CN111967999A - Investigation processing method, device, computer equipment and storage medium - Google Patents
Investigation processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111967999A CN111967999A CN202010880983.8A CN202010880983A CN111967999A CN 111967999 A CN111967999 A CN 111967999A CN 202010880983 A CN202010880983 A CN 202010880983A CN 111967999 A CN111967999 A CN 111967999A
- Authority
- CN
- China
- Prior art keywords
- case
- survey
- investigation
- risk
- calling
- 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
- 238000011835 investigation Methods 0.000 title claims abstract description 208
- 238000003672 processing method Methods 0.000 title abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012986 modification Methods 0.000 claims abstract description 13
- 230000004048 modification Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012502 risk assessment Methods 0.000 claims description 18
- 238000013210 evaluation model Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 238000012550 audit Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 201000008383 nephritis Diseases 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to artificial intelligence and provides a survey processing method, a device, computer equipment and a storage medium. The method comprises the following steps: when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case; creating a calling event according to the risk portrait label of the claim case, and generating an investigation case; setting investigation factors for each calling up event in the investigation case according to the claim settlement case information, and generating an investigation plan corresponding to each calling up item; when the execution of all the survey plans is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plans and survey factors; and receiving the modification of the preliminary survey report to obtain a final survey report of the claim case. By adopting the method, the investigators do not need to spend a large amount of time to make plans and write reports, and the investigation efficiency and the claim settlement efficiency are improved.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method and an apparatus for processing a survey, a computer device, and a storage medium.
Background
With the importance of insurance, more and more people have insurance purchasing requirements, and correspondingly, insurance claims are increased. The insurance settlement refers to the action of paying off or paying responsibility by an insurance company according to contract regulations when the insurance target has an insurance accident and the property of the insured person is lost or the life of the insured person is damaged or other insurance accidents appointed by the policy are carried out and insurance funds need to be paid out, and the action directly embodies the insurance function and the insurance responsibility. The investigation is an important process of insurance claim settlement, which refers to the case processing personnel combining insurance terms and accident occurrence processes, and in the case processing process, the investigation and the visit, evidence data collection and other claim settlement work are performed for further clearing facts and determining insurance responsibility. Therefore, the efficiency of the investigation often determines the efficiency of the claim settlement.
In a traditional investigation mode, after receiving a investigation task, investigators need to spend a lot of time on making a investigation plan and write a investigation report, so that the investigation period is long and the investigation efficiency is low.
Disclosure of Invention
In view of the above, it is desirable to provide a survey processing method, a device, a computer apparatus, and a storage medium capable of improving survey efficiency.
A method of survey processing, the method comprising:
when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case;
creating a calling event according to the risk portrait label of the claim case, and generating an investigation case;
setting investigation factors for each calling up event in the investigation case according to the claim settlement case information, and generating an investigation plan corresponding to each calling up item;
when the execution of the survey plan is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plan and survey factors;
and receiving the modification of the preliminary survey report to obtain a final survey report of the claim case.
In one embodiment, the method for analyzing the claim case information and acquiring the risk portrait label of the claim case comprises the following steps:
and inputting the claim case information into a pre-trained claim risk evaluation model, identifying risk content in the claim case information through the claim risk evaluation model, and outputting a risk portrait label of the claim case.
In one embodiment, creating an event of calling and generating a survey case according to the risk profile label of the claim case comprises:
acquiring case-related dangerous species of the claim settlement cases;
determining a calling event corresponding to the risk portrait label related to the case risk according to the mapping relation between the risk portrait label and each dangerous calling event;
and creating an investigation case corresponding to the claim case according to the calling up event.
In one embodiment, the way of training the claim risk assessment model includes:
querying historical claims, taking claims with risk point marks in the historical claims as positive samples, and obtaining risk point mark columns of the positive sample claims;
taking the claim cases without risk point marks in the historical claim cases as negative samples;
obtaining a training sample set according to the positive sample and the negative sample;
and training a semantic model according to the training sample set to obtain the trained claim risk assessment model.
In one embodiment, the survey factors include time, place, and object; setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item, wherein the investigation plan comprises the following steps:
extracting places and objects matched with the content of the calling event from the claim case information;
allocating investigation time according to the investigation sequence of the calling events;
and generating a survey plan of each calling event according to the time, the place and the object.
In one embodiment, when the survey plan is executed, whether the actually executed survey plan is consistent with the planned survey plan is checked according to the positioning information, and if not, the operation prompt is generated.
In one embodiment, after the execution of all the survey plans of the claim cases is finished, the operation tracks of the surveyors are generated according to the survey places where the survey plans are actually executed, and whether the operation of the surveyors meets the specifications or not is evaluated according to the operation tracks.
