Medicine supplier holographic monitoring method and system based on risk assessment

Abstract

The invention relates to the technical field of medicine supplier monitoring, in particular to a medicine supplier holographic monitoring method and system based on risk assessment, and the method comprises the steps: carrying out the data preprocessing of collected target medicine supplier risk control data, and generating target medicine supplier risk control feature data; performing data search processing on the established medicine supplier risk type feature data to generate target medicine supplier risk type data, and searching matched weight data from the established medicine supplier risk type weight data set, the method comprises the steps of obtaining target medicine supplier risk type weight data, calculating a target medicine supplier risk assessment value, performing numerical comparison on the target medicine supplier risk assessment value and a set risk threshold value, generating target medicine supplier risk level data according to a numerical comparison result, and finally constructing target medicine supplier monitoring data. And the information is pushed to a medical supplier holographic monitoring platform, so that holographic monitoring and risk assessment of the medical suppliers are scientifically realized.

Description

Technical Field

[0001] The present invention relates to the technical field of pharmaceutical supplier monitoring, and in particular to a pharmaceutical supplier holographic monitoring method and system based on risk assessment. Background Art

[0002] With the continuous development of the pharmaceutical industry, the reliability of pharmaceutical suppliers is crucial to the normal operation of the entire pharmaceutical supply chain. However, existing pharmaceutical supplier monitoring methods often have many shortcomings and cannot evaluate pharmaceutical suppliers in multiple dimensions.

[0003] The Chinese invention patent application with publication number CN118153964A introduces a supplier enterprise risk assessment method and system based on big data technology. The method reads the enterprise information data and business operation data of the supplier enterprise, selects appropriate summary models, risk sniffing models, feature models and risk assessment models to analyze and process the enterprise information data and business operation data in turn, generates and displays a business operation summary and risk assessment results, ensures the reference value of the business operation summary and the accuracy and reliability of the risk assessment results, but cannot achieve scientific classification of supplier enterprises, and it is difficult to directly select the required supplier enterprises based on the analysis results. Summary of the invention

[0004] 1. Technical issues to be resolved In order to solve the deficiencies in the background technology, the present invention provides a holographic monitoring method and system for pharmaceutical suppliers based on risk assessment, which scientifically realizes holographic monitoring and risk assessment of pharmaceutical suppliers.

[0005] (II) Technical solution A holographic monitoring method for pharmaceutical suppliers based on risk assessment comprises the following steps: S1. Collect risk control data of target pharmaceutical suppliers; S2. Preprocess the risk control data of the target pharmaceutical supplier to generate risk control feature data of the target pharmaceutical supplier; S3. Establish risk type characteristic data of pharmaceutical suppliers; S4, performing a target pharmaceutical supplier risk type search process on the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data to generate target pharmaceutical supplier risk type data; S5. Establish a pharmaceutical supplier risk type weight data set, and search for pharmaceutical supplier risk type weight data corresponding to the target pharmaceutical supplier risk type data to obtain the target pharmaceutical supplier risk type weight data; S6. Calculate the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data, compare the value with the set risk threshold, and generate the target pharmaceutical supplier risk level data according to the numerical comparison result; S7. Build target pharmaceutical supplier monitoring data based on the target pharmaceutical supplier risk assessment value and the target pharmaceutical supplier risk level data, and push it to the pharmaceutical supplier holographic monitoring platform.

[0006] The present invention generates target pharmaceutical supplier risk control feature data by performing data preprocessing on the collected target pharmaceutical supplier risk control data, performs data search processing on the established pharmaceutical supplier risk type feature data, generates target pharmaceutical supplier risk type data, searches for matching weight data from the established pharmaceutical supplier risk type weight data set, obtains the target pharmaceutical supplier risk type weight data and calculates the target pharmaceutical supplier risk assessment value, compares the target pharmaceutical supplier risk assessment value with the set risk threshold, analyzes the risk level of the target pharmaceutical supplier, generates target pharmaceutical supplier risk level data, and finally constructs target pharmaceutical supplier monitoring data and pushes it to the pharmaceutical supplier holographic monitoring platform, thereby scientifically realizing holographic monitoring and risk assessment of pharmaceutical suppliers.

[0007] Preferably, the specific steps for collecting risk control data of target pharmaceutical suppliers are as follows: S11. Collect various risk control data of target pharmaceutical suppliers online through the pharmaceutical supplier data management platform to obtain the target pharmaceutical supplier risk control data set ,in, Indicates that the first Risk control data, Indicates the total number of risk control data of the target pharmaceutical supplier, where the risk control data includes but is not limited to any one of industrial and commercial data, judicial data, tax data, invoice data, credit data and public opinion data.

[0008] Preferably, the specific steps of preprocessing the target pharmaceutical supplier risk control data to generate the target pharmaceutical supplier risk control feature data are as follows: S21. Use the exponential sliding filter method to perform data noise reduction on the target pharmaceutical supplier risk control data in the target pharmaceutical supplier risk control data set to generate a target pharmaceutical supplier risk control feature data set. ,in, Indicates that the first The target pharmaceutical supplier’s risk control characteristic data is obtained after data noise reduction processing of the risk control data.

