc. of the drugs. Each area is equipped with a corresponding intelligent sensing array to ensure comprehensive monitoring of the drug storage environment in the area. Specifically, the intelligent sensing array collects and records the key indicators of the drug storage environment in real time, and acquires a plurality of storage monitoring index sets, including a plurality of storage temperatures, a plurality of storage humidities, and a plurality of storage radiation amounts. The plurality of storage temperatures refer to the real-time measured temperature values in each storage area, reflecting the current temperature condition of the storage area, which is crucial for drugs that need to be stored under specific temperature conditions. The plurality of storage humidities refer to the real-time measured humidity values in each storage area, and humidity is an important factor affecting the stability and effectiveness of drugs. For most drugs, radiation amount may not be a major monitoring indicator, but in some special cases (such as radioactive drugs or drugs that need to be stored in the dark), monitoring of radiation amount is also necessary. Radiation amount may refer to light radiation or other forms of radiation, forming a plurality of storage radiation amounts.

[0028] The first risk identification result determination module 40 is configured to perform risk identification on the plurality of storage monitoring indicator sets based on the plurality of storage environment requirement sets, and determine a first risk identification result, wherein the first risk identification result includes a plurality of first risk drugs and a plurality of first risk coefficients. By comparing and analyzing the storage environment requirements and the real-time monitoring data, the drugs with potential risks and the corresponding risk coefficients are identified. Specifically, the risk identification process is to compare and analyze the storage environment requirement set and the storage monitoring indicator set. The system compares the storage environment requirements and the actual monitoring data of each drug one by one according to a preset algorithm or rule. If it is found that a monitoring indicator exceeds the range of the storage environment requirements of the drug, it is considered that the drug has potential risks. The first risk identification result is obtained, including a plurality of first risk drugs and a plurality of first risk coefficients. The plurality of first risk drugs refer to the drugs identified as having potential risks in the risk identification process. These drugs may be because one or more indicators of the storage environment exceed the range of their storage environment requirements, thereby possibly leading to the decline or failure of the drug. The plurality of first risk coefficients correspond to each first risk drug. The risk coefficient is used to quantify the risk degree of the drug. The calculation of the risk coefficient may be based on multiple factors, such as the degree of exceeding the range, the length of the exceeding time, the sensitivity of the drug itself, etc. The higher the risk coefficient, the greater the risk of the drug, and the more urgent the measures to be taken.

[0029] The second risk identification result determination module 50 is configured to perform regional confusion risk identification based on the plurality of drug name sets, the plurality of outer packaging image sets, the plurality of drugs, and the plurality of drug storage location identifiers, and determine a second risk identification result, wherein the second risk identification result comprises a plurality of risk regions and a plurality of second risk coefficients. The regional confusion risk identification based on the plurality of drug name sets, the plurality of outer packaging image sets, the plurality of drugs, and the plurality of drug storage location identifiers identifies the confusion risks that may exist in the storage region due to similar drug names, similar outer packaging, or improper storage locations, and quantifies the degrees of these risks, to determine the second risk identification result. Specifically, the regional confusion risk identification comprises name similarity analysis, outer packaging similarity analysis, and storage location analysis. The name similarity analysis refers to comparing the names in the drug name sets using a text analysis technique, identifying drugs with similar names or similar pronunciations, and analyzing whether these similar-name drugs are stored in adjacent or easily-confusable regions. The outer packaging similarity analysis refers to analyzing the images in the outer packaging image sets using an image recognition technique, identifying drugs with similar outer packaging or easily-confusable drugs, and evaluating whether these similar-outer-packaging drugs are stored in easily-confusable locations in combination with the storage location identifiers. The storage location analysis refers to checking the drug storage location identifiers, analyzing whether the storage layout is reasonable, and whether there is a confusion risk due to improper locations, and paying special attention to the storage locations of frequently-accessed, high-similarity, or high-risk drugs. Then, the results of the name similarity analysis, the outer packaging similarity analysis, and the storage location analysis are comprehensively evaluated to identify drug combinations and storage regions that have confusion risks, as the second risk identification result, comprising a plurality of risk regions and a plurality of second risk coefficients. The plurality of risk regions indicate specific regions or locations in the storage region that have confusion risks, and contain drugs with similar names, similar outer packaging, or improper storage locations. The plurality of second risk coefficients are quantified based on the number of similar-name drugs, the degree of similar outer packaging, the rationality of the storage locations, and the like, and correspond to each risk region. The higher the risk coefficient, the greater the confusion risk in the region, and the more urgent the measures to be taken.