A survey processing apparatus, the apparatus comprising:
the risk portrait label module is used for analyzing the claim settlement case information and acquiring a risk portrait label of the claim settlement case when the claim settlement request is acquired;
the investigation case generation module is used for creating an extraction event according to the risk portrait label of the claim case and generating an investigation case;
the investigation plan generating module is used for setting investigation factors for each calling up event in the investigation case according to the claim settlement case information and generating an investigation plan corresponding to each calling up item;
the survey processing module is used for generating a preliminary survey report according to the execution time of the survey plan and survey factors when the survey plan is executed;
and the report generation module is used for receiving the modification of the preliminary investigation report to obtain a final investigation report of the claim case.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case;
creating a calling event according to the risk portrait label of the claim case, and generating an investigation case;
setting investigation factors for each calling up event in the investigation case according to the claim settlement case information, and generating an investigation plan corresponding to each calling up item;
when the execution of the survey plan is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plan and survey factors;
and receiving the modification of the preliminary survey report to obtain a final survey report of the claim case.
A computer storage medium having a computer program stored thereon, the computer program when executed by a processor implementing the steps of:
when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case;
creating a calling event according to the risk portrait label of the claim case, and generating an investigation case;
setting investigation factors for each calling up event in the investigation case according to the claim settlement case information, and generating an investigation plan corresponding to each calling up item;
when the execution of the survey plan is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plan and survey factors;
and receiving the modification of the preliminary survey report to obtain a final survey report of the claim case.
According to the investigation processing method, the investigation processing device, the computer equipment and the storage medium, when a claim request is obtained, the risk portrait label of the claim case is obtained by analyzing the claim case information, the calling event of the claim investigation is created according to the risk portrait label, the investigation case is generated, investigation factors are set for each calling event in the investigation case, an investigation plan is generated, after the investigation plan is completed, an investigation report is preliminarily generated, and then the final investigation report is obtained by modifying on the basis of the preliminary investigation report. According to the method, the investigation items are automatically generated according to the pre-established standard, so that the operation of the investigator is facilitated, the investigator is helped to complete the investigation plan step by step, the preliminary investigation report is automatically formed according to the investigation, and the investigator can obtain the final investigation report by modifying the preliminary investigation report, so that the investigator does not need to spend a large amount of time for making the plan and writing the report, and the investigation efficiency and the claim settlement efficiency are improved.
Drawings
FIG. 1 is a diagram of an application scenario of a survey processing method in one embodiment;
FIG. 2 is a schematic flow diagram of a survey processing method in one embodiment;
FIG. 3 is a block diagram of an exemplary survey processing apparatus;
FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The investigation processing method provided by the application can be applied to the application environment shown in fig. 1. The survey terminal 102 and the server 104 communicate with each other via a network, and the claim audit terminal 106 and the server 104 communicate with each other via the network. When a claim occurs, after the claim checking terminal 106 operates and checks, the server 104 generates a survey event and distributes the survey event to the investigator for processing, and the investigator feeds back a survey result through the operation of the investigation terminal 102 during the survey process to generate a survey report by the server. Specifically, when the server acquires a claim settlement request, the server analyzes the claim settlement case information and acquires a risk portrait label of the claim settlement case; creating a calling event according to the risk portrait label of the claim case, and generating an investigation case; setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item; when the execution of the survey plan is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plan and survey factors; modifications to the preliminary survey report are received, resulting in a final survey report of the claim case. The investigation terminal 102 and the claim audit terminal 106 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a method for processing a survey is provided, which is described by taking the method as an example for being applied to the server in fig. 1, and includes the following steps:
step 202, when the claim settlement request is obtained, the information of the claim settlement case is analyzed, and the risk portrait label of the claim settlement case is obtained.
After the claim settlement request occurs, the system acquires the claim settlement case information, including insurance purchase records, payment records, certification materials provided for insurance, and the like. And acquiring the risk portrait label of the claim case by analyzing the claim case information.
The risk portrait label refers to the risk points of the case analyzed according to the claim case information. Generally, there are items in the insurance field that are inherently considered to be risky, i.e., points of risk. Common risk points include first year insurance, new insurance, additional insurance, continuous insurance and substantial adjustment of the insurance amount, continuous insurance and continuous insurance application for less than two years, false material risk, imposition risk and the like. When the claim auditing personnel audit, the claim case information needs to be analyzed to confirm whether the risk points exist in the claim case. If the risk points exist, the risk points need to be marked and are important to be investigated by investigators.
In this embodiment, the system sets risk portrait tags for each dangerous type in advance, and when a new claim settlement request is obtained, obtains risk portrait tags of a claim settlement case according to claim settlement case information. The risk portrait label is the risk point. Based on the risk image label, the risk points of the claim case can be determined.
It can be understood that the emphasis of different dangerous species is different, and the labels of the risk portrayal are also different. For example, the severe risk emphasizes serious diseases, and the risk is large, so the risk portrait label includes first year insurance, new insurance, additional insurance, continuous insurance and large adjustment of the insurance.
In one embodiment, the insurance auditor can manually label the claim case with the risk portrait label after reading the information of the claim case. If all risk points are listed in the audit interface, after the insurance auditor manually selects the risk points according to the situation, the risk portrait label of the claim case is marked.
