Intelligent recommendation methods and related products

Abstract

The present application discloses an intelligent recommendation method and related products, the method comprising: a recommendation device receives an information acquisition request sent by a terminal device, responds to the information acquisition request, sends an information filling page to the terminal device, and prompts the terminal device to enter commercial insurance information on the information filling page; the recommendation device receives the information page submitted by the terminal device, extracts several commercial insurance information in the information page, and determines several commercial insurances corresponding to the several commercial insurance information; the recommendation device arranges the several commercial insurances to obtain several commercial insurance combinations; the recommendation device performs claim calculation on the several commercial insurance combinations, determines the claim amount of each commercial insurance combination, and marks the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination; the recommendation device sends the target commercial insurance combination and prompt information to the terminal device, and the prompt information is used to prompt the terminal device to make claims and reimbursements according to the arrangement order of each commercial insurance in the target commercial insurance combination when making claims and reimbursements. The embodiments of the present application are conducive to increasing the claim amount and improving user experience.

Description

Technical Field

[0001] The present application relates to the field of electronic technology and specifically to an intelligent recommendation method and related products. Background Art

[0002] At present, for insured users, since the compensation liability of each insurance policy is inconsistent and the reimbursement scope is also different, if the user is not clear about the claims rules of each policy, or does not calculate in advance how to insure to maximize the user's interests, the amount of compensation may be smaller.

[0003] The claims terms of each company are different, but when users compare the claims terms of different companies, it is usually difficult to interpret what order of claims can get more claims, or which companies / insurance items will benefit more. Some claims terms are not very clear, and for customers, if they do not study each term carefully, it is difficult to determine how to insure and how to reimburse in the best way for them.

[0004] In the prior art, when multiple insurance policies are purchased, the recommendation method for the reimbursement order is single, with low accuracy and poor user experience. Summary of the invention

[0005] The embodiment of the present application provides an intelligent recommendation method, in order to intelligently recommend the best reimbursement sequence, increase the reimbursement amount, and improve the user experience.

[0006] In a first aspect, an embodiment of the present application provides an intelligent recommendation method, the method comprising:

[0007] The recommendation device receives an information acquisition request sent by a terminal device, responds to the information acquisition request, sends an information filling page to the terminal device, and prompts the terminal device to enter commercial insurance information on the information filling page;

[0008] The recommendation device receives the information page submitted by the terminal device, extracts a number of commercial insurance information in the information page, and determines a number of commercial insurances corresponding to the number of commercial insurance information;

[0009] The recommendation device arranges the plurality of commercial insurances to obtain a plurality of commercial insurance combinations;

[0010] The recommendation device performs claim calculation on the plurality of commercial insurance combinations, determines the claim amount of each commercial insurance combination, and marks the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination;

[0011] The recommendation device sends the target commercial insurance combination and prompt information to the terminal device, and the prompt information is used to prompt that claims and reimbursements should be made according to the arrangement order of each commercial insurance in the target commercial insurance combination when claims and reimbursements are made.

[0012] In a second aspect, an embodiment of the present application provides a recommendation device for intelligent recommendation, the recommendation device comprising:

[0013] A first receiving unit is used to receive an information acquisition request sent by a terminal device, and in response to the information acquisition request, send an information filling page to the terminal device, prompting the terminal device to enter commercial insurance information on the information filling page;

[0014] A second receiving unit is used to receive the information page submitted by the terminal device, extract the commercial insurance information in the information page, and determine the commercial insurance corresponding to the commercial insurance information;

[0015] An arrangement unit, used for arranging the plurality of commercial insurances to obtain a plurality of commercial insurance combinations;

[0016] A calculation unit, configured to perform claim calculation on the plurality of commercial insurance combinations, determine the claim amount of each commercial insurance combination, and mark the commercial insurance combination corresponding to the maximum claim amount as a target commercial insurance combination;

[0017] A sending unit is used to send the target commercial insurance combination and prompt information to the terminal device, and the prompt information is used to prompt that the claim reimbursement should be made according to the arrangement order of each commercial insurance in the target commercial insurance combination when making a claim reimbursement.

[0018] In a third aspect, an embodiment of the present application provides a recommendation device, comprising one or more processors, one or more memories, one or more transceivers, and one or more programs, wherein the one or more programs are stored in the memories and are configured to be executed by the one or more processors, and the programs include instructions for executing the steps in the method described in the first aspect.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program is executed by a processor to implement the method described in the first aspect.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method described in the first aspect.

[0021] Implementing the embodiments of the present application has at least the following beneficial effects:

[0022] Through the embodiments of the present application, according to the commercial insurance information input into the terminal device, the commercial insurances corresponding to the commercial insurance information are arranged to obtain several commercial insurance combinations, and the best commercial insurance combination is obtained. The best commercial insurance combination is pushed to the terminal device, prompting the user to make claims in the order of arrangement of the various commercial insurances in the best commercial insurance combination when making claims for reimbursement, so that the user can obtain the maximum reimbursement amount, thereby increasing the user's enthusiasm for insurance and the success rate of insurance recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1A A schematic diagram of a network architecture for intelligent recommendation provided in an embodiment of the present application

[0025] Figure 1B A flowchart of an intelligent recommendation method provided in an embodiment of the present application;

[0026] Figure 2 A flowchart of another intelligent recommendation method provided in an embodiment of the present application;

[0027] Figure 3 A flowchart of another intelligent recommendation method provided in an embodiment of the present application;

[0028] Figure 4 It is a structural diagram of a recommendation device for intelligent recommendation provided in an embodiment of the present application;

[0029] Figure 5 This is a block diagram of the functional units of a recommendation device for intelligent recommendation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0032] Reference to "embodiments" herein means that a particular feature, result, 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.

