CN110728585A - Authority guaranteeing method, device, equipment and storage medium - Google Patents
Authority guaranteeing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110728585A CN110728585A CN201911014238.9A CN201911014238A CN110728585A CN 110728585 A CN110728585 A CN 110728585A CN 201911014238 A CN201911014238 A CN 201911014238A CN 110728585 A CN110728585 A CN 110728585A
- Authority
- CN
- China
- Prior art keywords
- underwriting
- information
- historical
- underwritten
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 62
- 230000003044 adaptive effect Effects 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 16
- 238000004364 calculation method Methods 0.000 description 15
- 238000012795 verification Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000010365 information processing Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 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
Abstract
The embodiment of the invention provides an underwriting method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring information to be certified and protected; inputting the information to be underwritten into an underwriting model, if historical underwriting information matched with the information to be underwritten is acquired in a self-adaptive enumeration set generated by the underwriting model, taking an underwriting result of the historical underwriting information as an underwriting result of the information to be underwritten, wherein the underwriting model is acquired by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm for self-adaptive training; the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information. The method provided by the embodiment can overcome the problems that in the prior art, the underwriting efficiency is low, and further the customer experience is influenced.
Description
Technical Field
The embodiment of the invention relates to the technical field of underwriting, in particular to an underwriting method, an underwriting device, an underwriting equipment and a storage medium.
Background
With the improvement of the acceptance degree of users to insurance products, the domestic insurance business unit volume shows a trend of sharp increase, and all large insurance companies take the improvement of process automation as an important target. From the experience of the underwriting personnel and the user, the requirement for faster and more efficient underwriting service is provided.
At present, the rules of the current insurance underwriting are all stored in a database, all the insurance rules are bound on the dangerous seeds, the insurance of all insurance policies needs to find the product information corresponding to the insurance policy, the corresponding dangerous seed information is found through the product information, and whether the insurance policy can be underwritten or not is judged through the verification of the insurance rules of the dangerous seeds.
However, in the existing underwriting process, all underwriting pressures are concentrated in the database, the database has both data saving operation and underwriting rule operation, and the processing speed of the whole underwriting process is very slow. Therefore, the prior art has the problems that the efficiency of the underwriting is slow, and the customer experience is influenced.
Disclosure of Invention
The embodiment of the invention provides an underwriting method, an underwriting device, equipment and a storage medium, and aims to solve the problem that in the prior art, underwriting efficiency is low, and customer experience is further influenced.
In a first aspect, an embodiment of the present invention provides an underwriting method, including:
acquiring information to be certified and protected;
inputting the information to be underwritten into an underwriting model, if historical underwriting information matched with the information to be underwritten is acquired in a self-adaptive enumeration set generated by the underwriting model, taking an underwriting result of the historical underwriting information as an underwriting result of the information to be underwritten, wherein the underwriting model is acquired by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm for self-adaptive training;
the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information.
Optionally, each piece of historical underwriting information includes a plurality of underwriting factors, and the plurality of underwriting factors form an underwriting rule;
before the obtaining of the information to be certified, the method further comprises:
acquiring a plurality of historical underwriting information;
aiming at each historical underwriting information, taking a plurality of underwriting factors in the historical underwriting information as input quantity of the exhaustive algorithm, carrying out self-adaptive training on the exhaustive algorithm through underwriting results corresponding to preset underwriting rules configured in the exhaustive algorithm to obtain underwriting results of the historical underwriting information, wherein the historical underwriting information and the corresponding underwriting results of the historical underwriting information form a sample;
dividing each sample to generate a plurality of underwriting subsets, wherein the plurality of underwriting subsets form the self-adaptive enumeration set;
and taking the trained exhaustive algorithm as the underwriting model, wherein the self-adaptive enumeration set is stored in the underwriting model.
Optionally, the plurality of underwriting factors include risk species, age, gender, occupation category, premium, area under insurance, accident premium, and whether additional risks are tied;
the dividing each sample to generate a plurality of underwriting subsets includes:
according to a plurality of underwriting factors in all the historical underwriting information, dividing all the historical underwriting information into underwriting subsets, wherein the underwriting results comprise the same risk species, occupation types, insurance amounts, insuring areas, personal accident insurance amounts, underwriting passing historical underwriting information corresponding to whether additional risks are bound or not, and the underwriting results of the underwriting passing historical underwriting information;
acquiring ages in all historical underwriting information in all underwriting subsets aiming at each underwriting subset in all underwriting subsets, and taking age groups corresponding to all the ages as first identifications of the underwriting subsets;
and performing secondary identification on the first identifications of all the underwriting subsets, and marking the underwriting subsets containing the same first identifications with second identifications, wherein the second identifications are used for distinguishing a plurality of different underwriting subsets.
Optionally, after the inputting the information to be underwritten into an underwriting model, the method further includes:
encrypting each underwriting factor in the information to be underwrited by a Hash algorithm to obtain each encrypted underwriting factor;
searching whether target historical underwriting information exists from the self-adaptive enumeration set, wherein the target historical underwriting information is first historical underwriting information which is consistent with each encrypted underwriting factor;
and if so, acquiring the target historical underwriting information, and taking the target historical underwriting information as historical underwriting information matched with the information to be underwrited.
Optionally, after the inputting the information to be underwritten into an underwriting model, the method further includes:
if the historical underwriting information matched with the information to be underwrited is not acquired in the self-adaptive enumeration set generated by the underwriting model, acquiring a target underwriting rule matched with the information to be underwrited through the preset underwriting rule configured in the exhaustive algorithm;
and taking the underwriting result corresponding to the target underwriting rule as the underwriting result of the information to be underwrited.
Optionally, after the obtaining of the target underwriting rule matched with the information to be underwrited, the method further includes:
and storing the information to be underwritten and the underwriting result of the information to be underwritten in a corresponding underwriting subset or generating a new underwriting subset.
