Pet insurance adjusting method and device, equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence and insurance adjustment, and relates to a pet insurance adjustment method, which comprises the steps of receiving a pet insurance purchase request initiated by a user, and extracting a pet type and a corresponding high-risk probability value from the purchase request; based on the pet type and the corresponding high-risk probability value, calculating an updated insurance amount of the purchase request by using a decision tree model, and calculating a target insurance amount of the purchase request according to the basic insurance amount and the updated insurance amount; based on the updated insurance amount corresponding to the purchase request, predicting an updated insurance premium by using a linear regression model, and calculating a target insurance premium corresponding to the purchase request according to the basic insurance premium and the updated insurance premium; and pushing the target insurance amount and the target insurance premium to the user terminal. The invention further provides a device and equipment for adjusting the car insurance pet insurance and a storage medium. In addition, the invention also relates to a block chain technology, and pet privacy information and the like can be stored in a block chain. According to the method, the pet insurance can be customized in a personalized manner, and the fairness of different pet insurance is improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and insurance adjustment, and in particular to a method for adjusting pet insurance. Background Art

[0002] In the insurance field, pet insurance is a new type of insurance. Its original intention is to provide financial protection for pet owners, including covering pet medical care and third-party liability compensation caused by pet behavior (such as injury incidents). At present, pet insurance generally adopts a fixed premium and insured amount model, that is, pet insurance for any pet uses the same premium and the same insured amount.

[0003] However, due to the different potential risks of different pets, for example, high-risk injury incidents for fierce dog breeds (such as bulldogs) and low-risk injury incidents for docile dog breeds (Bichon Frise), pets with high-risk injury incidents may have insufficient compensation, while owners of pets with low-risk injury incidents bear unnecessarily high premiums, thereby limiting the further development of the pet insurance market and its ability to meet diversified needs.

[0004] Therefore, there is an urgent need for a method to personalize pet insurance. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a pet insurance adjustment method, device, equipment and storage medium, the main purpose of which is to realize personalized customization of pet insurance and improve the fairness of pet insurance corresponding to different pets.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a method for adjusting pet insurance, which adopts the following technical solution:

[0007] Receive a pet insurance purchase request initiated by a user, and extract a pet type and a corresponding high-risk probability value from the pet insurance purchase request;

[0008] Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to calculate the updated insured amount of the pet insurance purchase request, and a target insured amount of the pet insurance purchase request is calculated based on the basic insured amount and the updated insured amount;

[0009] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and a target premium corresponding to the pet insurance purchase request is calculated based on the basic premium and the updated premium;

[0010] The target insurance amount and the target premium are pushed to the user terminal.

[0011] Furthermore, extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request includes:

[0012] Extracting pet text information from the pet insurance purchase request, performing a word segmentation operation on the pet text information to obtain a text word segmentation set;

[0013] Performing part-of-speech tagging on each word in the text word set to generate a text word set with part-of-speech tags;

[0014] Performing named entity recognition on the text segmentation set with part-of-speech tags according to a predefined specific type to obtain a specific segmentation set;

[0015] Matching each word in the specific word set with a pet breed key library to determine the pet type of the pet insurance purchase request;

[0016] The high risk probability value corresponding to the pet type is determined according to a mapping table between the pet type and a predefined high risk probability value.

[0017] Furthermore, the word segmentation operation is performed on the pet text information to obtain a text word segmentation set, including:

[0018] Performing a word segmentation operation on the pet text information by using a forward matching algorithm to obtain a first word segmentation set;

[0019] Performing a word segmentation operation on the pet text information by using a reverse matching algorithm to obtain a second word segmentation set;

[0020] The first word segmentation set and the second word segmentation set are collected to obtain a third word segmentation set, and a deduplication operation is performed on the third word segmentation set to obtain a text word segmentation set.

[0021] Furthermore, before receiving the pet insurance purchase request initiated by the user, the method further includes:

[0022] Obtain pet data from a pet injury event database, and extract injury events of each pet breed from the pet data;

[0023] Based on the injury events of each pet breed, calculating the injury probability corresponding to each pet breed;

[0024] A pet high-risk probability value mapping table is formulated according to the pet type, the pet breed corresponding to the pet type, and the injury probability corresponding to the pet breed.

[0025] Furthermore, the method of calculating the updated insured amount of the pet insurance purchase request by using a decision tree model and calculating the target insured amount of the pet insurance purchase request according to the basic insured amount and the updated insured amount includes:

[0026] Obtaining the pet age in the pet insurance purchase request, and determining whether the pet age is less than or equal to a preset pet age threshold;

[0027] When the age of the pet is less than or equal to a preset pet age threshold, obtaining a corresponding risk probability value in the pet insurance purchase request;

[0028] determining a risk adjustment value based on the pet breed in the pet insurance purchase request;

[0029] Calculating a first updated insured amount corresponding to the pet insurance purchase request using the risk probability value and the risk adjustment value;

[0030] The first target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the first updated insurance amount.

