CN109254814A - Information configuring methods of insuring, device, computer equipment and storage medium neural network based - Google Patents
Information configuring methods of insuring, device, computer equipment and storage medium neural network based Download PDFInfo
- Publication number
- CN109254814A CN109254814A CN201810949641.XA CN201810949641A CN109254814A CN 109254814 A CN109254814 A CN 109254814A CN 201810949641 A CN201810949641 A CN 201810949641A CN 109254814 A CN109254814 A CN 109254814A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- insurance products
- user terminal
- image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Abstract
The embodiment of the invention discloses a kind of information configuring methods of insuring, device, computer equipment and storage medium neural network based, include the following steps: the information of the insurance products for the user's browsing for obtaining user terminal uploads；Information corresponding with the information of insurance products is obtained according to preset list database and collects list, wherein respectively information to be collected is respectively equipped with corresponding collection module in information collection list；List is collected according to information and calls corresponding collection module, and the collection module called is sent to the user terminal, so that user terminal shows the collection module called in the information gathering page of insurance products.By obtaining the information of the insurance products of user's browsing of user terminal uploads, artificial intelligence collects the information of user according to the information, improves the on-line selling rate of collection rate and insurance products on the line of user information.
Description
Technical field
The present embodiments relate to page configuration field of insuring, especially a kind of information configuration neural network based of insuring
Method, apparatus, computer equipment and storage medium.
Background technique
Insurance products are the synthesis that insurance company is tangible products and invisible service that market provides, and insurance products can be protected
Hinder user no matter when and where, because of the damage caused by any accident, can avoid allowing user and the household that lives by him to fall into
Impasse, and attenuating or loss of earning capacity without having to worry about income there itself, to provide certain living guarantee for user.
In the prior art, it when user buys insurance products, is required to be collected the user information of purchase insurance products,
And the collection of user information is required to user and goes at the sales department where insurance company or insurance agent submit information, so
Afterwards, after being checked by staff the identity information of user and the other information of offer, by the user and its purchase
Insurance products synchronize upload, complete the purchase of insurance products.
But user is needed to go to fixed business hall or fixed site in the prior art, it carries out artificially collecting user
User information, or made house calls by insurance agent, inefficiency discomfort zygonema is insured the quick sale of product.
Summary of the invention
The embodiment of the present invention provides a kind of by flexibly being collected according to the information of the insurance products browsed on user's line
Information configuring methods of insuring, device, computer equipment and the storage medium neural network based of user information.
In order to solve the above technical problems, the technical solution that the embodiment of the invention uses is: providing a kind of base
In the information configuring methods of insuring of neural network, include the following steps:
Obtain the information of the insurance products of user's browsing of user terminal uploads；
Information corresponding with the information of the insurance products, which is obtained, according to preset list database collects list,
In, respectively information to be collected is respectively equipped with corresponding collection module in the information collection list；
List is collected according to the information and calls corresponding collection module, and the collection module called is sent to described
User terminal, so that the user terminal shows the collection mould called in the information gathering page of the insurance products
Block.
Optionally, described that the corresponding collection module of list calling, and the collection mould that will have been called are collected according to the information
Block is sent to the user terminal, has called so that the user terminal is shown in the information gathering pages of the insurance products
After the step of collection module, and also specifically include the following steps:
The information of insuring corresponding with the insurance products of user terminal uploads is obtained, the information of insuring includes user's root
According to the user information and insurance information of information gathering page input；
The insurance policy of the insurance products is generated according to the user information and insurance information.
Optionally, described that the corresponding collection module of list calling, and the collection mould that will have been called are collected according to the information
Block is sent to the user terminal, has called so that the user terminal is shown in the information gathering pages of the insurance products
After the step of collection module, and also specifically include the following steps:
Obtain the facial image of user；
The facial image of the user is input to preset human face recognition model and carries out recognition of face, the recognition of face
Model is to train to convergent convolutional neural networks model.
Optionally, the facial image by the user is input to preset human face recognition model and carries out recognition of face,
Further include following step after the step of human face recognition model is training to convergent convolutional neural networks model:
The identity document information of user is obtained, the identity document information includes at least the name and identification card number of user
Code；
The name of the user and ID card No. are input to preset authentication model and carry out ID card information
Verifying.
Optionally, the training method of the convolutional neural networks model includes:
It obtains and is marked with classification referring to the training sample data of information, wherein the training sample data include: sample graph
Picture and the enhancing image for being derived from the sample image；
Training sample data input convolutional neural networks model is obtained to the classification judgement of the training sample data
Information；
Compare in the training sample data classification of different samples referring to information and the classification judge information whether one
It causes；
When the classification judges that information is inconsistent referring to information and the classification, the update of the iterative cycles iteration volume
Weight in product neural network model, until the classification terminates when judging that information is consistent with the classification referring to information.
Optionally, the acquisition methods of the training sample data include the following steps:
Obtain preset sample image；
The sample image is subjected to image procossing, to obtain at least one enhancing figure for being derived from the sample image
Picture.
Optionally, the described the step of sample image is subjected to image procossing, specifically include the following steps:
The sample image is input in preset Fuzzy Calculation model；
Obtain the enhancing image for being derived from the sample image of the Fuzzy Calculation model output.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of information configuration dress neural network based of insuring
It sets, comprising:
First obtains module, the information for the insurance products that the user for obtaining user terminal uploads browses；
Processing module, for obtaining letter corresponding with the information of the insurance products according to preset list database
Breath collects list, wherein respectively information to be collected is respectively equipped with corresponding collection module in the information collection list；
First execution module calls corresponding collection module for collecting list according to the information, and will call
Collection module is sent to the user terminal, so that the user terminal shows institute in the information gathering page of the insurance products
State the collection module called.
