CN116308823A - Knowledge graph-based wind control method and related equipment - Google Patents
Knowledge graph-based wind control method and related equipment Download PDFInfo
- Publication number
- CN116308823A CN116308823A CN202310293468.3A CN202310293468A CN116308823A CN 116308823 A CN116308823 A CN 116308823A CN 202310293468 A CN202310293468 A CN 202310293468A CN 116308823 A CN116308823 A CN 116308823A
- Authority
- CN
- China
- Prior art keywords
- data
- wind control
- target
- knowledge
- graph
- 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 50
- 238000003066 decision tree Methods 0.000 claims abstract description 21
- 230000036541 health Effects 0.000 claims abstract description 20
- 238000003745 diagnosis Methods 0.000 claims description 49
- 201000010099 disease Diseases 0.000 claims description 32
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 18
- 238000007689 inspection Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000012954 risk control Methods 0.000 abstract description 5
- 238000007726 management method Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a wind control method based on a knowledge graph, which is applied to the field of risk control. The method provided by the application comprises the following steps: acquiring historical case data and business knowledge associated with a target health insurance business as data to be processed; constructing a body of the claim management and control knowledge graph, and acquiring body field data contained in the body of the claim management and control knowledge graph and body association relation of the body of the claim management and control knowledge graph; importing the target claim wind control knowledge graph body and the body association relationship into a preset first graph database to obtain a target claim wind control knowledge graph; constructing a target knowledge-graph and claim wind control model according to the target claim wind control knowledge graph and the decision tree model; acquiring information data of gray list users which are not really informed of wind control model identification as data to be judged; and inputting information data of the gray list users to the target knowledge graph claim settlement wind control model, and outputting a corresponding claim settlement risk judgment result.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a wind control method based on a knowledge graph and related equipment.
Background
In the health insurance business of the insurance industry, the external expenditure of an insurance company is mostly the payment of claim settlement, namely, a user purchases health insurance, visits to a hospital after suffering from the health insurance, and the payment cost is settled, so that the risk control for the health insurance claim settlement is a very important link, and the final objective of automatic risk control is to avoid the risk, reduce the risk and improve the efficiency.
The traditional insurance wind control model is an inauguration wind control model and is mainly used for judging whether a report user has inauguration risk. However, the inauguration wind control model outputs a part of gray list report users which cannot be judged except the black list report users and the white list report users, namely the traditional insurance wind control model cannot obtain the claim wind control results corresponding to part of report users.
Disclosure of Invention
The embodiment of the application provides a wind control method, a device, computer equipment and a storage medium based on a knowledge graph, which are used for solving the problem that a traditional insurance wind control model cannot obtain a claim wind control result corresponding to a part of case reporting users.
In a first aspect of the present application, a knowledge-graph-based wind control method is provided, including:
Acquiring data of a historical insurance case related to a target health insurance service and first knowledge graph data of service knowledge data related to the target health insurance service, and taking the data of the historical insurance case and the first knowledge graph data as data to be processed;
constructing a target claim wind control knowledge graph body according to the ontology construction requirement, and acquiring ontology field data contained in the target claim wind control knowledge graph body and an ontology association relationship between the target claim wind control knowledge graph bodies from the data to be processed;
inputting the disease description content data of the target claim wind control knowledge graph body into a trained auxiliary diagnosis entity recognition model, and outputting a corresponding auxiliary diagnosis recognition result, wherein the auxiliary diagnosis recognition result comprises a disease entity and/or an inspection entity and/or a treatment entity;
importing the target claim wind control knowledge graph body, the body association relationship and the auxiliary diagnosis recognition result into a preset first graph database to obtain a target claim wind control knowledge graph;
constructing a target knowledge-graph and claim wind control model according to the target claim wind control knowledge graph and the decision tree model;
Acquiring information data of a gray list user identified by an inapplicable notification wind control model as data to be judged, wherein the inapplicable notification wind control model is an artificial intelligent claim settlement wind control model constructed based on XGBoost, and the information data of the gray list user cannot be identified by the inapplicable notification wind control model as either black list user information data or white list user information data;
and inputting information data of the gray list user to the target knowledge graph claim settlement wind control model, and outputting a target claim settlement risk judgment result corresponding to the gray list user.
In a second aspect of the present application, there is provided a knowledge-graph-based wind control apparatus, including:
the first data acquisition module is used for acquiring data of a historical insurance case related to a target health insurance service and first knowledge graph data of service knowledge data related to the target health insurance service, and taking the data of the historical insurance case and the first knowledge graph data as data to be processed;
the second data acquisition module is used for constructing a target claim management and wind control knowledge graph body according to the ontology construction requirement, and acquiring ontology field data contained in the target claim management and wind control knowledge graph body and ontology association relations among the target claim management and wind control knowledge graph bodies from the data to be processed;
The auxiliary diagnosis recognition module is used for inputting the disease description content data of the target claim management and control knowledge graph body into a trained auxiliary diagnosis entity recognition model and outputting a corresponding auxiliary diagnosis recognition result, wherein the auxiliary diagnosis recognition result comprises a disease entity and/or an inspection entity and/or a treatment entity;
the claim settlement wind control knowledge graph module is used for importing the target claim settlement wind control knowledge graph body, the body association relationship and the auxiliary diagnosis recognition result into a preset first graph database to obtain a target claim settlement wind control knowledge graph;
the claim settlement wind control model module is used for constructing a target knowledge spectrum claim settlement wind control model according to the target claim settlement wind control knowledge spectrum and the decision tree model;
the third data acquisition module is used for acquiring information data of the gray list user identified by the inauguration wind control model as data to be judged, wherein the inauguration wind control model is an artificial intelligent claim settlement wind control model constructed based on XGBoost, and the information data of the gray list user cannot be identified by the inauguration wind control model as either black list user information data or white list user information data;
And the claim risk judging module is used for inputting the information data of the gray list user to the target knowledge graph claim wind control model and outputting a target claim risk judging result corresponding to the gray list user.