[0030] The security risk management module 60 is configured to perform security risk management according to the plurality of first-risk drugs, the plurality of first-risk coefficients, the plurality of risk areas, and the plurality of second-risk coefficients. The plurality of first-risk drugs, the plurality of first-risk coefficients, the plurality of risk areas, and the plurality of second-risk coefficients are taken as drug storage risk identification results, which are comprehensive and quantitative evaluation results about drug storage risks, contain various types of risk information, and can help managers clearly understand which drugs in the storage warehouse have risks, how serious the risks are, and where the risks are located. Based on the information, targeted risk response measures can be developed, such as adjusting the storage environment, re-planning the storage layout, and strengthening personnel training, to minimize drug storage risks and ensure patient medication safety. In addition, new risk points or risk change trends can be discovered in a timely manner, thereby continuously optimizing storage management strategies and improving storage efficiency and safety.

[0031] The security risk management platform for multi-point collaborative analysis according to the embodiment of the present application can solve the technical problem of the existing drug storage risk identification, which is difficult to accurately identify the risks of multiple storage locations in the drug storage warehouse due to the large variety of drugs and different storage conditions, and further cannot predict potential risks in the drug storage process, resulting in insufficient drug storage safety. The security risk management platform for multi-point collaborative analysis can realize intelligent monitoring and risk identification of the whole drug storage process, and achieve the technical effect of improving drug storage safety. The security risk management platform for multi-point collaborative analysis includes a drug storage distribution data extraction module 10, a drug feature set generation module 20, a storage monitoring index set acquisition module 30, a first risk identification result determination module 40, a second risk identification result determination module 50, and a security risk management module 60.

[0032] The specific configuration of the drug feature set generation module 20 will be described in detail below. The drug feature set generation module 20 can further include that the preset risk features include drug name, outer packaging image, storage environment requirement. The preset risk features refer to the standard parameters closely related to the drug characteristics set to identify and prevent potential risks in advance, including drug name, outer packaging image, storage environment requirement, drug name is the basic identification of drug identity, including generic name, trade name, etc., when multiple drug names are similar, it is easy to cause confusion in drug taking, dispensing or drug use, increasing the risk of patient drug use; the outer packaging image is the visual element on the drug packaging, including pattern, color, text, etc., the similarity of the outer packaging image may lead to misidentification or misuse of drugs during storage and distribution, especially when multiple drugs have similar outer packaging, this risk is particularly prominent; the storage environment requirement refers to the specific conditions required to be met during the storage of the drug, such as temperature, humidity, illumination, etc., the unsuitable storage environment will directly affect the quality and stability of the drug, causing the drug to fail or produce harmful substances, not only reducing the efficacy of the drug, but also possibly increasing the risk of patient drug use, by formulating detailed storage environment standards, strengthening environmental monitoring and adjusting, etc., the drug can be ensured to be stored under suitable conditions, reducing the risk caused by unsuitable environment.

[0033] The specific configuration of the storage monitoring index set acquisition module 30 will be described in detail below. As shown in FIG. 3, the storage monitoring index set acquisition module 30 can further include that the preset storage monitoring index includes drug name, outer packaging image, storage environment requirement, and the preset storage monitoring index is obtained by the drug feature set generation module 20. Figure 2As shown, the storage monitoring index set acquisition module 30 can further include: respectively collecting data of the preset verification window for the plurality of intelligent sensing arrays, generating a plurality of verification temperature sequence sets, a plurality of verification humidity sequence sets and a plurality of verification radiation sequence sets. The preset verification window is a time period defined in advance based on the periodicity of environmental changes, the stability of sensor responses, and the needs of data processing, etc., which is used for special data collection and verification. Specifically, during the preset verification window, the sensor arrays arranged in the drug storage area or the related environment are used to continuously monitor and record the changes of environmental parameters, including temperature, humidity and radiation, etc. key indicators, for reflecting the environmental conditions of the storage area. Each array can contain multiple sensors for obtaining environmental data from different angles or positions, generating a plurality of verification temperature sequence sets, a plurality of verification humidity sequence sets and a plurality of verification radiation sequence sets. The verification temperature sequence set refers to the temperature data collected from all intelligent sensing arrays, which is formed into a sequence set after sorting. Each sequence represents the temperature change trend monitored by the corresponding array during the verification window. The verification humidity sequence set refers to the humidity data collected from all intelligent sensing arrays, which is formed into a sequence set after sorting. Each sequence reflects the humidity change monitored by the corresponding array during the verification window. The verification radiation sequence set refers to the radiation data (may include different types of radiation such as ultraviolet and infrared) collected from all intelligent sensing arrays, which is formed into a sequence set after sorting, providing detailed information about the radiation environment of the storage area.