[0009] The exponential sliding filtering method is used to perform data noise reduction processing on the risk control data of the target pharmaceutical supplier, accurately remove the noise data in the risk control data of the target pharmaceutical supplier, effectively reduce the impact of the noise data, and ensure the reliability and accuracy of the acquired data.

[0010] Preferably, the specific steps for establishing risk type characteristic data of pharmaceutical suppliers are as follows: S31. Establishing a risk type characteristic dataset for pharmaceutical suppliers ,in, Indicates the appearance of The risk control characteristic data of pharmaceutical suppliers when the risk type of pharmaceutical suppliers is Indicates the total number of risk type feature data of pharmaceutical suppliers, where the risk types of pharmaceutical suppliers include but are not limited to industrial and commercial change information, abnormal taxable sales, false invoices, tax evasion, violent tax resistance, abnormal corporate credit, a large number of negative public opinions, and abnormal personal credit.

[0011] Preferably, the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data are subjected to a target pharmaceutical supplier risk type search process, and the specific steps of generating the target pharmaceutical supplier risk type data are as follows: S41. Traverse each target pharmaceutical supplier risk control feature data in the target pharmaceutical supplier risk control feature data set through the flood optimization algorithm, and perform target pharmaceutical supplier risk type search processing with the pharmaceutical supplier risk type feature data in the pharmaceutical supplier risk type feature data set in order of the target pharmaceutical supplier risk control feature data number from small to large, and generate target pharmaceutical supplier risk determination data according to the search results; if the target pharmaceutical supplier risk determination data is risk-free, add the target pharmaceutical supplier to the list of strategic suppliers, and push the target pharmaceutical supplier risk determination data to the pharmaceutical supplier holographic monitoring platform through the Internet of Things communication network, and end the pharmaceutical supplier holographic monitoring operation at the same time; if the target pharmaceutical supplier risk determination data is risky, generate a target pharmaceutical supplier risk type data set; S411, taking the risk control feature data of each target pharmaceutical supplier in the risk control feature data set of the target pharmaceutical supplier as sample data in order from small to large according to the risk control feature data number of the target pharmaceutical supplier; S412, construct water flow population, set the water flow population size to , the current number of iterations is The maximum number of iterations is , the search space dimension of risk type feature data of pharmaceutical suppliers is ; The pharmaceutical supplier risk type feature data set is used as a pharmaceutical supplier risk type feature data search space, and a random The risk type characteristic data of each medical supplier corresponds to a water flow individual in the water flow population. The initial position set of the water flow population is initialized as ,in, Indicates the first The initial position of each individual flow; S413, calculating the fitness function value of each water flow individual in the water flow population, arranging each water flow individual in the water flow population from large to small according to the fitness function value, and selecting the water flow individual with the highest fitness function value as the current optimal individual; the fitness function formula is as follows: , in, Indicates the first The fitness function value of each water flow individual, Indicates the first The deviation between the risk type characteristic data of the pharmaceutical supplier corresponding to each individual in the water flow and the sample data, Indicates the correction value; S414, calculating the water consumption coefficient of each individual water flow in the water flow population in the current iteration process ; The calculation formula is as follows: , in, Indicates the water consumption coefficient of each individual water flow in the water flow population in the current iteration process; S415, calculating the water flow permeability coefficient of each water flow individual in the water flow population in the risk type characteristic data search space of the pharmaceutical supplier ; The calculation formula of water flow permeability coefficient is as follows: , in, Indicates the first The flow permeability coefficient of each individual flow is and Respectively represent the maximum value and the minimum value of the fitness function of each individual water flow in the water flow population; Each individual water flow in the water flow population will update its position in the medical supplier risk type feature data search space according to the water flow permeability coefficient to control the probability of flood occurrence; the position update formula is as follows: , in, Indicates the first The position of each individual water flow after the position update, and Respectively represent the first and The location of each individual water flow, , and Both represent random numbers that are uniformly distributed between (0,1). and They respectively represent the search upper limit and search lower limit of the search space of the risk type feature data of the pharmaceutical supplier, Indicates the position of the current optimal individual; S416. Each individual water flow in the water flow population will change the water volume in the watershed according to probability in the search space of the risk type characteristic data of the pharmaceutical supplier to update its position. The position update formula is as follows: , in, and Both represent random numbers that are uniformly distributed between (0,1); S417, calculating the fitness function value of each water flow individual in the water flow population after the position is updated, arranging each water flow individual in the water flow population from large to small according to the fitness function value, and selecting the water flow individual with the highest fitness function value as the current optimal individual; if the fitness function value of the water flow individual is greater than the original fitness function value, replacing the original position with the new position; otherwise, retaining the original position; When the fitness function value of a water flow individual is greater than the fitness function value of the current optimal individual, the water flow individual is used as the new current optimal individual; S418, determine the current number of iterations Is it less than the maximum number of iterations? , if the current number of iterations Less than the maximum number of iterations , then the current number of iterations Add 1 and return to S414; otherwise, take the current optimal individual as the global optimal solution; A fitness function threshold is set. If the fitness function value of the global optimal solution is greater than the fitness function threshold, it is determined that the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution matches the sample data successfully, and the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution is retained; if the fitness function value of the global optimal solution is less than or equal to the fitness function threshold, it is determined that the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution matches the sample data unsuccessfully, and the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution is discarded; S419, repeat the operations from S411 to S418 until all target pharmaceutical supplier risk control feature data in the target pharmaceutical supplier risk control feature data set are traversed. If there is no pharmaceutical supplier risk type feature data that successfully matches each sample data, the target pharmaceutical supplier risk determination data is output as no risk; otherwise, the target pharmaceutical supplier risk determination data is output as risk, and the pharmaceutical supplier risk types corresponding to all retained pharmaceutical supplier risk type feature data are combined to generate a target pharmaceutical supplier risk type data set. ,in, Indicates Target pharmaceutical supplier risk type data, Represents the total number of risk type data of target pharmaceutical suppliers.

