CN112035644A - Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium - Google Patents

Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112035644A
CN112035644A CN202010904253.7A CN202010904253A CN112035644A CN 112035644 A CN112035644 A CN 112035644A CN 202010904253 A CN202010904253 A CN 202010904253A CN 112035644 A CN112035644 A CN 112035644A
Authority
CN
China
Prior art keywords
user
vehicle
semantic
travel
score
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
Application number
CN202010904253.7A
Other languages
Chinese (zh)
Inventor
薄璐佳
董靓
徐齐胜
丘旋
刘贝宁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Navinfo Co Ltd
Original Assignee
Navinfo Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Navinfo Co Ltd filed Critical Navinfo Co Ltd
Priority to CN202010904253.7A priority Critical patent/CN112035644A/en
Publication of CN112035644A publication Critical patent/CN112035644A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • 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
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

The application provides a method and a device for adjusting a car insurance scheme, electronic equipment and a storage medium, wherein the method comprises the following steps: first driving data of a vehicle in a preset period is acquired. According to the first driving data, a user semantic portrait of the vehicle is established, wherein the user semantic portrait comprises a first semantic label, a second semantic label and a third semantic label, the first semantic label is used for describing a travel rule of the user, the second semantic label is used for describing a travel risk degree of the user, and the third semantic label is used for describing an abnormal driving behavior of the user. And adjusting the car insurance scheme of the vehicle by utilizing the semantic portrait of the user. The accuracy of the semantic sketch of the vehicle user is improved, the vehicle insurance scheme of the vehicle is adjusted by the semantic sketch of the user, the personalized adjustment of the vehicle insurance scheme is achieved, and the reliability of the personalized adjustment of the vehicle insurance scheme is improved.

Description

Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of vehicle insurance technologies, and in particular, to a method and an apparatus for adjusting a vehicle insurance scheme, an electronic device, and a storage medium.
Background
In the car insurance pricing, compared with non-driving behavior factors such as car models, car purchase prices, the annual risk rate and the like, actual driving behavior factors such as sudden braking, night driving, single driving mileage and the like can greatly improve the accuracy of prediction of the car insurance probability, and the risk is specifically refined to each car owner, so that the car insurance pricing can be used as an important basis for car insurance pricing, the car insurance pricing is more reasonable and reliable, and better identification and risk control of insurance companies are facilitated.
In the prior art, automobile Insurance (UBI) Based on driving behaviors of users attracts extensive attention of industries such as automobiles, Insurance, internet and the like. The conventional UBI automobile insurance calculation mode takes the driving behaviors of a vehicle and a driver as a calculation core. The traditional automobile insurance calculation index and the index for measuring the driving behavior habit are used as calculation basis to judge the safety level of the driver, and different premium benefits are given to the automobile owners with different safety levels, so that the automobile insurance with differential rates is realized. The traditional vehicle insurance comprises vehicle damage insurance, traffic intensity insurance, third party responsibility insurance, on-vehicle seat personnel insurance, whole vehicle theft and emergency, glass breakage insurance and the like, and measures the indexes of driving behavior habits: driving distance, emergency braking times, driving distance, four-point driving times from midnight to early morning and the like.
However, in the UBI in the prior art, the way of evaluating the driving behavior habit of the driver is very likely to cause misjudgment of the driver behavior, and further the reliability of personalized adjustment of the car insurance scheme is low.
Disclosure of Invention
The application provides a vehicle insurance scheme adjusting method and device, electronic equipment and a storage medium, so that personalized adjustment of different vehicle insurance schemes is realized, and the reliability of personalized adjustment of the vehicle insurance schemes is improved.
In a first aspect, an embodiment of the present application provides a method for adjusting a car insurance scheme, including:
first driving data of the vehicle in a preset period are acquired, and the first driving data are used for describing the running condition of the vehicle and the driving behavior of a user.
According to the first driving data, a user semantic portrait of the vehicle is established, wherein the user semantic portrait comprises a first semantic label, a second semantic label and a third semantic label, the first semantic label is used for describing a travel rule of the user, the second semantic label is used for describing a travel risk degree of the user, and the third semantic label is used for describing an abnormal driving behavior of the user.
And adjusting the car insurance scheme of the vehicle by utilizing the semantic portrait of the user.
In the embodiment of the application, the user semantic representation of the vehicle is established according to the first driving data of the vehicle in the preset period, besides the semantic tags describing abnormal driving behaviors of the user, the semantic tags describing travel rules and travel adventure degrees of the user are also considered in the user semantic representation, accuracy of the user semantic representation of the vehicle is improved, the vehicle insurance scheme of the vehicle is adjusted by the user semantic representation, personalized adjustment of the vehicle insurance scheme of the vehicle is achieved, and reliability of the personalized adjustment of the vehicle insurance scheme is improved.
In one possible embodiment, the first driving data includes vehicle trajectory data and vehicle driving data, and the creating a semantic representation of a user of the vehicle based on the first driving data includes:
determining a first semantic label and a second semantic label of a semantic portrait of a user according to vehicle track data; and determining a third semantic label of the semantic portrait of the user according to the vehicle driving data.
In one possible embodiment, determining a first semantic tag of a semantic representation of a user based on vehicle trajectory data includes one or more of the following:
and determining the distribution condition of interval time between adjacent trips by using the trip starting time in the vehicle track data so as to obtain the degree of the travel rule of the user in time, wherein the travel rule of the user comprises the degree of the travel rule of the user in time.
Or determining the distribution condition of the resident points of the vehicle by using the destination information in the vehicle track data to obtain the degree of regularity of the user on the trip destination, wherein the trip rule of the user comprises the degree of regularity of the user on the trip destination.
Or determining the distribution condition from the starting point to the destination of the travel route of the user by using the route starting point and the destination information in the vehicle track data so as to obtain the degree of regularity from the starting point to the destination of the travel route of the user, wherein the travel rule of the user comprises the degree of regularity from the starting point to the destination of the travel route of the user.
Or determining the distribution condition of the driving times of each driving road section of the user by using the driving path information in the vehicle track data so as to obtain the degree of regularity of the user on the travel path, wherein the travel rule of the user comprises the degree of regularity of the user on the travel path.
In one possible embodiment, determining a second semantic tag of the semantic representation of the user based on the vehicle trajectory data includes:
determining the distribution of the running times of each first running road section in the first running path of the vehicle in the running path information of the vehicle track data; determining the travel risk degree of the user by utilizing the distribution condition of the travel times of each first travel road section; and/or determining a stationary point of the vehicle by using destination information in the vehicle track data; and determining the resident point change condition of the vehicle in a preset period by utilizing the resident point of the vehicle so as to determine the travel risk degree of the user.
In one possible embodiment, the method for adjusting the vehicle insurance scheme of the vehicle by utilizing the semantic representation of the user comprises the following steps:
respectively determining first user scores corresponding to the first semantic label, the second semantic label and the third semantic label; or respectively determining a first score and a weight corresponding to the first semantic label, the second semantic label and the third semantic label, and determining a first user score of the vehicle by using the first score and the weight; the first user score is used for describing a travel rule, a travel risk degree and an abnormal driving behavior of the user in a preset period; and adjusting the car insurance scheme according to the first user score.
In one possible embodiment, adjusting the car insurance scheme based on the first user score includes:
comparing the first user score with a second user score in the last period of the preset period, wherein the second user score is used for describing the travel rule, the travel risk degree and the abnormal driving behavior of the user in the last period of the preset period; if the first user score is greater than the second user score, the premium of the vehicle insurance scheme is reduced and/or the premium of the vehicle insurance scheme is increased.