In one embodiment, the trained claim risk assessment model is used by the system to label the claim case with a risk portrait label. The method does not need manual participation and can greatly improve the portrait efficiency.
And step 204, creating a tone raising event according to the risk portrait label of the claim case, and generating an investigation case.
The calling event refers to the content of claims to be checked. Aiming at different risk types and different risk portrait labels, the set calling events are different, and the system automatically lists the contents to be investigated according to the risk portrait labels and the claim risk types of the claim case to generate the investigation case.
It can be understood that, for the case without risk, the corresponding pitch event is a regular pitch event. The system automatically lists the contents which need to be investigated regularly according to the claim risk types of the claim cases to generate investigation cases.
That is, each claim case has conventional reconciliation events, such as verifying the authenticity of the beneficiary information and transfer authorization information. The calling events of the claim cases with the risk portrait labels are added on the basis of the conventional calling events, and the calling events for checking risk points are added.
The investigation case corresponds to the claim settlement case, and the investigation result of the investigation case is the basis of the claim settlement case. For example, if the investigation result presented by the investigation case is that the claim case is a cheated insurance with diseases, no claim is required for the claim case. If the investigation result presented by the investigation case is that the claim settlement case is true and has no abnormal condition, the corresponding claim settlement case should be normally carried out.
The investigation cases are distributed to the investigators for processing, and the investigators sequentially perform investigation according to the listed event, so as to form investigation conclusions of the claim cases.
The risk portrait label and the calling event of each dangerous type are pre-established with a mapping relation, and after the risk portrait label of the claim case is determined, the corresponding calling event generates the investigation case according to the mapping relation.
Specifically, creating a calling event according to the risk portrait label of the claim case, and generating an investigation case, wherein the creating comprises: acquiring case-related dangerous species of claim cases; determining a calling event corresponding to the risk portrait label related to the case according to the mapping relation between the risk portrait label and each dangerous type calling event; and creating a survey case corresponding to the claim case according to the lifting and adjusting event.
Wherein, the related case risk is the insurance variety bought and presented by the claim settlement client. The mapping relation between the risk portrait label and each dangerous type calling event is preset, the system automatically matches the calling event corresponding to the risk portrait label of the dangerous type according to the risk portrait label, and creates an investigation case corresponding to the claim settlement case according to the calling event. For example, a risk profile label of a health risk includes first year risk and corresponding event of calling up is a medical history.
When the extraction event is generated, the risk remark of the extraction event is generated according to the claim settlement data so as to explain the risk condition of the extraction event. For example, a risk portrait label of health risks includes first year risks, corresponding adjustment events are investigation medical histories, and remarks are made according to medical history data of the adjustment events of the investigation medical histories (3 years ago recorded by the medical history, and the medical history recorded by the medical history is hospitalized in Nanjing hospital due to nephritis).
And step 206, setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item.
Survey factors refer to some information involved in implementing a survey including, but not limited to, survey location, survey subject and survey point, i.e., where and what content is surveyed for what event. The survey location, the survey subject, and the survey point constitute survey factors.
Specifically, a place and an object which are matched with the content of the extracted event are extracted from the claim case information; allocating investigation time according to the investigation sequence of the calling events; a survey plan for each lift event is generated based on time, location, and subject.
And if the calling event refers to the content to be investigated lifted by the claim, extracting the place and the object matched with the investigation content from the claim case information. The matching can be searched according to the semantic understanding of the keywords. Setting some keywords according to the investigation content of the calling event in advance, searching candidate information in the information of the claim case according to the keywords, performing semantic understanding on the candidate information, and analyzing whether the candidate information is matched with the investigation content of the calling event. If so, extracting the place and the object. For example, the event of calling a claim case for a serious illness is the medical institution for taking an insurance check, and the corresponding investigation content is the medical institution for being diagnosed by the insured person for checking. Corresponding keywords include "confirmed diagnosis", "hospital", and the like. And further, performing semantic analysis on the medical record or the examination report of the hospital according to the candidate information matched by the keyword, and determining whether the candidate information is matched with the calling event 'emergency medical institution examination'. Or matching, determining the name and department of the hospital with the medical record or the examination report, and obtaining the investigation place and the investigation object.
Where the semantic analysis may utilize a pre-trained semantic model. And respectively training a semantic understanding model for each type of the calling events in advance, and identifying semantic features required by the investigation content of each calling event.
Furthermore, the survey time is distributed according to the survey sequence of the dispatching events, and a survey plan of each dispatching event is formed. In the embodiment, the investigation factors are matched and extracted from the claim cases, and the investigation plan of the calling up event is automatically generated, so that the investigation processing efficiency is improved.
Each calling event corresponds to a survey plan, the survey plan refers to the content of how the calling events are implemented, all survey factors of one calling event form the survey plan, the names of the survey plans are fixed, and for example, the calling events for examining medical histories correspond to the survey plans for surveying in the medical institutions at risk.