[0012] The target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data are processed through the flood optimization algorithm to search for the target pharmaceutical supplier risk type, thereby achieving accurate identification of the target pharmaceutical supplier risk type, improving the reliability and accuracy of the target pharmaceutical supplier risk type search, and at the same time improving the speed and efficiency of the search process, and being able to quickly analyze the risk type of the target pharmaceutical supplier.

[0013] Preferably, a pharmaceutical supplier risk type weight data set is established, and pharmaceutical supplier risk type weight data corresponding to the target pharmaceutical supplier risk type data is searched out. The specific steps of obtaining the target pharmaceutical supplier risk type weight data are as follows: S51. Preset corresponding pharmaceutical supplier risk type weight data for each pharmaceutical supplier risk type feature data in the pharmaceutical supplier risk type feature data set through the pharmaceutical supplier risk type data entry interface to obtain a pharmaceutical supplier risk type weight data set. ,in, Indicates Weight data corresponding to the risk types of each pharmaceutical supplier; S52: traverse all the pharmaceutical supplier risk type weight data in the pharmaceutical supplier risk type weight data set by using a deep search algorithm, search for pharmaceutical supplier risk type weight data that matches the pharmaceutical supplier risk type corresponding to each target pharmaceutical supplier risk type data in the target pharmaceutical supplier risk type data set, and perform data identification to obtain the target pharmaceutical supplier risk type weight data set. ,in, Indicates The weight data corresponding to the risk type data of each target pharmaceutical supplier.

[0014] Preferably, the target pharmaceutical supplier risk assessment value is calculated based on the target pharmaceutical supplier risk type weight data, and a numerical comparison is performed with a set risk threshold value, and the specific steps of generating the target pharmaceutical supplier risk level data according to the numerical comparison result are as follows: S61, calculating the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data in the target pharmaceutical supplier risk type weight data set. ; S62, setting the first risk threshold and the second risk threshold is ; S63, the target pharmaceutical supplier risk assessment value , First risk threshold and the second risk threshold Perform numerical comparison and generate target pharmaceutical supplier risk level data based on the numerical comparison results ; like , then the target pharmaceutical supplier risk level data is output as mild risk, and the target pharmaceutical supplier is added to the list of suppliers to be investigated; like , then the target pharmaceutical supplier risk level data is output as medium risk, and the target pharmaceutical supplier is added to the list of eliminated suppliers; like , the target pharmaceutical supplier risk level data is output as severe risk, and the target pharmaceutical supplier is added to the supplier blacklist.

[0015] By calculating the risk assessment value of the target pharmaceutical supplier and performing numerical analysis with the set risk threshold, the target pharmaceutical supplier is divided into different risk levels according to the numerical analysis results, and the target pharmaceutical supplier is added to the corresponding supplier list according to the risk level. When the risk level is mild, the target pharmaceutical supplier is added to the list of suppliers to be investigated; when the risk level is moderate, the target pharmaceutical supplier is added to the list of eliminated suppliers; when the risk level is severe, the target pharmaceutical supplier is added to the supplier blacklist; the risk level of the pharmaceutical supplier is accurately identified to achieve intelligent monitoring of the pharmaceutical supplier.

[0016] Preferably, the specific steps of constructing the target pharmaceutical supplier monitoring data based on the target pharmaceutical supplier risk assessment value and the target pharmaceutical supplier risk level data and pushing the target pharmaceutical supplier monitoring data to the pharmaceutical supplier holographic monitoring platform are as follows: S71, the target pharmaceutical supplier risk assessment value and risk level data of the target pharmaceutical suppliers Combine data to construct monitoring data of target pharmaceutical suppliers ; S72, transmitting the target pharmaceutical supplier monitoring data through the Internet of Things communication network Push to the pharmaceutical supplier holographic monitoring platform and end the pharmaceutical supplier holographic monitoring operation.

