Laboratory management risk assessment system based on digital technology

Abstract

The invention provides a laboratory management risk assessment system based on a digital technology. The laboratory management risk assessment system comprises an analysis architecture and a decision architecture, wherein the analysis architecture performs feature data identification of the risk item, generates an identification stamp of the risk item based on an identification result, and performs risk assessment by adopting an assessment model based on the identification stamp to obtain a risk value of the risk item represented by the identification stamp; the decision framework is used for collecting data, cleaning and preprocessing the collected data, integrating and extracting risk feature data, verifying based on the risk feature data and an identification stamp, storing feature data of risk items and checking the feature data. According to the method, risk assessment and prediction of the influence possibly caused by the risk are completed, generation of the identification stamp is completed based on the digital technology, rapid matching of a subsequent assessment module is facilitated, identification of identification stamp text and digital data is completed based on the assessment model of the blind number theory, and data dependence is provided for laboratory risk assessment.

Description

Technical Field

[0001] The invention relates to a risk assessment system, in particular to a laboratory management risk assessment system based on digital technology. Background Art

[0002] At present, the laboratory's risk management expert group uses a subjective scoring method to assign corresponding weights to the probability of occurrence and degree of impact of each identified risk factor, derive the risk value of each risk factor, and then sort the risks. Based on the evaluation results, the overall risk level of the project is determined. If the overall risk of the project is acceptable, then according to Pareto's 80 / 20 principle, we focus on the risks that pose the greatest threat, while taking into account the reduction or avoidance of other minor risk factors, and formulate risk response strategies to effectively control risks.

[0003] However, the subjective scoring method of the risk management expert group assigns corresponding weights to each risk factor. However, laboratory management is divided into several major categories: decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk. The risk management expert group often has differences in identifying different risk items. If the corresponding weights of multiple expert groups and risk managers are derived, the risk assessment results will be generated slowly and cannot well integrate the judgments of all expert groups. In addition, the types of risks are often comprehensive, so further improvement is needed in risk matching and classification.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] Purpose of the invention: The technical problem to be solved by the present invention is to provide a laboratory management risk assessment system based on digital technology in view of the shortcomings of the prior art.

[0006] In order to solve the above technical problems, the present invention discloses a laboratory management risk assessment system based on digital technology, the system comprising: Analytical architecture and decision architecture; among them, The analysis framework includes: a risk identification module and a risk assessment module; wherein, The risk identification module identifies the characteristic data of the risk item and generates an identification stamp of the risk item based on the identification result; The risk assessment module uses an assessment model to perform risk assessment based on the identification stamp to obtain a risk value of the risk item represented by the identification stamp; The decision-making framework includes: a decision support module and a real-time monitoring module; wherein, The decision support module collects data, cleans and preprocesses the collected data, integrates and extracts risk feature data, and performs verification based on the risk feature data and identification stamps; The real-time monitoring module stores and verifies the characteristic data of risk items.

[0007] Furthermore, the identification stamp is in the following form: Feature recognition group + predicate node + numeric data The feature recognition group is used to identify the category of the risk item; the predicate node represents an actionable risk result; and the digital data represents a historical credibility variable of the occurrence of the risk item.

[0008] Furthermore, the feature identification group uses preset letters or letter combinations to represent the categories or category combinations of risk items.

[0009] Furthermore, the evaluation model includes: ; Wherein, R is the risk assessment result obtained by the risk assessment module, that is, the risk value of the risk item contained in the identification stamp, k is the adjacent risk coefficient of the risk item, i is the independent risk event number of the risk item, is the risk factor of the risk item, indicating the probability of risk occurring under the ith risk event. is the comprehensive credibility variable under the i-th risk event.

[0010] Furthermore, in the evaluation model, when the risk item included in the identification stamp is a separate risk item, k=1; otherwise, if the risk item included in the identification stamp is a mixed risk item, k≠1.

[0011] Furthermore, the calculation method of the comprehensive credibility variable is as follows: ; Where m represents the number of expert groups. represents the credibility of the j-th expert's score, is the historical credibility variable.

[0012] Furthermore, the risk factors are expressed as follows: ; in, It represents the probability assessment interval of the i-th independent risk event made by the j-th expert.

[0013] Furthermore, when the adjacent risk coefficient satisfies: When k=1, the evaluation model is as follows: ; When the adjacent risk coefficient satisfies: When k≠1, the evaluation model is as follows: ; in, Indicates the weight ratio of adjacent risks.

[0014] Furthermore, the data collected in the decision support module includes: Historical risk event data, real-time risk monitoring data and environmental data.

[0015] Furthermore, the verification in the real-time monitoring module is to complete the risk item feature data verification through the Apriori method.