Specifically, in order to facilitate the investigators to know the actual situation of the claim cases when viewing the investigation plan, the investigation plan is displayed, and meanwhile, a viewing tag of the investigation plan is also set, so that case information of investigation content related to the adjustment event in the claim case information is hidden in the viewing tag. When the investigator triggers to view the tag, the investigation content related to the pitch event is displayed. For example, one event of the event is the medical record or the examination report of the medical institution of the event, the medical record or the examination report is hidden in the examination tag, and when the examining tag is triggered by an investigator, the information of the claim case matched with the investigation plan can be obtained.
In this embodiment, look over the label through setting up and link investigation case information, have very big convenience, make things convenient for the investigator to know the case condition fast.
And step 208, when the execution of the survey plan is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plan and the survey factors.
When an investigator performs a survey plan at a survey location, the completion of the survey plan may be triggered by operation at the terminal. The survey plans are arranged in sequence, and when one adjustment plan is completed, the next survey plan can be unlocked. And after the execution of all the survey plans of one survey case is finished, calling a preset template according to the execution time and survey factors of each survey plan to generate a preliminary survey report.
After the execution of the survey plan is completed, a survey log of the survey plan is generated. The survey log records a survey plan ID, a survey plan execution time, and the like. And when all survey plans are executed, generating a preliminary survey report according to all survey logs of the claim cases and survey factors of the survey plans.
Step 210, receiving the modification to the preliminary survey report, and obtaining the final survey report of the claim case.
The preliminary survey report comprises the execution time, the survey location, the survey subject and the survey content of each survey plan, the preliminary survey report provides a basis for filling the survey report for the surveyors, and the surveyors add survey conclusions on the basis of the preliminary survey report to obtain a final survey report.
According to the investigation processing method, when a claim request is obtained, the risk portrait label of the claim case is obtained by analyzing the claim case information, the adjustment event of the claim investigation is created according to the risk portrait label, the investigation case is generated, investigation factors are set for each adjustment event in the investigation case, an investigation plan is generated, after the investigation plan is completed, an investigation report is generated preliminarily, and then the final investigation report is obtained by modifying on the basis of the preliminary investigation report. According to the method, the investigation items are automatically generated according to the pre-established standard, so that the operation of the investigator is facilitated, the investigator is helped to complete the investigation plan step by step in a standard manner, the preliminary investigation report is automatically formed according to the investigation, and the investigator can obtain the final investigation report by modifying the preliminary investigation report, so that the investigator does not need to spend a large amount of time for planning and writing the report, and the investigation efficiency and the claim settlement efficiency are improved.
In another embodiment, the analyzing the claim case information and obtaining the risk profile label of the claim case comprises: and inputting the claim case information into a pre-trained claim risk evaluation model, identifying risk content in the claim case information through the claim risk evaluation model, and outputting a risk portrait label of the claim case.
Specifically, the risk assessment model is determined in advance based on artificial intelligence according to a large amount of historical claim data. The historical claims data are labeled with risk points of claims cases in advance, the category of risk portrait labels is set according to the risk points, and a risk assessment model is trained through a semantic model (such as BERT). The semantic model can well understand semantic information in the claim case, so that a risk portrait label of the claim case is determined.
The mode of training the claim risk assessment model comprises the following steps: querying historical claims, taking claims with risk point marks in the historical claims as positive samples, and obtaining risk point mark columns of the positive sample claims; taking the claim cases without risk point marks in the historical claim cases as negative samples; obtaining a training sample set according to the positive sample and the negative sample; and training the semantic model according to the training sample set to obtain a trained claim risk assessment model.
Specifically, after the claim case information is read by an auditor in the historical claim cases, the risk portrait labels are manually marked on the claim cases. The method comprises the steps of extracting the claim cases with various types of risk portrait labels and the claim cases without risk portrait labels proportionally from a large number of historical claim cases. Taking the claim cases with the risk point marks in the historical claim cases as positive samples, obtaining risk point posts of the claim cases with the positive samples, and taking the claim cases without the risk point marks in the historical claim cases as negative samples; and obtaining a training sample set according to the positive sample and the negative sample.
And training the semantic model according to the training sample set, wherein the semantic model can be LSTM or BERT and the like. Training and adjusting parameters of the semantic model by using the training sample set, and finally obtaining the trained claim risk assessment model.
Through obtaining the training sample set from historical claims case, need not a large amount of artifical marks, improved training efficiency.
In the actual use process, the claim case information is input into the claim risk evaluation model, the characteristics of the claim case information are identified by the claim risk evaluation model, the risk content in the claim case is identified, and the risk portrait label of the claim case is output.
In the embodiment, the trained claim risk assessment model is used for automatically identifying the claim case information, risk portrait labels are carried out on the claim cases, the risk points of the claim cases are identified, the risk points can be determined without manually referring to the claim information, and time for manually analyzing the risk points is saved.
