CN114021990A

CN114021990A - Method, system, apparatus and medium for assessing risk of vehicle accident

Info

Publication number: CN114021990A
Application number: CN202111312724.6A
Authority: CN
Inventors: 王冠楠; 张纪元; 朱训; 杨志雄
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-11-08
Filing date: 2021-11-08
Publication date: 2022-02-08

Abstract

Disclosed is a method for assessing the risk of an accident in a user's vehicle, comprising: acquiring user information of the user, wherein the user information comprises one or more of basic identity information, relationship information, professional information and academic information of the user; processing the user information to authenticate authenticity of the user information; and automatically determining an accident risk of the vehicle based at least in part on the authenticated user information. The application also relates to related systems, apparatuses, and computer-readable storage devices. The scheme of the application can more accurately and automatically evaluate the accident risk of the vehicle of the user.

Description

Method, system, apparatus and medium for assessing risk of vehicle accident

Technical Field

One or more embodiments of the present description relate to accident risk assessment of vehicles, and more particularly, to methods, systems, apparatuses, and computer-readable storage media for assessing vehicle accident risk.

Background

In many scenarios, it is desirable to assess the risk or probability of a vehicle being involved in an accident (e.g., over a period of time, such as a year). For example, vehicle accident risk is one of the most important considerations when pricing vehicle insurance (or premium) for a particular customer. For example, due to the driving style of the vehicle driver (user), the vehicle type and condition of the vehicle, the driving route, and other factors, the risk or probability of accidents such as car accidents occurring in different vehicles is different, and the higher the risk of accidents occurring in the vehicle is, the higher the premium pricing is generally.

In existing vehicle accident risk assessment schemes, information about the vehicle itself is typically considered primarily. For example, the accident situation of a vehicle during one or several previous years (or other time intervals) is typically only considered, so that the future accident risk of the vehicle (or driver) is predicted based on the accident history of the vehicle (or driver).

However, predicting future risk of accidents based on accident history has major limitations. Since the driving years of a vehicle or a driver are generally not long and the amount of data is small, the accuracy in predicting the risk of a future accident is low.

In addition, data such as vehicle models and vehicle conditions, vehicle service life, vehicle mileage and the like are also generally considered in the conventional vehicle insurance pricing, but the data are still not abundant enough, and a space for improvement in accuracy is still provided.

User information for a driver (i.e., user) is typically not considered in the prior art because, on the one hand, the association between the user information and the accident risk of the vehicle is difficult to determine using conventional methods (e.g., the association between the user's occupational information and the accident risk of the vehicle), and, on the other hand, because inaccurate or outdated information may be included in the user information (e.g., the user may intentionally submit spurious information in an attempt to reduce the premium) resulting in inaccurate accident risk assessment.

Therefore, there is a need for a more accurate, automated solution for assessing the risk of an accident in a vehicle.

Disclosure of Invention

To overcome the disadvantages of the prior art, one or more embodiments of the present specification can more accurately and automatically assess the risk of an accident in a vehicle by taking into account more objective data including user information and eliminating inaccurate or outdated information through an authentication operation.

One or more embodiments of the present specification achieve the above objects by the following technical solutions.

In one aspect, a method for assessing the risk of an accident with a user's vehicle is provided, comprising: acquiring user information of the user, wherein the user information comprises one or more of basic identity information, relationship information, professional information and academic information of the user; processing the user information to authenticate authenticity of the user information; and automatically determining an accident risk of the vehicle based at least in part on the authenticated user information.

Preferably, the user is guided by the user's client device to submit at least a portion of the user information by one or more of: form submission, image uploading and service authorization.

Preferably, feedback or a prompt for the authenticity of the user information is provided via a client device of the user during or after the user submits the user information.

Preferably, the method further comprises: accessing, by a server, an online social networking service of the user to obtain relationship information of the user.

Preferably, the method further comprises: accessing, by a server, an online professional information service of the user to obtain professional information and/or academic information of the user.

Preferably, the method further comprises: obtaining authorization of the user prior to accessing the online social networking service or the online professional information service.

Preferably, the method further comprises: acquiring authentication data, wherein the authentication data comprises data which can be used for authenticating the authenticity of the user information; and authenticating the authenticity of the user information based at least in part on the authentication data.

Preferably, the authentication data comprises one or more of a geographical location of the user, a transfer record, a shopping record, historical compliance activities, a personal credit report, a historical credit bill.

Preferably, the method further comprises: accessing, by a server, an online payment service and/or a credit information service of the user to obtain at least a portion of the authentication data of the user.

Preferably, the authentication data includes user information of other users.

Preferably, the method further comprises: determining a vehicle insurance pricing for the vehicle based on the accident risk of the vehicle.

Preferably, the method further comprises: transmitting the accident risk of the vehicle or the vehicle insurance pricing determined based on the accident risk to the client device of the user.

Preferably, the accident risk is represented by an accident risk assessment score, the method further comprising: and transmitting the accident risk assessment score to a vehicle insurance service provider.

Preferably, the method further comprises: acquiring travel data of the user, the travel data being collected by a tachograph attached to a vehicle driven by the user; and evaluating the accident risk of the vehicle further based on the driving data of the user.

In another aspect, a system for assessing the risk of an accident with a user's vehicle is provided, comprising: an information acquisition module configured to acquire user information of the user, the user information including one or more of basic identity information, relationship information, occupation information, and academic information of the user; an authentication module configured to process the user information to authenticate authenticity of the user information; and an accident risk assessment module configured to automatically determine an accident risk for the vehicle based at least in part on the authenticated user information.

Preferably, the information acquisition module is further configured to: accessing an online social networking service of the user to obtain relationship information of the user; and/or accessing an online professional information service of the user to obtain professional information and/or academic information of the user.

Preferably, the authentication module is further configured to: acquiring authentication data, wherein the authentication data comprises data which can be used for authenticating the authenticity of the user information; and authenticating the authenticity of the user information based at least in part on the authentication data.

Preferably, the system further comprises: a vehicle insurance pricing module configured to determine vehicle insurance pricing for the vehicle based on the accident risk of the vehicle.

