CN112541831A - Medical insurance risk identification method, device, medium and electronic equipment - Google Patents
Medical insurance risk identification method, device, medium and electronic equipment Download PDFInfo
- Publication number
- CN112541831A CN112541831A CN202011490453.9A CN202011490453A CN112541831A CN 112541831 A CN112541831 A CN 112541831A CN 202011490453 A CN202011490453 A CN 202011490453A CN 112541831 A CN112541831 A CN 112541831A
- Authority
- CN
- China
- Prior art keywords
- information
- risk
- wind control
- settlement
- control model
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 29
- 201000010099 disease Diseases 0.000 claims description 22
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 239000003814 drug Substances 0.000 claims description 15
- 229940079593 drug Drugs 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000036541 health Effects 0.000 abstract description 14
- 239000002609 medium Substances 0.000 description 13
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 4
- 238000012954 risk control Methods 0.000 description 4
- 206010010356 Congenital anomaly Diseases 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 206010010904 Convulsion Diseases 0.000 description 1
- 206010013654 Drug abuse Diseases 0.000 description 1
- 208000026350 Inborn Genetic disease Diseases 0.000 description 1
- 208000028017 Psychotic disease Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 201000001173 choledochal cyst Diseases 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 206010015037 epilepsy Diseases 0.000 description 1
- 208000028329 epileptic seizure Diseases 0.000 description 1
- 208000016361 genetic disease Diseases 0.000 description 1
- WIGIZIANZCJQQY-RUCARUNLSA-N glimepiride Chemical compound O=C1C(CC)=C(C)CN1C(=O)NCCC1=CC=C(S(=O)(=O)NC(=O)N[C@@H]2CC[C@@H](C)CC2)C=C1 WIGIZIANZCJQQY-RUCARUNLSA-N 0.000 description 1
- 229960004346 glimepiride Drugs 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000001872 metatarsal bone Anatomy 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 208000011117 substance-related disease Diseases 0.000 description 1
- 238000006467 substitution reaction 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a medical insurance risk identification method, a medical insurance risk identification device, a medical insurance risk identification medium and electronic equipment. The method comprises the following steps: if the medical insurance claim settlement event which accords with the application range of the pre-configured identification method is detected, acquiring claim information; the claim information comprises insurance information and claim settlement request information; inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model; if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue; and carrying out claim processing and subsequent processes according to the check result of the artificial risk check queue. According to the technical scheme, intelligent identification of high-risk cases can be achieved, the operation flow of workers can be simplified, and the processing efficiency of health insurance claims is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of big data analysis, in particular to a medical insurance risk identification method, device, medium and electronic equipment.
Background
With the rapid development of economic society, the variety of commercial or other medical insurance styles is increasing. At present, the risk identification of health insurance claims is mainly realized by a manual offline checking mode. When a claim is processed, a claimant needs to check the information collected by a plurality of links of a client in a plurality of links such as underwriting, claims settling, investigation and the like one by one, and the information specifically comprises a security layer (such as risk species, responsibility type and the like), a client layer (such as date of birth, sex and the like), a claim settlement event layer (hospital name, insurance passing, historical claim information and the like), a bill layer (disease diagnosis, approved fee amount and the like) and an institution layer (branch institution code and the like) with nearly hundred levels of data information, and image information such as medical record information, disease diagnosis, accident certification, physical examination reports and the like, and the problems of large manual workload, high cost and slow time efficiency exist.
In the process of making a health insurance claim decision, medical professionals judge the reasonability of medication and the reasonability of treatment tracks on line at first, claim settling personnel check client insurance acceptance information and insurance approval information on line, and finally, the insurance company carries out computer operation and finishes the rational cost calculation by recording the rational cost and the unreasonable cost in terms.
The technology is obviously lagged behind under the conditions that health insurance claims grow rapidly year by year, medical cheat and insurance cases frequently occur, and all-weather refinement of customer requirements is achieved, so that the claim settlement service experience is greatly reduced.
Disclosure of Invention
The embodiment of the invention provides a risk identification method, a risk identification device, a risk identification medium and electronic equipment for medical insurance, which can realize intelligent identification of high-risk cases, simplify the operation process of workers and improve the processing efficiency of health insurance claims.
In a first aspect, an embodiment of the present invention provides a risk identification method for medical insurance, where the method includes:
if the medical insurance claim settlement event is detected, acquiring claim information; the claim information comprises insurance information and claim settlement request information;
inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model;
if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue;
and carrying out claim processing and subsequent processes according to the check result of the artificial risk check queue.
Further, the training process of the claim settlement intelligent wind control model comprises:
acquiring a preset amount of historical claim data, and taking the historical claim data as training samples;
and inputting the training samples into an initial model, and training the initial model according to the output result of the initial model and the historical risk evaluation result of the training samples to obtain the claim settlement intelligent wind control model.