Specifically, in order to facilitate an auditor to know the actual situation of a claim case when viewing the risk point, the risk portrait tag is displayed, the viewing tag corresponding to the risk portrait tag is also established, and the case fact corresponding to the risk portrait tag in the claim case information is hidden in the viewing tag. And when the auditor triggers to view the tag, displaying case facts corresponding to the risk portrait tag. For example, when a risk portrait tag is first year insurance, case facts corresponding to the tag can be extracted from case claim information, including insurance purchase date and insurance date, and the extracted case facts include "customer purchase accident in 1/2020 and insurance in 7/1/2020, which meets the first year insurance situation. The risk portrait label of "appearing in first year" is being displayed to "simultaneously, is provided with and looks over the label, hides this case fact in looking over the label, when the audit personnel triggered should look over the label, can obtain the actual conditions that the claim case and this risk portrait label match.
In this embodiment, look over the case fact that the label links the risk picture label through the setting, have very big convenience, make things convenient for the claim settlement personnel to know the case condition fast.
In another embodiment, when the survey plan is executed, whether the actually executed survey plan is consistent with the planned survey plan is checked according to the positioning information, and if not, the operation reminding is generated.
Specifically, all survey plans of one claim case are arranged in order, and each survey plan is provided with operation controls including "modify", "execute", and "cancel". When a certain survey plan is executed by a surveyor, an 'execution' control is triggered to indicate that the corresponding survey plan is being executed, namely, the survey plan is a survey plan scheduled to be executed.
As mentioned previously, survey plans have survey factor survey sites. For the claim case, there are a plurality of survey items, such as "medical institution for insurance" check "," on-site survey ", and the like. The investigation location of each investigation item is determined according to the case-related location of the claim case. When the investigator goes to the investigation place to investigate, the investigation plan of the planned execution is obtained by triggering the 'execution' control. The system acquires the positioning information of the investigator at the moment and checks whether the current position of the investigator is consistent with the investigation place of the investigation plan. By monitoring the positioning, false investigation by investigators can be avoided. And when the actually executed survey plan is inconsistent with the planned survey plan, generating a job reminder.
The operation reminding can help the investigators to standardize the investigation function, and the investigation operation can be monitored.
In another embodiment, after the execution of all the survey plans of the claim cases is completed, the operation tracks of the surveyors are generated according to the survey places where the survey plans are actually executed, and whether the operation of the surveyors meets the specifications is evaluated according to the operation tracks.
Specifically, when the survey plan is actually executed, the surveyor triggers the "execute" control, and the system acquires the location point and takes the current location point as the survey point where the survey plan is actually executed. After the execution of all the survey plans is completed, a work trajectory of the surveyor is generated from the survey point where the survey plan is actually executed, and the work trajectory can reflect the execution point and the execution order of the survey plan. The investigation order of the investigation work can also be analyzed by analyzing whether the investigation location of the operator coincides with the planned investigation location for the work trajectory. Therefore, whether the operation of the investigator meets the standard or not can be evaluated through the operation track, so that the investigation behavior of the investigator is standardized, and the investigation efficiency is improved.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 3, there is provided a survey processing apparatus comprising: a risk profile tagging module 302, a survey case generation module 304, a survey plan generation module 306, a survey processing module 308, and a report generation module 310, wherein:
the risk portrait label module 302 is configured to, when the claim settlement request is obtained, parse the claim settlement case information to obtain a risk portrait label of the claim settlement case.
The investigation case generation module 304 is configured to create an event of calling up and generate an investigation case according to the risk portrait label of the claim case.
And the survey plan generating module 306 is configured to set survey factors for each event in the survey case according to the claim case information, and generate a survey plan corresponding to each event.
And the survey processing module 308 is used for generating a preliminary survey report according to the execution time of the survey plan and the survey factors when the survey plan is completely executed.
A report generation module 310, configured to receive the modification to the preliminary survey report, and obtain a final survey report of the claim case.
When a claim request is acquired, the investigation processing device acquires a risk portrait label of a claim case by analyzing claim case information, creates an event for claim investigation according to the risk portrait label, generates an investigation case, sets investigation factors for each event in the investigation case, generates an investigation plan, generates an investigation report preliminarily after the investigation plan is completed, and then modifies the investigation report on the basis of the preliminary investigation report to obtain a final investigation report. According to the method, the investigation items are automatically generated according to the pre-established standard, so that the operation of the investigator is facilitated, the investigator is helped to complete the investigation plan step by step in a standard manner, the preliminary investigation report is automatically formed according to the investigation, and the investigator can obtain the final investigation report by modifying the preliminary investigation report, so that the investigator does not need to spend a large amount of time for planning and writing the report, and the investigation efficiency and the claim settlement efficiency are improved.
In another embodiment, the risk profile labeling module is configured to input the claim case information into a pre-trained claim risk assessment model, identify risk content in the claim case information through the claim risk assessment model, and output the risk profile label of the claim case.
In another embodiment, the survey case generation module comprises:
and the dangerous type determining module is used for acquiring the dangerous type involved in the claim case.
And the searching module is used for determining the calling events corresponding to the risk portrait labels related to the case types according to the mapping relation between the risk portrait labels and various dangerous calling events.
And the creating module is used for creating an investigation case corresponding to the claim case according to the lifting and adjusting event.