[0031] Furthermore, the method of determining whether the pet age is less than or equal to a preset pet age threshold also includes:

[0032] When the pet age is greater than the preset pet age threshold, obtaining the pet insurance purchase period and the pet age in the pet insurance purchase request;

[0033] Calculate the second updated insurance amount corresponding to the pet insurance purchase request according to the pet insurance purchase period and the pet age;

[0034] A second target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the second updated insurance amount.

[0035] Furthermore, before calculating the updated insurance amount of the pet insurance purchase request using the decision tree model, the method further includes:

[0036] Obtain the average age of each pet type, and construct a corresponding pet age threshold according to the average age of each pet type;

[0037] The age of each pet type is used as a root node, and the pet age threshold corresponding to each pet type is used as a decision node;

[0038] The result outputted that is less than or equal to the pet age threshold corresponding to each pet type is used as the first leaf node;

[0039] The output result that is greater than the pet age threshold corresponding to each pet type is used as the second leaf node;

[0040] A decision tree model corresponding to each pet type is constructed according to the root node, the decision node, the first leaf node and the second leaf node.

[0041] In order to solve the above technical problems, the embodiment of the present application further provides a pet insurance adjustment device, which adopts the following technical solution:

[0042] A receiving module, used to receive a pet insurance purchase request initiated by a user, and extract the pet type and the corresponding high-risk probability value from the pet insurance purchase request;

[0043] A calculation module, for calculating the updated insured amount of the pet insurance purchase request using a decision tree model based on the pet type and the corresponding high-risk probability value, and calculating the target insured amount of the pet insurance purchase request according to the basic insured amount and the updated insured amount; based on the updated insured amount corresponding to the pet insurance purchase request, predicting the updated premium using a linear regression model, and calculating the target premium corresponding to the pet insurance purchase request according to the basic premium and the updated premium;

[0044] A push module is used to push the target insurance amount and the target premium to the user terminal.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a device, which adopts the following technical solution:

[0046] Receive a pet insurance purchase request initiated by a user, and extract a pet type and a corresponding high-risk probability value from the pet insurance purchase request;

[0047] Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to calculate the updated insured amount of the pet insurance purchase request, and a target insured amount of the pet insurance purchase request is calculated based on the basic insured amount and the updated insured amount;

[0048] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and a target premium corresponding to the pet insurance purchase request is calculated based on the basic premium and the updated premium;

[0049] The target insurance amount and the target premium are pushed to the user terminal.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides a storage medium, which adopts the following technical solution:

[0051] Receive a pet insurance purchase request initiated by a user, and extract a pet type and a corresponding high-risk probability value from the pet insurance purchase request;

[0052] Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to calculate the updated insured amount of the pet insurance purchase request, and a target insured amount of the pet insurance purchase request is calculated based on the basic insured amount and the updated insured amount;

[0053] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and a target premium corresponding to the pet insurance purchase request is calculated based on the basic premium and the updated premium;

[0054] The target insurance amount and the target premium are pushed to the user terminal.

[0055] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0056] This application can extract the pet type and the corresponding high-risk probability value from the pet insurance purchase request, and can customize the pet insurance according to the pet type and the corresponding high-risk probability value, thereby improving the fairness of the pet insurance and avoiding the unfairness caused by the single pet insurance.

[0057] Based on the pet type and the corresponding high-risk probability value, the basic insured amount of the pet insurance purchase request is updated using a decision tree model to obtain the target insured amount corresponding to the pet insurance purchase request, thereby realizing personalized customization of the target insured amount corresponding to the pet, accurately considering the high-risk probability value of the pet, and dynamically adjusting the insured amount according to the high-risk probability value to avoid the situation where the insured amount does not correspond to the pet;

[0058] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and the target premium corresponding to the pet insurance purchase request is calculated based on the updated premium and the basic premium, thereby achieving differentiated premium pricing and personalized customization of pet insurance, and improving the fairness of purchasing different pet insurances;

[0059] The target insurance amount and target premium are pushed to the user's terminal through multiple channels, and the user is informed of the fee changes, which improves the user experience and user stickiness. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0062] Figure 2 A flowchart of an embodiment of a method for adjusting pet insurance according to the present application;

[0063] Figure 3is a structural schematic diagram of an embodiment of a pet insurance adjustment device according to the present application;

[0064] Figure 4 It is a structural schematic diagram of an embodiment of a device according to the present application. DETAILED DESCRIPTION

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0069] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0070] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0071] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0072] It should be noted that the method for obtaining vehicle insurance investigation evidence provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the device for obtaining vehicle insurance investigation evidence is generally set in the server / terminal device.

[0073] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0074] Continue to refer Figure 2 , shows a flow chart of an embodiment of a pet insurance adjustment method according to the present application. The pet insurance adjustment method comprises the following steps:

[0075] S201. Receive a pet insurance purchase request initiated by a user, and extract a pet type and a corresponding high-risk probability value from the pet insurance purchase request.

