CN111292159A - Method and system for calculating claim payment amount based on multi-factor influence - Google Patents
Method and system for calculating claim payment amount based on multi-factor influence Download PDFInfo
- Publication number
- CN111292159A CN111292159A CN202010055156.5A CN202010055156A CN111292159A CN 111292159 A CN111292159 A CN 111292159A CN 202010055156 A CN202010055156 A CN 202010055156A CN 111292159 A CN111292159 A CN 111292159A
- Authority
- CN
- China
- Prior art keywords
- user
- request
- historical
- preset
- reimbursement
- 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
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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The application discloses a method and a system for calculating a claim payment amount based on multi-factor influence, which relate to the technical field of data processing and comprise the following steps: acquiring a claim request of a user, wherein the claim request comprises user information and current order information; acquiring historical order information and historical claim payment information of a user; if the claim request of the user does not accord with the preset claim rule, ignoring the claim request; if the claim request of the user accords with a preset claim rule, discretizing the historical order information, and determining a training model according to the historical claim information and the discretized historical order information; discretizing the current order information, and determining the claim payment amount according to the discretized current order information by using a training model. According to the method and the device, a certain rule can be generated quickly by analyzing a series of sample data, heavy workload of business personnel can be replaced, subjective bias brought by manpower can be eliminated, and the calculation efficiency can be effectively improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method and a system for calculating a compensation amount based on multi-factor influence.
Background
With the rapid development of computers, data sources are more and more diverse, and coverage ranges are wider and wider, so that the researchers are always pursuing how to extract useful information from massive, fuzzy and incomplete data.
Most of conventional methods for calculating the reimbursement amount set the recommended amount through business experience mainly depend on business experience of business personnel, have poor scientificity and mainly depend on manpower, consume a lot of manpower when the variable combinations are more, and have low calculation efficiency.
Disclosure of Invention
In view of this, the present application provides a method and a system for calculating a reimbursement amount based on multi-factor influence, which can quickly generate a certain rule by analyzing a series of sample data, not only can replace heavy workload of business personnel, can eliminate subjective bias brought by manpower, but also can effectively improve calculation efficiency.
In order to solve the technical problem, the following technical scheme is adopted:
in a first aspect, the present application provides a method for calculating a reimbursement amount based on multi-factor influence, including:
acquiring a claim request of a user, wherein the claim request comprises user information and current order information;
acquiring historical order information and historical compensation information of the user according to the user information;
judging whether the claim request of the user accords with a preset claim rule or not, and if the claim request of the user does not accord with the preset claim rule, ignoring the claim request; if the claim request of the user accords with a preset claim rule, discretizing the historical order information, and determining a training model according to the historical claim information and the discretized historical order information;
discretizing the current order information, and determining the reimbursement amount according to the discretized current order information by using the training model.
Optionally, wherein:
judging whether the claim request of the user accords with a preset claim rule, specifically comprising the following steps:
inquiring the historical paying times and the historical ordering times of the user according to the user information;
judging the size relationship between the historical claims and the preset times: if the historical claims are more than or equal to the preset times, judging that the claims request of the user does not accord with the preset claims rule; and if the historical claims and payments are less than the preset times, judging that the claims and payments request of the user accords with a preset claims and payments rule.
Optionally, wherein:
the predetermined number of times is equal to one half of the number of times the history has been made.
Optionally, wherein:
before determining whether the claim request of the user complies with the preset claim rule, the method further includes:
obtaining effective reimbursement time of the user according to the user information, and obtaining a time point for initiating a reimbursement request according to the reimbursement request;
judging whether the claim request time point is in effective claim time or not, and if the claim request time point is in effective claim time, continuously judging whether the claim request of the user meets a preset claim rule or not; and if the requested pay time point exceeds the effective pay time, ignoring the pay request and no longer judging whether the pay request of the user accords with a preset pay rule.
