CN110070449A - Project kind matching process, device, computer equipment and storage medium - Google Patents
Project kind matching process, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110070449A CN110070449A CN201910198963.XA CN201910198963A CN110070449A CN 110070449 A CN110070449 A CN 110070449A CN 201910198963 A CN201910198963 A CN 201910198963A CN 110070449 A CN110070449 A CN 110070449A
- Authority
- CN
- China
- Prior art keywords
- history information
- risk
- user
- project
- history
- 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.)
- Withdrawn
Links
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of project kind matching process, device, computer equipment and storage medium, include the following steps: the history information for obtaining target user；According to the determining destination item type to match with the target user of the history information, wherein the destination item type is to search to obtain and project kind corresponding to the highest historical user of history information similarity in preset historical data base；The risk classifications of the destination item type are determined according to the history information and preset risk assessment rule, wherein, the risk assessment rule is that risk score is calculated according to the history information, and the information matches rule of the risk classifications is determined according to the risk score.It matches to obtain corresponding project kind and risk classifications by the history information according to user, carries out the human cost of screening verification when can effectively reduce items selection to user information, improve the matched accuracy of project kind.
Description
Technical field
The present invention relates to computer application technologies, more particularly to a kind of project kind matching process, device, calculating
Machine equipment and storage medium.
Background technique
With the development of economy and society, the insurance awareness of people is more and more stronger, and more and more users start purchase and protect
Danger service.However, the type with project kind is more and more, user selected in numerous project kinds in be suitble to itself guarantor
Danger becomes more and more difficult.
Commercial health insurance is the important component of China's health security system, accelerates the development of commercial health insurance,
Be conducive to tamp multi-level health security system, meet the diversified health care demand of the people.At this stage, health insurance
The selection of project is time-consuming and laborious for user and insurance institution mainly by manually completing under line, if user is same
When there are when multinomial health problem, user and insurance company, which require to expend bigger cost, could complete entire project kind
Process is selected, had both been unfavorable for user in this way and has secured good health in time the protection of insurance, being also unfavorable for insurance company reduces health insurance
The management and compensation cost of project.
Summary of the invention
The embodiment of the present invention is capable of providing a kind of saving human resources, for the project kind of user's accurate match project kind
Matching process, device, computer equipment and storage medium.
In order to solve the above technical problems, the technical solution that the embodiment of the invention uses is: providing a kind of item
Mesh type matching process, comprising the following steps:
Obtain the history information of target user；
According to the determining destination item type to match with the target user of the history information, wherein the target
Project kind in preset historical data base search obtain it is right with the highest historical user of history information similarity
The project kind answered；
The risk classifications of the destination item type are determined according to the history information and preset risk assessment rule,
In, the risk assessment rule is that risk score is calculated according to the history information, determines institute according to the risk score
State the information matches rule of risk classifications.
Optionally, described that the destination item type is determined according to the history information and preset risk assessment rule
The step of risk classifications, comprising the following steps:
The risk score of the target user is calculated according to the history information and preset computation rule, wherein described
Computation rule is to acquire corresponding score according to project data different in history information, is commented using the sum of all scores as risk
The data processing rule divided；
Obtain the risk classifications matching rule of the destination item type, wherein the risk classifications matching rule is root
According to the risk score of user identify project type risk classifications Data Matching rule；
The risk classifications of the destination item type are determined according to the risk score and the risk classifications matching rule.
It optionally, include multiple project datas in the history information, it is described according to the history information and preset meter
Calculate the step of rule calculates the risk score of the target user, comprising the following steps:
The reciprocal fraction of all items data in the history information is calculated according to the history information；
Defining the sum of all described reciprocal fractions is the risk score.
Optionally, described the step of determining destination item type according to the history information and preset recommendation rules, packet
Include following steps:
The medical history characteristics vector of the target user is determined according to the history information；
It is right with the smallest history feature vector institute of the medical history characteristics vector distance to search in preset historical data base
The user answered is as the historical user；
The project kind for defining the historical user is the destination item type.
Optionally, the step of medical history characteristics vector that the target user is determined according to the history information, including
Following step:
The history information is input in preset Feature Selection Model, wherein the Feature Selection Model is to have instructed
Practice to convergent, the neural network model of corresponding feature vector is generated for the history information according to input；
The medical history characteristics vector is determined according to the output result of the Feature Selection Model.
Optionally, described that the destination item type is determined according to the history information and preset risk assessment rule
After the step of risk classifications, include the following steps:
The medical history keyword of the target user is determined according to the history information；
The abnormal risk type that there are mapping relations with the medical history keyword is searched in preset vulnerability database；
The abnormal risk type of the destination item type is determined according to the abnormal risk type that lookup obtains.