In a third aspect of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the knowledge-graph-based wind control method described above when the processor executes the computer program.
In a fourth aspect of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the knowledge-graph-based wind control method described above.
According to the knowledge graph-based wind control method, the knowledge graph-based wind control device, the computer equipment and the storage medium, the corresponding target claim wind control knowledge graph is generated by acquiring and processing the historical insurance case data and the associated business knowledge data associated with the target health insurance business, the target claim wind control knowledge graph and the decision tree model are used for constructing a target knowledge graph claim wind control model, and the target knowledge graph claim wind control model is used for outputting a claim wind control result. The problem that the traditional insurance wind control model cannot obtain the claim settlement wind control results corresponding to part of the case reporting users is solved, the automatic risk control capability of insurance business is improved, and risks can be further avoided, and the claims are reduced and increased.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments of the present application will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an application environment of a knowledge-based wind control method according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of a knowledge-based wind control method in an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an air control device based on a knowledge graph according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a computer device in an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
The wind control method based on the knowledge graph can be applied to an application environment as shown in fig. 1, wherein computer equipment can be, but not limited to, various personal computers and notebook computers, the computer equipment can also be a server, the server can be an independent server, and also can be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDNs), basic cloud computing services such as big data and artificial intelligent platforms and the like. It will be appreciated that the number of computer devices in fig. 1 is merely illustrative and that any number of extensions may be made according to actual needs.
In an embodiment, as shown in fig. 2, a knowledge graph-based wind control method is provided, and the method is applied to the computer device in fig. 1, and is illustrated as an example, and includes the following steps S101 to S107:
s101, acquiring data of a historical insurance case related to a target health insurance service and first knowledge graph data of service knowledge data related to the target health insurance service, and taking the data of the historical insurance case and the first knowledge graph data as data to be processed.
S102, building a target claim wind control knowledge graph body according to the ontology building requirement, and acquiring ontology field data contained in the target claim wind control knowledge graph body and an ontology association relationship between the target claim wind control knowledge graph bodies from the data to be processed.
For example, the health insurance business of a certain financial and scientific platform generates the target claim management and control knowledge graph body including the following fields: the number of the person to be protected, the case number, the bill number, the disease project, the disease description, the case setting time, the time of the visit end, the inappropriately informed model prediction result, whether to actually upgrade, the product name, the time of the policy validation, whether to renew the insurance, the clinic or the hospitalization.
S103, inputting the disease description content data of the target claim wind control knowledge graph body into a trained auxiliary diagnosis entity recognition model, and outputting a corresponding auxiliary diagnosis recognition result, wherein the auxiliary diagnosis recognition result comprises a disease entity and/or an inspection entity and/or a treatment entity.
S104, importing the target claim wind control knowledge graph body, the body association relationship and the auxiliary diagnosis recognition result into a preset first graph database to obtain the target claim wind control knowledge graph.
Wherein, graph Database (GDB) is a non-relational Database that uses Graph structure for semantic queries, and uses ontologies, relationships, and attributes to represent and store data. The graph database directly associates data items in storage with data ontologies and collections of edges representing relationships between ontologies. Further, the first graph database may be selected from but not limited to: neo4j, orientDB, arangoDB, janusGraph, dgraph, hugeGraph, etc.
S105, constructing a target knowledge-graph and claim wind control model according to the target claim wind control knowledge-graph and the decision tree model.
The decision tree model includes processes of data processing, calculation, analysis and the like, and specifically includes a processing method (such as word segmentation processing of a disease description text) for performing data processing, a specific algorithm (such as an algorithm for calculating a disease association degree) for performing data calculation, an analysis step for performing data analysis, a judgment rule for performing data judgment and the like. Meanwhile, in the operation process of the decision tree model, one part of data comes from the input data of the current case to be judged, the other part of data comes from the target claim management and wind control knowledge graph, and the target claim management and wind control knowledge graph provides data support for the decision tree model to process the current case to be judged, so that the target knowledge graph management and wind control model is built by using the target claim management and wind control knowledge graph and the decision tree model together.
S106, acquiring information data of gray list users identified by the inauguration wind control model as data to be judged, wherein the inauguration wind control model is an artificial intelligent claim wind control model constructed based on XGBoost, and the information data of the gray list users cannot be identified by the inauguration wind control model as black list user information data or white list user information data.