In yet another aspect, there is provided an apparatus for assessing the risk of an accident with a user's vehicle, comprising: a memory; and a processor configured to perform the method of any of the above.

In yet another aspect, a computer-readable storage medium storing instructions that, when executed by a computer, cause the computer to perform the above-described method is provided.

Compared with the prior art, one or more embodiments of the present specification can achieve one or more of the following technical effects:

the risk assessment of the vehicle accident can be automatically realized, and the pricing of the vehicle insurance can be further automatically realized;

good interaction can be carried out with the user, and the user experience is improved; and

the accident risk of the vehicle can be more accurately evaluated.

Drawings

The foregoing summary, as well as the following detailed description of the embodiments, is better understood when read in conjunction with the appended drawings. It is to be noted that the appended drawings are intended as examples of the claimed invention. In the drawings, like reference characters designate the same or similar elements.

FIG. 1 illustrates a generalized schematic diagram of a process for pricing a user's car insurance based on an assessment of risk of vehicle accident, according to an embodiment of the present description.

FIG. 2 illustrates a generalized schematic diagram of an example method for assessing a risk of accident for a user's vehicle in accordance with an embodiment of the present description.

FIG. 3 shows a schematic diagram of an overall system for determining user pricing in accordance with one or more embodiments of the present description.

4A-4D illustrate schematic diagrams of alternative forms for guiding a user to submit user information according to embodiments of the present description.

Fig. 5 illustrates an example schematic diagram of the operation of a user information authentication system for authenticating user information in accordance with one or more embodiments of the present description.

FIG. 6 illustrates a schematic diagram of a method for determining pricing of car insurance for a user in accordance with one or more embodiments of the present description.

FIG. 7 shows a schematic diagram of another method for determining pricing of vehicle insurance for a user in accordance with one or more embodiments of the present description.

FIG. 8 illustrates a schematic diagram of an example system that may be used to assess a risk of accident for a user's vehicle in accordance with embodiments of the present description.

Fig. 9 illustrates a block diagram of an apparatus that may be used as a server or a client device according to embodiments of the present description.

Detailed Description

The following detailed description is sufficient to enable any person skilled in the art to understand the technical content of one or more embodiments of the present specification and to implement the same, and the objects and advantages related to one or more embodiments of the present specification can be easily understood by those skilled in the art from the description, claims and drawings disclosed in the present specification.

As described above, at present, in evaluating the accident risk of a vehicle, only data such as the accident history of the vehicle, the model and condition of the vehicle, the service life of the vehicle, and the mileage of the vehicle are generally used. However, these data usually only take into account information of the vehicle itself and not user information of the driver of the vehicle.

However, in the prior art solutions, the user information is not taken into account, and is difficult to take into account, since the weight of the influence of the user information on the accident risk of the vehicle cannot usually be evaluated. In addition, inaccuracy or obsolescence of user information may also lead to poor evaluation results.

One or more embodiments of the present specification take various factors including user information and the like into consideration, and automatically authenticate the user information first before using the user information, thereby enabling more accurate assessment of the accident risk of the vehicle. Further, one or more embodiments of the present description automate the evaluation of the risk of accident for a vehicle by performing automatic data acquisition, automatic authentication, automatic evaluation, and the like.

One or more embodiments of the present description may be used in various business systems relating to assessing risk of vehicle accidents. For example, such business systems may include systems for assessing vehicle accident risk to price vehicle insurance (e.g., for insurance companies), and may also include third party service systems that do not price vehicle insurance themselves, but rather provide vehicle accident risk assessment services to vehicle insurance service providers (e.g., vehicle insurance accident assessment service providers that provide accident risk assessment scores for vehicle insurance users to insurance companies). One or more embodiments of the present description may also be applied to any other suitable business system.

Note that in the following, unless the context clearly indicates or suggests otherwise, "user" is generally used to refer to the driver of the vehicle.

For example, the vehicle accident risk assessment system of one or more embodiments of the present description may be used to price vehicle insurance according to the process shown in FIG. 1.

Referring to FIG. 1, a generalized schematic diagram of a process 100 for pricing a user's car insurance based on an assessment of vehicle accident risk is shown, according to an embodiment of the present description.

As shown in FIG. 1, process 100 may generally include obtaining user information at operation 102. For example, the user information may include information relating to the user that may be used to assess the risk of a vehicle accident, such as attribute information of the user as described below. Preferably, the obtaining of the user information may be performed automatically or semi-automatically. For example, the user's information may be obtained automatically by the server from a database or other source of information that stores the user's information. Alternatively, submission of user information by a user may be received based on interaction with the user. Alternatively, a combination of the above two approaches may be employed. For more details of acquiring user information, reference may be made to the "user information acquisition" section below.

In a preferred example, process 100 may also include obtaining vehicle information (not shown in FIG. 1). For example, the vehicle information may include information related to the vehicle that is typically used to assess risk of vehicle accidents or price vehicle insurance. For example, the vehicle information may include accident history of the vehicle, a model and a condition of the vehicle, a service life of the vehicle, a mileage of the vehicle, and the like.

Preferably, process 100 also optionally includes authenticating the user information at operation 104.

In many cases, the acquired user information may be inaccurate. For example, the user may submit false information to trick into a more biased premium. Alternatively, the user may inadvertently submit the wrong information. Alternatively, where user information is obtained by a server from a database or other information source, the user information may be inaccurate or outdated. Inaccurate user information may result in inaccurate assessment of vehicle accident risk information. Therefore, in the preferred embodiment of the present specification, authentication can be performed on user information. For example, the user information may be processed to authenticate the accuracy of the user information. For example, individual items of user information may be cross-authenticated.

Preferably, to more accurately authenticate the user information (and in some examples also the vehicle information), the server may also obtain authentication data. In a preferred example, the authentication data may include location information of the user, shopping history information, transaction transfer information, credit information, and the like.

Preferably, the authentication of the user information may be performed automatically or semi-automatically. For example, the user information may be authenticated by the server through execution of an algorithm. Alternatively, user information that may be false or that is not certain of being true or false may be filtered out by an algorithm and submitted to human authentication. For more details of authenticating user information, reference may be made to the "user information authentication" section below.

In some cases, operation 104 may not be performed.