In another embodiment, the method further comprises:
the sample set acquisition module is used for inquiring historical claim cases, taking the claim cases with risk point marks in the historical claim cases as positive samples, and acquiring risk point mark columns of the positive sample claim cases; taking the claim cases without risk point marks in the historical claim cases as negative samples; and obtaining a training sample set according to the positive sample and the negative sample.
And the training module is used for training a semantic model according to the training sample set to obtain the trained claim risk assessment model.
In another embodiment, the survey factors include time, place, and object. The survey plan generating module is used for extracting places and objects matched with the content of the calling events from the claim case information; allocating investigation time according to the investigation sequence of the calling events; and generating a survey plan of each calling event according to the time, the place and the object.
In another embodiment, the system further comprises a positioning supervision module, which is used for checking whether the actually executed survey plan is consistent with the planned survey plan according to the positioning information when the survey plan is executed, and if not, generating a job reminder.
In another embodiment, the system further comprises a survey track supervision module, which is used for generating a work track of an investigator according to a survey place where the survey plan is actually executed after the execution of all survey plans of the claim cases is finished, and evaluating whether the work of the investigator meets the specification according to the work track.
For specific limitations of the survey processing apparatus, reference may be made to the above limitations of the survey processing method, which are not described herein again. The respective modules in the above-described survey processing apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the 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 comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing survey processing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a survey processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case;
creating a calling event according to the risk portrait label of the claim case, and generating an investigation case;
setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item;
when the execution of all the survey plans is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plans and survey factors;
modifications to the preliminary survey report are received, resulting in a final survey report of the claim case.
In one embodiment, the method for analyzing the claim case information and acquiring the risk portrait label of the claim case comprises the following steps:
and inputting the claim case information into a pre-trained claim risk evaluation model, identifying risk content in the claim case information through the claim risk evaluation model, and outputting a risk portrait label of the claim case.
In one embodiment, creating a calling event according to the risk profile label of the claim case, and generating a survey case comprises:
acquiring case-related dangerous species of claim cases;
determining a calling event corresponding to the risk portrait label related to the case according to the mapping relation between the risk portrait label and each dangerous type calling event;
and creating a survey case corresponding to the claim case according to the lifting and adjusting event.
In one embodiment, the way to train the claim risk assessment model includes:
querying historical claims, taking claims with risk point marks in the historical claims as positive samples, and obtaining risk point mark columns of the positive sample claims;
taking the claim cases without risk point marks in the historical claim cases as negative samples;
obtaining a training sample set according to the positive sample and the negative sample;
and training the semantic model according to the training sample set to obtain a trained claim risk assessment model.
In one embodiment, the survey factors include time, place, and object; setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item, wherein the investigation plan comprises the following steps:
extracting places and objects matched with the content of the extracted event from the claim case information;
allocating investigation time according to the investigation sequence of the calling events;
and generating a survey plan of each calling event according to the time, the place and the object.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and when the survey plan is executed, whether the actually executed survey plan is consistent with the planned survey plan is checked according to the positioning information, and if not, the operation prompt is generated.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
after the execution of all the investigation plans of the claim cases is finished, generating the operation track of the investigator according to the investigation place where the investigation plan is actually executed, and evaluating whether the operation of the investigator meets the specification or not according to the operation track.
In one embodiment, a computer storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of:
when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case;
creating a calling event according to the risk portrait label of the claim case, and generating an investigation case;
setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item;
when the execution of all the survey plans is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plans and survey factors;
modifications to the preliminary survey report are received, resulting in a final survey report of the claim case.
In one embodiment, the method for analyzing the claim case information and acquiring the risk portrait label of the claim case comprises the following steps:
and inputting the claim case information into a pre-trained claim risk evaluation model, identifying risk content in the claim case information through the claim risk evaluation model, and outputting a risk portrait label of the claim case.
In one embodiment, creating a calling event according to the risk profile label of the claim case, and generating a survey case comprises:
acquiring case-related dangerous species of claim cases;
determining a calling event corresponding to the risk portrait label related to the case according to the mapping relation between the risk portrait label and each dangerous type calling event;
and creating a survey case corresponding to the claim case according to the lifting and adjusting event.
In one embodiment, the way to train the claim risk assessment model includes:
querying historical claims, taking claims with risk point marks in the historical claims as positive samples, and obtaining risk point mark columns of the positive sample claims;
taking the claim cases without risk point marks in the historical claim cases as negative samples;
obtaining a training sample set according to the positive sample and the negative sample;
and training the semantic model according to the training sample set to obtain a trained claim risk assessment model.
