CN113673916B - Risk data identification method, terminal device and computer-readable storage medium - Google Patents
Risk data identification method, terminal device and computer-readable storage medium Download PDFInfo
- Publication number
- CN113673916B CN113673916B CN202111237378.XA CN202111237378A CN113673916B CN 113673916 B CN113673916 B CN 113673916B CN 202111237378 A CN202111237378 A CN 202111237378A CN 113673916 B CN113673916 B CN 113673916B
- Authority
- CN
- China
- Prior art keywords
- data
- value
- evaluated
- report
- risk
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 116
- 238000004364 calculation method Methods 0.000 claims abstract description 77
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 76
- 230000002159 abnormal effect Effects 0.000 claims description 48
- 238000012502 risk assessment Methods 0.000 claims description 26
- 238000012417 linear regression Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 9
- 238000005094 computer simulation Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 abstract description 15
- 238000012854 evaluation process Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 238000013501 data transformation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010079 rubber tapping Methods 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a risk data identification method, terminal equipment and a computer readable storage medium, wherein the risk data identification method comprises the following steps: the evaluation method comprises the steps of comprehensively evaluating data to be evaluated from multiple evaluation angles by using a calculation model constructed by a naive Bayesian algorithm, wherein the evaluation result is more accurate by using the calculation model, such as the fit degree of report data to be evaluated and a sample set mean value, the fit degree of the report data to be evaluated and the overall change trend of the sample set and the relation between the output evaluation result and the maximum value and the minimum value in the sample set, and meanwhile, the output evaluation result is input into the sample set of the calculation model for updating, so that the overall evaluation standard of the calculation model can adapt to the change trend of an application environment, manual secondary evaluation according to the change trend of the application environment is not needed, the evaluation process is quicker, and the timeliness requirement of enterprises for obtaining business information is met.
Description
Technical Field
The present invention relates to the field of real estate BI and data identification technologies, and in particular, to a risk data identification method, a terminal device, and a computer-readable storage medium.
Background
In the field of real estate BI (Business Intelligence), a lot of data or indicators are involved, such as subscription unsigned numbers, overdue unsigned numbers, sold quantities, remaining quantities, rate of refunds, etc.; these are the data indicators most concerned by real estate practitioners, but these data indicators tend to change and the trend of change is dynamic, some changes are normal fluctuations, some changes are abnormal, and these abnormal data can reflect some business information. However, the existing method for identifying whether the data index change is abnormal is to identify through setting a simple rule, the final identification result is often not accurate enough, and the existing method needs to further judge whether the data index change is abnormal manually, so that a certain trouble is brought to an enterprise to follow up business information or adjust an operation strategy in time.
Disclosure of Invention
The invention mainly aims to provide a risk data identification method, and aims to solve the technical problems that the existing technology for identifying whether the index change of data is abnormal is inaccurate in identification result and needs to be further judged manually.
In order to achieve the above object, the present invention provides a risk data identification method, including the steps of:
inputting the data value of the report data to be evaluated and the data generation time into a trained calculation model to calculate the characteristic number of the report data to be evaluated based on the full set of all data samples in a training sample set, wherein the characteristic number of the full set comprises a first full set characteristic value, a second full set characteristic value, a third full set characteristic value and a fourth full set characteristic value;
obtaining a first full set characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of all the data samples;
substituting the data value of the report data to be evaluated, the minimum data value of all the data samples, the maximum data value of all the data samples and the average data value of all the data samples into a preset calculation formula to obtain a second full set characteristic value;
obtaining a third full set characteristic value according to the size relationship between the data value of the report data to be evaluated and the minimum data values of all the data samples or the maximum data values of all the data samples;
obtaining a fourth full set characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression value, wherein the linear regression value is the value of the report data to be evaluated corresponding to the linear regression function generated by all the data samples;
and outputting a risk evaluation result of the report data to be evaluated by combining the feature number of the complete set and the calculation model, wherein the calculation model is constructed by a naive Bayesian algorithm, and the risk evaluation result comprises the following steps: normal, mild abnormal and severe abnormal;
adding the data generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated into a training sample set as data samples;
obtaining the training sample set to train the computational model, wherein the training sample set comprises a plurality of data samples, and a single data sample comprises: data generation time, data values, and risk assessment results.
Further, adding the data generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated as data samples to the training sample set includes:
and adding the data value generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated to the front end of the data training sample set according to the data generation time sequence, and deleting the data sample at the tail end of the data training sample set.