[0033] The recommended devices in this application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, mobile Internet devices MID (Mobile Internet Devices, MID for short) or wearable devices, etc. The above-mentioned recommended devices are only examples, not exhaustive, and include but are not limited to the above-mentioned recommended devices. For the convenience of description, the above-mentioned recommended devices are referred to as user equipment UE (User equipment, UE for short) in the following embodiments. Of course, in actual applications, the above-mentioned user equipment is not limited to the above-mentioned forms, for example, it can also include: smart vehicle terminals, computer equipment, etc.

[0034] First, see Figure 1A , Figure 1A A schematic diagram of a network architecture for intelligent recommendation is provided, the network architecture comprising: an intelligent recommendation device 100, a user terminal 200;

[0035] The intelligent recommendation device 100 may include a server, a mobile Internet device, a transmission reception point (TRP), a base station (e.g., a macro station), an LTE eNB, and a 5G NR NB access point (AccessPoint, referred to as AP). It should be noted that the specific type of the intelligent recommendation device 100 is not limited in the embodiments of the present invention.

[0036] The intelligent recommendation device 100 is used to receive an access request for inputting information sent by the user terminal 200, and in response to the access request, send an information filling page to the terminal device, prompting the user to input commercial insurance information on the information filling page, and prompting the user to input commercial insurance information in the information input area on the information filling page;

[0037] The user terminal 200 is used to receive a number of commercial insurance information input by the user on the first information filling page, and submit the information page after the commercial insurance information is filled in to the intelligent recommendation device 100;

[0038] The intelligent recommendation device 100 is used to receive an information page submitted by a user terminal 200, extract a number of commercial insurance information in the information page to determine a number of commercial insurances corresponding to the number of commercial insurance information; and to arrange the number of commercial insurances to obtain a number of commercial insurance combinations; and to perform claim calculations on the number of commercial insurance combinations, determine the claim amount of each commercial insurance combination, and mark the commercial insurance combination corresponding to the maximum claim amount as a target commercial insurance combination; and to send the target commercial insurance combination and prompt information to the terminal device, wherein the prompt information is used to prompt that claims and reimbursements should be made in accordance with the arrangement order of the commercial insurances in the target commercial insurance combination when claims are reimbursed.

[0039] The user terminal 200 is used to receive the target commercial insurance combination and prompt information sent by the intelligent recommendation device 100.

[0040] It can be seen that in the embodiment of the present application, based on the intelligent recommendation device, the insured can obtain the best reimbursement order when purchasing multiple commercial insurance policies, thereby bringing the insured the maximum reimbursement amount, improving the insured's enthusiasm for insurance, and the insured's experience.

[0041] Reference Figure 1B , Figure 1B An intelligent recommendation method is provided in an embodiment of the present application. The method is applied to a recommendation device. The method includes the contents shown in steps S101 to S105:

[0042] Step S101: The recommendation device receives an information acquisition request sent by a terminal device, responds to the information acquisition request, sends an information filling page to the terminal device, and prompts the terminal device to enter commercial insurance information on the information filling page.

[0043] Optionally, the access request is a hypertext markup language HTML of an information filling page, and the access request is used to request the intelligent recommendation device to send an information filling page corresponding to the hypertext markup language HTML. The intelligent recommendation device parses the access request, extracts the HTML of the access request, responds to the access request, sends an information filling page corresponding to the HTML, and displays prompt information in the information filling page, and the prompt information is used to prompt the user to enter commercial insurance information in the information input area of ​​the information filling page, wherein the commercial insurance information includes commercial insurance information that the user wants to insure or commercial insurance information that has been insured.

[0044] Step S102: the recommendation device receives the information page submitted by the terminal device, extracts a number of commercial insurance information from the information page, and determines a number of commercial insurances corresponding to the number of commercial insurance information.

[0045] Optionally, the recommendation device extracts several commercial insurance information from the information page, specifically including: the recommendation device performs text recognition on the information page to obtain the text area of ​​the information page; the recommendation device extracts the text information in the text area, performs keyword recognition on the text information, obtains multiple keywords that meet preset conditions, and obtains a keyword group; the recommendation device searches for multiple commercial insurances that match the keyword group in the insurance information library, and marks the multiple commercial insurances as several commercial insurances corresponding to the several commercial insurance information. For example, when it is recognized that "serious illness" is included in the keyword group, it is determined that the commercial insurance corresponding to the keyword is serious illness insurance.

[0046] Step S103: The recommendation device arranges the plurality of commercial insurances to obtain a plurality of commercial insurance combinations.

[0047] Optionally, the recommendation device arranges the plurality of commercial insurances in a specific manner including: arranging the plurality of commercial insurances in order to obtain a plurality of commercial insurance combinations. For example, when the number of the plurality of commercial insurances is N, then A is obtained. N N , where A is the permutation calculation formula.

[0048] Step S104: the recommendation device performs claim calculation on the plurality of commercial insurance combinations, determines the claim amount of each commercial insurance combination, and marks the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination.

[0049] Optionally, the recommendation device performs claim calculations on the several commercial insurance combinations to determine the claim amount of each commercial insurance combination, specifically including: the recommendation device determines the arrangement order of the several commercial insurances in each commercial insurance combination; the recommendation device calculates the claim amount of each commercial insurance in sequence according to the arrangement order of the several commercial insurances, and obtains several claim amounts corresponding to the several commercial insurances, wherein the commercial insurances and the claim amounts correspond one-to-one; the recommendation device adds the several claim amounts corresponding to the several commercial insurances, and obtains the claim amount of each commercial insurance combination.