In one embodiment, the survey factors include time, place, and object; setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item, wherein the investigation plan comprises the following steps:
extracting places and objects matched with the content of the extracted event from the claim case information;
allocating investigation time according to the investigation sequence of the calling events;
and generating a survey plan of each calling event according to the time, the place and the object.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and when the survey plan is executed, whether the actually executed survey plan is consistent with the planned survey plan is checked according to the positioning information, and if not, the operation prompt is generated.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
after the execution of all the investigation plans of the claim cases is finished, generating the operation track of the investigator according to the investigation place where the investigation plan is actually executed, and evaluating whether the operation of the investigator meets the specification or not according to the operation track.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile 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), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of survey processing, the method comprising:
when a claim settlement request is obtained, analyzing the claim settlement case information and obtaining a risk portrait label of the claim settlement case;
creating a calling event according to the risk portrait label of the claim case, and generating an investigation case;
setting investigation factors for each calling up event in the investigation case according to the claim settlement case information, and generating an investigation plan corresponding to each calling up item;
when the execution of the survey plan is finished, generating a preliminary survey report of the claim case according to the execution time of the survey plan and survey factors;
and receiving the modification of the preliminary survey report to obtain a final survey report of the claim case.
2. The method of claim 1, wherein analyzing the claim case information to obtain the risk profile label of the claim case comprises:
and inputting the claim case information into a pre-trained claim risk evaluation model, identifying risk content in the claim case information through the claim risk evaluation model, and outputting a risk portrait label of the claim case.
3. The method of claim 1, wherein creating a reconciliation event from the risk profile label of the claim case, generating a survey case comprises:
acquiring case-related dangerous species of the claim settlement cases;
determining a calling event corresponding to the risk portrait label related to the case risk according to the mapping relation between the risk portrait label and each dangerous calling event;
and creating an investigation case corresponding to the claim case according to the calling up event.
4. The method of claim 2, wherein training the claims risk assessment model comprises:
querying historical claims, taking claims with risk point marks in the historical claims as positive samples, and obtaining risk point mark columns of the positive sample claims;
taking the claim cases without risk point marks in the historical claim cases as negative samples;
obtaining a training sample set according to the positive sample and the negative sample;
and training a semantic model according to the training sample set to obtain the trained claim risk assessment model.
5. The method of claim 1, wherein the survey factors include time, location, and object; setting investigation factors for each calling event in the investigation case according to the claim case information, and generating an investigation plan corresponding to each calling item, wherein the investigation plan comprises the following steps:
extracting places and objects matched with the content of the calling event from the claim case information;
allocating investigation time according to the investigation sequence of the calling events;
and generating a survey plan of each calling event according to the time, the place and the object.
6. The method according to claim 1, wherein when the survey plan is executed, whether the actually executed survey plan is consistent with the planned survey plan is checked based on the positioning information, and if not, the job reminder is generated.
7. The method according to claim 1, wherein after execution of all the survey plans of the claim cases is completed, a work trajectory of the investigator is generated according to a survey site where the survey plans are actually executed, and whether or not the work of the investigator meets specifications is evaluated according to the work trajectory.
8. A survey processing apparatus, the apparatus comprising:
the risk portrait label module is used for analyzing the claim settlement case information and acquiring a risk portrait label of the claim settlement case when the claim settlement request is acquired;
the investigation case generation module is used for creating an extraction event according to the risk portrait label of the claim case and generating an investigation case;
the investigation plan generating module is used for setting investigation factors for each calling up event in the investigation case according to the claim settlement case information and generating an investigation plan corresponding to each calling up item;
the survey processing module is used for generating a preliminary survey report according to the execution time of the survey plan and survey factors when the survey plan is executed;
and the report generation module is used for receiving the modification of the preliminary investigation report to obtain a final investigation report of the claim case.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer storage medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010880983.8A CN111967999A (en) | 2020-08-27 | 2020-08-27 | Investigation processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010880983.8A CN111967999A (en) | 2020-08-27 | 2020-08-27 | Investigation processing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111967999A true CN111967999A (en) | 2020-11-20 |
Family