Further, after the step of calculating the full set feature number of all the data samples in the training sample set based on the report data to be evaluated, the method further includes:
calculating the time window characteristic number of the report data to be evaluated based on the data samples in the preset time period in the training sample set, wherein the time window characteristic number comprises the following steps: a first time window eigenvalue, a second time window eigenvalue, a third time window eigenvalue, and a fourth time window eigenvalue;
obtaining a first time window characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of the data samples in a preset time period;
substituting the data value of the report data to be evaluated, the minimum data value of the data sample in the preset time period, the maximum data value of the data sample in the preset time period and the average value of the data values of the data sample in the preset time period into a preset calculation formula to obtain a second time window characteristic value;
obtaining a third time window characteristic value according to the size relation between the data value of the report data to be evaluated and the minimum data value of the data sample in the preset time period or the maximum data value of the data sample in the preset time period;
obtaining a fourth time window characteristic value according to the ratio of the data value of the report data to be evaluated to a linear regression value in a preset time period, wherein the linear regression value in the preset time period is a corresponding value of the report data to be evaluated in a linear regression function generated by data samples in the preset time period;
and outputting a risk evaluation result of the report data to be evaluated by combining the complete set characteristic number, the time window characteristic number and the calculation model.
Further, the preset calculation formula is as follows:
wherein, a is the data value of the report data to be evaluated, b is the minimum value in the data set, c is the maximum value in the data set, and d is the average value of the data values in the data set.
Further, the step of outputting a risk assessment result of the report data to be assessed by combining the feature number of the full set, the feature number of the time window and the calculation model comprises:
and respectively calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated according to each characteristic value of the report data to be evaluated, and outputting the risk evaluation result with the maximum weight as the risk evaluation result of the report data to be evaluated.
Further, the step of respectively calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated comprises:
calculating the weight of the report data to be evaluated with normal evaluation result according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with normal risk evaluation result;
calculating the weight of the slightly abnormal evaluation result of the report data to be evaluated according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with the slightly abnormal risk evaluation result;
and calculating the weight of the report data to be evaluated with the serious abnormity evaluation result according to the frequency of each characteristic value of the report data to be evaluated in the training sample set with the serious abnormity risk evaluation result.
In addition, to achieve the above object, the present invention also provides a terminal device, which is characterized in that the terminal device includes: a memory, a processor and a risk data identification program stored on the memory and executable on the processor, the risk data identification program when executed by the processor implementing the steps of the risk data identification method as described above.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, wherein the readable storage medium stores thereon a risk data identification program, and the risk data identification program, when executed by a processor, implements the steps of the risk data identification method as described above.
According to the risk data identification method provided by the embodiment of the invention, the report data to be evaluated is comprehensively evaluated from a plurality of evaluation angles, the report data to be evaluated and the sample set mean value, the report data to be evaluated and the sample set overall variation trend and the relation between the report data to be evaluated and the sample set maximum value and minimum value are compared, so that the evaluation result is more objective and accurate, and meanwhile, the output evaluation result is input into the sample set of the calculation model for updating, so that the overall evaluation standard of the calculation model can adapt to the variation trend of the application environment, manual secondary evaluation according to the variation trend of the application environment is not needed, the evaluation process is quicker, and the timeliness requirement of enterprises for obtaining business information is met.
Drawings
Fig. 1 is a schematic structural diagram of a terminal device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a risk data identification method according to a first embodiment of the present invention;
fig. 3 is a flowchart illustrating a risk data identification method according to a second embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: the method comprises the steps of comprehensively evaluating report data to be evaluated from multiple evaluation angles, comparing the report data to be evaluated with a sample set mean value, the report data to be evaluated with a sample set overall variation trend and the report data to be evaluated with the maximum value and the minimum value in the sample set, outputting a risk evaluation result of the report data to be evaluated, and inputting the report data to be evaluated and a result risk evaluation result thereof into a calculation model.
In the prior art, the identification of whether the data index change is abnormal or not is realized by setting simple rules, the final identification result is often not accurate enough, and the data index change needs to be further judged manually, so that certain trouble is brought to enterprises to follow up business information or adjust operation strategies timely.
The invention provides a solution, so that the evaluation result is more objective and accurate, and the output evaluation result is input into the sample of the calculation model to be updated in a centralized manner, so that the overall evaluation standard of the calculation model can adapt to the change trend of the application environment, manual secondary evaluation according to the change trend of the application environment is not needed, the evaluation process is quicker, and the timeliness requirement of enterprises for acquiring business information is met.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a terminal device in a hardware operating environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, and can also be an electronic terminal device with a communication function, such as a smart phone, a tablet computer, a portable computer and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the terminal may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. Such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the mobile terminal is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile terminal; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a risk data identification program.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to invoke the risk data identification program stored in the memory 1005 and perform the following operations:
inputting the data value and the data generation time of the report data to be evaluated into the trained calculation model for risk evaluation to obtain a risk evaluation result of the report data to be evaluated, wherein the calculation model is constructed by a naive Bayesian algorithm;
adding the data generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated into a training sample set as data samples;
obtaining the training sample set to train the computational model, wherein the training sample set comprises a plurality of data samples, and a single data sample comprises: data generation time, data values, and risk assessment results.