[0034] The storage monitoring index set acquisition module 30 further includes normalizing the plurality of verification temperature sequence sets, the plurality of verification humidity sequence sets and the plurality of verification radiation sequence sets respectively to obtain a plurality of normalized verification temperature sequence sets, a plurality of normalized verification humidity sequence sets and a plurality of normalized verification radiation sequence sets. Linear normalization (also known as min-max normalization), Z-score normalization (also known as standard deviation normalization), etc. are used to normalize the plurality of verification temperature sequence sets, the plurality of verification humidity sequence sets and the plurality of verification radiation sequence sets respectively, that is, to scale the original data to the interval [0, 1] or to convert the data to a distribution with a mean of 0 and a standard deviation of 1, in order to eliminate the dimensional difference and distribution difference between different data, so that data of different sources or different types can be compared and analyzed in the same framework, obtaining a plurality of normalized verification temperature sequence sets, a plurality of normalized verification humidity sequence sets and a plurality of normalized verification radiation sequence sets.

[0035] The storage monitoring index set obtaining module 30 further includes window alignment of the plurality of normalized verification temperature sequence sets, the plurality of normalized verification humidity sequence sets, and the plurality of normalized verification radiation sequence sets, and synchronous distribution to a plurality of verification fitting branches to generate a plurality of verification fitting spaces, wherein the plurality of verification fitting spaces include a plurality of verification fitting particle sets. Window alignment refers to adjusting the plurality of normalized verification temperature sequence sets, the plurality of normalized verification humidity sequence sets, and the plurality of normalized verification radiation sequence sets to the same time starting point and ending point, or at least ensuring that they overlap within the analyzed time period, in order to eliminate minor differences in time (such as network delay, device startup time difference, etc.). Specifically, a common time window is determined, containing the effective part of all sequence data, i.e. deleting data beyond the window range, while filling may involve using interpolation or other methods to estimate missing data points. Then the window-aligned data set is sent to a plurality of parallel processing units (i.e. verification fitting branches) for further analysis and processing, i.e. using a distributed computing system or parallel processing framework to manage a plurality of verification fitting branches, the window-aligned data set is sent to all verification fitting branches at the same time, each verification fitting branch will independently process the input data and generate the corresponding output or result, finally generating a plurality of verification fitting spaces. Verification fitting space refers to a virtual space used to store and process all data and information related to a specific verification task, providing a clear and orderly environment for data analysis, which helps to reduce the complexity and error rate of data processing. The plurality of verification fitting spaces include a plurality of verification fitting particle sets, and the verification fitting particle set refers to a set of elements within the verification fitting space for representing data points, hypotheses or model parameters, which may represent different data subsets, model parameter combinations or fitting results.

[0036] The storage monitoring index set acquisition module 30 further includes performing linear fitting on the plurality of verification fitting particle sets in the plurality of verification fitting spaces, performing feasibility authentication on the plurality of intelligent sensing arrays according to the linear fitting results, and when the authentication is passed, performing index monitoring on the plurality of drug storage areas by the plurality of intelligent sensing arrays respectively to generate the plurality of storage monitoring index sets, wherein the linear fitting results include a plurality of fitting straight lines. Linear fitting is used to find a best-fitting straight line through a set of data points (in this scenario, data points in the verification fitting particle set), which can minimize the sum of the squares of the distances of the data points to the corresponding points on the straight line, that is, the least squares method is used for fitting. Specifically, in each verification fitting space, the verification fitting particle set is preprocessed, and the least squares method is used to perform a linear fitting operation on the verification fitting particle set in the selected verification fitting space, that is, to find the best straight line by minimizing the squared error between the data points and the fitting straight line. For example, calculate the mean, variance, and other statistics of the data points, and solve the parameters (such as slope and intercept) of the best straight line according to the fitting method. The goodness of the fitting result is evaluated by calculating the fitting error, goodness of fit, and other indicators. Then, according to the linear fitting result, the feasibility of the authentication of the plurality of intelligent sensing arrays is performed, which specifically includes setting the authentication standards of the intelligent sensing arrays according to the business requirements and data characteristics, including the fitting error threshold, data consistency requirements, etc. The linear fitting result is compared with the authentication standards to determine whether the intelligent sensing array meets the requirements. If the fitting result of the intelligent sensing array meets the authentication standards, the authentication is passed, and the plurality of intelligent sensing arrays are used to monitor the indexes of the plurality of drug storage areas respectively. According to the management requirements of the drug storage areas, set the indexes that need to be monitored, such as temperature, humidity, light intensity, etc. The intelligent sensing array collects the index data of the storage area in real time and performs preliminary processing (such as filtering, denoising, etc.). The processed data is organized in time sequence or region division, etc. to form a plurality of storage monitoring index sets, which contain the index data of the drug storage area under different times or different conditions.