[0050] Further, when calculating the claim amount of each commercial insurance in sequence according to the arrangement order of the several commercial insurances in the commercial insurance combination, the recommendation device first obtains the first commercial insurance that is ranked first in the arrangement order, performs claim calculation on the first commercial insurance, and obtains the claim amount of the first commercial insurance, wherein the claim calculation on the first commercial insurance specifically includes: the recommendation device obtains the accident information submitted by the user on the information filling page and the first insurance information in the first commercial insurance submitted on the information filling page, and extracts the first claim rule of the first commercial insurance from the insurance information database, wherein the first insurance information is included in the first commercial insurance the types of insurance and the insured amount of each type of insurance; the recommendation device performs settlement verification on the accident information according to the first claim settlement rule, such as extracting various expense information in the accident information through settlement verification, extracting various liability detail information from the insurance information, matching the various expense information with the various liability detail information respectively, obtaining multiple expense information matched in the various expense information, obtaining the claim ratio set in the liability details matching the multiple expense information, determining the claim amount of each expense information in the multiple expense information according to the claim ratio, obtaining the total claim amount corresponding to the multiple expense information, and marking the total claim amount as the claim amount of the first commercial insurance.

[0051] Furthermore, after performing claim calculation on the first commercial insurance and obtaining the claim amount of the first commercial insurance, when performing claim calculation on the claim amount of the i-th commercial insurance that is arranged in the i-th order among the several commercial insurances, the recommendation device determines whether the claim events corresponding to all commercial insurances that are arranged before the i-th commercial insurance restrict the claim events corresponding to the i-th commercial insurance. If so, obtain the restriction result and determine the claim amount of the i-th commercial insurance based on the restriction result. If not, directly perform claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance. When the number of the several commercial insurances is N, when i=N, obtain the claim amount of each commercial insurance, wherein i and N are both integers greater than or equal to 2, and i≤N. Among them, whether it is restricted specifically includes: whether the reimbursement process of the i-th commercial insurance is affected by all previous commercial insurances, and whether the claim events corresponding to all commercial insurances whose arrangement order is before the i-th commercial insurance restrict the claim events corresponding to the i-th commercial insurance specifically includes: the recommendation device extracts the i-th insurance information corresponding to the i-th insurance information from the information page, and determines multiple reimbursement items of the i-th commercial insurance according to the insurance information, wherein the i-th insurance information includes the insured types and the insured amount of each insurance type in the i-th commercial insurance. Generally speaking, each insured type is a reimbursement item; the recommendation device extracts the i-th claim settlement rule of the i-th commercial insurance from the insurance information database; based on the i-th claim settlement rule, determines the multiple reimbursement items. The claim amount of the reimbursement item is subject to the i-th claim rule, and the constraint condition on the claim amount of the reimbursement item is determined. Specifically, the claim rule will limit the claim amount of a certain reimbursement item. For example, when the reimbursement item is a critical illness insurance, the maximum reimbursement amount of the reimbursement item will be limited. If the constraint condition is that the reimbursement amount of the reimbursement item is subject to the same type of reimbursement items, obtain the reimbursement items of the same type in all commercial insurances whose arrangement order is before the i-th commercial insurance, obtain the total amount of claims for the reimbursement items of the same type, determine the first claim amount of the reimbursement item according to the total amount of claims, add the claim amounts of other reimbursements in the multiple reimbursement items to the first claim amount to obtain the total claim amount, and mark the total claim amount as the claim amount of the i-th commercial insurance.

[0052] Furthermore, the recommendation device determines the first claim amount of the reimbursement item based on the total amount reimbursed, specifically including: if the total amount reimbursed is greater than or equal to the maximum claim amount of the reimbursement item, the recommendation device determines the first claim amount of the reimbursement item to be zero; if the total amount reimbursed is less than the maximum claim amount of the reimbursement item, the recommendation device determines the first claim amount of the reimbursement item to be the difference between the maximum claim amount of the reimbursement item and the total amount reimbursed.

[0053] Furthermore, if the claim amounts of the multiple reimbursement items are not subject to the constraints of the i-th claim rules, the claim amount of the i-th commercial insurance can be determined in the same manner as the claim amount of the first commercial reimbursement, which will not be elaborated here.

[0054] For example, when the number of the several commercial insurances is two, and the two commercial insurances are specifically A and B, the several commercial insurance combinations are AB and BA. The insurance information in A is that the insurance covers three types of diseases A, B, and C, and the insurance covers three types of diseases B and C in B. It is assumed that A's reimbursement for A, B, and C is proportional and not subject to the same type of reimbursement items. B's reimbursement for B disease does not exceed M yuan, and the reimbursement for C is proportional and not subject to the same type of reimbursement items. For example, A reimburses B at 50%, and B's reimbursement for B does not exceed 3,000 yuan. If the user's expenditure on B disease is 10,000 yuan, , when the claims are settled according to the order of the commercial insurance combination AB, A will first reimburse 5,000 yuan for disease B. Since 5,000>3,000, B will no longer reimburse disease B. Therefore, when the claims are settled according to the order of AB, the claim amount for disease B is 5,000 yuan. When the claims are settled according to the order of the commercial insurance combination BA, BA will first reimburse 3,000 yuan for disease B. Since A's reimbursement for disease B is not restricted by B, A will reimburse 5,000 yuan for disease B. Therefore, when the claims are settled according to the order of BA, the claim amount for disease B is 8,000 yuan. Therefore, it is obvious that more claim amounts are obtained by settling claims according to the order of BA.