Optionally, further includes:
Second obtains module, described for obtaining the information of insuring corresponding with the insurance products of user terminal uploads
The user information and insurance information that information of insuring, which includes user, to be inputted according to the information gathering page；
Second execution module, the insurance for generating the insurance products according to the user information and insurance information are protected
It is single.
Optionally, further includes:
Third obtains module, for obtaining the facial image of user；
Face recognition module carries out face for the facial image of the user to be input to preset human face recognition model
Identification, the human face recognition model are to train to convergent convolutional neural networks model.
Optionally, further includes:
4th obtains module, and for obtaining the identity document information of user, the identity document information includes at least user
Name and ID card No.；
Authentication module, for by the name of the user and ID card No. be input to preset authentication model into
The verifying of row ID card information.
Optionally, further includes:
First acquisition submodule is marked with classification referring to the training sample data of information for obtaining, wherein the training
Sample data includes: sample image and the enhancing image for being derived from the sample image；
First implementation sub-module, for training sample data input convolutional neural networks model to be obtained the training
The classification of sample data judges information；
First compares submodule, for compare in the training sample data classification of different samples referring to information with it is described
Classification judges whether information is consistent；
The first adjustment submodule is used for when the classification judges that information is inconsistent referring to information and the classification, repeatedly
Weight in the update convolutional neural networks model of loop iteration, until the classification is believed referring to information and classification judgement
Terminate when ceasing consistent.
Optionally, further includes:
Second acquisition submodule, for obtaining preset sample image；
First processing submodule is derived from institute for the sample image to be carried out image procossing to obtain at least one
State the enhancing image of sample image.
Optionally, further includes:
Second implementation sub-module, for the sample image to be input in preset Fuzzy Calculation model；
Third acquisition submodule, for obtaining the enhancing for being derived from the sample image of the Fuzzy Calculation model output
Image.
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 execute described in the claims it is neural network based insure information configuring methods the step of.
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 power
Benefit require it is described it is neural network based insure information configuring methods the step of.
The kind for having the beneficial effect that the insurance products by the user's browsing for obtaining user terminal uploads of the embodiment of the present invention
Category information can get corresponding information according to the information of the insurance products in preset list database and collect column
Table is collected list calling collection module by the information and is sent to the user terminal collection module, and user terminal receives the receipts
The collection module is loaded in the information gathering page of the insurance products of user's browsing after collection module, thus to user's displaying and user
The corresponding information of the insurance products of browsing collects entry item, facilitates user to fill in input and buys letter required for the insurance products
Breath, buys function to realize on the line of insurance products.By the above method, it is able to solve people and needs to purchase according to user on line
The insurance products bought are collected the information of user, improve and sell on the line of collection rate and insurance products on the line of user information
Sell rate.
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 information configuring methods neural network based of insuring of the embodiment of the present invention；
Fig. 2 is the idiographic flow schematic diagram that the embodiment of the present invention generates insurance policy；
Fig. 3 is the flow diagram of user identity identification of the embodiment of the present invention；
Fig. 4 is the flow diagram that the identity document legitimacy of user of the embodiment of the present invention identifies；
Fig. 5 is the flow diagram of human face recognition model of embodiment of the present invention training method；
Fig. 6 is the flow diagram that the embodiment of the present invention obtains training sample data；
Fig. 7 is the flow diagram that sample image of the embodiment of the present invention carries out image procossing；
Fig. 8 is information configuration device basic structure schematic diagram neural network based of insuring of the embodiment of the present invention；
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 without creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment 1
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 (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), it may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His 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 any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, it is also possible to the equipment such as smart television, set-top box.
VGG is Oxford University's computer vision group (VisualGeometry Group) and GoogleDeepMind company
The depth convolutional neural networks that researcher researches and develops together.VGG is explored between the depth of convolutional neural networks and its performance
Relationship, by stacking the small-sized convolution kernel of 3*3 and the maximum pond layer of 2*2 repeatedly, VGG has successfully constructed 16~19 layer depths
Convolutional neural networks.The expansion of VGG is very strong, and the generalization moved on other image datas is very good.The structure of VGG is very
Succinctly, whole network all employs an equal amount of convolution kernel size (3*3) and maximum pond size (2*2).Up to the present,
VGG is still usually utilized to extract characteristics of image.Model parameter after VGG training is increased income in its official website, can be used to
Retraining (be equivalent to and provide extraordinary initialization weight) is carried out in specific image classification task.
In present embodiment, deep learning and content understanding are carried out using VGG convolutional neural networks model.But it is not limited to
This can be using CNN convolutional neural networks model or CNN convolutional neural networks model in some selective embodiments
Branch model.
Referring specifically to Fig. 1, Fig. 1 is that the basic procedure of the present embodiment information configuring methods neural network based of insuring shows
It is intended to.