Further, the claim settlement intelligent wind control model comprises at least five classifiers for outputting responsibility exemption, whether the treatment subject is abnormal, whether the treatment track is abnormal, whether the medication of the disease is abnormal and whether the hospital is abnormal.
Further, after acquiring the claim information, the method further comprises:
carrying out intelligent data quality inspection on the claim information to determine whether the claim information has data quality problems;
if the data is found to exist, the prompt information of the data quality problem is returned so as to intelligently correct the data and timely find out potential claim settlement risks.
Further, after determining the risk level of the claim information according to the result output by the claim intelligent wind control model, the method further comprises:
and if the risk level of the claim information meets the preset condition, carrying out claim processing and subsequent processes.
Further, after sending the claim information to a manual risk check queue, the method further comprises:
judging whether the output result identification of the claim intelligent wind control model is accurate or not according to the check result of the artificial risk check queue;
and if the output result of the claim settlement intelligent wind control model is not accurately identified, updating the claim settlement intelligent wind control model according to the check result.
Further, the claim settlement intelligent wind control model is updated, and the updating comprises:
and if the error feedback times of the output result to the target rule corresponding to the output result of the check result reach a preset threshold value, removing and updating the target rule of the claim settlement intelligent wind control model.
In a second aspect, an embodiment of the present invention further provides an online medical insurance risk identification apparatus, including:
the system comprises a claim information acquisition module, a data processing module and a data processing module, wherein the claim information acquisition module is used for acquiring claim information if a medical insurance claim settlement event is detected; the claim information comprises insurance information and claim settlement request information;
the risk grade output module is used for inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk grade of the claim information according to the result output by the claim intelligent wind control model;
the check module is used for sending the claim information to an artificial risk check queue if the risk level of the claim information does not accord with a preset condition;
and the claim processing module is used for carrying out claim processing and subsequent processes according to the check result of the artificial risk check queue.
In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a risk identification method for medical insurance according to an embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable by the processor, where the processor executes the computer program to implement the method for identifying risk of medical insurance according to an embodiment of the present application.
According to the technical scheme provided by the embodiment of the application, if the medical insurance claim settlement event which accords with the application range of the pre-configured identification method is detected, claim information is obtained; the claim information comprises insurance information and claim settlement request information; inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model; if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue; and carrying out claims processing according to the checking result of the artificial risk checking queue. According to the technical scheme, intelligent identification of high-risk cases can be achieved, the operation process of workers can be simplified, and the processing efficiency of health insurance claims is improved.
Drawings
FIG. 1 is a flow chart of a risk identification method for medical insurance provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a risk identification system for medical insurance provided in accordance with an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a risk identification device for medical insurance provided by a second embodiment of the invention;
fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a method for identifying risk of medical insurance provided by an embodiment of the present invention, where the embodiment is applicable to the case of medical insurance claim settlement, and the method can be executed by a device for identifying risk of medical insurance provided by an embodiment of the present invention, and the device can be implemented by software and/or hardware, and can be integrated in an electronic device.
As shown in fig. 1, the risk identification method for medical insurance includes:
s110, if a medical insurance claim settlement event is detected, acquiring claim information; the claim information comprises insurance information and claim settlement request information.
The medical insurance claim settlement event may be an event that a corresponding medical accident occurs after the user applies insurance and medical claims are required to be settled by applying the applied insurance. The claim settlement request sent by the user or the telephone application event of the user is received on the platform, and the medical insurance claim settlement event is determined to be detected.
The claim information can be information input by the user according to the requirements of the platform, such as the accident event, place, reason, treatment mode, generated cost and payment voucher, and can also be related information input by the telephone operator according to the user's report telephone. Here, it is understood that the claim information may include the insurance information, i.e., the kind of insurance and time limit for the insurance bought by the user before the accident occurs, etc. The information may be retrieved from the database based on the user's telephone number, identification number, etc.
The claim information also comprises claim settlement request information, wherein the claim settlement request information can be information such as expenses generated in the accident treatment process, can be text information, can also be picture certificates uploaded by a user, or payment codes in payment records. The payment code can be used for the staff to obtain detailed payment information such as operation fees, medical fees, hospitalization fees and the like by calling data of the medical system.
In this technical solution, optionally, after obtaining the claim information, the method further includes:
carrying out intelligent data quality inspection on the claim information to determine whether the claim information has data quality problems;
if the data is found to exist, the prompt information of the data quality problem is returned so as to intelligently correct the data and timely find out potential claim settlement risks.
The data quality problem may be data missing, data incomplete, and data error. For example, in the disease type, the inputted disease type is not complete, or is inputted as a treatment of the disease, or the user does not input the disease type field. The setting avoids the limited field range of entering of present claim settlement operating system, and the intelligent quality inspection function of data lacks, through intelligent means, will realize intelligent quality inspection, the intelligent correction of data, in time discovers latent claim settlement risk.