[0076] In this embodiment, the pet insurance purchase request refers to a pet insurance purchase request initiated by a user who owns a pet for his or her pet, for example, a pet insurance purchase request initiated by a user for his or her pet dog; the pet type refers to pets of different types and breeds, for example, dogs, cats, etc., and the corresponding breeds of dogs are Golden Retriever, Bichon Frise, Labrador Retriever, Bulldog, etc., and the corresponding breeds of cats are Blue Cat, Lilac Golden Cat, Garfield, etc.; the high-risk probability value refers to the probability of injury, the severity of injury, etc.

[0077] In this embodiment, a pet insurance purchase request initiated by a user is received, the type and breed of the pet is identified from the insurance purchase request, and the high-risk probability value corresponding to the pet is determined based on a pre-created pet risk mapping table and the type and breed of the pet.

[0078] In one embodiment, extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request includes:

[0079] Extracting pet text information from the pet insurance purchase request, performing a word segmentation operation on the pet text information to obtain a text word segmentation set;

[0080] Performing part-of-speech tagging on each word in the text word set to generate a text word set with part-of-speech tags;

[0081] Performing named entity recognition on the text segmentation set with part-of-speech tags according to a predefined specific type to obtain a specific segmentation set;

[0082] Matching each word in the specific word set with a pet breed key library to determine the pet type of the pet insurance purchase request;

[0083] The high risk probability value corresponding to the pet type is determined according to a mapping table between the pet type and a predefined high risk probability value.

[0084] In this embodiment, the pet text information refers to the text information that the user brings when initiating a pet insurance purchase request, such as the pet type, breed, age, etc. The specific type refers to the type of speech that needs to be identified, such as nouns, verbs, etc.; the pet breed key library refers to the types of all pets and the breeds of each pet type, for example, pet type: dog, pet breeds corresponding to dog: Golden Retriever, Bichon Frise, Labrador Retriever, Bulldog, etc.

[0085] In this embodiment, pet text information is extracted from the insurance purchase request, and the pet text information is preprocessed, including but not limited to removing repeated words and deleting punctuation marks, to obtain preprocessed pet text information; the preprocessed pet text information is segmented using a word segmentation algorithm to obtain a text word segmentation set; each word in the text word segmentation set is predicted and tagged by a pre-trained part-of-speech tagging model to obtain a text word segmentation set with part-of-speech tags; according to a predetermined specific type, entity recognition is performed on the text word segmentation set with part-of-speech tags by a named entity recognition model (NER) model to obtain a specific word segmentation set; each word in the specific word segmentation set is matched by a string matching algorithm and a pet breed key library to determine the pet type of the pet insurance purchase request; and a high risk probability value corresponding to the pet type is determined according to the pet type and a pre-defined high risk probability value mapping table.

[0086] In this embodiment, the word segmentation algorithm refers to a maximum matching algorithm, including a forward maximum matching algorithm (FMM) and a reverse maximum matching algorithm (RMM). The pre-processed pet text information is segmented by the forward maximum matching algorithm and the reverse maximum matching algorithm, respectively, to obtain a word segmentation set corresponding to the forward maximum matching algorithm and a word segmentation set corresponding to the reverse maximum matching algorithm, and the word segmentation set corresponding to the forward maximum matching algorithm and the word segmentation set corresponding to the reverse maximum matching algorithm are summarized to obtain a text word segmentation set; the pre-trained part-of-speech tagging model refers to a hidden Markov model (HMM), and the part-of-speech prediction is performed on each word in the text word segmentation set by the pre-trained Markov model to obtain the part-of-speech of each word, and each word is annotated with a specific label according to the part-of-speech of each word, for example, a verb is annotated with "v" and a noun is annotated with "n", to obtain a text word segmentation set with part-of-speech tags; the named entity recognition model (NER) model refers to an LST model. M,-CRF model; the predetermined specific type refers to the pet name; the text segmentation set with part-of-speech tags is input into the NER model, each segmentation is converted into a high-dimensional vector through the embedding layer of the NER model, an entity label is assigned to each segmentation through the LSTM layer, and a corresponding entity label sequence is assigned to each entity label through the CRF layer, and the label sequence is aligned with the text segmentation set with part-of-speech tags to obtain a text segmentation set with entity annotations, and the text segmentation set with entity annotations is screened according to the predetermined specific type to obtain a specific segmentation set; the pet breed key library refers to all pet types and the breed names corresponding to the pet types, and each segmentation of the specific segmentation set is matched through a string matching algorithm and the pet breed key library to determine the pet type of the pet insurance purchase request; the high risk probability value corresponding to the pet type is determined according to the pet type and a predefined high risk probability value mapping table.

[0087] In another embodiment, the segmentation operation is performed on the pet text information to obtain a text segmentation set, including:

[0088] Performing a word segmentation operation on the pet text information by using a forward matching algorithm to obtain a first word segmentation set;

[0089] Performing a word segmentation operation on the pet text information by using a reverse matching algorithm to obtain a second word segmentation set;

[0090] The first word segmentation set and the second word segmentation set are collected to obtain a third word segmentation set, and a deduplication operation is performed on the third word segmentation set to obtain a text word segmentation set.