In one possible embodiment, if the first user score is greater than the second user score, decreasing the premium and/or increasing the premium of the vehicle insurance scheme comprises:
determining a first preset interval in which the score of the first user exceeds the score of the second user, and a second preset interval in which the score of the second user is; determining a first adjustment amount of premium and/or a second adjustment amount of premium by using the first preset interval, the second preset interval and the first corresponding relation; the first corresponding relation is the relation between the first preset interval, the second preset interval and the first adjustment limit and/or the second adjustment limit; the premium is reduced by the first adjustment amount and/or the premium is increased by the second adjustment amount.
The apparatus, the electronic device, the computer-readable storage medium, and the computer program product provided in the embodiments of the present application are described below, and contents and effects thereof may refer to the car insurance scheme adjustment method provided in the embodiments of the present application, and are not described again.
In a second aspect, an embodiment of the present application provides a vehicle insurance scheme adjusting device, including:
the acquisition module is used for acquiring first driving data of the vehicle in a preset period, and the first driving data is used for describing the driving condition of the vehicle and the driving behavior of a user.
The building module is used for building a user semantic representation of the vehicle according to the first driving data, wherein the user semantic representation comprises a first semantic label, a second semantic label and a third semantic label, the first semantic label is used for describing a travel rule of the user, the second semantic label is used for describing a travel risk degree of the user, and the third semantic label is used for describing an abnormal driving behavior of the user.
And the adjusting module is used for adjusting the vehicle insurance scheme of the vehicle by utilizing the semantic portrait of the user.
In one possible embodiment, the first driving data includes vehicle trajectory data and vehicle driving data, and the establishing module is specifically configured to:
determining a first semantic label and a second semantic label of a semantic portrait of a user according to vehicle track data; and determining a third semantic label of the semantic portrait of the user according to the vehicle driving data.
In one possible embodiment, the establishing module is specifically configured to perform one or more of the following combinations:
and determining the distribution condition of interval time between adjacent trips by using the trip starting time in the vehicle track data so as to obtain the degree of the travel rule of the user in time, wherein the travel rule of the user comprises the degree of the travel rule of the user in time.
Or determining the distribution condition of the resident points of the vehicle by using the destination information in the vehicle track data to obtain the degree of regularity of the user on the trip destination, wherein the trip rule of the user comprises the degree of regularity of the user on the trip destination.
Or determining the distribution condition from the starting point to the destination of the travel route of the user by using the route starting point and the destination information in the vehicle track data so as to obtain the degree of regularity from the starting point to the destination of the travel route of the user, wherein the travel rule of the user comprises the degree of regularity from the starting point to the destination of the travel route of the user.
Or determining the distribution condition of the driving times of each driving road section of the user by using the driving path information in the vehicle track data so as to obtain the degree of regularity of the user on the travel path, wherein the travel rule of the user comprises the degree of regularity of the user on the travel path.
In a possible implementation, the establishing module is specifically configured to:
determining the distribution of the running times of each first running road section in the first running path of the vehicle in the running path information of the vehicle track data; determining the travel risk degree of the user by utilizing the distribution condition of the travel times of each first travel road section; and/or determining a stationary point of the vehicle by using destination information in the vehicle track data; and determining the resident point change condition of the vehicle in a preset period by utilizing the resident point of the vehicle so as to determine the travel risk degree of the user.
In a possible implementation, the adjusting module is specifically configured to:
respectively determining first user scores corresponding to the first semantic label, the second semantic label and the third semantic label; or respectively determining a first score and a weight corresponding to the first semantic label, the second semantic label and the third semantic label, and determining a first user score of the vehicle by using the first score and the weight; the first user score is used for describing a travel rule, a travel risk degree and an abnormal driving behavior of the user in a preset period; and adjusting the car insurance scheme according to the first user score.
In a possible implementation, the adjusting module is specifically configured to:
comparing the first user score with a second user score in the last period of the preset period, wherein the second user score is used for describing the travel rule, the travel risk degree and the abnormal driving behavior of the user in the last period of the preset period; if the first user score is greater than the second user score, the premium of the vehicle insurance scheme is reduced and/or the premium of the vehicle insurance scheme is increased.
In a possible implementation, the adjusting module is specifically configured to:
determining a first preset interval in which the score of the first user exceeds the score of the second user, and a second preset interval in which the score of the second user is; determining a first adjustment amount of premium and/or a second adjustment amount of premium by using the first preset interval, the second preset interval and the first corresponding relation; the first corresponding relation is the relation between the first preset interval, the second preset interval and the first adjustment limit and/or the second adjustment limit; the premium is reduced by the first adjustment amount and/or the premium is increased by the second adjustment amount.
In a third aspect, an embodiment of the present application provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as provided by the first aspect or the first aspect realizable manner.
In a fourth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method as provided in the first aspect or the first aspect implementable manner.
In a fifth aspect, an embodiment of the present application provides a computer program product, including: executable instructions for implementing the method as provided in the first aspect or the first aspect alternatives.
According to the method and the device for adjusting the vehicle insurance scheme, the electronic equipment and the storage medium, the first driving data of the vehicle in the preset period are obtained. According to the first driving data, a user semantic portrait of the vehicle is established, wherein the user semantic portrait comprises a first semantic label, a second semantic label and a third semantic label, the first semantic label is used for describing a travel rule of the user, the second semantic label is used for describing a travel risk degree of the user, and the third semantic label is used for describing an abnormal driving behavior of the user. And adjusting the car insurance scheme of the vehicle by utilizing the semantic portrait of the user. In the embodiment of the application, the user semantic representation of the vehicle is established according to the first driving data of the vehicle in the preset period, besides the semantic tags describing abnormal driving behaviors of the user, the semantic tags describing travel rules and travel adventure degrees of the user are also considered in the user semantic representation, accuracy of the user semantic representation of the vehicle is improved, the vehicle insurance scheme of the vehicle is adjusted by the user semantic representation, personalized adjustment of the vehicle insurance scheme of the vehicle is achieved, and reliability of the personalized adjustment of the vehicle insurance scheme is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is an exemplary application scenario architecture diagram provided by an embodiment of the present application;
fig. 2 is a schematic flow chart of a vehicle insurance scheme adjustment method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating a vehicle insurance scheme adjustment method according to another embodiment of the present application;
FIG. 4 is a schematic diagram of a first correspondence provided by an embodiment of the present application;
FIG. 5 is a schematic structural diagram of an adjustment apparatus for a vehicle insurance scheme according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the car insurance pricing, compared with non-driving behavior factors such as car models, car purchase prices, the annual risk rate and the like, actual driving behavior factors such as sudden braking, night driving, single driving mileage and the like can greatly improve the accuracy of prediction of the car insurance probability, and the risk is specifically refined to each car owner, so that the car insurance pricing can be used as an important basis for car insurance pricing, the car insurance pricing is more reasonable and reliable, and better identification and risk control of insurance companies are facilitated. The conventional UBI automobile insurance calculation mode takes the driving behaviors of a vehicle and a driver as a calculation core. The traditional automobile insurance calculation index and the index for measuring the driving behavior habit are used as calculation basis to judge the safety level of the driver, and different premium benefits are given to the automobile owners with different safety levels, so that the automobile insurance with differential rates is realized. The traditional vehicle insurance comprises vehicle damage insurance, traffic intensity insurance, third party responsibility insurance, on-vehicle seat personnel insurance, whole vehicle theft and emergency, glass breakage insurance and the like, and measures the indexes of driving behavior habits: driving distance, emergency braking times, driving distance, four-point driving times from midnight to early morning and the like. However, in the UBI in the prior art, the way of evaluating the driving behavior habit of the driver is very likely to cause misjudgment of the driver behavior, and further the reliability of personalized adjustment of the car insurance scheme is low.