S120, inputting the claim information into a pre-trained claim intelligent wind control model, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model.
The intelligent claims settlement wind control model can be obtained by training through historical claims information. The model can be used for determining the risk level of case information, such as the risk level of directly outputting the case information is high risk or low risk. Besides, the model can also identify information of several aspects, such as whether a condition of responsibility exemption exists or not, whether a condition of treatment subject abnormality exists or not, and the like, and finally determine the risk level of case information according to the identification result of each dimension.
In this scheme, specifically, the training process of claim settlement intelligent wind control model includes:
acquiring a preset amount of historical claim data, and taking the historical claim data as training samples;
and inputting the training samples into an initial model, and training the initial model according to the output result of the initial model and the historical risk evaluation result of the training samples to obtain the claim settlement intelligent wind control model.
The preset number may be 1000, or more, and the preset number may be divided for each risk. After the training sample is determined, whether to add a label to the training sample can be selected according to a final evaluation result so as to achieve the purpose of training in a supervised training mode. The initial model can be built or selected according to requirements, and whether the parameters of the initial model are trained completely can be determined according to the fact that the initial model is used as input data according to training samples and whether the output result and the historical risk assessment result are converged.
In this scheme, optionally, the claim settlement intelligent wind control model includes at least five classifiers, and the at least five classifiers are used for outputting responsibility exemption, whether the treatment subject is abnormal, whether the treatment track is abnormal, whether the medication for the disease is abnormal, and whether the hospital is abnormal.
The intelligent claims settlement wind control model comprises five categories of responsibility exemption, treatment subject abnormity, treatment track abnormity, disease medication abnormity and hospitalization abnormity, and the intelligent identification capability of 19 risk types is realized. The method is characterized in that the method comprises the following steps of firstly, the liability avoidance risk is large, and whether the insurance accident belongs to the scope of liability avoidance clauses or not is intelligently identified. Secondly, the main treatment body has large abnormal risks, and whether the disease diagnosis and treatment items conform to the ages and sexes of the persons at risk or not is intelligently identified. Thirdly, the treatment track is large in abnormal risk, and whether the treatment, the drug cost and the treatment frequency exceed the common level of the similar claims or not is intelligently identified. And fourthly, the abnormal risk of the disease medication is large, and whether the medication or the treatment mode conforms to the general rule or not is intelligently identified. Fifthly, the abnormal risks of hospitalization are large, and physical examination admission, low-standard admission and hanging-bed admission are intelligently identified.
And S130, if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue.
The preset condition may be a case in which the risk evaluation of the claim information is low risk, and if the preset condition is not met, it is indicated that the claim information may have high risk.
In the scheme, the manual risk checking queue can be a queue used for storing high-risk claim information and can be used for workers to manually check one by one.
And S140, carrying out claim processing according to the check result of the artificial risk check queue.
If the manual check shows that the claim risk behavior does exist, the claim information needs to be combed again and whether the claim standard is met is determined. If the claim risk behavior does not exist, the reasonable cost can be determined, the claim processing and the subsequent flow are carried out, and the relevant information is recorded.
In this technical solution, optionally, after determining the risk level of the claim information according to the result output by the claim intelligent wind control model, the method further includes:
and if the risk level of the claim information meets the preset condition, carrying out claim processing and subsequent processes.
It can be understood that if the risk level of the claim information is low risk, the claim processing and subsequent processes can be directly performed.
The subsequent process may be an operation process of recording the claim information and storing the claim information in the system.
Specifically, the claim processing comprises three steps of automatic insurance fund settlement, processing submission and approval of reasonable expenses after eliminating unreasonable expenses.
Through the arrangement, the workload of workers is greatly reduced, namely, only when the high risk condition exists, the workers need to check manually, the efficiency of medical insurance reimbursement is greatly improved, and the labor cost of the workers is reduced.
According to the technical scheme provided by the embodiment of the application, if the medical insurance claim settlement event which accords with the application range of the pre-configured identification method is detected, claim information is obtained; the claim information comprises insurance information and claim settlement request information; inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model; if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue; and carrying out claim processing and subsequent processes according to the check result of the artificial risk check queue. According to the technical scheme, intelligent identification of high-risk cases can be achieved, the operation process of workers can be simplified, and the processing efficiency of health insurance claims is improved.
On the basis of the above technical solutions, optionally, after the claim information is sent to the artificial risk checking queue, the method further includes:
judging whether the output result of the claim settlement intelligent wind control model is accurate or not according to the check result of the artificial risk check queue;
and if the output result of the claim settlement intelligent wind control model is not accurately identified, updating the claim settlement intelligent wind control model according to the check result.