[0091] In this embodiment, the pre-processed pet text information is first segmented using a forward maximum matching algorithm to determine the number of Chinese characters contained in the maximum word length, such as n, and the pet text information is scanned from left to right, each time the first n characters are intercepted as a matching segment, and the matching segment is matched with a forward dictionary. When the match is successful, the matching segment is intercepted, and the matching segment is intercepted from n+1 characters as a starting point with a length of n; when the match fails, the last character of the matching segment is removed, and the matching segment at this time is n-1 characters, and the matching segment is matched with the forward dictionary. This step is repeated until the match is successful or the last character is left, and the pet text information is traversed until the traversal is completed, and the successfully matched characters are segmented, and the characters that failed to match are taken as single characters, and the successfully matched words are collected to obtain a first segmented word set; then the pre-processed pet text information is segmented using a reverse matching algorithm to determine the number of Chinese characters contained in the maximum word length, For example, m characters are scanned from right to left in the pet text information, and the m characters after each interception are used as matching fragments. The matching fragments are matched with the reverse dictionary. When the match is successful, the matching fragment is intercepted, and the matching fragment is intercepted from m-1 characters as the starting point with a length of m; when the match fails, the first character of the matching fragment is removed. At this time, the matching fragment is m-1 characters, and the matching fragment is matched with the reverse dictionary. This step is repeated until the match is successful or the last character is left. The pet text information is traversed until the traversal is completed, and the successfully matched characters are segmented, and the characters that failed to match are taken as single characters. The successfully matched words are collected to obtain the second word segmentation set, and the first word segmentation set and the second word segmentation set are collected to obtain the third word segmentation set. The third word segmentation set is deduplicated to obtain a text word segmentation set. In addition, the text word segmentation step can also be implemented through a deep learning word segmentation model, such as a bidirectional long short-term memory network (BiLSTM-CRF).

[0092] In this embodiment, the pet text information is segmented simultaneously by using the forward maximum matching algorithm and the reverse maximum matching algorithm, and the two segmentation algorithms are complemented to avoid errors that may be caused by a single algorithm and improve the accuracy of segmentation.

[0093] In another embodiment, before receiving the pet insurance purchase request initiated by the user, the method further includes:

[0094] Obtain pet data from a pet injury event database, and extract injury events of each pet breed from the pet data;

[0095] Based on the injury events of each pet breed, calculating the injury probability corresponding to each pet breed;

[0096] A pet high-risk probability value mapping table is formulated according to the pet type, the pet breed corresponding to the pet type, and the injury probability corresponding to the pet breed.

[0097] In this embodiment, the preset database refers to a database storing pet data at home and abroad, such as an open source pet data website, etc.; the pet data refers to the type of pet, the breed corresponding to the type of pet, and the injury incidents of the breed; the pet data is obtained from the preset database, and a pet mapping table is formulated according to the type of pet, the breed corresponding to the type of pet, and the injury incidents of the breed.

[0098] For example, taking one of the pet types as an example, the pet high-risk probability value mapping table as described in Table 1 is as follows:

[0099]

[0100]

[0101] Table 1

[0102] In an implementable example A, for example, a pet insurance purchase request uploaded by a user is received, and pet text information "I want to purchase pet insurance for a bulldog" is extracted from the pet insurance purchase request, and the pet text information is deduplicated to remove the word "of", and then the pet text information is segmented using a forward maximum matching algorithm and a reverse maximum matching algorithm to obtain a text segmentation set "I", "want", "buy", "dog", "of", "bulldog", and "pet insurance"; a pre-trained part-of-speech tagging model is used, which refers to a hidden Markov model (HMM) that performs part-of-speech tagging on the text segmentation set to obtain a text segmentation set with part-of-speech tags "I", "want", "buy v", "dog n", "of", "bulldog n", and "pet insurance n", and the text segmentation set with part-of-speech tags is input into a NER model, and each segmentation in the text segmentation set with part-of-speech tags is recognized as an entity through the NER model, and each segmentation is embedded in the NER model through the embedding layer. All of them are converted into high-dimensional vectors. An entity label is assigned to each segmentation word through the LSTM layer. The corresponding entity label sequence is assigned to each entity label through the CRF layer. The label sequence is aligned with the text segmentation set with part-of-speech tags to obtain the text segmentation set with entity annotations "I, O (non-entity word)", "want, O (non-entity word)", "buy v, O (non-entity word)", "dog n, PROD (type)", "O (non-entity word)", "bulldog n, PROD (type)", "pet insurance n, PAOD (product)", and the text segmentation set with entity annotations is screened according to the type of species to obtain the specific segmentation set "dog n, PROD (type)", "bulldog n, PROD (type)"; the specific segmentation set is matched with the pet breed key library through the string algorithm to determine that the pet type is dog breed and the breed is bulldog, and then the high risk probability value of bulldog is determined to be 65.60% according to the pet high risk probability value mapping table.

[0103] In this embodiment, pet data is obtained from a preset database, and a pet high-risk probability value mapping table is formulated based on the pet data, which can improve the accuracy and efficiency of pet insurance adjustment.