The invention conception of the vehicle insurance scheme adjusting method, the device, the electronic equipment and the storage medium provided by the embodiment of the application is that the user semantic representation of the vehicle is established according to the first driving data of the vehicle in the preset period, and not only the semantic tags describing the abnormal driving behaviors of the user but also the semantic tags describing the travel rules and the travel risk degree of the user are considered in the user semantic representation, so that the accuracy of the user semantic representation of the vehicle is improved, the vehicle insurance scheme of the vehicle is adjusted by using the user semantic representation, the personalized adjustment of the vehicle insurance scheme of the vehicle is realized, and the reliability of the personalized adjustment of the vehicle insurance scheme is improved.
An exemplary application scenario of the embodiments of the present application is described below.
The vehicle insurance scheme adjusting method provided by the embodiment of the application can be executed through the vehicle insurance scheme adjusting device provided by the embodiment of the application, the vehicle insurance scheme adjusting device provided by the embodiment of the application can be integrated on terminal equipment or a server, or the vehicle insurance scheme adjusting device can be the terminal equipment or the server, the embodiment of the application does not limit the specific type of the terminal equipment or the server, for example, the terminal equipment can be a smart phone, a personal computer, a tablet computer, a wearable device, a vehicle-mounted terminal, a monitoring device and the like. Fig. 1 is an exemplary application scenario architecture diagram provided in an embodiment of the present application, and as shown in fig. 1, the architecture mainly includes: a terminal device 11 and a server 12. The method for adjusting the car insurance scheme provided by the embodiment of the present Application can be applied to the terminal device 11, and for example, can be implemented by Application software or a web page in the terminal device 11, for example, by an Application (APP) in the terminal device. The terminal device 11 and the server 12 perform data communication, for example, the terminal device 11 may obtain driving data of the vehicle and the like through the server 12, which is not limited in the embodiment of the present application, and the server may store and process the driving data and the like, which is not limited in the embodiment of the present application.
Fig. 2 is a schematic flow diagram of a vehicle insurance scheme adjustment method according to an embodiment of the present application, where the method may be executed by a vehicle insurance scheme adjustment device, and the device may be implemented in a software and/or hardware manner, and the vehicle insurance scheme adjustment method is described below with a terminal device as an execution subject, as shown in fig. 2, the vehicle insurance scheme adjustment method according to the embodiment of the present application may include:
step S101: first driving data of a vehicle in a preset period is acquired.
The first driving data is driving data of the vehicle in a preset period, and the preset period of the vehicle may be a period of updating a vehicle insurance scheme, for example, the vehicle updates the vehicle insurance scheme every half year, the first driving data may be driving data of the vehicle in half year before the current vehicle insurance scheme is updated, and for example, the vehicle updates the vehicle insurance scheme every other year, the first driving data may be driving data of the vehicle in one year before the current vehicle insurance scheme is updated.
The first driving data is used to describe a running condition of the vehicle and a driving behavior of the user. The embodiment of the application does not limit the specific data form, content and the like of the first driving data, and in a possible implementation, the first driving data may include vehicle trajectory data of the vehicle in a preset period, and the vehicle trajectory data may include information such as a trajectory of each trip of the vehicle, a trip time, trip weather, a trip starting Point, a destination, a stop Point, a trajectory path, and a Point of Interest (POI) on a vehicle trajectory. The first driving data may also be vehicle driving data, and the vehicle driving data may include driving behavior data of a user, a driving speed of the vehicle, a braking frequency, a starting speed, a turning frequency, a lane changing frequency, and the like.
In one possible embodiment, the first driving data of the vehicle in the preset period may be data that has been preprocessed, in another possible embodiment, the first driving data of the vehicle in the preset period may be raw data, and if the first driving data is raw data, in one possible embodiment, before creating the semantic representation of the user of the vehicle according to the first driving data, the method further includes: and performing road network matching processing, data cleaning processing and data compression on the first driving data to obtain the preprocessed first driving data.
The embodiment of the present application does not limit the specific implementation manner of performing the road network matching process, the data cleaning process, and the data compression on the first driving data. The original data may have noise, the data with larger noise value is removed through data cleaning, the data with acceptable noise value is corrected, and the static degree of the driving data is ensured. Because the driving data may have positioning errors, the path data is not necessarily on the road network, and can be matched through the road network so as to facilitate subsequent processing. Because the original data volume is very large, the efficiency of the algorithm can be greatly reduced by directly using the original data volume, and therefore, the efficiency of subsequent analysis can be improved by carrying out data compression on the first driving data.
Step S102: and establishing a user semantic portrait of the vehicle according to the first driving data, wherein the user semantic portrait comprises a first semantic label, a second semantic label and a third semantic label.
After the first driving data of the vehicle in the preset period is acquired, a user semantic representation of the vehicle can be established according to the first driving data. For convenience of introduction, the embodiment of the application divides the user semantic representation into a low semantic user representation and a high semantic user representation. The high-semantic user portrait comprises a first semantic label and a second semantic label, and the first semantic label and the second semantic label are respectively used for describing a travel rule of a user and a travel risk degree of the user; the low semantic user representation includes a third semantic tag describing abnormal driving behavior of the user.
Specific implementation manners for establishing the low-semantic user portrait may be different for different third semantic tags, and the specific implementation manner for establishing the low-semantic user portrait according to the first driving data is not limited in the embodiment of the application. In one possible embodiment, the first driving data includes vehicle driving data, and the third semantic tag of the user semantic representation is determined based on the vehicle driving data. The vehicle travel data may include, among other things, travel speed, travel time, travel acceleration, and the like. The third semantic tag may include one or more indicators, which is not limited in this embodiment. In one possible embodiment, the third semantic tag includes a combination of one or more of the following: the present invention is not limited to the above embodiments, and the present invention is not limited to the embodiments, but may include rapid acceleration data, rapid deceleration data, rapid start data, rapid brake data, overspeed data, turning data, lane change data, night driving data, and the like. After the third semantic tag is determined, the low semantic user representation can be established through the first driving data corresponding to the third semantic tag. Taking the third semantic tag including the rapid acceleration data as an example, the rapid acceleration data in the first driving data of the user may be counted, and the rapid acceleration data is subjected to statistical processing, so as to determine the frequency of the rapid acceleration of the user, or the rapid acceleration of the user is scored by using the frequency of the rapid acceleration of the user, so as to obtain the score of the rapid acceleration of the user. The low semantic user profile may include a frequency of rapid acceleration of the user, or a score of rapid acceleration behavior of the user, and this embodiment of the application is only exemplified by the third semantic tag including rapid acceleration data, and a manner of processing other indexes in the third semantic tag may refer to this manner, but is not limited thereto.
The high semantic user portrait comprises a first semantic label and a second semantic label and is used for describing the travel rule and the travel risk degree of the user so as to highlight information such as user character characteristics, social roles and favorite preferences. The embodiment of the application is not limited to the specific implementation mode of establishing the high semantic user portrait of the vehicle according to the first driving data. In one possible embodiment, creating a semantic representation of a user of a vehicle based on first driving data includes: and determining a first semantic label and a second semantic label of the semantic portrait of the user according to the vehicle track data.