Optionally, after the information to be underwritten is input into an underwriting model, the method further includes:
and generating an underwriting result of the information to be underwritten according to the preset underwriting rule configured in the exhaustive algorithm.
In a second aspect, an embodiment of the present invention provides an underwriting apparatus, including:
the information acquisition module to be certified is used for acquiring information to be certified;
the first underwriting result acquisition module is used for inputting the information to be underwritten into an underwriting model, and if historical underwriting information matched with the information to be underwritten is acquired in an adaptive enumeration set generated by the underwriting model, the underwriting result of the historical underwriting information is used as the underwriting result of the information to be underwritten, and the underwriting model is obtained by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm for adaptive training;
the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information.
In a third aspect, an embodiment of the present invention provides an electronic device, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the underwriting method as set forth above in the first aspect and various possible designs of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the method for underwriting according to the first aspect and various possible designs of the first aspect are implemented.
According to the underwriting method, the underwriting device, the underwriting equipment and the storage medium, information to be underwrited is acquired firstly, the information to be underwrited is input into an underwriting model and is underwritten through the underwriting model, if historical underwriting information matched with the information to be underwrited is acquired in an adaptive enumeration set generated by the underwriting model, underwriting results of the historical underwriting information are used as underwriting results of the information to be underwrited, the underwriting model is acquired by performing adaptive training by using a plurality of historical underwriting information as samples and adopting an exhaustive algorithm, underwriting can be rapidly achieved on an underwriting, and customer experience is improved. According to the scheme, the information to be underwritten is input into the underwriting model through the underwriting model, the underwriting result of the information to be underwritten can be quickly searched in a self-adaptive enumeration set stored in the underwriting model, the acquired underwriting result of the historical underwriting information matched with the information to be underwrited is used as the underwriting result of the information to be underwrited, the underwriting efficiency is high, and meanwhile, the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of an underwriting method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for underwriting according to another embodiment of the present invention;
FIG. 3 is a flowchart illustrating the division of the underwriting rule according to yet another embodiment of the present invention;
FIG. 4 is a flowchart illustrating an underwriting method according to another embodiment of the present invention;
FIG. 5 is a flowchart illustrating an underwriting method according to yet another embodiment of the present invention;
FIG. 6 is a flowchart illustrating an underwriting method according to yet another embodiment of the present invention;
FIG. 7 is a flowchart illustrating an underwriting method according to another embodiment of the present invention;
fig. 8 is a schematic structural diagram of an underwriting apparatus according to an embodiment of the present invention;
FIG. 9 is a schematic structural diagram of an underwriting apparatus according to yet another embodiment of the present invention;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, the rules of insurance underwriting are all stored in a database, all the insurance rules are bound to the dangerous seeds, the insurance underwriting of all insurance policies needs to find the product information corresponding to the insurance policy, the corresponding dangerous seed information is found through the product information, and whether the insurance policy can be underwritten or not is judged through the verification of the insurance rule of the dangerous seeds. However, in the existing underwriting process, all underwriting pressures are concentrated in the database, the database has both data saving operation and underwriting rule operation, and the processing speed of the whole underwriting process is very slow. Therefore, the prior art has the problems that the efficiency of the underwriting is slow, and the customer experience is influenced.
For example, see tables 1 and 2:
TABLE 1
TABLE 2
As shown in tables 1 and 2 above, if customer A commits policy 1001 and the product corresponding to the policy is PRO-1, the verification method is as follows: (TY represents general risk species, 1001, 1002, etc. may represent special risk species)
(1) As shown in Table 1, the corresponding dangerous seed information is found through the product code PRO-1, and the dangerous seed information is 1001 and 1002.
(2) In table 2, the underwriting rules of all risk varieties are stored in the table, and the underwriting rules corresponding to the product PRO-1 are of two types:
one type is as follows: encoding 1 to 4: and (4) checking the insurance rules of all products and all insurance policies.
The second type is as follows: nos. 5 to 7: the dangerous seeds 1001 and 1002 correspond to special underwriting rules.
In the prior art, in the checking of the underwriting, a first type rule and a second type rule are called. All the underwriting pressure is concentrated in the database, the database has data storage operation and underwriting rule operation, and the whole underwriting process is very slow in processing speed; all business core systems use the oracle database. Because oracle is a business database, is a heavyweight database and is not easy to expand, the system cannot expand transversely to improve efficiency, all transaction requests penetrate to a database layer under the high-concurrency scene of the Internet, the system underwriting verification becomes a performance bottleneck, all underwriting rules are formulated through SQL expressions, for example, the underwriter age verification and the cumulative premium verification do not need cumulative data at all, and much time is wasted by verifying the rules through the SQL expressions.
In order to solve the above technical problem, an embodiment of the present invention provides an underwriting method to solve the above problem.
Fig. 1 is a schematic flow chart of an underwriting method according to an embodiment of the present invention, where an execution main body in this embodiment may be a terminal or a server, and the execution main body is not limited herein.
Referring to fig. 1, the underwriting method includes:
s101, obtaining information to be certified.
In this embodiment, the obtaining of the information to be certified may be that the execution subject receives the information to be certified collected by the data collection device, or may be that the execution subject obtains the information to be certified.
In practical application, the execution subject of this embodiment may be an underwriting device, and the underwriting device may be implemented in various ways, for example, the underwriting device may be program software, or a medium storing a related computer program, such as a usb disk, a cloud disk, or the like; alternatively, the underwriting apparatus may also be a physical device, such as a chip, a server, a terminal, etc., in which the relevant computer program is loaded or installed.
In this embodiment, obtaining the information to be certified may be implemented by: collecting policy information of client application, analyzing the policy information, and generating information to be underwritten, wherein the information to be underwritten comprises client identity information, occupation, application insurance risk and the like.