As shown in Figure 1, a kind of information configuring methods neural network based of insuring, include the following steps:
The information for the insurance products that S1100, the user for obtaining user terminal uploads browse；
User terminal is a kind of computer system device that can carry out data transmission with server end, specifically, user
Terminal includes mobile phone, notebook, tablet computer, POS machine and including vehicle-mounted computer etc..Insurance products are that insurance company is market
The tangible products of offer and the synthesis of invisible service, user is before buying insurance products, it will usually by user terminal come clear
Look at the relevant informations of insurance products.When user is to the desired purchase interested of an insurance products, user is clear by user terminal
Look at the information of the insurance products, specifically, different product bar lines makes insurance products have different product form, such as
Producing danger insure personal information control, health insurance of target information, endowment insurance of insuring has the control of warrantee's number, life insurance to have to be protected
People's occupation etc., a part of data for requiring to insure as user are shown.By taking insurance products are Product for life insurance agent as an example,
When user browses Product for life insurance agent, user terminal can monitor the type of the insurance products in the page that user is browsing
Information, and the information of the insurance products is sent to server end.
S1200, information collection list corresponding with the information of insurance products is obtained according to preset list database,
Wherein, respectively information to be collected is correspondingly provided with collection module in information collection list；
According to the information of the insurance products of user's browsing, so that it is determined that needing to receive when user buys the insurance products
The information of collection, specifically, list database are the preconfigured databases of system, and database (Database) is according to number
Come the warehouse of tissue, storage and management data according to structure, includes that there is corresponding relationship with each insurance products in the list database
Information collect list, information, which collects to be equipped in list, needs the corresponding receipts of the information respectively to be collected that is collected with insurance products
Collect module, different insurance products are corresponding with different information and collect list, so that it is determined that each insurance products must be received
The user information of collection, for example, Product for life insurance agent need the user information collected include user name, ID card No., the age and
The information such as physical condition；Property insurance need the user information collected include position where property target, property target it is all
People's information etc..
S1300, the corresponding collection module of list calling is collected according to information, and the collection module called is sent to use
Family terminal, so that user terminal shows the collection module called in the information gathering page of insurance products.
System collects list after obtaining information corresponding with the information of insurance products and collecting list, according to the information
Collection module is called, is then sent to the user terminal collection module, so that user terminal is produced in the insurance that user browses
The information gathering page of product shows collection module.Collection module is the information collection entry item that user terminal carries out that the page is shown,
When user browses insurance products and click the purchase item of the insurance products by user terminal, system can be obtained on user terminal
The information of the insurance products of user's browsing of biography, obtains the type with the insurance products further according to preset list database
The corresponding information of information collects list, then according to the information collects list calling and information collects in list respectively information to be collected
Corresponding collection module, and the collection module called is sent to the user terminal, user terminal is by the way of Dynamically Announce
The collection module received is shown, specifically, user terminal show collection module composition information gathering page when,
It needs to carry out typesetting to combination page background and different collection modules to show, since different insurance products correspond to different receipts
Collecting module, user terminal receives the need collection module to be shown of server end transmission, and user terminal stores the collection module,
Then the storage address of the collection module is recorded, user clicks page jump to information gathering page on the subscriber terminal
When, then the collection module of the processor item storage address in user terminal distributes to video card that carry out rendering aobvious into memory
Show.When implementing, user terminal stores the collection module of downloading into a specified path, and the processor of user terminal exists
Collection module in the path is called directly when calling to memory, then rendering is carried out by video card and is shown, improves the generation of the page
Speed.
By taking Product for life insurance agent as an example, Product for life insurance agent need the information collected include: user name, ID card No.,
Age and physical condition information, wherein information is collected in list and is equipped with and user name, ID card No., age and body
The one-to-one collection module of condition information, user terminal receive the collection module rear line and are shown, so that
User can distinguish typing user name, ID card No., age and physical condition information according to the collection module, improve pair
The collection efficiency of user information.
In some embodiments, it after collection module being sent to the user terminal, needs to collect user according to information
The page and the information of insuring inputted extracts, and corresponding insurance policy is generated according to the information of insuring.Specific declaration form is raw
At process referring to Fig. 2, Fig. 2 is the idiographic flow schematic diagram that the present embodiment generates insurance policy.
As shown in Fig. 2, further including following step after step S1300:
S1400, the information of insuring corresponding with insurance products for obtaining user terminal uploads, information of insuring include user according to
The user information and insurance information of information gathering page input；
User information is to buy the personal information of the insurer of insurance products, and user information includes at least the user of the insurer
The information such as name, ID card No., native place and permanent address.Insurance information is the demand information that user buys insurance products, is protected
Dangerous information includes at least the kind of insurance of insurance products, insures the time limit and the information such as points for attention of accepting insurance.It is produced with life insurance
For product, when user passes through the user information of user terminal typing individual, typing name, ID card No., age are at least needed
And physical condition information, user terminal can acquire the insurance information of the insurance products simultaneously, including user insures
The time limit and Form-of-payment information, the user information and insurance information are then uploaded to server end by user terminal.
S1500, the insurance policy that insurance products are generated according to user information and insurance information.
System obtains the information of insuring corresponding with insurance products of user terminal uploads, then according to the use in information of insuring
Family information and insurance information generate the insurance policy of insurance insurance products, realize the sale of display insurance products.It is optional at one
In embodiment, insurance information can also include special underwriting conditions, by taking medical insurance as an example, when there are medical histories by user, and the disease
When disease incidence of the disease in next Effective Period of Insurance reaches preset threshold value, special underwriting conditions can be generated, this is special to accept insurance
Condition means that greatly " within the time limit of accepting insurance, user suffers from medical expense caused by XXX disease and suffers from the death of the person caused by the disease and do not exist
Within the scope of the compensation of insurance products ".Certainly, which is not limited to above-mentioned form, according to the difference of application scenarios,
According to user information and preset it can also accept insurance rule and generate other special underwriting conditions.