[0037] The storage monitoring indicator set obtaining module 30 further includes, the specific configuration of the storage monitoring indicator set obtaining module 30 will be described in detail below. The storage monitoring indicator set obtaining module 30 can further include: a plurality of starting straight lines are randomly generated in the plurality of verification fitting spaces respectively, the number of verification fitting particles with a distance to the plurality of starting straight lines being a preset bandwidth is counted, and a plurality of starting fitting quantities are generated. In each verification fitting space, a plurality of starting straight lines are randomly generated, and then a preset bandwidth is set to define the range of verification fitting particles close to the straight line. Specifically, if the vertical distance of a certain verification fitting particle to the straight line is less than or equal to the preset bandwidth, it is considered that the particle is within the bandwidth, then the distances of all particles in the verification fitting space to the straight line are calculated, the number of verification fitting particles with a distance to the starting straight line within the preset bandwidth is counted, and the closeness of the starting straight line to the data point set is reflected. For each starting straight line, a starting fitting quantity is generated according to the number of verification fitting particles (or the number after transformation) corresponding to the starting straight line, which is used for subsequent iterative updating process to find a better fitting straight line.

[0038] The storage monitoring indicator set obtaining module 30 further includes, according to the preset bandwidth and the plurality of starting fitting quantities, iteratively updating the plurality of starting straight lines in the plurality of verification fitting spaces to obtain a plurality of iterative straight lines. Using gradient descent method (used for optimization in continuous space), genetic algorithm (used for optimization in discrete or complex space) and the like, according to the preset bandwidth and the plurality of starting fitting quantities, iteratively updating the plurality of starting straight lines in the plurality of verification fitting spaces, specifically, based on the preset bandwidth and the starting fitting quantity, defining an error function (or called loss function) to measure the fitting degree between the current straight line and the data point set, in each iteration, updating the parameters (such as slope, intercept, etc.) of the straight line according to the value of the current error function and the rules of the selected optimization algorithm, after each iteration, recalculating the distances (or errors) of all data points in the verification fitting space to the updated straight line, and evaluating the iteration effect, for example, calculating the new fitting quantity (such as the number of particles falling within the preset bandwidth, the value of the error function, etc.) and comparing it with the previous iteration result, if the iteration effect meets the preset stopping condition (such as the error is less than a certain threshold, the number of iterations reaches the upper limit, etc.), the iteration is stopped; otherwise, continue to iterate until the stopping condition is met. Finally, a plurality of iterative straight lines are obtained, which can more accurately describe the linear relationship of the data point set.

[0039] The storage monitoring index set obtaining module 30 further includes: iteratively obtaining a plurality of angle iterative straight lines by respectively iterating the plurality of iterative straight lines in the plurality of verification fitting spaces according to a preset angle step. The preset angle step is a fixed angle value for adjusting the direction of the straight line in the iteration process. A smaller step size means a more refined search, but it can require more iteration times. A larger step size can cause the search process to skip the optimal solution. Specifically, a straight line is selected from the iterative straight lines in each verification fitting space as a reference straight line as the starting point for subsequent angle iteration. A new straight line is generated in the verification fitting space according to the preset angle step, taking the reference straight line as the reference. The new generated straight line is evaluated to determine whether its fitting effect is better than that of the reference straight line. If the fitting effect of the new straight line is better than that of the reference straight line, the new straight line is replaced as the new reference straight line. Otherwise, the original reference straight line remains unchanged, and multiple iterations are performed until a preset stop condition is met (such as reaching a maximum number of iterations, an error being less than a certain threshold, etc.). In the iteration process, all generated and evaluated new straight lines are collected to form a set of angle iterative straight lines, representing the fitting results obtained by fine-tuning the reference straight line in different directions.