In a preferred example, process 100 may also include authenticating vehicle information (not shown in FIG. 1). Similarly, authentication of the vehicle information may be performed automatically or semi-automatically.

The process 100 may also include assessing the risk of accident for the vehicle based at least on the user information at operation 106. The user information may be user information that is authenticated to be genuine. Preferably, the assessment of the risk of accident of the vehicle may be performed automatically or semi-automatically. For example, the risk of accident for the vehicle may be calculated by the server by executing an algorithm. Alternatively, server evaluation may be combined with manual evaluation.

Preferably, the assessment of the risk of accident for the vehicle may also be further based on vehicle information. The vehicle information may be vehicle information that is authenticated as being genuine. For example, the user information may be combined with vehicle information to assess the risk of an accident for the vehicle.

Process 100 also optionally includes: at operation 108, after assessing the risk of accident for the vehicle, insurance pricing may also be determined based on the assessment of the risk of accident for the vehicle. Preferably, the assessment of the risk of accident of the vehicle may be performed automatically or semi-automatically. For example, the accident risk of the vehicle may be represented in the form of an accident risk assessment score. In a preferred example, the accident risk of the vehicle may comprise more information, such as separate assessment points for different types of accident risk.

In some embodiments, the process 100 may not include the step of determining pricing for car insurance. For example, in the case where the embodiments of the present specification are implemented at a third party service system that provides a vehicle accident risk assessment service, the third party service system may not perform a vehicle insurance pricing operation, but transmit the assessed vehicle accident risk to an insurance company and price the vehicle insurance by the insurance company.

Process 100 also optionally includes: at operation 110, the determined car insurance pricing may be fed back to the user. For example, where a user submits an application for car insurance in the form of an application, web page, applet, or the like, the determined car insurance pricing may be displayed to the user on the application, web page, applet, or the like used by the user. The user may then determine whether to participate in the car insurance item based on the car insurance pricing.

The various operations of process 100 may be performed by one or more servers, as desired. For example, operation 100 may be performed by an information acquisition server, a client device of a user, or a combination of both. Operation 104 may be performed by an authentication server. Operation 106 may be performed by the evaluation server. Operation 108 may be performed by an insurance pricing server, which may be located at an accident risk service provider or at an insurance service provider. Operation 110 may be performed by a feedback server, a client device of a user, or a combination of both. One or more of the information acquisition server, the authentication server, the evaluation server, the pricing server, the feedback server may be the same server or may be different servers.

Referring to fig. 2, a generalized schematic diagram of an example method 200 for assessing a risk of accident for a user's vehicle in accordance with an embodiment of the present description is shown. For example, the user is a driver of the vehicle. The method 200 is a more detailed illustration of the process shown in fig. 1.

As shown in fig. 2, method 200 may include: at operation 202, user information for the user may be obtained, the user information including one or more of relationship information, career information, academic information for the user. The details of obtaining user information are further described below with reference to fig. 3 and 4.

The method 200 may further include: optionally, at operation 204, authentication data may be obtained. The authentication data includes data that can be used to authenticate the authenticity of the user information. Such authentication data may include, for example, user information for other users, other authentication data for the user, and the like, examples of which include, but are not limited to, one or more of the user's geographic location, transfer records, shopping records, historical watch behavior, personal credit reports, historical credit bills. The specific details of obtaining authentication data are described further below with reference to fig. 5.

The method 200 may further include: at operation 206, the user information submitted by the user may be processed to authenticate the authenticity of the user information. If authentication data is obtained at operation 204, the authentication of the user information may also be based on additional authentication data, the specific details of which are further described below with reference to FIG. 5.

The method 200 may further include: at operation 208, an accident risk for the vehicle may be automatically determined based at least in part on the authenticated user information. The specific details of determining the risk of an accident are described further below.

Referring to FIG. 3, a schematic diagram of an overall system 300 for determining pricing for a user is shown, in accordance with one or more embodiments of the present description.

As shown in FIG. 3, the system 300 may include a client device 302 of a user. For example, a user may submit an application for car insurance via a client device, or otherwise initiate a request to assess the user's risk of an accident. In some embodiments, the user's client device 102 may also be used to interactively guide the user to submit user information (e.g., based on interaction with the server) and/or other data (e.g., partial authentication data, etc.). Further, the user's client device 102 may also provide a prompt for the authenticity of the user's information during or after the user submits the information. In addition, the user's client device 102 may also be used to receive feedback from the accident risk assessment server (or car insurance pricing server) and provide the feedback (e.g., car insurance pricing) to the user.

In some embodiments, the user's client device 302 may not be needed. For example, where an accident risk assessment service is provided to an insurance service provider of a third party, a request to initiate assessment of the accident risk of the user may be provided by the insurance service provider, and user information and other data may be provided by the insurance service provider.

The system 300 may also include an accident risk assessment server 304. The accident risk assessment server 304 may be used to perform some or all of the

operations

202, 204, 206 in the method 200 as described above. For example, the incident risk assessment server 304 may obtain user information, authentication data (and other data), etc., submitted by the user from the user's client device 302, and may also access or crawl other services (e.g., social networking services, professional information services, etc.) or databases (e.g., user identity databases, etc.) in order to obtain user information. Further, the accident risk assessment server 304 may receive an accident risk assessment request from a user's client device or a car insurance service provider to begin the assessment. Further, the incident risk assessment server 304 may interact with the user's client device 302 to provide instructions or data thereto (e.g., instructions to guide the user in submitting information or feedback on the authenticity of information, etc.) or to receive data (e.g., user information, authentication data, etc.), as necessary. The accident risk assessment server 304, after determining the accident risk, may transmit the accident risk to the car insurance pricing server 306.

The system 300 may also include an insurance pricing server 306. The car insurance pricing server 306 may be configured to receive a risk assessment (e.g., a risk assessment score) from the accident risk assessment server and determine car insurance pricing for the user based on the risk assessment. In addition, the insurance pricing server 306 may also transmit insurance pricing to the user's client device to feedback insurance pricing to the user.