[0016] Beneficial effects: 1. The present invention completes risk assessment and predicts the possible impact of risks through the risk identification module, and completes the generation of identification stamps based on digital technology, which is convenient for the rapid matching of subsequent evaluation modules. The evaluation model based on blind number theory completes the identification of identification stamp text and digital data, and well adopts and integrates the evaluation results of multiple risk events, providing scientific and reliable data support for multiple risk projects in the laboratory.

[0017] 2. The present invention completes the feature data identification of adjacent related risk items through the risk identification module, and the risk assessment module completes the coefficient division of multiple risk items based on historical experience and historical data, and completes the verification of the identification stamp generated by the risk identification module based on the decision support module, and the real-time monitoring module assists in completing the reconfirmation of the single correlation or multiple correlation of the risk assessment module, so as to ensure that the assessment result is accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the above and / or other advantages of the present invention will become more clear.

[0019] Figure 1 Schematic diagram of the system of the present invention.

[0020] Figure 2 Flow chart of risk assessment in the present invention. DETAILED DESCRIPTION

[0021] The present invention is implemented by the following technical scheme: a laboratory management risk assessment system based on digital technology, such as Figure 1 As shown, the system includes an analysis framework and a decision framework. The analysis framework includes a risk identification module and a risk assessment module. The decision framework includes a decision support module and a real-time monitoring module. Analytical architecture and decision architecture; among them, The analysis framework includes: a risk identification module and a risk assessment module; wherein, The risk identification module identifies the characteristic data of the risk item and generates an identification stamp of the risk item based on the identification result; The risk assessment module uses an assessment model to perform risk assessment based on the identification stamp to obtain a risk value of the risk item represented by the identification stamp; The decision-making framework includes: a decision support module and a real-time monitoring module; wherein, The decision support module collects data, cleans and preprocesses the collected data, integrates and extracts risk feature data, and performs verification based on the risk feature data and identification stamps; The real-time monitoring module stores and verifies the characteristic data of risk items.

[0022] The real-time monitoring module stores and verifies the characteristic data of risk items.

[0023] A further improvement of the technical solution of the present invention is that the first text data of the identification stamp includes any single letter or multiple letter combinations including letters AG, wherein the letters AG correspond to decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk respectively, that is, the identification stamp is in the form of: feature identification group (AG) + predicate node + digital data.

[0024] The combination of feature identification group (AG) includes A, B, C, D, E, F, G, corresponding to decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk. If AB exists, the identification stamp contains decision-making risk and site selection risk, and BCG means that the identification stamp contains site selection risk, financial risk and procurement risk. Furthermore, the predicate node takes the natural risk in laboratory management as an example, which is expressed as an increase in the salary of laboratory personnel, an increase in the number of laboratory personnel, an increase in the total number of laboratory infrastructure or laboratory equipment, etc. The risk factors include procurement volume, instrument price, laboratory project progress value, downtime caused by natural risks, specific salary increase value, and personnel increase value. The last byte of the digital data is a number, which means the historical credibility variable of the risk item.

[0025] A further improvement of the technical solution of the present invention is that the evaluation model comprises: ; Where R is the risk value of the risk item, k is the adjacent risk coefficient of the item, when the risk is a separate risk item, k=1, when k≠1, it represents a mixed risk item, i is the independent risk event of the risk item, is the risk factor of the risk item, indicating the probability of occurrence of the i-th risk event, is the credibility variable under the i-th risk event.

[0026] A further improvement of the technical solution of the present invention is that the comprehensive credibility variable Depend on The expert groups gave The comprehensive income is: ; Among them, i represents the i-th independent risk event, j represents the number of expert groups, is the historical credibility variable.

[0027] A further improvement of the technical solution of the present invention is that each of the risk items includes multiple risk factors, each of the risk factors The probability of occurrence is in the interval [0, 1], and each of the risk factors The probability of occurrence of an unknown event needs to be evaluated by the expert group. ,in It represents the probability estimate made by the j-th expert for the i-th independent risk event. The probability estimate of the occurrence of the ith independent risk event made by the mth person.

[0028] A further improvement of the technical solution of the present invention is that when the evaluation model evaluates the independent risk item k=1, the evaluation model is expressed as: ; When the adjacent risk coefficient k≠1, the assessment model introduces the historical weight ratios of decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk. The risk identification module completes the identification of the weight of independent risk events based on the risk item feature data, and completes the weight ratio of the adjacent risk based on the probability of occurrence of the independent risk event. The calculation of the evaluation model is expressed as follows when k≠1: ; A further improvement of the technical solution of the present invention is that the decision support module forms a text library based on the identification and extraction of predicate nodes in historical risk event data, real-time risk monitoring data, and environmental data, and the predicate nodes in the identification stamps formed by the risk identification module are used as index sentences to retrieve the obtained text library, and the retrieved results are expressed in binary.