[0104] In this embodiment, by extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request, pet insurance can be customized according to the pet type and the corresponding high-risk probability value, thereby improving the fairness of pet insurance and avoiding the unfairness caused by the single pet insurance.

[0105] S202. Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to calculate an updated insured amount of the pet insurance purchase request, and a target insured amount of the pet insurance purchase request is calculated based on a basic insured amount and the updated insured amount.

[0106] In this embodiment, the decision tree model is a classification and regression algorithm. Based on the species characteristics of the pet type and the high-risk probability value characteristics and age characteristics corresponding to the breed, a pre-built decision tree model is used to update the basic insured amount corresponding to the pet insurance to obtain the target insured amount corresponding to the pet insurance purchase request.

[0107] In one embodiment, before calculating the updated insurance amount of the pet insurance purchase request using a decision tree model, the method further includes:

[0108] Obtain the average age of each pet type, and construct a corresponding pet age threshold according to the average age of each pet type;

[0109] The age of each pet type is used as a root node, and the pet age threshold corresponding to each pet type is used as a decision node;

[0110] The result outputted that is less than or equal to the pet age threshold corresponding to each pet type is used as the first leaf node;

[0111] The output result that is greater than the pet age threshold corresponding to each pet type is used as the second leaf node;

[0112] A decision tree model corresponding to each pet type is constructed according to the root node, the decision node, the first leaf node and the second leaf node.

[0113] Since the lifespan, risk probability value, etc. of each type of pet are different, the judgment conditions are also different accordingly. For example, the average lifespan of a cat is generally 13-18 years, and the average lifespan of a dog is generally 10-15 years, and their judgment conditions are different. Therefore, in this embodiment, a corresponding decision tree model is constructed for each type of pet. The decision tree model includes obtaining the average age of each type of pet, calculating the pet age threshold corresponding to each type of pet according to the average age of each type of pet, taking the age corresponding to each type of pet as the root node, and taking the pet age threshold corresponding to each type of pet as the decision node to perform the first step of judgment, dividing the root node into two leaf nodes through the decision node, calculating the updated insurance amount corresponding to the pet through the two leaf nodes, calculating the target insurance amount through the updated insurance amount, and obtaining a constructed decision tree model.

[0114] In this embodiment, by constructing a corresponding decision tree model according to the pet type, the unique characteristics of the pet type can be fully taken into account, thereby improving the accuracy of the insurance amount adjustment.

[0115] In one embodiment, the method of calculating the updated insured amount of the pet insurance purchase request using a decision tree model and calculating the target insured amount of the pet insurance purchase request using the basic insured amount and the updated insured amount includes:

[0116] Obtaining the pet age in the pet insurance purchase request, and determining whether the pet age is less than or equal to a preset pet age threshold;

[0117] When the age of the pet is less than or equal to a preset pet age threshold, obtaining a corresponding risk probability value in the pet insurance purchase request;

[0118] determining a risk adjustment value based on the pet breed in the pet insurance purchase request;

[0119] Calculating a first updated insured amount corresponding to the pet insurance purchase request using the risk probability value and the risk adjustment value;

[0120] The first target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the first updated insurance amount.

[0121] In this embodiment, the preset pet age threshold is set according to the average life span of the pet. Generally, the pet age threshold is half of the average life span of the pet, which depends on the specific situation. First, the pet type, pet breed and pet age in the pet insurance purchase request are obtained, and the corresponding decision tree model is determined according to the pet type. Secondly, it is determined whether the pet age is less than or equal to the preset pet age threshold. When the pet age is less than or equal to the preset threshold, the risk probability value corresponding to the pet breed and the preset risk adjustment mapping table are obtained, and the risk adjustment value is determined according to the risk probability value and the risk adjustment mapping table. The first updated insurance amount corresponding to the pet insurance purchase request is calculated using the risk probability value and the risk adjustment value, and the first target insurance amount in the pet insurance purchase request is calculated according to the basic insurance amount and the first updated insurance amount. The preset risk adjustment mapping table is: risk probability value 0%- The risk adjustment value corresponding to 5% is -1000, the risk adjustment value corresponding to the risk probability value of 5%-10% is -750, the risk adjustment value corresponding to the risk probability value of 10%-15% is -500, the risk adjustment value corresponding to the risk probability value of 15%-20% is -200, the risk adjustment value corresponding to the risk probability value of 20%-25% is 0, the risk adjustment value corresponding to the risk probability value of 25%-30% is +100, the risk adjustment value corresponding to the risk probability value of 30%-35% is +200, the risk adjustment value corresponding to the risk probability value of 35%-40% is +300, the risk adjustment value corresponding to the risk probability value of 40%-45% is +400, the risk adjustment value corresponding to the risk probability value of 45%-50% is +500, and the risk adjustment value corresponding to the risk probability value of 50%-100% is +1000; the first updated insurance amount is the value corresponding to the risk adjustment value.

[0122] The specific values ​​mentioned above do not represent real data, but are for example purposes only. The setting of values ​​depends on the specific situation.