[0040] The storage monitoring index set obtaining module 30 further includes: determining whether the fitting quantity difference between the plurality of angle iterative straight lines and the plurality of iterative straight lines satisfies a preset fitting quantity difference. If yes, the plurality of angle iterative straight lines are taken as the plurality of fitting straight lines. The preset fitting quantity difference is a threshold value for determining whether angle iteration brings sufficient improvement in fitting effect. Specifically, for each angle iterative straight line, its corresponding fitting quantity (such as the number of particles falling within a preset bandwidth, the value of an error function, etc.) is calculated. For each original iterative straight line, its corresponding fitting quantity is also calculated. The fitting quantity difference between each angle iterative straight line and its corresponding original iterative straight line is calculated, reflecting the degree of improvement in fitting effect after angle iteration. If the fitting quantity difference between the plurality of angle iterative straight lines and their corresponding original iterative straight lines is greater than or equal to the preset fitting quantity difference, it is considered that these angle iterative straight lines have significantly improved in fitting effect and are selected as the final fitting straight lines, representing the best fitting results of the original data point set in different directions.

[0041] In the following, the specific configuration of the storage monitoring index set obtaining module 30 will be described in detail. The storage monitoring index set obtaining module 30 can further include: extracting a plurality of slopes of the plurality of fitting straight lines. The slope is extracted from the plurality of straight lines that have been determined as fitting straight lines. The smaller the slope, the higher it is, indicating that the intelligent perception array is more stable and the monitoring data is more reliable, which can be put into use.

[0042] The storage monitoring index set obtaining module 30 further includes judging whether the plurality of slopes is less than or equal to a preset slope threshold value, and if yes, the authentication is passed. The extracted slopes are compared with the preset slope threshold value, and if the slopes of all the fitting straight lines are less than or equal to the preset slope threshold value, it is considered that the inclination degrees of the straight lines meet the requirements, and thus the authentication is passed, wherein the preset slope threshold value is a set value for judging whether the inclination degrees of the fitting straight lines are within an acceptable range.

[0043] The storage monitoring index set obtaining module 30 further includes, if no, the authentication is not passed, a perception risk instruction is generated, and the perception risk instruction is sent to the staff. If the slope of any one of the fitting straight lines is greater than the preset slope threshold value, it is considered that the inclination degrees of the straight lines exceed the acceptable range, which may indicate an abnormal or risk situation, and thus the authentication is not passed. A perception risk instruction is generated, which contains specific information about why the authentication is not passed, such as which straight line has a slope exceeding the threshold value, the degree of exceeding, etc., and is sent to the staff.

[0044] Next, the specific configuration of the first risk identification result determination module 40 will be described in detail. The first risk identification result determination module 40 can further include: performing demand difference calculation according to the plurality of storage environment demand sets and the plurality of storage monitoring index sets to obtain a plurality of storage demand difference sets. By comparing each storage environment demand with the corresponding monitoring index, the difference between them is calculated to obtain a plurality of storage demand difference sets, which reflect the gap between the actual storage environment and the ideal storage environment.

[0045] The first risk identification result determination module 40 further includes judging whether the plurality of storage demand difference sets is greater than or equal to a plurality of preset tolerance difference sets, respectively, and if yes, a plurality of first risk drugs are obtained. These storage demand differences are compared with the preset tolerance difference set, and if a certain storage demand difference is greater than or equal to the corresponding preset tolerance difference, it indicates that the environment demand is not met, which may lead to damage to the quality of the drug or safety risk, and a plurality of first risk drugs are obtained, wherein the preset tolerance difference set defines the maximum deviation range that each environment demand can accept.

[0046] The first risk identification result determination module 40 further includes calculating the difference between the plurality of storage demand difference sets corresponding to the plurality of first risk drugs and the plurality of preset tolerance difference sets, and comparing the calculation result with the plurality of preset tolerance difference sets to obtain the plurality of first risk coefficients. For the drugs marked as first risk drugs, the risk degree is further calculated, i.e. the difference between the corresponding storage demand difference and the preset tolerance difference is calculated, and the difference is divided by the preset tolerance difference to obtain a plurality of first risk coefficients, which reflect the degree of unmet environment demand. The larger the coefficient, the higher the risk.

[0047] The first risk identification result determination module 40 further comprises the plurality of first risk drugs and the plurality of first risk coefficients as the first risk identification result. Outputting all the identified first risk drugs and their corresponding first risk coefficients as the first risk identification result can understand which drugs have storage risks and the specific degree of risk, so as to take corresponding measures to reduce the risk.