[0017] The present invention also discloses a holographic monitoring system for pharmaceutical suppliers based on risk assessment, including a target pharmaceutical supplier risk control data acquisition module, a target pharmaceutical supplier risk control data preprocessing module, a pharmaceutical supplier risk type characteristic data establishment module, a target pharmaceutical supplier risk type identification module, a target pharmaceutical supplier risk type weight search module, a target pharmaceutical supplier risk level determination module and a target pharmaceutical supplier monitoring data construction module; The target pharmaceutical supplier risk control data collection module collects various risk control data of the target pharmaceutical supplier online through the pharmaceutical supplier data management platform to obtain the target pharmaceutical supplier risk control data; The target pharmaceutical supplier risk control data preprocessing module uses an exponential sliding filter method to perform data noise reduction processing on the target pharmaceutical supplier risk control data in the target pharmaceutical supplier risk control data set to generate target pharmaceutical supplier risk control feature data; The pharmaceutical supplier risk type characteristic data establishment module establishes pharmaceutical supplier risk type characteristic data by collecting risk control characteristic data of pharmaceutical suppliers when different pharmaceutical supplier risk types occur; The target pharmaceutical supplier risk type identification module searches for the target pharmaceutical supplier risk type using the flood optimization algorithm for the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data, and generates target pharmaceutical supplier risk determination data based on the search results. If the target pharmaceutical supplier risk determination data is no risk, the pharmaceutical supplier holographic monitoring operation is terminated; if the target pharmaceutical supplier risk determination data is risky, a target pharmaceutical supplier risk type data set is generated; The target pharmaceutical supplier risk type weight search module presets corresponding weight data for the pharmaceutical supplier risk type characteristic data through the pharmaceutical supplier risk type data entry interface to obtain pharmaceutical supplier risk type weight data, and uses a deep search algorithm to search for pharmaceutical supplier risk type weight data corresponding to the target pharmaceutical supplier risk type data to obtain the target pharmaceutical supplier risk type weight data; The target pharmaceutical supplier risk level determination module calculates the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data, compares the value with the set risk threshold, and generates the target pharmaceutical supplier risk level data according to the value comparison result; The target pharmaceutical supplier monitoring data construction module constructs the target pharmaceutical supplier monitoring data by combining the target pharmaceutical supplier risk assessment value and the target pharmaceutical supplier risk level data, and pushes it to the pharmaceutical supplier holographic monitoring platform through the Internet of Things communication network, and simultaneously ends this pharmaceutical supplier holographic monitoring operation.

[0018] (III) Beneficial effects 1. The present invention performs data preprocessing on the collected risk control data of the target pharmaceutical supplier to generate the risk control characteristic data of the target pharmaceutical supplier, performs data search processing with the established risk type characteristic data of the pharmaceutical supplier to generate the risk type data of the target pharmaceutical supplier, searches for matching weight data from the established pharmaceutical supplier risk type weight data set, obtains the risk type weight data of the target pharmaceutical supplier and calculates the risk assessment value of the target pharmaceutical supplier, compares the risk assessment value of the target pharmaceutical supplier with the set risk threshold, analyzes the risk level of the target pharmaceutical supplier, generates the risk level data of the target pharmaceutical supplier, and finally constructs the monitoring data of the target pharmaceutical supplier and pushes it to the pharmaceutical supplier holographic monitoring platform, so as to scientifically realize the holographic monitoring and risk assessment of the pharmaceutical supplier; 2. Use the exponential sliding filter method to perform data noise reduction on the risk control data of the target pharmaceutical supplier, accurately remove the noise data in the risk control data of the target pharmaceutical supplier, effectively reduce the impact of the noise data, and ensure the reliability and accuracy of the acquired data; 3. The target pharmaceutical supplier risk type search is performed on the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data through the flood optimization algorithm, so as to achieve accurate identification of the target pharmaceutical supplier risk type, improve the reliability and accuracy of the target pharmaceutical supplier risk type search, and at the same time improve the speed and efficiency of the search process, so as to quickly analyze the risk type of the target pharmaceutical supplier; 4. By calculating the risk assessment value of the target pharmaceutical supplier and performing numerical analysis with the set risk threshold, the target pharmaceutical supplier is divided into different risk levels according to the numerical analysis results, and the target pharmaceutical supplier is added to the corresponding supplier list according to the risk level. When the risk level is mild, the target pharmaceutical supplier is added to the list of suppliers to be investigated; when the risk level is moderate, the target pharmaceutical supplier is added to the list of eliminated suppliers; when the risk level is severe, the target pharmaceutical supplier is added to the supplier blacklist; the risk level of the pharmaceutical supplier is accurately identified to realize intelligent monitoring of the pharmaceutical supplier. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0020] Figure 1 A flow chart of a holographic monitoring method for pharmaceutical suppliers based on risk assessment provided by the present invention; Figure 2 A module schematic diagram of a risk assessment-based holographic monitoring system for pharmaceutical suppliers provided by the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0023] Embodiment 1 is as follows: See also Figure 1 , a holographic monitoring method for pharmaceutical suppliers based on risk assessment, comprising the following steps: S1. Collect risk control data of target pharmaceutical suppliers; S11. Collect various risk control data of target pharmaceutical suppliers online through the pharmaceutical supplier data management platform to obtain the target pharmaceutical supplier risk control data set ,in, Indicates that the first Risk control data, Indicates the total number of risk control data of the target pharmaceutical supplier, where the risk control data includes but is not limited to any one of industrial and commercial data, judicial data, tax data, invoice data, credit data and public opinion data.