In some embodiments, when user buys insurance products, it is also necessary to be identified to the identity information of user.
Specific identification process is referring to Fig. 3, Fig. 3 is the idiographic flow schematic diagram of the present embodiment user identity identification.
As shown in figure 3, further including following step after step S1300:
S1600, the facial image for obtaining user；
It is carried out in acquisition process in the facial image to user, system obtains the face figure of the user of user terminal uploads
Picture, user terminal shoot or record a video to user, are obtained by way of timing acquiring and are extracted from video information
Target image is uploaded to server end as the facial image of user.Such as the speed opened with 0.5s mono- is in video information
A Target Photo is extracted in frame picture image, but not limited to this, according to the difference of concrete application scene, acquire target image
Speed be able to carry out the adjustment of adaptability, Adjustment principle is, system processing capacity is stronger and tracking accuracy requirement is higher
Then acquisition time is shorter, reach with user terminal acquisition image Frequency Synchronization when until；Otherwise, then acquisition time interval is got over
It is long, but longest acquisition time interval must not exceed 1s.That target image specifically refers to acquire from video information includes people
The picture image of face image frame.
S1700, the facial image of user is input to preset human face recognition model progress recognition of face, the face is known
Other model is to train to convergent convolutional neural networks model.
Human face recognition model is training to convergent convolutional neural networks model, by orientation training to convergent convolution mind
The face information of the facial image of the user of input can be extracted through network model, then by the face information and user
Identity document image in user's head portrait check, to judge whether the identity information of user correct, when the body of user
When part certificate image and the facial image of user mismatch, the identity document that confirmation user uploads is not the identity card of user
Part, system not will do it the operation of subsequent purchase insurance products；If the identity document image of user and the facial image of user
When matching, the identity document that confirmation user uploads is the identity document of user, and system carries out subsequent purchase insurance products
Operation.Specifically, the identity document image of user can be uploaded to obtain by user using user terminal, can also be led to
Cross the identity document image that data crawler technology crawls user in internet.
In present embodiment, human face recognition model, that is, convolutional neural networks model, the convolution of orientation training to convergence state
Whether the identity document image of neural network model, the facial image and user that can identify user matches, thus realize to
The identification for the identity information that family uploads.
In some embodiments, in the facial image to user into after identification, it is also necessary to the identity document of user
Legitimacy is identified.The legitimacy identification process of specific identity document is referring to Fig. 4, Fig. 4 is the body of the present embodiment user
The idiographic flow schematic diagram of part certificate legitimacy identification.
As shown in figure 4, further including following step after step S1700:
S1800, the identity document information for obtaining user, identity document information include at least the name and identity card of user
Number；
Identity document that is to say resident identification card, is a kind of legal certificate for proving holder's identity, is everyone
Important documentation of identity.When verifying the legitimacy of identity document of user, by the user for obtaining user terminal uploads
Identity document information, such as user by user terminal shoot user identity document obtain identity document image, then use
The identity document image is sent to server end by family terminal, it is, of course, also possible to logical by the user for obtaining user terminal uploads
The identity document information being manually entered is crossed, which includes the name and ID card No. of user.It may be noted that
It is that identity document information is not limited to above-mentioned name and ID card No., according to the difference of concrete application scene, identity document
Information further includes other information, such as the information such as issuing authority and the date of issuance.
S1900, ID card information is carried out according to name and ID card No. of the preset auth method to user
Verifying.
After the identity document information for obtaining user, need to verify the identity document information, specifically verification side
Method are as follows: establish connection with notarial data library, specifically, which is the ID card information system of the Ministry of Public Security, by user
Identity document information be sent to the notarial data library, request notarial data library verification with the presence or absence of the identity document information,
I.e. by notarial data library verification whether store the ID card No., and check the proprietary name of the ID card No. whether with
The name of user is consistent, may know that whether the identity document is that insurer is authentic and valid according to the information of notarial data library feedback
Certificate.
In one embodiment, when acquisition be the identity document image of user of user terminal uploads when, can pass through
The softwares such as OCR or OpenCV in identity document image name and ID card No. extract, then again with notarial data
It is checked in library.It is deposited by the effective identity document information and identity document image of identification as the declaration form attachment of insurance products
Storage is in server end.
It in some embodiments, further include the training method of convolutional neural networks model.It is referring specifically to Fig. 5, Fig. 5
The idiographic flow schematic diagram of the present embodiment human face recognition model training method.
As shown in figure 5, convolutional neural networks model training method includes the following steps:
S1710, acquisition are marked with classification referring to the training sample data of information, wherein training sample data include: sample
Image and the enhancing image for being derived from sample image；
In convolutional neural networks model in training, the training sample data of use are by several (such as 1,000,000 people)
Facial image composition, and everyone has the facial image of multiple varying environment states, in multiple people to the same person
It before face image is trained, needs that the classification of facial image is marked referring to information, anticipation can use the prior art
In trained to convergent human face recognition model judged.
The training sample data that the present embodiment is obtained by web crawlers or existing image data base, pass through above-mentioned instruction
Practice sample data training to convergent neural network model, due to the facial image of people same in training under various circumstances
Identical, therefore, the classification corresponding with facial image of the same people of neural network model output under various circumstances judges information
With higher convergence, the dispersion of data is lower.
Training sample data are formed referring to information to classification by data and (judge data centering identity document image and people
Whether face image is the same person), wherein the classification of training sample data is by manually being demarcated referring to information.Classification
Refer to that people according to the training direction of input convolutional neural networks model, pass through the judgment criteria and the fact of universality referring to information
The judgement thought that state makes training sample data, that is, people are to the phase of convolutional neural networks model output data
It hopes.