[0055] Step S105: the recommendation device sends the target commercial insurance combination and prompt information to the terminal device, wherein the prompt information is used to prompt the terminal device to make claims and reimbursements in the order in which the commercial insurances in the target commercial insurance combination are arranged.

[0056] Optionally, after determining the target commercial insurance combination, the target commercial insurance combination and prompt information are pushed to the terminal device, wherein the prompt information can be displayed in the form of email, text message, voice, etc. The prompt information is used to prompt that when the accident occurs, the maximum reimbursement amount can be obtained when the claim is settled and reimbursed according to the arrangement order of each commercial insurance in the target commercial insurance combination.

[0057] It can be seen that in the embodiment of the present application, based on the commercial insurance information submitted by the terminal device, a number of commercial insurances are determined, and the several commercial insurances are arranged to obtain a number of commercial insurance combinations, the claim amount of each commercial insurance combination is calculated, and the commercial insurance combination corresponding to the largest claim amount is marked as a target commercial insurance combination, and the target commercial insurance combination is pushed to the terminal device, prompting the user to obtain the maximum reimbursement amount by making claims and reimbursement in the order of arrangement in the target commercial insurance combination, thereby improving the accuracy of the recommendation on the claim reimbursement order; since the user can obtain the maximum reimbursement amount, the user's enthusiasm for insurance is increased, and the user experience is improved.

[0058] Reference Figure 2 , Figure 2 Another intelligent recommendation method provided in an embodiment of the present application is applied to a recommendation device, and the method includes the contents shown in steps S201 to S207:

[0059] Step S201: The recommendation device extracts a preset number of commercial insurance claim samples from the insurance information database.

[0060] Among them, each commercial insurance claim sample includes multiple commercial insurances, the claim rules of each of the multiple commercial insurances, the accident information corresponding to the commercial insurance claim sample, and the maximum claim amount corresponding to the accident information.

[0061] Step S202, the recommendation device divides the preset number of commercial insurance claim samples into a training set of a first proportion and a test set of a second proportion, uses the commercial insurance claim samples in the training set for training to obtain a trained commercial insurance recommendation model, and uses the commercial insurance claim samples in the test set to test the trained commercial insurance recommendation model. If the test passes, the training ends; if the test fails, commercial insurance claim samples are added from the insurance information database and retrained.

[0062] Optionally, using the commercial insurance claim samples in the training set for training specifically includes: adding label information to the commercial insurance claim samples in the training set for supervised training, wherein the label information is the actual maximum claim amount of the commercial insurance sample; marking multiple commercial insurances in each commercial insurance claim sample, the claim rules of each commercial insurance, and the accident information corresponding to the commercial insurance claim sample as input data, inputting the input data matrix into the initial network model, predicting the maximum claim amount corresponding to the accident information, parsing the label information, obtaining the actual maximum claim amount of the commercial insurance sample, and determining whether the similarity between the predicted maximum claim amount and the actual maximum claim amount is less than a threshold value. If so, the training of the initial network model is terminated to obtain the commercial insurance recommendation model. If not, reverse training is performed on the initial model based on the loss function in the initial model, and the weight gradient in the initial network model is updated until, when the commercial insurance claim sample is input, the difference between the predicted maximum claim amount and the corresponding maximum claim amount is less than the threshold value.

[0063] Among them, the first ratio can be 90%, 80%, 70%, 60% or other values.

[0064] The second ratio may be 10%, 20%, 30%, 40% or other values.

[0065] The preset number may be 1000, 2000, 4000, 5000, or other values.

[0066] Step S203: the recommendation device receives an information acquisition request sent by the terminal device, responds to the information acquisition request, sends an information filling page to the terminal device, and prompts the terminal device to enter commercial insurance information on the information filling page.

[0067] Step S204: the recommendation device receives the information page submitted by the terminal device, extracts a number of commercial insurance information in the information page, and determines a number of commercial insurances corresponding to the number of commercial insurance information.

[0068] Step S205: The recommendation device arranges the plurality of commercial insurances to obtain a plurality of commercial insurance combinations.

[0069] Step S206: the recommendation device inputs the several commercial insurance combinations into the commercial insurance recommendation model, outputs the claim amounts of the several commercial insurance combinations, and marks the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination.

[0070] Step S207: the recommendation device sends the target commercial insurance combination and prompt information to the terminal device, wherein the prompt information is used to prompt the terminal device to make claims and reimbursements in the order in which the commercial insurances in the target commercial insurance combination are arranged.

[0071] It can be seen that in the embodiment of the present application, based on the commercial insurance information submitted by the terminal device, a number of commercial insurances are determined, and the several commercial insurances are arranged to obtain a number of commercial insurance combinations, and the claim amount of each commercial insurance combination is calculated based on the trained commercial insurance recommendation model, thereby improving the accuracy of the claim amount calculation of each commercial insurance; then, the commercial insurance combination corresponding to the maximum claim amount is marked as a target commercial insurance combination, and the target commercial insurance combination is pushed to the terminal device, prompting the user to obtain the maximum reimbursement amount by making a claim in the order of arrangement in the target commercial insurance combination, thereby improving the accuracy of the recommendation on the claim reimbursement order; since the user can obtain the maximum reimbursement amount, the user's enthusiasm for insurance is increased, and the user experience is improved.

[0072] Reference Figure 3 , Figure 3 Another intelligent recommendation method provided in an embodiment of the present application is applied to a recommendation device, and the method includes the contents shown in steps S301 to S307:

[0073] Step S301: The recommendation device receives an information acquisition request sent by a terminal device, responds to the information acquisition request, sends an information filling page to the terminal device, and prompts the terminal device to enter commercial insurance information on the information filling page.

