1. An insurance recommendation method, the method comprising:

acquiring historical user characteristic information and historical purchase insurance information of a historical user, wherein the historical user characteristic information comprises historical characteristic types and historical characteristic quantitative evaluation data;

grouping the historical user characteristic information according to the historical purchase insurance information to obtain a plurality of historical user groups, and converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data;

acquiring new user characteristic information of a new user, wherein the new user characteristic information comprises a new characteristic type and new characteristic quantitative evaluation data, and converting the new user characteristic information into a new coordinate information group according to the new characteristic type and the new characteristic quantitative evaluation data;

determining an intra-group average distance and an extra-group minimum average distance, and determining a multiplexing coefficient, wherein the determining mode of the intra-group average distance comprises the steps of setting the newly added coordinate information group in one historical user group, and determining the intra-group average distance between the newly added coordinate information group and each historical coordinate information group in the historical user group, and the determining mode of the extra-group minimum average distance comprises the step of taking the minimum value in the average distances between the newly added coordinate information group and each historical coordinate information group in other historical user groups as the extra-group minimum average distance;

and respectively acquiring a plurality of multiplexing coefficients determined by arranging the newly-added coordinate information groups in the historical user groups, and recommending insurance according to the multiplexing coefficients.

2. The insurance recommendation method of claim 1, wherein the determination of the multiplexing coefficient comprises:

wherein, F (n) is a multiplexing coefficient, Gn is a historical user group where the newly added coordinate information group is located currently, Zn is the newly added coordinate information group, d (n) is an intra-group average distance, Mind (n) is an extra-group minimum average distance, and k is the number of the historical user groups.

3. The insurance recommendation method of claim 1, wherein said making insurance recommendations according to said multiplexing factor comprises:

and if at least one multiplexing coefficient is larger than a preset multiplexing coefficient threshold value, recommending the historical purchase insurance information of the historical user group corresponding to the maximum value in the multiplexing coefficients to the newly added user.

4. The insurance recommendation method of claim 1, wherein said making insurance recommendations according to said multiplexing factor comprises:

and if the multiplexing coefficients are not more than the preset multiplexing coefficient threshold, obtaining historical purchase insurance information of a corresponding historical user group when the multiplexing coefficients are maximum, adjusting the historical purchase insurance information according to the new user characteristic information, and recommending the adjusted historical purchase insurance information to the new user.

5. The insurance recommendation method of claim 4, wherein said adjusting said historical purchase insurance information based on said added user characteristic information comprises:

according to the historical characteristic types, respectively acquiring difference information between historical characteristic quantitative evaluation data of historical users in a historical user group corresponding to the maximum multiplexing coefficient and newly added characteristic quantitative evaluation data of the newly added users;

and adjusting the historical purchase insurance information according to the difference information.

6. The insurance recommendation method of claim 4, wherein said adjusting said historical purchase insurance information based on said added user characteristic information comprises:

taking the difference between the quantitative evaluation data of each historical characteristic in the historical user group corresponding to the maximum multiplexing coefficient and the quantitative evaluation of the newly added characteristic of the newly added user;

acquiring a preset category difference threshold corresponding to each historical feature category, and if a difference quantity is larger than the corresponding preset category difference threshold, taking the historical feature category corresponding to the preset category difference threshold as a difference historical feature category;

and acquiring the corresponding relation between the historical purchase insurance information and the historical characteristic types, screening out the historical purchase sub-information corresponding to the different historical characteristic types from the historical purchase insurance information, and recommending the screened out historical purchase insurance information to the new user.

7. The insurance recommendation method of claim 5, wherein said adjusting the historical purchase insurance information according to the difference information comprises:

acquiring a target characteristic type and a type influence factor of a historical characteristic type, wherein the target characteristic type comprises the historical characteristic type corresponding to the difference information;

if the category influence factor corresponding to each target characteristic category is smaller than a preset influence factor threshold value, keeping the historical insurance purchasing information;

and if the type influence factor corresponding to one target characteristic type is larger than a preset influence factor threshold value, adjusting historical purchase sub-information corresponding to the target characteristic type in the historical purchase insurance information.