[0123] Continuing with the above-mentioned feasible example A, the type of the pet is obtained: dog, breed: bulldog, age: 3 years old, and the decision tree is used to determine whether the age of the bulldog is less than the preset pet age threshold of 8 years old. The judgment result is that the age of the bulldog is less than the preset pet age threshold. The pet high-risk probability value mapping table is queried to obtain a high-risk probability value corresponding to the bulldog of 65.60%. The risk adjustment mapping table is queried through the high-risk probability value to obtain a risk adjustment value of +1000, then the first updated insurance amount corresponding to the bulldog is +1000, and the first target insurance amount of the bulldog = basic insurance amount 1000 + first updated insurance amount 1000 = 11000.

[0124] In another embodiment, the determining whether the pet age is less than or equal to a preset pet age threshold, the method further comprises:

[0125] When the pet age is greater than the preset pet age threshold, obtaining the pet insurance purchase period and the pet age in the pet insurance purchase request;

[0126] Calculate the second updated insurance amount corresponding to the pet insurance purchase request according to the pet insurance purchase period and the pet age;

[0127] A second target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the second updated insurance amount.

[0128] In this embodiment, when it is determined that the pet's age is greater than the pet age threshold, the purchase years and claim records of the pet insurance are obtained from the pet insurance purchase request, and the corresponding second updated insurance amount in the pet insurance purchase request is calculated by the annual incremental coefficient and the pet insurance purchase years. The second target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the second updated insurance amount.

[0129] In another embodiment, the calculation of the second updated insured amount corresponding to the pet insurance purchase request according to the pet insurance purchase years and the insurance claim record comprises the formula:

[0130] X=BB*【1+R A *(AT)+R Y *Y】

[0131] Wherein, X refers to the second updated insured amount, B refers to the basic insured amount, and R A refers to the age increment coefficient, A refers to the pet's age, T refers to the preset pet age threshold, R Y Refers to the annual increment coefficient, Y is the number of years that pet insurance is purchased; and R Y The specific settings may depend on the situation.

[0132] In another embodiment, the first target insured amount = the basic insured amount + the first updated insured amount; the second target insured amount = the basic insured amount + the second updated insured amount. It is worth noting that the first updated insured amount can be a positive number or a negative number.

[0133] In this embodiment, based on the pet type and the corresponding high-risk probability value, a decision tree model is used to update the basic insured amount of the pet insurance purchase request to obtain the target insured amount corresponding to the pet insurance purchase request, thereby realizing personalized customization of the target insured amount corresponding to the pet, accurately considering the high-risk probability value of the pet, and dynamically adjusting the insured amount according to the high-risk probability value to avoid the situation where the insured amount does not correspond to the pet.

[0134] S203: Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict an updated premium, and a target premium corresponding to the pet insurance purchase request is calculated based on a basic premium and the updated premium.

[0135] In this embodiment, the renewal premium refers to the premium adjusted according to the new risk assessment results when the insurance is renewed; based on the renewal amount of insurance corresponding to the pet insurance purchase request and the pet insurance purchase years and the insurance loss amount, the renewal premium is calculated by a linear regression algorithm, and the target premium corresponding to the pet insurance purchase request is calculated based on the renewal premium and the basic premium. It is worth mentioning that the pet insurance purchase years and insurance loss amount referred to above are some of the features referred to in the present invention, which are used as examples without limitation. In actual applications, other features can be added for the calculation of the linear regression model to obtain the renewal premium.

[0136] In this embodiment, a linear regression model for predicting renewal premiums is pre-built to obtain a large number of training data sets. Taking the above two features as an example, the training data set includes renewal premiums, intercept terms, renewal sum insured, years of pet insurance purchase, and insured amount. The linear regression formula is:

[0137] Renewal premium = β0 + β1 * renewal sum insured + β2 * number of years of pet insurance purchase + β3 * amount of insurance loss + ε;

[0138] Among them, β0 refers to the intercept term, β1 refers to the regression coefficient corresponding to the updated insurance amount, β2 refers to the regression coefficient corresponding to the number of years of pet insurance purchase, β3 refers to the regression coefficient corresponding to the insurance amount, and ε refers to the error term.

[0139] Through the above formula, the optimal solutions of the regression coefficient β1 corresponding to the updated insured amount, the regression coefficient β2 corresponding to the years of pet insurance purchase, and the regression coefficient β3 corresponding to the insurance amount are obtained to obtain the trained linear regression model.

[0140] In practical applications, the formula of the linear regression model is:

[0141] Renewal premium = β0+β1*Feature1+β2*Feature2+β3*Feature3+…+β n * characteristic n+ε;

[0142] The updated premium is calculated based on the optimal solution of the pre-defined features and the regression coefficients corresponding to the features.

[0143] In this embodiment, the renewal premium is calculated by a trained linear regression model, and the sum of the renewal premium and the basic premium is obtained to obtain the target premium corresponding to the pet insurance purchase request.

[0144] In this embodiment, based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and the target premium corresponding to the pet insurance purchase request is calculated based on the updated premium and the basic premium, thereby achieving differentiated premium pricing and personalized customization of pet insurance, and improving the fairness of purchasing different pet insurance policies.