S102, inputting the information to be underwritten into an underwriting model, and if historical underwriting information matched with the information to be underwritten is acquired in a self-adaptive enumeration set generated by the underwriting model, taking an underwriting result of the historical underwriting information as an underwriting result of the information to be underwritten, wherein the underwriting model is acquired by performing self-adaptive training by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm; the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information.
In this embodiment, an underwriting model is obtained by performing adaptive training using an exhaustive algorithm with a plurality of pieces of historical underwriting information as samples, a terminal or a server sends or writes the obtained information to be underwriting into the underwriting model, so that the underwriting model searches historical underwriting information matched with the information to be underwriting from an adaptive enumeration set, if the historical underwriting information matched with the information to be underwriting is found, the terminal or the server obtains the historical underwriting information matched with the information to be underwriting from the adaptive enumeration set stored in the underwriting model, and uses an underwriting result of the historical underwriting information as an underwriting result of the information to be underwriting, and the underwriting model is obtained by performing adaptive training using an exhaustive algorithm with a plurality of pieces of historical underwriting information as samples.
In practical application, a client inputs policy information into a terminal or uploads the policy information to a server, an underwriter receives or acquires policy information of the client as information to be underwritten through a background, the information to be underwritten is sent or transmitted to the underwriting model, a rapid underwriting function is started, if historical underwriting information matched with the information to be underwritten is searched from a self-adaptive enumeration set, taking the approval result of the historical approval and insurance information matched with the information to be approved as the approval and insurance result of the information to be approved and insured, and the approval and insurance result of the information to be approved and insured is sent to the node corresponding to the order acceptance, and the approval and insurance result of the information to be approved and insured is sent to the front end (or the client end) to display the current state and the approval and insurance result to the client or the approval and insured personnel, thereby not only effectively carrying out the approval and insurance operation of the insurance policy, but also improving the user experience, and further, the time saved by the underwriting can be used for customer maintenance or other problem processing.
In the embodiment, the underwriting rule and the insurance data are learned to be an underwriting experience data source through a collision model of experience data, and the original underwriting mode of executing rule verification one by one aiming at one piece of insurance data is changed into a simple mode of inputting insurance matching underwriting conclusion.
Optionally, before the customer insurance policy is underwritten through the underwriting model, the underwriting model needs to be established first, referring to fig. 2, fig. 2 is a schematic flow chart of an underwriting method according to another embodiment of the present invention, and this embodiment explains the construction of the underwriting model in detail on the basis of the above-described embodiment, for example, on the basis of the embodiment shown in fig. 1. Each piece of historical underwriting information comprises a plurality of underwriting factors, and the underwriting factors form an underwriting rule; before the obtaining of the information to be certified, the method further comprises:
s201, obtaining a plurality of historical underwriting information.
In this embodiment, the acquired historical underwriting information may be the historical underwriting information acquired by the data acquisition device received by the execution subject, or the historical underwriting information acquired from the database by the execution subject. Each piece of historical underwriting information comprises a plurality of underwriting factors, and the underwriting factors form an underwriting rule. In the field of underwriting, a calculation factor (underwriting factor) can be described by a rule, such as the age of a person to be underwrited, the category of occupation, and the like, or for example, a person wants to participate in insurance policy information of a certain security amount at a certain place where the age of the person belongs, and an underwriting rule corresponding to the insurance policy is formed according to the insurance policy information and the underwriting rule corresponding to the insurance policy, that is, a plurality of underwriting factors can form an underwriting rule based on a preset underwriting rule.
S201, aiming at each historical underwriting information, taking a plurality of underwriting factors in the historical underwriting information as input quantity of the exhaustive algorithm, carrying out self-adaptive training on the exhaustive algorithm through underwriting results corresponding to preset underwriting rules configured in the exhaustive algorithm to obtain underwriting results of the historical underwriting information, wherein the historical underwriting information and the corresponding underwriting results of the historical underwriting information form a sample.
In this embodiment, in combination with the division of the underwriting rule shown in fig. 3, the preset underwriting rule may divide the underwriting rule by five dimensions. The method comprises a general rule set, an insurance mode rule set, a dangerous type rule set, a region rule set and a special rule set. The dangerous type and the region type are fixed lengths, and the special rule set can be distributed according to the existing underwriting rules and has fixed numbers.
The exhaustive algorithm is trained through a plurality of historical underwriting information, and the training mode is self-adaptive training. The exhaustive algorithm enumerates each element one by one from a possible solution set, and determines which are useless and which are useful and can make the problem be established by using the retrieval condition given by the problem, namely the solution, so that in the process of training the exhaustive algorithm, the exhaustive algorithm can realize self-adaptive training by one-to-one training, namely, one piece of historical underwriting information is input into the exhaustive algorithm, and an underwriting result corresponding to the preset underwriting rule can be obtained by using the preset underwriting rule configured in the exhaustive algorithm as the retrieval condition. The historical underwriting information and corresponding underwriting results of the historical underwriting information form a sample, and a plurality of historical underwriting information and corresponding underwriting results form a plurality of samples to form an adaptive enumeration set.
S203, dividing each sample to generate a plurality of underwriting subsets, wherein the underwriting subsets form the self-adaptive enumeration set;
s204, taking the trained exhaustive algorithm as the underwriting model, wherein the self-adaptive enumeration set is stored in the underwriting model.