In a second aspect, the present application further provides a system for calculating a reimbursement amount based on multi-factor influence, comprising:
the system comprises a user information acquisition module, a payment processing module and a payment processing module, wherein the user information acquisition module is used for acquiring a claim request of a user, and the claim request comprises user information and current order information;
the extraction module is used for acquiring historical order information and historical claim payment information of the user according to the user information;
the judging module is used for judging whether the claim request of the user accords with a preset claim rule or not;
the training model generation module is used for ignoring the claim request when the claim request of the user does not accord with the preset claim rule; when the claim request of the user accords with a preset claim rule, discretizing the acquired historical order information through the training model generation module, and determining a training model according to the historical claim information and the discretized historical order information;
and the calculation module is used for carrying out discretization processing on the current order information and determining the claim payment amount according to the discretized current order information by utilizing the training model.
Optionally, wherein:
the extraction module is also used for inquiring the historical paying times and the historical ordering times of the user according to the user information;
the judging module is used for judging the size relationship between the historical claims and the preset times: if the historical claims are more than or equal to the preset times, judging that the claims request of the user does not accord with the preset claims rule; and if the historical claims and payments are less than the preset times, judging that the claims and payments request of the user accords with a preset claims and payments rule.
Optionally, wherein:
further comprising: and the preset times calculation module is used for calculating the preset times, and the preset times are equal to one half of the historical ordering times.
Optionally, wherein:
the system also comprises an effective paying time judgment module;
the extraction module is further used for acquiring effective pay time of the user according to the user information and acquiring a time point for initiating a pay request according to the pay request;
the effective reimbursement time judging module is used for judging whether the requested reimbursement time point is within the effective reimbursement time or not, and if the requested reimbursement time point is within the effective reimbursement time, continuously judging whether the reimbursement request of the user meets preset reimbursement rules or not; and if the requested pay time point exceeds the effective pay time, ignoring the pay request and no longer judging whether the pay request of the user accords with a preset pay rule.
Compared with the prior art, the method and the system for calculating the claim payment amount based on the multi-factor influence achieve the following effects:
in the method and the system for calculating the claim payment amount based on the multi-factor influence, when a claim payment request of a user is received, after historical order information and historical claim payment information are obtained through user information corresponding to the request, a relation between the historical order information and the historical claim payment information is obtained through a machine learning technology, a training model is obtained, and the corresponding claim payment amount can be obtained by substituting the current order information of the user into the training model. Therefore, a certain rule can be generated quickly by analyzing a series of sample data, heavy workload of business personnel can be replaced, subjective bias brought by manpower can be eliminated, and the calculation efficiency can be effectively improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart illustrating a method for calculating a payout amount based on multi-factor influence according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a method for determining whether a user's request for reimbursement complies with preset reimbursement rules according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating a method for calculating a payout amount based on multi-factor influence according to an embodiment of the present application;
FIG. 4 is a block diagram of a system for calculating a payout amount based on multi-factor influence according to an embodiment of the present application;
FIG. 5 is a block diagram of another embodiment of a system for calculating a payout amount based on multi-factor influence according to the present disclosure;
fig. 6 is a schematic structural diagram of a system for calculating a reimbursement amount based on multi-factor influence according to an embodiment of the present application.
Detailed Description
As used in the specification and in the claims, certain terms are used to refer to particular components. As one skilled in the art will appreciate, manufacturers may refer to a component by different names. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. "substantially" means within an acceptable error range, and a person skilled in the art can solve the technical problem within a certain error range to substantially achieve the technical effect. Furthermore, the term "coupled" is intended to encompass any direct or indirect electrical coupling. Thus, if a first device couples to a second device, that connection may be through a direct electrical coupling or through an indirect electrical coupling via other devices and couplings. The description which follows is a preferred embodiment of the present application, but is made for the purpose of illustrating the general principles of the application and not for the purpose of limiting the scope of the application. The protection scope of the present application shall be subject to the definitions of the appended claims.
Most of conventional methods for calculating the reimbursement amount set the recommended amount through business experience mainly depend on business experience of business personnel, have poor scientificity and mainly depend on manpower, consume a lot of manpower when the variable combinations are more, and have low calculation efficiency.