8. An insurance recommendation system, the system comprising:

the history acquisition module is used for acquiring historical user characteristic information and historical purchase insurance information of a historical user, wherein the historical user characteristic information comprises historical characteristic types and historical characteristic quantitative evaluation data;

the grouping module is used for grouping the historical user characteristic information according to the historical purchase insurance information to obtain a plurality of historical user groups, and converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data;

the newly-added obtaining module is used for obtaining the feature information of a newly-added user of the newly-added user, wherein the feature information of the newly-added user comprises a newly-added feature type and newly-added feature quantitative evaluation data, and the feature information of the newly-added user is converted into a newly-added coordinate information group according to the newly-added feature type and the newly-added feature quantitative evaluation data;

a determining module, configured to determine an average distance in a group and a minimum average distance outside the group, and determine a multiplexing coefficient, where a determination manner of determining the average distance in the group includes setting the newly added coordinate information group in one historical user group, and determining an average distance in the group between the newly added coordinate information group and each historical coordinate information group in the historical user group where the newly added coordinate information group is located, and a determination manner of the minimum average distance outside the group includes taking a minimum value of average distances between the newly added coordinate information group and each historical coordinate information group in other historical user groups as a minimum average distance outside the group;

and the recommending module is used for respectively acquiring a plurality of multiplexing coefficients determined by arranging the newly-added coordinate information groups in the historical user groups and recommending insurance according to the multiplexing coefficients.

9. An electronic device comprising a processor, a memory, and a communication bus;

the communication bus is used for connecting the processor and the memory;

the processor is configured to execute a computer program stored in the memory to implement the method of any one of claims 1-7.

10. A computer-readable storage medium, having stored thereon a computer program for causing a computer to perform the method of any one of claims 1-7.

Background

In recent years, people's insurance awareness is gradually improved, corresponding insurance products are more and more diversified, and in a large number of insurance products, how to provide more accurate and more comfortable insurance products for consumers becomes a difficult problem facing many insurance industries.

At present, recommendation of insurance products is usually based on targeted recommendation of insurance practitioners after deeply knowing user requirements, requirements on service levels of the insurance products are high, case analysis is performed on each client, working efficiency of the insurance products can be affected, and waste of time, energy and resources can be caused.

Disclosure of Invention

In view of the above disadvantages of the prior art, the present invention provides an insurance recommendation method, system, device and medium, so as to solve the problem in the related art that recommendation for insurance products requires manual product recommendation, which affects work efficiency and causes waste of time, energy and resources.

The invention provides an insurance recommendation method, which comprises the following steps:

acquiring historical user characteristic information and historical purchase insurance information of a historical user, wherein the historical user characteristic information comprises historical characteristic types and historical characteristic quantitative evaluation data;

grouping the historical user characteristic information according to the historical purchase insurance information to obtain a plurality of historical user groups, and converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data;

acquiring new user characteristic information of a new user, wherein the new user characteristic information comprises a new characteristic type and new characteristic quantitative evaluation data, and converting the new user characteristic information into a new coordinate information group according to the new characteristic type and the new characteristic quantitative evaluation data;

determining an intra-group average distance and an extra-group minimum average distance, and determining a multiplexing coefficient, wherein the determining mode of the intra-group average distance comprises the steps of setting the newly added coordinate information group in one historical user group, and determining the intra-group average distance between the newly added coordinate information group and each historical coordinate information group in the historical user group, and the determining mode of the extra-group minimum average distance comprises the step of taking the minimum value in the average distances between the newly added coordinate information group and each historical coordinate information group in other historical user groups as the extra-group minimum average distance;

and respectively acquiring a plurality of multiplexing coefficients determined by arranging the newly-added coordinate information groups in the historical user groups, and recommending insurance according to the multiplexing coefficients.