In this embodiment, in order to implement fast underwriting, in the process of adaptively training the exhaustive algorithm, an adaptive enumeration set is generated, and in each underwriting process, only a sample matched with an input quantity, that is, historical underwriting information, is acquired from the adaptive enumeration set stored in the underwriting model through the input quantity, so that an output quantity (underwriting result of information to be underwrited) corresponding to the input quantity can be obtained. The adaptive enumeration set is composed of a plurality of underwriting subsets, and the plurality of underwriting subsets are generated by dividing each sample. For example, several sets of sample data are selected as a plurality of historical underwriting information (the data is entered by the applicant at the time of application), as shown in Table 3 below:
TABLE 3
In table 3, the risk types, ages, sexes, occupation categories, insurance amounts, insurance areas, personal accident insurance amounts, whether additional risks are bound or not are used as calculation factors, the values of the calculation factors are different, the calculation factors and the verification results are recorded and accumulated to form a self-adaptive enumeration set, and the verification result corresponds to a verification result through the existing verification of the underwriting rule. Due to the fact that sampling data, namely historical underwriting information and information to be underwritten (different latitude value changes) are continuously increased, corresponding result values are continuously generated through the same rule verification, the result sets are not repeated and are continuously accumulated, and the self-adaptive enumeration sets are more and more abundant.
The dividing manner of each sample may include two implementation manners.
The first method is as follows: the dangerous type classification is used for dividing samples belonging to the same dangerous type into an underwriting subset, and the dangerous type is used as the identifier of the underwriting subset.
In a second way, referring to fig. 4, fig. 4 is a schematic flow chart of an underwriting method according to another embodiment of the present invention, and this embodiment details how to divide the samples and further generate the adaptive enumeration set on the basis of the above embodiment, for example, on the basis of the embodiment described in fig. 2. Wherein the plurality of underwriting factors include risk species, age, gender, occupation category, premium, area under insurance, accident premium, and whether additional risk is bound; the dividing each sample to generate a plurality of underwriting subsets includes:
s401, according to a plurality of underwriting factors in all the historical underwriting information, dividing all the historical underwriting information into underwriting subsets, wherein the historical underwriting information contains the same risk species, occupation type, premium, insurance area, personal accident premium, and underwriting result of the underwriting historical underwriting information and the underwriting result of the underwriting historical underwriting information corresponding to whether additional risk is bound or not.
In this embodiment, according to a plurality of underwriting factors in all the historical underwriting information, in order to obtain an underwriting result quickly in an underwriting model, the generated adaptive enumeration set needs to be subdivided, for example, for a risk species, each sample containing the same risk species is divided into a plurality of first underwriting subsets, each sample containing the same occupation category in each first underwriting subset is divided into a plurality of second underwriting subsets, each sample containing the same warrant in each second underwriting subset is divided into a plurality of third underwriting subsets, and by analogy, the historical underwriting information of passing underwriting and the underwriting result of the historical underwriting information of passing underwriting, which correspond to the same risk species, occupation type, insurance amount, insurable area and personal insurance amount, whether additional risks are bound or not, are finally divided into an underwriting subset.
S402, aiming at each underwriting subset in all underwriting subsets, acquiring the ages in all historical underwriting information in the underwriting subsets, and taking the age groups corresponding to all the ages as first identifications of the underwriting subsets.
In this embodiment, after dividing all samples into a plurality of underwriting subsets, it is necessary to divide the ages in all underwriting subsets, and for each underwriting subset, first obtain the ages in all history information in the underwriting subset, then count the age groups corresponding to all ages, and use the age groups as the first identifiers of the underwriting subsets, so that each underwriting subset at this time includes one corresponding first identifier. The insurance policy of the customer or at least one underwriting subset of the age corresponding to the information to be underwritten can be quickly inquired through the first identification.
S403, performing secondary identification on the first identifications of all the underwriting subsets, and marking the underwriting subsets containing the same first identifications with second identifications, wherein the second identifications are used for distinguishing a plurality of different underwriting subsets.
In this embodiment, since age groups corresponding to a plurality of underwriting subsets having different risk categories, occupation categories, insurance amounts, insurance areas, personal insurance amounts, and whether additional risks are bound or not may overlap, that is, different underwriting subsets may have the same first identifier, it is necessary to perform identifier division on the plurality of subsets according to age groups, the division of the mode realizes that one piece of underwriting information only corresponds to one underwriting subset, samples matching the underwriting information (either historical underwriting information or information to be underwrited) can be quickly and efficiently queried, so the second identifier is used to distinguish between multiple different underwriting subsets.
Specifically, the age group of the age in the information to be underwritten or the historical underwriting information is searched through a first identifier, then a unique underwriting subset corresponding to each underwriting factor in the information to be underwritten or the historical underwriting information is obtained through a second identifier, a self-adaptive exhaustive-algorithm (SAEA) is generated through adaptive training in which a plurality of pieces of historical underwriting information are continuously input and output in a model of an exhaustive algorithm, then the trained exhaustive-algorithm (SAEA) is used as the underwriting model, the adaptive enumeration set is stored in the underwriting model, when underwriting the information to be underwriting, the underwriting information can be input into the underwriting model first, the historical underwriting information matched with the information to be underwriting can be searched in the adaptive enumeration set, if the historical underwriting information matched with the information to be underwrited is searched, and further obtaining an underwriting result of the information to be underwrited through historical underwriting information.
In practical application, the adaptive enumeration set is continuously updated and perfected. Wherein the exhaustive algorithm is characterized by: the calculation result (exhaustive set) of all factor combinations can be exhausted by the calculation factors of the field in a specific field range, and the algorithm is an exhaustive method. With the increase of the number of the calculation factors and the range of the calculation factor values, the exhaustive calculation amount is increased in a geometric level, and the efficiency is not high. The sampling data variable is introduced on the basis of an exhaustive algorithm, a calculation result can be obtained from one sampling data, and the result is continuously recorded and accumulated, so that a result set is generated, wherein the result set is a subset of a calculation result set (an exhaustive set) of all factor combinations and is called an adaptive enumerated set. The algorithm is a reverse calculation algorithm derived based on an exhaustive algorithm, with the goal of generating an adaptive enumerated set, rather than a full-scale set (exhaustive set). And this set can be enriched continuously as the sampled data changes, called the adaptive property. The higher the precision and value degree of the sampled data in the field, the higher the precision and value degree of the adaptive enumeration set.