[0024] S2. Preprocess the risk control data of the target pharmaceutical supplier to generate risk control feature data of the target pharmaceutical supplier; S21. Use the exponential sliding filter method to perform data noise reduction on the target pharmaceutical supplier risk control data in the target pharmaceutical supplier risk control data set to generate a target pharmaceutical supplier risk control feature data set. ,in, Indicates that the first The target pharmaceutical supplier’s risk control characteristic data is obtained after data noise reduction processing of the risk control data.

[0025] S3. Establish risk type characteristic data of pharmaceutical suppliers; S31. Establishing a risk type characteristic dataset for pharmaceutical suppliers ,in, Indicates the appearance of The risk control characteristic data of pharmaceutical suppliers when the risk type of pharmaceutical suppliers is Indicates the total number of risk type feature data of pharmaceutical suppliers, where the risk types of pharmaceutical suppliers include but are not limited to industrial and commercial change information, abnormal taxable sales, false invoices, tax evasion, violent tax resistance, abnormal corporate credit, a large number of negative public opinions, and abnormal personal credit.

[0026] S4, performing a target pharmaceutical supplier risk type search process on the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data to generate target pharmaceutical supplier risk type data; S41. Traverse each target pharmaceutical supplier risk control feature data in the target pharmaceutical supplier risk control feature data set through the flood optimization algorithm, and perform target pharmaceutical supplier risk type search processing with the pharmaceutical supplier risk type feature data in the pharmaceutical supplier risk type feature data set in order of the target pharmaceutical supplier risk control feature data number from small to large, and generate target pharmaceutical supplier risk determination data according to the search results; if the target pharmaceutical supplier risk determination data is risk-free, add the target pharmaceutical supplier to the list of strategic suppliers, and push the target pharmaceutical supplier risk determination data to the pharmaceutical supplier holographic monitoring platform through the Internet of Things communication network, and end the pharmaceutical supplier holographic monitoring operation at the same time; if the target pharmaceutical supplier risk determination data is risky, generate a target pharmaceutical supplier risk type data set; S411, taking the risk control feature data of each target pharmaceutical supplier in the risk control feature data set of the target pharmaceutical supplier as sample data in order from small to large according to the risk control feature data number of the target pharmaceutical supplier; S412, construct water flow population, set the water flow population size to , the current number of iterations is The maximum number of iterations is , the search space dimension of risk type feature data of pharmaceutical suppliers is ; The pharmaceutical supplier risk type feature data set is used as a pharmaceutical supplier risk type feature data search space, and a random The risk type characteristic data of each medical supplier corresponds to a water flow individual in the water flow population. The initial position set of the water flow population is initialized as ,in, Indicates the first The initial position of each individual flow; S413, calculating the fitness function value of each water flow individual in the water flow population, arranging each water flow individual in the water flow population from large to small according to the fitness function value, and selecting the water flow individual with the highest fitness function value as the current optimal individual; the fitness function formula is as follows: , in, Indicates the first The fitness function value of each water flow individual, Indicates the first The deviation between the risk type characteristic data of the pharmaceutical supplier corresponding to each individual in the water flow and the sample data, Indicates the correction value; S414, calculating the water consumption coefficient of each individual water flow in the water flow population in the current iteration process ; The calculation formula is as follows: , in, Indicates the water consumption coefficient of each individual water flow in the water flow population in the current iteration process; S415, calculating the water flow permeability coefficient of each water flow individual in the water flow population in the risk type characteristic data search space of the pharmaceutical supplier ; The calculation formula of water flow permeability coefficient is as follows: , in, Indicates the first The flow permeability coefficient of each individual flow is and Respectively represent the maximum value and the minimum value of the fitness function of each individual water flow in the water flow population; Each individual water flow in the water flow population will update its position in the medical supplier risk type feature data search space according to the water flow permeability coefficient to control the probability of flood occurrence; the position update formula is as follows: , in, Indicates the first The position of each individual water flow after the position update, and Respectively represent the first and The location of each individual water flow, , and Both represent random numbers that are uniformly distributed between (0,1). and They respectively represent the search upper limit and search lower limit of the search space of the risk type feature data of the pharmaceutical supplier, Indicates the position of the current optimal individual; S416. Each individual water flow in the water flow population will change the water volume in the watershed according to probability in the search space of the risk type characteristic data of the pharmaceutical supplier to update its position. The position update formula is as follows: , in, and Both represent random numbers that are uniformly distributed between (0,1); S417, calculating the fitness function value of each water flow individual in the water flow population after the position is updated, arranging each water flow individual in the water flow population from large to small according to the fitness function value, and selecting the water flow individual with the highest fitness function value as the current optimal individual; if the fitness function value of the water flow individual is greater than the original fitness function value, replacing the original position with the new position; otherwise, retaining the original position; When the fitness function value of a water flow individual is greater than the fitness function value of the current optimal individual, the water flow individual is used as the new current optimal individual; S418, determine the current number of iterations Is it less than the maximum number of iterations? , if the current number of iterations Less than the maximum number of iterations , then the current number of iterations Add 1 and return to S414; otherwise, take the current optimal individual as the global optimal solution; A fitness function threshold is set. If the fitness function value of the global optimal solution is greater than the fitness function threshold, it is determined that the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution matches the sample data successfully, and the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution is retained; if the fitness function value of the global optimal solution is less than or equal to the fitness function threshold, it is determined that the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution matches the sample data unsuccessfully, and the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution is discarded; S419, repeat the operations from S411 to S418 until all target pharmaceutical supplier risk control feature data in the target pharmaceutical supplier risk control feature data set are traversed. If there is no pharmaceutical supplier risk type feature data that successfully matches each sample data, the target pharmaceutical supplier risk determination data is output as no risk; otherwise, the target pharmaceutical supplier risk determination data is output as risk, and the pharmaceutical supplier risk types corresponding to all retained pharmaceutical supplier risk type feature data are combined to generate a target pharmaceutical supplier risk type data set. ,in, Indicates Target pharmaceutical supplier risk type data, Represents the total number of risk type data of target pharmaceutical suppliers.