In view of this, the present application provides a method and a system for calculating a reimbursement amount based on multi-factor influence, which can quickly generate a certain rule by analyzing a series of sample data, not only can replace heavy workload of business personnel, can eliminate subjective bias brought by manpower, but also can effectively improve calculation efficiency.
The following detailed description is to be read in connection with the drawings and the detailed description.
Fig. 1 is a flowchart illustrating a method for calculating a payout amount based on multi-factor influence according to an embodiment of the present application, and referring to fig. 1, the embodiment of the present application provides a method for calculating a payout amount based on multi-factor influence, including:
step 10: when a claim request of a user is obtained, the claim request comprises user information and current order information;
step 20: acquiring historical order information and historical compensation information of a user according to the user information;
step 30: judging whether the claim request of the user accords with a preset claim rule or not, and if the claim request of the user does not accord with the preset claim rule, ignoring the claim request; if the claim request of the user accords with a preset claim rule, discretizing the historical order information, and generating a training model according to the historical claim information and the discretized historical order information;
step 40: discretizing the current order information, and determining the claim payment amount according to the discretized current order information by using a training model.
Specifically, referring to fig. 1, in the method for calculating a reimbursement amount based on multi-factor influence according to the embodiment of the present application, a reimbursement request of a user is received through step 10, and user information and current order information are obtained according to the reimbursement request, where the user information includes historical order information, historical reimbursement information, commodity information, and the like of the user. In step 20, the historical order information and the historical claim payment information corresponding to the user are extracted according to the user information, so as to facilitate subsequent use. The method determines the user's claim request through step 30, and determines whether the user's claim request complies with the preset claim rule.
Referring to fig. 1, if it is determined that the claim request of the user does not conform to the preset claim rule, the claim request of the user is ignored; if the claim request of the user is judged to accord with the preset claim rule, discretizing the historical order information of the user, wherein any one of the existing discretization methods such as a finite difference method, a finite element method or a weighted remainder method can be adopted during discretization, and the method is not limited in the application. Compared with continuous data, the data after discretization processing are integers, the use in the subsequent calculation process is more convenient, after discretization historical order information is obtained, a training model is determined according to the historical claims information and the discretization historical order information, and the training model can represent the relation between the historical claims information and the historical order information. After the training model is obtained, the claim amount is calculated through step 40, and when the claim amount is calculated, firstly, discretization processing needs to be performed on the current order information, and the discretized current order information is substituted into the training model, so that the claim amount can be calculated.
According to the method for calculating the claim payment amount based on the multi-factor influence, when a claim payment request of a user is received, after historical order information and historical claim payment information are obtained through user information corresponding to the request, a relation between the historical order information and the historical claim payment information is obtained through a machine learning technology, a training model is obtained, and the current order information of the user is substituted into the training model to obtain the corresponding claim payment amount. Therefore, a certain rule can be generated quickly by analyzing a series of sample data, heavy workload of business personnel can be replaced, subjective bias brought by manpower can be eliminated, and the calculation efficiency can be effectively improved.
Optionally, fig. 2 is a flowchart illustrating a process of determining whether the claim request of the user meets the preset claim rule, please refer to fig. 2, where determining whether the claim request of the user meets the preset claim rule specifically includes: step 31: inquiring the historical paying times and the historical ordering times of the user according to the user information; step 32: judging the size relationship between the historical paying times and the preset times: if the historical claims are more than or equal to the preset times, judging that the claims request of the user does not accord with the preset claims rule; and if the historical claims are less than the preset times, judging that the claims request of the user accords with the preset claims rule. Specifically, referring to fig. 2, when a user sends a claims request, it is required to determine whether the claims request meets a preset claims rule, when determining whether the claims request meets the preset claims rule, first set a predetermined number of times, query the historical claims number and historical order placing number of the user through step 31, use the predetermined number as a threshold, determine a size relationship between the historical claims number and the predetermined number of times through step 32, determine whether the claims request of the user meets the preset claims rule, and when the historical claims number is greater than or equal to the predetermined number of times, that is, the historical claims number is greater than or equal to the threshold, determine that the claims request of the user does not meet the preset claims rule. Otherwise, when the historical reimbursement number of the user is smaller than the preset number, the reimbursement request of the user is considered to be in accordance with the preset reimbursement rule, the reimbursement amount is calculated through the subsequent steps, and the reimbursement is carried out according to the calculated reimbursement amount.
