CN111507578A - Risk assessment method and related device and equipment - Google Patents
Risk assessment method and related device and equipment Download PDFInfo
- Publication number
- CN111507578A CN111507578A CN202010220568.XA CN202010220568A CN111507578A CN 111507578 A CN111507578 A CN 111507578A CN 202010220568 A CN202010220568 A CN 202010220568A CN 111507578 A CN111507578 A CN 111507578A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- assessment
- evaluation
- personal data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 107
- 238000011156 evaluation Methods 0.000 claims description 132
- 238000013210 evaluation model Methods 0.000 claims description 74
- 238000012545 processing Methods 0.000 claims description 42
- 230000002159 abnormal effect Effects 0.000 claims description 41
- 238000007781 pre-processing Methods 0.000 claims description 17
- 230000000875 corresponding effect Effects 0.000 claims description 16
- 230000002596 correlated effect Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 8
- 238000012854 evaluation process Methods 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a risk assessment method and a related device and equipment, wherein the risk assessment method comprises the following steps: acquiring personal data of a person to be evaluated; and carrying out risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed. According to the scheme, the efficiency, the accuracy and the stability of risk assessment can be improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a risk assessment method and related apparatus and devices.
Background
In social life, various risks are present, and it is necessary to evaluate the risks in advance.
At present, risk assessment often depends on expert experience, but a manual mode is easy to bring subjectivity into the assessment process, so that the accuracy of assessment is difficult to maintain stably. In view of this, how to improve the efficiency, accuracy and stability of risk assessment becomes an urgent problem to be solved.
Disclosure of Invention
The application provides a risk assessment method and a related device and equipment.
A first aspect of the present application provides a risk assessment method, including: acquiring personal data of a person to be evaluated; and carrying out risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed.
Therefore, the risk evaluation result of the personnel to be evaluated is obtained by acquiring the personal data of the personnel to be evaluated and carrying out risk evaluation on the personal data by using the artificial intelligence evaluation model, so that the low efficiency caused by artificial evaluation can be avoided, the evaluation efficiency can be improved, and in addition, the evaluation accuracy and stability can be improved because the evaluation process is not influenced by subjectivity.
The method for evaluating the risk of the personal data by using the artificial intelligence evaluation model to obtain the risk evaluation result of the personnel to be evaluated comprises the following steps: carrying out risk assessment on the personal data by using the artificial intelligence assessment model to obtain a preliminary assessment result output by the artificial intelligence assessment model; taking the preliminary evaluation result as a risk evaluation result; or generating a risk assessment result based on the preliminary assessment result.
Therefore, the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data to obtain a preliminary evaluation result output by the artificial intelligence evaluation model, the preliminary evaluation result is used as a risk evaluation result, or the risk evaluation result is generated based on the preliminary evaluation result, and the risk evaluation can be quickly and accurately realized.
Wherein the preliminary evaluation result comprises at least one of the following: normal risk probability of the person to be evaluated and abnormal risk probability of the person to be evaluated; the larger the normal risk probability is, the lower the risk of the person to be evaluated is, the larger the abnormal risk probability is, and the higher the risk of the person to be evaluated is.
Therefore, the preliminary evaluation result is set to include at least one of the normal risk probability of the person to be evaluated and the abnormal risk probability of the person to be evaluated, the larger the normal risk probability is, the lower the risk of the person to be evaluated is, the larger the abnormal risk probability is, the higher the risk of the person to be evaluated is, and the risk can be expressed quantitatively, so that the risk can be reflected visually, and the user experience can be improved.
Wherein generating a risk assessment result based on the preliminary assessment result comprises: and obtaining the risk score of the person to be evaluated by utilizing the normal risk probability and/or the abnormal risk probability, wherein the risk score is positively correlated with the normal risk probability and negatively correlated with the abnormal risk probability.
Therefore, the risk score of the personnel to be evaluated is obtained through the normal risk probability and/or the abnormal risk probability, the risk score is positively correlated with the normal risk probability and negatively correlated with the abnormal risk probability, the risk probability can be converted into the score, the risk can be quantitatively expressed, the risk can be visually reflected, and the user experience can be improved.
After the risk assessment is performed on the personal data by using the artificial intelligence assessment model to obtain the risk assessment result of the person to be assessed, the method further comprises the following steps: and obtaining a risk processing measure corresponding to the person to be evaluated according to the risk evaluation result.
Therefore, after the risk assessment result is obtained, the risk processing measures corresponding to the person to be assessed are obtained according to the risk assessment result, so that suggestions can be given for the person to be assessed, and the user experience can be improved.