The first semantic tag is used for describing a travel rule of the user, and the travel rule of the user can be represented by one or more of the following combinations: the method includes the steps of determining a travel rule degree of a user in time, a travel rule degree of the user in a travel purpose, a travel rule degree of the user from a travel starting point to a travel destination, or a travel route, and setting a specific representation form of the travel rule of the user according to needs.
In a first possible implementation manner, the travel rule of the user includes a travel rule degree of the user in time, and the determining, according to the vehicle trajectory data, a first semantic tag of the semantic representation of the user includes: and determining the distribution condition of interval time between adjacent trips by using the trip starting time in the vehicle trajectory data so as to obtain the travel rule degree of the user in time.
The vehicle track data may include a trip start time by counting an interval of the trip start times of adjacent trips of the vehicle as an interval time between the adjacent trips. After determining the interval time between adjacent trips, the distribution of the interval time between adjacent trips may be further determined. For example, the interval time is divided into a plurality of time intervals, such as time intervals including within 1 hour, between 1 hour and 2 hours, between 2 hours and 3 hours, and so on.
The distribution situation of the interval time between the adjacent trips is represented by counting the time interval of the interval time between the adjacent trips and the probability of the interval time in different time intervals, so as to represent the travel regularity degree of the user in time. The more dispersed the probability distribution of the interval time between the adjacent trips in different time intervals, the lower the degree of the travel regularity of the user in time. In one possible implementation, the degree of travel regularity of the user in time may be represented by the time rhythm entropy. Wherein the time rhythm entropy can be calculated by the following formula:
Figure BDA0002660838200000111
wherein E istRepresenting the time rhythm entropy, n representing the total number of time intervals, i representing the number of time intervals, tiDenotes the ith time interval, p (t)i) Indicating the spacing of adjacent strokesAt time tiThe probability of (c). Wherein E istThe larger the value of (A), the lower the degree of the travel regularity of the user in time is, EtThe smaller the value of (b), the higher the degree of the travel regularity of the user in time.
In a second possible implementation manner, the travel rule of the user includes a degree of rule of the user on a travel purpose, and the determining, according to the vehicle trajectory data, a first semantic tag of the semantic representation of the user includes: and determining the distribution condition of resident points of the vehicle by using the destination information in the vehicle track data so as to obtain the degree of regularity of the user on the travel purpose.
The destination information may be represented by longitude and latitude, a geographical sign, a name of a place, and the like, and the resident point of the vehicle may be considered as a place where the vehicle is frequently parked or an area range where the vehicle is frequently parked, for example, the resident point may include a cell where the user is located, an office building area where the user is located, a business district where the user frequently goes, and the like. The distribution situation of the resident points of the vehicle is determined by using the destination information in the vehicle track data, and the resident points of the vehicle can be determined by performing cluster analysis on the destinations in the vehicle track data. The regular degree of the user on the trip purpose can be represented by the distribution situation of the resident points of the vehicle, wherein the more concentrated the distribution of the resident points of the vehicle is, the higher the regular degree of the user on the trip purpose is, and the more dispersed the distribution of the resident points of the vehicle is, the lower the regular degree of the user on the trip purpose is.
In one possible implementation, the degree of regularity of the user for the travel purpose may be represented by a resident point entropy value, which may be calculated by the following formula:
Figure BDA0002660838200000112
wherein E isspRepresenting the entropy of the resident points, m representing the total number of resident points, j representing the number of resident points, SjDenotes the jth resident point, p (S)j) Representing the frequency of user access to the jth resident pointHeat label of the gauge constant stagnation point. The stagnation point entropy values may be used to represent heterogeneity of the user's stagnation points to determine predictability of the user's travel destination. The larger the entropy value of the resident point is, the lower the rule degree of the user on the trip destination is, the lower the predictability of the trip destination of the user is, and the risk of the vehicle is probably relatively higher; the smaller the entropy value of the resident point is, the higher the degree of regularity of the user on the travel purpose is, the higher the predictability of the travel destination of the user is, and the risk of the vehicle is likely to be relatively low.
In a third possible implementation manner, the travel rule of the user includes a degree of a rule from a travel starting point to a destination of the user, and the determining, according to the vehicle trajectory data, a first semantic tag of the semantic representation of the user includes: and determining the distribution condition from the starting point to the destination of the trip travel of the user by using the information of the starting point and the destination of the travel in the vehicle track data so as to obtain the degree of regularity from the starting point to the destination of the trip of the user.
The relationship between each trip of the vehicle can be determined according to the distribution condition of the starting point and the destination of the trip of the user, and the higher the frequency of the same trip of the vehicle is, the higher the degree of regularity of the trip from the starting point to the destination of the user is, and further the higher the predictability of the trip destination of the user is, the lower the risk rate of the vehicle is. In one possible implementation, the degree of regularity of the user from the starting point of the trip to the destination may be represented by a travel entropy value, which may be calculated by the following formula:
Figure BDA0002660838200000121
wherein E isODRepresenting travel entropy, OIDJIndicating user slave OIPoint out to arrive DJDot, p (O)IDJ) Indicating user slave OIPoint out to arrive DJFrequency of travel of points, I denotes the number of starting points, J denotes the number of destinations, N denotes the number of starting points, M denotes the number of destinations, OIDenotes the I-th starting point, DJIndicating the jth destination.
In a fourth possible implementation manner, the determining, by the vehicle trajectory data, a first semantic tag of the semantic representation of the user according to the travel rule of the user including a degree of regularity of a travel path of the user includes: and determining the distribution condition of the driving times of each driving road section of the user by using the driving path information in the vehicle track data so as to obtain the degree of regularity of the travel path of the user.
The vehicle driving track data includes driving path information, and the driving path information may include driving sections passed by a trip and the number of driving times of each driving section. By using the number of times of travel of each travel section, the distribution of the number of times of travel of each travel section of the user is determined. The more concentrated the distribution condition of the driving times of each driving road section is, the higher the degree of regularity of the user on the travel path is, and the higher the predictability of the user travel path is; the more distributed the running times of each running road section, the lower the regularity degree of the user on the travel route is, and the lower the predictability of the user travel route is.
In one possible implementation, the degree of regularity of the user on the travel path may be represented by a path entropy value, which may be calculated by the following formula:
Figure BDA0002660838200000131
wherein E isrRepresenting the path entropy, K representing the total number of travel links traveled by the user, K representing the number of travel links, rkDenotes the kth road segment, p (r)k) Indicating the frequency of travel of the user for the k-th travel segment. ErThe larger the value of (E), the lower the degree of regularity of the user in the travel route, ErThe smaller the value of (A), the more regular the user is in the travel path.
It should be noted that, any of the four manners for determining the first semantic tag of the semantic representation of the user may be combined at will, for example, the travel rule of the user includes a travel rule degree of the user in time and a rule degree of the user in a travel destination, and the first semantic tag of the semantic representation of the user may be determined through the first and second possible embodiments, and for example, the travel rule of the user includes a travel rule degree in time, a rule degree of the user in a travel destination, a rule degree of a travel starting point to a destination, and a rule degree of a travel route, and the first semantic tag of the semantic representation of the user may be determined through the four manners. The embodiments of the present application are only examples, and other possible combinations are not described again.