[0029] A further improvement of the technical solution of the present invention is that the real-time monitoring module completes the retention of the database based on the risk item feature data after data mining, and the real-time monitoring module completes the single or multiple correlation verification of the risk item feature data on decision-making, site selection, finance, progress, management, nature and procurement through the Apriori algorithm.

[0030] Example

[0031] The present invention provides a laboratory management risk assessment system based on digital technology. The system includes an analysis framework and a decision framework. The analysis framework includes a risk identification module and a risk assessment module. The decision framework includes a decision support module and a real-time monitoring module. The risk identification module completes the identification of risk item characteristic data of decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk based on data mining, and generates an identification stamp belonging to the risk item based on the identification results; The risk assessment module completes the assessment of the assessment model based on the generated identification stamp, and the assessment model includes the probability P of the risk event represented by the identification stamp, the risk factor C of the risk event, and the adjacent risk coefficient k, wherein the adjacent risk coefficient k is determined by the risk item involved in the risk event; The decision support module includes the collection of historical risk event data, real-time risk monitoring data, and environmental data. It cleans, processes, and integrates the collected data to extract risk feature data, and completes verification based on the formed risk feature data and the identification stamp containing the risk data features. The real-time monitoring module includes the storage of risk item feature data based on data mining, and completes single or multiple correlation checks on decision-making, site selection, finance, progress, management, nature and procurement based on the risk item feature data.

[0032] The first text data of the identification stamp includes any single letter or multiple letter combinations including the letters AG, where the letters AG correspond to decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk respectively. That is, the form of the identification stamp is: feature identification group (AG) + predicate node + digital data.

[0033] The combination of feature identification group (AG) includes A, B, C, D, E, F, G, corresponding to decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk. If AB exists, the identification stamp contains decision-making risk and site selection risk, and BCG means that the identification stamp contains site selection risk, financial risk and procurement risk. Furthermore, the predicate node takes the natural risk in laboratory management as an example, which is expressed as an increase in the salary of laboratory personnel, an increase in the number of laboratory personnel, an increase in the total number of laboratory infrastructure or laboratory equipment, etc. The risk factors include procurement volume, instrument price, laboratory project progress value, downtime caused by natural risks, specific salary increase value, and personnel increase value. The last byte of the digital data is a number, which means the historical credibility variable of the occurrence of the risk item.

[0034] The evaluation model comprises: ; Where R is the risk value of the risk item, k is the adjacent risk coefficient of the item, when the risk is a separate risk item, k=1, when k≠1, it represents a mixed risk item, i is the independent risk event of the risk item, is the risk factor of the risk item, indicating the probability of occurrence of the i-th risk event, is the credibility variable under the i-th risk event.

[0035] A further improvement of the technical solution of the present invention is that the comprehensive credibility variable Depend on The expert groups gave The comprehensive income is: ; Among them, i represents the i-th independent risk event, j represents the number of expert groups, is the historical credibility variable.

[0036] A further improvement of the technical solution of the present invention is that each of the risk items includes multiple risk factors, each of the risk factors The probability of occurrence is in the interval [0, 1], and each of the risk factors The probability of occurrence of an unknown event needs to be evaluated by the expert group. ,in It represents the probability estimate made by the j-th expert for the i-th independent risk event. The probability estimate of the occurrence of the ith independent risk event made by the mth person.

[0037] A further improvement of the technical solution of the present invention is that when the evaluation model evaluates the independent risk item k=1, the evaluation model is expressed as: ; When the adjacent risk coefficient k≠1, the assessment model introduces the historical weight ratios of decision-making risk, site selection risk, financial risk, schedule risk, management risk, natural risk and procurement risk. The risk identification module completes the identification of the weight of independent risk events based on the risk item feature data, and completes the weight ratio of the adjacent risk based on the probability of occurrence of the independent risk event. The calculation of the evaluation model is expressed as follows when k≠1: ; The evaluation method for the expert group is that the organizer designs the questions in advance, collects opinions from the selected experts by letter, and then organizes, summarizes and modifies the opinions fed back by the experts, and then sends them to the experts in the form of anonymous letters to solicit their opinions again. This is repeated for several rounds until the amount of information fed back by the experts gradually decreases and the opinions tend to be unified. Then the investigation can be stopped. Finally, the organizer comprehensively processes the opinions of the experts, so it is suitable for the evaluation of this application; like When the given credibility of the expert group is {0.2, 0.4, 0.7, 1} and the historical credibility is 0.5, ; therefore: ; According to the credibility values ​​given by the above four expert groups, the risk value can be obtained: ; Based on the above risk values, it can be seen that the average risk value is far more than 0.5, so once this risk item occurs, its risk value is too large.