S1720, the classification that training sample data input convolutional neural networks model obtains training sample data is judged into letter
Breath；
Convolutional neural networks model is already existing all kinds of human face recognition models in the prior art, in present embodiment
Convolutional neural networks model can be CNN convolutional neural networks model, VGG convolutional neural networks model or insightface
Human face recognition model.
Facial image in training sample data is sequentially inputted in convolutional neural networks model, convolutional neural networks mould
Type carries out feature extraction and classification to facial image, and then according to the classification results of the weight calculation facial image, i.e. output should
The classification of facial image judges information.
Classification judgement is carried out to the multiple pictures that the same person shoots in different environments first, specifically, by multiple people
Face image is once input in human face recognition model, and the classification for obtaining each facial image judges information.
Classification judge when information convolutional neural networks model according to the facial image (qualification additional clause image) of input and
The excited data of output is not trained to before convergence in neural network model, and classification judges information for the biggish number of discreteness
Value, when neural network model is trained to after convergence, classification judges information for metastable data.
S1730, the classification for comparing different samples in training sample data judge whether information is consistent referring to information and classification；
Desired output is calculated by loss function and whether excitation output is consistent, that is, compares point of same facial image
Class output value information judges whether information is consistent with classification, and loss function is for detecting category of model in convolutional neural networks model
Information is judged, with desired classification referring to the whether consistent detection function of information.It is defeated when convolutional neural networks model
When result is inconsistent referring to information with classification out, need to be corrected the weight in convolutional neural networks model, so that convolution
The output result of neural network model is identical referring to the expected result of information as classification.
L (Y, f (x))=Shu Y-f (X) Shu
L indicates that the Euclidean distance between excitation output of desired output, Y indicate that desired output, f (X) indicate that excitation is defeated
Out.
When L refers to greater than preset distance threshold, show that there is biggish difference between desired output and excitation output, it is defeated
Result is inconsistent out.
When the classification of the output of convolutional neural networks model judges information and classification is inconsistent referring to information, basis is needed
Back-propagation algorithm is adjusted the weight in convolutional neural networks model, so that the output result of convolutional neural networks model
It is identical referring to the expected result of information as classification.
In some embodiments, loss function by calculate excitation classification value and setting expectation classification value between away from
From (Euclidean distance or space length), whether the expectation classification value to determine excitation classification value and setting is consistent, setting first
Threshold value (for example, 0.05), when the distance between expectation classification value for motivating classification value and setting is less than or equal to first threshold,
It then determines that excitation classification value is consistent with the expectation classification value of setting, otherwise, then motivates classification value and the expectation classification value of setting not
Unanimously.
S1740, when classification referring to information and classification judge that information is inconsistent when, the update convolutional Neural of iterative cycles iteration
Weight in network model, until classification terminates when judging that information is consistent with classification referring to information.
When the excitation classification value of convolutional neural networks model and the expectation classification value of setting it is inconsistent (classification referring to information and
Classification judges that information is inconsistent) when, it needs to carry out the weight in convolutional neural networks model using stochastic gradient descent algorithm
Correction, so that the output result of convolutional neural networks model is identical referring to the expected result of information as classification.Pass through numerous faces
The training and correction repeatedly of image, when convolutional neural networks model output category judges that the classification of information and each training sample is joined
When reaching and (be not limited to) 99.9% according to information comparison, training terminates.
In some embodiments, referring to Fig. 6, the detailed process that Fig. 6 is the present embodiment acquisition training sample data is shown
It is intended to.
As shown in fig. 6, the acquisition methods of training sample data include the following steps:
The acquisition methods of the training sample data include the following steps:
S1711, preset sample image is obtained；
Sample image can be acquired by web crawlers or existing image data base, by taking web crawlers as an example,
The photo that identity card picture and my picture compare, each identity card picture and reality are crawled in internet by data crawler
Task photo composition data pair, for each data to a training sample is become, training sample is the structure of entire training sample data
At unit, training sample data are made of several (10,000,000 training samples) training samples.
S1712, sample image is subjected to image procossing, to obtain at least one enhancing image for being derived from sample image.
By carrying out image procossing to sample image, to obtain several enhancing images for being derived from sample image, only need
A small amount of sample image can be obtained large number of training sample data, such as each sample image can derive 100
Enhance image, if obtaining 10,000 sample images from image data base, is by carrying out image procossing to 10,000 sample images
1,000,000 enhancing images can be obtained, thus training sample data of the composition more than million pictures.In some embodiments,
The method that sample image is subjected to image procossing.It is that the present embodiment carries out at image sample image referring specifically to Fig. 7, Fig. 7
The idiographic flow schematic diagram of reason.
As shown in fig. 7, the method that sample image carries out image procossing is included the following steps:
S1713, sample image is input in preset Fuzzy Calculation model；
S1714, the enhancing image for being derived from sample image for obtaining the output of Fuzzy Calculation model.
During carrying out image procossing to sample image, first sample image is input in Fuzzy Calculation model, mould
It pastes computation model and corresponding blurred picture is generated according to the sample image technology.The working principle of Fuzzy Calculation model are as follows: given
Clear image I generates corresponding blurred picture J according to following formula.
J=I*K+N
Wherein, * indicates convolution operation, and K indicates fuzzy core, and N indicates random noise.