It is noted that, although not shown in fig. 3, in some embodiments, the user's client device 302 may interact directly with the car insurance pricing server 306 and submit user information and other data to the car insurance pricing server 306, and the accident risk assessment server 304 may receive the user information and other data from the car insurance pricing server 306. Also, as described above for process 100, the individual servers are not limited to one server, but may be a server cluster, cloud, or the like. Further, the various servers are not limited to being located at the same site or belonging to the same entity. For example, the accident risk assessment server 304 and the car insurance pricing server 306 may belong to the same or different entities, e.g., the accident risk assessment server 304 may belong to an accident risk assessment service provider and the car insurance pricing server 306 may belong to a car insurance service provider.

User information acquisition

Unlike the prior art, which typically only considers vehicle attribute information (e.g., accident history of the vehicle, model and condition of the vehicle, age of the vehicle, mileage of the vehicle, etc.), one or more embodiments of the present description also considers attribute information of the user in evaluating the risk of an accident of the vehicle.

The attribute information of the user may include, for example, one or more of the following:

basic identity information of the user, including but not limited to one or more of the user's name, age, place of residence, native place, etc. For example, the native place of the user may have an impact on the driving style of the user, thereby affecting the risk of accidents. Likewise, the age of the user, the place of residence, etc. may also affect the risk of accidents.

The user's career information includes, but is not limited to, the user's current career, current employment company, career experience, and the like. For example, users in different professions, such as taxi drivers, lawyers, free-job owners, etc., may have different driving styles, thereby affecting accident risk. In addition, if the user cares stably, the daily driving route is relatively fixed, and another user works and changes frequently, the driving route is variable, the user needs to know the new road condition in time, and the accident risks of the two users may be different.

The relationship information of the user includes, but is not limited to, the couple relationship, the parent-child relationship, the co-worker relationship, the friend relationship, etc. of the user. For example, assuming that the user is a husband of woman a and that the husband of a group similar to woman a has known probability of accident risk, this knowledge may be used as an influencing factor to evaluate the accident risk of the user.

The user's academic information includes, but is not limited to, the user's highest academic calendar, graduate school, academic specialty, and the like.

The form and specific means of user information acquisition are described below.

Forms of user-submitted information

Referring to fig. 4A-4D, schematic diagrams of alternative forms for guiding a user to submit user information according to embodiments of the present description are shown. For example, a user may submit a car insurance application through an application installed on their client device (e.g., a smartphone), or may request an assessment of the risk of accident for their vehicle (without submitting a car insurance application). In this case, the server may communicate with the user's client device in order to direct the user to submit user information by the user's client device by one or more of: form submission, image uploading and service authorization are carried out, so that the information of the user is obtained.

FIG. 4A shows a schematic diagram of an interface of an application for a user to submit information. As shown in FIG. 4A, a user may submit various categories of user information through the interface, such as identity information (e.g., an identity card, passport, travel ticket, etc. as shown in FIG. 4A), educational information (e.g., a scholarly membership, etc. as shown in FIG. 4A), professional information (e.g., professional information, work information, etc. as shown in FIG. 4A). In addition, the user may also submit various additional information through the interface, such as asset information (e.g., equity, real estate, car property, financial product, etc., as shown in FIG. 4A). For example, the interface may direct the user to submit the corresponding information by clicking on the corresponding information item.

FIG. 4B shows a schematic diagram of a user submitting information in the form of a submit form. For example, after the user clicks on the work information in FIG. 4A (as shown at 402 in FIG. 4A), the application may display the interface shown in FIG. 4B for the user to enter the work information. In the interface shown in fig. 4B, the user can fill in information on his/her job category, job unit, job place, detailed address, time of employment, annual income interval, and the like.

Preferably, an ambiguous search can be performed during the process of the user filling out the form. For example, after entering a portion of the content, the server may perform a fuzzy search in the database with the content entered by the user and return possible results as the user fills in the work unit. For example, after the user enters "Jili," a "Jili Car group" or the like may be suggested, as shown at 412 in FIG. 4B.

Preferably, the information is automatically completed during the process of filling out the form by the user. For example, after the user enters a work unit, the server may retrieve the work place and detailed address corresponding to the work unit in the server and automatically replenish the information, as shown at 414 in FIG. 4B.

Preferably, during the process of the user filling out the form or at the user click submission (as shown at 416 in FIG. 4B), a validity check may be performed on the information entered by the user to identify a mismatch in the information and prompt the user if necessary. For example, when the user fills out a place where the work is not meaningful, the user may be prompted to fill out an error with work.

Fig. 4C shows a schematic diagram of a user submitting information in the form of an authorization service. For example, after the user clicks on the equity fund in FIG. 4A (as shown at 404 in FIG. 4A), the application may display the interface shown in FIG. 4C for the user to authorize the server to obtain the user's equity fund information. As shown in FIG. 4C, the user may click on the "Add My accumulation fund" button (shown as 422 in FIG. 4C) to select to add their accumulation fund information. After the user clicks on the button, the application may prompt the user to agree to an authorization protocol. For sensitive services, biometric identification (e.g., facial recognition (face brushing), etc.) may be performed on the user to further verify the user's identity prior to authorization. After obtaining the user's authorization, the server may access a database provided by a service provider (e.g., a public accumulation institution) to obtain corresponding information.

Fig. 4D shows a schematic diagram of a user submitting information in the form of an uploaded image. For example, after the user clicks on the property in FIG. 4A (as shown at 406 in FIG. 4A), the application may display the interface shown in FIG. 4D to upload or take an associated image. For example, for a vehicle property, the application may display an image (shown as 432 in FIG. 4D) of a driver license (which may include a home page or a sub-page) uploaded or captured by the user. Further, after the user uploads the image, image recognition may be performed on the image and text recognition may be performed on text in the image to automatically add information included in or associated with the image. The added information is also preferably collated by the user and the user may be allowed to modify the information if necessary. As shown in FIG. 4D, a confirm button (such as the "check error, confirm Add" button shown in FIG. 4D) may be clicked to formally submit the information to the server (such as shown at 434 in FIG. 4D).

Preferably, after the user uploads the image, fuzzy retrieval, automatic information filling, and/or validity checking operations may also be performed on the information identified from the image.