On the basis of the above technical solutions, optionally, the updating of the claim settlement intelligent wind control model includes:
and if the error feedback times of the output result to the target rule corresponding to the output result of the check result reach a preset threshold value, removing and updating the target rule of the claim settlement intelligent wind control model.
Specifically, the model can perform a self-updating function according to manual feedback of claim settlement personnel, and the self-updating function comprises three modes. Firstly, reject and update, update according to the number of times of claims personnel error feedback, reach the error number standard, this rule no longer prompts. And secondly, statistics updating, namely automatically updating the model rules and parameter values by the model after newly adding 100 claims of the same type according to the statistics rules. And thirdly, updating the model, recalculating the model and the rule value every month according to the statistical rule, and intelligently updating the wind control model knowledge graph.
Meanwhile, managers can export and confirm rules for removing updates regularly, and timely repair rules for removing errors due to non-standardization feedback of claim settlement personnel.
The following is a specific embodiment provided in the examples of the present application:
in this scheme, optionally, the risk identification system for medical insurance may include a claim settlement operating system and a claim settlement intelligent wind control model.
Fig. 2 is a schematic diagram of a risk identification system for medical insurance provided in an embodiment of the present invention. As shown in fig. 2, the method includes five links of model configuration, claim risk identification, manual feedback, model self-update and claim case processing, and the five links are respectively deployed in a claim settlement operating system and a claim settlement intelligent wind control model. The model configuration is configured individually by each branch company according to service characteristics and risk identification control requirements, after risk identification is carried out on claims by claim settlement operators on the claims in the intelligent claim wind control model, manual feedback is carried out on the accuracy of the model identification, intelligent iteration can be carried out on the models according to the manual feedback, and the claim settlement experience knowledge base is continuously perfected. And an intelligent model is introduced, so that the pain point with high health insurance claim settlement risk checking cost can be effectively solved.
The model configuration comprises three dimensions, wherein one dimension is general risk, namely risk scenes and liability-exemption rules applicable to the risk configuration are configured according to the risk; and secondly, a group single special contract, namely, configuring the special contract on a single basis on the basis of dangerous seed configuration, and if the configured group single special contract rule is adopted, preferentially applying the group single configuration rule. And thirdly, product combination, namely, configuration is carried out according to product codes on the basis of dangerous type configuration, so that the product is suitable for learning the special stipulation of risk to the responsibility exemption range, and the product does not need to be configured according to the policy. The applicable priority of three dimensions is policy > product > risk. The configuration mode is divided into an input mode and an input mode, and the problems that a large group bill, a special wind control rule and a responsibility avoidance range of a learning level-risk service cannot be rapidly configured and the workload is large are solved.
Particularly, the risk general risk control model configuration can support full-scale query and accurate query, and the scenario supports switch configuration and disease liability avoidance scenario configuration.
Specifically, the clique special appointment wind control model configuration can support full-scale query and accurate query, and the risk scenario supports switch configuration.
Specifically, the single product is combined with the wind control model configuration, so that full-scale query and accurate query can be supported, and risk scene configuration is supported.
Aiming at the claim risk identification step, the current claim settlement intelligent wind control model comprises five categories of responsibility exemption, treatment subject abnormity, treatment track abnormity, disease medication abnormity and hospitalization abnormity, and the intelligent identification capability of 19 claim settlement risk types. The method is characterized in that the method comprises the following steps of firstly, the liability avoidance risk is large, and whether the insurance accident belongs to the scope of liability avoidance clauses or not is intelligently identified. Secondly, the main treatment body has large abnormal risks, and whether the disease diagnosis and treatment items conform to the ages and sexes of the persons at risk or not is intelligently identified. Thirdly, the treatment track is large in abnormal risk, and whether the treatment, the drug cost and the treatment frequency exceed the common level of the similar claims or not is intelligently identified. And fourthly, the abnormal risk of the disease medication is large, and whether the medication or the treatment mode conforms to the general rule or not is intelligently identified. Fifthly, the abnormal risks of hospitalization are large, and physical examination admission, low-standard admission and hanging-bed admission are intelligently identified.
And (3) a manual feedback step, wherein the feedback of the claim settlement intelligent wind control model is the most important link in the operation of the model, and the feedback quality directly influences the effect of the application of the model. And (4) checking the image data, the client identity information and the past claim settlement information by the claim settlement personnel according to the prompt of the intelligent wind control model, and feeding back the case risk processing result if the risk scene identification is accurate.
And in the model self-updating step, the model can perform a self-updating function according to manual feedback of claim settlement personnel, and the self-updating comprises three modes. Firstly, reject and update, update according to the number of times of claims personnel error feedback, reach the error number standard, this rule no longer prompts. And secondly, statistics updating, namely automatically updating the model rules and parameter values by the model after newly adding 100 claims of the same type according to the statistics rules. And thirdly, updating the model, recalculating the model and the rule value every month according to the statistical rule, and intelligently updating the wind control model knowledge graph.