[0074] Step S302: The recommendation device receives the information page submitted by the terminal device, extracts a number of commercial insurance information from the information page, and determines a number of commercial insurances corresponding to the number of commercial insurance information.

[0075] Step S303: The recommendation device arranges the plurality of commercial insurances to obtain a plurality of commercial insurance combinations.

[0076] Step S304: the recommendation device performs claim calculation on the plurality of commercial insurance combinations, determines the claim amount of each commercial insurance combination, and marks the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination.

[0077] The claim amount for each commercial insurance combination may be determined in accordance with the method of determining the claim amount in the first embodiment or the second embodiment, which will not be repeated here.

[0078] Step S305: The recommendation device obtains the location information of the terminal device.

[0079] Optionally, the recommendation device obtains the location information of the terminal device specifically including: the recommendation device obtains the network IP address used by the terminal device when submitting the information page, and obtains the location information of the terminal device based on the IP address, wherein determining the location information based on the IP address is a prior art and will not be described in detail here.

[0080] Step S306, the recommendation device determines each insured company corresponding to each commercial insurance of the target commercial insurance combination, determines each offline company that is closest to the location information, determines each navigation route between each offline company and the location information, and obtains a navigation route set corresponding to the target commercial insurance combination.

[0081] Step S307, the recommendation device sends the target commercial insurance group, the navigation route set and prompt information to the terminal device, and the prompt information is used to prompt that claims should be reimbursed according to the arrangement order of each commercial insurance in the target commercial insurance combination when claims are reimbursed.

[0082] Optionally, the recommendation device sends the target commercial insurance group and the navigation route set to the terminal device specifically including: when sending the target commercial insurance group, arranging the navigation routes corresponding to each commercial insurance in the target commercial insurance group in the same area, so that after the terminal device receives the target commercial insurance group and the navigation route set, it can correctly display the navigation route corresponding to each commercial insurance, so that the user can make claims and reimbursements offline.

[0083] It can be seen that in the embodiment of the present application, based on the commercial insurance information submitted by the terminal device, a number of commercial insurances are determined, and the several commercial insurances are arranged to obtain a number of commercial insurance combinations, and the claim amount of each commercial insurance combination is calculated based on the trained commercial insurance recommendation model, thereby improving the accuracy of the claim amount calculation of each commercial insurance; then, the commercial insurance combination corresponding to the maximum claim amount is marked as the target commercial insurance combination, and the target commercial insurance combination is pushed to the terminal device, prompting the user to make claims and reimbursements in the order of arrangement in the target commercial insurance combination to obtain the maximum reimbursement amount, thereby improving the accuracy of the recommendation of the claim reimbursement order; since the user can obtain the maximum reimbursement amount, the user's enthusiasm for insurance is increased, and the user experience is improved; moreover, the navigation routes of the offline companies corresponding to each commercial insurance are pushed to the terminal device together, which is convenient for the user to make claims and reimbursements offline, further improving the user experience.

[0084] With the above Figure 1B , Figure 2 , Figure 3 For details on the embodiments shown in the drawings, please refer to Figure 4 , Figure 4 A schematic diagram of a structure of a recommendation device 400 for intelligent recommendation provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the recommendation device 400 includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are different from the one or more application programs, and the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the following steps;

[0085] Receiving an information acquisition request sent by a terminal device, responding to the information acquisition request, sending an information filling page to the terminal device, and prompting the terminal device to enter commercial insurance information on the information filling page;

[0086] Receiving the information page submitted by the terminal device, extracting a number of commercial insurance information in the information page, and determining a number of commercial insurances corresponding to the number of commercial insurance information;

[0087] Arranging the plurality of commercial insurances to obtain a plurality of commercial insurance combinations;

[0088] Performing claim calculations on the several commercial insurance combinations, determining the claim amount of each commercial insurance combination, and marking the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination;

[0089] The target commercial insurance combination and prompt information are sent to the terminal device, where the prompt information is used to prompt that claims should be settled and reimbursed in the order in which the commercial insurances in the target commercial insurance combination are arranged.

[0090] In a possible example, in terms of extracting several commercial insurance information from the information page and determining several commercial insurances corresponding to the several commercial insurance information, the instructions in the above program are specifically used to perform the following operations: perform text recognition on the information page to obtain a text area of ​​the information page; extract text information from the text area, perform keyword recognition on the text information, obtain multiple keywords that meet preset conditions, and obtain a keyword group; query the insurance information library for multiple commercial insurances that match the keyword group, and mark the multiple commercial insurances as several commercial insurances corresponding to the several commercial insurance information.

[0091] In a possible example, in terms of performing claim calculations on the several commercial insurance combinations and determining the claim amount of each commercial insurance combination, the instructions in the above program are specifically used to perform the following operations: determine the arrangement order of the several commercial insurances in each commercial insurance combination; calculate the claim amount of each commercial insurance in sequence according to the arrangement order of the several commercial insurances in the commercial insurance combination to obtain several claim amounts corresponding to the several commercial insurances, wherein the commercial insurances correspond to the claim amounts one-to-one; add the several claim amounts corresponding to the several commercial insurances to obtain the claim amount of the commercial insurance combination.