[0145] S204: Push the target insurance amount and the target premium to the user terminal.

[0146] In this embodiment, after the target insured amount and the target premium are calculated, they are pushed to the user via a preset method (such as SMS push method, APP push method, email push method, etc.), and the user is informed of the cost change description (such as the reason for the change, the change item).

[0147] In this embodiment, the target insurance amount and target premium are pushed to the user's terminal through multiple channels, and the user is informed of the fee changes, thereby improving the user experience and user stickiness.

[0148] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned pet insurance information and user information, the above-mentioned pet insurance information and user information can also be stored in a node of a blockchain.

[0149] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0150] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0151] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0152] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0153] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0154] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a pet insurance adjustment device, which is similar to Figure 2 Corresponding to the method embodiment shown, the apparatus can be specifically applied to various computer devices.

[0155] like Figure 3 As shown, the pet insurance adjustment device 300 described in this embodiment includes: a receiving module 301, a calculation module 302, and a push module 303. Among them:

[0156] The receiving module 301 is used to receive a pet insurance purchase request initiated by a user, and extract the pet type and the corresponding high-risk probability value from the pet insurance purchase request;

[0157] The calculation module 302 is used to calculate the updated insurance amount of the pet insurance purchase request using a decision tree model based on the pet type and the corresponding high-risk probability value, and calculate the target insurance amount of the pet insurance purchase request according to the basic insurance amount and the updated insurance amount; based on the updated insurance amount corresponding to the pet insurance purchase request, use a linear regression model to predict the updated premium, and calculate the target premium corresponding to the pet insurance purchase request according to the basic premium and the updated premium;

[0158] The push module 303 is used to push the target insurance amount and the target premium to the user terminal.

[0159] In this embodiment, the present application can personalize pet insurance according to the pet type and the corresponding high-risk probability value by extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request, thereby improving the fairness of pet insurance and avoiding the unfairness caused by the single pet insurance.

[0160] Based on the pet type and the corresponding high-risk probability value, the basic insured amount of the pet insurance purchase request is updated using a decision tree model to obtain the target insured amount corresponding to the pet insurance purchase request, thereby realizing personalized customization of the target insured amount corresponding to the pet, accurately considering the high-risk probability value of the pet, and dynamically adjusting the insured amount according to the high-risk probability value to avoid the situation where the insured amount does not correspond to the pet;

[0161] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and the target premium corresponding to the pet insurance purchase request is calculated based on the updated premium and the basic premium, thereby achieving differentiated premium pricing and personalized customization of pet insurance, and improving the fairness of purchasing different pet insurances;

[0162] The target insurance amount and target premium are pushed to the user's terminal through multiple channels, and the user is informed of the fee changes, which improves the user experience and user stickiness.

[0163] In order to solve the above technical problems, the present application embodiment also provides a device (computer device). Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0164] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0165] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0166] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the adjustment method of pet insurance, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0167] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the pet insurance adjustment method.

[0168] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0169] During the implementation of the electronic device of the present application, by extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request, the pet insurance can be customized according to the pet type and the corresponding high-risk probability value, thereby improving the fairness of the pet insurance and avoiding the unfairness caused by the single pet insurance.

[0170] Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to update the basic insured amount of the pet insurance purchase request to obtain the target insured amount corresponding to the pet insurance purchase request, thereby achieving personalized customization of the target insured amount corresponding to the pet, accurately considering the high-risk probability value of the pet, and dynamically adjusting the insured amount according to the high-risk probability value to avoid the situation where the insured amount does not correspond to the pet.

[0171] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and the target premium corresponding to the pet insurance purchase request is calculated based on the updated premium and the basic premium, thereby achieving differentiated premium pricing and personalized customization of pet insurance, and improving the fairness of purchasing different pet insurance policies.

[0172] The target insurance amount and target premium are pushed to the user's terminal through multiple channels, and the user is informed of the fee changes, which improves the user experience and user stickiness.

[0173] The present application also provides another embodiment, namely, providing a storage medium (computer-readable storage medium), wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the pet insurance adjustment method as described above.

[0174] During the implementation process of the computer-readable storage medium of the present application, by extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request, the pet insurance can be customized according to the pet type and the corresponding high-risk probability value, thereby improving the fairness of the pet insurance and avoiding the unfairness caused by the single pet insurance.

[0175] Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to update the basic insured amount of the pet insurance purchase request to obtain the target insured amount corresponding to the pet insurance purchase request, thereby achieving personalized customization of the target insured amount corresponding to the pet, accurately considering the high-risk probability value of the pet, and dynamically adjusting the insured amount according to the high-risk probability value to avoid the situation where the insured amount does not correspond to the pet.

[0176] Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and the target premium corresponding to the pet insurance purchase request is calculated based on the updated premium and the basic premium, thereby achieving differentiated premium pricing and personalized customization of pet insurance, and improving the fairness of purchasing different pet insurance policies.

[0177] The target insurance amount and target premium are pushed to the user's terminal through multiple channels, and the user is informed of the fee changes, which improves the user experience and user stickiness.