How to search for the historical underwriting information matched with the information to be underwriting is achieved after the information to be underwriting is input into an underwriting model, see fig. 5, where fig. 5 is a schematic flow chart of an underwriting method according to still another embodiment of the present invention, and this embodiment introduces details on how to achieve the search for the historical underwriting information matched with the information to be underwriting on the basis of the above-described embodiment, for example, on the basis of the embodiment described in fig. 2. After the inputting the information to be underwritten into an underwriting model, the method further comprises:
s501, encrypting each underwriting factor in the information to be underwrited through a Hash algorithm to obtain each encrypted underwriting factor;
s502, searching whether target historical underwriting information exists in the self-adaptive enumeration set, wherein the target historical underwriting information is the historical underwriting information consistent with the encrypted underwriting factors;
and S503, if the target historical underwriting information exists, acquiring the target historical underwriting information, and using the target historical underwriting information as the historical underwriting information matched with the information to be underwrited.
In this embodiment, each underwriting factor in the information to be underwrited is encrypted through a hash algorithm to obtain each encrypted underwriting factor, each encrypted underwriting factor conforms to a description mode of an underwriting rule corresponding to historical underwriting information, then a target underwriting subset is determined from each underwriting subset containing a first identifier or a second identifier in a self-adaptive enumeration set, if the target underwriting subset exists, whether target historical underwriting information exists or not is searched from the target underwriting subset, that is, the historical underwriting information consistent with each encrypted underwriting factor, and if the target historical underwriting information exists, that is, the historical underwriting information matched with the information to be underwrited is obtained, so that fast underwriting based on an underwriting model can be achieved, and time and resources are saved.
In practical application, an adaptive enumeration set generated by the SAEA Algorithm in the adaptive fast underwriting node is persisted to a storage carrier (REDIS, which is an open source written in ANSI C language, supports network, a log-type or Key-Value database that can be based on memory and can be persisted, and provides APIs of multiple languages, a hash Algorithm (i.e., Message Digest Algorithm, MD5) is performed on a Key Value as a Value of a calculation factor, a Value is an underwriting result of underwriting check, i.e., pass or fail), after a terminal or a server collects or receives information to be underwriting, i.e., a front end collects insurance information, the terminal or the server first calls an underwriting model, i.e., calls the adaptive fast underwriting node, the node encrypts the calculation factor Value by MD5, the encrypted Value is inquired from the REDIS whether the result exists, if the result exists, the result is used as an underwriting result, if the order processing node passes the process, the process is pushed to the order processing node, the check and guarantee result is recorded and pushed to the order processing staff, and if the order processing node does not pass the process, the input insurance information (information to be checked and guaranteed) node is returned.
Optionally, after the information to be underwritten is input into the underwriting model, how to process the historical underwriting information that is not acquired in the adaptive enumeration set and is matched with the information to be underwritten is processed, as shown in fig. 6, fig. 6 is a schematic flow diagram of an underwriting method according to still another embodiment of the present invention, and this embodiment describes in detail how to process the historical underwriting information that is not acquired and is matched with the information to be underwritten on the basis of the above embodiment. After the inputting the information to be underwritten into an underwriting model, the method further comprises:
s601, if the historical underwriting information matched with the information to be underwrited is not obtained in the self-adaptive enumeration set generated by the underwriting model, obtaining a target underwriting rule matched with the information to be underwrited according to the preset underwriting rule configured in the exhaustive algorithm;
and S602, taking an underwriting result corresponding to the target underwriting rule as an underwriting result of the information to be underwrited.
Optionally, after the obtaining of the target underwriting rule matched with the information to be underwrited, the method further includes: and storing the information to be underwritten and the underwriting result of the information to be underwritten in a corresponding underwriting subset or generating a new underwriting subset.
Optionally, after the information to be underwritten is input into an underwriting model, the method further includes: and generating an underwriting result of the information to be underwritten according to the preset underwriting rule configured in the exhaustive algorithm.
In this embodiment, if the historical underwriting information matched with the information to be underwriting is not obtained in the adaptive enumeration set generated by the underwriting model, an underwriting result matched with the information to be underwriting needs to be searched through a preset underwriting rule, wherein the underwriting result matched with the information to be underwriting is used as the underwriting result of the information to be underwriting, and the information to be underwriting and the underwriting result of the information to be underwriting are stored in a corresponding underwriting subset or a new underwriting subset is generated, so that the adaptive enumeration set is updated. Meanwhile, the determination of the approval result of the information to be approved can be realized by searching the historical approval information or can not be realized by searching the historical approval information. The method is realized by searching historical underwriting information: if the historical underwriting information matched with the information to be underwrited is found, taking an underwriting result of the historical underwriting information as an underwriting result of the information to be underwrited; if the historical underwriting information matched with the information to be underwrited is not found, calling the preset underwriting rule configured in the exhaustive algorithm to obtain a target underwriting rule matched with the information to be underwrited, and taking an underwriting result corresponding to the target underwriting rule as the underwriting result of the information to be underwrited; the method is realized without searching the historical underwriting information: after the information to be underwritten is input into an underwriting model, the preset underwriting rule configured in the exhaustive algorithm is directly called, a target underwriting rule matched with the information to be underwrited is obtained, an underwriting result corresponding to the target underwriting rule is used as the underwriting result of the information to be underwrited, and underwriting rules which need historical data and do not need the historical data are isolated.
In practical application, the flow diagram of the underwriting method shown in fig. 7 is combined. Front end: inputting insurance information, submitting an order, starting self-adaptive rapid insurance checking, and if the insurance information does not pass through the order, re-inputting the insurance information; if the order passes, the order is directly received by the node; and if the order is not received, verifying the underwriting rule, and if the order is not received, supplementing the data into the sample library and submitting the data to the node for order reception.