Optionally, the determining manner of the multiplexing coefficient includes:

wherein, F (n) is a multiplexing coefficient, Gn is a historical user group where the newly added coordinate information group is located currently, Zn is the newly added coordinate information group, d (n) is an intra-group average distance, Mind (n) is an extra-group minimum average distance, and k is the number of the historical user groups.

Optionally, the recommending insurance according to the multiplexing coefficient includes:

and if at least one multiplexing coefficient is larger than a preset multiplexing coefficient threshold value, recommending the historical purchase insurance information of the historical user group corresponding to the maximum value in the multiplexing coefficients to the newly added user.

Optionally, the recommending insurance according to the multiplexing coefficient includes:

and if the multiplexing coefficients are not more than the preset multiplexing coefficient threshold, obtaining historical purchase insurance information of a corresponding historical user group when the multiplexing coefficients are maximum, adjusting the historical purchase insurance information according to the new user characteristic information, and recommending the adjusted historical purchase insurance information to the new user.

Optionally, the adjusting the historical insurance purchase information according to the new user feature information includes:

according to the historical characteristic types, respectively acquiring difference information between historical characteristic quantitative evaluation data of historical users in a historical user group corresponding to the maximum multiplexing coefficient and newly added characteristic quantitative evaluation data of the newly added users;

and adjusting the historical purchase insurance information according to the difference information.

Optionally, the adjusting the historical insurance purchase information according to the new user feature information includes:

taking the difference between the quantitative evaluation data of each historical characteristic in the historical user group corresponding to the maximum multiplexing coefficient and the quantitative evaluation of the newly added characteristic of the newly added user;

acquiring a preset category difference threshold corresponding to each historical feature category, and if a difference quantity is larger than the corresponding preset category difference threshold, taking the historical feature category corresponding to the preset category difference threshold as a difference historical feature category;

and acquiring the corresponding relation between the historical purchase insurance information and the historical characteristic types, screening out the historical purchase sub-information corresponding to the different historical characteristic types from the historical purchase insurance information, and recommending the screened out historical purchase insurance information to the new user.

Optionally, the adjusting the historical purchase insurance information according to the difference information includes:

acquiring a target characteristic type and a type influence factor of a historical characteristic type, wherein the target characteristic type comprises the historical characteristic type corresponding to the difference information;

if the category influence factor corresponding to each target characteristic category is smaller than a preset influence factor threshold value, keeping the historical insurance purchasing information;

and if the type influence factor corresponding to one target characteristic type is larger than a preset influence factor threshold value, adjusting historical purchase sub-information corresponding to the target characteristic type in the historical purchase insurance information.

The invention also provides an insurance recommendation system, which comprises:

the history acquisition module is used for acquiring historical user characteristic information and historical purchase insurance information of a historical user, wherein the historical user characteristic information comprises historical characteristic types and historical characteristic quantitative evaluation data;

the grouping module is used for grouping the historical user characteristic information according to the historical purchase insurance information to obtain a plurality of historical user groups, and converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data;

the newly-added obtaining module is used for obtaining the feature information of a newly-added user of the newly-added user, wherein the feature information of the newly-added user comprises a newly-added feature type and newly-added feature quantitative evaluation data, and the feature information of the newly-added user is converted into a newly-added coordinate information group according to the newly-added feature type and the newly-added feature quantitative evaluation data;

a determining module, configured to determine an average distance in a group and a minimum average distance outside the group, and determine a multiplexing coefficient, where a determination manner of determining the average distance in the group includes setting the newly added coordinate information group in one historical user group, and determining an average distance in the group between the newly added coordinate information group and each historical coordinate information group in the historical user group where the newly added coordinate information group is located, and a determination manner of the minimum average distance outside the group includes taking a minimum value of average distances between the newly added coordinate information group and each historical coordinate information group in other historical user groups as a minimum average distance outside the group;

and the recommending module is used for respectively acquiring a plurality of multiplexing coefficients determined by arranging the newly-added coordinate information groups in the historical user groups and recommending insurance according to the multiplexing coefficients.