Optionally, before the step of history information for obtaining target user, include the following steps:
Obtain the medical history data of the target user；
Contents extraction is carried out to the medical history data and obtains corresponding history data；
The history information of the target user is generated according to the history data.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of project kind recommendation apparatus, comprising:
Module is obtained, for obtaining the history information of target user；
Processing module, the destination item type for being matched according to history information determination with the target user,
Wherein, the destination item type be in preset historical data base search obtain it is highest with the history information similarity
Project kind corresponding to historical user；
Execution module, for determining the destination item type according to the history information and preset risk assessment rule
Risk classifications, wherein the risk assessment rule is according to the history information risk score to be calculated, according to the wind
Danger scoring determines the information matches rule of the risk classifications.
Optionally, the project kind recommendation apparatus, further includes:
First computational submodule, for calculating the target user's according to the history information and preset computation rule
Risk score, wherein the computation rule is to acquire corresponding score according to project data different in history information, with all
Data processing rule of the sum of the score as risk score；
First acquisition submodule, for obtaining the risk classifications matching rule of the destination item type, wherein the wind
Dangerous type matching rule be according to the risk score of user identify project type risk classifications Data Matching rule；
First processing submodule, for determining the target according to the risk score and the risk classifications matching rule
The risk classifications of project kind.
Optionally, the project kind recommendation apparatus, further includes:
Second computational submodule, for calculating pair of all items data in the history information according to the history information
Answer score；
First implementation sub-module is the risk score for defining the sum of all described reciprocal fractions.
Optionally, the project kind recommendation apparatus, further includes:
Second processing submodule, for determining the medical history characteristics vector of the target user according to the history information；
First searches submodule, minimum with the medical history characteristics vector distance for searching in preset historical data base
History feature vector corresponding to user as the historical user；
Second implementation sub-module, the project kind for defining the historical user are the destination item type.
Optionally, the project kind recommendation apparatus, further includes:
First input submodule, for the history information to be input in preset Feature Selection Model, wherein described
Feature Selection Model is to have trained to convergent, and the nerve net of corresponding feature vector is generated for the history information according to input
Network model；
Third handle submodule, for the output result according to the Feature Selection Model determine the medical history characteristics to
Amount.
Optionally, the project kind recommendation apparatus, further includes:
Fourth process submodule, for determining the medical history keyword of the target user according to the history information；
Second searches submodule, with the medical history keyword there is mapping to close for searching in preset vulnerability database
The abnormal risk type of system；
5th processing submodule, the abnormal risk type for being obtained according to lookup determine the destination item type
Abnormal risk type.
Optionally, the project kind recommendation apparatus, further includes:
Second acquisition submodule, for obtaining the medical history data of the target user；
First extracting sub-module obtains corresponding history data for carrying out contents extraction to the medical history data；
6th processing submodule, for generating the history information of the target user according to the history data.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of computer equipment, including memory and processing
Device is stored with computer-readable instruction in the memory, when the computer-readable instruction is executed by the processor, so that
The processor executes the step of project kind matching process described above.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of storage Jie for being stored with computer-readable instruction
Matter, when the computer-readable instruction is executed by one or more processors, so that one or more processors execute above-mentioned institute
The step of stating project kind matching process.
The beneficial effect of the embodiment of the present invention is: by utilizing the production recommended for historical user existing in historical record
Product are matched according to the history information of user, search the most similar historical user of corresponding situation, will be recommended for historical user
Or project kind that project kind that historical user selects is remembered as target, can be effectively according to the history information of user
Accurately select product for user, with it is traditional by manually selected and recommend in the way of, the scheme of the embodiment of the present invention
It can be effectively saved time and the human cost of project kind selection, improve the accuracy of recommended project type, further
Ground is identified project the risk classifications of type using the history information of user, is reduced artificial nucleus and is protected the mistake that may occur, improves core
Protect efficiency and accuracy.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the basic procedure schematic diagram of project kind of embodiment of the present invention matching process；
Fig. 2 is the flow diagram for the risk classifications that the embodiment of the present invention determines destination item type；
Fig. 3 is the flow diagram that the embodiment of the present invention calculates target user's risk score；
Fig. 4 is the flow diagram that the embodiment of the present invention determines destination item type；
Fig. 5 is the flow diagram for the medical history characteristics vector that the embodiment of the present invention determines target user；
Fig. 6 is the flow diagram that the embodiment of the present invention determines abnormal risk type；
Fig. 7 is the flow diagram for the history information that the embodiment of the present invention obtains target user；
Fig. 8 is the basic structure block diagram of project kind of embodiment of the present invention recommendation apparatus；
Fig. 9 is computer equipment of embodiment of the present invention basic structure block diagram.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
In some processes of the description in description and claims of this specification and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those skilled in the art's every other implementation obtained under that premise of not paying creative labor
Example, shall fall within the protection scope of the present invention.