Before risk assessment is carried out on the personal data by using the artificial intelligence assessment model to obtain a risk assessment result of a person to be assessed, the method further comprises the following steps of carrying out characteristic processing on the personal data: adding new personal data with a first preset data characteristic by using the acquired personal data; and/or eliminating personal data with second preset data characteristics from the acquired personal data; carrying out risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed, wherein the risk assessment result comprises the following steps: and carrying out risk assessment on the personal data subjected to the feature processing by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed.
Therefore, the new personal data with the first preset data characteristic is added by utilizing the personal data, so that the artificial intelligence evaluation model can obtain more knowledge, and/or the personal data with the second preset data characteristic is removed from the personal data, so that the interference of irrelevant data or error data can be reduced, the artificial intelligence evaluation model is utilized to carry out risk evaluation on the personal data after the characteristic processing, and the accuracy of the obtained risk evaluation result can be improved.
Wherein the personal data comprises at least one data; before the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data and obtaining the risk evaluation result of the person to be evaluated, the method also comprises the following steps: determining a data type to which each piece of data in the personal data belongs, wherein the data type comprises continuous data and discrete data; and respectively preprocessing the continuous data and the discrete data by utilizing different preset preprocessing modes.
Therefore, by determining the data types of various data in the personal data and respectively preprocessing the continuous data and the discrete data by using different preset processing modes, the artificial intelligence evaluation model can understand the data more deeply, and the evaluation accuracy can be improved.
The determining the data type of each data in the personal data comprises the following steps: if the data in the personal data is numerical data, determining the data as continuous data; if the data in the personal data is non-numerical data, determining the data to be discrete data; respectively preprocessing continuous data and discrete data by utilizing different preset preprocessing modes, wherein the preprocessing modes comprise the following steps: carrying out Gaussian distribution processing on the continuous data; and/or encoding the discrete data.
Therefore, the numerical data is determined as continuous data, the continuous data is subjected to Gaussian distribution processing, the non-numerical data is determined as discrete data, and the discrete data is encoded, so that the artificial intelligence evaluation model can understand the data more deeply, and the evaluation accuracy can be improved.
The artificial intelligence evaluation model comprises any one of a machine learning model and a deep learning model; and/or the artificial intelligence evaluation model is obtained by training sample evaluation data marked with real risk evaluation results.
Therefore, the artificial intelligence evaluation model is set to be any one of the machine learning model and the deep learning model, the artificial intelligence evaluation model is obtained by training the sample evaluation data marked with the real risk evaluation result, and the accuracy of the artificial intelligence evaluation model can be improved.
After the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data to obtain a risk evaluation result of a person to be evaluated, the method further comprises the following steps: acquiring an artificial risk assessment result of personal data; and adjusting parameters of the artificial intelligence evaluation model based on the artificial risk evaluation result and the output evaluation result of the artificial intelligence evaluation model.
Therefore, after the risk evaluation result of the person to be evaluated is obtained, the artificial risk evaluation result of the personal data is obtained, the parameters of the artificial intelligence evaluation model are adjusted based on the artificial risk evaluation result and the output evaluation result of the artificial intelligence evaluation model, and the artificial intelligence evaluation model can be retrained, so that the accuracy of the artificial intelligence evaluation model can be improved.
Wherein the personal data of the person to be assessed comprises at least one of: basic information data, medical insurance data, medical data and social insurance data of the personnel to be evaluated.
Therefore, the personal data of the person to be evaluated is set to include at least one of the basic information data, the medical insurance data, the medical data and the social insurance data of the person to be evaluated, so that the coverage of the personal data can be favorably improved, and the accuracy of the artificial intelligence evaluation model can be favorably improved.
The second aspect of the application provides a risk assessment device, which comprises a data acquisition module and an assessment processing module, wherein the data acquisition module is used for acquiring personal data of a person to be assessed; and the evaluation processing module is used for carrying out risk evaluation on the personal data by utilizing the artificial intelligence evaluation model to obtain a risk evaluation result of the personnel to be evaluated.
A third aspect of the present application provides an electronic device, which includes a memory and a processor coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the risk assessment method in the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon program instructions that, when executed by a processor, implement the risk assessment method of the first aspect described above.
According to the scheme, the personal data of the personnel to be evaluated are obtained, the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data, the risk evaluation result of the personnel to be evaluated is obtained, low efficiency caused by manual evaluation can be avoided, evaluation efficiency can be improved, and in addition, the evaluation accuracy and stability can be improved as the evaluation process is not influenced subjectively.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a risk assessment method of the present application;
FIG. 2 is a flowchart illustrating an embodiment of step S12 in FIG. 1;
FIG. 3 is a schematic flow chart diagram illustrating another embodiment of the risk assessment method of the present application;
FIG. 4 is a block diagram of an embodiment of the risk assessment device of the present application;
FIG. 5 is a block diagram of an embodiment of an electronic device of the present application;
FIG. 6 is a block diagram of an embodiment of a computer-readable storage medium of the present application.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a risk assessment method according to the present application. Specifically, the method may include the steps of:
step S11: and acquiring personal data of the person to be evaluated.