[0048] Next, the specific configuration of the second risk identification result determination module 50 will be described in detail. The second risk identification result determination module 50 can further comprise: randomly extracting one drug from each of the plurality of drug storage areas as a first neighbor center drug to obtain a plurality of first neighbor center drugs.

[0049] The second risk identification result determination module 50 further comprises: extracting a plurality of first drug neighborhoods of the plurality of first neighbor center drugs based on the plurality of drug storage location identifiers. A reasonable neighborhood range is defined, for example, a region within a certain physical distance centered on the center drug, or other drugs in the same shelf, the same layer or the same area. According to the defined neighborhood range, all drugs located in the range are extracted from the storage area to form the first drug neighborhood of the center drug. For each center drug, a first drug neighborhood set containing all drugs in its neighborhood is formed, and a plurality of first drug neighborhood sets corresponding to the plurality of first neighbor center drugs are obtained.

[0050] The second risk identification result determination module 50 further comprises: performing similarity identification on the plurality of first neighbor center drugs and the plurality of first drug neighborhoods according to the plurality of drug name sets and the plurality of outer packaging image sets to obtain a plurality of first neighbor similarity coefficients. Using the plurality of drug name sets and the plurality of outer packaging image sets as data sources, similarity identification is performed on each first neighbor center drug and the drugs in its corresponding first drug neighborhood, such as text similarity comparison (such as string matching or fuzzy matching of drug names), image similarity comparison (such as feature extraction and comparison of outer packaging images), etc. According to the similarity identification result, a plurality of first neighbor similarity coefficients are obtained, reflecting the similarity between the center drug and the drugs in its neighborhood.

[0051] The second risk identification result determination module 50 further comprises: performing neighbor similarity identification on the plurality of drug sets to obtain a plurality of neighbor similarity coefficient sets. In a wider range, neighbor similarity identification is performed on all drugs in each drug set. Through the same similarity identification method, a plurality of neighbor similarity coefficient sets are calculated, each set containing the similarity coefficients between all pairs of drugs in the region.

[0052] The second risk identification result determination module 50 further comprises: performing regional confusion risk identification on the plurality of neighbor similarity coefficient sets by using a preset similarity threshold to determine the second risk identification result. The similarity threshold is used to perform regional confusion risk identification on each neighbor similarity coefficient set. If the similarity coefficient between a certain drug pair exceeds the threshold, it is considered that the two drugs have confusion risk. By analyzing the similarity coefficients of all drug pairs, it can be determined which regions or which drug combinations have higher confusion risk. According to the regional confusion risk identification result, the second risk identification result is determined, that is, which regions or which drug combinations need special attention to avoid confusion errors.

[0053] Next, the specific configuration of the second risk identification result determination module 50 will be described in detail. The second risk identification result determination module 50 can further comprise: constructing a similarity identification function, wherein the similarity identification function is:

[0054] ;

[0055] wherein, is the first neighbor similarity coefficient, is the number of drugs in the first drug neighborhood, and n is a positive integer greater than or equal to 1, is the drug name of the first neighbor central drug, is the drug name of the i-th drug in the first drug neighborhood, is the outer packaging image of the first neighbor central drug, is the outer packaging image of the i-th drug in the first drug neighborhood, is the weight of the similarity degree of the drug name when performing neighbor similarity identification, is the weight of the similarity degree of the outer packaging image when performing neighbor similarity identification.

[0056] The second risk identification result determination module 50 further comprises: performing mapping matching on the plurality of first near-neighbor center medicines and the plurality of first medicine neighborhoods based on the plurality of medicine name sets and the plurality of outer packaging image sets to obtain a plurality of first near-neighbor center medicine names, a plurality of first near-neighbor center medicine outer packaging images, a plurality of first medicine neighborhood name sets and a plurality of first medicine neighborhood outer packaging image sets. For each first near-neighbor center medicine, the corresponding name is found in the medicine name set by matching the unique identifier (such as the bar code, SKU number or drug code) of the medicine to form a plurality of first near-neighbor center medicine names. Similarly, the outer packaging image corresponding to each first near-neighbor center medicine is found in the outer packaging image set to form a plurality of first near-neighbor center medicine outer packaging images. Based on the position of each first near-neighbor center medicine in the storage area, the first medicine neighborhood thereof is determined, and other medicines that are physically adjacent or close to the center medicine are usually selected as neighborhood members. For each first medicine neighborhood, each medicine therein is traversed, and the corresponding name is found in the medicine name set to obtain a plurality of first medicine neighborhood name sets. Similarly, the outer packaging image corresponding to each medicine in the neighborhood is found in the outer packaging image set to form a plurality of first medicine neighborhood outer packaging image sets.