The second semantic label is used for describing the travel risk degree of the user, and the second semantic label can represent that the user usually selects a more unfamiliar road or a familiar path as much as possible when facing a new destination, so as to describe the travel risk degree of the user. In one possible embodiment, determining a second semantic tag of the semantic representation of the user based on the vehicle trajectory data includes: determining the distribution of the running times of each first running road section in the first running path of the vehicle in the running path information of the vehicle track data; and determining the travel risk degree of the user by utilizing the distribution condition of the travel times of each first travel road section.
The destination of the first travel path is a new destination, where the new destination may be a location or area outside of the resident point. The user may travel through multiple first travel segments when arriving at the new destination. Through the driving path information of the vehicle track data, the driving times of each first driving road section in the first driving path of the vehicle can be determined, and then the distribution situation of the driving times of each first driving road section in the first driving path of the vehicle is determined, so that the travel risk degree of the user is determined.
In one possible implementation, the travel risk degree of the user may be represented by a driving route exploration trend, the driving route exploration trend represents the risk degree of the user on the driving route selection when a new destination appears, and the driving route exploration trend may be calculated by the following formula:
Figure BDA0002660838200000141
Figure BDA0002660838200000142
wherein E isChoiceExploring trends for driving paths, PHotRoadFor the probability that the user accesses the traveled road section when accessing the new destination, the similarity is the access frequency, Num, of each traveled road sectionAllRoadAnd W is the total number of the access driving road sections when the user accesses the new destination, and W is the number of the access driving road sections of the user to the new destination in a period of time.
In yet another possible implementation, determining a second semantic tag of the user semantic representation based on the vehicle trajectory data includes: determining a stationary point of the vehicle by using destination information in the vehicle track data; and determining the resident point change condition of the vehicle in a preset period by utilizing the resident point of the vehicle so as to determine the travel risk degree of the user.
In one possible implementation, the travel risk degree of the user can be represented by a resident point heat variation value, wherein the resident point heat variation value represents the variation situation of the user's resident point, and the resident point heat variation value can be calculated by the following formula:
Figure BDA0002660838200000143
wherein, HGspIs the heat variation value of the constant stagnation point, Delta FspHeat variation value of constant stagnation point, FspTemperature tag, U, being a stationary pointspA specificity tag, U, being a stationarity pointspThe larger the contribution of the resident point to semantic analysis of the user, the larger the U is the total number of the resident points.
In one possible embodiment, determining a second semantic tag of the semantic representation of the user based on the vehicle trajectory data includes:
determining the distribution of the running times of each first running road section in the first running path of the vehicle in the running path information of the vehicle track data; determining the travel risk degree of the user by utilizing the distribution condition of the travel times of each first travel road section; determining a stationary point of the vehicle by using destination information in the vehicle track data; and determining the resident point change condition of the vehicle in a preset period by utilizing the resident point of the vehicle so as to determine the travel risk degree of the user. For a specific implementation, reference may be made to the above contents, which are not described in detail.
In yet another possible embodiment, the travel risk degree of the user may be represented by a travel section heat variation value, wherein the travel section heat variation value represents a variation situation of a travel section frequently driven by the user. For example, the resident point of the user changes in a period of time, and the heat change value of the traveling road section of the user can be calculated by monitoring the heat, the specificity and the like of the route which the user frequently travels. In one possible embodiment, the driving section heat variation value may be calculated by the following formula:
Figure BDA0002660838200000151
wherein, HGrAs a heat change value of the road section, Δ FrIs a heat change value of a road section, FrFor the heat of the road section, UrFor distinctness of path, UrThe larger the contribution of the driving road section to the semantic analysis of the user, the larger V is the total number of the driving road sections.
Step S103: and adjusting the car insurance scheme of the vehicle by utilizing the semantic portrait of the user.
After the user semantic representation is determined, the vehicle insurance scheme of the vehicle can be adjusted according to the user semantic representation. For example, the higher the travel regularity of the user is, the smaller the travel risk degree is, and the lower the frequency of the abnormal driving behavior of the user is, the lower the possibility of the vehicle causing a traffic accident is, and the relatively lower the risk rate of the user is, the vehicle risk scheme may be adjusted by reducing the premium of the vehicle risk scheme, or increasing the deposit of the vehicle risk scheme of the user by a suitable amount. For another example, the lower the travel regularity of the user, the higher the travel risk degree, and the higher the frequency of the abnormal driving behavior of the user, the higher the possibility of a traffic accident occurring to the vehicle is, and the relatively higher the risk rate of the user, the vehicle risk scheme of the vehicle may be adjusted by increasing the premium of the vehicle risk scheme, or reducing the deposit of the vehicle risk scheme of the user by a proper amount, and the like.
In the embodiment of the application, the user semantic representation of the vehicle is established according to the first driving data of the vehicle in the preset period, besides the semantic tags describing abnormal driving behaviors of the user, the semantic tags describing travel rules and travel adventure degrees of the user are also considered in the user semantic representation, accuracy of the user semantic representation of the vehicle is improved, the vehicle insurance scheme of the vehicle is adjusted by the user semantic representation, personalized adjustment of the vehicle insurance scheme of the vehicle is achieved, and reliability of the personalized adjustment of the vehicle insurance scheme is improved.
Based on the embodiment shown in fig. 2, fig. 3 is a schematic flow chart of a vehicle insurance scheme adjustment method according to another embodiment of the present application, and as shown in fig. 3, the vehicle insurance scheme adjustment method according to the embodiment of the present application adjusts a vehicle insurance scheme of a vehicle by using a semantic representation of a user in step S103, and may further include:
step S201: and determining a first user score of the vehicle according to the first semantic tag, the second semantic tag and the third semantic tag in the semantic portrait of the user.
The first user score is used for describing a travel rule, a travel risk degree and an abnormal driving behavior of the user in a preset period. After the user semantic representation is determined, the vehicle can be scored by utilizing a first semantic label, a second semantic label, a third semantic label and the like in the semantic representation, and a first user score of the vehicle is obtained. The embodiment of the present application does not limit the specific implementation manner of determining the first user score of the vehicle according to the first semantic tag, the second semantic tag, and the third semantic tag, and in a possible implementation manner, the determining the first user score of the vehicle according to the first semantic tag, the second semantic tag, and the third semantic tag in the semantic representation of the user includes: and respectively determining first user scores corresponding to the first semantic label, the second semantic label and the third semantic label.
The method comprises the steps of calculating a first user score of each semantic label, determining the weight of each index in the semantic labels through an analytic hierarchy process, and then performing weighted calculation through the score of each index and the weight of each index after scoring is performed according to the probability of each index to obtain the first user score of each semantic label. The embodiments of the present application are merely examples, and are not limited thereto.
In another possible implementation manner, the method for adjusting a car insurance scheme provided by the embodiment of the present application determines a first user score of a vehicle according to a first semantic tag, a second semantic tag, and a third semantic tag in a semantic representation of a user, and includes: respectively determining a first score and a weight corresponding to the first semantic label, the second semantic label and the third semantic label; a first user score for the vehicle is determined using the first score and the weight.
Determining the first scores corresponding to the first semantic tag, the second semantic tag, and the third semantic tag may be implemented by determining the first user scores corresponding to the first semantic tag, the second semantic tag, and the third semantic tag provided in the above embodiments, which is not repeated in this embodiment. In addition, the weights corresponding to the first semantic tag, the second semantic tag, and the third semantic tag may be respectively determined, and finally, a weighted calculation may be performed by using the multiple first scores and the weight of each first score to obtain the first user score of the vehicle.
Step S202: and adjusting the car insurance scheme according to the first user score.