[0178] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0179] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0180] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for adjusting pet insurance, characterized in that: The steps include: Receive a pet insurance purchase request initiated by a user, and extract a pet type and a corresponding high-risk probability value from the pet insurance purchase request; Based on the pet type and the corresponding high-risk probability value, a decision tree model is used to calculate the updated insured amount of the pet insurance purchase request, and a target insured amount of the pet insurance purchase request is calculated based on the basic insured amount and the updated insured amount; Based on the updated insured amount corresponding to the pet insurance purchase request, a linear regression model is used to predict the updated premium, and a target premium corresponding to the pet insurance purchase request is calculated based on the basic premium and the updated premium; The target insurance amount and the target premium are pushed to the user terminal.

2. The pet insurance adjustment method according to claim 1, characterized in that: The step of extracting the pet type and the corresponding high-risk probability value from the pet insurance purchase request includes: Extracting pet text information from the pet insurance purchase request, performing a word segmentation operation on the pet text information to obtain a text word segmentation set; Performing part-of-speech tagging on each word in the text word set to generate a text word set with part-of-speech tags; Performing named entity recognition on the text segmentation set with part-of-speech tags according to a predefined specific type to obtain a specific segmentation set; Matching each word in the specific word set with a pet breed key library to determine the pet type of the pet insurance purchase request; The high risk probability value corresponding to the pet type is determined according to a mapping table between the pet type and a predefined high risk probability value.

3. The pet insurance adjustment method according to claim 2, characterized in that: The word segmentation operation is performed on the pet text information to obtain a text word segmentation set, including: Performing a word segmentation operation on the pet text information by using a forward matching algorithm to obtain a first word segmentation set; Performing a word segmentation operation on the pet text information by using a reverse matching algorithm to obtain a second word segmentation set; The first word segmentation set and the second word segmentation set are collected to obtain a third word segmentation set, and a deduplication operation is performed on the third word segmentation set to obtain a text word segmentation set.

4. The pet insurance adjustment method according to claim 1, characterized in that: Before receiving the pet insurance purchase request initiated by the user, the method further includes: Acquire pet data from a pet injury event database, and extract injury events of each pet breed from the pet data; Based on the injury events of each pet breed, calculating the injury probability corresponding to each pet breed; A pet high-risk probability value mapping table is formulated according to the pet type, the pet breed corresponding to the pet type, and the injury probability corresponding to the pet breed.

5. The pet insurance adjustment method according to claim 1, characterized in that: The method of calculating the updated insured amount of the pet insurance purchase request by using a decision tree model, and calculating the target insured amount of the pet insurance purchase request according to the basic insured amount and the updated insured amount, includes: Obtaining the pet age in the pet insurance purchase request, and determining whether the pet age is less than or equal to a preset pet age threshold; When the age of the pet is less than or equal to a preset pet age threshold, obtaining a corresponding risk probability value in the pet insurance purchase request; determining a risk adjustment value based on the pet breed in the pet insurance purchase request; Calculating a first updated insured amount corresponding to the pet insurance purchase request using the risk probability value and the risk adjustment value; The first target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the first updated insurance amount.

6. The pet insurance adjustment method according to claim 5, characterized in that: The method of determining whether the pet age is less than or equal to a preset pet age threshold further includes: When the pet age is greater than the preset pet age threshold, obtaining the pet insurance purchase period and the pet age in the pet insurance purchase request; Calculate the second updated insurance amount corresponding to the pet insurance purchase request according to the pet insurance purchase period and the pet age; A second target insurance amount in the pet insurance purchase request is calculated based on the basic insurance amount and the second updated insurance amount.

7. The pet insurance adjustment method according to claim 5, characterized in that: Before calculating the updated insurance amount of the pet insurance purchase request using the decision tree model, the method further includes: Obtain the average age of each pet type, and construct a corresponding pet age threshold according to the average age of each pet type; The age of each pet type is used as a root node, and the pet age threshold corresponding to each pet type is used as a decision node; The result outputted that is less than or equal to the pet age threshold corresponding to each pet type is used as the first leaf node; The output result that is greater than the pet age threshold corresponding to each pet type is used as the second leaf node; A decision tree model corresponding to each pet type is constructed according to the root node, the decision node, the first leaf node and the second leaf node.

8. A pet insurance adjustment device, characterized in that: The device comprises: A receiving module, used to receive a pet insurance purchase request initiated by a user, and extract the pet type and the corresponding high-risk probability value from the pet insurance purchase request; A calculation module, for calculating the updated insured amount of the pet insurance purchase request using a decision tree model based on the pet type and the corresponding high-risk probability value, and calculating the target insured amount of the pet insurance purchase request according to the basic insured amount and the updated insured amount; based on the updated insured amount corresponding to the pet insurance purchase request, predicting the updated premium using a linear regression model, and calculating the target premium corresponding to the pet insurance purchase request according to the basic premium and the updated premium; The push module is used to push the target insurance amount and the target premium to the user terminal.

9. A computer device, characterized in that: The computer device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the pet insurance adjustment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the pet insurance adjustment method according to any one of claims 1 to 7 is implemented.

Images