Optionally, the predetermined number of times is equal to one-half of the number of times the order was taken in the history. Specifically, in this embodiment, the predetermined number of times is set according to the historical order placing times, and the predetermined number of times is set to be equal to one half of the historical order placing times, that is, when the historical reimbursement number of the user is greater than or equal to one half of the historical order placing times, the reimbursement request of the user is considered to be a malicious attack behavior, and it is determined that the reimbursement request of the user does not conform to the preset reimbursement rule. Otherwise, when the historical reimbursement number of the user is less than one-half of the historical order placing number, the reimbursement request of the user is considered to be a normal request, the request is considered to be in accordance with the preset reimbursement rule, the reimbursement amount is calculated through the subsequent steps, and reimbursement is carried out according to the calculated reimbursement amount. Of course, setting the predetermined number of times to be one half of the historical order count is only one setting in this embodiment of the present application, and in other embodiments, the value of the predetermined number of times may also be set to other values, for example, two thirds of the historical order count or three quarters of the historical order count, and the present application does not limit this.
Optionally, fig. 3 is another flowchart of a method for calculating a reimbursement amount based on multi-factor influence according to an embodiment of the present application, and referring to fig. 3, before determining whether a reimbursement request of a user complies with preset reimbursement rules, the method further includes: step 21: obtaining effective pay time of a user according to the user information, and obtaining a time point for initiating a pay request according to the pay request; step 22: judging whether the claim request time point is within the effective claim time or not, and if the claim request time point is within the effective claim time, continuously judging whether the claim request of the user accords with a preset claim rule or not; and if the requested pay time point exceeds the effective pay time, ignoring the pay request and no longer judging whether the pay request of the user accords with the preset pay rule.
Specifically, referring to fig. 3, in general, the user's reimbursement service has a certain validity period, and therefore, in this embodiment, before determining whether the reimbursement request of the user meets the preset reimbursement rule, it is first determined whether the time when the user initiates the reimbursement request is within the validity period, and first in step 21, the valid reimbursement time of the user and the time when the user initiates the reimbursement request are obtained according to the user information. After obtaining the time point when the user initiates the reimbursement request and the valid reimbursement time of the user, in step 22, it is determined whether the time point when the user initiates the reimbursement request is within the valid reimbursement time, for example, if the effective reimbursement period is 1 year, when the user initiates the reimbursement request within 1 year after the order is finished, the reimbursement request is within the valid period, and the reimbursement request needs to be processed accordingly; if the user initiates a claim payment request after the order is finished for one year, the request initiated by the user at this time is ignored and is not processed because the effective claim payment time is exceeded. Therefore, the user requests exceeding the validity period can be screened out before judging whether the requests accord with the preset claims rules, and only the claims requests in the validity period are processed, so that the data volume can be effectively reduced, and the calculation efficiency can be further improved.
Based on the same inventive concept, the present application further provides a system 100 for calculating a reimbursement amount based on multi-factor influence, fig. 4 is a schematic structural diagram of the system 100 for calculating a reimbursement amount based on multi-factor influence according to the embodiment of the present application, please refer to fig. 4, the system 100 for calculating a reimbursement amount based on multi-factor influence according to the embodiment of the present application includes:
the user information obtaining module 110 is configured to obtain a claim request of a user, where the claim request includes user information and current order information;
the extracting module 120 is configured to obtain historical order information and historical claim payment information of the user according to the user information;
the judging module 130 is configured to judge whether the claim request of the user meets a preset claim rule;
the training model generation module 140 ignores the claim request when the claim request of the user does not conform to the preset claim rule; when the claim request of the user accords with the preset claim rule, discretizing the acquired historical order information through the training model generating module 140, and generating a training model according to the historical claim information and the discretized historical order information;
and the calculation module 150 is configured to perform discretization processing on the current order information, and determine a reimbursement amount according to the discretized current order information by using the training model.
Specifically, referring to fig. 4, the system 100 for calculating a reimbursement amount based on multi-factor influence according to the embodiment of the present application includes a user information obtaining module 110, an extracting module 120, a determining module 130, a training model generating module 140, and a calculating module 150. The user information obtaining module 110 receives a claim request of a user, and obtains user information and current order information according to the claim request, wherein the user information includes historical order information, historical claim information, commodity information, and the like of the user. After obtaining the user information, the extracting module 120 extracts the historical order information and the historical claim payment information corresponding to the user according to the user information, so as to facilitate subsequent use, and determines whether the claim payment request of the user meets the preset claim payment rule by determining the claim payment request of the user through the determining module 130.
If the claim payment request of the user is judged to be not in accordance with the preset claim payment rule, the claim payment request of the user is ignored; if the claim request of the user is judged to conform to the preset claim rule, discretization processing is performed on the historical order information of the user through the training model generation module 140, and any one of the existing discretization methods such as a finite difference method, a finite element method or a weighted remainder method can be adopted during the discretization processing, which is not limited in the application. Compared with continuous data, the data after discretization processing are integers, so that the data can be used in a subsequent calculation process more conveniently, after discretization historical order information is obtained, the training model generating module 140 is continuously utilized to generate a training model according to the historical claim information and the discretization historical order information, and the training model can represent the relation between the historical claim information and the historical order information. After the training model is obtained, the calculation module 150 calculates the pay amount, and when the pay amount is calculated, firstly, the discretization processing is needed to be performed on the current order information, and the discretized current order information is substituted into the training model, so that the pay amount can be calculated.
In the system 100 for calculating the reimbursement amount based on the multi-factor influence, when a reimbursement request of a user is received, after historical order information and historical reimbursement information are obtained through user information corresponding to the request, a training model is obtained by obtaining a relation between the historical order information and the historical reimbursement information through a machine learning technology, and the corresponding reimbursement amount can be obtained by substituting the current order information of the user into the training model. Therefore, a certain rule can be generated quickly by analyzing a series of sample data, heavy workload of business personnel can be replaced, subjective bias brought by manpower can be eliminated, and the calculation efficiency can be effectively improved.
Optionally, the extracting module 120 is further configured to query historical times of paying and historical times of placing orders of the user according to the user information; the determining module 130 is further configured to determine a relationship between the historical reimbursement times and the predetermined times, and if the reimbursement times is greater than or equal to the predetermined times, determine that the reimbursement request of the user does not conform to the preset reimbursement rule; and if the number of times of claims is less than the preset number of times, judging that the claim request of the user accords with the preset claim rule. Specifically, when a user sends a claims request, it is required to determine whether the claims request meets a preset claims rule, when determining whether the claims request meets the preset claims rule, first setting a predetermined number of times, querying a historical claims number and a historical order placing number of the user through the extraction module 120, taking the predetermined number of times as a threshold, obtaining a size relationship between the historical claims number and the predetermined number of times through the determination module 130, determining whether the claims request of the user meets the preset claims rule, and when the historical claims number is greater than or equal to the predetermined number of times, that is, the historical claims number is greater than or equal to the threshold, so that the user can be considered as a malicious attack, and determining that the claims request of the user does not meet the preset claims rule. Otherwise, when the historical reimbursement number of the user is smaller than the preset number, the reimbursement request of the user is considered to be in accordance with the preset reimbursement rule, the reimbursement amount is calculated through the subsequent steps, and the reimbursement is carried out according to the calculated reimbursement amount.