Further, the processor 1001 may call the risk data identification program stored in the memory 1005, and also perform the following operations:
adding the data generation time, the data value and the risk assessment result corresponding to the report data to be assessed as data samples to the training sample set comprises:
and adding the data value generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated to the front end of the data training sample set according to the data generation time sequence, and deleting the data sample at the tail end of the data training sample set.
Further, the processor 1001 may call the risk data identification program stored in the memory 1005, and also perform the following operations:
inputting the data value of the report data to be evaluated and the data generation time into the trained calculation model for risk evaluation, and obtaining the risk evaluation result of the report data to be evaluated comprises the following steps:
calculating the characteristic number of the report data to be evaluated based on the full set of all data samples in the training sample set;
and outputting a risk evaluation result of the report data to be evaluated by combining the complete set characteristic number and the calculation model, wherein the risk evaluation result comprises the following steps: normal, mild abnormal and severe abnormal.
Further, the processor 1001 may call the risk data identification program stored in the memory 1005, and also perform the following operations:
the calculating the characteristic number of the report data to be evaluated based on the full set of all the data samples in the training sample set comprises the following steps:
obtaining a first full set characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of all the data samples;
substituting the data value of the report data to be evaluated, the minimum data value of all the data samples, the maximum data value of all the data samples and the average data value of all the data samples into a preset calculation formula to obtain a second full set characteristic value;
obtaining a third full set characteristic value according to the size relationship between the data value of the report data to be evaluated and the minimum data values of all the data samples or the maximum data values of all the data samples;
obtaining a fourth corpus characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression values of all the data samples;
wherein the full set eigenvalue comprises a first full set eigenvalue, a second full set eigenvalue, a third full set eigenvalue, and a fourth full set eigenvalue.
Further, the processor 1001 may call the risk data identification program stored in the memory 1005, and also perform the following operations:
after the step of calculating the full set characteristic number of all the data samples in the training sample set based on the report data to be evaluated, the method further comprises the following steps:
calculating the time window characteristic number of the report data to be evaluated based on the data samples in the preset time period in the training sample set, wherein the time window characteristic number comprises the following steps: a first time window eigenvalue, a second time window eigenvalue, a third time window eigenvalue, and a fourth time window eigenvalue;
obtaining a first time window characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of the data samples in a preset time period;
substituting the data value of the report data to be evaluated, the minimum data value of the data sample in the preset time period, the maximum data value of the data sample in the preset time period and the average value of the data values of the data sample in the preset time period into a preset calculation formula to obtain a second time window characteristic value;
obtaining a third time window characteristic value according to the size relation between the data value of the report data to be evaluated and the minimum data value of the data sample in the preset time period or the maximum data value of the data sample in the preset time period;
obtaining a fourth time window characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression value of the data sample in the preset time period;
and outputting a risk evaluation result of the report data to be evaluated by combining the complete set characteristic number, the time window characteristic number and the calculation model.
Further, the preset calculation formula is as follows:
wherein, a is the data value of the report data to be evaluated, b is the minimum value in the data set, c is the maximum value in the data set, and d is the average value of the data values in the data set.
Further, the processor 1001 may call the risk data identification program stored in the memory 1005, and also perform the following operations:
the risk assessment result of the report data to be assessed output by combining the complete set characteristic number, the time window characteristic number and the calculation model comprises the following steps:
and respectively calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated according to each characteristic value of the report data to be evaluated, and outputting the risk evaluation result with the maximum weight as the risk evaluation result of the report data to be evaluated.
Further, the processor 1001 may call the risk data identification program stored in the memory 1005, and also perform the following operations:
the step of respectively calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated comprises the following steps:
calculating the weight of the report data to be evaluated with normal evaluation result according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with normal risk evaluation result;
calculating the weight of the slightly abnormal evaluation result of the report data to be evaluated according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with the slightly abnormal risk evaluation result;
and calculating the weight of the report data to be evaluated with the serious abnormity evaluation result according to the frequency of each characteristic value of the report data to be evaluated in the training sample set with the serious abnormity risk evaluation result.