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and including receiving and emitting hardware
Equipment, have on bidirectional communication link, can execute two-way communication reception and emit hardware equipment.This equipment
It may include: honeycomb or other communication equipments, shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (PersonalCommunicationsService, PCS Personal Communications System), can be with
Combine voice, data processing, fax and/or communication ability；PDA (PersonalDigitalAssistant, individual digital
Assistant), may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, calendar and/
Or GPS (GlobalPositioningSystem, global positioning system) receiver；Conventional laptop and/or palmtop computer
Or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or other equipment.
" terminal " used herein above, " terminal device " can be it is portable, can transport, be mounted on the vehicles (aviation, sea-freight and/
Or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth and/or sky
Between any other position operation." terminal " used herein above, " terminal device " can also be communication terminal, access terminals,
Music/video playback terminal, for example, can be PDA, MID (MobileInternetDevice, mobile internet device) and/or
Mobile phone with music/video playing function is also possible to the equipment such as smart television, set-top box.
Specifically referring to Fig. 1, Fig. 1 is the basic procedure schematic diagram of the present embodiment project kind matching process.
As shown in Figure 1, a kind of project kind matching process, comprising the following steps:
S1100, the history information for obtaining target user；
User is when needing bought item type or understanding project kind, in the application program of intelligent terminal
Instruction is recommended in triggering, starts the selection process of project kind.Pass through the history information of application program typing user itself, medical history letter
Breath includes but is not limited to the illness experience of user and record etc. of being hospitalized, and in some embodiments, in history information further includes using
The living habit at family itself, for example whether excessive drinking of smoking, whether daily exercise and whether often stay up late, but not limited to this, it uses
In reflection user's risk that may be present.
The input method of history information can be user and directly input data, or the medical history data uploaded by user into
Row content recognition is extracted.Specifically, user inputs the disease keyword suffered from the application, in preset historical data
It is searched in library and obtains corresponding disease name, be selected as one of corresponding medical history project, each user can have multiple diseases
History project is select and set according to the actual conditions of user, on the other hand, may remind the user that upload medical history data, example
It such as diagnoses proof and is hospitalized and record, but not limited to this, the image that the medical history data of upload can be scanning or take pictures
File obtains key message therein carrying out content recognition to image file and by way of extracting text, such as diagnosis
Disease name or in hospital reason etc., using corresponding information as the history information of user
S1200, the destination item type to be matched according to history information determination with the target user, wherein institute
Stating destination item type is to search to obtain using with the highest history of the history information similarity in preset historical data base
Project kind corresponding to family；
History information is input in preset Feature Selection Model, Feature Selection Model is the information extraction according to input
Feature therein obtains the neural network model of feature vector, determines history information according to the output result of Feature Selection Model
Feature vector searches a feature vector nearest with features described above vector distance in historical data base, determines corresponding go through
History user and target user's situation are most close, to recommend target using the project kind of historical user as destination item type
User.
It is stored with a large amount of historical transactional information in historical data base, includes corresponding in every portion historical transactional information
Historical user information, the history information of historical user, the feature vector of historical user and project kind of final choice etc., but not
It is limited to this.Historical transactional information is the transaction record carried out in enterprise's history, can be the medical history formerly according to historical user
Information is the transaction record that user carried out project kind recommendation, for what is determined as similar users lookup and project kind
Reference standard.
S1300, the risk that the destination item type is determined according to the history information and preset risk assessment rule
Type, wherein the risk assessment rule is that risk score is calculated according to the history information, according to the risk score
Determine the information matches rule of the risk classifications；
The risk score that user is calculated according to history information, for reflecting risk possibility existing for user.Risk score
Can be calculated separately by the data of each project in the history information got, finally obtain total score as risk score,
Such as the corresponding score of various habits in the corresponding score of various diseases and living habit in illness experience.Risk is calculated
After scoring, the risk classifications matching rule of destination item type is obtained.All project kinds are correspondingly arranged in system
Risk classifications matching rule, risk classifications matching rule can carry out different settings, core according to the core guaranteed request of project kind
Guaranteed request is identical or same risk classifications matching rule can be used in approximate project kind, in project kind without more special
When different core guaranteed request, general risk classifications matching rule can be used, i.e., same risk classifications matching rule can be right
Answer a variety of project kinds.Corresponding risk classifications, risk are provided with for different risk scores in risk classifications matching rule
Type includes normally accepting insurance plus taking to accept insurance and declinature, but not limited to this, when the setting of risk classifications can be according to practical application
Difference be adjusted.After getting risk classifications matching rule, the risk of user in risk classifications matching rule is defined
Score risk classifications of the corresponding risk classifications as target user.