Optionally, fig. 5 is a schematic structural diagram of another system 100 for calculating a payout amount based on multi-factor influence according to an embodiment of the present application, please refer to fig. 5, where the system 100 for calculating a payout amount based on multi-factor influence further includes: and the predetermined number calculating module 160 is used for calculating the predetermined number, wherein the predetermined number is equal to one half of the historical ordering number. Specifically, referring to fig. 5, the system 100 for calculating a claim amount based on multi-factor influence further includes a predetermined number calculating module 160, the predetermined number calculating module 160 calculates the predetermined number, and sets the predetermined number equal to one half of the historical ordering number, that is, when the historical claim number of the user is greater than or equal to one half of the historical ordering number, the claim request of the user is considered as a malicious attack, and it is determined that the claim request of the user does not conform to the preset claim rule. Otherwise, when the historical reimbursement number of the user is less than one-half of the historical order placing number, the reimbursement request of the user is considered to be a normal request, the request is considered to be in accordance with the preset reimbursement rule, the reimbursement amount is calculated through the subsequent steps, and reimbursement is carried out according to the calculated reimbursement amount. Of course, setting the predetermined number of times to be one half of the historical order count is only one setting in this embodiment of the present application, and in other embodiments, the value of the predetermined number of times may also be set to other values, for example, two thirds of the historical order count or three quarters of the historical order count, and the present application does not limit this.
Optionally, fig. 6 is a schematic structural diagram of a system 100 for calculating a reimbursement amount based on multi-factor influence according to an embodiment of the present application, please refer to fig. 6, which further includes an effective reimbursement time determination module 170; the extracting module 120 is further configured to obtain effective reimbursement time of the user according to the user information, and obtain a time point for initiating the reimbursement request according to the reimbursement request; the effective reimbursement time judging module 170 is configured to judge whether the requested reimbursement time point is within the effective reimbursement time, and if the requested reimbursement time point is within the effective reimbursement time, continue to judge whether the reimbursement request of the user meets a preset reimbursement rule; and if the requested pay time point exceeds the effective pay time, ignoring the pay request and no longer judging whether the pay request of the user accords with the preset pay rule.
Specifically, referring to fig. 6, in general, a user's pay service has a certain validity period, and therefore, in this embodiment, before determining whether a user's pay request meets a preset pay rule, it is determined whether a time when the user initiates the pay request is within the validity period, and first, the extraction module 120 is utilized to obtain, according to user information, an effective pay time of the user and a time point when the user initiates the pay request. After obtaining the time point when the user initiates the reimbursement request and the effective reimbursement time of the user, the effective reimbursement time determining module 170 determines whether the time point is within the effective reimbursement time, for example, if the effective reimbursement period is 1 year, when the user initiates the reimbursement request within 1 year after the order, the reimbursement request is within the effective period, and the reimbursement request needs to be processed; if the user initiates a claim payment request after the order is finished for one year, the request initiated by the user at this time is ignored and is not processed because the effective claim payment time is exceeded. Therefore, the user requests exceeding the validity period can be screened out before judging whether the requests accord with the preset claims rules, and only the claims requests in the validity period are processed, so that the data volume can be effectively reduced, and the calculation efficiency can be further improved.
According to the embodiments, the application has the following beneficial effects:
in the method and the system for calculating the claim payment amount based on the multi-factor influence, when a claim payment request of a user is received, after historical order information and historical claim payment information are obtained through user information corresponding to the request, a relation between the historical order information and the historical claim payment information is obtained through a machine learning technology, a training model is obtained, and the corresponding claim payment amount can be obtained by substituting the current order information of the user into the training model. Therefore, a certain rule can be generated quickly by analyzing a series of sample data, heavy workload of business personnel can be replaced, subjective bias brought by manpower can be eliminated, and the calculation efficiency can be effectively improved.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing description shows and describes several preferred embodiments of the present application, but as aforementioned, it is to be understood that the application is not limited to the forms disclosed herein, but is not to be construed as excluding other embodiments and is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the application, which is to be protected by the claims appended hereto.