Further, after the acquiring the gray list user information data which is not actually informed of the wind control model identification as the data to be judged, the method further comprises: firstly, corresponding historical case data is obtained according to a unique user code contained in the gray list user information data. And if the historical case data is empty, directly outputting the gray list user information data and the corresponding gray judgment result, and not inputting the gray list user information data into the target knowledge graph claim settlement wind control model.
S107, inputting information data of the gray list user to the target knowledge graph claim settlement wind control model, and outputting a target claim settlement risk judgment result corresponding to the gray list user.
Specifically, the inputting the information data of the gray list user to the target knowledge graph claim management and control model, and outputting the target claim management and risk judgment result corresponding to the gray list user includes: firstly, acquiring corresponding gray list user history case data according to the unique user codes of the gray list users. And then, judging a first map relation between the current risk content of the gray list user and the historical case data of the gray list user according to the target claim risk knowledge map. And finally, the decision tree model calculates the target claim risk judgment result of the gray list user according to the first map relation and the target claim wind control knowledge map.
Specifically, the determining, according to the target claim risk knowledge graph, a first graph relationship between the current risk content of the gray list user and the historical case data of the gray list user includes: in a first aspect, a first determination result is obtained, whether the current risk content corresponding to the gray list user information data is identical to the disease item in the corresponding historical case data and the auxiliary diagnosis recognition result or whether the characters comprise the same or not. In a second aspect, a second determination result of whether the disease item and the auxiliary diagnosis recognition result in the current risk content corresponding to the gray list user information data and the corresponding historical case data are inclusion relationships is obtained. In a third aspect, a third determination result of whether a sibling relationship exists between the current risk content corresponding to the gray list user information data and the disease item and the auxiliary diagnosis recognition result in the corresponding historical case data is obtained. In a fourth aspect, a fourth determination result of whether an association relationship exists between the current risk content corresponding to the gray list user information data and the disease item and the auxiliary diagnosis recognition result in the corresponding historical case data is obtained. In a fifth aspect, a fifth determination result of whether a similarity relationship exists between the current risk content corresponding to the gray list user information data and the disease item and the auxiliary diagnosis recognition result in the corresponding historical case data is obtained. And finally, adding the first judgment result, the second judgment result, the third judgment result, the fourth judgment result and the fifth judgment result to the first map relation.
In a more specific embodiment, first, a first identification variable corresponding to the first determination result is set as old_flag, a second identification variable corresponding to the second determination result is set as included_flag, a third identification variable corresponding to the third determination result is set as branch_flag, a fourth identification variable corresponding to the fourth determination result is set as related_flag, and a fifth identification variable corresponding to the fifth determination result is set as flag. Wherein the five identification variables of the old_flag, the incorporated_flag, the other_flag, the related_flag and the alike_flag have values of 1, 2 or 3. The corresponding judgment result is represented as an upgrade when the identification variable value is 1, the corresponding judgment result is represented as a pass when the identification variable value is 2, and the corresponding judgment result is represented as an incapability of judgment when the identification variable value is 3. Further, initial values of the first identification variable, the second identification variable, the third identification variable, the fourth identification variable and the fifth identification variable are all 0.
Further, in the more specific embodiment, a sixth identification variable is set to old_get_flag, where old_get_flag is used to indicate whether the first determination result is empty, and a seventh identification variable is set to old_2_num, where old_2_num is used to indicate the first number of times that the history case is whitened in the first determination result. And setting an eighth identification variable as an included_get_flag, wherein the included_get_flag is used for indicating whether the second judging result is empty, and setting a ninth identification variable as an included_2_num, and the included_2_num is used for indicating the second number of times that the historical case is judged to be white in the second judging result. Setting a tenth identification variable as a branch_get_flag, wherein the branch_get_flag is used for indicating whether the third judging result is empty, setting an eleventh identification variable as a branch_2_num, and the branch_2_num is used for indicating the third number of times that the historical case is whitened in the third judging result. Setting a twelfth identification variable as a related_get_flag, wherein the related_get_flag is used for indicating whether the fourth judging result is empty, and setting a thirteenth identification variable as a related_2_num, wherein the related_2_num is used for indicating the fourth number of times that the historical case is judged to be white in the fourth judging result. Setting a fourteenth identification variable as an alike_get_flag, wherein the alike_get_flag is used for indicating whether the fifth judging result is empty, setting a fifteenth identification variable as alike_2_num, and the alike_2_num is used for indicating the fifth number of times that the historical case is judged to be white in the fifth judging result. Further, initial values of the sixth, seventh, eighth, ninth, tenth, eleventh, twelfth, thirteenth, fourteenth, and fifteenth identification variables are all 0.
Further, in the more specific embodiment, the process of data processing, calculating and judging by the decision tree model includes the following steps S201 to S222:
s201, traversing the gray list user history case data, judging whether the first judging result is empty, and if not, assigning the old_get_flag to be 1.
S202, judging whether the diagnosis ending time of the currently traversed historical case is larger than the diagnosis time of the current dangerous content, if so, assigning the old_flag to be 1, and if not, executing the step S203.
S203, judging whether the insurance product of the current traversed historical case is the same as the insurance product of the current insurance content, if not, executing the step S204; if yes, step S205 is executed.