As shown in Fig. 2, step S1300 specifically includes the following steps:
S1310, the risk score that the target user is calculated according to the history information and preset computation rule,
In, the computation rule is to acquire corresponding score according to project data different in history information, with the sum of all scores work
For the data processing rule of risk score；It include the data of target user's difference illness project in history information, in history information
Different item types correspond to respective fractional value, and methods of marking for the definition of customer risk or can accept insurance according to enterprise
Range is determined, and formulates methods of marking according to actual applicable cases first, each disease or illness experience are set
A fixed corresponding score value, the size of score value are improved with the increase of risk, such as with fatty liver or Hyperlipemia are 1
Point, it is 5 points etc. with rheumatic heart disease.It is searched to obtain corresponding score value according to all data in user's history information, and
In code of points search less than the contents of a project can be defined as devoid of risk, i.e., 0 point.Getting corresponding point of each project
After number, all scores are summed, risk score of the obtained total score as target user.
S1320, the risk classifications matching rule for obtaining the destination item type, wherein the risk classifications matching rule
Then for according to the risk score of user identify project type risk classifications Data Matching rule；
Risk classifications matching rule is correspondingly arranged on for all project kinds in system, risk classifications matching rule
Can carry out different settings according to the core guaranteed request of project kind, core guaranteed request is identical or approximate project kind use it is same
General risk classifications can be used when project kind is without more special core guaranteed request in kind risk classifications matching rule
Matching rule, i.e., same risk classifications matching rule can correspond to a variety of project kinds.In risk classifications matching rule for
Different risk scores is provided with corresponding risk classifications, and risk classifications are including normally accepting insurance plus expense is accepted insurance and declinatured, but not
It is limited to this, the difference when setting of risk classifications can be according to practical application is adjusted.It is commented in the risk that user is calculated
/ after, get the corresponding risk classifications matching rule of destination item type.
S1330, the wind that the destination item type is determined according to the risk score and the risk classifications matching rule
Dangerous type；
After getting the corresponding risk classifications matching rule of destination item type, according to the risk score of target user
Corresponding risk classifications are searched in risk classifications matching rule.In some embodiments, risk is arranged in risk classifications to comment
Point gradient correspond to different risk classifications, such as risk score 50 is divided below, and normally to accept insurance, risk score 50-100 divides
, to add Fei Chengbao, risk score is more than 100 points, to declinature.Corresponding risk classifications are determined according to the risk score of user
For the risk classifications of destination item type.
Saved after destination item type has been determined artificial nucleus protect the step of, switch to calculate user risk score from
And the method for determining risk classifications, can save core protect when cost of labor and time cost, reduce artificial nucleus protect there may be
Mistake or because core caused by subjective many factors protects mistake, improve the accuracy that core is protected.
As shown in figure 3, step S1310 specifically includes the following steps:
S1311, the reciprocal fraction that all items data in the history information are calculated according to the history information；
It include the data of target user's difference illness project in history information, different item types are corresponding in history information
Respective fractional value, methods of marking the definition of customer risk or insurance coverage can be determined according to enterprise, first
Methods of marking is formulated according to actual applicable cases, a corresponding score is set for each disease or illness experience,
The size of score is improved with the increase of risk, such as with fatty liver or Hyperlipemia is 1 point, suffers from rheumatic heart
Disease is 5 points etc..It is searched to obtain corresponding score value according to all data in user's history information, and is searched not in code of points
To the contents of a project can be defined as devoid of risk, i.e., 0 point.
S1312, the sum of all reciprocal fractions are defined as the risk score；
The reciprocal fraction according to determined by disparity items data in user's history information is subjected to statistics summation, what is obtained is total
It is divided into the risk score of target user.
The risk score of user is calculated using the history information of user, the risk score of user is higher, the potential wind of user
Danger is higher, and risk possibility existing for user can be more intuitively reflected in a manner of risk score, improves what core was protected
Efficiency and accuracy.
As shown in figure 4, step S1200 specifically includes the following steps:
S1210, the medical history characteristics vector that the target user is determined according to the history information；
History information is input in Feature Selection Model, Feature Selection Model is to carry out feature extraction to the data of input
The neural network model of corresponding feature vector is obtained, the medical history of target user is determined according to the output result of Feature Selection Model
Feature vector, a kind of forms of characterization of the medical history characteristics vector as every history data feature of user.
S1220, in preset historical data base search with the smallest history feature of medical history characteristics vector distance to
The corresponding user of amount is as the historical user；
It is stored with a large amount of historical transactional information in historical data base, includes corresponding in every portion historical transactional information
User information, the history information of user, the feature vector of user and project kind of final choice etc., but not limited to this.History
Transaction Information is the transaction record carried out in enterprise's history, and can be formerly is that user carried out according to the history information of user
The transaction record that project kind is recommended, the reference standard for being searched as similar users and project kind determines.It is establishing
When historical data base, the history information of each user is input in Feature Selection Model, gets the corresponding spy of each user
Vector is levied, for the lookup foundation as similar users.After getting the medical history characteristics vector of target user, with historical data base
In all feature vector compare.The judgment method of distance can be by calculating the Europe between two vectors between feature vector
Family name's distance, the Euclidean distance obtained after medical history characteristics vector is calculated separately with feature vectors all in historical data base are arranged
Sequence determines that user corresponding to the wherein the smallest feature vector of Euclidean distance is historical user.
S1230, the project kind for defining the historical user are the destination item type；
The project kind of historical user is corresponded to after historical user is calculated according to the distance of feature vector, in historical record
Class is destination item type, recommends target user.In some embodiments, it is compared according to the distance between feature vector
To apart from the smallest multiple historical users, it is ranked up by the size of distance, the project kind of multi-user is shown, for
Target user selects, if there are identical project kind in multiple historical users, by the information of identical project kind into
Row folds, and only shows similarity highest one.
The method for searching the highest historical user of similarity using the distance of feature vector, can quickly and accurately search
It is target user's selection target project kind to the historical user similar with target user, and according to the project kind of historical user
Class dramatically saves the time that matched and searched project kind is carried out to the history information of historical user, while making the item recommended
Mesh type is more suitable the actual conditions of user.
As shown in figure 5, step S1210 specifically include the following steps:
S1211, the history information is input in preset Feature Selection Model, wherein the Feature Selection Model
To have trained to convergent, the neural network model of corresponding feature vector is generated for the history information according to input；
Feature Selection Model is classified according to project data different in the history information of user, the classification knot that will be obtained
Fruit is integrated into feature vector.In some embodiments, classify for each project data, relatively simple judgement side
Method is yes/no, corresponding 1 or 0, such as a certain disease project, there are relevant information then it is 1 in history information, is not present
It is then 0, history information can be filled in when generating according to specific list, and corresponding content is filled in specific project
In column, when generating feature vector, classified according to a variety of different disease projects of setting, it is every by the rule distribution of setting
Dimension corresponding to one project, the result that classification is obtained is as the data of corresponding dimension, according to point of each disease project
Class result generates feature vector.In other embodiments, the numerical value of each disease project can be divided into multiple class, example
If current illness is 2, once illness is 1, is 0 without data, the corresponding numerical value class of disease project can be answered according to actual
It is adjusted with scene, such as when characteristics of needs vector can more accurately reflect the medical history characteristics of user, it can be by one
A disease project is divided into more class.
S1212, the medical history characteristics vector is determined according to the output result of the Feature Selection Model；
Using the feature vector that Feature Selection Model exports as the medical history characteristics vector of target user.
By way of converting feature vector for the history information of user, keep similarity comparison between user more convenient fast
It is prompt.
As shown in fig. 6, further including following step after step S1300:
S1410, the medical history keyword that the target user is determined according to the history information；
It is preset with a large amount of keyword message in system, for carrying out the corresponding disease project of match cognization, medical history is believed
Breath carries out participle or sub-item, is then matched with the keyword message in system, searches and exists in user's history information
Keyword message, such as carcinoma of mouth or rheumatic heart disease etc., using keyword message present in history information as
The medical history keyword of user.In some embodiments, the determination of medical history keyword can also have timeliness, such as work as lookup
It obtains in user's history information there are carcinoma of mouth, the sick time of available carcinoma of mouth, such as with carcinoma of mouth or once currently
Suffer from carcinoma of mouth to have cured, but not limited to this.
S1420, the abnormal risk that there are mapping relations with the medical history keyword is searched in preset vulnerability database
Type；
After getting the medical history keyword of user, searching in vulnerability database with medical history keyword there is mapping to close
The abnormal risk type of system, abnormal risk type, that is, user because certain diseases when may cause the dangerous risk of biggish compensation,
Selection project kind excludes certain insurance coverages of setting.For example, user suffers from tumor stomach, in purchase disease phase
The part removed other than stomach can be protected when closing project kind, i.e., not undertake the wind damaged by disease of stomach
Danger.Each abnormal risk type corresponds to multiple medical history keywords, such as accepting insurance except stomach, corresponding tumor stomach,
Gastric perforation and subtotal gastrectomy etc. keyword.
S1430, the abnormal risk class that the destination item type is determined according to the abnormal risk type that lookup obtains
Type；
The abnormal risk type that obtained abnormal risk type is destination item type is searched in definition.
Abnormal risk type is determined using the history information of user, more efficiently ensure that when carrying out core guarantor to user
The accuracy of project kind improves core and protects efficiency, at the same save for user into verify artificial of abnormal risk type and when
Between cost.
As shown in fig. 7, further including following step before step S1100:
S1010, the medical history data for obtaining the target user；
Target user is uploaded when starting project kind recommended flowsheet, by medical history data by the application program of intelligent terminal
Into server, the content of upload can be the image file that medical history data is scanned or be obtained after taking pictures.Medical history data includes
But it is not limited to the case history of target user, be hospitalized record and diagnosis proof etc..
S1020, corresponding history data is obtained to medical history data progress contents extraction；
The medical history data input content that will acquire extracts in model, and contents extraction model can be existing according to input
Image document extract model that content therein generates corresponding text information, such as OCR Text region model etc..It gets
Text information of the output result of contents extraction model as medical history data, the text information then obtained for extraction close
The identification of key word generates the corresponding history data of each project in medical history data.
S1030, the history information that the target user is generated according to the history data；
The history data that will acquire is divided according to corresponding project, the history information of user is generated, some
In embodiment, subfield is carried out for each project in history information, after getting the history data of user, by medical history number
According to inserting in corresponding project subfield, to generate the history information completed.
The method that the history information of user is generated by the information extracted in user's medical history data, can be improved history information
The efficiency of typing, while the accuracy of typing is improved, avoid the mistake that may cause when manual entry.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of project kind recommendation apparatus.Referring specifically to
Fig. 8, Fig. 8 are the basic structure block diagram of this implementation project kind recommendation apparatus.
As shown in figure 8, project kind recommendation apparatus, comprising: obtain module 2100, processing module 2200 and execution module
2300.Wherein, the history information that module is used to obtain target user is obtained；Processing module is used to be determined according to the history information
The destination item type to match with the target user, wherein the destination item type is in preset historical data base
Middle lookup obtains and project kind corresponding to the highest historical user of history information similarity；Execution module is used for basis
The history information and preset risk assessment rule determine the risk classifications of the destination item type, wherein the risk
Assessment rule determines the risk classifications according to the risk score for risk score is calculated according to the history information
Information matches rule.
By being carried out according to the history information of user using the product recommended for historical user existing in historical record
Matching, searches the most similar historical user of corresponding situation, the project kind that recommend for historical user or historical user is selected
The project kind that class is remembered as target can be effectively that user accurately selects product according to the history information of user, with
It is traditional by manually selected and recommend in the way of, the scheme of the embodiment of the present invention can be effectively saved project kind choosing
The time selected and human cost improve the accuracy of recommended project type, further, are determined using the history information of user
The risk classifications of project kind reduce artificial nucleus and protect the mistake that may occur, and improve core and protect efficiency and accuracy.
In some embodiments, project kind recommendation apparatus further include: the first computational submodule, first obtain submodule
Block, the first processing submodule.Wherein the first computational submodule is used to be calculated according to the history information and preset computation rule
The risk score of the target user, wherein the computation rule is to be acquired pair according to project data different in history information
The score answered, using the sum of all scores as the data processing rule of risk score；First acquisition submodule is described for obtaining
The risk classifications matching rule of destination item type, wherein the risk classifications matching rule is the risk score according to user
The Data Matching rule of type of identifying project risk classifications；First processing submodule is used for according to the risk score and the wind
Dangerous type matching rule determines the risk classifications of the destination item type.
In some embodiments, project kind recommendation apparatus further include: the second computational submodule, first execute submodule
Block.Wherein, the second computational submodule is used to calculate pair of all items data in the history information according to the history information
Answer score；First implementation sub-module is the risk score for defining the sum of all described reciprocal fractions.
In some embodiments, project kind recommendation apparatus further include: second processing submodule, first search submodule
Block, the second implementation sub-module.Wherein, second processing submodule is used to determine the disease of the target user according to the history information
History feature vector；First, which searches submodule, is used to search with the medical history characteristics vector distance most in preset historical data base
User corresponding to small history feature vector is as the historical user；Second implementation sub-module is used for defining the history
The project kind at family is the destination item type.
In some embodiments, project kind recommendation apparatus further include: the first input submodule, third handle submodule
Block.Wherein, the first input submodule is for the history information to be input in preset Feature Selection Model, wherein described
Feature Selection Model is to have trained to convergent, and the nerve net of corresponding feature vector is generated for the history information according to input
Network model；Third processing submodule is used to determine the medical history characteristics vector according to the output result of the Feature Selection Model.
In some embodiments, project kind recommendation apparatus further include: fourth process submodule, second search submodule
Block, the 5th processing submodule.Wherein, fourth process submodule is used to determine the disease of the target user according to the history information
History keyword；Second, which searches submodule, is used for lookup and the medical history keyword in preset vulnerability database, and there is mapping to close
The abnormal risk type of system；5th processing submodule is used to determine the target according to the abnormal risk type that lookup obtains
The abnormal risk type of project kind.
In some embodiments, project kind recommendation apparatus further include: the second acquisition submodule, first extract submodule
Block, the 6th processing submodule.Wherein, the second acquisition submodule is used to obtain the medical history data of the target user；First extracts
Submodule is used to carry out contents extraction to the medical history data to obtain corresponding history data；6th processing submodule is used for basis
The history data generates the history information of the target user.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of computer equipment.Referring specifically to Fig. 9, Fig. 9
For the present embodiment computer equipment basic structure block diagram.
As shown in figure 9, the schematic diagram of internal structure of computer equipment.As shown in figure 9, the computer equipment includes passing through to be
Processor, non-volatile memory medium, memory and the network interface of bus of uniting connection.Wherein, the computer equipment is non-easy
The property lost storage medium is stored with operating system, database and computer-readable instruction, can be stored with control information sequence in database
Column, when which is executed by processor, may make processor to realize a kind of project kind matching process.The calculating
The processor of machine equipment supports the operation of entire computer equipment for providing calculating and control ability.The computer equipment
It can be stored with computer-readable instruction in memory, when which is executed by processor, processor may make to hold
A kind of project kind matching process of row.The network interface of the computer equipment is used for and terminal connection communication.Those skilled in the art
Member is it is appreciated that structure shown in figure, and only the block diagram of part-structure relevant to application scheme, is not constituted to this
The restriction for the computer equipment that application scheme is applied thereon, specific computer equipment may include more than as shown in the figure
Or less component, perhaps combine certain components or with different component layouts.
Processor obtains module 2100, processing module 2200 and execution module for executing in present embodiment in Fig. 8
2300 concrete function, program code and Various types of data needed for memory is stored with the above-mentioned module of execution.Network interface is used for
To the data transmission between user terminal or server.Memory in present embodiment is stored in project kind recommendation apparatus
Program code needed for executing all submodules and data, server is capable of the program code of invoking server and data execute institute
There is the function of submodule.
The present invention also provides a kind of storage mediums for being stored with computer-readable instruction, and the computer-readable instruction is by one
When a or multiple processors execute, so that one or more processors execute project kind match party described in any of the above-described embodiment
The step of method.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disk, CD, read-only memory (Read-OnlyMemory, ROM) or random storage note
Recall body (RandomAccessMemory, RAM) etc..
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of project kind matching process, which comprises the following steps:
Obtain the history information of target user；
According to the determining destination item type to match with the target user of the history information, wherein the destination item
Type be in preset historical data base search obtain with corresponding to the highest historical user of history information similarity
Project kind；
The risk classifications of the destination item type are determined according to the history information and preset risk assessment rule, wherein
The risk assessment rule is that risk score is calculated according to the history information, determines the wind according to the risk score
The information matches rule of dangerous type.
2. project kind matching process as described in claim 1, which is characterized in that described according to the history information and default
Risk assessment rule the step of determining the risk classifications of the destination item type, comprising the following steps:
The risk score of the target user is calculated according to the history information and preset computation rule, wherein the calculating
Rule is acquires corresponding score according to project data different in history information, using the sum of all scores as risk score
Data processing rule；
Obtain the risk classifications matching rule of the destination item type, wherein the risk classifications matching rule be according to
The risk score at family identify project type risk classifications Data Matching rule；
The risk classifications of the destination item type are determined according to the risk score and the risk classifications matching rule.
3. project kind matching process as claimed in claim 2, which is characterized in that include multiple projects in the history information
Data, the described the step of risk score of the target user is calculated according to the history information and preset computation rule, packet
Include following steps:
The reciprocal fraction of all items data in the history information is calculated according to the history information；
Defining the sum of all described reciprocal fractions is the risk score.
4. project kind matching process as described in claim 1, which is characterized in that described according to the history information and default
Recommendation rules the step of determining destination item type, comprising the following steps:
The medical history characteristics vector of the target user is determined according to the history information；
In preset historical data base search with the smallest history feature vector of the medical history characteristics vector distance corresponding to
User is as the historical user；
The project kind for defining the historical user is the destination item type.
5. project kind matching process as claimed in claim 4, which is characterized in that described to determine institute according to the history information
The step of stating the medical history characteristics vector of target user, includes the following steps:
The history information is input in preset Feature Selection Model, wherein the Feature Selection Model is to have trained extremely
It is convergent, the neural network model of corresponding feature vector is generated for the history information according to input；
The medical history characteristics vector is determined according to the output result of the Feature Selection Model.
6. project kind matching process as described in claim 1, which is characterized in that described according to the history information and default
Risk assessment rule the step of determining the risk classifications of the destination item type after, include the following steps:
The medical history keyword of the target user is determined according to the history information；
The abnormal risk type that there are mapping relations with the medical history keyword is searched in preset vulnerability database；
The abnormal risk type of the destination item type is determined according to the abnormal risk type that lookup obtains.
7. project kind matching process as claimed in any one of claims 1 to 6, which is characterized in that described to obtain target user's
Before the step of history information, include the following steps:
Obtain the medical history data of the target user；
Contents extraction is carried out to the medical history data and obtains corresponding history data；
The history information of the target user is generated according to the history data.
8. a kind of project kind recommendation apparatus characterized by comprising
Module is obtained, for obtaining the history information of target user；
Processing module, for according to the determining destination item type to match with the target user of the history information, wherein
The destination item type is to search to obtain and the highest history of history information similarity in preset historical data base
Project kind corresponding to user；
Execution module, for determining the wind of the destination item type according to the history information and preset risk assessment rule
Dangerous type, wherein the risk assessment rule is that risk score is calculated according to the history information, is commented according to the risk
Divide the information matches rule for determining the risk classifications.
9. a kind of computer equipment characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing project kind matching process described in the claims 1-7 any one.
10. a kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal
When device executes, so that mobile terminal is able to carry out a kind of project kind matching process, the method includes the claims 1-7
Project kind matching process described in any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910198963.XA CN110070449A (en) | 2019-03-15 | 2019-03-15 | Project kind matching process, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910198963.XA CN110070449A (en) | 2019-03-15 | 2019-03-15 | Project kind matching process, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110070449A true CN110070449A (en) | 2019-07-30 |
Family
ID=67366274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910198963.XA Withdrawn CN110070449A (en) | 2019-03-15 | 2019-03-15 | Project kind matching process, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070449A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652737A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance underwriting method and device based on text semantic processing |
| CN112132646A (en) * | 2020-08-27 | 2020-12-25 | 绿瘦健康产业集团有限公司 | User distribution processing method, device, medium and terminal equipment |
| CN112632995A (en) * | 2020-12-02 | 2021-04-09 | 北京健康之家科技有限公司 | User service request processing method and device, server and storage medium |
-
2019
- 2019-03-15 CN CN201910198963.XA patent/CN110070449A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652737A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance underwriting method and device based on text semantic processing |
| CN111652737B (en) * | 2020-04-17 | 2023-12-22 | 世纪保众(北京)网络科技有限公司 | Insurance verification method and apparatus based on text semantic processing |
| CN112132646A (en) * | 2020-08-27 | 2020-12-25 | 绿瘦健康产业集团有限公司 | User distribution processing method, device, medium and terminal equipment |
| CN112632995A (en) * | 2020-12-02 | 2021-04-09 | 北京健康之家科技有限公司 | User service request processing method and device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20110191336A1 (en) | Contextual image search | |
| CN104143005B (en) | A kind of related search system and method | |
| CN109189991A (en) | Repeat video frequency identifying method, device, terminal and computer readable storage medium | |
| WO2015200509A1 (en) | Determining affiliated colors from keyword searches of color palettes for color based searches | |
| JP4366119B2 (en) | Document processing device | |
| CN110070449A (en) | Project kind matching process, device, computer equipment and storage medium | |
| CN102893280B (en) | Data serching device, data search method and program | |
| CN110633407B (en) | Information retrieval method, device, equipment and computer readable medium | |
| US20110202543A1 (en) | Optimising content based image retrieval | |
| CN110472027A (en) | Intension recognizing method, equipment and computer readable storage medium | |
| CN114332680A (en) | Image processing method, video searching method, image processing device, video searching device, computer equipment and storage medium | |
| KR20170131924A (en) | Method, apparatus and computer program for searching image | |
| CN109582859B (en) | Insurance pushing method and device, computer equipment and storage medium | |
| US11615263B2 (en) | Content prediction based on pixel-based vectors | |
| CN107656918B (en) | Obtain the method and device of target user | |
| CN109388743A (en) | The determination method and apparatus of language model | |
| Wang et al. | Towards indexing representative images on the web | |
| US20240143684A1 (en) | Information presentation method and apparatus, and device and medium | |
| CN110543484A (en) | prompt word recommendation method and device, storage medium and processor | |
| WO2020000715A1 (en) | Index feature extraction-based stock index prediction method, server and storage medium | |
| JP2011014035A (en) | Retrieval system and retrieval method | |
| CN116976920A (en) | Commodity shopping guide method and device, equipment and medium thereof | |
| CN107092621A (en) | Information search method and device | |
| CN117271818B (en) | Visual question-answering method, system, electronic equipment and storage medium | |
| CN106776910A (en) | The display methods and device of a kind of Search Results |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190730 |