Referring to fig. 2, in a first embodiment of the risk data identification method of the present invention, the risk data identification method includes:
step S10, inputting the data value and the data generation time of the report data to be evaluated into the trained calculation model for risk evaluation to obtain the risk evaluation result of the report data to be evaluated, wherein the calculation model is constructed by a naive Bayes algorithm;
the calculation model is constructed by a naive Bayesian algorithm and is trained by using a training sample set, and report data to be evaluated is received, wherein the report data to be evaluated comprises the generation time and specific data values, and the risk evaluation is required to be carried out if the data index is a subscription rate and the subscription rate in 2021 and 8 months is 30%. Calculating the characteristic number of the report data to be evaluated based on the full set of all data samples in the training sample set; and outputting a risk evaluation result of the report data to be evaluated by combining the complete set characteristic number and the calculation model, wherein the risk evaluation result comprises the following steps: normal, mild abnormal and severe abnormal.
For a more convenient description, in this embodiment, data of nearly three years is selected from all data sample sets in the training sample, and the specific time range may be determined according to the actual application scenario, which is not limited herein. The full set characteristic number comprises a first full set characteristic value, a second full set characteristic value, a third full set characteristic value and a fourth full set characteristic value, and the calculation mode of each full set characteristic value is as follows: obtaining a first full set characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of all the data samples; substituting the data value of the report data to be evaluated, the minimum data value of all the data samples, the maximum data value of all the data samples and the average data value of all the data samples into a preset calculation formula to obtain a second full set characteristic value; obtaining a third full set characteristic value according to the size relationship between the data value of the report data to be evaluated and the minimum data values of all the data samples or the maximum data values of all the data samples; and obtaining a fourth full set characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression values of all the data samples. If the contract signing rate of the current report data to be evaluated is 2021 year 8 month is 30%, and the average contract signing rate of the calculation model statistics in the last three years per month is 50%, the first full set characteristic value is 30%/50% = 0.6; the lowest subscription rate and the highest subscription rate of the calculation model statistics in the last three years are respectively 20% and 70%, and the calculation model is substituted into a preset calculation formula:
(wherein, a is the data value of the report data to be evaluated, b is the minimum value in the data set, c is the maximum value in the data set, and d is the average value of the data values in the data set), and the second full set characteristic value is about 0.65; the size relationship is whether the data value is larger than the maximum value or the data value is smaller than the minimum value, and the contract signing rate of the report data to be evaluated is 30% larger than the minimum contract signing rate of 20% and smaller than the maximum contract signing rate of 70%, so that the characteristic value of the third complete set is negative; the linear regression values of all the data samples (a linear regression function is constructed by the calculation model according to each data sample in the training sample set, wherein each data sample comprises time and a signing rate, the time is used as an independent variable signing rate and is used as a dependent variable, the time of the report data to be evaluated is substituted into the constructed linear regression function to obtain the linear regression value, the linear regression value is the signing rate predicted according to the training sample under the condition of evaluating the data time), the calculation model calculates that the characteristic value of the fourth complete set is 60%, and the characteristic value of the fourth complete set is 0.5.
Further, according to each characteristic value of the report data to be evaluated, calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated respectively, and outputting the risk evaluation result with the maximum weight as the risk evaluation result of the report data to be evaluated. The weight of each risk assessment result is specifically calculated as follows: calculating the weight of the report data to be evaluated with normal evaluation result according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with normal risk evaluation result; calculating the weight of the slightly abnormal evaluation result of the report data to be evaluated according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with the slightly abnormal risk evaluation result; and calculating the weight of the report data to be evaluated with the serious abnormity evaluation result according to the frequency of each characteristic value of the report data to be evaluated in the training sample set with the serious abnormity risk evaluation result. If the proportion of the risk assessment results in all the training samples is normal is 73%, and the distribution of the first full set characteristic values in the data samples with normal risk assessment results is 18% or less than 0.4 proportion, 21% or less than 0.4 proportion and less than or equal to 0.8 proportion, 29% or more than 0.8 proportion and less than or equal to 1.2 proportion, 22% or less than 1.2 proportion and less than or equal to 1.6 proportion, and 10% or more than 1.6 proportion, the first full set characteristic of the report data to be assessed is 0.5 which belongs to more than 0.4 and less than or equal to 0.8, so that the proportion is 21%, namely the frequency is 0.21; similarly, the second full set characteristic value, the third full set characteristic value and the fourth full set characteristic value are not repeated herein according to the distribution situation, the frequencies of the characteristic values are 0.27, 0.89 and 0.52 respectively, and the weight of the report data to be evaluated is calculated to be 0.73 (the normal proportion of all the training sample risk evaluation results) x 0.21 x 0.27 x 0.89 x 0.52=0.01915 when the evaluation result is normal. The weights of the report data to be evaluated under the condition that the evaluation result is slightly abnormal and under the condition that the evaluation result is seriously abnormal are calculated to be 0.00725 and 0.00392 respectively by using the same method, and the weight of the report data to be evaluated under the condition that the evaluation result is normal is obtained by comparison, so that the risk evaluation result of the report data to be evaluated is normal and is output to a user.