Taking the poverty risk assessment as an example, the person to be assessed may be a person who is not poverty, specifically, the person to be assessed may be obtained by screening from medical records of a hospital, or the person to be assessed may be obtained by screening from records of medical insurance, bank flow and the like. For example, screening residents in a certain poor village, if the residents have medical records in a hospital recently or medical insurance records and bank running water with large amount of expenditure, the residents are used as the personnel to be evaluated, and other application scenes can be analogized, which is not exemplified herein.
In one implementation scenario, the personal data may include at least one of: basic information data (such as age, sex and the like), medical insurance data, medical data (such as outpatient service data, hospitalization data and the like) and social insurance data of the person to be evaluated, so that the coverage of personal data can be improved, and the accuracy of a risk evaluation model can be improved.
Step S12: and carrying out risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed.
The artificial intelligence evaluation model may include any one of a machine learning model, a deep learning model. For example, the Artificial intelligence evaluation model may include a machine learning model such as a linear model, a tree model, a support vector machine, or the like, or may further include a deep learning model such as ANN (Artificial Neural Network), deep fm, xDeepFM, NCF (Neural Collaborative Filtering), or the like.
In one implementation scenario, the artificial intelligence assessment model is trained using sample assessment data labeled with real risk assessment results. Specifically, the artificial intelligence evaluation model can be used for performing risk evaluation on the sample evaluation data to obtain a corresponding predicted risk evaluation result, the predicted risk evaluation result and the real risk evaluation result are used for determining the loss value of the artificial intelligence evaluation model, and the loss value is used for adjusting the parameters of the artificial intelligence evaluation model. In one specific implementation scenario, the training may be ended when the loss value is less than a predetermined loss value threshold. In another specific implementation scenario, when the number of times of training reaches a preset number threshold, the training may be ended, which is not limited herein. In another specific implementation scenario, parameters of the artificial intelligence evaluation model may be adjusted by using a loss value in a random Gradient Descent (SGD), a Batch Gradient Descent (BGD), a Mini-Batch Gradient Descent (MBGD), and the like, where the Batch Gradient Descent refers to updating the parameters by using all samples during each iteration; the random gradient descent means that one sample is used for parameter updating in each iteration; the small batch gradient descent means that a batch of samples is used for parameter updating at each iteration, and details are not repeated here.
In one implementation scenario, the risk assessment result includes at least one of a normal risk probability of the person to be assessed and an abnormal risk probability of the person to be assessed, and the higher the normal risk probability is, the lower the risk of the person to be assessed is, the higher the abnormal risk probability is, and the higher the risk of the person to be assessed is. Taking the poverty-causing risk as an example, if the normal risk probability of the person to be evaluated is 90%, the poverty-causing risk of the person to be evaluated can be considered to be lower, or if the abnormal risk probability of the person to be evaluated is 90%, the poverty-causing risk of the person to be evaluated can be considered to be 90%. The risk assessment result is set to at least one of the normal risk probability of the person to be assessed and the abnormal risk probability of the person to be assessed, so that the risk can be expressed quantitatively, the risk degree can be reflected visually, and the user experience can be improved.
In an implementation scenario, in order to improve the evaluation accuracy, the obtained personal data may be used to add new personal data with the first preset data characteristic before the personal data is evaluated by the artificial intelligence evaluation model, so that the artificial intelligence evaluation model can obtain more knowledge and the risk evaluation is more accurate. For example, the first preset data characteristic may include a Body health Index (BMI) such that the Body weight of the person to be evaluated is divided by the square of the height, and the first preset data characteristic may further include other characteristics, which may be specifically set according to actual conditions, which is not illustrated herein. In another implementation scenario, in order to improve the evaluation accuracy, before the personal data is evaluated by using the artificial intelligence evaluation model, the personal data with the second preset data characteristic is removed from the acquired personal data, so that the interference of irrelevant data or error data can be reduced before the evaluation processing is performed by using the artificial intelligence evaluation model, and the risk evaluation is more accurate. For example, the second preset data characteristics may include marital status, educational experience, and the like, and may be specifically set according to actual situations, which are not illustrated herein. Through the characteristic processing, the artificial intelligence evaluation model can carry out risk evaluation on the personal data subjected to the characteristic processing, so that the obtained risk evaluation result is more accurate.