[0092] In a possible example, in terms of calculating the claim amount of each commercial insurance in sequence according to the arrangement order of the several commercial insurances in the commercial insurance combination, the instructions in the above program are specifically used to perform the following operations: perform claim calculation on the first commercial insurance that is arranged in the first order among the several commercial insurances to obtain the claim amount of the first commercial insurance; when performing claim calculation on the claim amount of the i-th commercial insurance that is arranged in the i-th order among the several commercial insurances, determine whether the claim events corresponding to all commercial insurances whose arrangement order is before the i-th commercial insurance restrict the claim event corresponding to the i-th commercial insurance, if so, obtain the restriction result, and determine the claim amount of the i-th commercial insurance according to the restriction result, if not, directly perform claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance, and when the number of the several commercial insurances is N, when i=N, obtain the claim amount of each commercial insurance; wherein, i and N are both integers greater than or equal to 2, and i≤N.

[0093] In a possible example, in terms of performing claim calculation for the first commercial insurance and obtaining the claim amount of the first commercial insurance, the instructions in the above program are specifically used to perform the following operations: extract the accident information and the first insurance information corresponding to the first commercial insurance from the information page; extract the first claim rule of the first commercial insurance from the insurance information database; perform settlement verification on the accident information according to the first claim rule, such as extracting various expense information in the accident information through settlement verification, extracting various liability detail information from the insurance information, matching the various expense information with the various liability detail information respectively, obtaining multiple expense information matched in the various expense information, obtaining the claim ratio set in the liability details matching the multiple expense information, determining the claim amount of each expense information in the multiple expense information according to the claim ratio, obtaining the total claim amount corresponding to the multiple expense information, and marking the total claim amount as the claim amount of the first commercial insurance.

[0094] In a possible example, in determining whether the claim events corresponding to all commercial insurances whose arrangement order is before the i-th commercial insurance restrict the claim events corresponding to the i-th commercial insurance, and if so, obtaining the restriction result, and determining the claim amount of the i-th commercial insurance according to the restriction result, the instructions in the above program are specifically used to perform the following operations: extracting the i-th insurance information of the i-th insurance information from the information page, and determining multiple reimbursement items of the i-th commercial insurance according to the i-th insurance information; extracting the i-th claim rule of the i-th commercial insurance from the insurance information database; and determining the multiple reimbursement items based on the i-th claim rule. The claim amount of the reimbursement item is subject to the i-th claim rule, determine the constraint condition on the claim amount of the reimbursement item, if the constraint condition is that the claim amount of the reimbursement item is subject to the same type of reimbursement items, obtain the reimbursement items of the same type that exist in all commercial insurances whose arrangement order is before the i-th commercial insurance, obtain the total amount of claims paid for the reimbursement items of the same type, determine the first claim amount of the reimbursement item according to the total amount of claims paid, add the claim amounts of other reimbursements in the multiple reimbursement items and the first claim amount to obtain the total claim amount, and mark the total claim amount as the claim amount of the i-th commercial insurance.

[0095] In a possible example, in terms of determining the first claim amount of the reimbursement item based on the total amount reimbursed, the instructions in the above program are specifically used to perform the following operations: if the total amount reimbursed is greater than or equal to the maximum claim amount of the reimbursement item, determine that the first claim amount of the reimbursement item is zero; if the total amount reimbursed is less than the maximum claim amount of the reimbursement item, determine that the first claim amount of the reimbursement item is the difference between the maximum claim amount of the reimbursement item and the total amount reimbursed.

[0096] See also Figure 5 , Figure 5 A possible functional unit composition block diagram of an electronic device 500 for intelligent recommendation involved in the above embodiment is shown, and the electronic device 500 includes a first receiving unit 510, a second receiving unit 520, an arrangement unit 530, a calculation unit 540, and a sending unit 550, wherein;

[0097] The first receiving unit 510 is used to receive an information acquisition request sent by a terminal device, and in response to the information acquisition request, send an information filling page to the terminal device, prompting the terminal device to enter commercial insurance information on the information filling page;

[0098] The second receiving unit 520 is used to receive the information page submitted by the terminal device, extract the commercial insurance information in the information page, and determine the commercial insurance corresponding to the commercial insurance information;

[0099] An arrangement unit 530 is used to arrange the plurality of commercial insurances to obtain a plurality of commercial insurance combinations;

[0100] The calculation unit 540 is used to perform claim calculation on the plurality of commercial insurance combinations, determine the claim amount of each commercial insurance combination, and mark the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination;

[0101] The sending unit 550 is used to send the target commercial insurance combination and prompt information to the terminal device, and the prompt information is used to prompt that the claim reimbursement should be made according to the arrangement order of each commercial insurance in the target commercial insurance combination when making a claim reimbursement.

[0102] In a possible example, when the recommendation device extracts several commercial insurance information from the information page and determines several commercial insurances corresponding to the several commercial insurance information, the second receiving unit 520 is specifically used to: perform text recognition on the information page to obtain a text area of ​​the information page; extract text information in the text area, perform keyword recognition on the text information, obtain multiple keywords that meet preset conditions, and obtain a keyword group; query the insurance information library for multiple commercial insurances that match the keyword group, and mark the multiple commercial insurances as several commercial insurances corresponding to the several commercial insurance information.

[0103] In a possible example, when performing claim calculations on the several commercial insurance combinations and determining the claim amount of each commercial insurance combination, the calculation unit 540 is specifically used to: determine the arrangement order of the several commercial insurances in each commercial insurance combination; calculate the claim amount of each commercial insurance in turn according to the arrangement order of the several commercial insurances in the commercial insurance combination to obtain several claim amounts corresponding to the several commercial insurances, wherein the commercial insurances correspond to the claim amounts one-to-one; add the several claim amounts corresponding to the several commercial insurances to obtain the claim amount of the commercial insurance combination.

[0104] In a possible example, when calculating the claim amount of each commercial insurance in sequence according to the arrangement order of the several commercial insurances in the commercial insurance combination, the calculation unit 540 is specifically used to: perform claim calculation on the first commercial insurance that is ranked first among the several commercial insurances to obtain the claim amount of the first commercial insurance; when performing claim calculation on the claim amount of the i-th commercial insurance that is ranked i-th among the several commercial insurances, determine whether the claim events corresponding to all commercial insurances whose arrangement order is before the i-th commercial insurance restrict the claim event corresponding to the i-th commercial insurance, if so, obtain the restriction result, and determine the claim amount of the i-th commercial insurance according to the restriction result, if not, directly perform claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance, and when the number of the several commercial insurances is N, when i=N, obtain the claim amount of each commercial insurance; wherein, i and N are both integers greater than or equal to 2, and i≤N.

[0105] In a possible example, when performing a claim calculation for the first commercial insurance and obtaining the claim amount of the first commercial insurance, the calculation unit 540 is specifically used to: extract the accident information and the first insurance information corresponding to the first commercial insurance from the information page; extract the first claim rule of the first commercial insurance from the insurance information database; perform settlement verification on the accident information according to the first claim rule, such as extracting various expense information in the accident information through settlement verification, extracting various liability detail information from the insurance information, matching the various expense information with the various liability detail information respectively, obtaining multiple expense information matched in the various expense information, obtaining the claim ratio set in the liability details matching the multiple expense information, determining the claim amount of each expense information in the multiple expense information according to the claim ratio, obtaining the total claim amount corresponding to the multiple expense information, and marking the total claim amount as the claim amount of the first commercial insurance.

[0106] In a possible example, when determining whether the claim events corresponding to all commercial insurances whose arrangement order is before the i-th commercial insurance restrict the claim events corresponding to the i-th commercial insurance, if so, obtaining the restriction result, and determining the claim amount of the i-th commercial insurance according to the restriction result, the calculation unit 540 is specifically used to: extract the i-th insurance information of the i-th insurance information from the information page, and determine multiple reimbursement items of the i-th commercial insurance according to the i-th insurance information; extract the i-th claim rule of the i-th commercial insurance from the insurance information database; determine the reimbursement rules of the multiple reimbursement items based on the i-th claim rule; For the reimbursement item whose claim amount is subject to the i-th claim settlement rule, determine the constraint condition on the claim amount of the reimbursement item; if the constraint condition is that the claim amount of the reimbursement item is subject to the constraint of the same type of reimbursement items, obtain the reimbursement items of the same type that exist in all commercial insurances whose arrangement order is before the i-th commercial insurance, obtain the total amount of claims paid for the reimbursement items of the same type, determine a first claim amount for the reimbursement item based on the total amount of claims paid, add the claim amounts of other reimbursements in the multiple reimbursement items to the first claim amount to obtain the total claim amount, and mark the total claim amount as the claim amount of the i-th commercial insurance.

[0107] In a possible example, when determining the first claim amount of the reimbursement item based on the total amount reimbursed, the calculation unit 540 is specifically used to: if the total amount reimbursed is greater than or equal to the maximum claim amount of the reimbursement item, determine that the first claim amount of the reimbursement item is zero; if the total amount reimbursed is less than the maximum claim amount of the reimbursement item, determine that the first claim amount of the reimbursement item is the difference between the maximum claim amount of the reimbursement item and the total amount reimbursed.

[0108] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the intelligent recommendation methods recorded in the above method embodiments.

[0109] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the intelligent recommendation methods recorded in the above method embodiments.

[0110] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0115] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0116] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0117] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An intelligent recommendation method, characterized in that: The method comprises: The recommendation device receives an information acquisition request sent by a terminal device, responds to the information acquisition request, sends an information filling page to the terminal device, and prompts the terminal device to enter commercial insurance information on the information filling page; The recommendation device receives the information page submitted by the terminal device, extracts a number of commercial insurance information in the information page, and determines a number of commercial insurances corresponding to the number of commercial insurance information; The recommendation device arranges the plurality of commercial insurances to obtain a plurality of commercial insurance combinations; The recommendation device performs claim calculation on the plurality of commercial insurance combinations to determine the claim amount of each commercial insurance combination, including: The recommendation device determines the order of arrangement of the several commercial insurances in each commercial insurance combination; the recommendation device performs claim calculation on the first commercial insurance in the order of arrangement among the several commercial insurances to obtain the claim amount of the first commercial insurance; when performing claim calculation on the claim amount of the i-th commercial insurance in the order of arrangement among the several commercial insurances, the recommendation device determines whether the claim events corresponding to all commercial insurances in the order of arrangement before the i-th commercial insurance restrict the claim event corresponding to the i-th commercial insurance, if so, obtains the restriction result, and determines the claim amount of the i-th commercial insurance according to the restriction result; if not, directly performs claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance, and when the number of the several commercial insurances is N, when i=N, obtains the claim amount of each commercial insurance; wherein, i and N are both integers greater than or equal to 2, and i≤N; the recommendation device adds the several claim amounts corresponding to the several commercial insurances to obtain the claim amount of the commercial insurance combination; The performing claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance includes: Extracting accident information and first insurance information corresponding to the first commercial insurance from the information page; extracting first claim settlement rules of the first commercial insurance from the insurance information database; Performing settlement verification on the accident information according to the first claim settlement rule, such as extracting various expense information from the accident information through settlement verification, extracting various liability detail information from the insurance information, matching the various expense information with the various liability detail information respectively, obtaining multiple expense information matched in the various expense information, obtaining the claim settlement ratio set in the liability details matched with the multiple expense information, determining the claim settlement amount of each expense information in the multiple expense information according to the claim settlement ratio, obtaining the total claim settlement amount corresponding to the multiple expense information, and marking the total claim settlement amount as the claim settlement amount of the first commercial insurance; Mark the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination; The recommendation device sends the target commercial insurance combination and prompt information to the terminal device, and the prompt information is used to prompt that claims and reimbursements should be made according to the arrangement order of each commercial insurance in the target commercial insurance combination when claims and reimbursements are made.