It can be understood that the evaluation of the report data to be evaluated does not simply set the abnormal range, but uses several characteristic values. The first full set characteristic value reflects the degree that the report data to be evaluated is far away from or close to the sample set mean value; the second set characteristic value and the fourth set characteristic value reflect the degree of the trend of the report data to be evaluated away from or approaching the whole sample set; the third set of characteristic values directly reflects the relationship with the maximum value and the minimum value in the sample set; further, the probability of the data with the plurality of characteristic values under the corresponding evaluation result can be calculated according to the distribution of each characteristic value in the data sample of each evaluation result. Therefore, the risk evaluation result evaluation angle of the report data to be evaluated is more, and the evaluation result is more accurate.
Step S20, adding the data generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated into a training sample set as data samples;
it can be understood that, in this embodiment, the data value generation time, the data value, and the risk assessment result corresponding to the report data to be evaluated are added to the front end of the data training sample set according to the data generation time sequence, and the data sample at the tail end of the data training sample set is deleted, where the risk assessment result with the contract rate of 2021 year 8 month being 30% is normal, and the risk assessment result is input into the training set, and the relevant data with the contract rate of 2019 year 8 month is deleted.
And the output result of the calculation model is input into the sample set of the calculation model again to form a feedback effect, so that the sample set in the calculation model is continuously optimized, and the evaluation standard is more in line with the current application environment.
Step S30, obtaining the training sample set to train the computational model, where the training sample set includes a plurality of data samples, and a single data sample includes: data generation time, data values, and risk assessment results.
It can be understood that in this implementation, the calculation model constructed by the training sample set and the naive bayes algorithm is for a certain type of data index, and thus the data samples in the training samples are related data of the type of data index. The training sample set may be a historical data sample set of the data index, or may be a data sample set of the data index generated manually. In particular, a single data sample includes a data value, a date the data value was generated, and a risk assessment result for the data value. For example, in the real estate domain, the data index is the contract signing rate, and a single data sample in the contract signing rate includes: the specific data value of the contract rate at 1 month in 2021 was 62% and the risk assessment results were normal. The training sample set will also be different for different data indices. The training of the calculation model is to input the acquired training sample set into the calculation model, and the subsequent risk assessment of the current data is based on the training sample set.
The calculation model can count the data value of each data sample in the input training sample set and each characteristic value of each data sample, and respectively generate the distribution conditions of each index under the normal, slight abnormal and serious abnormal evaluation results. The distribution condition of each index can reflect the judgment standard of the current calculation model on the certain type of data index. The output result of the calculation model is continuously added into the training sample, so that the subsequently received calculation result of the characteristic value of the report data to be evaluated is more consistent with the current application environment.
In the embodiment, the evaluation standard of the report data to be evaluated is not set with an abnormal range simply, but the report data to be evaluated is evaluated comprehensively from multiple evaluation angles by using a naive Bayesian algorithm, for example, the matching degree of the report data to be evaluated and the mean value of the sample set, the matching degree of the report data to be evaluated and the overall change trend of the sample set, and the relation between the report data to be evaluated and the maximum value and the minimum value in the sample set are used, so that the evaluation result is more accurate, and meanwhile, the output evaluation result is input into the sample set of the calculation model for updating, so that the overall evaluation standard of the calculation model can adapt to the change trend of the application environment, manual secondary evaluation according to the change trend of the application environment is not needed, the evaluation process is quicker, and the timeliness requirement of enterprises for obtaining business information is met.
Further, referring to fig. 3, a risk data identification method according to a second embodiment of the present invention includes:
step S11, calculating the characteristic number of the report to be evaluated based on the full set of all the data samples in the training sample set;
obtaining a first full set characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of all the data samples; substituting the data value of the report data to be evaluated, the minimum data value of all the data samples, the maximum data value of all the data samples and the average data value of all the data samples into a preset calculation formula to obtain a second full set characteristic value; obtaining a third full set characteristic value according to the size relationship between the data value of the report data to be evaluated and the minimum data values of all the data samples or the maximum data values of all the data samples; and obtaining a fourth full set characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression values of all the data samples. In the first embodiment, the way of calculating the feature value of each complete set is specifically described, and details are not described here.