The invention also provides an electronic device, which comprises a processor, a memory and a communication bus;

the communication bus is used for connecting the processor and the memory;

the processor is configured to execute the computer program stored in the memory to implement the method according to any of the embodiments described above.

The invention also provides a computer-readable storage medium having stored thereon a computer program for causing a computer to perform the method according to any one of the embodiments described above.

The invention has the beneficial effects that: the invention relates to an insurance recommending method, a system, equipment and a medium, which obtains historical user characteristic information and historical insurance purchasing information, groups the historical user characteristic information to obtain a plurality of historical user groups, converts data in each historical user group into a historical coordinate information group, obtains newly added user characteristic information, converts the newly added user characteristic information into a newly added coordinate information group, obtains a plurality of multiplexing coefficients by determining the average distance in the group and the minimum average distance outside the group obtained by placing the newly added coordinate information group in different historical user groups, and further carries out insurance recommendation, can solve the problem that the recommendation of insurance products in the related technology needs to depend on manual work to carry out product recommendation, influences the working efficiency, causes the waste of time and other resources, achieves the purposes of improving the working efficiency, reducing the waste of time and other resources, meanwhile, the objectivity of insurance recommendation can be improved, and the customer satisfaction degree is improved.

Drawings

Fig. 1 is a flowchart illustrating an insurance recommendation method according to an embodiment of the present invention.

Fig. 2 is a schematic structural diagram of an insurance recommendation system according to an embodiment of the present invention.

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the invention.

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present invention, however, it will be apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details, and in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present invention.

Example one

Referring to fig. 1, the present embodiment provides an insurance recommendation method, including:

s101: and acquiring historical user characteristic information and historical purchase insurance information of the historical user.

The historical user characteristic information comprises historical characteristic types and historical characteristic quantitative evaluation data.

The historical characteristic category includes but is not limited to at least one of physical health condition (such as chronic disease, family genetic disease history, etc.), family or individual income condition, family member condition, family or individual bought insurance condition, work information, age, sex, vehicle and vehicle service life, hobbies, etc.

The historical feature quantitative evaluation data includes, but is not limited to, quantitative representation of data of each historical feature type, which may be a data vector or a weighted average, an assignment, a classification, etc. of the data of each historical feature type, as known to those skilled in the art.

The historical user characteristic information and the historical purchase insurance information of the historical user can be obtained by a method known by those skilled in the art, and are not limited herein.

The historical insurance purchase information comprises a plurality of purchased insurance products purchased by the historical user before, and at least one of the selling price, insurance content, disclaimer clause, insurance application requirement, claim condition and the like of the insurance products sold.

S102: and grouping the historical user characteristic information according to the historical purchase insurance information to obtain a plurality of historical user groups, and converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data.

The method for converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data includes but is not limited to constructing a multi-dimensional coordinate system according to each historical characteristic type, and forming position points of each historical user in the multi-dimensional coordinate system by taking the historical characteristic quantitative evaluation data as data points.

The manner in which the historical user characteristic information is grouped according to the historical purchase insurance information includes, but is not limited to, any of the following:

s1021, dividing the historical user characteristic information corresponding to the historical users with the same historical insurance purchasing information into the same historical user group;

and S1022, extracting purchased insurance products in the historical insurance purchase information, and dividing the historical user characteristic information corresponding to the historical users with the same purchased insurance products into the same historical user group.

For example, for a plurality of insurance products such as car insurance, life insurance, accident insurance, property insurance and the like purchased by a certain historical user, the historical users completely identical to the purchased insurance products can be divided into the same historical user group, and the characteristic information of the historical users can be further grouped according to the corresponding historical users. Therefore, the product actually purchased and selected by the customer with the similar physical state of the family property can be directly recommended, the selection time of the customer is saved, and the transaction rate and the customer satisfaction are improved for the more suitable customer.