Claims (8)
1. A method for calculating a claim amount based on multi-factor influence is characterized by comprising the following steps:
acquiring a claim request of a user, wherein the claim request comprises user information and current order information;
acquiring historical order information and historical compensation information of the user according to the user information;
judging whether the claim request of the user accords with a preset claim rule or not, and if the claim request of the user does not accord with the preset claim rule, ignoring the claim request; if the claim request of the user accords with a preset claim rule, discretizing the historical order information, and determining a training model according to the historical claim information and the discretized historical order information;
discretizing the current order information, and determining the reimbursement amount according to the discretized current order information by using the training model.
2. The method for calculating a claim amount based on multi-factor influence according to claim 1, wherein the step of judging whether the claim request of the user meets a preset claim rule specifically comprises:
inquiring the historical paying times and the historical ordering times of the user according to the user information;
judging the size relationship between the historical claims and the preset times: if the historical claims are more than or equal to the preset times, judging that the claims request of the user does not accord with the preset claims rule; and if the historical claims and payments are less than the preset times, judging that the claims and payments request of the user accords with a preset claims and payments rule.
3. The multi-factor influence-based claims amount calculation method as recited in claim 2, wherein the predetermined number of times is equal to one-half of the number of times the order was made in the history.
4. The method for calculating a reimbursement amount based on multi-factor influence according to claim 1, wherein before determining whether the reimbursement request of the user complies with the preset reimbursement rules, the method further comprises:
obtaining effective reimbursement time of the user according to the user information, and obtaining a time point for initiating a reimbursement request according to the reimbursement request;
judging whether the claim request time point is in effective claim time or not, and if the claim request time point is in effective claim time, continuously judging whether the claim request of the user meets a preset claim rule or not; and if the requested pay time point exceeds the effective pay time, ignoring the pay request and no longer judging whether the pay request of the user accords with a preset pay rule.
5. A system for calculating a payout amount based on a multi-factor effect, comprising:
the system comprises a user information acquisition module, a payment processing module and a payment processing module, wherein the user information acquisition module is used for acquiring a claim request of a user, and the claim request comprises user information and current order information;
the extraction module is used for acquiring historical order information and historical claim payment information of the user according to the user information;
the judging module is used for judging whether the claim request of the user accords with a preset claim rule or not;
the training model generation module is used for ignoring the claim request when the claim request of the user does not accord with the preset claim rule; when the claim request of the user accords with a preset claim rule, discretizing the acquired historical order information through the training model generation module, and determining a training model according to the historical claim information and the discretized historical order information;
and the calculation module is used for carrying out discretization processing on the current order information and determining the claim payment amount according to the discretized current order information by utilizing the training model.
6. The multi-factor influence-based reimbursement amount computing system of claim 5,
the extraction module is also used for inquiring the historical paying times and the historical ordering times of the user according to the user information;
the judging module is used for judging the size relationship between the historical claims and the preset times: if the historical claims are more than or equal to the preset times, judging that the claims request of the user does not accord with the preset claims rule; and if the historical claims and payments are less than the preset times, judging that the claims and payments request of the user accords with a preset claims and payments rule.
7. The multi-factor impact-based payout amount calculation system as defined in claim 6, further comprising: and the preset times calculation module is used for calculating the preset times, and the preset times are equal to one half of the historical ordering times.