Specifically, if there is no historical underwriting information matching the information to be underwritten in the adaptive enumeration set, it means that the current data is not learned, and is not in the sample library (adaptive enumeration set), it needs to call underwriting check rules (preset underwriting rules) for processing, after the processing is completed, MD5 encryption is performed on the calculation factor (underwriting factor) of the sample data (information to be underwritten) as a KEY VALUE, and the VALUE is the underwriting check result and is stored in the sample library. The self-adaptive fast underwriting model is a core key processing node based on an SAEA algorithm. Compared with the prior scheme, the method has the following advantages:
1. the self-adaptive fast underwriting model has self-adaptive learning ability in an overall process mechanism, and the learning ability shows that a sample library can be enriched continuously according to real underwriting data until almost all underwriting groups are covered.
2. The mechanism of hitting the underwriting conclusion based on the REDIS sample library can greatly improve underwriting efficiency, and the underwriting processing aging estimation can be improved by more than 100 times.
3. The efficiency self-adaptive underwriting mechanism can continuously enrich the sample library, and the more the samples are covered, the higher the efficiency of the whole underwriting processing is.
4. The sample data is generated by automatic learning, and the generation of redundant data can be effectively avoided. And the method can be used for dimension analysis of insurable people and guiding to make a corresponding processing strategy.
5. The calculation factor can be adjusted at any time according to actual needs, and the method has strong expansibility.
Therefore, in practical application, the embodiment of the invention can greatly improve the processing speed of the underwriting, shield the bottleneck of the database in the prior art, has self-adaptive learning capability, can meet the requirement of the Internet architecture as the sample collection is richer and the processing speed is faster when the system runs, can be transversely expanded, and has higher flexibility.
In order to implement the underwriting method, the present embodiment provides an underwriting apparatus. Referring to fig. 8, fig. 8 is a schematic structural diagram of an underwriting apparatus according to an embodiment of the present invention; the underwriting device 80 includes: an information to be underwritten obtaining module 801 and a first underwriting result obtaining module 802; the information to be underwritten acquiring module 801 is configured to acquire information to be underwritten; the first underwriting result obtaining module 802 is configured to input the information to be underwriting into an underwriting model, and if historical underwriting information matched with the information to be underwriting is obtained in an adaptive enumeration set generated by the underwriting model, take an underwriting result of the historical underwriting information as an underwriting result of the information to be underwriting, where the underwriting model is obtained by performing adaptive training by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm; the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information.
In this embodiment, by providing the to-be-certified information obtaining module 801 and the first certified result obtaining module 802, the to-be-certified information is obtained and input into the certified model for certifying the to-be-certified information through the certified model, if the historical certified information matched with the to-be-certified information is obtained in the adaptive enumeration set generated by the certified model, the certified result of the historical certified information is used as the certified result of the to-be-certified information, and the certified model is obtained by performing adaptive training by using a plurality of historical certified information as samples and adopting an exhaustive algorithm, so that the certification of the warranty can be quickly realized, and the customer experience is improved. According to the scheme, the information to be underwritten is input into the underwriting model through the underwriting model, the underwriting result of the information to be underwritten can be quickly searched in a self-adaptive enumeration set stored in the underwriting model, the acquired underwriting result of the historical underwriting information matched with the information to be underwrited is used as the underwriting result of the information to be underwrited, the underwriting efficiency is high, and meanwhile, the user experience is improved.
The apparatus provided in this embodiment may be used to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.
Optionally, fig. 9 is a schematic structural diagram of an underwriting device according to yet another embodiment of the present invention, and this embodiment describes the underwriting device in detail on the basis of the foregoing embodiment, for example, on the basis of the embodiment shown in fig. 8. Each piece of historical underwriting information comprises a plurality of underwriting factors, and the underwriting factors form an underwriting rule; the device further comprises: a history underwriting information obtaining module 803, a second underwriting result obtaining module 804, an underwriting subset generating module 805 and an underwriting model determining module 806; the historical underwriting information obtaining module 803 is configured to obtain a plurality of pieces of historical underwriting information before the obtaining of the information to be underwrited; the second underwriting result obtaining module 804 is configured to, for each piece of historical underwriting information, use a plurality of underwriting factors in the historical underwriting information as input quantities of the exhaustive algorithm, perform adaptive training on the exhaustive algorithm through underwriting results corresponding to preset underwriting rules configured in the exhaustive algorithm, obtain underwriting results of the historical underwriting information, where the historical underwriting information and the corresponding underwriting results of the historical underwriting information form a sample; the underwriting subset generating module 805 is configured to divide each sample to generate a plurality of underwriting subsets, where the plurality of underwriting subsets form the adaptive enumeration set; the underwriting model determining module 806 is configured to use the trained exhaustive algorithm as the underwriting model, where the adaptive enumeration set is stored in the underwriting model.
Optionally, in this embodiment, on the basis of the above-described embodiment, for example, on the basis of the embodiment shown in fig. 9, the underwriting subset generating module 805 is described in detail. Wherein the plurality of underwriting factors include risk species, age, gender, occupation category, premium, area under insurance, accident premium, and whether additional risk is bound; the underwriting subset generating module 805 is specifically configured to:
according to a plurality of underwriting factors in all the historical underwriting information, dividing all the historical underwriting information into underwriting subsets, wherein the underwriting results comprise the same risk species, occupation types, insurance amounts, insuring areas, personal accident insurance amounts, underwriting passing historical underwriting information corresponding to whether additional risks are bound or not, and the underwriting results of the underwriting passing historical underwriting information; acquiring ages in all historical underwriting information in all underwriting subsets aiming at each underwriting subset in all underwriting subsets, and taking age groups corresponding to all the ages as first identifications of the underwriting subsets; and performing secondary identification on the first identifications of all the underwriting subsets, and marking the underwriting subsets containing the same first identifications with second identifications, wherein the second identifications are used for distinguishing a plurality of different underwriting subsets.
Optionally, the present embodiment describes the underwriting device in detail on the basis of the above-mentioned embodiment, for example, on the basis of the embodiment shown in fig. 8. The device further comprises: a first underwriting information processing module; the first underwriting information processing module is configured to: after the information to be certified is input into a certification model, encrypting each certification factor in the information to be certified through a Hash algorithm to obtain each encrypted certification factor; searching whether target historical underwriting information exists in the self-adaptive enumeration set, wherein the target historical underwriting information is historical underwriting information consistent with the encrypted underwriting factors; and if so, acquiring the target historical underwriting information, and taking the target historical underwriting information as historical underwriting information matched with the information to be underwrited.
Optionally, the present embodiment describes the underwriting device in detail on the basis of the above-mentioned embodiment, for example, on the basis of the embodiment shown in fig. 8. The device further comprises: the second underwriting information processing module; the second underwriting information processing module is configured to: after the information to be underwritten is input into an underwriting model, if historical underwriting information matched with the information to be underwritten is not acquired in a self-adaptive enumeration set generated by the underwriting model, acquiring a target underwriting rule of the information to be underwritten through the preset underwriting rule configured in the exhaustive algorithm; and taking the underwriting result corresponding to the target underwriting rule as the underwriting result of the information to be underwrited.
Optionally, the apparatus further comprises: a storage module to: and storing the information to be underwritten and the underwriting result of the information to be underwritten in a corresponding underwriting subset or generating a new underwriting subset.
Optionally, the apparatus further comprises: the underwriting result generating module is used for: and after the information to be underwritten is input into an underwriting model, generating an underwriting result of the information to be underwritten through the preset underwriting rule configured in the exhaustive algorithm.
The embodiment of the invention can greatly improve the processing speed of the underwriting, shield the database bottleneck in the prior art, has self-adaptive learning capability, can meet the requirement of an internet framework as the sample collection is richer and the processing speed is faster when the system runs, can be transversely expanded, and has higher flexibility.
In order to implement the underwriting method, the embodiment provides an electronic device. Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 10, the electronic apparatus 100 of the present embodiment includes: a processor 1001 and a memory 1002; the memory 1002 is used for storing computer execution instructions; the processor 1001 is configured to execute computer-executable instructions stored in the memory to implement the steps performed in the above embodiments. Reference may be made in particular to the description relating to the method embodiments described above.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the method for underwriting is implemented as described above.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form. In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware form, and can also be realized in a form of hardware and a software functional unit.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present invention are not limited to only one bus or one type of bus. The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An underwriting method, comprising:
acquiring information to be certified and protected;
inputting the information to be underwritten into an underwriting model, if historical underwriting information matched with the information to be underwritten is acquired in a self-adaptive enumeration set generated by the underwriting model, taking an underwriting result of the historical underwriting information as an underwriting result of the information to be underwritten, wherein the underwriting model is acquired by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm for self-adaptive training;
the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information.
2. The method of claim 1, wherein each of the historical underwriting information includes a plurality of underwriting factors, and the plurality of underwriting factors form an underwriting rule;
before the obtaining of the information to be certified, the method further comprises:
acquiring a plurality of historical underwriting information;
aiming at each historical underwriting information, taking a plurality of underwriting factors in the historical underwriting information as input quantity of the exhaustive algorithm, carrying out self-adaptive training on the exhaustive algorithm through underwriting results corresponding to preset underwriting rules configured in the exhaustive algorithm to obtain underwriting results of the historical underwriting information, wherein the historical underwriting information and the corresponding underwriting results of the historical underwriting information form a sample;
dividing each sample to generate a plurality of underwriting subsets, wherein the plurality of underwriting subsets form the self-adaptive enumeration set;
and taking the trained exhaustive algorithm as the underwriting model, wherein the self-adaptive enumeration set is stored in the underwriting model.
3. The method of claim 2, wherein the plurality of underwriting factors include risk species, age, gender, occupational category, premium, area under insurance, accident premium, and whether additional risks are tied;
the dividing each sample to generate a plurality of underwriting subsets includes:
according to a plurality of underwriting factors in all the historical underwriting information, dividing all the historical underwriting information into underwriting subsets, wherein the underwriting results comprise the same risk species, occupation types, insurance amounts, insuring areas, personal accident insurance amounts, underwriting passing historical underwriting information corresponding to whether additional risks are bound or not, and the underwriting results of the underwriting passing historical underwriting information;
acquiring ages in all historical underwriting information in all underwriting subsets aiming at each underwriting subset in all underwriting subsets, and taking age groups corresponding to all the ages as first identifications of the underwriting subsets;
and performing secondary identification on the first identifications of all the underwriting subsets, and marking the underwriting subsets containing the same first identifications with second identifications, wherein the second identifications are used for distinguishing a plurality of different underwriting subsets.
4. The method of claim 2, wherein after the inputting the information to be underwritten into an underwriting model, the method further comprises:
encrypting each underwriting factor in the information to be underwrited by a Hash algorithm to obtain each encrypted underwriting factor;
searching whether target historical underwriting information exists in the self-adaptive enumeration set, wherein the target historical underwriting information is historical underwriting information consistent with the encrypted underwriting factors;
and if so, acquiring the target historical underwriting information, and taking the target historical underwriting information as historical underwriting information matched with the information to be underwrited.
5. The method according to any one of claims 2-4, wherein after said entering said information to be underwritten into an underwriting model, the method further comprises:
if the historical underwriting information matched with the information to be underwrited is not acquired in the self-adaptive enumeration set generated by the underwriting model, acquiring a target underwriting rule matched with the information to be underwrited through the preset underwriting rule configured in the exhaustive algorithm;
and taking the underwriting result corresponding to the target underwriting rule as the underwriting result of the information to be underwrited.
6. The method of claim 5, wherein after the obtaining of the target underwriting rule matching the information to be underwritten, the method further comprises:
and storing the information to be underwritten and the underwriting result of the information to be underwritten in a corresponding underwriting subset or generating a new underwriting subset.
7. The method of claim 2, wherein after the inputting the information to be underwritten into an underwriting model, the method further comprises:
and generating an underwriting result of the information to be underwritten according to the preset underwriting rule configured in the exhaustive algorithm.
8. An underwriting device, comprising:
the information acquisition module to be certified is used for acquiring information to be certified;
the first underwriting result acquisition module is used for inputting the information to be underwritten into an underwriting model, and if historical underwriting information matched with the information to be underwritten is acquired in an adaptive enumeration set generated by the underwriting model, the underwriting result of the historical underwriting information is used as the underwriting result of the information to be underwritten, and the underwriting model is obtained by using a plurality of pieces of historical underwriting information as samples and adopting an exhaustive algorithm for adaptive training;
the adaptive enumeration set comprises a plurality of underwriting subsets, and each sample in each underwriting subset comprises historical underwriting information and underwriting results of the historical underwriting information.
9. An electronic device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the underwriting method of any of claims 1 to 7.
10. A computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a processor, implement the underwriting method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911014238.9A CN110728585A (en) | 2019-10-23 | 2019-10-23 | Authority guaranteeing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911014238.9A CN110728585A (en) | 2019-10-23 | 2019-10-23 | Authority guaranteeing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110728585A true CN110728585A (en) | 2020-01-24 |
Family
ID=69222951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911014238.9A Pending CN110728585A (en) | 2019-10-23 | 2019-10-23 | Authority guaranteeing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728585A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625646A (en) * | 2020-05-22 | 2020-09-04 | 泰康保险集团股份有限公司 | Method and device for processing insurance policy, electronic equipment and storage medium |
| CN112347201A (en) * | 2020-11-26 | 2021-02-09 | 德联易控科技(北京)有限公司 | Information processing method, information processing device and terminal equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460692A (en) * | 2018-03-23 | 2018-08-28 | 深圳市慧择保险经纪有限公司 | A kind of line coker guarantor method, apparatus, equipment and storage medium based on health insurance |
| CN108492197A (en) * | 2018-03-15 | 2018-09-04 | 北京百度网讯科技有限公司 | Prediction technique of being in danger, device and the server of insurance |
| CN109559130A (en) * | 2018-10-26 | 2019-04-02 | 阿里巴巴集团控股有限公司 | A kind of processing method of insurance business, device and equipment |
-
2019
- 2019-10-23 CN CN201911014238.9A patent/CN110728585A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492197A (en) * | 2018-03-15 | 2018-09-04 | 北京百度网讯科技有限公司 | Prediction technique of being in danger, device and the server of insurance |
| CN108460692A (en) * | 2018-03-23 | 2018-08-28 | 深圳市慧择保险经纪有限公司 | A kind of line coker guarantor method, apparatus, equipment and storage medium based on health insurance |
| CN109559130A (en) * | 2018-10-26 | 2019-04-02 | 阿里巴巴集团控股有限公司 | A kind of processing method of insurance business, device and equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625646A (en) * | 2020-05-22 | 2020-09-04 | 泰康保险集团股份有限公司 | Method and device for processing insurance policy, electronic equipment and storage medium |
| CN111625646B (en) * | 2020-05-22 | 2023-04-21 | 泰康保险集团股份有限公司 | Method, device, electronic equipment and storage medium for processing insurance policy |
| CN112347201A (en) * | 2020-11-26 | 2021-02-09 | 德联易控科技(北京)有限公司 | Information processing method, information processing device and terminal equipment |
| CN112347201B (en) * | 2020-11-26 | 2021-05-18 | 德联易控科技(北京)有限公司 | Information processing method, information processing device and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200057958A1 (en) | Identification and application of hyperparameters for machine learning | |
| US20160285918A1 (en) | System and method for classifying documents based on access | |
| JP2017091515A (en) | Computer-implemented system and method for automatically identifying attributes for anonymization | |
| US10452627B2 (en) | Column weight calculation for data deduplication | |
| CN111241389B (en) | Sensitive word filtering method and device based on matrix, electronic equipment and storage medium | |
| KR20110081177A (en) | Detection of confidential information | |
| WO2007044763A2 (en) | System and method for detecting fraudulent transactions | |
| CN109885597B (en) | User grouping processing method and device based on machine learning and electronic terminal | |
| CN110679114B (en) | Method for estimating deletability of data object | |
| CN116194922A (en) | Protecting sensitive data in a document | |
| CN109558409B (en) | Data processing method and device | |
| CN111767565A (en) | Data desensitization processing method, processing device and storage medium | |
| CN114186275A (en) | Privacy protection method and device, computer equipment and storage medium | |
| CN114186760A (en) | Analysis method and system for stable operation of enterprise and readable storage medium | |
| CN110728585A (en) | Authority guaranteeing method, device, equipment and storage medium | |
| CN114154198A (en) | Data processing method and device | |
| US11308130B1 (en) | Constructing ground truth when classifying data | |
| CN112348041B (en) | Log classification and log classification training method and device, equipment and storage medium | |
| CN110661913B (en) | User sorting method and device and electronic equipment | |
| Alneyadi et al. | A semantics-aware classification approach for data leakage prevention | |
| CN113051601A (en) | Sensitive data identification method, device, equipment and medium | |
| CN114817518B (en) | License handling method, system and medium based on big data archive identification | |
| CN113269179B (en) | Data processing method, device, equipment and storage medium | |
| CN111291370B (en) | Network data intrusion detection method, system, terminal and storage medium | |
| CN113688206A (en) | Text recognition-based trend analysis method, device, equipment and 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: 20200124 |
|
| RJ01 | Rejection of invention patent application after publication |