S204, judging whether the current traversed historical case is upgraded or not, if not, assigning the old_flag to be 3 if the old_flag is not equal to 1; if yes, the old_flag is assigned to be 1, the history cases which are not traversed are obtained from the history case data of the gray list user to update the current traversed history cases, and step S202 is executed.
S205, judging whether the effective time of the policy of the currently traversed historical case is smaller than the effective time of the current dangerous content, if so, executing a step S206; if not, step S214 is performed.
S206, judging whether the old_flag is equal to 1, if so, executing a step S207; if yes, the history cases which are not traversed are obtained from the history case data of the gray list user to update the current traversed history cases, and step S202 is executed.
S207, judging whether the current traversed historical case is continued or not, if so, executing a step S208; if not, the old_flag is assigned to 1, and the history cases which are not traversed are obtained from the history case data of the gray list user to update the current traversed history cases, and step S202 is executed.
S208, judging whether the current traversed historical case is lifted, and if so, executing a step S210; if not, adding 1 to the old_2_num; judging whether the time difference between the effective time of the policy of the currently traversed historical case and the effective time of the policy of the currently-in-danger content is less than 1 year, wherein the time difference between the diagnosis end time of the currently traversed historical case and the effective time of the currently-in-danger content is less than 1 year, the old_flag is not equal to 3, if so, the old_flag is assigned to 2, and the history case which is not traversed is obtained from the history case data of the gray list user to update the currently traversed historical case, and executing step S202; if not less than 1 year, step S209 is performed.
S209, judging whether the old_2_num is larger than 2, if so, assigning the old_flag to be 2, acquiring a history case which is not traversed from the history case data of the gray list user to update the current traversed history case, and executing step S202; if not, the old_flag is assigned to 3.
S210, subtracting 1 from the old_2_num, judging whether the old_2_num is larger than or equal to 2, if so, assigning the old_flag to be 2, acquiring a history case which is not traversed from the gray list user history case data, updating the current traversed history case, and executing step S202; if not, the old_flag is assigned to 3, and step S211 is executed.
S211, if the effective time of the policy of the current traversed historical case is equal to the effective time of the current dangerous content in the step S205, judging whether the old_flag is equal to 1, if so, acquiring the history case which is not traversed from the gray list user historical case data to update the current traversed historical case, and executing the step S202; if not, step S212 is performed.
S212, if the current traversed history case is not lifted, adding 1 to the old_2_num; judging whether the time difference between the time of the end of the consultation of the currently traversed historical case and the effective time of the policy of the currently risky content is less than 1 year and the old_flag is not equal to 3, if so, assigning the old_flag to be 2, acquiring the history case which is not traversed from the gray list user history case data to update the currently traversed historical case, and executing step S202; if not less than 1 year, step S213 is performed.
S213, if the current traversed history case is not lifted, assigning the old_flag to be 3, and then executing step S214.
S214, judging whether the effective time of the policy of the currently traversed historical case is smaller than the effective time of the currently-risked content, if not, assigning old_flag to be 1, and then executing step S215.
S215, if the diagnosis ending time of the current traversed historical case is equal to the diagnosis time of the current dangerous content, judging whether the insurance products of the current traversed historical case are identical to the insurance products of the current dangerous content, and if not, executing the step S216.
S216, judging whether the current traversed historical case is upgraded, if so, assigning the old_flag to be 1, acquiring the history case which is not traversed from the gray list user historical case data to update the current traversed historical case, and executing step S202; if not, the old_flag is assigned to 3, and then step S217 is performed.
S217, if the insurance product of the current traversed historical case is the same as the insurance product of the current dangerous content, further judging whether old_flag is equal to 1, if so, acquiring the history case which is not traversed from the gray list user historical case data to update the current traversed historical case, and executing step S202; if not, step S218 is performed.
S218, judging whether the current traversed historical case is lifted, if so, assigning the old_flag to be 1; if not, add 1 to the old_2_num, and then execute step S219.
S219, judging whether the time difference between the diagnosis ending time of the currently traversed historical case and the policy effective time of the currently risky content is less than 1 year, if yes, assigning the old_flag to be 2, acquiring the history case which is not traversed from the gray list user history case data to update the currently traversed historical case, and executing step S202; if not, step S220 is performed.
S220, continuing to traverse the gray list user historical case data until all the historical cases contained in the gray list user historical case data are judged to be completed, resetting the old_flag to be 0 if the old_flag is equal to 3 and resetting the old_flag to be 2 if the old_flag is equal to 0 and the old_get_flag is equal to 1 before each traversing.
S221, continuing to process the second judging result, the third judging result and the fourth judging result according to the steps, wherein the old_get_flag corresponds to the incorporated_get_flag, the broth_get_flag, the related_get_flag and the alike_get_flag, the old_flag corresponds to the incorporated_flag, the broth_flag, the related_flag and the alike_flag, and the old_2_num corresponds to the incorporated_2_num, the broth_2_num and the alike_2_num.
S222, counting the number of values 1 of the old_flag, the incorporated_flag, the other_flag, the related_flag, and the alike_flag as black_num, counting the number of values 2 of the old_flag, the incorporated_flag, the other_flag, the related_flag, and the alike_flag as white_num, and counting the number of values 0 of the old_flag, the incorporated_flag, the other_flag, the related_flag, and the alike_flag as grey_num.