Step S12, calculating the time window characteristic number of the report data to be evaluated based on the data samples in the preset time period in the training sample set;
wherein, the time window characteristic number comprises: obtaining a first time window characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of the data samples in a preset time period; substituting the data value of the report data to be evaluated, the minimum data value of the data sample in the preset time period, the maximum data value of the data sample in the preset time period and the average value of the data values of the data sample in the preset time period into a preset calculation formula to obtain a second time window characteristic value; obtaining a third time window characteristic value according to the size relation between the data value of the report data to be evaluated and the minimum data value of the data sample in the preset time period or the maximum data value of the data sample in the preset time period; and obtaining a fourth time window characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression value of the data sample in the preset time period. It can be understood that the time window feature number is different from the full set feature number in that the sample set in the time window feature number calculation is recent data, for convenience of description, in this embodiment, a data sample of the last year is selected as the time window feature number calculation training sample set, and a specific time period can be set according to the characteristics and requirements of the data index.
As in the above example, the data index is the contract signing rate, the contract signing rate at 8 months in 2021 is 30%, and the average contract signing rate is 60% in each month in the last year according to the statistical result, then the first time window characteristic value is 30%/60% = 0.5; the minimum contract signing rate is 30% and the maximum contract signing rate is 80% every month in the last year, and the minimum contract signing rate and the maximum contract signing rate are substituted into a preset calculation formula:
(wherein, a is the data value of the report data to be evaluated, b is the minimum value in the data set, c is the maximum value in the data set, and d is the average value of the data values in the data set), and the characteristic value of the second time window is about 0.5; the contract signing rate of the report data to be evaluated is 30% and is equal to the lowest contract signing rate of 30% and is less than the highest contract signing rate of 80%, so that the characteristic value of the third time window is negative; the linear regression value of the data sample in the preset time period is 65%, and the feature value of the fourth full set is 0.46.
Step S13, combining the feature number of the complete set, the feature number of the time window and the calculation model to output the risk evaluation result of the report data to be evaluated;
and the calculation model respectively calculates the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated according to each characteristic value of the report data to be evaluated, and outputs the risk evaluation result with the maximum weight as the risk evaluation result of the report data to be evaluated. Each characteristic value of the calculation model according to the report data to be evaluated can be a characteristic value contained in the characteristic number of a single time window, or can be all characteristic values in the characteristic number of a full set and the characteristic number of the single time window. The calculation method in the case of the feature values included in the feature number of the single time window is the same as the calculation method in the case of using the feature values of the feature number of the full set. Similarly, when the full-set feature number and the single-time-window feature number are both contained, the distribution conditions of the first full-set feature value, the second full-set feature value, the third full-set feature value, the fourth full-set feature value, the first time window feature value, the second time window feature value, the third time window feature value and the fourth time window feature value under the normal, slight abnormal and serious abnormal risk assessment results are counted, the frequency of each feature value of the report data to be assessed under the normal, slight abnormal and serious abnormal risk assessment results is obtained, and the weight of the report data to be assessed under each assessment result is calculated (for example, when the full-set feature number and the single-time-window feature number are contained, the assessment result of the report data to be assessed is the normal weight = the frequency of the first full-set feature value x the frequency of the second full-set feature value x the frequency of the third full-set feature value x the frequency of the fourth full-set feature value x the frequency of the first time-window feature value x the frequency of the second time-window The frequency of the mouth feature value × the frequency of the third time window feature value × the frequency of the fourth time window feature value), the evaluation result with the largest weight is output.
The first time window characteristic value, the second time window characteristic value, the third time window characteristic value and the fourth time window characteristic value are involved in weight calculation of different risk assessment results, and the time window characteristic values can reflect the relation between data to be estimated and recent data better, so that the final risk assessment results are more fit with the recent data transformation trend, and the accuracy of the final assessment results is guaranteed.
Step S21, adding the data value generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated into the training sample set as data samples;
and generating time and data value of the report data to be evaluated and the finally obtained risk evaluation result, inputting the data value and the finally obtained risk evaluation result into the calculation model again to form a training sample with a forward feedback function in the calculation model, so that the evaluation standard of the calculation model is updated in real time, and the evaluation result is more accurately matched with the current application environment.
Step S31, a training sample set is obtained to train the calculation model constructed by the naive Bayes algorithm, the training sample set comprises a plurality of data samples, wherein, a single data sample comprises: data generation time, data values, and data risk assessment results.
And training a calculation model constructed by a naive Bayesian algorithm by using the updated training sample set, wherein a single data sample comprises data generation time, a data value and a data risk evaluation result. The calculation model will count and process the training samples, and calculate multiple feature values of a single data sample, and the specific calculation manner is the same as that of the feature values of the report data to be evaluated in the first embodiment. In addition, when the relevant data of all the data samples in the training sample set is counted, the distribution of each feature value under each evaluation result of the data samples in one year in the near training sample set is also counted.