[0027] S5. Establish a pharmaceutical supplier risk type weight data set, and search for pharmaceutical supplier risk type weight data corresponding to the target pharmaceutical supplier risk type data to obtain the target pharmaceutical supplier risk type weight data; S51. Preset corresponding pharmaceutical supplier risk type weight data for each pharmaceutical supplier risk type feature data in the pharmaceutical supplier risk type feature data set through the pharmaceutical supplier risk type data entry interface to obtain a pharmaceutical supplier risk type weight data set. ,in, Indicates Weight data corresponding to the risk types of each pharmaceutical supplier; S52: traverse all the pharmaceutical supplier risk type weight data in the pharmaceutical supplier risk type weight data set by using a deep search algorithm, search for pharmaceutical supplier risk type weight data that matches the pharmaceutical supplier risk type corresponding to each target pharmaceutical supplier risk type data in the target pharmaceutical supplier risk type data set, and perform data identification to obtain the target pharmaceutical supplier risk type weight data set. ,in, Indicates The weight data corresponding to the risk type data of each target pharmaceutical supplier.

[0028] S6. Calculate the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data, compare the value with the set risk threshold, and generate the target pharmaceutical supplier risk level data according to the numerical comparison result; S61, calculating the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data in the target pharmaceutical supplier risk type weight data set. ; S62, setting the first risk threshold and the second risk threshold is ; S63, the target pharmaceutical supplier risk assessment value , First risk threshold and the second risk threshold Perform numerical comparison and generate target pharmaceutical supplier risk level data based on the numerical comparison results ; like , then the target pharmaceutical supplier risk level data is output as mild risk, and the target pharmaceutical supplier is added to the list of suppliers to be investigated; like , then the target pharmaceutical supplier risk level data is output as medium risk, and the target pharmaceutical supplier is added to the list of eliminated suppliers; like , the target pharmaceutical supplier risk level data is output as severe risk, and the target pharmaceutical supplier is added to the supplier blacklist.

[0029] S7. Constructing target pharmaceutical supplier monitoring data based on the target pharmaceutical supplier risk assessment value and the target pharmaceutical supplier risk level data, and pushing the data to the pharmaceutical supplier holographic monitoring platform; S71, the target pharmaceutical supplier risk assessment value and risk level data of the target pharmaceutical suppliers Combine data to construct monitoring data of target pharmaceutical suppliers ; S72, transmitting the target pharmaceutical supplier monitoring data through the Internet of Things communication network Push to the pharmaceutical supplier holographic monitoring platform and end the pharmaceutical supplier holographic monitoring operation.