For another example, for a historical user F who purchased a plurality of insurance products such as car insurance, life insurance, accident insurance, property insurance A, and property insurance B, the historical user who purchased property insurance A can be divided into the same historical user group U₁Further, the historical user characteristic information is grouped according to the corresponding historical users, and the historical users who purchased the property risk B are divided into the same historical user group U₂And further grouping the historical user characteristic information according to the corresponding historical users. At this time, the historical user characteristic information corresponding to the historical user F may be divided into a plurality of historical user groups, and the historical user groups are divided by adopting the method, so that even if the newly added user characteristic information of the newly added user is special in certain types of data, one or more optional user historical groups can be matched, further insurance recommendation can be carried out on the newly added user, and more appropriate insurance products can be recommended to the newly added user to a certain extent.

S103: and acquiring the feature information of the newly added user, and converting the feature information of the newly added user into a newly added coordinate information set according to the newly added feature type and the newly added feature quantitative evaluation data.

The new user feature information comprises new feature types and new feature quantitative evaluation data.

The manner of converting the newly added user feature information into the newly added coordinate information group according to the newly added feature type and the newly added feature quantitative evaluation data is similar to the formation manner of the historical coordinate information group, and is not repeated here.

The method for acquiring the feature information of the new user can be implemented in a manner known by those skilled in the art, and will not be described herein again.

The new user feature types may be the same as the historical user feature types or may be less than the historical user feature types. Newly added user feature types which are not included in the historical user feature types can be temporarily removed in advance, so that subsequent insurance recommendation is facilitated, and the calculation amount and the calculation power waste are reduced. And when the insurance recommendation is finally formed, making a corresponding recommended insurance product according to the newly added user characteristic types which are not included in the historical user characteristic types, and performing supplementary recommendation.

S104: the intra-group average distance and the out-of-group minimum average distance are determined, and the multiplexing coefficient is determined.

Wherein, the determination mode for determining the average distance in the group comprises the following steps:

and setting the newly added coordinate information group in a historical user group, and determining the intra-group average distance between the newly added coordinate information group and each historical coordinate information group in the historical user group.

The method for determining the minimum average distance outside the group comprises the following steps:

and taking the minimum value in the average distances between the newly added coordinate information group and each historical coordinate information group in other historical user groups as the minimum average distance outside the group.

The average distance in each group can be obtained by respectively determining the distance between the historical coordinate information group and the newly added coordinate information group in each group and then determining the average value of each distance.

The distance determination method in this embodiment may be implemented in a manner known to those skilled in the art, and is not limited herein. For example, by determining the euclidean distance between the new set of coordinate information and the historical set of coordinate information, etc.

Taking the total number of N historical user groups as an example, when the newly added coordinate information group is set in the Nth group, one implementation of the average distance outside the group may be to obtain the distance between the newly added coordinate information group and the historical coordinate information group in the 1 st group of user historical groups, and obtain the average distance q₁Calculating the distance between the newly added coordinate information group and the historical coordinate information group in the historical group of the 2 nd group of users, and calculating the average distance q₂… … calculating the distance between the newly added coordinate information group and the historical coordinate information group in the N-1 th group of user history groups, and calculating the average distance q_N-1Then take q again₁ ，q₂……q_N-1The minimum value of (3) is taken as the minimum average distance outside the group.

In some embodiments, the determining of the multiplexing coefficient includes:

formula (1)

Formula (2)

Formula (3)

Wherein, F (n) is a multiplexing coefficient, Gn is a historical user group where the newly added coordinate information group is located currently, Zn is the newly added coordinate information group, d (n) is an intra-group average distance, Mind (n) is an extra-group minimum average distance, and k is the number of the historical user groups.

Optionally, the value of the multiplexing coefficient should theoretically belong to the interval of [ 1,1 ], and if the multiplexing coefficient f (n) =1 is preferred, it may be considered that the historical insurance purchasing information corresponding to the current historical user group is the most suitable for the newly added object, that is, the historical insurance purchasing information recommended for the newly added object.

S105: and respectively acquiring a plurality of multiplexing coefficients determined by arranging the newly-added coordinate information groups in the historical user groups, and recommending insurance according to the multiplexing coefficients.