8. The multi-factor impact-based reimbursement amount calculation system of claim 5, further comprising an effective reimbursement time determination module;
the extraction module is further used for acquiring effective pay time of the user according to the user information and acquiring a time point for initiating a pay request according to the pay request;
the effective reimbursement time judging module is used for judging whether the requested reimbursement time point is within the effective reimbursement time or not, and if the requested reimbursement time point is within the effective reimbursement time, continuously judging whether the reimbursement request of the user meets preset reimbursement rules or not; and if the requested pay time point exceeds the effective pay time, ignoring the pay request and no longer judging whether the pay request of the user accords with a preset pay rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010055156.5A CN111292159A (en) | 2020-01-17 | 2020-01-17 | Method and system for calculating claim payment amount based on multi-factor influence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010055156.5A CN111292159A (en) | 2020-01-17 | 2020-01-17 | Method and system for calculating claim payment amount based on multi-factor influence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111292159A true CN111292159A (en) | 2020-06-16 |
Family
ID=71030688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010055156.5A Pending CN111292159A (en) | 2020-01-17 | 2020-01-17 | Method and system for calculating claim payment amount based on multi-factor influence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111292159A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320233A (en) * | 2018-02-26 | 2018-07-24 | 平安科技（深圳）有限公司 | Annotation generation method, device and the computer readable storage medium of bill |
| CN109255718A (en) * | 2018-06-28 | 2019-01-22 | 平安科技（深圳）有限公司 | Insurance benefits method and apparatus, computer equipment and readable storage medium storing program for executing |
| CN110047007A (en) * | 2018-11-27 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of Claims Resolution method for processing business and device |
| CN110443716A (en) * | 2019-06-17 | 2019-11-12 | 中国平安财产保险股份有限公司 | Claims Resolution method, apparatus, computer equipment and storage medium |
-
2020
- 2020-01-17 CN CN202010055156.5A patent/CN111292159A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320233A (en) * | 2018-02-26 | 2018-07-24 | 平安科技（深圳）有限公司 | Annotation generation method, device and the computer readable storage medium of bill |
| CN109255718A (en) * | 2018-06-28 | 2019-01-22 | 平安科技（深圳）有限公司 | Insurance benefits method and apparatus, computer equipment and readable storage medium storing program for executing |
| CN110047007A (en) * | 2018-11-27 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of Claims Resolution method for processing business and device |
| CN110443716A (en) * | 2019-06-17 | 2019-11-12 | 中国平安财产保险股份有限公司 | Claims Resolution method, apparatus, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107168854B (en) | Internet advertisement abnormal click detection method, device, equipment and readable storage medium | |
| JP6422617B2 (en) | Network access operation identification program, server, and storage medium | |
| US20210035126A1 (en) | Data processing method, system and computer device based on electronic payment behaviors | |
| KR20180075641A (en) | Service processing method and apparatus | |
| CN107347052B (en) | Method and device for detecting database collision attack | |
| WO2018028430A1 (en) | Method, apparatus and system for identification and auxiliary identification of fake traffic | |
| CN110175278B (en) | Detection method and device for web crawler | |
| WO2020233360A1 (en) | Method and device for generating product evaluation model | |
| CN111371858A (en) | Group control equipment identification method, device, medium and electronic equipment | |
| CN109670931B (en) | Loan user behavior detection method, loan user behavior detection device, loan user behavior detection equipment and loan user behavior detection storage medium | |
| CN105656867A (en) | Monitoring method and device for account theft event | |
| CN104079559A (en) | Web address security detecting method and device and server | |
| CN112395118A (en) | Equipment data detection method and device | |
| CN109495471B (en) | Method, device and equipment for judging WEB attack result and readable storage medium | |
| CN116015842A (en) | Network attack detection method based on user access behaviors | |
| CN111292159A (en) | Method and system for calculating claim payment amount based on multi-factor influence | |
| CN115801455B (en) | Method and device for detecting counterfeit website based on website fingerprint | |
| CN110610070A (en) | User identity identification method and device | |
| CN107995167B (en) | Equipment identification method and server | |
| CN113297583B (en) | Vulnerability risk analysis method, device, equipment and storage medium | |
| CN112087414A (en) | Detection method and device for mining trojans | |
| CN112333155B (en) | Abnormal flow detection method and system, electronic equipment and storage medium | |
| CN114579711A (en) | Method, device, equipment and storage medium for identifying fraud application program | |
| CN114297735A (en) | Data processing method and related device | |
| CN112800281A (en) | Method and device for processing engineering cost data |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200616 |