[0030] Embodiment 2 is as follows: See also Figure 2 , a holographic monitoring system for pharmaceutical suppliers based on risk assessment, including a target pharmaceutical supplier risk control data acquisition module, a target pharmaceutical supplier risk control data preprocessing module, a pharmaceutical supplier risk type characteristic data establishment module, a target pharmaceutical supplier risk type identification module, a target pharmaceutical supplier risk type weight search module, a target pharmaceutical supplier risk level determination module and a target pharmaceutical supplier monitoring data construction module; The target pharmaceutical supplier risk control data collection module collects various risk control data of the target pharmaceutical supplier online through the pharmaceutical supplier data management platform to obtain the target pharmaceutical supplier risk control data; The target pharmaceutical supplier risk control data preprocessing module uses an exponential sliding filter method to perform data noise reduction processing on the target pharmaceutical supplier risk control data in the target pharmaceutical supplier risk control data set to generate target pharmaceutical supplier risk control feature data; The pharmaceutical supplier risk type characteristic data establishment module establishes pharmaceutical supplier risk type characteristic data by collecting risk control characteristic data of pharmaceutical suppliers when different pharmaceutical supplier risk types occur; The target pharmaceutical supplier risk type identification module searches for the target pharmaceutical supplier risk type using the flood optimization algorithm for the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data, and generates target pharmaceutical supplier risk determination data based on the search results. If the target pharmaceutical supplier risk determination data is no risk, the pharmaceutical supplier holographic monitoring operation is terminated; if the target pharmaceutical supplier risk determination data is risky, a target pharmaceutical supplier risk type data set is generated; The target pharmaceutical supplier risk type weight search module presets corresponding weight data for the pharmaceutical supplier risk type characteristic data through the pharmaceutical supplier risk type data entry interface to obtain pharmaceutical supplier risk type weight data, and uses a deep search algorithm to search for pharmaceutical supplier risk type weight data corresponding to the target pharmaceutical supplier risk type data to obtain the target pharmaceutical supplier risk type weight data; The target pharmaceutical supplier risk level determination module calculates the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data, compares the value with the set risk threshold, and generates the target pharmaceutical supplier risk level data according to the value comparison result; The target pharmaceutical supplier monitoring data construction module constructs the target pharmaceutical supplier monitoring data by combining the target pharmaceutical supplier risk assessment value and the target pharmaceutical supplier risk level data, and pushes it to the pharmaceutical supplier holographic monitoring platform through the Internet of Things communication network, and simultaneously ends this pharmaceutical supplier holographic monitoring operation.

[0031] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0032] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A holographic monitoring method for pharmaceutical suppliers based on risk assessment, characterized in that: The steps include: S1. Collect risk control data of target pharmaceutical suppliers; S2. Preprocess the risk control data of the target pharmaceutical supplier to generate risk control feature data of the target pharmaceutical supplier; S3. Establish risk type characteristic data of pharmaceutical suppliers; S4, performing a target pharmaceutical supplier risk type search process on the target pharmaceutical supplier risk control feature data and the pharmaceutical supplier risk type feature data to generate target pharmaceutical supplier risk type data; S5. Establish a pharmaceutical supplier risk type weight data set, and search for pharmaceutical supplier risk type weight data corresponding to the target pharmaceutical supplier risk type data to obtain the target pharmaceutical supplier risk type weight data; S6. Calculate the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data, compare the value with the set risk threshold, and generate the target pharmaceutical supplier risk level data according to the numerical comparison result; S7. Construct target pharmaceutical supplier monitoring data based on the target pharmaceutical supplier risk assessment value and the target pharmaceutical supplier risk level data, and push it to the pharmaceutical supplier holographic monitoring platform.

2. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 1, characterized in that: The S1 comprises the following steps: S11. Collect various risk control data of target pharmaceutical suppliers online through the pharmaceutical supplier data management platform to obtain the target pharmaceutical supplier risk control data set ,in, Indicates that the first Risk control data, Indicates the total number of risk control data of the target pharmaceutical supplier.

3. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 2, characterized in that: The S2 comprises the following steps: S21. Use the exponential sliding filter method to perform data noise reduction on the target pharmaceutical supplier risk control data in the target pharmaceutical supplier risk control data set to generate a target pharmaceutical supplier risk control feature data set. ,in, Indicates that the first The target pharmaceutical supplier’s risk control characteristic data is obtained after data noise reduction processing of the risk control data.

4. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 3, characterized in that: The S3 comprises the following steps: S31. Establishing a risk type characteristic dataset for pharmaceutical suppliers ,in, Indicates the appearance of The risk control characteristic data of pharmaceutical suppliers when the risk type of pharmaceutical suppliers is Represents the total number of risk type characteristic data of pharmaceutical suppliers.

5. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 4, characterized in that: The S4 comprises the following steps: S41. Traverse each target pharmaceutical supplier risk control feature data in the target pharmaceutical supplier risk control feature data set through the flood optimization algorithm, and perform target pharmaceutical supplier risk type search processing with the pharmaceutical supplier risk type feature data in the pharmaceutical supplier risk type feature data set in order of the target pharmaceutical supplier risk control feature data number from small to large, and generate target pharmaceutical supplier risk determination data according to the search results. If the target pharmaceutical supplier risk determination data is risk-free, the target pharmaceutical supplier is added to the list of strategic suppliers, and the target pharmaceutical supplier risk determination data is pushed to the pharmaceutical supplier holographic monitoring platform through the Internet of Things communication network, and the pharmaceutical supplier holographic monitoring operation is terminated at the same time; if the target pharmaceutical supplier risk determination data is risky, generate a target pharmaceutical supplier risk type data set.

6. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 5, characterized in that: The S41 comprises the following steps: S411, taking the risk control feature data of each target pharmaceutical supplier in the risk control feature data set of the target pharmaceutical supplier as sample data in order from small to large according to the risk control feature data number of the target pharmaceutical supplier; S412, construct water flow population, set the water flow population size to , the current number of iterations is The maximum number of iterations is , the search space dimension of risk type feature data of pharmaceutical suppliers is ; The pharmaceutical supplier risk type feature data set is used as a pharmaceutical supplier risk type feature data search space, and a random Each medical supplier risk type feature data corresponds to a water flow individual in the water flow population, and the initial position set of the water flow population is initialized; S413, calculating the fitness function value of each water flow individual in the water flow population; S414, calculating the water consumption coefficient of each individual water flow in the water flow population in the current iteration process; S415, calculating the water flow permeability coefficient of each water flow individual in the water flow population in the search space of the risk type characteristic data of the pharmaceutical supplier; Each individual water flow in the water flow population will update its position in the medical supplier risk type characteristic data search space according to the water flow permeability coefficient to control the probability of flood occurrence; S416, each individual water flow in the water flow population will change the water volume in the watershed according to probability to update the position in the search space of the risk type characteristic data of the pharmaceutical supplier; S417, calculating the fitness function value of each water flow individual in the water flow population after the position is updated, and selecting the water flow individual with the highest fitness function value as the current optimal individual; if the fitness function value of the water flow individual is greater than the original fitness function value, the new position is used to replace the original position; otherwise, the original position is retained; When the fitness function value of a water flow individual is greater than the fitness function value of the current optimal individual, the water flow individual is used as the new current optimal individual; S418, Judgment Is it less than ,like Less than ,but Add 1 and return to S414; otherwise, take the current optimal individual as the global optimal solution; A fitness function threshold is set. If the fitness function value of the global optimal solution is greater than the fitness function threshold, the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution is retained; if the fitness function value of the global optimal solution is less than or equal to the fitness function threshold, the risk type characteristic data of the pharmaceutical supplier corresponding to the global optimal solution is discarded; S419, repeat the operations from S411 to S418 until all target pharmaceutical supplier risk control feature data in the target pharmaceutical supplier risk control feature data set are traversed. If there is no pharmaceutical supplier risk type feature data that successfully matches each sample data, the target pharmaceutical supplier risk determination data is output as no risk; otherwise, the target pharmaceutical supplier risk determination data is output as risk, and the pharmaceutical supplier risk types corresponding to all retained pharmaceutical supplier risk type feature data are combined to generate a target pharmaceutical supplier risk type data set. ,in, Indicates Target pharmaceutical supplier risk type data, Represents the total number of risk type data of target pharmaceutical suppliers.

7. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 6, characterized in that: The S5 comprises the following steps: S51. Preset corresponding pharmaceutical supplier risk type weight data for each pharmaceutical supplier risk type feature data in the pharmaceutical supplier risk type feature data set through the pharmaceutical supplier risk type data entry interface to obtain a pharmaceutical supplier risk type weight data set. ,in, Indicates Weight data corresponding to the risk types of each pharmaceutical supplier; S52: traverse all the pharmaceutical supplier risk type weight data in the pharmaceutical supplier risk type weight data set by using a deep search algorithm, search for pharmaceutical supplier risk type weight data that matches the pharmaceutical supplier risk type corresponding to each target pharmaceutical supplier risk type data in the target pharmaceutical supplier risk type data set, and perform data identification to obtain the target pharmaceutical supplier risk type weight data set. ,in, Indicates The weight data corresponding to the risk type data of each target pharmaceutical supplier.

8. The holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 7 is characterized in that: The S6 comprises the following steps: S61, calculating the target pharmaceutical supplier risk assessment value based on the target pharmaceutical supplier risk type weight data in the target pharmaceutical supplier risk type weight data set. ; S62, setting the first risk threshold and the second risk threshold is ; S63, the , and stated Perform numerical comparison and generate target pharmaceutical supplier risk level data based on the numerical comparison results ; like , then the output is The risk is low, and the target pharmaceutical supplier is added to the list of suppliers to be investigated; like , then the output is The risk is medium, and the target pharmaceutical supplier is added to the list of eliminated suppliers; like , then the output is It is a serious risk, and the target pharmaceutical supplier will be added to the supplier blacklist.

9. A holographic monitoring method for pharmaceutical suppliers based on risk assessment according to claim 8, characterized in that: The S7 comprises the following steps: S71, the and stated Combine data to construct monitoring data of target pharmaceutical suppliers ; S72, through the Internet of Things communication network Push to the pharmaceutical supplier holographic monitoring platform and end this pharmaceutical supplier holographic monitoring operation.

10. A system for implementing the risk assessment-based holographic monitoring method for pharmaceutical suppliers as described in any one of claims 1 to 9.

Images