As described in the foregoing embodiment, each time a new coordinate information group is placed in a historical user group, a multiplexing coefficient is obtained, so that multiplexing coefficients with the same number as the historical user groups can be obtained, and the multiplexing coefficients may be the same or different according to whether the dividing method of the historical user characteristic information is the method of step S1021 or the method of step S1022, and whether the data amount in the new user characteristic information is perfect.

Optionally, the preset multiplexing coefficient threshold belongs to the interval of [ 1,1 ], and a person skilled in the art can select the threshold according to needs, which is not limited herein.

In some embodiments, making insurance recommendations based on the reuse factor comprises:

and if at least one multiplexing coefficient is larger than a preset multiplexing coefficient threshold value, recommending the historical purchase insurance information of the historical user group corresponding to the maximum value in the multiplexing coefficients to the newly added user.

If too many insurance products are recommended to the user at one time, the user may be unwilling to know the insurance products due to too large information amount or generate a daunting emotion, so that only the historical purchase insurance information corresponding to the maximum value in the multiplexing coefficient can be selected and recommended to the newly added user.

Optionally, if multiple pieces of multiplexing coefficients are the same and equal to the maximum value of the multiplexing coefficients, the historical purchase insurance information corresponding to each multiplexing coefficient may be integrated and recommended to the new user after the repeated information is deleted, or one piece of historical purchase insurance information including the most historical purchase insurance information corresponding to each multiplexing coefficient may be selected and recommended to the new user. Of course, the recommended mode in this case may be other modes known to those skilled in the art.

In some embodiments, making insurance recommendations based on reuse factors includes:

and if the multiplexing coefficients are not more than the preset multiplexing coefficient threshold value, acquiring historical purchase insurance information of a corresponding historical user group when the multiplexing coefficient is maximum, adjusting the historical purchase insurance information according to the new user characteristic information, and recommending the adjusted historical purchase insurance information to the new user.

In some embodiments, adjusting the historical purchase insurance information based on the added user characteristic information comprises:

respectively acquiring difference information between historical characteristic quantitative evaluation data of historical users and newly added characteristic quantitative evaluation data of newly added users in a historical user group corresponding to the maximum multiplexing coefficient according to the historical characteristic types;

and adjusting the historical purchase insurance information according to the difference information.

That is, if the new user type is greater than the historical user type, the supplementary insurance recommendation information is determined according to the added new user type and the new user characteristic quantitative evaluation data, and the supplementary insurance recommendation information is added to the historical insurance purchasing information and then recommended to the new user. And if the types of the historical users are more than the types of the newly added users, after the historical purchase insurance information corresponding to the types of the excessive historical users is screened out, recommending the screened out historical purchase insurance information to the newly added users.

In some embodiments, the difference information may be a difference amount of the characteristic quantitative evaluation data, and/or a difference of the user characteristic information. For example, the historical user characteristic information includes a historical user category 1, whose historical characteristic quantitative evaluation data is S1, a historical user category 2, the quantitative evaluation data of the historical characteristics is S2 and the type 3 of the historical users, the quantitative evaluation data of the historical characteristics is S3, the characteristic information of the newly added users comprises the type 1 of the newly added users, the newly added feature quantitative evaluation data is S4, the newly added user category 2, the newly added feature quantitative evaluation data is S2, the newly added user category 3, the added feature quantitative evaluation data is S3, wherein the added user categories 1, 2, 3 are substantially the same as the historical user categories 1, 2, 3, and at this time, the difference information is the added feature quantitative evaluation data of the added user category 1 (S1-S4), part of the information on the newly added user category 1 in the historical purchase insurance information can be adjusted directly based on the difference information.