In this embodiment, data samples in a recent year are additionally calculated and processed, the time window characteristic number of the report data to be estimated is calculated on the basis of the data samples in the recent year, and the time window characteristic number is involved in risk assessment, so that the risk assessment result of the calculation model is more suitable for the trend of a real-time environment, the phenomenon that the time span of a training sample set is too long, the trend of recent training samples is weakened, and the final risk assessment result is more accurate is avoided.
In addition, the present invention also provides a terminal device, which is characterized in that the terminal device includes: a memory, a processor and a risk data identification program stored on the memory and executable on the processor, the risk data identification program when executed by the processor implementing the steps of the risk data identification method as described above.
The present invention also provides a computer-readable storage medium, wherein the readable storage medium stores a risk data identification program, and the risk data identification program, when executed by a processor, implements the steps of the risk data identification method as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A risk data identification method, characterized in that the risk data identification method comprises the steps of:
inputting the data value of the report data to be evaluated and the data generation time into a trained calculation model to calculate the characteristic number of the report data to be evaluated based on the full set of all data samples in a training sample set, wherein the characteristic number of the full set comprises a first full set characteristic value, a second full set characteristic value, a third full set characteristic value and a fourth full set characteristic value;
obtaining a first full set characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of all the data samples;
substituting the data value of the report data to be evaluated, the minimum data value of all the data samples, the maximum data value of all the data samples and the average data value of all the data samples into a preset calculation formula to obtain a second full set characteristic value;
obtaining a third full set characteristic value according to the size relationship between the data value of the report data to be evaluated and the minimum data values of all the data samples or the maximum data values of all the data samples;
obtaining a fourth full set characteristic value according to the ratio of the data value of the report data to be evaluated to the linear regression value, wherein the linear regression value is the value of the report data to be evaluated corresponding to the linear regression function generated by all the data samples;
and outputting a risk evaluation result of the report data to be evaluated by combining the feature number of the complete set and the calculation model, wherein the calculation model is constructed by a naive Bayesian algorithm, and the risk evaluation result comprises the following steps: normal, mild abnormal and severe abnormal;
adding the data generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated into a training sample set as data samples;
obtaining the training sample set to train the computational model, wherein the training sample set comprises a plurality of data samples, and a single data sample comprises: data generation time, data values, and risk assessment results.
2. The method for identifying risk data according to claim 1, wherein adding the data generation time, the data value and the risk assessment result corresponding to the report data to be assessed as the data sample to the training sample set comprises:
and adding the data value generation time and the data value of the report data to be evaluated and the risk evaluation result corresponding to the report data to be evaluated to the front end of the data training sample set according to the data generation time sequence, and deleting the data sample at the tail end of the data training sample set.
3. The risk data identification method according to claim 2, wherein after the step of calculating the full set feature number of all the data samples in the training sample set based on the report data to be evaluated, the method further comprises:
calculating the time window characteristic number of the report data to be evaluated based on the data samples in the preset time period in the training sample set, wherein the time window characteristic number comprises the following steps: a first time window eigenvalue, a second time window eigenvalue, a third time window eigenvalue, and a fourth time window eigenvalue;
obtaining a first time window characteristic value according to the ratio of the data value of the report data to be evaluated to the average value of the data values of the data samples in a preset time period;
substituting the data value of the report data to be evaluated, the minimum data value of the data sample in the preset time period, the maximum data value of the data sample in the preset time period and the average value of the data values of the data sample in the preset time period into a preset calculation formula to obtain a second time window characteristic value;
obtaining a third time window characteristic value according to the size relation between the data value of the report data to be evaluated and the minimum data value of the data sample in the preset time period or the maximum data value of the data sample in the preset time period;
obtaining a fourth time window characteristic value according to the ratio of the data value of the report data to be evaluated to a linear regression value in a preset time period, wherein the linear regression value in the preset time period is a corresponding value of the report data to be evaluated in a linear regression function generated by data samples in the preset time period;
and outputting a risk evaluation result of the report data to be evaluated by combining the complete set characteristic number, the time window characteristic number and the calculation model.
4. The risk data identification method of claim 3, wherein the preset calculation formula is:
wherein, a is the data value of the report data to be evaluated, b is the minimum value in the data set, c is the maximum value in the data set, and d is the average value of the data values in the data set.
5. The risk data identification method according to claim 4, wherein the outputting the risk assessment result of the report data to be assessed by combining the feature number of the full set, the feature number of the time window and the calculation model comprises:
and respectively calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated according to each characteristic value of the report data to be evaluated, and outputting the risk evaluation result with the maximum weight as the risk evaluation result of the report data to be evaluated.