In an implementation scenario, in order to improve accuracy of the artificial intelligence evaluation model, after obtaining a risk evaluation result, an artificial risk evaluation result for personal data may be obtained, specifically, the personal data may be evaluated by an expert to obtain an artificial risk evaluation result, and a parameter of the artificial intelligence evaluation model is adjusted based on the artificial risk evaluation result and an output result of the artificial intelligence evaluation model, specifically, a loss value of the artificial intelligence evaluation model may be determined according to the artificial risk evaluation result and the output result of the artificial intelligence evaluation model, so that the parameter of the artificial intelligence evaluation model is adjusted by using the loss value, which is not described in detail herein. By acquiring the artificial risk assessment result of the personal data and adjusting the parameters of the artificial intelligence assessment model based on the artificial risk assessment result and the output assessment result of the artificial intelligence assessment model, the artificial intelligence assessment model can be retrained, and therefore the accuracy of the artificial intelligence assessment model can be improved. In a specific implementation scenario, personal data of a person to be evaluated, which is evaluated by the artificial intelligence evaluation model in error or has a certain deviation, can be selected, and the selected data is re-labeled to retrain the artificial intelligence evaluation model, so that the accuracy of the artificial intelligence evaluation model is improved.
In an implementation scenario, the business process for obtaining the personal data of the person to be assessed and performing risk assessment on the personal data by using the artificial intelligence assessment model to obtain the risk assessment result of the person to be assessed can be set in a business system of an institution such as a medical insurance bureau, so that the risk of residents can be assessed, and further, services and support are provided for related businesses such as subsequent medical insurance. In a specific implementation scenario, an artificial intelligence evaluation model may be embedded in a business system of an institution such as a medical insurance office, and an interface for data transmission is provided between the business system and other institutions (e.g., hospitals, pharmacies, banks) to obtain personal data of a person to be evaluated from other institutions. In another specific implementation scenario, after the risk assessment result is obtained, a risk treatment measure corresponding to the person to be assessed can be obtained according to the risk assessment result. Specifically, the corresponding relationship between the risk assessment result and the risk handling measure may be preset, for example, a lower risk may correspond to a lower degree of support measure, and a higher risk may correspond to a higher degree of support measure. Still taking the poverty-causing risk as an example, if the risk evaluation result shows that the poverty-causing risk of the person to be evaluated is higher, the corresponding risk treatment measures may include giving a certain social security payment preference, and if the risk evaluation result shows that the poverty-causing risk of the person to be evaluated is lower, the corresponding risk treatment measures may include giving a certain amount of money, and the like, and may be specifically set according to an actual situation. And are not limited herein.
According to the scheme, the personal data of the personnel to be evaluated are obtained, the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data, the risk evaluation result of the personnel to be evaluated is obtained, low efficiency caused by manual evaluation can be avoided, evaluation efficiency can be improved, and in addition, the evaluation accuracy and stability can be improved as the evaluation process is not influenced subjectively.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating an embodiment of step S12 in fig. 1. The method specifically comprises the following steps:
step S121: and carrying out risk assessment on the personal data by using the artificial intelligence assessment model to obtain a preliminary assessment result output by the artificial intelligence assessment model.
In one implementation scenario, the preliminary evaluation results include at least one of: the normal risk probability of the person to be evaluated and the abnormal risk probability of the person to be evaluated are greater, the risk of the person to be evaluated is lower, the abnormal risk probability is greater, and the risk of the person to be evaluated is higher.
Step S122: taking the preliminary evaluation result as a risk evaluation result; or generating a risk assessment result based on the preliminary assessment result.
In one implementation scenario, the preliminary assessment results may be used as risk assessment results. In another implementation scenario, in order to improve the intuitiveness of the risk assessment and thus improve the user experience, a preset processing mode can be adopted to process the risk assessment result based on the preliminary assessment result to obtain the risk assessment result. Specifically, the risk score of the person to be evaluated can be obtained by using the normal risk probability and/or the abnormal risk probability, and the risk score is positively correlated with the normal risk probability and negatively correlated with the abnormal risk probability, i.e., the higher the normal risk probability is, the higher the risk score is, the lower the risk of the person to be evaluated is; the greater the probability of abnormal risk, the lower the risk score, and the lower the risk of the person to be assessed. Taking the percentile risk score as an example, the product of the normal risk probability and 100 may be used as the risk score, for example, 90% of the normal risk probability corresponds to a risk score of 90; alternatively, the risk score may be the square of the product of the normal risk probability and 10, e.g., a normal risk probability of 90% with a corresponding risk score of 81; or, a product of the square root of the normal risk probability and 100 may be used as a risk score, for example, a normal risk probability of 90% and a corresponding risk score of 95%, in other implementation scenarios, the preset processing manner may further include other processing manners, which may be specifically set according to an actual application situation, and is not limited herein. Still taking the percentile risk score as an example, the difference between the product of the abnormal risk probability and 100 may be taken as the risk score, e.g., 90% abnormal risk probability with a corresponding risk score of 10; alternatively, the difference between the square of the product of the abnormal risk probability and 10 and 100 may be taken as the risk score, e.g., a 90% abnormal risk probability with a corresponding risk score of 19; or, a difference between a square root of the abnormal risk probability and a product of 100 and 100 may be used as a risk score, for example, a 90% abnormal risk probability and a corresponding risk score of 15, in other implementation scenarios, the preset processing manner may further include other processing manners, which may be specifically set according to an actual application situation, and is not limited herein. In addition, the risk score of the person to be evaluated can be obtained by using the normal risk probability and/or the abnormal risk probability, the risk score is in negative correlation with the normal risk probability and is in positive correlation with the abnormal risk probability, namely, the larger the normal risk probability is, the lower the risk score is, the lower the risk of the person to be evaluated is, the larger the abnormal risk probability is, the higher the risk score is, the higher the risk of the person to be evaluated is, and no limitation is made herein. In a specific implementation scenario, a risk processing measure corresponding to a person to be evaluated may also be obtained according to the risk score, which may specifically refer to the relevant steps in the foregoing embodiment, and details are not described here.