For another example, the historical user feature information includes a historical user type 1, the historical feature quantitative evaluation data is S1, the historical user type 2, the historical feature quantitative evaluation data is S2, the historical user type 3, the historical feature quantitative evaluation data is S3, the new user feature information includes a new user type 1, the new feature quantitative evaluation data is S1, the new user type 2, and the new feature quantitative evaluation data is S2, where the new user types 1 and 2 are substantially the same as the historical user types 1 and 2, and at this time, the difference information is the historical user type 3 (difference historical feature type), a part of the historical purchase insurance information corresponding to the historical user type 3 may be directly deleted, and the deleted historical purchase insurance information may be recommended to the new user.

For another example, the historical user characteristic information includes a historical user category 1, whose historical characteristic quantitative evaluation data is S1, a historical user category 2, whose historical characteristic quantitative evaluation data is S2, a historical user category 3, whose historical characteristic quantitative evaluation data is S3, the new user characteristic information includes a new user category 1, whose new characteristic quantitative evaluation data is S1, a new user category 2, whose new characteristic quantitative evaluation data is S2, a new user category 3, whose new characteristic quantitative evaluation data is S3, a new user category 4, whose new characteristic quantitative evaluation data is S4, at this time, the difference information is a new user category 4 (difference historical characteristic category), whose specific new characteristic quantitative evaluation data is S4, the additional insurance recommendation information can be added to the data of the new user category 4, the new characteristic quantitative evaluation data S4 directly in the historical purchase insurance information, and recommending the increased historical insurance purchasing information to the newly added user.

Optionally, adjusting the historical insurance purchase information according to the feature information of the new user includes:

taking the difference between the quantitative evaluation data of each historical characteristic in the historical user group corresponding to the maximum multiplexing coefficient and the quantitative evaluation of the newly added characteristic of the newly added user;

acquiring preset category difference thresholds corresponding to the historical feature categories, and if one difference is greater than the corresponding preset category difference threshold, taking the historical feature category corresponding to the preset category difference threshold as a difference historical feature category;

and acquiring the corresponding relation between the historical purchase insurance information and the historical characteristic types, screening out the historical purchase sub-information corresponding to the different historical characteristic types from the historical purchase insurance information, and recommending the screened-out historical purchase insurance information to the new user.

The preset species difference threshold may be a value set by a person skilled in the art.

The correspondence between the historical purchase insurance information and the historical feature type may be preset by those skilled in the art. Optionally, the historical insurance purchasing information may be divided into a plurality of pieces of historical insurance purchasing sub-information, the historical feature categories may be divided into a plurality of historical feature sub-categories, and then the corresponding relationship may be established. Optionally, the correspondence may be one-to-one, one-to-many, or many-to-one.

Optionally, adjusting the historical purchase insurance information according to the difference information includes:

acquiring a target characteristic type and a type influence factor of a historical characteristic type, wherein the target characteristic type comprises the historical characteristic type corresponding to the difference information;

if the category influence factors corresponding to the target feature categories are smaller than the preset influence factor threshold, keeping historical insurance purchasing information;

and if the type influence factor corresponding to one target characteristic type is larger than the preset influence factor threshold, adjusting historical purchase sub-information corresponding to the target characteristic type in the historical purchase insurance information.

The category impact factor and the predetermined impact factor threshold can be preset by those skilled in the art according to the needs.

The embodiment of the invention provides an insurance recommendation method, a system, equipment and a medium, wherein historical user characteristic information and historical insurance purchasing information are obtained by obtaining the historical user characteristic information and grouping the historical user characteristic information to obtain a plurality of historical user groups, data in each historical user group is converted into a historical coordinate information group, newly added user characteristic information is obtained and converted into a newly added coordinate information group, and a plurality of multiplexing coefficients are obtained by determining the average distance in the group and the minimum average distance outside the group, which are obtained by placing the newly added coordinate information group in different historical user groups, so that insurance recommendation is carried out, the problem that the recommendation of insurance products in the related technology needs to depend on manual product recommendation to influence the working efficiency, cause the waste of time and other resources, and achieve the purposes of improving the working efficiency, reducing the waste of the resources such as time and the like, meanwhile, the objectivity of insurance recommendation can be improved, and the customer satisfaction degree is improved.