In addition, user information may also be submitted by the user in various other forms. For example, user information may be submitted in forms other than forms, images, authorizations, including voice entry, authentication code authorization, document upload, and the like.

Various forms of obtaining user information through interaction with a user are described above. Various types of user information that may be obtained and specific ways of obtaining corresponding user information are described below.

It is to be noted that, although a form of acquiring user information through an interactive interface is described above, the present specification embodiment is not limited to the above form, but may acquire user information in various other ways. Further, the acquisition of information for the user is not necessarily from the user's request or other interaction, but may be initiated by the server in other circumstances (e.g., actively by the server or by the server based on a request from a third party (e.g., an accident risk service provider based on a request by an insurance service provider)).

Preferably, feedback or a prompt for the authenticity of the user information may be provided via the user's client device during or after the user submits the user information. For example, during submission of user information by a user, the user information may be preliminarily authenticated by the user's client device, providing feedback or a prompt for the authenticity of the user. Alternatively, real-time communication may be made with the server during or after the user submits the user information, and the authenticity of the user information as determined by the server is communicated to the user's client device and feedback or prompts displayed by the client device.

Obtaining basic identity information of user

In one or more aspects of embodiments of the present specification, biometric identification may be used to determine the identity of a user. For example, biometric information of the user may be collected and the identity of the user may be identified based on the biometric information of the user. The user's biometric information may be collected using, for example, the user's client device (e.g., a smartphone) or other device (e.g., a device at an insurance service provider). For example, the identity of the user may be determined by face recognition, voiceprint recognition, fingerprint recognition, iris recognition, and the like.

In another aspect of embodiments of the present description, the identity of the user may be identified using information on the identity document captured in association with the user. For example, the identity of the user may be identified based on information in an image/video or other formatted file of an identification card, driving license, or other identification uploaded by the user. For example, the identity of the user may be recognized by performing text recognition on the identity document or by performing face recognition on a head portrait on the identity document.

In performing user identification, a user identity database (e.g., a resident identity database provided by a national institution) or other database (e.g., a user database provided by an insurance service provider or a third party institution (e.g., a payment service provider, etc.)) may be accessed, if necessary, to determine the identity of the user.

At the same time or after the identity of the user is determined, other basic identity information of the user may be obtained, such as name, age, place of residence, native place. For example, an image of the user's identification card, driving license, etc. may be text recognized in order to obtain one or more of the above other basic identification information. Also for example, one or more of the above other basic identity information may be obtained by accessing an identity information database, such as an identity information database provided by a national institution or insurance facilitator, or a third party institution, or the like.

In another or more embodiments of the present description, an interactive interface may be employed to receive identity information from a user.

For example, an interactive interface may be presented to a user on the user's client (e.g., a car insurance application installed on the user's smartphone, etc.) in order to guide the user in entering or otherwise submitting identity information. For example, a user may be directed to enter one or more of the various basic identity information described above.

In one or more embodiments of the present description, the authorization of the user may be obtained, and the basic identity information of the user is obtained from a service authorized by the user if the authorization of the user is obtained. For example, a user may first be requested for authorization of one or more identity information providing services (e.g., an identity information database provided by a national institution or insurance facilitator, or a third party institution, etc.), and basic identity information of the user may be obtained after authorization.

One or more of the above embodiments may be used in combination, if necessary.

Preferably, fuzzy query techniques are used during interaction with the user. Preferably, during the interaction with the user, a validity check may be performed. Preferably, the automatic completion of the information may be performed during interaction with the user. Those skilled in the art will know how to implement the above techniques and will not be described in detail herein.

Acquiring professional information or academic information of user

As described above, the user's career information includes, but is not limited to, the user's current career, current employment company, career experience, and the like. The user's sequence information may include, for example, but is not limited to, the user's highest scholarly, graduation institution, academic specialty, and the like.

In one or more embodiments of the present description, the professional information of the user may be acquired based on image recognition or character recognition. For example, an image or video submitted by a user that includes professional information may be received and processed to obtain the user's professional information. For example, an image or video of a user's business card, employee badge, etc. may be received and processed to obtain the user's professional information. For another example, an image or video of a user such as a graduation certificate or a degree certificate may be received and processed to acquire the academic information of the user.

In one or more embodiments of the present description, an online professional information service may be accessed to obtain professional information and/or academic information for a user. Examples of online professional information services include, but are not limited to: online recruitment services (e.g., various recruitment websites), online enterprise services (e.g., nailing, SLACK, etc.), professional-based social networking services (e.g., LinkedIn, etc.), and other services that may obtain professional and/or academic information for a user.

Preferably, the service may be accessed after obtaining the user's authorization in order to obtain the user's professional and/or academic information. For example, the authorization may be performed in a similar manner as in fig. 4C.

Likewise, an interactive interface may be used to guide the user in submitting professional and/or academic information, as introduced above.

Obtaining relationship information of a user

As described above, the relationship information of the user includes, but is not limited to, the user's couple relationship, co-worker relationship, friend relationship, and the like.

In one or more embodiments of the present description, the relationship information of the user may be acquired based on image recognition or character recognition. For example, an image or video submitted by a user that includes relationship information may be received and processed to obtain the relationship information of the user. For example, an image or video of a user's marriage certificate, registration certificate, or the like may be received, and text recognition may be performed on the image or video to acquire relationship information of the user.

In one or more embodiments of the present description, an online social networking service may be accessed to obtain relationship information for a user. Other online services that store relationship information may also be accessed to obtain the user's relationship information.

Preferably, the service is accessible after obtaining the user's authorization in order to obtain the user's professional information. For example, the authorization may be performed in a similar manner as in fig. 4C.

Likewise, an interactive interface may be used to guide the user in submitting professional information, as introduced above.

Obtaining driving data of user

In order to better determine the accident risk of the vehicle of the user, in addition to the user information, the driving data of the user can also be acquired. The driving data of the user includes, but is not limited to, the total driving mileage of the user, the driving route, the danger during driving, the average driving speed, etc. Details of the user's driving record, such as road conditions of the driving route, length of the daily driving route, frequency of driving route changes, driving speed, etc., will affect the accident risk.