Different from the embodiment, the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data to obtain a preliminary evaluation result output by the artificial intelligence evaluation model, and the preliminary evaluation result is used as a risk evaluation result or is generated based on the preliminary evaluation result, so that the risk evaluation can be quickly and accurately realized.
Referring to fig. 3, fig. 3 is a schematic flow chart of another embodiment of the risk assessment method of the present application. Specifically, the method may include the steps of:
step S31: and acquiring personal data of the person to be evaluated.
Please refer to the related steps in the previous embodiment.
Step S32: and determining the data type of each data in the personal data, wherein the data type comprises continuous data and discrete data.
The personal data includes at least one data, and in one implementation scenario, if the data in the personal data is numerical data, the data can be determined to be continuous data. For example, the height data "171 cm", the weight data "120 kg", the age data "20 years" and the like may be determined as continuous data, and other application scenarios may be analogized, and no examples are given here. In another implementation scenario, if the data in the personal data is non-numerical data, the data may be determined to be discrete data. For example, sex data "male", marital status data "not married", etc. may be determined as discrete data, and other application scenarios may be analogized, and no examples are given here.
Step S33: and respectively preprocessing the continuous data and the discrete data by utilizing different preset preprocessing modes.
In one implementation scenario, the continuous data may be subjected to gaussian distribution processing, for example, normalization and discretization of the continuous data, and processing such as log (log) acquisition, so that the distribution of the continuous data tends to be gaussian. In another implementation scenario, the discrete data may be encoded, for example, for the discrete data of the type, one-hot (one-hot) encoding, hash (hash) encoding, and the like may be used, where the one-hot encoding is also called one-bit effective encoding, and a multi-bit status register is used to encode a plurality of statuses, each status corresponds to an independent register bit, and at any time, only one of the statuses is effective, for example, the three statuses may be respectively represented as: 001. 010, 100, and so on, and no more than one example is shown here, the character-type discrete data can be converted into numerical data, so that the artificial intelligence evaluation model can understand the data more deeply.
In one implementation scenario, outliers and outliers in the data may also be removed before the data is preprocessed. The outlier and outlier may be values outside a predetermined range, for example, for height data, if the value is 10 cm, the outlier and outlier are determined; for the weight data, if the value is 100 g, it is an abnormal value, an outlier, and the other cases can be analogized, which is not illustrated herein. By removing the abnormal values and outliers in the data before preprocessing the data, the damage caused by the abnormal values and the outliers can be avoided, and the accuracy of subsequent evaluation can be improved.
Step S34: and carrying out risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed.
Reference may be made in particular to the relevant steps in the preceding embodiments.
Different from the embodiment, the data types of various data in the personal data are determined, and the continuous data and the discrete data are respectively preprocessed in different preset processing modes, so that the artificial intelligence evaluation model can understand the data more deeply, and the evaluation accuracy can be improved.
Referring to fig. 4, fig. 4 is a schematic block diagram of an embodiment of a risk assessment apparatus 40 according to the present application. The risk assessment device 40 comprises a data acquisition module 41 and an assessment processing module 42, wherein the data acquisition module 41 is used for acquiring personal data of a person to be assessed; the evaluation processing module 42 is configured to perform risk evaluation on the personal data by using an artificial intelligence evaluation model to obtain a risk evaluation result of the person to be evaluated.
According to the scheme, the personal data of the personnel to be evaluated are obtained, the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data, the risk evaluation result of the personnel to be evaluated is obtained, low efficiency caused by manual evaluation can be avoided, evaluation efficiency can be improved, and in addition, the evaluation accuracy and stability can be improved as the evaluation process is not influenced subjectively.
In some embodiments, the evaluation processing module 42 includes a preliminary evaluation sub-module configured to perform risk evaluation on the personal data by using the artificial intelligence evaluation model to obtain a preliminary evaluation result output by the artificial intelligence evaluation model, and the evaluation processing module 42 includes a result obtaining sub-module configured to use the preliminary evaluation result as a risk evaluation result; or generating a risk assessment result based on the preliminary assessment result.