[0057] The second risk identification result determination module 50 further comprises: inputting the plurality of first near-neighbor center medicine names, the plurality of first near-neighbor center medicine outer packaging images, the plurality of first medicine neighborhood name sets and the plurality of first medicine neighborhood outer packaging image sets into the similarity identification function respectively to obtain the plurality of first near-neighbor similarity coefficients. For each first near-neighbor center medicine, the name and the outer packaging image thereof are inputted into the similarity identification function as a set of data. For the name of the center medicine and the name of each neighborhood medicine, the text similarity algorithm in the similarity identification function is used to calculate the similarity coefficient therebetween. Similarly, for the outer packaging image of the center medicine and the outer packaging image of each neighborhood medicine, the image similarity algorithm (such as histogram comparison, feature matching, deep learning model, etc.) in the similarity identification function is used to calculate the similarity coefficient therebetween. For the name and image similarity calculation between the center medicine and each medicine in the neighborhood, a similarity coefficient is obtained. Finally, the similarity identification function outputs the plurality of first near-neighbor similarity coefficients, which reflect the similarity degree between each center medicine and each medicine in the neighborhood thereof.

[0058] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server, and the various units and modules included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of mutual differentiation, and do not limit the protection scope of the present application.

[0059] The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of specific terminology. However, embodiments thereof can be practiced with the exact description not being set forth but with the same essence. Therefore, embodiments cannot be limited to the specific details and / or the exact examples described. It should be appreciated that the specific order or hierarchy of steps in the processes can differ from what is described herein, depending on the implementation. Therefore, the process can be implemented with the order of steps differing from what is described herein.

Claims

1. A security risk management platform for multi-point collaboration analysis, characterized by, The platform comprises: a drug storage distribution data extraction module for interacting with a storage system of a target drug storage bin to extract drug storage distribution data, wherein the drug storage distribution data comprises a plurality of drug storage areas corresponding to a plurality of drug sets and a plurality of drug storage location identifiers; a drug feature set generation module for performing feature extraction on the plurality of drug sets according to preset risk features to generate a plurality of drug feature sets, wherein the plurality of drug feature sets comprise a plurality of drug name sets, a plurality of outer packaging image sets, and a plurality of storage environment requirement sets; a storage monitoring indicator set acquisition module for respectively interacting with a plurality of intelligent sensing arrays of the plurality of drug storage areas to acquire a plurality of storage monitoring indicator sets, wherein the plurality of storage monitoring indicator sets comprise a plurality of storage temperatures, a plurality of storage humidities, and a plurality of storage radiation amounts; a first risk identification result determination module for performing risk identification on the plurality of storage monitoring indicator sets based on the plurality of storage environment requirement sets to determine a first risk identification result, wherein the first risk identification result comprises a plurality of first risk drugs and a plurality of first risk coefficients; a second risk identification result determination module for performing regional confusion risk identification based on the plurality of drug name sets, the plurality of outer packaging image sets, the plurality of drug sets, and the plurality of drug storage location identifiers to determine a second risk identification result, wherein the second risk identification result comprises a plurality of risk regions and a plurality of second risk coefficients; a safety risk management module for performing safety risk management according to the plurality of first risk drugs, the plurality of first risk coefficients, the plurality of risk regions, and the plurality of second risk coefficients; a plurality of first neighbor center drugs are randomly extracted from a plurality of drug sets of the plurality of drug storage areas; a plurality of first drug neighborhoods of the plurality of first neighbor center drugs are extracted based on the plurality of drug storage location identifiers; a plurality of first neighbor similarity coefficients are obtained by performing similarity identification on the plurality of first neighbor center drugs and the plurality of first drug neighborhoods according to the plurality of drug name sets and the plurality of outer packaging image sets; a plurality of neighbor similarity coefficient sets are obtained by performing neighbor similarity identification on the plurality of drug sets; the second risk identification result is determined by performing regional confusion risk identification on the plurality of neighbor similarity coefficient sets using a preset similarity threshold; a similarity identification function is constructed, wherein the similarity identification function is: ； wherein, is a first neighbor similarity coefficient, is a number of drugs in the first drug neighborhood, n is a positive integer greater than or equal to 1, is a drug name of the first neighbor central drug, is a drug name of the i-th drug in the first drug neighborhood, is an outer package image of the first neighbor central drug, is an outer package image of the i-th drug in the first drug neighborhood, is a weight of a similarity degree of a drug name in performing neighbor similarity identification, is a weight of a similarity degree of an outer package image in performing neighbor similarity identification. a plurality of first neighbor center drug names, a plurality of first neighbor center drug outer packaging images, a plurality of first drug neighborhood name sets, and a plurality of first drug neighborhood outer packaging image sets are obtained by performing mapping matching on the plurality of first neighbor center drugs and the plurality of first drug neighborhoods according to the plurality of drug name sets and the plurality of outer packaging image sets; the plurality of first neighbor similarity coefficients are obtained by inputting the plurality of first neighbor center drug names, the plurality of first neighbor center drug outer packaging images, the plurality of first drug neighborhood name sets, and the plurality of first drug neighborhood outer packaging image sets into the similarity identification function.