S223, setting a judgment result as result_flag, and if the old_flag is equal to 2, assigning the result_flag as 2; if the black_num is equal to 1 and the other_flag is 1 or the alike_flag is 1, the result_flag is assigned to 0, otherwise, the result_flag is assigned to 1; if the black_num is larger than 1, the result_flag is assigned to be 1; if the grey_num is equal to 5, the result_flag is assigned to 0; if the black_num is equal to 0, or if the white_num is 1, or if the brier_flag or the alike_flag is 2, the result_flag is assigned to 0, otherwise, the result_flag is assigned to 2. Wherein, the judgment result result_flag is 0 represents the gray judgment, the judgment result result_flag is 1 represents the black judgment, and the judgment result result_flag is 2 represents the white judgment.
Further, the inputting the information data of the gray list user to the target knowledge graph claim settlement wind control model, and outputting the target claim settlement risk judgment result corresponding to the gray list user further includes: firstly, obtaining case setting result data of the claim case corresponding to the target claim risk judging result, and importing the case setting result data into the first graph database to update the target claim wind control knowledge graph. And then, obtaining comparison result data between the target claim risk judgment result and the case setting result data, and optimizing parameters of the inauguration notification wind control model and the decision tree model according to the comparison result data.
Further, after obtaining the case settlement result data of the claim case corresponding to the target claim risk judgment result, the method further includes: firstly, counting first statistical results of output results of the unrealistic notification wind control model and the target knowledge graph claim wind control model, wherein the first statistical results comprise a black judgment hit rate, a black judgment accuracy rate, a black judgment coverage rate, a white judgment hit rate, a white judgment accuracy rate and a white judgment coverage rate; the hit rate is the ratio of the black or white claim case to the historical insurance case, the accuracy rate is the ratio of the black or white claim case to the total number of the black or white claim cases, and the coverage rate is the ratio of the black or white claim case to the black or white claim case. And then, setting a first statistical result threshold range corresponding to the first statistical result, and creating a monitoring thread to monitor whether the first statistical result exceeds the first statistical result threshold range, if so, generating early warning information comprising the first statistical result and the corresponding first statistical result threshold range.
According to the knowledge-graph-based wind control method, the historical insurance case data related to the target health insurance business and the related business knowledge data are acquired and processed to generate the corresponding target claim wind control knowledge graph, the target knowledge-graph claim wind control model is built through the target claim wind control knowledge graph and the decision tree model, and the target knowledge-graph claim wind control model is used for outputting claim wind control results. The problem that the traditional insurance wind control model cannot obtain the claim settlement wind control results corresponding to part of the case reporting users is solved, the automatic risk control capability of insurance business is improved, and risks can be further avoided, and the claims are reduced and increased.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
In an embodiment, a knowledge-graph-based wind control device 100 is provided, where the knowledge-graph-based wind control device 100 corresponds to the knowledge-graph-based wind control method in the foregoing embodiment one by one. As shown in fig. 3, the knowledge-graph-based wind control apparatus 100 includes a first data acquisition module 11, a second data acquisition module 12, a sub-diagnosis recognition module 13, a claim-settlement wind control knowledge graph module 14, a claim-settlement wind control model module 15, a third data acquisition module 16, and a claim-settlement risk judgment module 17. The functional modules are described in detail as follows:
A first data obtaining module 11, configured to obtain data of a historical insurance case associated with a target health insurance service, and first knowledge-graph data of service knowledge data associated with the target health insurance service, and take the data of the historical insurance case and the first knowledge-graph data as data to be processed;
the second data obtaining module 12 is configured to construct a target claim wind control knowledge graph body according to the ontology construction requirement, and obtain ontology field data included in the target claim wind control knowledge graph body and an ontology association relationship between the target claim wind control knowledge graph bodies from the data to be processed;
the auxiliary diagnosis recognition module 13 is configured to input the disease description content data of the target claim management and control knowledge graph body into an auxiliary diagnosis entity recognition model that has been trained, and output a corresponding auxiliary diagnosis recognition result, where the auxiliary diagnosis recognition result includes a disease entity, and/or an inspection entity, and/or a treatment entity;
the claim management and wind control knowledge graph module 14 is configured to import the target claim management and wind control knowledge graph body, the body association relationship and the auxiliary diagnosis recognition result into a preset first graph database, so as to obtain a target claim management and wind control knowledge graph;
The claim settlement wind control model module 15 is used for constructing a target knowledge graph claim settlement wind control model according to the target claim settlement wind control knowledge graph and the decision tree model;
a third data obtaining module 16, configured to obtain information data of a gray list user identified by an inauguration wind control model as data to be determined, where the inauguration wind control model is an artificial intelligence claim wind control model constructed based on XGBoost, and the information data of the gray list user cannot be identified by the inauguration wind control model as either black list user information data or white list user information data;
and the claim risk judging module 17 is used for inputting the information data of the gray list user to the target knowledge graph claim wind control model and outputting a target claim risk judging result corresponding to the gray list user.
Further, the claim risk judging module 17 further includes:
the gray list user data sub-module is used for acquiring corresponding gray list user history case data according to the unique user codes of the gray list users;
the first map relation sub-module is used for judging a first map relation between the current risk content of the gray list user and the historical case data of the gray list user according to the target claim risk knowledge map;
And the claim risk calculation sub-module is used for calculating the target claim risk judgment result of the gray list user according to the first map relation and the target claim wind control knowledge map by the decision tree model.
Further, the first map relationship sub-module further includes:
a first judging result subunit, configured to obtain a first judging result that whether the current risk content corresponding to the gray list user information data is the same as the disease item in the corresponding historical case data or the sub-diagnosis recognition result or the character is included;
a second judging result subunit, configured to obtain a second judging result that whether the disease item and the auxiliary diagnosis recognition result in the current risk content corresponding to the gray list user information data and the corresponding historical case data are in a inclusion relationship;
a third judging result subunit, configured to obtain a third judging result that whether a sibling relationship exists between the current dangerous content corresponding to the gray list user information data and the disease item in the corresponding historical case data, and the auxiliary diagnosis recognition result;
a fourth judging result subunit, configured to obtain a fourth judging result that whether an association exists between the current risk content corresponding to the gray list user information data and the disease item in the corresponding historical case data, and the auxiliary diagnosis recognition result;
A fifth judging result subunit, configured to obtain a fifth judging result that whether a similarity exists between the current risk content corresponding to the gray list user information data and the disease item in the corresponding historical case data, and the auxiliary diagnosis recognition result;
and the first map relation generation subunit is used for adding the first judgment result, the second judgment result, the third judgment result, the fourth judgment result and the fifth judgment result to the first map relation.
Further, the third data acquisition module 16 further includes:
a fourth data obtaining sub-module, configured to obtain corresponding historical case data according to a unique user code included in the gray list user information data;
and the historical data empty judging sub-module is used for directly outputting the gray list user information data and the corresponding gray judging result if the historical case data are empty, and not inputting the gray list user information data into the target knowledge graph claim settlement wind control model.
Further, the claim risk judging module 17 further includes:
the knowledge map updating sub-module is used for acquiring the case setting result data of the claim case corresponding to the target claim risk judging result, and importing the case setting result data into the first map database so as to update the target claim wind control knowledge map;
And the parameter optimization sub-module is used for acquiring comparison result data between the target claim risk judgment result and the case setting result data, and optimizing parameters of the unrealistic notification wind control model and the decision tree model according to the comparison result data.
Further, the knowledge graph updating sub-module further includes:
the first statistical result sub-module is used for counting first statistical results of the output results of the unrealistic notification wind control model and the target knowledge graph claim settlement wind control model, and the first statistical results comprise a black judgment hit rate, a black judgment accuracy rate, a black judgment coverage rate, a white judgment hit rate, a white judgment accuracy rate and a white judgment coverage rate; the hit rate is the ratio of the black or white claim case to the historical insurance case, the accuracy rate is the ratio of the black or white claim case to the total number of the black or white claim cases, and the coverage rate is the ratio of the black or white claim case to the black or white claim case.
The early warning information generation sub-module is used for setting a first statistical result threshold range corresponding to the first statistical result, creating a monitoring thread to monitor whether the first statistical result exceeds the first statistical result threshold range, and if yes, generating early warning information containing the first statistical result and the corresponding first statistical result threshold range.
The meaning of "first" and "second" in the above modules/units is merely to distinguish different modules/units, and is not used to limit which module/unit has higher priority or other limiting meaning. Furthermore, the terms "comprises," "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and the partitioning of such modules by means of such elements is only a logical partitioning and may be implemented in a practical application.
For specific limitations of the knowledge-based wind control apparatus, reference may be made to the above limitation of the knowledge-based wind control method, and no further description is given here. All or part of the modules in the wind control device based on the knowledge graph can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data related to the wind control method based on the knowledge graph. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements a knowledge-graph-based wind control method.
In one embodiment, a computer device is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the knowledge-graph-based wind control method of the above embodiment, such as steps S101 to S107 shown in fig. 2 and other extensions of the method and extensions of related steps. Alternatively, the processor may implement the functions of each module/unit of the wind control device based on the knowledge graph in the above embodiment, for example, the functions of the modules 11 to 17 shown in fig. 3 when executing the computer program. In order to avoid repetition, a description thereof is omitted.
The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is a control center of the computer device, connecting various parts of the overall computer device using various interfaces and lines.
The memory may be used to store the computer program and/or modules, and the processor may implement various functions of the computer device by running or executing the computer program and/or modules stored in the memory, and invoking data stored in the memory. The memory 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 (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the cellular phone, etc.
The memory may be integrated in the processor or may be provided separately from the processor.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the steps of the knowledge-graph-based wind control method in the above embodiment, such as steps S101 to S107 shown in fig. 2 and other extensions of the method and extensions of related steps. Alternatively, the computer program when executed by the processor implements the functions of each module/unit of the knowledge-graph-based wind control apparatus in the above embodiment, such as the functions of the modules 11 to 17 shown in fig. 3. In order to avoid repetition, a description thereof is omitted.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. The wind control method based on the knowledge graph is characterized by comprising the following steps of:
acquiring data of a historical insurance case related to a target health insurance service and first knowledge graph data of service knowledge data related to the target health insurance service, and taking the data of the historical insurance case and the first knowledge graph data as data to be processed;
Constructing a target claim wind control knowledge graph body according to the ontology construction requirement, and acquiring ontology field data contained in the target claim wind control knowledge graph body and an ontology association relationship between the target claim wind control knowledge graph bodies from the data to be processed;
inputting the disease description content data of the target claim wind control knowledge graph body into a trained auxiliary diagnosis entity recognition model, and outputting a corresponding auxiliary diagnosis recognition result, wherein the auxiliary diagnosis recognition result comprises a disease entity and/or an inspection entity and/or a treatment entity;
importing the target claim wind control knowledge graph body, the body association relationship and the auxiliary diagnosis recognition result into a preset first graph database to obtain a target claim wind control knowledge graph;
constructing a target knowledge-graph and claim wind control model according to the target claim wind control knowledge graph and the decision tree model;
acquiring information data of a gray list user identified by an inapplicable notification wind control model as data to be judged, wherein the inapplicable notification wind control model is an artificial intelligent claim settlement wind control model constructed based on XGBoost, and the information data of the gray list user cannot be identified by the inapplicable notification wind control model as either black list user information data or white list user information data;
And inputting information data of the gray list user to the target knowledge graph claim settlement wind control model, and outputting a target claim settlement risk judgment result corresponding to the gray list user.
2. The knowledge-graph-based wind control method according to claim 1, wherein the inputting the information data of the gray list user to the target knowledge-graph-based claim wind control model outputs a target claim risk judgment result corresponding to the gray list user, includes:
acquiring corresponding gray list user historical case data according to the unique user codes of the gray list users;
judging a first map relation between the current risk content of the gray list user and the historical case data of the gray list user according to the target claim risk knowledge map;
and the decision tree model calculates the target claim risk judgment result of the gray list user according to the first map relation and the target claim wind control knowledge map.
3. The knowledge-graph-based wind control method according to claim 2, wherein the determining a first graph relationship between the current risk content of the gray list user and the gray list user history case data according to the target claim risk knowledge graph includes:
Acquiring a first judgment result of whether the current dangerous content corresponding to the gray list user information data is the same as a disease item in the corresponding historical case data or not and whether the auxiliary diagnosis and identification result is the same as the disease item or the character;
acquiring a second judgment result of whether the current risk content corresponding to the gray list user information data, the disease item in the corresponding historical case data and the auxiliary diagnosis recognition result are inclusion relations or not;
acquiring a third judging result of whether a brother relation exists between the current dangerous content corresponding to the gray list user information data and the disease item in the corresponding historical case data and the auxiliary diagnosis and identification result;
acquiring a fourth judging result of whether the association relationship exists between the current risk content corresponding to the gray list user information data and the disease item in the corresponding historical case data as well as the auxiliary diagnosis and identification result;
obtaining a fifth judging result of whether a similar relationship exists between the current dangerous content corresponding to the gray list user information data and the disease item in the corresponding historical case data as well as the auxiliary diagnosis and identification result;
and adding the first judgment result, the second judgment result, the third judgment result, the fourth judgment result and the fifth judgment result to the first map relation.
4. The knowledge-graph-based wind control method according to claim 2, wherein after the acquiring of the gray list user information data which does not actually inform about the wind control model identification as the data to be judged, further comprises:
acquiring corresponding historical case data according to a unique user code contained in the gray list user information data;
if the historical case data is empty, directly outputting the gray list user information data and the corresponding gray judgment result, and not inputting the gray list user information data into the target knowledge graph claim settlement wind control model.
5. The knowledge-graph-based wind control method according to claim 1, wherein the inputting the information data of the gray list user to the target knowledge-graph-based claim wind control model, and outputting the target claim risk judgment result corresponding to the gray list user, further comprises:
obtaining the case setting result data of the claim case corresponding to the target claim risk judgment result, and importing the case setting result data into the first graph database to update the target claim wind control knowledge graph;
and obtaining comparison result data between the target claim risk judgment result and the case setting result data, and optimizing parameters of the unrealistic notification wind control model and the decision tree model according to the comparison result data.
6. The knowledge-graph-based wind control method according to claim 5, wherein after obtaining the case settlement result data of the claim case corresponding to the target claim risk judgment result, further comprises:
counting first statistical results of output results of the unrealistic notification wind control model and the target knowledge graph claim wind control model, wherein the first statistical results comprise a black judgment hit rate, a black judgment accuracy rate, a black judgment coverage rate, a white judgment hit rate, a white judgment accuracy rate and a white judgment coverage rate;
the hit rate is the ratio of the black or white claim case to the historical insurance case, the accuracy rate is the ratio of the black or white claim case to the total number of the black or white claim cases, and the coverage rate is the ratio of the black or white claim case to the black or white claim case.
Setting a first statistical result threshold range corresponding to the first statistical result, creating a monitoring thread to monitor whether the first statistical result exceeds the first statistical result threshold range, and if so, generating early warning information comprising the first statistical result and the corresponding first statistical result threshold range.
7. The utility model provides a wind control device based on knowledge graph which characterized in that includes:
the first data acquisition module is used for acquiring data of a historical insurance case related to a target health insurance service and first knowledge graph data of service knowledge data related to the target health insurance service, and taking the data of the historical insurance case and the first knowledge graph data as data to be processed;
the second data acquisition module is used for constructing a target claim management and wind control knowledge graph body according to the ontology construction requirement, and acquiring ontology field data contained in the target claim management and wind control knowledge graph body and ontology association relations among the target claim management and wind control knowledge graph bodies from the data to be processed;
the auxiliary diagnosis recognition module is used for inputting the disease description content data of the target claim management and control knowledge graph body into a trained auxiliary diagnosis entity recognition model and outputting a corresponding auxiliary diagnosis recognition result, wherein the auxiliary diagnosis recognition result comprises a disease entity and/or an inspection entity and/or a treatment entity;
the claim settlement wind control knowledge graph module is used for importing the target claim settlement wind control knowledge graph body, the body association relationship and the auxiliary diagnosis recognition result into a preset first graph database to obtain a target claim settlement wind control knowledge graph;
The claim settlement wind control model module is used for constructing a target knowledge spectrum claim settlement wind control model according to the target claim settlement wind control knowledge spectrum and the decision tree model;
the third data acquisition module is used for acquiring information data of the gray list user identified by the inauguration wind control model as data to be judged, wherein the inauguration wind control model is an artificial intelligent claim settlement wind control model constructed based on XGBoost, and the information data of the gray list user cannot be identified by the inauguration wind control model as either black list user information data or white list user information data;
and the claim risk judging module is used for inputting the information data of the gray list user to the target knowledge graph claim wind control model and outputting a target claim risk judging result corresponding to the gray list user.
8. The knowledge-graph-based wind control apparatus of claim 7, wherein the claim risk determination module further comprises:
the gray list user data sub-module is used for acquiring corresponding gray list user history case data according to the unique user codes of the gray list users;
the first map relation sub-module is used for judging a first map relation between the current risk content of the gray list user and the historical case data of the gray list user according to the target claim risk knowledge map;
And the claim risk calculation sub-module is used for calculating the target claim risk judgment result of the gray list user according to the first map relation and the target claim wind control knowledge map by the decision tree model.
9. Computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the knowledge-graph based wind control method according to any of claims 1 to 6 when the computer program is executed.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the knowledge-graph based wind control method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310293468.3A CN116308823A (en) | 2023-03-23 | 2023-03-23 | Knowledge graph-based wind control method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310293468.3A CN116308823A (en) | 2023-03-23 | 2023-03-23 | Knowledge graph-based wind control method and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116308823A true CN116308823A (en) | 2023-06-23 |
Family
ID=86779525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310293468.3A Pending CN116308823A (en) | 2023-03-23 | 2023-03-23 | Knowledge graph-based wind control method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116308823A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934507A (en) * | 2023-09-19 | 2023-10-24 | 国任财产保险股份有限公司 | Intelligent claim settlement method and system based on big data driving |
| 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 |
-
2023
- 2023-03-23 CN CN202310293468.3A patent/CN116308823A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934507A (en) * | 2023-09-19 | 2023-10-24 | 国任财产保险股份有限公司 | Intelligent claim settlement method and system based on big data driving |
| CN116934507B (en) * | 2023-09-19 | 2023-12-26 | 国任财产保险股份有限公司 | Intelligent claim settlement method and system based on big data driving |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111309822B (en) | User identity recognition method and device | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| CN111383102A (en) | Financial credit risk identification method, model construction method and device | |
| Alqahtani et al. | Sv-af—a security vulnerability analysis framework | |
| CN113379301A (en) | Method, device and equipment for classifying users through decision tree model | |
| CN116308823A (en) | Knowledge graph-based wind control method and related equipment | |
| CN112801773A (en) | Enterprise risk early warning method, device, equipment and storage medium | |
| US20230350862A1 (en) | Methods and systems for data management, integration, and interoperability | |
| CN115130887B (en) | Reservoir dam environmental impact evaluation method and device, electronic equipment and storage medium | |
| CN116401379A (en) | Financial product data pushing method, device, equipment and storage medium | |
| CN116703682B (en) | Government affair data platform based on deep learning | |
| CN117035416A (en) | Enterprise risk assessment method, enterprise risk assessment device, equipment and storage medium | |
| CN117034273A (en) | Android malicious software detection method and system based on graph rolling network | |
| CN115795345A (en) | Information processing method, device, equipment and storage medium | |
| CN111241297A (en) | Map data processing method and device based on label propagation algorithm | |
| KR20200112495A (en) | Server and method for providing commercial analysis services | |
| CN115375370A (en) | Patent pricing evaluation method, device, computer equipment and medium | |
| CN111429257B (en) | Transaction monitoring method and device | |
| CN114493903A (en) | Damage assessment model optimization method in injury risk assessment and related equipment | |
| Kaur et al. | A fuzzy approach for estimating quality of aspect oriented systems | |
| CN113094595A (en) | Object recognition method, device, computer system and readable storage medium | |
| CN112765236A (en) | Adaptive abnormal equipment mining method, storage medium, equipment and system | |
| CN114707488B (en) | Data processing method, device, computer equipment and storage medium | |
| US20090228232A1 (en) | Range-based evaluation | |
| CN114881755B (en) | Commodity origin rule auditing method and system |
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 |