Different from the embodiment, the artificial intelligence evaluation model is used for carrying out risk evaluation on the personal data to obtain a preliminary evaluation result output by the artificial intelligence evaluation model, and the preliminary evaluation result is used as a risk evaluation result or is generated based on the preliminary evaluation result, so that the risk evaluation can be quickly and accurately realized.
In some embodiments, the preliminary evaluation results include at least one of: normal risk probability of the person to be evaluated and abnormal risk probability of the person to be evaluated; the larger the normal risk probability is, the lower the risk of the person to be evaluated is, the larger the abnormal risk probability is, and the higher the risk of the person to be evaluated is.
Different from the embodiment, the preliminary evaluation result is set to include at least one of the normal risk probability of the person to be evaluated and the abnormal risk probability of the person to be evaluated, and the higher the normal risk probability is, the lower the risk of the person to be evaluated is, the higher the abnormal risk probability is, the higher the risk of the person to be evaluated is, so that the risk degree can be visually reflected, and the user experience can be improved.
In some embodiments, the result obtaining sub-module is specifically configured to obtain a risk score of the person to be evaluated by using the normal risk probability and/or the abnormal risk probability, where the risk score is positively correlated with the normal risk probability and negatively correlated with the abnormal risk probability.
Different from the embodiment, the risk score of the person to be evaluated is obtained through the normal risk probability and/or the abnormal risk probability, the risk score is positively correlated with the normal risk probability and negatively correlated with the abnormal risk probability, the risk probability can be converted into the score, and the risk can be quantitatively expressed, so that the risk degree can be intuitively reflected, and the user experience can be improved.
In some embodiments, the risk assessment apparatus 40 further includes a measure obtaining module, configured to obtain a risk processing measure corresponding to the person to be assessed according to the risk assessment result.
Different from the embodiment, after the risk assessment result is obtained, the risk processing measures corresponding to the person to be assessed are obtained according to the risk assessment result, so that suggestions can be given for the person to be assessed, and the user experience can be improved.
In some embodiments, the risk assessment apparatus 40 further includes a feature processing module, configured to add new personal data with a first preset data feature by using the obtained personal data, and/or to remove personal data with a second preset data feature from the obtained personal data, and the assessment processing module 42 is specifically configured to perform risk assessment on the personal data after feature processing by using an artificial intelligence assessment model, so as to obtain a risk assessment result of the person to be assessed.
Different from the embodiment, the method has the advantages that the new personal data with the first preset data characteristic is added by utilizing the personal data, so that the artificial intelligence evaluation model can obtain more knowledge, and/or the personal data with the second preset data characteristic is removed from the personal data, so that the interference of irrelevant data or error data can be reduced, the artificial intelligence evaluation model is utilized to carry out risk evaluation on the personal data after the characteristic processing, and the accuracy of the obtained risk evaluation result can be improved.
In some embodiments, the risk assessment apparatus 40 includes a type determination module for determining a data type to which each data in the personal data belongs, wherein the data type includes continuous data and discrete data, and the risk assessment apparatus 40 includes a preprocessing module for preprocessing the continuous data and the discrete data respectively by using different preset preprocessing manners.
Different from the embodiment, the data types of various data in the personal data are determined, and the continuous data and the discrete data are respectively preprocessed in different preset processing modes, so that the artificial intelligence evaluation model can understand the data more deeply, and the evaluation accuracy can be improved.
In some embodiments, the type determining module is specifically configured to determine the data in the personal data as continuous data when the data in the personal data is numerical data, determine the data in the personal data as discrete data when the data in the personal data is non-numerical data, and the preprocessing module is specifically configured to perform gaussian distribution processing on the continuous data and/or encode the discrete data.
Different from the foregoing embodiment, the numerical data is determined as continuous data, gaussian distribution processing is performed on the continuous data, the non-numerical data is determined as discrete data, and the discrete data is encoded, which is beneficial to enabling an artificial intelligence evaluation model to understand the data more deeply, thereby being beneficial to improving the evaluation accuracy.
In some embodiments, the artificial intelligence assessment model comprises any one of a machine learning model, a deep learning model; and/or the artificial intelligence evaluation model is obtained by training sample evaluation data marked with real risk evaluation results.
Different from the embodiment, the artificial intelligence evaluation model is set to be any one of a machine learning model and a deep learning model, and the artificial intelligence evaluation model is obtained by training the sample evaluation data marked with the real risk evaluation result, so that the accuracy of the artificial intelligence evaluation model can be improved.
In some embodiments, the risk assessment apparatus 40 includes a manual assessment acquisition module for acquiring a manual risk assessment result for the personal data, and the risk assessment apparatus 40 includes a model parameter adjustment module for adjusting a parameter of the artificial intelligence assessment model based on the manual risk assessment result and an output assessment result of the artificial intelligence assessment model.