6. The method for identifying risk data according to claim 5, wherein the step of respectively calculating the normal weight, the slight abnormal weight and the serious abnormal weight of the risk evaluation result of the report data to be evaluated comprises the following steps:
calculating the weight of the report data to be evaluated with normal evaluation result according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with normal risk evaluation result;
calculating the weight of the slightly abnormal evaluation result of the report data to be evaluated according to the frequency of each characteristic value of the report data to be evaluated appearing in the training sample set with the slightly abnormal risk evaluation result;
and calculating the weight of the report data to be evaluated with the serious abnormity evaluation result according to the frequency of each characteristic value of the report data to be evaluated in the training sample set with the serious abnormity risk evaluation result.
7. A terminal device, characterized in that the terminal device comprises: memory, a processor and a risk data identification program stored on the memory and executable on the processor, the risk data identification program when executed by the processor implementing the steps of the risk data identification method according to any one of claims 1 to 6.
8. A computer-readable storage medium, characterized in that the readable storage medium has stored thereon a risk data identification program which, when executed by a processor, implements the steps of the risk data identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237378.XA CN113673916B (en) | 2021-10-25 | 2021-10-25 | Risk data identification method, terminal device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237378.XA CN113673916B (en) | 2021-10-25 | 2021-10-25 | Risk data identification method, terminal device and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113673916A CN113673916A (en) | 2021-11-19 |
| CN113673916B true CN113673916B (en) | 2022-02-08 |
Family
ID=78550950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111237378.XA Active CN113673916B (en) | 2021-10-25 | 2021-10-25 | Risk data identification method, terminal device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673916B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063747A (en) * | 2014-06-26 | 2014-09-24 | 上海交通大学 | Performance abnormality prediction method in distributed system and system |
| CN106872657A (en) * | 2017-01-05 | 2017-06-20 | 河海大学 | A kind of multivariable water quality parameter time series data accident detection method |
| CN109242499A (en) * | 2018-09-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of processing method of transaction risk prediction, apparatus and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092582B (en) * | 2017-03-31 | 2021-04-27 | 江苏方天电力技术有限公司 | Online abnormal value detection and confidence evaluation method based on residual posterior |
| CN110046633B (en) * | 2018-11-23 | 2023-05-02 | 创新先进技术有限公司 | Data quality detection method and device |
| US20210158236A1 (en) * | 2019-11-25 | 2021-05-27 | EMC IP Holding Company LLC | Ai driven supplier selection and tam allocation |
-
2021
- 2021-10-25 CN CN202111237378.XA patent/CN113673916B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063747A (en) * | 2014-06-26 | 2014-09-24 | 上海交通大学 | Performance abnormality prediction method in distributed system and system |
| CN106872657A (en) * | 2017-01-05 | 2017-06-20 | 河海大学 | A kind of multivariable water quality parameter time series data accident detection method |
| CN109242499A (en) * | 2018-09-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of processing method of transaction risk prediction, apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113673916A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222925B (en) | Performance quantitative assessment method and device and computer readable storage medium | |
| CN109993627B (en) | Recommendation method, recommendation model training device and storage medium | |
| CN111383101A (en) | Post-loan risk monitoring method, device, equipment and computer-readable storage medium | |
| CN112862593B (en) | Credit scoring card model training method, device and system and computer storage medium | |
| US11748452B2 (en) | Method for data processing by performing different non-linear combination processing | |
| CN111428032B (en) | Content quality evaluation method and device, electronic equipment and storage medium | |
| CN115082920A (en) | Deep learning model training method, image processing method and device | |
| CN110825611A (en) | Abnormal program analysis method and device and computer readable storage medium | |
| CN112766402A (en) | Algorithm selection method and device and electronic equipment | |
| CN111382064B (en) | Test method, test device, test medium and electronic equipment | |
| CN106557178B (en) | Method and device for updating entries of input method | |
| CN113779257A (en) | Method, device, equipment, medium and product for analyzing text classification model | |
| CN113673916B (en) | Risk data identification method, terminal device and computer-readable storage medium | |
| CN110392115B (en) | Block chain node management method, device and readable storage medium | |
| CN108416426B (en) | Data processing method, device and computer readable storage medium | |
| CN111476144A (en) | Pedestrian attribute identification model determination method and device and computer readable storage medium | |
| CN110019813B (en) | Life insurance case searching method, searching device, server and readable storage medium | |
| CN110674994A (en) | Data value evaluation method, terminal, device and readable storage medium | |
| CN113869964A (en) | Data processing method and related device | |
| CN108009393B (en) | Data processing method, device and computer readable storage medium | |
| CN109525548B (en) | White list updating method and device based on cost function and electronic equipment | |
| CN113420538B (en) | Numerical value format intelligent display method, equipment terminal and computer readable storage medium | |
| CN111339770A (en) | Method and apparatus for outputting information | |
| CN113391989B (en) | Program evaluation method, device, equipment, medium and program product | |
| CN113760834B (en) | File classification method, device, equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |