CN117114706A - Fraud risk prediction method, device and equipment for claim case - Google Patents
Fraud risk prediction method, device and equipment for claim case Download PDFInfo
- Publication number
- CN117114706A CN117114706A CN202310988048.7A CN202310988048A CN117114706A CN 117114706 A CN117114706 A CN 117114706A CN 202310988048 A CN202310988048 A CN 202310988048A CN 117114706 A CN117114706 A CN 117114706A
- Authority
- CN
- China
- Prior art keywords
- risk
- information
- historical
- medical
- fraud 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000000463 material Substances 0.000 claims abstract description 371
- 238000013058 risk prediction model Methods 0.000 claims abstract description 37
- 238000012986 modification Methods 0.000 claims description 26
- 230000004048 modification Effects 0.000 claims description 26
- 238000012795 verification Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000012550 audit Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 9
- 208000017667 Chronic Disease Diseases 0.000 description 8
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 208000030090 Acute Disease Diseases 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000004321 preservation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 208000012260 Accidental injury Diseases 0.000 description 2
- 238000013475 authorization Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 239000012567 medical material Substances 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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
Abstract
The invention discloses a fraud risk prediction method, a fraud risk prediction device and fraud risk prediction equipment for claim cases, relates to the technical field of artificial intelligence, and can solve the technical problems of long period, high cost, low efficiency and low accuracy caused by manual auditing. The method comprises the following steps: acquiring claim declaration materials of medical cases to be claiming, wherein the claim declaration materials comprise claim user information and claim proving materials; acquiring auxiliary proof materials of the claim settlement users based on the claim settlement user information; generating the claim risk feature of the medical case to be claim-resolved according to the claim user information, the claim proving material and the auxiliary proving material; and carrying out fraud risk prediction on the claims risk feature through a fraud risk prediction model to obtain fraud risk information of the medical case to be subjected to claims.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a fraud risk prediction method, a fraud risk prediction device and fraud risk prediction equipment for claim settlement cases.
Background
With the increasing emphasis on medical insurance, medical case claims are increased, and fraud risk prevention of insurance enterprises is more and more important, so that in order to prevent phenomena of multiple claims and false claims, the fraud risk of medical case claims needs to be predicted.
At present, auditing personnel need to conduct fraud risk auditing on a large number of case materials for claim settlement, the auditing period is long, the manpower cost is high, the efficiency is low, and the accuracy rate cannot be ensured by long-term manual auditing.
Disclosure of Invention
In view of the above, the invention provides a fraud risk prediction method, a fraud risk prediction device and fraud risk prediction equipment for claim settlement cases, which can solve the technical problems of long period, high cost, low efficiency and low accuracy caused by manual auditing.
According to a first aspect of the present invention, there is provided a fraud risk prediction method of a claim case, the method comprising:
acquiring claim declaration materials of medical cases to be claiming, wherein the claim declaration materials comprise claim user information and claim proving materials;
acquiring auxiliary proof materials of the claim settling user based on the claim settling user information;
generating the claim risk feature of the medical case to be subjected to claim settlement according to the claim settlement user information, the claim settlement proving material and the auxiliary proving material;
and carrying out fraud risk prediction on the claims risk feature through a fraud risk prediction model to obtain fraud risk information of the medical case to be subjected to the claims.
Preferably, the fraud risk information includes a fraud risk probability; after obtaining the fraud risk information for the medical case to be claiming, the method further includes:
If the fraud risk probability is greater than a preset rechecking probability, generating a manual auditing material of the case to be claiming based on the claiming material, the auxiliary proof material and the fraud risk probability, and sending the manual auditing material to a preset manual auditing terminal;
and if the fraud risk probability is smaller than or equal to the preset rechecking probability, determining that the medical case to be claiming passes the fraud risk auditing.
Preferably, the generating the claim risk feature of the medical case to be claimed according to the claim user information, the claim proof material and the auxiliary proof material includes:
inquiring auxiliary proving materials with the same type of the medical cases to be claiming as materials to be checked;
comparing the claim verification material with the material to be verified, and acquiring a part, which is not matched with the material to be verified, of the claim verification material as the material to be confirmed;
generating proving material inquiry information based on the proving material to be confirmed and the material to be verified, and sending the proving material inquiry information to a claim settlement user terminal;
receiving material modification information fed back from the claim user terminal;
And generating the claim risk feature of the medical case to be claimed based on the claim user information, the material modification information, the claim proving material and the auxiliary proving material.
Preferably, after the sending the certification material inquiry information to the claim settlement user terminal, the method further includes:
receiving objection evidence-providing materials fed back by the claim user terminal;
the material to be confirmed, the material to be verified and the objection evidence obtaining material are sent to a preset evidence obtaining and checking terminal;
receiving evidence passing information fed back from the preset evidence checking terminal, and generating the claim risk feature based on the claim user information, the claim evidence material, the auxiliary evidence material and the objection evidence material; or alternatively, the first and second heat exchangers may be,
and receiving the proof failing information fed back by the preset proof auditing terminal, modifying the to-be-confirmed proof material by utilizing the to-be-verified material to obtain updated claim proof material, and generating the claim risk feature based on the claim user information, the updated claim proof material and the auxiliary proof material.
Preferably, the generating the claim risk feature of the medical case to be claimed based on the claim user information, the material modification information, the claim proof material, and the auxiliary proof material includes:
According to the type, acquiring risk characteristic contribution value ranking of the medical cases to be claiming, and determining risk prediction information of a preset quantity before the risk characteristic contribution value ranking based on the claiming user information, the material modification information, the claiming evidence material and the auxiliary evidence material;
and extracting features of the risk prediction information to obtain the risk feature of the claim to be subjected to claim settlement of the medical case.
Preferably, before the acquiring the ranking of the risk feature contribution values of the medical cases to be claiming, the method further includes:
acquiring the same type of historical medical cases, wherein the historical medical cases comprise non-risk historical medical cases passing fraud risk auditing and risk historical medical cases not passing fraud risk auditing;
acquiring initial characteristics based on historical claim proof materials of the historical medical cases, historical claim user information and historical auxiliary proof materials of the historical claim users, wherein the historical claim proof materials comprise hospital names, medical history and operation history, the historical claim user information comprises names, applicant ages, insured ages, first claim amount and social insurance years, and the historical auxiliary proof materials comprise whether insured persons apply for funding or not;
Calculating the proportion of any one initial feature in the non-risk historical medical case and the risk historical medical case respectively, and calculating the contribution value of the initial feature to risk prediction according to the proportion to obtain the ranking of the contribution values of the risk features.
Preferably, the acquiring the initial feature based on the historical claims evidencing material, the historical claims evidencing user information and the historical auxiliary evidencing material of the historical claims evidencing user of the historical medical case includes:
extracting non-computing initial characteristics from historical claim proof materials and historical claim user information of the historical medical case;
generating computing type initial characteristics according to the non-computing type initial characteristics and the computing rules;
and determining the non-computing class initial feature and the computing class initial feature as initial features.
According to a second aspect of the present invention, there is provided a fraud risk prediction apparatus for a claim case, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring claim declaration materials of medical cases to be claiming, and the claim declaration materials comprise claim user information and claim proof materials;
the second acquisition module is used for acquiring auxiliary proof materials of the claim settlement users based on the claim settlement user information;
The generation module is used for generating the claim risk characteristics of the medical case to be subjected to claim settlement according to the claim settlement user information, the claim settlement proving material and the auxiliary proving material;
and the prediction module is used for predicting the fraud risk of the claims to be clashed according to the fraud risk prediction model to obtain the fraud risk information of the medical case to be clashed.
According to a third aspect of the present application there is provided a storage medium having stored thereon a computer program which when executed by a processor implements the fraud risk prediction method of claim case described above.
According to a fourth aspect of the present application, there is provided a computer device comprising a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, the processor implementing the fraud risk prediction method of claim cases described above when executing the program.
By means of the technical scheme, the fraud risk prediction method, the fraud risk prediction device and the fraud risk prediction equipment for the claim case can firstly obtain claim declaration materials of the medical case to be subjected to claim settlement, wherein the claim declaration materials comprise claim settlement user information and claim settlement evidence materials; further, based on the information of the claim user, acquiring auxiliary proving materials of the claim user; then, according to the information of the claim user, the claim proving material and the auxiliary proving material, generating claim risk characteristics of the medical case to be claimed; and finally, carrying out fraud risk prediction on the risk features of the claims to be resolved through a fraud risk prediction model to obtain fraud risk information of the medical cases to be resolved. According to the technical scheme, the method and the device for predicting the fraud risk by using the medical case to be claiming and the medical case to be claiming generate the risk feature of the medical case to be claiming by using multidimensional information (comprising the information of the claiming user, the claiming proving material and the auxiliary proving material), so that the comprehensiveness and the accuracy of the risk feature of the claiming are improved, the accuracy of the fraud risk prediction by using the fraud risk prediction model is further improved, manual checking is not needed, the efficiency of the fraud risk prediction is improved, the cost is reduced, and the accuracy is improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute an undue limitation to the present application. In the drawings:
FIG. 1 shows a schematic flow chart of a fraud risk prediction method for claim settlement cases according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for predicting risk of fraud for claim settlement cases according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a fraud risk prediction device for claim settlement cases according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of another fraud risk prediction apparatus for claim settlement according to the embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the drawings in conjunction with embodiments. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
It should be noted that in the prior art, the claim settlement user submits claim settlement reporting materials, and auditors judge whether the claim settlement reporting materials are fraudulent cases or not according to the claim settlement reporting materials, but the medical cases to be claiming are large in quantity, slow in manual audit and low in audit accuracy. In order to solve the technical problems of long period, high cost, low efficiency and low accuracy caused by manual auditing in the prior art, the embodiment provides a fraud risk prediction method for a claim case, as shown in fig. 1, the method includes:
101. and acquiring the claim declaration material of the medical case to be claiming, wherein the claim declaration material comprises claim user information and claim proving material.
The claim reporting material is uploaded by a claim user, and specifically comprises claim user information and claim proof material, wherein the claim user information can comprise information related to a user and a claim, such as name information, applicant age information, insured age information, first claim amount information, whether to keep information, whether to pay for 3 years continuously for social insurance, etc., and the claim proof material can comprise admission records, discharge records, case reports, etc.
102. Based on the claim user information, auxiliary proving materials of the claim user are obtained.
For this embodiment, in order to improve the accuracy of fraud risk prediction, it is necessary to obtain multidimensional information that includes auxiliary proof material in addition to the claim user information and the claim proof material.
It should be noted that the auxiliary proof material is obtained after the authorization of the claim user, where the auxiliary proof material may include proof information from the current platform or other platforms, for example, the claim user information includes information about whether the social security is continuously paid for 3 years, for example, whether the social security of the medical case to be claim is continuously paid for 3 years, specifically, whether the social security is continuously paid for 3 years, and the auxiliary proof material may be a payment condition of the social security platform. For example, the claim user information includes information about whether the main illness is chronic disease, whether the main illness of the medical case to be claim is chronic disease, specifically, whether disease a is chronic disease, and disease B is acute disease, and the auxiliary proof material may be disease library information, in which whether disease a is chronic disease, and whether disease B is acute disease may be queried.
It should be noted that, if the claim declaration material and the auxiliary proof material exist in a picture form, in order to facilitate information acquisition from the claim declaration material and the auxiliary proof material, the picture form needs to be converted into a text form, and the conversion manner may include using OCR (Optical Character Recognition ) or the like, which is not limited herein.
103. And generating the claim risk feature of the medical case to be claim-resolved according to the claim user information, the claim proving material and the auxiliary proving material.
For this embodiment, in order to ensure the accuracy of the claims proof material, the claims proof material uploaded by the claims user needs to be accurately verified to ensure the accuracy of fraud risk prediction.
And (3) verifying that the auxiliary proof material is not contradictory, and generating the claim risk characteristics of the medical case to be subjected to claim settlement according to the claim settlement user information and the claim settlement proof material. Specifically, feature information is extracted from the claim user information and the claim proof material as claim risk features.
There is a contradiction to the fear of verifying with the auxiliary proof material: for example, the contradiction between the claim user information and the claim proof material and the auxiliary proof material is that: the method comprises the steps of judging whether a main illness in a claim proof material is chronic disease information or not, specifically, judging whether the illness A in the claim proof material is chronic disease and the illness B in the claim proof material is acute disease, and displaying that the illness A is acute disease and the illness B is chronic disease by an auxiliary proof material, at the moment, modifying the illness A by the auxiliary proof material to obtain updated claim proof material, and generating claim risk characteristics of a medical case to be subjected to claim according to claim user information and updated claim proof material. Specifically, feature information is extracted from the claim user information and the updated claim proof material as claim risk features.
104. And carrying out fraud risk prediction on the claims risk feature through a fraud risk prediction model to obtain fraud risk information of the medical case to be subjected to claims.
It should be noted that, on the one hand, since the claim risk feature has characteristics of time and space (for example, time of visit, city of visit hospital, etc.), the fraud risk prediction model needs to model the spatiotemporal information and can capture high-dimensional data of these spatiotemporal information, and on the other hand, medical materials submitted by patients (admission records, discharge records, case reports, etc.) are one main criterion for predicting fraud risk, so the fraud risk prediction model needs to process text information, and finally, as the data volume increases, the accuracy of the fraud risk prediction model needs to be higher and a large number of data processing speeds need to be faster.
In summary, as an implementation manner, the fraud risk prediction model may be constructed by using a bert+full connection layer, which may model time information, may process text information, has higher precision and faster data processing speed, and trains an initial fraud risk prediction model by using a training set, and adjusts parameters of the initial fraud risk prediction model until a loss function converges, so as to obtain a trained fraud risk prediction model. The data acquisition mode in the training set comprises the following steps: acquiring data in a non-risk historical medical case, marking the data with a non-risk tag, acquiring the data in the risk historical medical case, marking the data with a risk tag, preprocessing the two data (for example, converting non-text data into text data, deleting repeated data and the like), and putting the data into a training set.
And inputting the claim risk characteristics into a fraud risk prediction model, performing fraud risk prediction on the claim risk characteristics by the fraud risk prediction model, accumulating precipitated expert wind control rules by an auditing expert after obtaining fraud risk information of the medical case to be claiming, presetting a plurality of fraud risk probability ranges including wind control rules pointed by refused claim resolution and wind control rules pointed by investigation, and performing risk classification, namely, each fraud risk probability range corresponds to one fraud risk grade, obtaining the probability that the medical case to be claiming has fraud risk after performing fraud risk prediction, and directly corresponding to the fraud risk probability range to obtain the risk grade of the medical case to be claiming.
The invention provides a fraud risk prediction method, a fraud risk prediction device and fraud risk prediction equipment for a claim case, which can firstly acquire claim declaration materials of a medical case to be subjected to claim settlement, wherein the claim declaration materials comprise claim settlement user information and claim settlement evidence materials; further, based on the information of the claim user, acquiring auxiliary proving materials of the claim user; then, according to the information of the claim user, the claim proving material and the auxiliary proving material, generating claim risk characteristics of the medical case to be claimed; and finally, carrying out fraud risk prediction on the risk features of the claims to be resolved through a fraud risk prediction model to obtain fraud risk information of the medical cases to be resolved. According to the technical scheme, the method and the device for predicting the fraud risk by using the medical case to be claiming and the medical case to be claiming generate the risk feature of the medical case to be claiming by using multidimensional information (comprising the information of the claiming user, the claiming proving material and the auxiliary proving material), so that the comprehensiveness and the accuracy of the risk feature of the claiming are improved, the accuracy of the fraud risk prediction by using the fraud risk prediction model is further improved, manual checking is not needed, the efficiency of the fraud risk prediction is improved, the cost is reduced, and the accuracy is improved.
Further, as a refinement and extension of the foregoing embodiment, in order to fully describe the implementation procedure in this embodiment, another fraud risk prediction method for a claim case is provided, as shown in fig. 2, where the method includes:
201. and acquiring the claim declaration material of the medical case to be claiming, wherein the claim declaration material comprises claim user information and claim proving material.
The specific implementation is the same as that of the embodiment step 101, and will not be described here again.
202. Based on the claim user information, auxiliary proving materials of the claim user are obtained.
The specific implementation is the same as the embodiment step 102, and will not be described here again.
203. Inquiring auxiliary proving materials with the same type as the medical case to be claiming as materials to be checked, comparing the proving materials to be claiming with the materials to be checked, acquiring the unmatched parts of the proving materials to be claiming as the proving materials to be checked, generating proving material inquiry information based on the proving materials to be checked and the materials to be checked, and sending the proving material inquiry information to the claim user terminal.
For this embodiment, in order to ensure the accuracy of the claims proof material, the claims proof material uploaded by the claims user needs to be accurately verified to ensure the accuracy of fraud risk prediction. In particular, the method comprises the steps of,
Firstly, since the claim settlement user may purchase other insurance different from the type of the claim settlement medical case in addition to the claim settlement medical case, for predicting the fraud risk of the claim settlement medical case, the auxiliary proof material of the same type as the claim settlement medical case should be queried as the material to be verified, and it should be noted that the query of the material to be verified is performed after the authorization of the claim settlement user, wherein the auxiliary proof material may include proof information from the current platform or other platforms, the type of the claim settlement medical case is common medical insurance or accidental injury medical insurance or hospitalization medical insurance, and the type of the claim settlement medical case is hospitalization medical insurance, and the material to be verified includes actual admission record, actual discharge record, actual case report and the like from the hospital to be diagnosed, and correspondingly, the claim settlement material includes the claim admission record, claim discharge record, claim report and the like uploaded by the claim settlement user.
Then, comparing the material to be verified with the material to be verified, obtaining a portion of the material to be verified, which does not match the material to be verified, as the material to be verified, for example, the admission record of the material to be verified is the same as the actual admission record, the discharge record is the same as the actual discharge record, but the report case report is different from the actual case report, at this time, the report case report in the material to be verified is taken as the material to be verified, based on the material to be verified and the material to be verified, generating inquiry information of the material to be verified, and sending inquiry information of the material to the user terminal to be verified, for example, the inquiry information of the material may be "report case report (material to be verified) is different from the actual case report (material to be verified), please confirm.
It should be noted that, after sending the certification material query information to the claim user terminal, the feedback of the claim user terminal includes two types, i.e., the embodiment step 204a and the embodiment step 204b.
204a, receiving material modification information fed back from the claim settlement user terminal, and generating claim settlement risk characteristics of the medical case to be settled based on the claim settlement user information, the material modification information, the claim settlement proving material and the auxiliary proving material.
It should be noted that, the claim settlement user terminal modifies the proof material to be confirmed to obtain material modification information, after receiving the material modification information fed back from the claim settlement user terminal, it needs to check whether the material modification information is based on the material to be checked, if so, the claim settlement risk feature of the medical case to be claiming is generated based on the claim settlement user information, the material modification information, the claim settlement proof material and the auxiliary proof material.
For the present embodiment, as an implementation manner, the generating the claim risk feature of the medical case to be claim-resolved based on the claim-resolved user information, the material modification information, the claim-resolved proof material, and the auxiliary proof material includes: according to the types of the medical cases to be claiming, acquiring the risk characteristic contribution value ranking of the medical cases to be claiming, determining the risk prediction information with the risk characteristic contribution value ranking of the preset quantity before based on the claiming user information, the material modification information, the claiming evidence material and the auxiliary evidence material, and carrying out characteristic extraction on the risk prediction information to obtain the claiming risk characteristics of the medical cases to be claiming.
Specifically, first, for obtaining a rank of risk feature contribution values of medical cases to be claiming according to types of the medical cases to be claiming, before obtaining the rank of risk feature contribution values of the medical cases to be claiming, a rank of risk feature contribution values corresponding to each type needs to be obtained, including: acquiring the same type of historical medical cases, wherein the historical medical cases comprise non-risk historical medical cases which pass fraud risk audits and risk historical medical cases which do not pass fraud risk audits, and acquiring initial characteristics based on historical claims evidence materials, historical claims user information and historical auxiliary evidence materials of historical claims users of the historical medical cases, wherein the historical claims evidence materials comprise hospital names, medical history and operation history, the historical claims user information comprises names, applicant ages, insured ages, first claims amount and social insurance years, and the historical auxiliary evidence materials comprise whether insurers apply for funding; calculating the proportion of any initial feature in the non-risk historical medical case and the risk historical medical case respectively, and calculating the contribution value of the initial feature to the risk prediction according to the proportion to obtain the ranking of the contribution values of the risk features.
The types of medical cases to be claiming include general medical insurance, accidental injury medical insurance, hospitalized medical insurance, and the like, and two types of historical medical cases of the same type, such as: a non-risk historical medical case of a general medical insurance and a risk historical medical case of a general medical insurance; also for example: non-risk historical medical cases of hospitalization medical insurance and risk historical medical cases of hospitalization medical insurance.
Wherein, for the historical claims proof material based on the historical medical case, the historical claims user information and the historical auxiliary proof material of the historical claims user, obtaining the initial characteristics comprises: extracting non-computing initial characteristics from historical claim proof materials of historical medical cases and historical claim user information; generating computing type initial characteristics according to the non-computing type initial characteristics and the computing rules; the non-computational class initial features and the computational class initial features are determined as initial features. It should be noted that, the initial features include a non-computing type initial feature and a computing type initial feature, where the non-computing type initial feature is directly extracted from existing information, and the computing type initial feature is obtained after computing according to existing information and computing rules, for example, the non-computing type initial feature is obtained from historical claims proof material and historical claims user information, including: the applicant identity card home market, the insured identity card home market, the applicant phone home market, the insured phone home market, the applicant age, the insured age, the earliest visit hospital city, the latest visit hospital city, the earliest visit time, the latest visit time, the insured occupation, the payment mode, the main diagnosis name, the earliest visit hospital type and grade (public or not), whether accidents, whether renewal, the invoice quantity, whether the insured person applies for funding, whether the insured person is consistent, whether the cross-province visit is performed, whether the visit hospital is the identity card position, the chronic disease diagnosis quantity and the like. For example, the calculation-like initial characteristics include the maximum outpatient invoice amount of the case (the calculation rule is the maximum value of all outpatient invoice amounts), the accumulated reimbursement amount of the insured (the calculation rule is the sum of all reimbursement amounts of the insured), the longest residence time (the calculation rule is the maximum value of all hospitalization time periods), and the like.
For calculating the proportion of any one initial feature in the non-risk historical medical cases and the risk historical medical cases, calculating the contribution value of the initial feature to the risk prediction according to the proportion, and obtaining the ranking of the contribution values of the risk features, for example, calculating the proportion of continuous preservation in all the risk historical medical cases, for example, 10%, and the proportion of continuous preservation in the non-risk historical medical cases, for example, 80%, and calculating the proportion of the earliest visit hospital type in all the risk historical medical cases, for example, 40%, and the proportion of the earliest visit hospital type in the non-risk historical medical cases, for example, 50%, so that whether the continuous preservation has a great influence on whether the historical medical cases are at risk or not, whether the earliest visit hospital type is public has a small influence on the historical medical cases or not, namely, whether the continuous preservation of the contribution value is ranked before the earliest visit hospital type is public. Thus, all initial features under each type are ranked according to the contribution value, and ranking of the contribution values of the risk features is achieved.
Specifically, second, risk prediction information of the number of the risk feature contribution values before the ranking is determined based on the information of the claim settlement user, the material modification information, the claim settlement proving material and the auxiliary proving material, and feature extraction is carried out on the risk prediction information to obtain claim settlement risk features of the medical case to be claiming. The preset number may be set by itself, for example, the preset number is 20, and only the first 20 initial features are obtained from the ranking of the contribution values of the risk features of the medical cases to be claiming, and these 20 initial features do not have the information of the medical cases to be claiming, so that the risk prediction information corresponding to these 20 initial features is determined from the claiming user information, the material modification information, the claiming evidence material and the auxiliary evidence material, and then the claiming risk feature is extracted from the risk prediction information, for example, the first position of the initial feature: the applicant identity card belongs to the city, and the second position is: the identity card of the insured life belongs to the city, and the third place: whether to renew, fourth bit: whether the earliest hospital visit type is public, determining risk prediction information from the claim user information, the material modification information, the claim proof material and the auxiliary proof material, and extracting claim risk characteristics from the risk prediction information, wherein the method comprises the following steps of: the applicant identity card belongs to the city: beijing city, the insured life card is in the city: beijing city, whether to renew: if the earliest hospital visit type is public: is.
204b, receiving the objection proof material fed back by the claim settlement user terminal, and sending the material to be confirmed, the material to be checked and the objection proof material to a preset evidence checking terminal.
It should be noted that, after the to-be-confirmed proof material, the to-be-verified material and the objection proof material are sent to the preset proof checking terminal, the feedback of the preset proof checking terminal includes two types, namely, the embodiment step 204b1 and the embodiment step 204b2.
204b1, receiving the proof passing information fed back by the preset proof auditing terminal, and generating the claim risk characteristics based on the claim settlement user information, the claim settlement evidence material, the auxiliary evidence material and the objection proof material.
204b2, receiving the proof failing information fed back from the preset proof auditing terminal, modifying the proof material to be confirmed by using the material to be verified to obtain updated claim proof material, and generating claim risk characteristics based on the claim user information, the updated claim proof material and the auxiliary proof material.
For the embodiment steps 204b1 and 204b2, the manner of generating the claim risk feature is the same as that of the embodiment step 204a, except that the material is different, so that the actual situation is more consistent, and in particular, since the embodiment step 204a is that the material modification information is fed back by the claim user terminal, the material is that the material is the claim user information, the material modification information, the claim proof material and the auxiliary proof material; since the embodiment step 204b1 is that the claim user terminal feeds back the proof passing information, the materials based on are the claim user information, the claim proof material, the auxiliary proof material and the objection proof material; since the embodiment step 204b2 is that the claims user terminal feeds back the proof failed information, the materials based on are claims user information, updated claims proof material, and auxiliary proof material.
Wherein the material to be verified is an auxiliary proof material corresponding to the material to be verified, and the material to be verified is a portion of the material to be verified, which is not matched with the material to be verified, in the material to be verified, and since the verification is failed, that is, the material to be verified is correct, and the material to be verified uploaded by the user to be verified is incorrect, for the embodiment step 204b2, modifying the material to be verified with the material to be verified to obtain an updated material to be verified means modifying the incorrect material to be verified with the correct material to be verified, so that the obtained updated material to be verified is matched with the material to be verified.
205. And carrying out fraud risk prediction on the claims risk feature through a fraud risk prediction model to obtain fraud risk information of the medical case to be subjected to claims.
206. The fraud risk information comprises fraud risk probability, if the fraud risk probability is larger than preset rechecking probability, based on the claim reporting material, the auxiliary proof material and the fraud risk probability, manual auditing material of the case to be subjected to claim settlement is generated, the manual auditing material is sent to a preset manual auditing terminal, and if the fraud risk probability is smaller than or equal to the preset rechecking probability, the medical case to be subjected to claim settlement is determined to pass through fraud risk auditing.
It should be noted that, on the one hand, since the claim risk feature has characteristics of time and space (for example, time of visit, city of visit hospital, etc.), the fraud risk prediction model needs to model the spatiotemporal information and can capture high-dimensional data of these spatiotemporal information, and on the other hand, medical materials submitted by the patient (admission record, discharge record, case report, etc.) are one main criterion for predicting fraud risk, so that the fraud risk prediction model needs to process text information, and finally, as the data amount increases, the accuracy of the fraud risk prediction model needs to be higher.
To sum up, as an implementation manner, the fraud risk prediction model may be constructed by adopting a bert+ full connection layer, training the initial fraud risk prediction model by using a training set, adjusting parameters of the initial fraud risk prediction model until a loss function converges, and then verifying whether the initial fraud risk prediction model reaches a preset accuracy by using a verification set, if not, continuing training, and if yes, finishing training to obtain the fraud risk prediction model. The data acquisition modes in the training set and the verification set comprise: acquiring data in a non-risk historical medical case, marking the data with a non-risk tag, acquiring the data in the risk historical medical case, marking the data with a risk tag, preprocessing the two data (for example, converting non-text data into text data, deleting repeated data and the like), putting the data into a training set, preprocessing the two data (for example, converting non-text data into text data, deleting repeated data and the like), and putting the data into a verification set.
For example steps 205 and 206, as an implementation manner, the claim risk feature is input into a fraud risk prediction model (as an implementation manner, the claim risk feature is a piece of text information, the text information can be spliced into a piece of whole text information, the whole text information is input into a fraud risk prediction model), the fraud risk prediction model predicts the fraud risk of the claim risk feature to obtain fraud risk information of the medical case to be claiming, the fraud risk information includes fraud risk probability, after obtaining the fraud risk probability, the fraud risk probability is compared with a preset rechecking probability, if the fraud risk probability is greater than the preset rechecking probability, in order to improve accuracy, the medical case to be claiming is not directly determined to pass the fraud risk audit, but a manual audit material of the medical case to be claiming is generated, and the manual audit material is sent to a preset manual audit terminal, and the medical case to be claiming, which is fed back by the manual audit terminal, passes the fraud risk audit or does not pass the fraud audit.
Therefore, the medical cases to be claiming with the fraud risk probability larger than the preset rechecking probability are screened out through the fraud risk prediction model, manual auditing is not needed for all the medical cases to be claiming, and only the medical cases to be claiming with the fraud risk probability larger than the preset rechecking probability are required to be manually audited, so that the accuracy of fraud risk prediction is improved. If the fraud risk probability is smaller than or equal to the preset rechecking probability, the medical cases to be clawed are directly determined to pass the fraud risk auditing, and the fraud risk prediction efficiency is improved. For the embodiment steps 201-206, the intellectualization and automation are realized in the flow, and the cost is reduced.
The invention provides a fraud risk prediction method, a fraud risk prediction device and fraud risk prediction equipment for a claim case, which can firstly acquire claim declaration materials of a medical case to be subjected to claim settlement, wherein the claim declaration materials comprise claim settlement user information and claim settlement evidence materials; further, based on the information of the claim user, acquiring auxiliary proving materials of the claim user; then, according to the information of the claim user, the claim proving material and the auxiliary proving material, generating claim risk characteristics of the medical case to be claimed; and finally, carrying out fraud risk prediction on the risk features of the claims to be resolved through a fraud risk prediction model to obtain fraud risk information of the medical cases to be resolved. According to the technical scheme, the method and the device for predicting the fraud risk by using the medical case to be claiming and the medical case to be claiming generate the risk feature of the medical case to be claiming by using multidimensional information (comprising the information of the claiming user, the claiming proving material and the auxiliary proving material), so that the comprehensiveness and the accuracy of the risk feature of the claiming are improved, the accuracy of the fraud risk prediction by using the fraud risk prediction model is further improved, manual checking is not needed, the efficiency of the fraud risk prediction is improved, the cost is reduced, and the accuracy is improved.
Further, as a specific implementation of the method shown in fig. 1 and fig. 2, an embodiment of the present invention provides a fraud risk prediction apparatus for a claim case, as shown in fig. 3, where the apparatus includes: a first acquisition module 31, a second acquisition module 32, a generation module 33, a prediction module 34;
A first obtaining module 31, configured to obtain claim declaration materials of a medical case to be claiming, where the claim declaration materials include claim user information and claim proof materials;
a second obtaining module 32, configured to obtain auxiliary proof materials of the claim user based on the claim user information;
a generating module 33, configured to generate a claim risk feature of the medical case to be claim according to the claim user information, the claim proof material, and the auxiliary proof material;
and the prediction module 34 is configured to predict fraud risk for the claims risk feature through a fraud risk prediction model, so as to obtain fraud risk information of the medical case to be claiming.
In a specific application scenario, the fraud risk information includes fraud risk probabilities; as shown in fig. 4, a fraud risk prediction apparatus for a claim case, the apparatus further comprising: the auditing module 35 is specifically configured to generate a manual auditing material of the case to be claiming based on the claim reporting material, the auxiliary proof material and the fraud risk probability if the fraud risk probability is greater than a preset rechecking probability, and send the manual auditing material to a preset manual auditing terminal; and if the fraud risk probability is smaller than or equal to the preset rechecking probability, determining that the medical case to be claiming passes the fraud risk auditing.
Accordingly, in order to generate the claim risk feature of the medical case to be claimed according to the claim user information, the claim proof material, and the auxiliary proof material, as shown in fig. 4, the generating module 33 includes:
the query unit 331 may be configured to query the auxiliary proof materials with the same type of the medical case to be claiming as the material to be verified;
the comparison unit 332 may be configured to compare the claim verification material with the material to be verified, and obtain a portion of the claim verification material that is not matched with the material to be verified as the material to be verified;
an interrogation unit 333, configured to generate certification material interrogation information based on the certification material to be confirmed and the material to be verified, and send the certification material interrogation information to a claim user terminal;
a first generating unit 334, configured to receive material modification information fed back from the claim user terminal; and generating the claim risk feature of the medical case to be claimed based on the claim user information, the material modification information, the claim proving material and the auxiliary proving material.
A second generating unit 335, configured to receive the objection prover material fed back by the claim user terminal; the material to be confirmed, the material to be verified and the objection evidence obtaining material are sent to a preset evidence obtaining and checking terminal; receiving evidence passing information fed back from the preset evidence checking terminal, and generating the claim risk feature based on the claim user information, the claim evidence material, the auxiliary evidence material and the objection evidence material; or receiving the proof failing information fed back by the preset proof auditing terminal, modifying the to-be-confirmed proof material by using the to-be-verified material to obtain updated claim proof material, and generating the claim risk feature based on the claim user information, the updated claim proof material and the auxiliary proof material.
Accordingly, in order to generate the risk feature of the medical case to be claiming based on the claim user information, the material modification information, the claim proof material and the auxiliary proof material, the first generating unit 334 is specifically configured to obtain the risk feature contribution ranking of the medical case to be claiming according to the type, and determine the risk prediction information of the preset number before the risk feature contribution ranking based on the claim user information, the material modification information, the claim proof material and the auxiliary proof material; and extracting features of the risk prediction information to obtain the risk feature of the claim to be subjected to claim settlement of the medical case.
Correspondingly, the first generating unit 334 may be further specifically configured to obtain, before the step of obtaining the rank of the risk feature contribution value of the medical case to be claiming, a historical medical case of the same type, where the historical medical case includes a non-risk historical medical case that passes the fraud risk audit and a risk historical medical case that does not pass the fraud risk audit; acquiring initial characteristics based on historical claim proof materials of the historical medical cases, historical claim user information and historical auxiliary proof materials of the historical claim users, wherein the historical claim proof materials comprise hospital names, medical history and operation history, the historical claim user information comprises names, applicant ages, insured ages, first claim amount and social insurance years, and the historical auxiliary proof materials comprise whether insured persons apply for funding or not; calculating the proportion of any one initial feature in the non-risk historical medical case and the risk historical medical case respectively, and calculating the contribution value of the initial feature to risk prediction according to the proportion to obtain the ranking of the contribution values of the risk features.
Correspondingly, in order to obtain initial features based on the historical claims evidencing material, the historical claims evidencing user information and the historical auxiliary evidencing material of the historical claims evidencing user of the historical medical case, the first generating unit 334 is specifically further configured to extract non-computing initial features from the historical claims evidencing material and the historical claims evidencing user information of the historical medical case; generating computing type initial characteristics according to the non-computing type initial characteristics and the computing rules; and determining the non-computing class initial feature and the computing class initial feature as initial features.
It should be noted that, other corresponding descriptions of the functional units related to the fraud risk prediction apparatus for claim case provided in this embodiment may refer to corresponding descriptions of fig. 1 to fig. 2, and are not repeated herein.
Based on the above-mentioned methods shown in fig. 1 to 2, correspondingly, the present embodiment further provides a storage medium, which may be specifically volatile or nonvolatile, and has a computer program stored thereon, where the program, when executed by a processor, implements the fraud risk prediction method for the claim case shown in fig. 1 to 2.
Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which may be stored in a storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method of each implementation scenario of the present invention.
Based on the method shown in fig. 1 to 2 and the virtual device embodiments shown in fig. 3 and 4, in order to achieve the above object, the present embodiment further provides a computer device, where the computer device includes a storage medium and a processor; a storage medium storing a computer program; a processor for executing a computer program to implement the fraud risk prediction method for claim cases as shown in fig. 1 to 2.
Optionally, the computer device may also include a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, and the like. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
It will be appreciated by those skilled in the art that the architecture of a computer device provided in this embodiment is not limited to this physical device, but may include more or fewer components, or may be combined with certain components, or may be arranged in a different arrangement of components.
The storage medium may also include an operating system, a network communication module. An operating system is a program that manages the computer device hardware and software resources described above, supporting the execution of information handling programs and other software and/or programs. The network communication module is used for communication among components in the actual storage medium and communication with other hardware and software in the information processing entity device.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present invention may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware.
The invention provides a fraud risk prediction method, a fraud risk prediction device and fraud risk prediction equipment for a claim case, which can firstly acquire claim declaration materials of a medical case to be subjected to claim settlement, wherein the claim declaration materials comprise claim settlement user information and claim settlement evidence materials; further, based on the information of the claim user, acquiring auxiliary proving materials of the claim user; then, according to the information of the claim user, the claim proving material and the auxiliary proving material, generating claim risk characteristics of the medical case to be claimed; and finally, carrying out fraud risk prediction on the risk features of the claims to be resolved through a fraud risk prediction model to obtain fraud risk information of the medical cases to be resolved. According to the technical scheme, the method and the device for predicting the fraud risk by using the medical case to be claiming and the medical case to be claiming generate the risk feature of the medical case to be claiming by using multidimensional information (comprising the information of the claiming user, the claiming proving material and the auxiliary proving material), so that the comprehensiveness and the accuracy of the risk feature of the claiming are improved, the accuracy of the fraud risk prediction by using the fraud risk prediction model is further improved, manual checking is not needed, the efficiency of the fraud risk prediction is improved, the cost is reduced, and the accuracy is improved.
Those skilled in the art will appreciate that the drawing is merely a schematic illustration of a preferred implementation scenario and that the modules or flows in the drawing are not necessarily required to practice the invention. Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above-mentioned inventive sequence numbers are merely for description and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely illustrative of some embodiments of the invention, and the invention is not limited thereto, as modifications may be made by those skilled in the art without departing from the scope of the invention.
Claims (10)
1. A fraud risk prediction method for a claim case, the method comprising:
acquiring claim declaration materials of medical cases to be claiming, wherein the claim declaration materials comprise claim user information and claim proving materials;
acquiring auxiliary proof materials of the claim settling user based on the claim settling user information;
Generating the claim risk feature of the medical case to be subjected to claim settlement according to the claim settlement user information, the claim settlement proving material and the auxiliary proving material;
and carrying out fraud risk prediction on the claims risk feature through a fraud risk prediction model to obtain fraud risk information of the medical case to be subjected to the claims.
2. The method of claim 1, wherein the fraud risk information includes a fraud risk probability; after obtaining the fraud risk information for the medical case to be claiming, the method further includes:
if the fraud risk probability is greater than a preset rechecking probability, generating a manual auditing material of the case to be claiming based on the claiming material, the auxiliary proof material and the fraud risk probability, and sending the manual auditing material to a preset manual auditing terminal;
and if the fraud risk probability is smaller than or equal to the preset rechecking probability, determining that the medical case to be claiming passes the fraud risk auditing.
3. The method of claim 1, wherein the generating the claim risk feature of the medical case to be claimed from the claim user information, the claim proof material, and the auxiliary proof material comprises:
Inquiring auxiliary proving materials with the same type of the medical cases to be claiming as materials to be checked;
comparing the claim verification material with the material to be verified, and acquiring a part, which is not matched with the material to be verified, of the claim verification material as the material to be confirmed;
generating proving material inquiry information based on the proving material to be confirmed and the material to be verified, and sending the proving material inquiry information to a claim settlement user terminal;
receiving material modification information fed back from the claim user terminal;
and generating the claim risk feature of the medical case to be claimed based on the claim user information, the material modification information, the claim proving material and the auxiliary proving material.
4. The method of claim 3, wherein after the sending the certification material challenge to the claim user terminal, the method further comprises:
receiving objection evidence-providing materials fed back by the claim user terminal;
the material to be confirmed, the material to be verified and the objection evidence obtaining material are sent to a preset evidence obtaining and checking terminal;
receiving evidence passing information fed back from the preset evidence checking terminal, and generating the claim risk feature based on the claim user information, the claim evidence material, the auxiliary evidence material and the objection evidence material; or alternatively, the first and second heat exchangers may be,
And receiving the proof failing information fed back by the preset proof auditing terminal, modifying the to-be-confirmed proof material by utilizing the to-be-verified material to obtain updated claim proof material, and generating the claim risk feature based on the claim user information, the updated claim proof material and the auxiliary proof material.
5. The method of claim 3 or 4, wherein the generating the claim risk feature of the medical case to be claimed based on the claim user information, the material modification information, the claim proof material, and the auxiliary proof material comprises:
according to the type, acquiring risk characteristic contribution value ranking of the medical cases to be claiming, and determining risk prediction information of a preset quantity before the risk characteristic contribution value ranking based on the claiming user information, the material modification information, the claiming evidence material and the auxiliary evidence material;
and extracting features of the risk prediction information to obtain the risk feature of the claim to be subjected to claim settlement of the medical case.
6. The method of claim 5, wherein prior to the obtaining the rank of risk characteristic contribution values for the medical case to be claiming, the method further comprises:
Acquiring the same type of historical medical cases, wherein the historical medical cases comprise non-risk historical medical cases passing fraud risk auditing and risk historical medical cases not passing fraud risk auditing;
acquiring initial characteristics based on historical claim proof materials of the historical medical cases, historical claim user information and historical auxiliary proof materials of the historical claim users, wherein the historical claim proof materials comprise hospital names, medical history and operation history, the historical claim user information comprises names, applicant ages, insured ages, first claim amount and social insurance years, and the historical auxiliary proof materials comprise whether insured persons apply for funding or not;
calculating the proportion of any one initial feature in the non-risk historical medical case and the risk historical medical case respectively, and calculating the contribution value of the initial feature to risk prediction according to the proportion to obtain the ranking of the contribution values of the risk features.
7. The method of claim 6, wherein the obtaining initial characteristics based on the historical claims proof material of the historical medical case, the historical claims user information, and the historical auxiliary proof material of the historical claims user comprises:
Extracting non-computing initial characteristics from historical claim proof materials and historical claim user information of the historical medical case;
generating computing type initial characteristics according to the non-computing type initial characteristics and the computing rules;
and determining the non-computing class initial feature and the computing class initial feature as initial features.
8. A fraud risk prediction apparatus for a claim case, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring claim declaration materials of medical cases to be claiming, and the claim declaration materials comprise claim user information and claim proof materials;
the second acquisition module is used for acquiring auxiliary proof materials of the claim settlement users based on the claim settlement user information;
the generation module is used for generating the claim risk characteristics of the medical case to be subjected to claim settlement according to the claim settlement user information, the claim settlement proving material and the auxiliary proving material;
and the prediction module is used for predicting the fraud risk of the claims to be clashed according to the fraud risk prediction model to obtain the fraud risk information of the medical case to be clashed.
9. A storage medium having stored thereon a computer program, which when executed by a processor implements the fraud risk prediction method of the claim case of any of claims 1 to 7.
10. A computer device comprising a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, characterized in that the processor implements the fraud risk prediction method of the claim case of any of claims 1 to 7 when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988048.7A CN117114706A (en) | 2023-08-07 | 2023-08-07 | Fraud risk prediction method, device and equipment for claim case |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988048.7A CN117114706A (en) | 2023-08-07 | 2023-08-07 | Fraud risk prediction method, device and equipment for claim case |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117114706A true CN117114706A (en) | 2023-11-24 |
Family
ID=88793978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310988048.7A Pending CN117114706A (en) | 2023-08-07 | 2023-08-07 | Fraud risk prediction method, device and equipment for claim case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114706A (en) |
-
2023
- 2023-08-07 CN CN202310988048.7A patent/CN117114706A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| 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 | |
| CN109993233B (en) | Method and system for predicting data auditing objective based on machine learning | |
| US20160063645A1 (en) | Computer program, method, and system for detecting fraudulently filed tax returns | |
| CN109978033B (en) | Method and device for constructing same-operator recognition model and method and device for identifying same-operator | |
| US20100332362A1 (en) | Tax return evaluation system | |
| US20170018030A1 (en) | System and Method for Determining Credit Worthiness of a User | |
| US11461298B1 (en) | Scoring parameter generation for identity resolution | |
| CN110348471B (en) | Abnormal object identification method, device, medium and electronic equipment | |
| US20120089415A1 (en) | Nursing home evaluation system | |
| US20210374886A1 (en) | Machine-learning prediction of occupancy status of real property | |
| CN108470312B (en) | Method and device for analyzing claim case, storage medium and terminal | |
| CN110766275A (en) | Data verification method and device, computer equipment and storage medium | |
| CN112529716A (en) | Quota prediction method, device and computer readable storage medium | |
| WO2022155740A1 (en) | Systems and methods for outlier detection of transactions | |
| CN110610431A (en) | Intelligent claim settlement method and intelligent claim settlement system based on big data | |
| CN111179095A (en) | Health risk assessment-based underwriting method, system, equipment and storage medium | |
| CN109859060B (en) | Risk determination method, risk determination device, risk determination medium and electronic equipment | |
| CN110941644A (en) | Policy data generation method, device, equipment and storage medium | |
| CN112702410B (en) | Evaluation system, method and related equipment based on blockchain network | |
| CN113344437A (en) | Claim settlement service processing method and device, computer equipment and storage medium | |
| Parente et al. | Assessment of predictive modeling for identifying fraud within the Medicare program | |
| US20220414125A1 (en) | Systems and Methods for Computer Modeling Using Incomplete Data | |
| CN117114706A (en) | Fraud risk prediction method, device and equipment for claim case | |
| CN113269179B (en) | Data processing method, device, equipment and storage medium | |
| Park et al. | An assessment of juvenile justice reform in Ohio: Impact on youth placement and recidivism from 2008 to 2015 |
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 |