Different from the embodiment, after the risk evaluation result of the person to be evaluated is obtained, the artificial risk evaluation result of the personal data is obtained, the parameters of the artificial intelligence evaluation model are adjusted based on the artificial risk evaluation result and the output evaluation result of the artificial intelligence evaluation model, and the artificial intelligence evaluation model can be retrained, so that the accuracy of the artificial intelligence evaluation model can be improved.
In some embodiments, the personal data of the person under evaluation includes at least one of: basic information data, medical insurance data, medical data and social insurance data of the personnel to be evaluated.
Different from the embodiment, the personal data of the person to be evaluated is set to include at least one of the basic information data, the medical insurance data, the medical data and the social insurance data of the person to be evaluated, so that the coverage of the personal data can be favorably improved, and the accuracy of the artificial intelligence evaluation model can be favorably improved.
Referring to fig. 5, fig. 5 is a schematic block diagram of an embodiment of an electronic device 50 according to the present application. The electronic device 50 comprises a memory 51 and a processor 52 coupled to each other, and the processor 52 is configured to execute program instructions stored in the memory 51 to implement the steps in any of the above-described embodiments of the risk assessment method. In one particular implementation scenario, electronic device 50 may include, but is not limited to: a microcomputer, a server, and the electronic device 50 may also include a mobile device such as a notebook computer, a tablet computer, and the like, which is not limited herein.
In particular, the processor 52 is configured to control itself and the memory 51 to implement the steps in any of the above-described embodiments of the risk assessment method. Processor 52 may also be referred to as a CPU (Central Processing Unit). Processor 52 may be an integrated circuit chip having signal processing capabilities. The Processor 52 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 52 may be commonly implemented by an integrated circuit chip.
According to the scheme, low efficiency caused by manual evaluation can be avoided, so that the evaluation efficiency can be improved, and in addition, the evaluation accuracy and stability can be improved as the evaluation process is not subjectively influenced.
Referring to fig. 6, fig. 6 is a block diagram illustrating an embodiment of a computer readable storage medium 60 according to the present application. The computer readable storage medium 60 stores program instructions 601 capable of being executed by a processor, the program instructions 601 for implementing the steps in any of the above-described embodiments of the risk assessment method.
According to the scheme, low efficiency caused by manual evaluation can be avoided, so that the evaluation efficiency can be improved, and in addition, the evaluation accuracy and stability can be improved as the evaluation process is not subjectively influenced.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely one type of logical division, and an actual implementation may have another division, for example, a unit or a component may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on network elements. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Claims (14)
1. A method of risk assessment, comprising:
acquiring personal data of a person to be evaluated;
and carrying out risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed.
2. The method according to claim 1, wherein the performing risk assessment on the personal data by using an artificial intelligence assessment model to obtain a risk assessment result of the person to be assessed comprises:
performing risk assessment on the personal data by using the artificial intelligence assessment model to obtain a primary assessment result output by the artificial intelligence assessment model;
taking the preliminary evaluation result as the risk evaluation result; or generating the risk assessment result based on the preliminary assessment result.
3. The method of claim 2, wherein the preliminary evaluation result comprises at least one of: the normal risk probability of the person to be evaluated and the abnormal risk probability of the person to be evaluated; the larger the normal risk probability is, the lower the risk of the person to be evaluated is, and the larger the abnormal risk probability is, the higher the risk of the person to be evaluated is.
4. The method of claim 3, wherein generating the risk assessment result based on the preliminary assessment result comprises:
and obtaining the risk score of the person to be evaluated by utilizing the normal risk probability and/or the abnormal risk probability, wherein the risk score is positively correlated with the normal risk probability and negatively correlated with the abnormal risk probability.
5. The method according to any one of claims 1 to 4, wherein after the risk assessment is performed on the personal data by using the artificial intelligence assessment model and the risk assessment result of the person to be assessed is obtained, the method further comprises:
and obtaining a risk treatment measure corresponding to the person to be evaluated according to the risk evaluation result.
6. The method according to any one of claims 1 to 5, wherein before the risk assessment of the personal data by using the artificial intelligence assessment model to obtain the risk assessment result of the person to be assessed, the method further comprises the following steps of performing characteristic processing on the personal data:
adding new personal data with a first preset data characteristic by using the acquired personal data; and/or eliminating personal data with a second preset data characteristic from the acquired personal data;
the method for performing risk assessment on the personal data by using the artificial intelligence assessment model to obtain a risk assessment result of the person to be assessed comprises the following steps:
and carrying out risk assessment on the personal data subjected to the feature processing by using an artificial intelligence assessment model to obtain a risk assessment result of the personnel to be assessed.