[0038] The decision support module forms a text library based on the recognition and extraction of predicate nodes in historical risk event data, real-time risk monitoring data, and environmental data. The predicate nodes in the identification stamps formed by the risk identification module are used as index sentences to retrieve the obtained text library, and the retrieval results are expressed in binary.

[0039] The real-time monitoring module completes the retention of the database based on the risk item feature data after data mining. The real-time monitoring module completes the single or multiple correlation verification of the risk item feature data on decision-making, site selection, finance, progress, management, nature and procurement through the Apriori algorithm.

[0040] In a specific implementation, the present application provides a computer storage medium and a corresponding data processing unit, wherein the computer storage medium can store a computer program, and when the computer program is executed by the data processing unit, the invention content of a laboratory management risk assessment system based on digital technology provided by the present invention and some or all of the steps in each embodiment can be run. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0041] Those skilled in the art can clearly understand that the technical solutions in the embodiments of the present invention can be implemented by means of computer programs and their corresponding general hardware platforms. Based on such understanding, the technical solutions in the embodiments of the present invention can be essentially or partly contributed to the prior art in the form of computer programs, i.e., software products, which can be stored in a storage medium and include several instructions for enabling a device including a data processing unit (which can be a personal computer, a server, a single-chip microcomputer, an MCU or a network device, etc.) to execute the methods described in various embodiments of the present invention or certain parts of the embodiments.

[0042] The present invention provides a laboratory management risk assessment system based on digital technology. There are many methods and ways to implement the technical solution. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention. All components not specified in this embodiment can be implemented by existing technologies.

Claims

1. A laboratory management risk assessment system based on digital technology, characterized in that: The system comprises: Analytical architecture and decision-making architecture; among them, The analysis framework includes: a risk identification module and a risk assessment module; wherein, The risk identification module identifies the characteristic data of the risk item and generates an identification stamp of the risk item based on the identification result; The risk assessment module uses an assessment model to perform risk assessment based on the identification stamp to obtain a risk value of the risk item represented by the identification stamp; The decision-making framework includes: a decision support module and a real-time monitoring module; wherein, The decision support module collects data, cleans and preprocesses the collected data, integrates and extracts risk feature data, and performs verification based on the risk feature data and identification stamps; The real-time monitoring module stores and verifies the characteristic data of risk items.

2. According to claim 1, a laboratory management risk assessment system based on digital technology is characterized in that: The identification stamp is in the following form: Feature recognition group + predicate node + numeric data; The feature recognition group is used to identify the category of the risk item; the predicate node represents an actionable risk result; and the digital data represents a historical credibility variable of the occurrence of the risk item.

3. According to claim 2, a laboratory management risk assessment system based on digital technology is characterized in that: The feature identification group uses preset letters or letter combinations to represent the categories or category combinations of risk items.

4. According to claim 3, a laboratory management risk assessment system based on digital technology is characterized in that: The evaluation model comprises: ； Wherein, R is the risk assessment result obtained by the risk assessment module, that is, the risk value of the risk item contained in the identification stamp, k is the adjacent risk coefficient of the risk item, i is the independent risk event number of the risk item, is the risk factor of the risk item, indicating the probability of risk occurring under the ith risk event. is the comprehensive credibility variable under the i-th risk event.

5. According to claim 4, a laboratory management risk assessment system based on digital technology is characterized in that: In the evaluation model, when the risk item included in the identification stamp is a single risk item, k=1; otherwise, if the risk item included in the identification stamp is a mixed risk item, k≠1.

6. A laboratory management risk assessment system based on digital technology according to claim 5, characterized in that: The comprehensive credibility variable is calculated as follows: ； Where m represents the number of expert groups. represents the credibility of the j-th expert's score, is the historical credibility variable.

7. A laboratory management risk assessment system based on digital technology according to claim 6, characterized in that: The risk factors are as follows: ； in, It represents the probability assessment interval of the i-th independent risk event made by the j-th expert.

8. A laboratory management risk assessment system based on digital technology according to claim 7, characterized in that: When the adjacent risk coefficient satisfies: When k=1, the evaluation model is as follows: ； When the adjacent risk coefficient satisfies: When k≠1, the evaluation model is as follows: ； in, Indicates the weight ratio of adjacent risks.

9. A laboratory management risk assessment system based on digital technology according to claim 8, characterized in that: The data collected in the decision support module includes: Historical risk event data, real-time risk monitoring data and environmental data.

10. A laboratory management risk assessment system based on digital technology according to claim 9, characterized in that: The verification in the real-time monitoring module is to complete the risk item feature data verification through the Apriori method.

Images