2. The method according to claim 1, characterized in that The recommendation device extracts a plurality of commercial insurance information from the information page, and determines that a plurality of commercial insurances corresponding to the plurality of commercial insurance information specifically include: The recommendation device performs text recognition on the information page to obtain a text area of ​​the information page; The recommendation device extracts text information in the text area, performs keyword recognition on the text information, obtains multiple keywords that meet preset conditions, and obtains a keyword group; The recommendation device searches the insurance information database for multiple commercial insurances that match the keyword group, and marks the multiple commercial insurances as multiple commercial insurances corresponding to the multiple commercial insurance information.

3. The method according to claim 1, characterized in that The recommendation device determines whether the claim events corresponding to all commercial insurances arranged before the i-th commercial insurance restrict the claim event corresponding to the i-th commercial insurance, and if so, obtains the restriction result, and determines the claim amount of the i-th commercial insurance according to the restriction result, specifically including: The recommendation device extracts the i-th insurance information of the i-th commercial insurance from the information page, and determines a plurality of reimbursement items of the i-th commercial insurance according to the i-th insurance information; The recommendation device extracts the i-th claim settlement rule of the i-th commercial insurance from the insurance information database; The recommendation device determines, based on the i-th claim rule, the reimbursement items whose claim amounts of the multiple reimbursement items are subject to the i-th claim rule, determines the constraint condition on the claim amount of the reimbursement item, if the constraint condition is that the claim amount of the reimbursement item is subject to the same type of reimbursement items, obtains the reimbursement items of the same type that exist in all commercial insurances whose arrangement order is before the i-th commercial insurance, obtains the total amount of claims paid for the reimbursement items of the same type, determines a first claim amount for the reimbursement item based on the total amount of claims paid, adds the claim amounts of other reimbursements in the multiple reimbursement items to the first claim amount to obtain a total claim amount, and marks the total claim amount as the claim amount of the i-th commercial insurance.

4. The method according to claim 3, characterized in that The recommendation device determines the first claim amount of the reimbursement item according to the total amount of claims paid, specifically including: If the total amount of claims paid is greater than or equal to the maximum claim amount of the reimbursement item, the recommendation device determines that the first claim amount of the reimbursement item is zero; If the total amount of claims settled is less than the maximum claim amount of the reimbursement item, the recommendation device determines that the first claim amount of the reimbursement item is the difference between the maximum claim amount of the reimbursement item and the total amount of claims settled.

5. A recommendation device for intelligent recommendation, characterized in that: The recommended devices include: A first receiving unit is used to receive an information acquisition request sent by a terminal device, and in response to the information acquisition request, send an information filling page to the terminal device, prompting the terminal device to enter commercial insurance information in the information filling page; A second receiving unit is used to receive the information page submitted by the terminal device, extract the commercial insurance information in the information page, and determine the commercial insurance corresponding to the commercial insurance information; An arrangement unit, used for arranging the plurality of commercial insurances to obtain a plurality of commercial insurance combinations; A calculation unit, used to perform claim calculation on the plurality of commercial insurance combinations to determine the claim amount of each commercial insurance combination, including: The recommendation device determines the order of arrangement of the several commercial insurances in each commercial insurance combination; the recommendation device performs claim calculation on the first commercial insurance in the order of arrangement among the several commercial insurances to obtain the claim amount of the first commercial insurance; when performing claim calculation on the claim amount of the i-th commercial insurance in the order of arrangement among the several commercial insurances, the recommendation device determines whether the claim events corresponding to all commercial insurances in the order of arrangement before the i-th commercial insurance restrict the claim event corresponding to the i-th commercial insurance, if so, obtains the restriction result, and determines the claim amount of the i-th commercial insurance according to the restriction result; if not, directly performs claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance, and when the number of the several commercial insurances is N, when i=N, obtains the claim amount of each commercial insurance; wherein, i and N are both integers greater than or equal to 2, and i≤N; the recommendation device adds the several claim amounts corresponding to the several commercial insurances to obtain the claim amount of the commercial insurance combination; The performing claim calculation on the first commercial insurance to obtain the claim amount of the first commercial insurance includes: Extracting accident information and first insurance information corresponding to the first commercial insurance from the information page; extracting first claim settlement rules of the first commercial insurance from the insurance information database; Performing settlement verification on the accident information according to the first claim settlement rule, such as extracting various expense information from the accident information through settlement verification, extracting various liability detail information from the insurance information, matching the various expense information with the various liability detail information respectively, obtaining multiple expense information matched in the various expense information, obtaining the claim settlement ratio set in the liability details matched with the multiple expense information, determining the claim settlement amount of each expense information in the multiple expense information according to the claim settlement ratio, obtaining the total claim settlement amount corresponding to the multiple expense information, and marking the total claim settlement amount as the claim settlement amount of the first commercial insurance; Mark the commercial insurance combination corresponding to the maximum claim amount as the target commercial insurance combination; A sending unit is used to send the target commercial insurance combination and prompt information to the terminal device, and the prompt information is used to prompt that the claim reimbursement should be made according to the arrangement order of each commercial insurance in the target commercial insurance combination when making a claim reimbursement.

6. A recommendation device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in any one of the methods of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: It is used to store a computer program, wherein the computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

Images