The image processing process to sample image can be realized according to above-mentioned formula, several be derived from sample graph to generate
The enhancing image of picture.It should be pointed out that the method that sample image carries out image procossing is not limited to above-mentioned method, according to tool
Sample image can also be carried out image procossing in other manners by the difference of body application scenarios.
In order to solve the above technical problems, the embodiment of the present invention also provides information configuration device neural network based of insuring.
Referring specifically to Fig. 8, Fig. 8 is the present embodiment information configuration device basic structure signal neural network based of insuring
Figure.
As shown in figure 8, a kind of information configuration device neural network based of insuring, comprising: first obtains module 2100, place
Manage module 2200 and the first execution module 2300, wherein the first acquisition module 2100 is used to obtain the user of user terminal uploads
The information of the insurance products of browsing；Processing module 2200 is used to be obtained according to preset list database and produce with the insurance
The corresponding information of the information of product collects list, wherein respectively information to be collected is respectively equipped in the information collection list
Corresponding collection module；First execution module 2300, which is used to collect list according to the information, calls corresponding collection module, and
The collection module called is sent to the user terminal, so that the user terminal is collected in the information of the insurance products
The page shows the collection module called.
By obtaining the information of the insurance products of user's browsing of user terminal uploads, according to the kind of the insurance products
Category information can get corresponding information in preset list database and collect list, collect list by the information and call receipts
Collection module is simultaneously sent to the user terminal by collection module, and user terminal produces after receiving the collection module in the insurance that user browses
The information gathering page of product loads the collection module, to show that information corresponding with the insurance products that user browses is received to user
Collect entry item, facilitates user to fill in input and buy information required for the insurance products, purchased on the line of insurance products to realize
Buy function.By the above method, be able to solve insurance products that people needs to buy according to user on line to the information of user into
Row is collected, and the on-line selling rate of collection rate and insurance products on the line of user information is improved.
In some embodiments, information configuration device neural network based of insuring further include: second obtain module and
Second execution module, wherein the second acquisition module is used to obtain the letter of insuring corresponding with the insurance products of user terminal uploads
Breath, the user information and insurance information that the information of insuring, which includes user, to be inputted according to the information gathering page；Second executes
Module is used to generate the insurance policy of the insurance products according to the user information and insurance information.
In some embodiments, information configuration device neural network based of insuring further include: third obtain module and
Face recognition module, third obtain the facial image that module is used to obtain user；Face recognition module is used for the user's
Facial image is input to preset human face recognition model and carries out recognition of face, and the human face recognition model is to train to convergent volume
Product neural network model.
In some embodiments, information configuration device neural network based of insuring further include: the 4th obtain module and
Authentication module, the 4th acquisition module are used to obtain the identity document information of user, and the identity document information includes at least user
Name and ID card No.；Authentication module is used to the name of the user and ID card No. being input to preset body
Part verifying model carries out ID card information verifying.
In some embodiments, information configuration device neural network based of insuring further include: the first acquisition submodule,
First implementation sub-module, first compare submodule and the first adjustment submodule, and the first acquisition submodule is marked with point for obtaining
Training sample data of the class referring to information, wherein the training sample data include: sample image and are derived from the sample graph
The enhancing image of picture；Described in first implementation sub-module is used to obtain on training sample data input convolutional neural networks model
The classification of training sample data judges information；First comparison submodule is used to compare different samples in the training sample data
Classification judges whether information is consistent referring to information and the classification；The first adjustment submodule be used for when the classification referring to information and
When the classification judges that information is inconsistent, the weight of iterative cycles iteration updated in the convolutional neural networks model, until institute
Stating when classification judges that information is consistent with the classification referring to information terminates.
In some embodiments, information configuration device neural network based of insuring further include: the second acquisition submodule
With the first processing submodule, the second acquisition submodule is for obtaining preset sample image；First processing submodule is used for institute
It states sample image and carries out image procossing, to obtain at least one enhancing image for being derived from the sample image.
In some embodiments, information configuration device neural network based of insuring further include: the second implementation sub-module
With third acquisition submodule, the second implementation sub-module is for the sample image to be input in preset Fuzzy Calculation model；
Third acquisition submodule is used to obtain the enhancing image for being derived from the sample image of the Fuzzy Calculation model output.
In order to solve the above technical problems, the embodiment of the present invention also provides computer equipment.It is this referring specifically to Fig. 9, Fig. 9
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 the computer-readable instruction is executed by processor, may make processor to realize a kind of information neural network based of insuring
Configuration method.The processor of the computer equipment supports the operation of entire computer equipment for providing calculating and control ability.
Computer-readable instruction can be stored in the memory of the computer equipment, when which is executed by processor,
Processor may make to execute a kind of information configuring methods neural network based of insuring.The network interface of the computer equipment is used for
With terminal connection communication.It will be understood by those skilled in the art that structure shown in Fig. 9, only related to application scheme
Part-structure block diagram, do not constitute the restriction for the computer equipment being applied thereon to application scheme, it is specific to count
Calculating machine equipment may include perhaps combining certain components or with different portions than more or fewer components as shown in the figure
Part arrangement.
Processor is held for executing the first acquisition module 2100, processing module 2200 and first in Fig. 8 in present embodiment
The concrete function of row module 2300, program code and Various types of data needed for memory is stored with the above-mentioned module of execution.Network connects
Mouth to the data between user terminal or server for transmitting.Memory in present embodiment is stored with based on neural network
Information configuration device of insuring in execute all submodules needed for program code and data, server is capable of invoking server
Program code and data execute the function of all submodules.