Meanwhile, managers can export and confirm rules for removing updates regularly, and timely repair rules for removing errors due to non-standardization feedback of claim settlement personnel.
And aiming at the claim processing step, the claim settling personnel eliminates unreasonable claim payment expenses according to the prompt of the intelligent wind control model, such as processing of claim refusal, agreement payment, claim refusal bills, item elimination and the like. And if the wind control model prompts: epileptic seizure is a disease of the (psychosis) category and is exempted from responsibility. The claim settlement personnel find that the accident is a mental disease according to the prompt, and belongs to the scope of obligation exemption of terms agreement. In the investigation process, the insurance and disclaimer items are informed during the insurance sale process, and the client does not inform the insured person of the existing hospitalization record. The decision to disqualify the claim is made on the grounds of the exemption of the liability and the insurance contract is released.
Currently, a commercial medical insurance claim settlement risk intelligent system already comprises 5 major categories of 19 risk scenes, and more than 11 ten thousand rules are built in. The following is a description of a typical case of application:
claim one, wind control model prompt: the disease diagnosis [ common bile duct cyst ] is a (congenital heredity) disease, belonging to the exemption of responsibility.
The claim settling staff asks the investigator to check whether the past treatment record exists or not according to the prompt, and then the investigator can know whether the treatment is congenital or not and verify whether the sales are normal or not. The investigation conclusion is that firstly, a plurality of local large-scale hospitals have no past treatment record; secondly, the disease belongs to congenital genetic diseases; thirdly, the group insurance business, when underwriting, the business personnel do not inform the parents of the terms and contents, the sales defect exists, the investigation is qualified as a common positive piece, and the business personnel agree with the client to make the decision of agreement payment.
Claim two, wind control model prompt: the probability of use of [ glimepiride ] in [ metatarsal fractures ] was very low, please verify the rationality of the treatment.
According to the prompt, the claimant finds that the medicine for treating the chronic diabetes is used in the treatment of the fracture, and eliminates the medical expense for treating the diabetes due to the reason that the medicine for treating the disease is used by unexpected responsibility.
The invention aims to effectively solve the business problems in the background technology, adapt to the high-speed increase of the claim quantity and meet the requirements of quick and accurate risk identification of health insurance claims under the background of fine requirements of customers. After the application of the invention, the following technical effects can be achieved:
firstly, realize the intelligent recognition of high risk claim. The big data artificial intelligence technology is introduced, and based on the quick processing and strong learning ability, the medical records of general medical science and insurance rules are analyzed in the claim settlement process, the high-risk claim is accurately identified, and the quick processing of the low-risk claim is ensured.
And secondly, the claim settlement experience is inherited. The method has the advantages that claim settlement operators of insurance companies are distributed in various branches, the difference between medical experience and claim settlement processing experience is large, the requirements of complex health insurance claim processing cannot be met completely, and the processing experience base of high-level claim settlement operators can be subjected to structured processing through an intelligent means, so that effective inheritance is achieved.
Thirdly, the method adapts to the differentiated risk control requirements of various regions, and because the insurance products of various regions are different in form and different in medical environment, the health insurance claims cannot be subjected to risk control through national unified standards in the processing process, and the method needs to be realized by means of a new technical means.
Fourthly, the quality of the basic data is effectively improved. The short board of the current claim settlement operating system is limited in field entering range, the intelligent quality inspection function of data is lost, intelligent quality inspection and intelligent correction of the data are realized through an intelligent means, and potential claim settlement risks are found in time.
And fifthly, the hidden or false claims in company personnel are avoided. According to the analysis of the past data, partial claim settlement risk claims exist partnerships and work cases of personnel in insurance companies or medical personnel, and such cases can be screened to a certain extent by an intelligent risk screening means.
Sixthly, cost reduction and efficiency improvement of company operation are realized. The intelligent wind control model is introduced, so that the mode that the original claims are subjected to risk check one by one to consume manpower is thoroughly changed, the cost reduction and the efficiency improvement of claim settlement service are realized, the steady development of business is promoted, and the subversive change of client service and operation management of insurance enterprises is promoted.
Example two
Fig. 3 is a schematic structural diagram of a medical insurance risk identification apparatus according to a second embodiment of the present invention. As shown in fig. 3, the medical insurance risk identification device includes:
the claim information acquiring module 310 is configured to acquire claim information if a medical insurance claim settlement event is detected; the claim information comprises insurance information and claim settlement request information;
the risk grade output module 320 is used for inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk grade of the claim information according to the result output by the claim intelligent wind control model;
the checking module 330 is configured to send the claim information to an artificial risk checking queue if the risk level of the claim information does not meet a preset condition;
the claim processing module 340 is configured to perform claim processing and subsequent processes according to the check result of the artificial risk check queue.
The invention provides an intelligent claims settlement wind control model based on manual operation feedback, which is used for converting business experience into a unified wind control rule by applying a frontier technology and checking standardized data. The intelligent claims settlement wind control model thoroughly changes the manual mode that the risk check is carried out on the original claims one by one, realizes the cost reduction and efficiency improvement of the claims settlement service and promotes the steady development of the service.
The intelligent wind control model for claim settlement enables the health insurance claim settlement wind control to be more suitable for business characteristics and differentiated risk control requirements of various regions. At present, risk identification types of the health risk claim settlement intelligent wind control model are divided into 5 types and 19 types, and data types suitable for risk assessment comprise a security layer, a client layer, an insurance information layer, a medical data layer, a rule layer and a mechanism layer, and rules cover medical knowledge maps of a full-scale disease directory library, a social security medical standard directory library, a drug applicable condition rule library and a social security basic gold audit library. Identified scenarios include risk of medical violations, risk of improper hospitalization, risk of drug abuse, risk of non-insurance liability, and the like. Meanwhile, due to the introduction of the deep learning technology, incorrect interception rules can be automatically corrected according to the feedback of service personnel to the model identification effect, and the model identification accuracy is continuously improved. Since the short-term trial, the intelligent wind control model for health insurance claim settlement runs from the whole country, and two million yuan is paid for reducing unreasonable claims for companies.
The product can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for risk identification of medical insurance, the method comprising:
if the medical insurance claim settlement event is detected, acquiring claim information; the claim information comprises insurance information and claim settlement request information;
inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model;
if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue;
and carrying out claim processing and subsequent processes according to the check result of the artificial risk check queue.
Storage medium-any of various types of memory electronics or storage electronics. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network (such as the internet). The second computer system may provide the program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application contains computer-executable instructions, and the computer-executable instructions are not limited to the risk identification operation of the online medical insurance described above, and may also perform related operations in the risk identification method of the medical insurance provided in any embodiment of the present application.
Example four
The embodiment of the application provides electronic equipment, and the risk identification device for medical insurance provided by the embodiment of the application can be integrated in the electronic equipment. Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present application. As shown in fig. 4, the present embodiment provides an electronic device 400, which includes: one or more processors 420; the storage device 410 is used for storing one or more programs, and when the one or more programs are executed by the one or more processors 420, the one or more processors 420 implement the method for identifying risk of medical insurance provided by the embodiment of the application, the method includes:
if the medical insurance claim settlement event is detected, acquiring claim information; the claim information comprises insurance information and claim settlement request information;
inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model;
if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue;
and carrying out claim processing and subsequent processes according to the check result of the artificial risk check queue.
The electronic device 400 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 4, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of the processors 420 in the electronic device may be one or more, and one processor 420 is taken as an example in fig. 4; the processor 420, the storage device 410, the input device 430, and the output device 440 in the electronic apparatus may be connected by a bus or other means, and are exemplified by a bus 450 in fig. 4.
The storage device 410 is a computer readable storage medium, and can be used for storing software programs, computer executable programs, and module units, such as program instructions corresponding to the risk identification method for medical insurance in the embodiment of the present application.
The storage device 410 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the storage 410 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, storage 410 may further include memory located remotely from processor 420, which may be connected via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 430 may be used to receive input numbers, character information, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. The output device 440 may include a display screen, speakers, or other electronic equipment.
The electronic equipment provided by the embodiment of the application can realize quick response to users, fully utilizes the elasticity, the flexibility and the economy of public cloud resources, and aims to guarantee the safety and the continuity of services.
The risk identification device, the medium and the electronic device for medical insurance provided in the above embodiments can operate the risk identification method for medical insurance provided in any embodiment of the present application, and have corresponding functional modules and beneficial effects for operating the method. Technical details that are not described in detail in the above embodiments may be referred to a risk identification method for medical insurance provided in any of the embodiments of the present application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for risk identification of a medical insurance, comprising:
if the medical insurance claim settlement event is detected, acquiring claim information; the claim information comprises insurance information and claim settlement request information;
inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk level of the claim information according to the result output by the claim intelligent wind control model;
if the risk level of the claim information does not meet the preset condition, sending the claim information to a manual risk checking queue;
and carrying out claims processing according to the checking result of the artificial risk checking queue.
2. The method of claim 1, wherein the training process of the claim settlement intelligent wind control model comprises:
acquiring a preset amount of historical claim data, and taking the historical claim data as training samples;
and inputting the training samples into an initial model, and training the initial model according to the output result of the initial model and the historical risk evaluation result of the training samples to obtain the claim settlement intelligent wind control model.
3. The method of claim 2, wherein the claims intelligent wind control model comprises at least five classifiers for outputting liability avoidance, whether a subject is abnormal, whether a treatment trajectory is abnormal, whether a medication for a disease is abnormal, and whether a hospital stay is abnormal.