It should be noted that the user's driving record may not be the user's driving record of driving the current vehicle, but may include the user's driving record of driving another vehicle. For example, the driving data is collected by a tachograph attached to a vehicle that the user has driven. For example, data recorded by a user's tachograph or other tachograph device (e.g., a smartphone) may be uploaded by the user through the user's client device. In the case of acquiring the driving data of the user, the accident risk of the vehicle may be further evaluated based on the driving data of the vehicle.

Authenticating authenticity of user information

As described above, in many cases, the acquired user information may be inaccurate. For example, the user may intentionally or unintentionally submit erroneous information; alternatively, where user information is obtained by the server from a database or other information source, the user information may be inaccurate or outdated, etc. In these cases, the user information may preferably be authenticated. Authentication of the user information may generally be based on the acquired user information. In a preferred embodiment, the authentication of the user information may also be based on additional authentication data in general.

Referring to fig. 5, an example schematic diagram illustrating operation of a user information authentication system 500 for authenticating user information in accordance with one or more embodiments of the present description is shown.

As shown in fig. 5, system 500 may receive user information for a user. For example, the system 500 may receive user information to be authenticated. Additionally, the system 500 may also receive user information for one or more other users. As shown in FIG. 5, system 500 may receive user A's user information 504, user B's user information 506, user C's user information 508 … …, and so on.

After receiving user information for a user, system 500 may process the user information to authenticate the authenticity of the user information. For example, various items of user information may be cross-compared to determine the authenticity of the items of user information. For example, relationship information (e.g., co-worker relationships) of a user may be compared to professional information (e.g., assigned companies) of the user to determine the authenticity of the user information.

Further, where a user uploads or otherwise obtains imagery data (e.g., from various services), various image processing algorithms may be employed to authenticate the user information for the user based on the impact data.

For example, object detection, optical character recognition, image classification, and the like may be performed on an image or video frame to recognize information included in the image or video frame and authenticate user information using the recognized information. For example, an image classification algorithm may be used to identify whether a driver license image submitted by a user is likely to be a false driver license or an expired driver license, or the like. Alternatively, object detection (e.g., face detection) may be performed on the travel license image to determine whether the travel license is indeed the user's travel license. Further, the image of the travel certificate may be subjected to optical character recognition to recognize information on the travel certificate, thereby determining whether the travel certificate includes false or outdated information or the like.

Further, to more accurately authenticate, system 500 may also receive authentication data (e.g., authentication data 510 in FIG. 5). The authentication data is data that can be used to authenticate user information. The authentication data may be, for example, information such as the user's geographic location, transfer records, shopping records, historical compliance activities, personal credit reports, historical credit bills, etc., of the user to be authenticated. For example, it can be appreciated that the better the personal credits of a user, the more trustworthy the personal information that is typically provided by the user. The authentication data may also include other conceivable data.

Preferably, the user's online payment service may be accessed by a server to obtain information such as a transfer record, a shopping record, etc. of the user. The credit information service may also be accessed by the server to obtain a record of the user's transfer. Examples of the credit information service may include an online service involving credit information of the user, such as a crime record or a loss of credit record provided by a national institution, a default record provided by a bank or the like, a credit dispute record provided by a judicial institution, and the like.

The compliance data provided by, for example, a judicial agency or road authority, may also be accessed by the server. Similar to the user information, the credit information service may also be acquired after obtaining the user authorization.

The authentication data may also include user information for other users. For example, when authenticating the user information of the user a, the user information of the user B may be used. For example, assuming that user a and user B are in the same work unit, the work unit information of user B may be used to authenticate the work unit information of user a. In the example of fig. 5, authentication data 510 may include authentication data for verifying user a's user information, authentication data for verifying user B's user information, authentication data … … for verifying user C's user information, and so forth.

In one or more embodiments of the present description, various algorithms may be employed to achieve authentication of user information. For example, one or more machine learning models may be employed to enable authentication of user information. With machine learning, in particular deep learning, associations hidden in the data can be mined, enabling the authenticity of the user information of the user to be authenticated based on data such as transfer records, shopping records, and the like.

An example of such a machine learning model is a graph neural network algorithm. The graph neural network algorithm is a deep learning architecture based on a graph (including nodes and edges) data structure. In the embodiment of the present specification, for example, a plurality of users may be used as nodes, the acquired relationship information may be used as a continuous edge, and a user information entry (for example, a current user occupation, etc.) may be used as a prediction tag to predict the user information. Other algorithms that may be envisaged by those skilled in the art may be employed to effect authentication of the user information.

Preferably, various authentication algorithms (e.g., the image-based authentication algorithm and the graph neural network algorithm described above) may be combined in order to obtain a more accurate authentication result. For example, if the travel license information of the user is determined to be "uncertain" in the image algorithm, but determined to be "true" in the other machine learning algorithms, the travel license information of the user can be considered to be "true".

In addition to the above information, other information may be utilized to authenticate the authenticity of the user information. For example, the authenticity of the user information may also be authenticated in the form of identifying the user using a laser radar, detecting the interaction environment of the user using infrared rays, and the like.

Subsequently, the system 500 may output the authentication result of the user. For example, after authenticating the user information of the user, the authentication result of the user (e.g., the authentication result 512 of the user a, the authentication result 514 of the user B, the authentication result 516 … … of the user C, etc.) may be output. The authentication result may include an indication of authenticity of the user information of the user. The indication may indicate, for example, that the user information is true, that the user information is false, or that the user information cannot be determined to be true or false, etc. Preferably, the authentication result may further include a confidence level associated with the indication of the authenticity of the user information. For example, when user information is indicated as being true, a confidence level that the user information is true may also be included in the authentication result. Preferably, the authentication result may further include authenticity of a specific item of user information. For example, the authentication result may indicate that the time of entry in the user's work information is false, and so on. User information items that are judged to be false are not generally used for subsequent accident risk assessment operations.

Assessing risk of accident

After authenticating the authenticity of the user information, the vehicle's accident risk may be assessed using the authenticated user information.

Preferably, a weight may be given to each item of the user information, and the accident risk of the vehicle may be finally determined via the weight of each item of the user information.

Taking the professional information as an example, in the case of an authenticated user working in enterprise a, the professional information entry may be assigned a weight y1 based on the probability of accident risk of other employees of enterprise a (e.g., represented by the rate of occurrence of employees of the enterprise, or inferred by the car insurance pricing of employees of the enterprise).

Taking the relationship information as an example, assuming that the user is a husband of woman a and that the probability of accident risk occurring for the husband of a crowd similar to woman a is already known, a weight y2 may be assigned to the relationship information entry based on the probability.

Taking the academic information as an example, assuming that the academic history and the profession of the user are known, the academic history information entry may be assigned a weight y3 based on the probability of accident risk for the population of the same academic history and profession.

The weights of the various scholarly information entries may then be evaluated synthetically (e.g., weighted summation of y1, y2, y3 … …, etc.) to obtain a final risk of accident.

In a more preferred embodiment, a machine learning model may be employed to determine the accident risk of the vehicle. For example, the machine learning model may be a machine learning model trained using user information of a large number of users and their known risk of accidents. The machine learning model may employ various algorithms known in the art and will not be described in detail herein. Hidden associations in the data can be mined by adopting a machine learning model, so that the accident risk of a user can be more accurately evaluated.

For example, the user's accident risk may be expressed in the form of an accident risk assessment score. Other forms are also conceivable to represent the risk of accident for the user.

Although the above mainly describes the case of determining the accident risk of the vehicle based on the user information, it should be appreciated that the accident risk of the vehicle may also be determined based on the vehicle information or a combination of the user information and the vehicle information. Determining the risk of an accident for a vehicle based on vehicle information (e.g., accident history of the vehicle, model and condition of the vehicle, age of the vehicle, mileage of the vehicle, etc.) is well known to those skilled in the art and will not be described in detail herein.

Determining vehicle insurance pricing

As described above, after determining the accident risk for the user's vehicle, the insurance pricing for the user's vehicle may be determined based further on the determined accident risk. Pricing the vehicle's insurance based on the vehicle's risk of accident (as well as other factors such as interest rates, etc.) may be based on certain rules. For example, the vehicle insurance service provider may make an actuarial based on the accident risk and price the vehicle insurance of the vehicle based on the actuarial result.

As described above, embodiments of determining an accident risk for a vehicle as described herein may be performed by an insurance service provider or by an insurance service provider delegating a dedicated accident risk assessment service provider. Both of these cases are discussed below with reference to fig. 6 and 7, respectively.

Referring to fig. 6, a schematic diagram is shown of a method 600 for determining pricing of vehicle insurance for a user, according to one or more embodiments of the present description.

The method 600 may include: at operation 602, a request for a vehicle insurance may be received from the user. For example, a request for a car insurance submitted by a user via a client device may be received by a server.

The method 600 may also include: at operation 604, the accident risk of the user's vehicle may be assessed based on the user's request. The specific operation of the evaluation of the accident risk of the vehicle may refer to the above description.

The method 600 may also include: at operation 606, vehicle insurance pricing for the user may be determined based on the accident risk of the user's vehicle.

The method 600 may also include: optionally, at operation 608, after determining the user's car insurance pricing, the car insurance pricing may be transmitted to the user's client device.

Referring to FIG. 7, a schematic diagram of another method 700 for determining pricing of vehicle insurance for a user is shown, according to one or more embodiments of the present description.

The method 700 may include: at operation 702, a request from an insurance service provider to assess an accident risk of a user's vehicle may be received. For example, the request may also include user information for the user. In addition, the request may also include other information, such as vehicle information, etc.

In this case, a request for a car insurance from a user may be received by the car insurance service provider, and user information and other data submitted by the user may be received by the car insurance service provider. Of course, some of the user information may be obtained by the server of the accident risk assessment service provider from various services or databases, as introduced above.

The method 700 may include: at operation 704, the risk of accident for the user's vehicle may be assessed based on the request of the car insurance service provider. The accident risk may be represented, for example, by an accident risk assessment score.

The method 700 may further include: at operation 706, the accident risk (e.g., represented by the accident risk assessment score) for the user's vehicle may be transmitted to the insurance service provider for use by the insurance service provider in pricing the vehicle insurance for the user. After pricing the car insurance, the car insurance service provider may feed back the car insurance pricing to the user, e.g., the car insurance pricing may be transmitted to the user's client device.

Referring to fig. 8, a schematic diagram of an example system 800 that may be used to assess a risk of accident for a user's vehicle in accordance with embodiments herein is shown.

As shown in fig. 8, system 800 may include an information acquisition module 802. The information obtaining module 802 may be configured to obtain various information, for example, obtain user information of the user, the user information including one or more of basic identity information, relationship information, professional information, and academic information of the user. The information acquisition module 802 may also be configured to acquire vehicle information. The specific operation of the information obtaining module 802 may refer to the above description of obtaining user information, vehicle information, and the like. As described above, the information acquisition module may access an online social networking service of the user to acquire relationship information of the user. Alternatively, the information acquisition module may access an online professional information service of the user to acquire professional information and/or academic information of the user.

The system 800 may also include an authentication module 804. Authentication module 804 may be configured to process the user information to authenticate the authenticity of the user information. The specific operation of the authentication module 804 may be as described above with reference to the operation of authenticating user information. Preferably, the authentication module 804 may be further configured to obtain authentication data including data that can be used to authenticate the authenticity of the user information. The authentication data may include, for example, user information for other users, and/or the user's geographic location, transfer records, shopping records, historical compliance activities, personal credit reports, historical credit bills, and the like. In this case, authenticating the authenticity of the user information may also be further based on the authentication data.

The system 800 may also include an accident risk assessment module 806. The accident risk assessment module 806 may be configured to automatically determine an accident risk for the vehicle based at least in part on the authenticated user information. The specific operations of the authentication module 804 may be as described above for the operations of assessing risk of an accident.

Preferably, the system 800 may further include an insurance pricing module 808 configured to determine insurance pricing for the vehicle based on the risk of accident for the vehicle. Alternatively, the system 800 may include an accident risk transmission module (not shown in fig. 8) that transmits the accident risk to the insurance service provider.

It should be noted that the modules may be located on the same server or on different servers.