After determining the first user score for the vehicle, the vehicle insurance scheme is adjusted using the first user score. The embodiment of the application does not limit the specific implementation manner of adjusting the car insurance scheme according to the first user score. For example, the vehicle may be subjected to point reward or point deduction punishment through the first user score, wherein the point of the vehicle is positively correlated with the vehicle insurance type, the premium of the vehicle insurance, the deposit of the vehicle insurance and the like. The embodiments of the present application are only examples thereof.
In one possible embodiment, adjusting the car insurance scheme based on the first user score includes:
comparing the first user score with a second user score in a previous period of a preset period; if the first user score is greater than the second user score, the premium of the vehicle insurance scheme is reduced and/or the premium of the vehicle insurance scheme is increased.
The second user score is a user score in the last period of the preset period, and the second user score is used for describing the travel rule, the travel risk degree and the abnormal driving behavior of the user in the last period of the preset period. By comparing the first user score and the second user score, whether the user is improved or deteriorated in the travel rule, the travel risk degree and the abnormal driving behavior can be judged. If the first user score is larger than the second user score or the first user score exceeds the second user score preset score, the travel rule, the travel risk degree and the abnormal driving behavior of the user in the preset period are improved, and the vehicle risk scheme can be adjusted by reducing the premium of the vehicle risk scheme, or increasing the premium of the vehicle risk scheme, or simultaneously reducing the premium of the vehicle risk scheme and increasing the premium. The reliability of adjusting the automobile insurance can be improved, and safe driving of a user can be encouraged.
If the first user score is smaller than the second user score, the travel rule, the travel risk degree and the abnormal driving behavior of the user in the preset period are worsened, the vehicle insurance scheme can be adjusted by improving the insurance premium of the vehicle insurance scheme, or reducing the insurance premium of the vehicle insurance scheme, or simultaneously improving the insurance premium of the vehicle insurance scheme and reducing the insurance premium, the compensation cost of insurance companies is reduced, the fairness of the vehicle insurance scheme is promoted, and the guide of the user to drive normally can be effectively promoted, so that the road traffic safety is promoted.
The specific implementation manner of reducing the premium of the vehicle insurance scheme and/or increasing the premium of the vehicle insurance scheme is similar to the implementation manner of increasing the premium of the vehicle insurance scheme and/or decreasing the premium of the vehicle insurance scheme when the first user score is greater than the second user score, and the embodiment of the application takes the scheme of reducing the premium of the vehicle insurance scheme and/or increasing the premium of the vehicle insurance scheme as an example when the first user score is greater than the second user score.
In one possible embodiment, if the first user score is greater than the second user score, decreasing the premium and/or increasing the premium of the vehicle insurance scheme comprises:
determining a first preset interval in which the score of the first user exceeds the score of the second user, and a second preset interval in which the score of the second user is; determining a first adjustment amount of premium and/or a second adjustment amount of premium by using the first preset interval, the second preset interval and the first corresponding relation; the first corresponding relation is the relation between the first preset interval, the second preset interval and the first adjustment limit and/or the second adjustment limit; the premium is reduced by the first adjustment amount, and/or the premium is reduced by the second adjustment amount.
For convenience of introduction, in one possible implementation, fig. 4 is a schematic diagram of a first corresponding relationship provided by an embodiment of the present application, such as a five-row and five-column bar diagram shown in fig. 4, in which each row respectively represents a first preset interval in which a score of a first user score exceeds a score of a second user score, for example, respectively < 1%, 1% -2%, 2% -3%, 3% -4%, and 4% -5%, and each column respectively represents a second preset interval in which a score of a second user score exists, for example, respectively >90, 90-80, 80-70, 70-60, and < 60%, and in which heights corresponding to the columns are adjustment amounts or adjustment ratios. For example, if the first predetermined interval is 4% to 5%, the adjustment amount or the adjustment ratio of the premium or the deposit is the same, for example, 6%, regardless of which interval the second predetermined interval is located. For another example, if the first preset interval is 3% to 4%, if the second preset interval is greater than 90%, the adjustment amount or the adjustment ratio for the premium or the deposit is 4%, and the adjustment amount or the adjustment ratio for the premium or the deposit is 5% when the second preset interval is in other intervals, and so on, reference may be made to fig. 4 specifically, which is not described herein again in this embodiment of the present application. Fig. 4 is an example of only the higher the score of the first user is increased as the score of the second user is lower, and the bonus amount is larger.
In the embodiment of the application, the first user score of the vehicle is determined according to the first semantic tag, the second semantic tag and the third semantic tag in the semantic representation of the user, the deposit or the premium of the vehicle insurance scheme is adjusted according to the first user score, the information in the semantic representation of the user is standardized, the deposit or the premium of the vehicle insurance scheme is adjusted, and the fairness and the reliability of the vehicle insurance scheme are further improved.
The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
Fig. 5 is a schematic structural diagram of a vehicle insurance scheme adjusting apparatus provided in an embodiment of the present application, where the apparatus may be implemented in a software and/or hardware manner, for example, the apparatus may be implemented by a terminal device, as shown in fig. 5, and the vehicle insurance scheme adjusting apparatus provided in the embodiment of the present application may include: an acquisition module 61, a setup module 62 and an adjustment module 63.
The obtaining module 61 is configured to obtain first driving data of the vehicle in a preset period, where the first driving data is used for describing a driving condition of the vehicle and a driving behavior of a user.
The establishing module 62 is configured to establish a user semantic representation of the vehicle according to the first driving data, where the user semantic representation includes a first semantic tag, a second semantic tag and a third semantic tag, the first semantic tag is used to describe a travel rule of the user, the second semantic tag is used to describe a travel risk degree of the user, and the third semantic tag is used to describe an abnormal driving behavior of the user.
And the adjusting module 63 is used for adjusting the car insurance scheme of the vehicle by utilizing the semantic representation of the user.
In one possible embodiment, the first driving data includes vehicle trajectory data and vehicle driving data, and the establishing module 62 is specifically configured to:
determining a first semantic label and a second semantic label of a semantic portrait of a user according to vehicle track data; and determining a third semantic label of the semantic portrait of the user according to the vehicle driving data.
In one possible embodiment, the establishing module 62 is specifically configured to perform one or more of the following combinations:
and determining the distribution condition of interval time between adjacent trips by using the trip starting time in the vehicle track data so as to obtain the degree of the travel rule of the user in time, wherein the travel rule of the user comprises the degree of the travel rule of the user in time.
Or determining the distribution condition of the resident points of the vehicle by using the destination information in the vehicle track data to obtain the degree of regularity of the user on the trip destination, wherein the trip rule of the user comprises the degree of regularity of the user on the trip destination.
Or determining the distribution condition from the starting point to the destination of the travel route of the user by using the route starting point and the destination information in the vehicle track data so as to obtain the degree of regularity from the starting point to the destination of the travel route of the user, wherein the travel rule of the user comprises the degree of regularity from the starting point to the destination of the travel route of the user.
Or determining the distribution condition of the driving times of each driving road section of the user by using the driving path information in the vehicle track data so as to obtain the degree of regularity of the user on the travel path, wherein the travel rule of the user comprises the degree of regularity of the user on the travel path.
In a possible implementation, the establishing module 62 is specifically configured to:
determining the distribution of the running times of each first running road section in the first running path of the vehicle in the running path information of the vehicle track data; determining the travel risk degree of the user by utilizing the distribution condition of the travel times of each first travel road section; and/or determining a stationary point of the vehicle by using destination information in the vehicle track data; and determining the resident point change condition of the vehicle in a preset period by utilizing the resident point of the vehicle so as to determine the travel risk degree of the user.