4. The method of claim 1, wherein after obtaining claim information, the method further comprises:
carrying out intelligent data quality inspection on the claim information to determine whether the claim information has data quality problems;
if the data quality problem exists, prompt information of the data quality problem is returned so as to intelligently correct the data and timely find out potential claim settlement risks.
5. The method of claim 1, wherein after determining a risk level for the claim information based on the results output by the claims intelligent wind control model, the method further comprises:
and if the risk level of the claim information meets the preset condition, carrying out claim processing and subsequent processes.
6. The method of claim 1, wherein after sending the claim information to a human risk check queue, the method further comprises:
judging whether the output result identification of the claim intelligent wind control model is accurate or not according to the check result of the artificial risk check queue;
and if the output result of the claim settlement intelligent wind control model is not accurately identified, updating the claim settlement intelligent wind control model according to the check result.
7. The method of claim 6, wherein updating the claim intelligent wind control model comprises:
and if the error feedback times of the output result to the target rule corresponding to the output result of the check result reach a preset threshold value, removing and updating the target rule of the claim settlement intelligent wind control model.
8. A medically-assured risk identification device, comprising:
the system comprises a claim information acquisition module, a data processing module and a data processing module, wherein the claim information acquisition module is used for acquiring claim information if a medical insurance claim settlement event is detected; the claim information comprises insurance information and claim settlement request information;
the risk grade output module is used for inputting the claim information into a claim intelligent wind control model obtained through pre-training, and determining the risk grade of the claim information according to the result output by the claim intelligent wind control model;
the check module is used for sending the claim information to an artificial risk check queue if the risk level of the claim information does not accord with a preset condition;
and the claim processing module is used for processing the claim according to the checking result of the artificial risk checking queue.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method for risk identification of a medical insurance according to any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for risk identification of medical insurance according to any one of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011490453.9A CN112541831B (en) | 2020-12-16 | 2020-12-16 | Medical insurance risk identification method, device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011490453.9A CN112541831B (en) | 2020-12-16 | 2020-12-16 | Medical insurance risk identification method, device, medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112541831A true CN112541831A (en) | 2021-03-23 |
| CN112541831B CN112541831B (en) | 2024-06-28 |
Family
ID=75018915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011490453.9A Active CN112541831B (en) | 2020-12-16 | 2020-12-16 | Medical insurance risk identification method, device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541831B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283995A (en) * | 2021-05-20 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Insurance public estimation remote access summary method, device and equipment |
| CN113469826A (en) * | 2021-07-22 | 2021-10-01 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
| CN113658009A (en) * | 2021-07-22 | 2021-11-16 | 北京健康之家科技有限公司 | Claim settlement information processing method and device |
| CN113724094A (en) * | 2021-08-31 | 2021-11-30 | 平安养老保险股份有限公司 | Risk information checking method, device, equipment and medium |
| CN113793226A (en) * | 2021-09-30 | 2021-12-14 | 上海健交科技服务有限责任公司 | Health insurance wind control rule compiling method based on big data |
| CN115374190A (en) * | 2022-10-25 | 2022-11-22 | 支付宝(杭州)信息技术有限公司 | Method and device for searching variety, storage medium and electronic equipment |
| CN115439033A (en) * | 2022-11-09 | 2022-12-06 | 浙江浙大网新软件产业集团有限公司 | Risk user screening method and device based on social security data and computing equipment |
| CN117934177A (en) * | 2024-03-22 | 2024-04-26 | 湖南多层次商保科技有限公司 | Method and system for constructing insurance intelligent responsibility determination model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN107798618A (en) * | 2017-04-11 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of intelligent Claims Resolution treating method and apparatus |
| CN107909299A (en) * | 2017-12-11 | 2018-04-13 | 凯泰铭科技（北京）有限公司 | People hinders Claims Resolution data risk checking method and system |
| CN108257029A (en) * | 2017-09-13 | 2018-07-06 | 平安科技（深圳）有限公司 | Insurance data checking method, device, computer equipment and readable storage medium storing program for executing |
| CN108492196A (en) * | 2018-03-08 | 2018-09-04 | 平安医疗健康管理股份有限公司 | The air control method of medical insurance unlawful practice is inferred by data analysis |
| CN110033382A (en) * | 2019-02-12 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of processing method of insurance business, device and equipment |
| WO2020119119A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Machine learning-based method for settling insurance claim, apparatus, device, and storage device |