Referring to fig. 9, there is shown a schematic block diagram of an apparatus 900 that may be used as a server or client device as described above according to an embodiment of the present description.

The apparatus may include a processor 910 configured to perform any of the methods described above, and a memory 915. The memory may store, for example, acquired user information, vehicle information, authentication data, and the like.

The apparatus may include a network connection element 925, which may include, for example, a network connection device that connects to other devices (e.g., a server may connect to a user's client device and/or other servers, to which the client device may connect) through a wired connection or a wireless connection. The wireless connection may be, for example, a WiFi connection, a Bluetooth connection, a 3G/4G/5G network connection, or the like.

The device may also optionally include other peripheral components 920 such as a keyboard and mouse, for example.

Each of these modules may communicate with each other directly or indirectly, e.g., via one or more buses, such as bus 905.

Also, the present application discloses a computer-readable storage medium comprising computer-executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method of the embodiments described herein.

Additionally, an apparatus is disclosed that includes a processor and a memory having stored thereon computer-executable instructions that, when executed by the processor, cause the processor to perform the method of the embodiments described herein.

Additionally, a system comprising means for implementing the methods of the embodiments described herein is also disclosed.

It is to be understood that methods according to one or more embodiments of the present description can be implemented in software, firmware, or a combination thereof.

It should be understood that the embodiments in the present specification are described in a progressive manner, and the same or similar parts in the embodiments are referred to each other, and each embodiment is described with emphasis on the differences from the other embodiments. In particular, as to the apparatus and system embodiments, since they are substantially similar to the method embodiments, the description is relatively simple and reference may be made to some descriptions of the method embodiments for related points.

It should be understood that the above description describes particular embodiments of the present specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

It should be understood that an element described herein in the singular or shown in the figures only represents that the element is limited in number to one. Furthermore, modules or elements described or illustrated herein as separate may be combined into a single module or element, and modules or elements described or illustrated herein as single may be split into multiple modules or elements.

It is also to be understood that the terms and expressions employed herein are used as terms of description and not of limitation, and that the embodiment or embodiments of the specification are not limited to those terms and expressions. The use of such terms and expressions is not intended to exclude any equivalents of the features shown and described (or portions thereof), and it is recognized that various modifications may be made within the scope of the claims. Other modifications, variations, and alternatives are also possible. Accordingly, the claims should be looked to in order to cover all such equivalents.

Also, it should be noted that while the present invention has been described with reference to specific exemplary embodiments, it should be understood by those skilled in the art that the above embodiments are merely illustrative of one or more embodiments of the present invention, and various changes and substitutions of equivalents may be made without departing from the spirit of the present invention, and therefore, it is intended that all changes and modifications to the above embodiments be included within the scope of the appended claims.

Claims

1. A method for assessing a user's vehicle for risk of accident, comprising:

acquiring user information of the user, wherein the user information comprises one or more of basic identity information, relationship information, professional information and academic information of the user;

processing the user information to authenticate authenticity of the user information; and

automatically determining an accident risk for the vehicle based at least in part on the authenticated user information.

2. The method of claim 1, wherein the user is guided by the user's client device to submit at least a portion of the user information by one or more of: form submission, image uploading and service authorization.

3. The method of claim 2, wherein feedback or a prompt for authenticity of the user information is provided via a client device of the user during or after the user submits the user information.

4. The method of claim 1, further comprising:

accessing, by a server, an online social networking service of the user to obtain relationship information of the user.

5. The method of claim 1, further comprising:

accessing, by a server, an online professional information service of the user to obtain professional information and/or academic information of the user.

6. The method of claim 4 or 5, further comprising:

obtaining authorization of the user prior to accessing the online social networking service or the online professional information service.

7. The method of claim 1, further comprising:

acquiring authentication data, wherein the authentication data comprises data which can be used for authenticating the authenticity of the user information; and

authenticating authenticity of the user information based at least in part on the authentication data.

8. The method of claim 1, wherein the authentication data comprises one or more of a geographic location of the user, a transfer record, a shopping record, historical gauge behavior, a personal credit report, a historical credit bill.

9. The method of claim 8, further comprising:

accessing, by a server, an online payment service and/or a credit information service of the user to obtain at least a portion of the authentication data of the user.

10. The method of claim 7, wherein the authentication data includes user information of other users.

11. The method of claim 7, wherein the authentication data comprises one or more of a geographic location of the user, a transfer record, a shopping record, historical gauge behavior, a personal credit report, a historical credit bill.

12. The method of claim 1, further comprising:

determining a vehicle insurance pricing for the vehicle based on the accident risk of the vehicle.

13. The method of claim 1, further comprising:

transmitting the accident risk of the vehicle or the vehicle insurance pricing determined based on the accident risk to the client device of the user.

14. The method of claim 1, wherein the accident risk is represented by an accident risk assessment score, the method further comprising:

and transmitting the accident risk assessment score to a vehicle insurance service provider.

15. The method of claim 1, further comprising:

acquiring travel data of the user, the travel data being collected by a tachograph attached to a vehicle driven by the user; and

the accident risk of the vehicle is further assessed based on the user's travel data.

16. A system for assessing the risk of an accident with a user's vehicle, comprising:

an information acquisition module configured to acquire user information of the user, the user information including one or more of basic identity information, relationship information, occupation information, and academic information of the user;

an authentication module configured to process the user information to authenticate authenticity of the user information; and

an accident risk assessment module configured to automatically determine an accident risk for the vehicle based at least in part on the authenticated user information.

17. The system of claim 16, the information acquisition module further configured to:

accessing an online social networking service of the user to obtain relationship information of the user; and/or

Accessing an online professional information service of the user to obtain professional information and/or academic information of the user.

18. The system of claim 16, the authentication module further configured to:

19. The system of claim 16, further comprising:

a vehicle insurance pricing module configured to determine vehicle insurance pricing for the vehicle based on the accident risk of the vehicle.

20. An apparatus for assessing the risk of an accident with a user's vehicle, comprising:

a memory; and

a processor configured to perform the method of any one of claims 1-15.

21. A computer-readable storage medium storing instructions that, when executed by a computer, cause the computer to perform the method of any of claims 1-15.