The apparatus of this embodiment may perform the method embodiment shown in fig. 2, and the technical principle and technical effect are similar to those of the above embodiment, which are not described herein again.
On the basis of the embodiment shown in fig. 5, further, in another embodiment of the vehicle insurance scheme adjusting apparatus provided in the present application, the adjusting module 63 is specifically configured to:
respectively determining first user scores corresponding to the first semantic label, the second semantic label and the third semantic label; or respectively determining a first score and a weight corresponding to the first semantic label, the second semantic label and the third semantic label, and determining a first user score of the vehicle by using the first score and the weight; the first user score is used for describing a travel rule, a travel risk degree and an abnormal driving behavior of the user in a preset period; and adjusting the car insurance scheme according to the first user score.
In a possible implementation, the adjusting module 63 is specifically configured to:
comparing the first user score with a second user score in the last period of the preset period, wherein the second user score is used for describing the travel rule, the travel risk degree and the abnormal driving behavior of the user in the last period of the preset period; if the first user score is greater than the second user score, the premium of the vehicle insurance scheme is reduced and/or the premium of the vehicle insurance scheme is increased.
In a possible implementation, the adjusting module 63 is specifically configured to:
determining a first preset interval in which the score of the first user exceeds the score of the second user, and a second preset interval in which the score of the second user is; determining a first adjustment amount of premium and/or a second adjustment amount of premium by using the first preset interval, the second preset interval and the first corresponding relation; the first corresponding relation is the relation between the first preset interval, the second preset interval and the first adjustment limit and/or the second adjustment limit; the premium is reduced by the first adjustment amount and/or the premium is increased by the second adjustment amount.
The apparatus of this embodiment may perform the method embodiment shown in fig. 3, and the technical principle and technical effect are similar to those of the above embodiment, which are not described herein again.
The device embodiments provided in the present application are merely schematic, and the module division in fig. 5 is only one logic function division, and there may be another division manner in actual implementation. For example, multiple modules may be combined or may be integrated into another system. The coupling of the various modules to each other may be through interfaces that are typically electrical communication interfaces, but mechanical or other forms of interfaces are not excluded. Thus, modules described as separate components may or may not be physically separate, may be located in one place, or may be distributed in different locations on the same or different devices.
Fig. 6 is a schematic structural diagram of an electronic device provided in an embodiment of the present application, and as shown in fig. 6, the electronic device includes:
a processor 71, a memory 72, a transceiver 73 and a computer program; wherein the transceiver 73 implements data transmission with other devices, a computer program is stored in the memory 72 and configured to be executed by the processor 71, the computer program comprises instructions for executing the above-mentioned car insurance scheme adjusting method, the contents and effects thereof refer to the method embodiment.
In addition, embodiments of the present application further provide a computer-readable storage medium, in which computer-executable instructions are stored, and when at least one processor of the user equipment executes the computer-executable instructions, the user equipment performs the above-mentioned various possible methods.
Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in user equipment. Of course, the processor and the storage medium may reside as discrete components in a communication device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims (10)

1. A vehicle insurance scheme adjustment method is characterized by comprising the following steps:
acquiring first driving data of a vehicle in a preset period, wherein the first driving data is used for describing the running condition of the vehicle and the driving behavior of a user;
establishing a user semantic representation of the vehicle according to the first driving data, wherein the user semantic representation comprises a first semantic label, a second semantic label and a third semantic label, the first semantic label is used for describing a travel rule of the user, the second semantic label is used for describing a travel risk degree of the user, and the third semantic label is used for describing an abnormal driving behavior of the user;
and adjusting the vehicle insurance scheme of the vehicle by utilizing the semantic representation of the user.
2. The method of claim 1, wherein the first driving data includes vehicle trajectory data and vehicle travel data, and wherein creating the user semantic representation of the vehicle based on the first driving data comprises:
determining the first semantic tag and the second semantic tag of the user semantic representation according to the vehicle track data;
and determining the third semantic label of the user semantic representation according to the vehicle driving data.
3. The method of claim 2, wherein determining the first semantic tag of the user semantic representation based on the vehicle trajectory data comprises one or more of the following:
determining the distribution condition of interval time between adjacent trips by using the trip starting time in the vehicle trajectory data to obtain the degree of the travel rule of the user in time, wherein the travel rule of the user comprises the degree of the travel rule of the user in time;
determining the distribution condition of resident points of the vehicle by using destination information in the vehicle track data to obtain the degree of regularity of the user on the trip destination, wherein the trip rule of the user comprises the degree of regularity of the user on the trip destination;
determining the distribution condition from the starting point to the destination of the travel route of the user by using the route starting point and the destination information in the vehicle track data so as to obtain the degree of regularity from the starting point to the destination of the travel route of the user, wherein the travel rule of the user comprises the degree of regularity from the starting point to the destination of the travel route of the user;
and determining the distribution condition of the driving times of each driving road section of the user by using the driving path information in the vehicle track data so as to obtain the degree of regularity of the user on the travel path, wherein the travel rule of the user comprises the degree of regularity of the user on the travel path.
4. The method of claim 2 or 3, wherein determining the second semantic tag of the user semantic representation from the vehicle trajectory data comprises:
determining the distribution of the running times of each first running road section in the first running path of the vehicle in the running path information of the vehicle track data; determining the travel risk degree of the user by utilizing the distribution condition of the travel times of each first travel road section;
and/or the presence of a gas in the gas,
determining a stationary point of the vehicle by using destination information in the vehicle trajectory data; and determining the resident point change condition of the vehicle in the preset period by utilizing the resident point of the vehicle so as to determine the travel risk degree of the user.
5. The method according to any one of claims 1-3, wherein the utilizing the user semantic representation to adjust the vehicle insurance scheme of the vehicle comprises:
respectively determining first user scores corresponding to the first semantic label, the second semantic label and the third semantic label; or respectively determining a first score and a weight corresponding to the first semantic label, the second semantic label and the third semantic label, and determining a first user score of the vehicle by using the first score and the weight; the first user score is used for describing a travel rule, a travel risk degree and an abnormal driving behavior of the user in the preset period;
and adjusting the car insurance scheme according to the first user score.
6. The method of claim 5, wherein adjusting the car insurance scheme based on the first user score comprises:
comparing the first user score with a second user score in the last period of the preset period, wherein the second user score is used for describing a travel rule, a travel risk degree and abnormal driving behaviors of the user in the last period of the preset period;
and if the first user score is larger than the second user score, reducing the premium of the car insurance scheme and/or increasing the deposit of the car insurance scheme.
7. The method of claim 6, wherein decreasing the premium of the car insurance scheme or increasing the premium of the car insurance scheme if the first user score is greater than the second user score comprises:
determining a first preset interval in which the score of the first user score exceeds the score of the second user score and a second preset interval in which the second user score is;
determining the first adjustment amount of the premium or determining the second adjustment amount of the premium by using the first preset interval, the second preset interval and a first corresponding relationship, wherein the first corresponding relationship is the relationship between the first preset interval, the second preset interval and the first adjustment amount or the second adjustment amount;
and reducing the premium by the first adjustment amount, or increasing the premium by the second adjustment amount.