7. The method of any one of claims 1 to 6, wherein the personal data comprises at least one data; before the risk assessment is performed on the personal data by using the artificial intelligence assessment model and the risk assessment result of the person to be assessed is obtained, the method further comprises the following steps:
determining a data type to which each data in the personal data belongs, wherein the data type comprises continuous data and discrete data;
and respectively preprocessing the continuous data and the discrete data by utilizing different preset preprocessing modes.
8. The method of claim 7, wherein determining the data type to which each of the personal data belongs comprises:
if the data in the personal data is numerical data, determining the data to be continuous data;
if the data in the personal data is non-numerical data, determining the data to be discrete data;
the preprocessing the continuous data and the discrete data respectively by using different preset preprocessing modes comprises:
carrying out Gaussian distribution processing on the continuous data; and/or the presence of a gas in the gas,
and encoding the discrete data.
9. The method of any of claims 1 to 8, wherein the artificial intelligence assessment model comprises any of a machine learning model, a deep learning model; and/or the presence of a gas in the gas,
the artificial intelligence evaluation model is obtained by training sample evaluation data marked with real risk evaluation results.
10. The method of claim 9, wherein after the risk assessment of the personal data is performed by using an artificial intelligence assessment model to obtain a risk assessment result of the person to be assessed, the method further comprises:
acquiring an artificial risk assessment result of the personal data;
and adjusting parameters of the artificial intelligence evaluation model based on the artificial risk evaluation result and the output evaluation result of the artificial intelligence evaluation model.
11. The method according to any one of claims 1 to 10, wherein the personal data of the person to be assessed comprises at least one of: and the basic information data, the medical insurance data, the medical data and the social insurance data of the personnel to be evaluated.
12. A risk assessment device, comprising:
the data acquisition module is used for acquiring personal data of a person to be evaluated;
and the evaluation processing module is used for carrying out risk evaluation on the personal data by utilizing an artificial intelligence evaluation model to obtain a risk evaluation result of the personnel to be evaluated.
13. An electronic device comprising a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the risk assessment method of any one of claims 1 to 10.
14. A computer readable storage medium having stored thereon program instructions which, when executed by a processor, implement the risk assessment method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010220568.XA CN111507578A (en) | 2020-03-25 | 2020-03-25 | Risk assessment method and related device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010220568.XA CN111507578A (en) | 2020-03-25 | 2020-03-25 | Risk assessment method and related device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111507578A true CN111507578A (en) | 2020-08-07 |
Family
ID=71869020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010220568.XA Withdrawn CN111507578A (en) | 2020-03-25 | 2020-03-25 | Risk assessment method and related device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507578A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115098508A (en) * | 2022-07-04 | 2022-09-23 | 成都秦川物联网科技股份有限公司 | Smart city check list generation method, system and device based on Internet of things |
-
2020
- 2020-03-25 CN CN202010220568.XA patent/CN111507578A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115098508A (en) * | 2022-07-04 | 2022-09-23 | 成都秦川物联网科技股份有限公司 | Smart city check list generation method, system and device based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3292492B1 (en) | Predicting likelihoods of conditions being satisfied using recurrent neural networks | |
| EP3413221A1 (en) | Risk assessment method and system | |
| CN109816092A (en) | Deep neural network training method, device, electronic equipment and storage medium | |
| CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
| CN111785384A (en) | Abnormal data identification method based on artificial intelligence and related equipment | |
| CN111582341B (en) | User abnormal operation prediction method and device | |
| CN110135681A (en) | Risk subscribers recognition methods, device, readable storage medium storing program for executing and terminal device | |
| CN113298121B (en) | Message sending method and device based on multi-data source modeling and electronic equipment | |
| CN111967655A (en) | Short-term load prediction method and system | |
| CN111179089A (en) | Money laundering transaction identification method, device and equipment | |
| CN113486302A (en) | Data processing method and device | |
| CN110941644B (en) | Policy data generation method, device, equipment and storage medium | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| CN116739759A (en) | Asset and fund matching method, device and equipment based on order risk identification | |
| CN109584086B (en) | Method for predicting hospitalization rationality based on prediction model and related products | |
| CN111507578A (en) | Risk assessment method and related device and equipment | |
| CN111507850A (en) | Authority guaranteeing method and related device and equipment | |
| CN117198446A (en) | Ward-round report automatic generation method based on medical care intercom equipment | |
| CN110633971A (en) | Method and device for estimating loss | |
| CN112308294B (en) | Method and device for predicting default probability | |
| CN112085584A (en) | Enterprise credit default probability calculation method and system | |
| CN114707420A (en) | Credit fraud behavior identification method, device, equipment and storage medium | |
| CN114170000A (en) | Credit card user risk category identification method, device, computer equipment and medium | |
| CN113256404A (en) | Data processing method and device | |
| CN113159419A (en) | Group feature portrait analysis method, device and equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200807 |