ID=73399577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010880983.8A Pending CN111967999A (en) | 2020-08-27 | 2020-08-27 | Investigation processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967999A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507141A (en) * | 2020-12-01 | 2021-03-16 | 平安医疗健康管理股份有限公司 | Investigation task generation method and device, computer equipment and storage medium |
| CN112767180A (en) * | 2021-01-06 | 2021-05-07 | 大童保险销售服务有限公司 | Method and device for generating insurance case public estimation report and storage medium |
| CN114218453A (en) * | 2021-12-14 | 2022-03-22 | 中国平安财产保险股份有限公司 | Data display method, device and equipment and readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700183A (en) * | 2013-12-06 | 2015-06-10 | 大连灵动科技发展有限公司 | Accident management method of commanding and training drill system |
| CN106355319A (en) * | 2016-08-26 | 2017-01-25 | 南京安全无忧网络科技有限公司 | Safety risk assessment system and method |
| CN107909299A (en) * | 2017-12-11 | 2018-04-13 | 凯泰铭科技（北京）有限公司 | People hinders Claims Resolution data risk checking method and system |
| CN108335215A (en) * | 2017-06-26 | 2018-07-27 | 平安科技（深圳）有限公司 | Case Claims Resolution method, server and computer readable storage medium |
| CN109035030A (en) * | 2017-06-12 | 2018-12-18 | 平安科技（深圳）有限公司 | case investigation method, server and computer readable storage medium |
| CN109410029A (en) * | 2018-09-04 | 2019-03-01 | 深圳市佰仟金融服务有限公司 | A kind of anti-fraud investigation method and system towards financial field |
| CN109523118A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Risk data screening technique, device, computer equipment and storage medium |
| CN110246032A (en) * | 2019-06-21 | 2019-09-17 | 深圳前海微众银行股份有限公司 | Risk monitoring and control method, apparatus and computer readable storage medium after loan |
| CN110349038A (en) * | 2019-06-13 | 2019-10-18 | 中国平安人寿保险股份有限公司 | Risk evaluation model training method and methods of risk assessment |
-
2020
- 2020-08-27 CN CN202010880983.8A patent/CN111967999A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700183A (en) * | 2013-12-06 | 2015-06-10 | 大连灵动科技发展有限公司 | Accident management method of commanding and training drill system |
| CN106355319A (en) * | 2016-08-26 | 2017-01-25 | 南京安全无忧网络科技有限公司 | Safety risk assessment system and method |
| CN109035030A (en) * | 2017-06-12 | 2018-12-18 | 平安科技（深圳）有限公司 | case investigation method, server and computer readable storage medium |
| CN108335215A (en) * | 2017-06-26 | 2018-07-27 | 平安科技（深圳）有限公司 | Case Claims Resolution method, server and computer readable storage medium |
| CN107909299A (en) * | 2017-12-11 | 2018-04-13 | 凯泰铭科技（北京）有限公司 | People hinders Claims Resolution data risk checking method and system |
| CN109410029A (en) * | 2018-09-04 | 2019-03-01 | 深圳市佰仟金融服务有限公司 | A kind of anti-fraud investigation method and system towards financial field |
| CN109523118A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Risk data screening technique, device, computer equipment and storage medium |
| CN110349038A (en) * | 2019-06-13 | 2019-10-18 | 中国平安人寿保险股份有限公司 | Risk evaluation model training method and methods of risk assessment |
| CN110246032A (en) * | 2019-06-21 | 2019-09-17 | 深圳前海微众银行股份有限公司 | Risk monitoring and control method, apparatus and computer readable storage medium after loan |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507141A (en) * | 2020-12-01 | 2021-03-16 | 平安医疗健康管理股份有限公司 | Investigation task generation method and device, computer equipment and storage medium |
| CN112767180A (en) * | 2021-01-06 | 2021-05-07 | 大童保险销售服务有限公司 | Method and device for generating insurance case public estimation report and storage medium |
| CN114218453A (en) * | 2021-12-14 | 2022-03-22 | 中国平安财产保险股份有限公司 | Data display method, device and equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767322B (en) | Suspicious transaction analysis method and device based on big data and computer equipment | |
| US10176526B2 (en) | Processing system for data elements received via source inputs | |
| CN111967999A (en) | Investigation processing method, device, computer equipment and storage medium | |
| WO2021004132A1 (en) | Abnormal data detection method, apparatus, computer device, and storage medium | |
| US11710203B2 (en) | Apparatus and method for generating title products | |
| US9026467B2 (en) | Systems and methods for monitoring and detecting fraudulent uses of business applications | |
| US20070294271A1 (en) | Systems and methods for monitoring and detecting fraudulent uses of business applications | |
| US10445697B2 (en) | System for selection of data records containing structured and unstructured data | |
| CN110729054B (en) | Abnormal diagnosis behavior detection method and device, computer equipment and storage medium | |
| US9978031B2 (en) | Systems and methods for monitoring and detecting fraudulent uses of business applications | |
| US11675750B2 (en) | User generated tag collection system and method | |
| CN112036795A (en) | Method, device, equipment and storage medium for determining medicine purchasing plan | |
| CN109741035A (en) | Data processing method, device, computer equipment and storage medium | |
| CN110442713A (en) | Abstract generation method, apparatus, computer equipment and storage medium | |
| Nagbe et al. | Integrated disease surveillance and response implementation in Liberia, findings from a data quality audit, 2017 | |
| Raman | Operational risk management in Indian banks in the context of Basel II: A survey of the state of preparedness and challenges in developing the framework | |
| CN114201090A (en) | Product production abnormity early warning system, method, computer equipment and storage medium | |
| CN112669039B (en) | Knowledge graph-based customer risk management and control system and method | |
| CN112650659B (en) | Buried point setting method and device, computer equipment and storage medium | |
| CN112086175A (en) | Medical price charge monitoring method, system, computer equipment and storage medium | |
| CN112836041A (en) | Personnel relationship analysis method, device, equipment and storage medium | |
| US10235716B2 (en) | System for generating historical hail evaluation data | |
| CN115587898A (en) | Cloud service-based financial data secure sharing method and system | |
| CN113177396B (en) | Report generation method and device, computer equipment and storage medium | |
| CN114819896A (en) | AI-based bill management system, method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201120 |