8. A vehicle insurance scheme adjustment apparatus, comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring first driving data of a vehicle in a preset period, and the first driving data is used for describing the driving condition of the vehicle and the driving behavior of a user;
the building module is used for building a user semantic representation of the vehicle according to the first driving data, wherein the user semantic representation comprises a first semantic label, a second semantic label and a third semantic label, the first semantic label is used for describing a travel rule of the user, the second semantic label is used for describing a travel adventure degree of the user, and the third semantic label is used for describing an abnormal driving behavior of the user;
and the adjusting module is used for adjusting the vehicle insurance scheme of the vehicle by utilizing the semantic representation of the user.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
CN202010904253.7A 2020-09-01 2020-09-01 Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium Pending CN112035644A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010904253.7A CN112035644A (en) 2020-09-01 2020-09-01 Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010904253.7A CN112035644A (en) 2020-09-01 2020-09-01 Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112035644A true CN112035644A (en) 2020-12-04

Family

ID=73590809

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010904253.7A Pending CN112035644A (en) 2020-09-01 2020-09-01 Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112035644A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113177660A (en) * 2021-04-28 2021-07-27 平安科技（深圳）有限公司 Driving intention prediction and processing method, device, equipment and storage medium
CN113221984A (en) * 2021-04-29 2021-08-06 平安科技（深圳）有限公司 Method, device and equipment for analyzing and predicting drunk driving behaviors of user and storage medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070282638A1 (en) * 2006-06-04 2007-12-06 Martin Surovy Route based method for determining cost of automobile insurance
US20100238009A1 (en) * 2009-01-26 2010-09-23 Bryon Cook Driver Risk Assessment System and Method Employing Automated Driver Log
US8332242B1 (en) * 2009-03-16 2012-12-11 United Services Automobile Association (Usaa) Systems and methods for real-time driving risk prediction and route recommendation
KR20140097669A (en) * 2013-01-28 2014-08-07 군산대학교산학협력단 Apparatus and method for determining insurance premium based on driving pattern recognition
US20150066543A1 (en) * 2013-09-03 2015-03-05 Interactive Driving Systems, Inc. Methods for facilitating a motor vehicle insurance exchange and devices thereof
CN105894609A (en) * 2015-11-11 2016-08-24 乐卡汽车智能科技（北京）有限公司 Data processing method and device and car insurance system
US20170109827A1 (en) * 2015-10-15 2017-04-20 International Business Machines Corporation Method and system to determine auto insurance risk
CN107066458A (en) * 2016-08-26 2017-08-18 北京车网互联科技有限公司 A kind of Spatial dimensionality user portrait analysis method based on car networking data
CN109146610A (en) * 2018-07-16 2019-01-04 众安在线财产保险股份有限公司 It is a kind of intelligently to insure recommended method, device and intelligence insurance robot device
WO2019056680A1 (en) * 2017-09-19 2019-03-28 平安科技（深圳）有限公司 Travel mode identification method and apparatus, terminal device, and storage medium
CN109636235A (en) * 2018-12-26 2019-04-16 北京汽车研究总院有限公司 The determination method and processing system of driving behavior portrait model
CN111080402A (en) * 2019-11-25 2020-04-28 泰康保险集团股份有限公司 Car insurance pushing method and device, electronic equipment and storage medium
KR102082680B1 (en) * 2019-07-26 2020-05-29 캐롯손해보험 주식회사 Automated system for estimating insurance premium based on trip information of vehicle

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070282638A1 (en) * 2006-06-04 2007-12-06 Martin Surovy Route based method for determining cost of automobile insurance
US20100238009A1 (en) * 2009-01-26 2010-09-23 Bryon Cook Driver Risk Assessment System and Method Employing Automated Driver Log
US8332242B1 (en) * 2009-03-16 2012-12-11 United Services Automobile Association (Usaa) Systems and methods for real-time driving risk prediction and route recommendation
KR20140097669A (en) * 2013-01-28 2014-08-07 군산대학교산학협력단 Apparatus and method for determining insurance premium based on driving pattern recognition
US20150066543A1 (en) * 2013-09-03 2015-03-05 Interactive Driving Systems, Inc. Methods for facilitating a motor vehicle insurance exchange and devices thereof
US20170109827A1 (en) * 2015-10-15 2017-04-20 International Business Machines Corporation Method and system to determine auto insurance risk
CN105894609A (en) * 2015-11-11 2016-08-24 乐卡汽车智能科技（北京）有限公司 Data processing method and device and car insurance system
US20170132709A1 (en) * 2015-11-11 2017-05-11 Leauto Intelligent Technology (Beijing) Co. Ltd. Data processing method, data processing device and vehicle insurance system
CN107066458A (en) * 2016-08-26 2017-08-18 北京车网互联科技有限公司 A kind of Spatial dimensionality user portrait analysis method based on car networking data
WO2019056680A1 (en) * 2017-09-19 2019-03-28 平安科技（深圳）有限公司 Travel mode identification method and apparatus, terminal device, and storage medium
CN109146610A (en) * 2018-07-16 2019-01-04 众安在线财产保险股份有限公司 It is a kind of intelligently to insure recommended method, device and intelligence insurance robot device
CN109636235A (en) * 2018-12-26 2019-04-16 北京汽车研究总院有限公司 The determination method and processing system of driving behavior portrait model
KR102082680B1 (en) * 2019-07-26 2020-05-29 캐롯손해보험 주식회사 Automated system for estimating insurance premium based on trip information of vehicle
CN111080402A (en) * 2019-11-25 2020-04-28 泰康保险集团股份有限公司 Car insurance pushing method and device, electronic equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
蒋晓雪等: "基于聚类思想对车险客户精准画像的研究", 智库时代, pages 242 - 243 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113177660A (en) * 2021-04-28 2021-07-27 平安科技（深圳）有限公司 Driving intention prediction and processing method, device, equipment and storage medium
CN113221984A (en) * 2021-04-29 2021-08-06 平安科技（深圳）有限公司 Method, device and equipment for analyzing and predicting drunk driving behaviors of user and storage medium

Similar Documents

Publication Publication Date Title
US10262530B2 (en) Determining customized safe speeds for vehicles
US10605615B2 (en) Vehicle routing and notifications based on characteristics
EP2354762B1 (en) Navigation system and method for determining parameters in a navigation system
CN111859178B (en) Method and system for recommending get-on point
CN110599353A (en) Vehicle insurance and claims rate prediction method, device, equipment and medium
CN112035644A (en) Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium
CN110132293B (en) Route recommendation method and device
CN111861618A (en) Boarding point recommendation method and system
JP2007213324A (en) Driving evaluation support system and method for calculating driving evaluation data
CN111861077A (en) Method and system for determining driving habits of users and pushing service information
CN109636235A (en) The determination method and processing system of driving behavior portrait model
CN111932341A (en) Method and system for determining car pooling order
CN110909907A (en) Method and device for predicting fuel consumption of truck and storage medium
US9898876B2 (en) Method and apparatus for vehicle usage recording
US20240089325A1 (en) Using contextual information for vehicle trip loss risk assessment scoring
Stankevich et al. Usage-based vehicle insurance: Driving style factors of accident probability and severity
CN114596709A (en) Data processing method, device, equipment and storage medium
CN111862587B (en) Travel guidance strategy generation method and device
CN116703612A (en) Automobile insurance risk level assessment method
WO2010095119A1 (en) Vehicle driving behaviour monitoring device and system and method of determining an insurance premium
US20230051243A1 (en) Systems and methods for creating driving challenges
US20230132673A1 (en) Method and system for presenting driver performance metrics on a user interface
CN112525213B (en) ETA prediction method, model training method, device and storage medium
JP7122726B1 (en) Information processing system, information processing method, and program
CN111191957B (en) UBI scoring method, UBI scoring device and readable 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