2. The platform for security risk management of multi-point coordination analysis of claim 1, wherein, The preset risk features include drug name, outer packaging image, storage environment requirement.

3. The platform for security risk management of multi-point coordination analysis of claim 1, wherein, The method comprises the following steps: Respectively collecting data of the preset verification window of the plurality of intelligent sensing arrays, to generate a plurality of verification temperature sequence sets, a plurality of verification humidity sequence sets and a plurality of verification radiation sequence sets; Respectively performing normalization processing on the plurality of verification temperature sequence sets, the plurality of verification humidity sequence sets and the plurality of verification radiation sequence sets, to obtain a plurality of normalized verification temperature sequence sets, a plurality of normalized verification humidity sequence sets and a plurality of normalized verification radiation sequence sets; Respectively performing window alignment on the plurality of normalized verification temperature sequence sets, the plurality of normalized verification humidity sequence sets and the plurality of normalized verification radiation sequence sets, and synchronously distributing them to a plurality of verification fitting branches to generate a plurality of verification fitting spaces, wherein the plurality of verification fitting spaces comprise a plurality of verification fitting particle sets; Performing linear fitting on the plurality of verification fitting particle sets in the plurality of verification fitting spaces, and performing feasibility authentication on the plurality of intelligent sensing arrays according to the linear fitting result; when the authentication is passed, the plurality of intelligent sensing arrays are used to respectively monitor the plurality of drug storage areas to generate a plurality of storage monitoring index sets, wherein the linear fitting result comprises a plurality of fitting straight lines.

4. The security risk management platform for multi-point coordination analysis of claim 3, wherein, The method comprises the following steps: Respectively randomly generating a plurality of starting straight lines in the plurality of verification fitting spaces, and counting the number of verification fitting particles with a distance to the plurality of starting straight lines being a preset bandwidth to generate a plurality of starting fitting amounts; According to the preset bandwidth and the plurality of starting fitting amounts, iteratively updating the plurality of starting straight lines in the plurality of verification fitting spaces to obtain a plurality of iterative straight lines; According to a preset angle step, iteratively updating the plurality of iterative straight lines in the plurality of verification fitting spaces to obtain a plurality of angle iterative straight lines; Judging whether the fitting amount difference between the plurality of angle iterative straight lines and the plurality of iterative straight lines satisfies a preset fitting amount difference; if yes, the plurality of angle iterative straight lines are taken as a plurality of fitting straight lines.

5. The security risk management platform for multi-point coordination analysis of claim 3, wherein, The method comprises the following steps: Extracting a plurality of slopes of the plurality of fitting straight lines; Judging whether the plurality of slopes is less than or equal to a preset slope threshold; if yes, the authentication is passed; If not, the authentication is failed, a sensing risk instruction is generated, and the sensing risk instruction is sent to a worker.

6. The platform for security risk management of multi-point coordination analysis of claim 1, wherein, The method comprises the following steps: According to the plurality of storage environment requirement sets and the plurality of storage monitoring index sets, performing requirement difference calculation to obtain a plurality of storage requirement difference sets; Respectively judging whether the plurality of storage requirement difference sets is greater than or equal to a plurality of preset tolerance difference sets; if yes, a plurality of first risk drugs are obtained; Calculating the difference between the plurality of storage requirement difference sets corresponding to the plurality of first risk drugs and the plurality of preset tolerance difference sets, and comparing the calculation result with the plurality of preset tolerance difference sets to obtain a plurality of first risk coefficients; Taking the plurality of first risk drugs and the plurality of first risk coefficients as the first risk identification result.

Images