Computer is produced by the information of the insurance products of user's browsing of acquisition user terminal uploads according to the insurance
The information of product can get corresponding information and collect list, collected list calling collection module by the information and will be collected
Module is sent to the user terminal, and user terminal receives the information collection page of the insurance products browsed after the collection module in user
Face loads the collection module, thus show that information corresponding with the insurance products that user browses collects entry item to user, it is convenient
User fills in input and buys information required for the insurance products, to realize the purchase function of insurance products.Pass through above-mentioned side
Method is able to solve people and needs the insurance products bought to be collected the information of user according to user on line, improves user
The on-line selling rate of collection rate and insurance products on the line of information.
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 neural network based described in any of the above-described embodiment of one or more processors execution
Insure information configuring methods the step of.
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-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, 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.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of information configuring methods neural network based of insuring, which is characterized in that include the following steps:
Obtain the information of the insurance products of user's browsing of user terminal uploads；
Information corresponding with the information of the insurance products, which is obtained, according to preset list database collects list, wherein
Respectively information to be collected is respectively equipped with corresponding collection module in the information collection list；
List is collected according to the information and calls corresponding collection module, and the collection module called is sent to the user
Terminal, so that the user terminal shows the collection module called in the information gathering page of the insurance products.
2. information configuring methods neural network based of insuring according to claim 1, which is characterized in that described according to institute
It states information and collects the corresponding collection module of list calling, and the collection module called is sent to the user terminal, so that
The user terminal is also specific after the step of information gathering page of the insurance products shows the collection module called
Include the following steps:
The information of insuring corresponding with the insurance products of user terminal uploads is obtained, the information of insuring includes user according to institute
State the user information and insurance information of information gathering page input；
The insurance policy of the insurance products is generated according to the user information and insurance information.
3. information configuring methods neural network based of insuring according to claim 1, which is characterized in that described according to institute
It states information and collects the corresponding collection module of list calling, and the collection module called is sent to the user terminal, so that
The user terminal is also specific after the step of information gathering page of the insurance products shows the collection module called
Include the following steps:
Obtain the facial image of user；
The facial image of the user is input to preset human face recognition model and carries out recognition of face, the human face recognition model
For training to convergent convolutional neural networks model.
4. information configuring methods neural network based of insuring according to claim 3, which is characterized in that it is described will be described
The facial image of user is input to preset human face recognition model and carries out recognition of face, and the human face recognition model is that training is extremely received
Further include following step after the step of convolutional neural networks model held back:
The identity document information of user is obtained, the identity document information includes at least the name and ID card No. of user；
ID card information verifying is carried out according to name and ID card No. of the preset auth method to the user.
5. information configuring methods neural network based of insuring according to claim 3, which is characterized in that the convolution mind
Training method through network model includes:
Obtain be marked with classification referring to information training sample data, wherein the training sample data include: sample image and
It is derived from the enhancing image of the sample image；
The classification that training sample data input convolutional neural networks model obtains the training sample data is judged into information；
The classification for comparing different samples in the training sample data judges whether information is consistent referring to information and the classification；
When the classification judges that information is inconsistent referring to information and the classification, the update of the iterative cycles iteration convolution mind
Through the weight in network model, until the classification terminates when judging that information is consistent with the classification referring to information.
6. information configuring methods neural network based of insuring according to claim 5, which is characterized in that the trained sample
The acquisition methods of notebook data include the following steps:
Obtain preset sample image；
The sample image is subjected to image procossing, to obtain at least one enhancing image for being derived from the sample image.
7. information configuring methods neural network based of insuring according to claim 6, which is characterized in that it is described will be described
Sample image carries out the step of image procossing, specifically include the following steps:
The sample image is input in preset Fuzzy Calculation model；
Obtain the enhancing image for being derived from the sample image of the Fuzzy Calculation model output.
8. a kind of information configuration device neural network based of insuring characterized by comprising
First obtains module, the information for the insurance products that the user for obtaining user terminal uploads browses；
Processing module is received for obtaining information corresponding with the information of the insurance products according to preset list database
Collect list, wherein respectively information to be collected is respectively equipped with corresponding collection module in the information collection list；
First execution module calls corresponding collection module, and the collection that will have been called for collecting list according to the information
Module is sent to the user terminal so that the user terminal the information gathering page of the insurance products show it is described
The collection module of calling.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor executes such as any one of claims 1 to 7 right