Example two

Referring to fig. 2, an embodiment of the present invention further provides an insurance recommendation system 200, including:

the history acquisition module 201 is configured to acquire historical user feature information and historical purchase insurance information of a historical user, where the historical user feature information includes historical feature types and historical feature quantitative evaluation data;

the grouping module 202 is used for grouping the historical user characteristic information according to the historical purchase insurance information to obtain a plurality of historical user groups, and converting the historical user characteristic information in each historical user group into a plurality of historical coordinate information groups according to the historical characteristic types and the historical characteristic quantitative evaluation data;

the newly added obtaining module 203 is configured to obtain newly added user feature information of the newly added user, where the newly added user feature information includes a newly added feature type and newly added feature quantitative evaluation data, and convert the newly added user feature information into a newly added coordinate information group according to the newly added feature type and the newly added feature quantitative evaluation data;

a determining module 204, configured to determine an average distance in a group and a minimum average distance outside the group, and determine a multiplexing coefficient, where the determining manner of determining the average distance in the group includes setting a newly added coordinate information group in a historical user group, and determining an average distance in the group between the newly added coordinate information group and each historical coordinate information group in the historical user group where the newly added coordinate information group is located, and the determining manner of the minimum average distance outside the group includes taking a minimum value of average distances between the newly added coordinate information group and each historical coordinate information group in other historical user groups as a minimum average distance outside the group;

and the recommending module 205 is configured to obtain a plurality of multiplexing coefficients determined by setting the newly added coordinate information groups in each historical user group, and perform insurance recommendation according to the multiplexing coefficients.

In this embodiment, the insurance recommendation system executes the method described in any of the above embodiments, and specific functions and technical effects are described with reference to the above embodiments, which are not described herein again.

Referring to fig. 3, an embodiment of the present application further provides an electronic device 1600, where the electronic device 1600 includes a processor 1601, a memory 1602 and a communication bus 1603;

the communication bus 1603 is used to connect the processor 1601 and the memory 1602;

the processor 1601 is configured to execute a computer program stored in the memory 1602 to implement the method according to any of the above embodiments.

Embodiments of the present application also provide a non-transitory readable storage medium, where one or more modules (programs) are stored in the storage medium, and when the one or more modules are applied to a device, the device may execute instructions (instructions) included in an embodiment of the present application.

The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, the computer program is used for causing the computer to execute the method according to the embodiment.

The foregoing embodiments are merely illustrative of the principles of the present invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

In the corresponding figures of the above embodiments, the connecting lines may represent the connection relationship between the various components to indicate that more constituent signal paths (consistent _ signal paths) and/or one or more ends of some lines have arrows to indicate the main information flow direction, the connecting lines being used as a kind of identification, not a limitation on the scheme itself, but rather to facilitate easier connection of circuits or logic units using these lines in conjunction with one or more example embodiments, and any represented signal (determined by design requirements or preferences) may actually comprise one or more signals that may be transmitted in any one direction and may be implemented in any suitable type of signal scheme.

In the above embodiments, unless otherwise specified, the description of common objects by using "first", "second", etc. ordinal numbers only indicate that they refer to different instances of the same object, rather than indicating that the objects being described must be in a given sequence, whether temporally, spatially, in ranking, or in any other manner.

In the above-described embodiments, reference in the specification to "the embodiment," "an embodiment," "another embodiment," or "other embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least some embodiments, but not necessarily all embodiments. The various appearances of the phrase "the present embodiment," "one embodiment," or "another embodiment" are not necessarily all referring to the same embodiment. If the specification states a component, feature, structure, or characteristic "may", "might", or "could" be included, that particular component, feature, structure, or characteristic is not necessarily included. If the specification or claim refers to "a" or "an" element, that does not mean there is only one of the element. If the specification or claim refers to "a further" element, that does not preclude there being more than one of the further element.

In the embodiments described above, although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory structures (e.g., dynamic ram (dram)) may use the discussed embodiments. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.