| CN111986039A (en) * | 2020-09-02 | 2020-11-24 | 平安养老保险股份有限公司 | Claims wind control identification method and device, computer equipment and readable storage medium |
-
2020
- 2020-12-16 CN CN202011490453.9A patent/CN112541831B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN107798618A (en) * | 2017-04-11 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of intelligent Claims Resolution treating method and apparatus |
| CN108257029A (en) * | 2017-09-13 | 2018-07-06 | 平安科技（深圳）有限公司 | Insurance data checking method, device, computer equipment and readable storage medium storing program for executing |
| CN107909299A (en) * | 2017-12-11 | 2018-04-13 | 凯泰铭科技（北京）有限公司 | People hinders Claims Resolution data risk checking method and system |
| CN108492196A (en) * | 2018-03-08 | 2018-09-04 | 平安医疗健康管理股份有限公司 | The air control method of medical insurance unlawful practice is inferred by data analysis |
| WO2020119119A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Machine learning-based method for settling insurance claim, apparatus, device, and storage device |
| CN110033382A (en) * | 2019-02-12 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of processing method of insurance business, device and equipment |
| CN111986039A (en) * | 2020-09-02 | 2020-11-24 | 平安养老保险股份有限公司 | Claims wind control identification method and device, computer equipment and readable storage medium |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283995A (en) * | 2021-05-20 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Insurance public estimation remote access summary method, device and equipment |
| CN113283995B (en) * | 2021-05-20 | 2022-07-12 | 支付宝(杭州)信息技术有限公司 | Insurance public estimation remote access summary method, device and equipment |
| CN113469826A (en) * | 2021-07-22 | 2021-10-01 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
| CN113658009A (en) * | 2021-07-22 | 2021-11-16 | 北京健康之家科技有限公司 | Claim settlement information processing method and device |
| CN113469826B (en) * | 2021-07-22 | 2022-12-09 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
| CN113724094A (en) * | 2021-08-31 | 2021-11-30 | 平安养老保险股份有限公司 | Risk information checking method, device, equipment and medium |
| CN113793226A (en) * | 2021-09-30 | 2021-12-14 | 上海健交科技服务有限责任公司 | Health insurance wind control rule compiling method based on big data |
| CN115374190A (en) * | 2022-10-25 | 2022-11-22 | 支付宝(杭州)信息技术有限公司 | Method and device for searching variety, storage medium and electronic equipment |
| CN115439033A (en) * | 2022-11-09 | 2022-12-06 | 浙江浙大网新软件产业集团有限公司 | Risk user screening method and device based on social security data and computing equipment |
| CN117934177A (en) * | 2024-03-22 | 2024-04-26 | 湖南多层次商保科技有限公司 | Method and system for constructing insurance intelligent responsibility determination model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112541831B (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112541831A (en) | Medical insurance risk identification method, device, medium and electronic equipment | |
| JP5586373B2 (en) | Computer-readable storage medium storing a program for causing a computer system to realize the function of a component that processes a payment request, and a method of operating a computer system that causes a computer system to process a payment request | |
| US20160267396A1 (en) | System and Method for Using Machine Learning to Generate a Model from Audited Data | |
| US20200320638A1 (en) | Subrogation case management | |
| CN111192131A (en) | Financial risk prediction method and device and electronic equipment | |
| CN109784707A (en) | Rating business credit method, apparatus, computer equipment and storage medium | |
| CN112016788A (en) | Risk control strategy generation and risk control method and device and electronic equipment | |
| CN113343058B (en) | Voice session supervision method, device, computer equipment and storage medium | |
| CN113505936A (en) | Project approval result prediction method, device, equipment and storage medium | |
| US20210174453A1 (en) | Managing risk assessment and services through modeling | |
| CN116843481A (en) | Knowledge graph analysis method, device, equipment and storage medium | |
| CN111242779A (en) | Financial data characteristic selection and prediction method, device, equipment and storage medium | |
| US20230306279A1 (en) | Guided feedback loop for automated information categorization | |
| CN117010892A (en) | Payment risk detection method, device, electronic equipment and readable medium | |
| CN114529402A (en) | Credit management method, device and medium based on big data wind control | |
| CN113487440A (en) | Model generation method, health insurance claim settlement determination method, device, equipment and medium | |
| CN114757786A (en) | Data prediction method and device, electronic equipment and computer readable medium | |
| CN113723685A (en) | Method, device, equipment and storage medium for determining hazardous waste generation amount | |
| CN112417329A (en) | Method and device for monitoring illegal internet foreign exchange deposit transaction platform | |
| CN114723570B (en) | Agricultural risk monitoring method and device, storage medium and computer equipment | |
| CN116974858A (en) | Information generation method, system, device, equipment and storage medium | |
| CN117422479A (en) | Anti-medical institution medical insurance fraud supervision method based on ensemble learning and deep learning | |
| Rao et al. | Data Validation for Eligibility Criteria and Death Benefit Claims for Insurance Policies | |
| CN118211832A (en) | Financial tax data risk monitoring method, system, electronic equipment and storage medium | |
| CN117934183A (en) | System and method for tax declaration and risk early warning |
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 |