It is required that it is described it is neural network based insure information configuring methods the step of.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors are executed is based on nerve net as described in any one of claims 1 to 7 claim
Network insure information configuring methods the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949641.XA CN109254814A (en) | 2018-08-20 | 2018-08-20 | Information configuring methods of insuring, device, computer equipment and storage medium neural network based |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949641.XA CN109254814A (en) | 2018-08-20 | 2018-08-20 | Information configuring methods of insuring, device, computer equipment and storage medium neural network based |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109254814A true CN109254814A (en) | 2019-01-22 |
Family
ID=65050219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810949641.XA Pending CN109254814A (en) | 2018-08-20 | 2018-08-20 | Information configuring methods of insuring, device, computer equipment and storage medium neural network based |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109254814A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961370A (en) * | 2019-01-29 | 2019-07-02 | 宜信博诚保险销售服务(北京)股份有限公司 | A kind of the interests methods of exhibiting and device of insurance products |
| CN112700300A (en) * | 2020-12-25 | 2021-04-23 | 山东众阳健康科技集团有限公司 | Intelligent auditing and controlling method, system, storage medium and equipment for supplier qualification |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182726A (en) * | 2014-02-25 | 2014-12-03 | 苏凯 | Real name authentication system based on face identification |
| CN106780906A (en) * | 2016-12-28 | 2017-05-31 | 北京品恩科技股份有限公司 | A kind of testimony of a witness unification recognition methods and system based on depth convolutional neural networks |
| CN106778607A (en) * | 2016-12-15 | 2017-05-31 | 国政通科技股份有限公司 | A kind of people based on recognition of face and identity card homogeneity authentication device and method |
| US20170278546A1 (en) * | 2016-03-25 | 2017-09-28 | Samsung Electronics Co., Ltd. | Method and device for processing multimedia information |
| CN107292749A (en) * | 2017-08-04 | 2017-10-24 | 平安科技（深圳）有限公司 | Car damages sorting technique, system and the readable storage medium storing program for executing of certificate photograph |
| CN107481150A (en) * | 2017-07-18 | 2017-12-15 | 尹作军 | A kind of investment return method of the identity insurance based on Internet technology |
| CN107886474A (en) * | 2017-11-22 | 2018-04-06 | 北京达佳互联信息技术有限公司 | Image processing method, device and server |
| CN108022169A (en) * | 2017-11-30 | 2018-05-11 | 平安科技（深圳）有限公司 | Method, apparatus, equipment and the medium of purchase insurance are docked by website |
-
2018
- 2018-08-20 CN CN201810949641.XA patent/CN109254814A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182726A (en) * | 2014-02-25 | 2014-12-03 | 苏凯 | Real name authentication system based on face identification |
| US20170278546A1 (en) * | 2016-03-25 | 2017-09-28 | Samsung Electronics Co., Ltd. | Method and device for processing multimedia information |
| CN106778607A (en) * | 2016-12-15 | 2017-05-31 | 国政通科技股份有限公司 | A kind of people based on recognition of face and identity card homogeneity authentication device and method |
| CN106780906A (en) * | 2016-12-28 | 2017-05-31 | 北京品恩科技股份有限公司 | A kind of testimony of a witness unification recognition methods and system based on depth convolutional neural networks |
| CN107481150A (en) * | 2017-07-18 | 2017-12-15 | 尹作军 | A kind of investment return method of the identity insurance based on Internet technology |
| CN107292749A (en) * | 2017-08-04 | 2017-10-24 | 平安科技（深圳）有限公司 | Car damages sorting technique, system and the readable storage medium storing program for executing of certificate photograph |
| CN107886474A (en) * | 2017-11-22 | 2018-04-06 | 北京达佳互联信息技术有限公司 | Image processing method, device and server |
| CN108022169A (en) * | 2017-11-30 | 2018-05-11 | 平安科技（深圳）有限公司 | Method, apparatus, equipment and the medium of purchase insurance are docked by website |
Non-Patent Citations (1)
| Title |
|---|
| 八百里加急: "人脸识别向保险业的渗透，未来保险会有哪些新玩法？", pages 1 - 4, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/29376215> * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961370A (en) * | 2019-01-29 | 2019-07-02 | 宜信博诚保险销售服务(北京)股份有限公司 | A kind of the interests methods of exhibiting and device of insurance products |
| CN112700300A (en) * | 2020-12-25 | 2021-04-23 | 山东众阳健康科技集团有限公司 | Intelligent auditing and controlling method, system, storage medium and equipment for supplier qualification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112491551B (en) | Data verification method and device based on block chain and electronic equipment | |
| US10643062B2 (en) | Facial recognition pet identifying system | |
| CN107808118A (en) | Personal identification method, electronic installation and computer-readable recording medium | |
| US9286295B2 (en) | Apparatus and method for cloud based storage using a multi-layer scannable tag | |
| CN108833942A (en) | Video cover choosing method, device, computer equipment and storage medium | |
| US20210312561A1 (en) | Secure digital media authentication and analysis | |
| CN109446302A (en) | Question and answer data processing method, device and computer equipment based on machine learning | |
| CN109726624A (en) | Identity identifying method, terminal device and computer readable storage medium | |
| CN107644209A (en) | Method for detecting human face and device | |
| US20160260185A1 (en) | Electronic Contract Creator | |
| CN109583970A (en) | Advertisement placement method, device, computer equipment and storage medium | |
| CN107679546A (en) | Face image data acquisition method, device, terminal device and storage medium | |
| CN110335100A (en) | Information-pushing method, device, computer and storage medium based on artificial intelligence | |
| WO2021114936A1 (en) | Information recommendation method and apparatus, electronic device and computer readable storage medium | |
| CN109254814A (en) | Information configuring methods of insuring, device, computer equipment and storage medium neural network based | |
| US20210019511A1 (en) | Systems and methods for extracting data from an image | |
| CN110060750A (en) | Medical data method for pushing, system, computer equipment and readable storage medium storing program for executing | |
| CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
| US20200311136A1 (en) | Measuring and increasing the quality of user-provided information | |
| CN107656959A (en) | A kind of message leaving method, device and message equipment | |
| WO2021185184A1 (en) | Content recommendation method and apparatus, electronic device, and storage medium | |
| US20230281462A1 (en) | Data processing method and apparatus, device, and medium | |
| WO2023142550A1 (en) | Abnormal event detection method and apparatus, computer device, storage medium, computer program, and computer program product | |
| CN113658010B (en) | Electronic insurance policy generation method, device, equipment and storage medium | |
| CN116681045A (en) | Report generation method, report generation device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |