Family asset configuration strategy generation method and device, medium and terminal

Abstract

The invention discloses a household asset configuration strategy generation method and device, a medium and a terminal, relates to the technical field of artificial intelligence and the field of finance, and mainly aims to solve the problem that the configuration strategy of household assets cannot be generated due to high dependence on own experience and professional knowledge of agents and relatively high subjectivity in the prior art. Due to the fact that manual carding and analysis are completely depended on agents, the workload is huge, a large amount of time needs to be consumed, and the labor cost is high. Comprising the following steps: acquiring total asset information of a target family; calculating the asset balance of the target family based on the total asset information; dividing each piece of asset information into a corresponding asset category group, and calculating the ratio of the asset value of each asset category group to the total asset value of the total amount of asset information to obtain the current family asset ratio of the target family; and according to the asset balance, adjusting the current family asset proportion based on a preset family asset proportion rule, and generating a family asset allocation strategy of the target family.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology and the financial field, and in particular to a method and device, medium, and terminal for generating a family asset allocation strategy. Background Art

[0002] With the rapid growth of the national economy and the continuous improvement of residents' income levels, the scale of family wealth continues to expand, and traditional asset management methods are facing a series of challenges and demands. In traditional asset management, asset allocation decisions based on the family unit usually require professional agents to first help all family members recall their assets one by one, then conduct financial sorting, and finally conduct asset allocation analysis for the family based on the sorting results and the agent's own experience and professional knowledge. However, due to the high reliance on the agent's own experience and professional knowledge, it is highly subjective and can easily lead to poor reliability of asset allocation results; at the same time, due to the complete reliance on agents for manual sorting and analysis, the workload is huge and takes a lot of time, resulting in high labor costs. Summary of the invention

[0003] In view of this, the present application provides a method and device, medium, and terminal for generating a family asset allocation strategy. The main purpose is to solve the problem that the existing asset allocation results are highly reliable due to the high reliance on the agent's own experience and professional knowledge, which is highly subjective and easily leads to poor reliability, and the manual sorting and analysis by the agent is completely dependent on the huge workload and takes a lot of time, resulting in high labor costs.

[0004] According to one aspect of the present application, a method for generating a family asset allocation strategy is provided, comprising:

[0005] Acquire the full asset information of the target family, wherein the full asset information includes multiple asset information, and the asset information is identified from the asset voucher image based on the image information recognition model, and / or is extracted from the voice information of each family member based on the voice information extraction model, wherein the image information recognition model is used to identify the asset information in the asset voucher image, and the voice information extraction model is used to extract the asset information from the voice information of the family members;

[0006] Calculating the asset balance of the target family based on the full asset information;

[0007] Divide each of the asset information into corresponding asset category groups, and calculate the proportion of the asset value of each of the asset category groups to the total asset value of the full amount of asset information to obtain the current family asset ratio of the target family;

[0008] According to the asset balance, based on a preset family asset allocation rule, the current family asset allocation is adjusted to generate a family asset allocation strategy for the target family.

[0009] Preferably, the image information recognition model includes an optical character recognition sub-model and a text recognition sub-model, and the step of obtaining the full asset information of the target family includes:

[0010] Obtain images of each asset certificate of the target family;

[0011] Taking each of the asset credential images as a target asset credential image;

[0012] Extracting the text contained in the target asset voucher image based on the optical character recognition sub-model and converting it into a text format to obtain the text information contained in the target asset voucher image;

[0013] Recognize the text information based on the text recognition sub-model, and extract the asset information contained in the target asset voucher image from the text information;

[0014] The asset information in each target asset voucher image is integrated to obtain the full asset information of the target family.

[0015] Preferably, the voice information extraction model includes a voice-to-text sub-model and an information recognition sub-model, and the acquisition of the full asset information of the target family includes:

[0016] Get voice messages from each family member;

[0017] Taking each of the voice information as target voice information one by one;

[0018] Converting the target voice information into a text format based on the voice-to-text sub-model to obtain text information contained in the target voice information;

[0019] Based on the information recognition sub-model, the text information is sequentially subjected to text classification processing, named entity recognition processing, and relationship extraction processing to obtain the asset information contained in the target voice information;

[0020] The asset information in each target voice message is integrated to obtain the full asset information of the target family.

[0021] Preferably, the dividing each asset information into corresponding asset category groups includes:

[0022] According to the multiple quadrants included in the Standard & Poor's chart, a corresponding rule base is configured, wherein the rule base corresponds to the asset category group and is used to store the mapping relationship between the asset category and the asset information thereof;

[0023] Taking each of the asset information as target asset information one by one;

[0024] Matching the target asset information with the asset information in the rule base, determining the asset category of the target asset information, and classifying the target asset information into corresponding asset category groups;

[0025] Each of the target asset information is divided into corresponding asset category groups.

[0026] Preferably, the step of classifying each asset information into corresponding asset category groups further includes:

[0027] Inputting the target asset information into a preset asset information classification model to determine a reference asset category of the target asset information;

[0028] If the reference asset category is consistent with the asset category determined according to the rule base, the current classification result of the target asset information is maintained;

[0029] If the reference asset category is inconsistent with the asset category determined according to the rule base, a prompt message for manual intervention verification is output to prompt manual intervention verification.

[0030] Preferably, according to the asset balance, based on a preset family asset allocation rule, the current family asset allocation ratio is adjusted to obtain the family asset allocation strategy of the target family, including:

[0031] If the asset balance is less than the first balance threshold, obtaining a first family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the first family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0032] If the asset balance is greater than or equal to the first balance threshold and less than the second balance threshold, obtaining a second family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the second family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0033] If the asset balance is greater than or equal to the second balance threshold and less than the third balance threshold, obtaining a third family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the third family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0034] If the asset balance is greater than or equal to the third balance threshold, a fourth family asset allocation rule is obtained, and the current family asset allocation is adjusted to the family asset allocation in the fourth family asset allocation rule to generate a family asset allocation strategy for the target family.

[0035] Preferably, the asset categories include liquid asset categories, defensive asset categories, stable asset categories, and offensive asset categories.

[0036] According to another aspect of the present application, a device for generating a configuration strategy for family assets is provided, comprising:

[0037] An asset information acquisition module, used to acquire the full asset information of the target family, wherein the full asset information includes multiple asset information, and the asset information is identified from the asset voucher image based on an image information recognition model, and / or extracted from the voice information of each family member based on a voice information extraction model, wherein the image information recognition model is used to identify the asset information in the asset voucher image, and the voice information extraction model is used to extract the asset information from the voice information of the family members;

[0038] An asset balance calculation module, used to calculate the asset balance of the target family based on the full asset information;

[0039] An asset information division module is used to divide each asset information into corresponding asset category groups, and calculate the proportion of the asset value of each asset category group to the total asset value of the full asset information, so as to obtain the current family asset ratio of the target family;

[0040] The family asset allocation strategy generating module is used to adjust the current family asset allocation ratio according to the asset balance and based on the preset family asset allocation rule to generate the family asset allocation strategy of the target family.

[0041] Preferably, the image information recognition model includes an optical character recognition sub-model and a text recognition sub-model, and the asset information acquisition module is used to:

[0042] Obtain images of each asset certificate of the target family;

[0043] Taking each of the asset credential images as a target asset credential image;

[0044] Extracting the text contained in the target asset voucher image based on the optical character recognition sub-model and converting it into a text format to obtain the text information contained in the target asset voucher image;

[0045] Recognize the text information based on the text recognition sub-model, and extract the asset information contained in the target asset voucher image from the text information;

[0046] The asset information in each target asset voucher image is integrated to obtain the full asset information of the target family.

[0047] Preferably, the speech information extraction model includes a speech-to-text sub-model and an information recognition sub-model, and the asset information acquisition module is further used to:

[0048] Get voice messages from each family member;

[0049] Taking each of the voice information as target voice information one by one;

[0050] Converting the target voice information into a text format based on the voice-to-text sub-model to obtain text information contained in the target voice information;

[0051] Based on the information recognition sub-model, the text information is sequentially subjected to text classification processing, named entity recognition processing, and relationship extraction processing to obtain the asset information contained in the target voice information;

[0052] The asset information in each target voice message is integrated to obtain the full asset information of the target family.

[0053] Preferably, the asset information partitioning module is used to:

[0054] According to the multiple quadrants included in the Standard & Poor's chart, a corresponding rule base is configured, wherein the rule base corresponds to the asset category group and is used to store the mapping relationship between the asset category and the asset information thereof;

[0055] Taking each of the asset information as target asset information one by one;

[0056] Matching the target asset information with the asset information in the rule base, determining the asset category of the target asset information, and classifying the target asset information into corresponding asset category groups;

[0057] Each of the target asset information is divided into corresponding asset category groups.

[0058] Preferably, the asset information partitioning module is further used to:

[0059] Inputting the target asset information into a preset asset information classification model to determine a reference asset category of the target asset information;

[0060] If the reference asset category is consistent with the asset category determined according to the rule base, the current classification result of the target asset information is maintained;

[0061] If the reference asset category is inconsistent with the asset category determined according to the rule base, a prompt message for manual intervention verification is output to prompt manual intervention verification.

[0062] Preferably, the family asset allocation strategy generation module is used to:

[0063] If the asset balance is less than the first balance threshold, obtaining a first family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the first family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0064] If the asset balance is greater than or equal to the first balance threshold and less than the second balance threshold, obtaining a second family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the second family asset allocation rule to generate a family asset allocation strategy for the target family;

[0065] If the asset balance is greater than or equal to the second balance threshold and less than the third balance threshold, obtaining a third family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the third family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0066] If the asset balance is greater than or equal to the third balance threshold, a fourth family asset allocation rule is obtained, and the current family asset allocation is adjusted to the family asset allocation in the fourth family asset allocation rule to generate a family asset allocation strategy for the target family.

[0067] Preferably, the asset categories include liquid asset categories, defensive asset categories, stable asset categories, and offensive asset categories.

[0068] According to another aspect of the present application, a storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned method for generating a configuration strategy for home assets.

[0069] According to another aspect of the present application, a terminal is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;

[0070] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned method for generating a configuration strategy for family assets.

[0071] By means of the above technical solution, the technical solution provided by the embodiment of the present application has at least the following advantages:

[0072] The present application provides a method and device, medium, and terminal for generating a family asset allocation strategy. First, the full asset information of a target family is obtained, the full asset information includes multiple asset information, the asset information is identified from an asset certificate image based on an image information recognition model, and / or extracted from voice information of each family member based on a voice information extraction model, the image information recognition model is used to identify and process the asset information in the asset certificate image, and the voice information extraction model is used to extract and process the asset information from the voice information of the family members; secondly, the asset balance of the target family is calculated based on the full asset information; again, each of the asset information is divided into corresponding asset category groups, and the asset value of each of the asset category groups is calculated to account for the proportion of the total asset value of the full asset information, so as to obtain the current family asset ratio of the target family; finally, according to the asset balance, based on a preset family asset ratio rule, the current family asset ratio is adjusted to generate a family asset allocation strategy for the target family. Compared with the prior art, the embodiment of the present application utilizes an image information recognition model to recognize asset certificate images and utilizes a voice information extraction model to extract voice information from each family member to obtain the full asset information of the target family. Compared with manual sorting, it saves a lot of time, reduces labor costs, and improves efficiency, while avoiding the omission of asset information that may occur during manual sorting; further, based on the asset balance of the target family and the preset family asset allocation rules, a family asset allocation strategy is generated, which avoids reliance on the agent's own experience and expertise, reduces the influence of human subjectivity, and improves the reliability of the family asset allocation strategy.

[0073] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0075] Figure 1A flow chart of a method for generating a configuration strategy for family assets provided in an embodiment of the present application is shown;

[0076] Figure 2 A flowchart of asset information identification provided by an embodiment of the present application is shown;

[0077] Figure 3 Another asset information identification flow chart provided by an embodiment of the present application is shown;

[0078] Figure 4 The asset information division flow chart provided in the embodiment of the present application is shown;

[0079] Figure 5 A block diagram of a device for generating a configuration strategy for household assets provided in an embodiment of the present application is shown;

[0080] Figure 6 A schematic diagram of the structure of a terminal provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0081] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0082] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0083] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0084] Based on this, in one embodiment, Figure 1As shown, a method for generating a configuration strategy for household assets is provided, and the method is applied to a computer device such as a server as an example for explanation, wherein the server can be an independent server, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, such as smart medical systems, digital medical platforms, etc. The above method includes the following steps:

[0085] 101. Obtain the complete asset information of the target family.

[0086] Among them, the full asset information includes multiple asset information, including but not limited to bank statements, consumption records, financial investments, transaction records, collectible photos, insurance, real estate, car properties, overseas assets, etc.; the asset information is identified from the asset certificate image based on the image information recognition model, and the asset certificate image includes but is not limited to bank statements, consumption records, financial investments, transaction records, collectible photos and other pictures, and / or, extracted from the voice information of each family member based on the voice information extraction model, and the voice information is used to characterize the customer's oral voice, including but not limited to oral information for insurance, real estate, car properties, overseas assets, etc.; the image information recognition model is used to identify and process the asset information in the asset certificate image; the voice information extraction model is used to extract and process the asset information from the voice information of family members. In an embodiment of the present application, the current execution end can be a generation module of the family asset allocation strategy of the financial platform, which is used to generate a family asset allocation strategy based on the family's asset balance.

[0087] It should be noted that in the embodiment of the present application, the image information recognition model is used to recognize the asset certificate image, and the voice information extraction model is used to extract the voice information of each family member to obtain the full asset information of the target family. Compared with manual sorting, it saves a lot of time, reduces labor costs and improves efficiency.

[0088] 102. Calculate the target family’s asset balance based on the full asset information.

[0089] Among them, the asset balance is used to represent the difference between the family's income and expenditure over a period of time, such as a year, quarter, month, etc.; the family's income includes but is not limited to the husband's annual income, the wife's annual income, bonuses, dividends, sideline income, rental income, insurance annuity income, financial investment income, etc.; the family's expenditure includes but is not limited to living expenses, housing loans, support for the elderly, children's education, personal pension, etc. In the embodiment of the present application, the total income and total expenditure of the family can be determined from the full asset information obtained in step 101 of the embodiment, and the difference is determined as the asset balance.

[0090] 103. Classify each asset information into a corresponding asset category group, and calculate the ratio of the asset value of each asset category group to the total asset value of the entire asset information to obtain the current household asset ratio of the target household.

[0091] Among them, asset categories include liquid asset categories, defensive asset categories, stable asset categories, and offensive asset categories; asset information of liquid asset categories includes but is not limited to bank current accounts, cash, money funds, etc.; asset information of defensive asset categories includes but is not limited to social security personal accounts, medical insurance coverage, critical illness insurance coverage, life insurance coverage, etc.; asset information of stable asset categories includes but is not limited to real estate, time deposits, government bonds, index investments, annuity insurance, parking spaces, etc.; asset information of offensive asset categories includes but is not limited to stocks, funds, foreign exchange, artworks, commodity futures, etc.

[0092] It should be noted that asset information can be divided into asset categories according to preset rules. For example, the configuration rules indicate that asset information of the current asset category can include bank current accounts, cash, money funds, etc., then according to the rules, the identified bank current asset information can be divided into the current asset category group; a pre-trained classification model can also be used to divide assets into categories, which is not specifically limited in the embodiments of the present application.

[0093] 104. According to the asset balance and based on the preset family asset allocation rules, the current family asset allocation is adjusted to generate the family asset allocation strategy for the target family.

[0094] Among them, the preferred family asset ratio is recorded in the family asset allocation rule, for example, asset information of the current asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 2:7:1, asset information of the current asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 1:5:4, etc. Since families with different asset balances have different allocation ratios for family assets, for example, high-income families can appropriately increase their investment in offensive assets due to more disposable assets, while families with lower family incomes can reduce their investment in offensive assets due to the need to prioritize stability. Based on this, in the embodiment of the present application, according to the asset balance of the target family, an adaptive family asset ratio is selected to generate a family asset allocation strategy for the target family, which can make the family asset allocation strategy more reliable.

[0095] Compared with the prior art, the embodiment of the present application utilizes an image information recognition model to recognize asset certificate images and utilizes a voice information extraction model to extract voice information from each family member to obtain the full asset information of the target family. Compared with manual sorting, it saves a lot of time, reduces labor costs, and improves efficiency, while avoiding the omission of asset information that may occur during manual sorting; further, based on the asset balance of the target family and the preset family asset allocation rules, a family asset allocation strategy is generated, which avoids reliance on the agent's own experience and expertise, reduces the influence of human subjectivity, and improves the reliability of the family asset allocation strategy.

[0096] In an embodiment of the present application, in order to further define and illustrate, Figure 2 As shown, when asset information is recognized from an asset voucher image based on an image information recognition model, the image information recognition model includes an optical character recognition sub-model and a text recognition sub-model. Step 101 of the embodiment obtains the full amount of asset information of the target family, including:

[0097] 201. Obtain each asset certificate image of the target family; and use each asset certificate image as a target asset certificate image one by one.

[0098] In an embodiment of the present application, all asset certificate images such as bank statements, consumption records, financial investments, transaction records, and collectibles photos owned by the target family are obtained, and all asset certificate images are used as target asset certificate images one by one, that is, as objects for asset information identification.

[0099] 202. Extract the text contained in the target asset certificate image based on the optical character recognition sub-model and convert it into a text format to obtain the text information contained in the target asset certificate image.

[0100] Among them, the optical character recognition sub-model is built based on optical character recognition technology, which can be used to extract the text information contained in the asset certificate image and convert it into text format.

[0101] 203. Recognize the text information based on the text recognition sub-model, and extract the asset information contained in the target asset voucher image from the text information.

[0102] The text recognition sub-model is constructed based on a machine learning model such as a convolutional neural network or a recurrent neural network, and is used to recognize the text information extracted in step 202 of the embodiment and extract asset information therefrom. Specifically, asset information such as date, transaction amount, account information, etc. can be extracted from bank statements and consumption records; asset information such as investment amount, rate of return, transaction date, etc. can be extracted from financial investments and transaction records; asset information such as artwork name, author, creation year, etc. can be extracted from collectible photos.

[0103] 204. Integrate the asset information in each target asset voucher image to obtain the full asset information of the target family.

[0104] In the embodiment of the present application, the asset information in each target asset voucher image is integrated, that is, the asset information extracted from all asset voucher images owned by the target family is integrated, that is, the full asset information of the family is obtained.

[0105] In an embodiment of the present application, in order to further define and illustrate, Figure 3 As shown, when asset information is extracted from the voice information of each family member based on the voice information extraction model, the voice information extraction model includes a voice-to-text sub-model and an information recognition sub-model. In the embodiment, step 101 obtains the full amount of asset information of the target family, including

[0106] 301. Acquire voice information of each family member; and use each voice information as target voice information one by one.

[0107] In an embodiment of the present application, all voice information of each family member of the target family is obtained, and the voice information is oral information regarding insurance, real estate, car property, overseas assets, etc., and all voice information is used as target voice information one by one, that is, the object for asset information extraction.

[0108] 302. Convert the target voice information into a text format based on the voice-to-text sub-model to obtain text information contained in the target voice information.

[0109] Among them, the speech-to-text sub-model is built based on the speech recognition engine and can be used to convert speech information into text format to obtain the text information contained in the speech information.

[0110] 303. Based on the information recognition sub-model, text classification processing, named entity recognition processing, and relationship extraction processing are performed on the text information in sequence to obtain the asset information contained in the target voice information.

[0111] Among them, the information recognition sub-model is constructed based on the pre-trained NLP model, and is used to perform semantic understanding on the text information obtained in step 303 of the embodiment. Specifically, the text information is first classified into categories such as insurance, real estate, automobile property, overseas assets, etc.; then key entities such as names of people, places, names of institutions, asset types, amounts, etc. are identified from the text information; and the relationship between entities is extracted from the text information, such as the owner of the real estate, the beneficiary of the insurance, the purchase date of the automobile property, etc.; finally, the above text classification processing results, named entity recognition processing results, and relationship extraction processing results are integrated to obtain the asset information contained in the target voice information.

[0112] 304. Integrate the asset information in each target voice message to obtain the full asset information of the target family.

[0113] In an embodiment of the present application, the asset information in each target voice message is integrated, that is, the asset information extracted from all voice messages of each family member of the target family is integrated, that is, the full asset information of the family is obtained.

[0114] In an embodiment of the present application, in order to further define and illustrate, Figure 4 As shown, in step 103 of the embodiment, each asset information is divided into corresponding asset category groups, including:

[0115] 401. According to the multiple quadrants included in the Standard & Poor's chart, configure the corresponding rule base.

[0116] Among them, the Standard & Poor's chart contains multiple quadrants, such as the liquid asset quadrant, the defensive asset quadrant, the stable asset quadrant, and the offensive asset quadrant. A corresponding rule base is configured for each quadrant, such as the liquid asset rule base, the defensive asset rule base, the stable asset rule base, and the offensive asset rule base. Each rule base corresponds to an asset category group, such as the liquid asset rule base corresponds to the liquid asset category group, the defensive asset rule base corresponds to the defensive asset category group, the stable asset rule base corresponds to the stable asset category group, and the offensive asset rule base corresponds to the offensive asset category group. Each rule base stores the mapping relationship between the asset category and the asset information to which it belongs. For example, the asset information of the liquid asset category includes bank current, cash, money funds, etc.; the asset information of the defensive asset category includes social security personal accounts, medical insurance coverage, critical illness insurance coverage, life insurance coverage, etc.; the asset information of the stable asset category includes real estate, time deposits, government bonds, index fixed investment, annuity insurance, parking spaces, etc.; the asset information of the offensive asset category includes stocks, funds, foreign exchange, artworks, commodity futures, etc.

[0117] 402. Take each piece of asset information as target asset information one by one.

[0118] In the embodiment of the present application, all the asset information extracted as above is used as target asset information one by one, that is, the object for asset category classification.

[0119] 403. Match the target asset information with the asset information in the rule base, determine the asset category of the target asset information, and classify the target asset information into corresponding asset category groups.

[0120] Exemplarily, the target asset information is stocks. According to the asset information of the offensive asset category stored in the offensive asset rule base, including stocks, funds, foreign exchange, artworks, commodity futures, etc., it can be known that stocks belong to the offensive asset category and can be classified into the offensive asset category group.

[0121] 404. Input the target asset information into a preset asset information classification model to determine a reference asset category of the target asset information.

[0122] Among them, the asset information classification model can be constructed based on a machine learning algorithm with classification function, and is used to classify the target asset information, so as to verify the asset category determined according to the rule base in step 403 of the embodiment according to the classification result; the control asset category is used to characterize the asset category obtained by classifying the target asset information based on the asset information classification model.

[0123] 405a. If the reference asset category is consistent with the asset category determined according to the rule base, the current classification result of the target asset information is maintained.

[0124] 405b. If the comparison asset category is inconsistent with the asset category determined according to the rule base, a prompt message for manual intervention verification is output to prompt manual intervention verification.

[0125] Steps 405a and 405b of the embodiment are possible results of verifying the asset category determined according to the rule base in step 403 of the embodiment.

[0126] 406. Classify each target asset information into corresponding asset category groups.

[0127] In the embodiment of the present application, according to the steps described in steps 401-405b of the embodiment, all asset information is divided into corresponding asset category groups.

[0128] In one embodiment of the present application, for further limitation and explanation, the embodiment step 104 adjusts the current family asset ratio according to the asset balance based on the preset family asset ratio rule to generate a family asset allocation strategy for the target family, including: if the asset balance is less than the first balance threshold, obtain the first family asset ratio rule, and adjust the current family asset ratio to the family asset ratio in the first family asset ratio rule to generate the family asset allocation strategy for the target family; if the asset balance is greater than or equal to the first balance threshold and less than the second balance threshold, obtain the second family asset ratio rule, and adjust the current family asset ratio to the family asset ratio in the first family asset ratio rule to generate the family asset allocation strategy for the target family. The ratio is adjusted to the family asset ratio in the second family asset ratio rule to generate a family asset allocation strategy for the target family; if the asset balance is greater than or equal to the second balance threshold and less than the third balance threshold, the third family asset ratio rule is obtained, and the current family asset ratio is adjusted to the family asset ratio in the third family asset ratio rule to generate a family asset allocation strategy for the target family; if the asset balance is greater than or equal to the third balance threshold, the fourth family asset ratio rule is obtained, and the current family asset ratio is adjusted to the family asset ratio in the fourth family asset ratio rule to generate a family asset allocation strategy for the target family.

[0129] Exemplarily, the first balance threshold is 200,000 yuan, the second balance threshold is 1 million yuan, and the third balance threshold is 10 million yuan. The family asset ratio in the first family asset ratio rule is asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 3:7:0. The family asset ratio in the second family asset ratio rule is asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 2:7:1. The family asset ratio in the third family asset ratio rule is asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 1:7:2. The family asset ratio in the fourth family asset ratio rule is asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 1:5:4.

[0130] Based on this, when the asset balance is less than 200,000, the current family asset ratio will be adjusted to asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 3:7:0; when the asset balance is greater than or equal to 200,000 and less than 1 million, the current family asset ratio will be adjusted to asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 2:7:1; when the asset balance is greater than or equal to 1 million and less than 10 million, the current family asset ratio will be adjusted to asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 1:7:2; when the asset balance is greater than or equal to 1 million, the current family asset ratio will be adjusted to asset information of the liquid asset category + asset information of the defensive asset category: asset information of the stability asset category: asset information of the offensive asset category = 1:5:4.

[0131] The present application provides a method for generating a family asset allocation strategy, firstly obtaining the full asset information of a target family, wherein the full asset information includes multiple asset information, the asset information is identified from an asset voucher image based on an image information recognition model, and / or extracted from voice information of each family member based on a voice information extraction model, wherein the image information recognition model is used to identify and process the asset information in the asset voucher image, and the voice information extraction model is used to extract and process the asset information from the voice information of the family members; secondly calculating the asset balance of the target family based on the full asset information; thirdly dividing each asset information into corresponding asset category groups, and calculating the proportion of the asset value of each asset category group to the total asset value of the full asset information, to obtain the current family asset ratio of the target family; finally, according to the asset balance and based on a preset family asset ratio rule, adjusting the current family asset ratio to generate a family asset allocation strategy for the target family. Compared with the prior art, the embodiment of the present application utilizes an image information recognition model to recognize asset certificate images and utilizes a voice information extraction model to extract voice information from each family member to obtain the full asset information of the target family. Compared with manual sorting, it saves a lot of time, reduces labor costs, and improves efficiency, while avoiding the omission of asset information that may occur during manual sorting; further, based on the asset balance of the target family and the preset family asset allocation rules, a family asset allocation strategy is generated, which avoids reliance on the agent's own experience and expertise, reduces the influence of human subjectivity, and improves the reliability of the family asset allocation strategy.

[0132] Furthermore, as a response to the above Figure 1 The implementation of the method shown in the figure, the embodiment of the present application provides a device for generating a configuration strategy for family assets, such as Figure 5 As shown, the device comprises:

[0133] Asset information acquisition module 51, asset balance calculation module 52, asset information division module 53, family asset allocation strategy generation module 54;

[0134] The asset information acquisition module 51 is used to acquire the full asset information of the target family, wherein the full asset information includes multiple asset information, and the asset information is obtained by identifying the asset voucher image based on the image information recognition model, and / or is extracted from the voice information of each family member based on the voice information extraction model, wherein the image information recognition model is used to identify the asset information in the asset voucher image, and the voice information extraction model is used to extract the asset information from the voice information of the family members;

[0135] An asset balance calculation module 52, configured to calculate the asset balance of the target family based on the full asset information;

[0136] The asset information division module 53 is used to divide each of the asset information into corresponding asset category groups, and calculate the proportion of the asset value of each of the asset category groups to the total asset value of the full amount of asset information, so as to obtain the current family asset ratio of the target family;

[0137] The family asset allocation strategy generating module 54 is used to adjust the current family asset allocation ratio according to the asset balance and based on a preset family asset allocation rule to generate a family asset allocation strategy for the target family.

[0138] In a specific application scenario, the image information recognition model includes an optical character recognition sub-model and a text recognition sub-model, and the asset information acquisition module is used to:

[0139] Obtain images of each asset certificate of the target family;

[0140] Taking each of the asset credential images as a target asset credential image;

[0141] Extracting the text contained in the target asset voucher image based on the optical character recognition sub-model and converting it into a text format to obtain the text information contained in the target asset voucher image;

[0142] Recognize the text information based on the text recognition sub-model, and extract the asset information contained in the target asset voucher image from the text information;

[0143] The asset information in each target asset voucher image is integrated to obtain the full asset information of the target family.

[0144] In a specific application scenario, the speech information extraction model includes a speech-to-text sub-model and an information recognition sub-model, and the asset information acquisition module is further used to:

[0145] Get voice messages from each family member;

[0146] Taking each of the voice information as target voice information one by one;

[0147] Converting the target voice information into a text format based on the voice-to-text sub-model to obtain text information contained in the target voice information;

[0148] Based on the information recognition sub-model, the text information is sequentially subjected to text classification processing, named entity recognition processing, and relationship extraction processing to obtain the asset information contained in the target voice information;

[0149] The asset information in each target voice message is integrated to obtain the full asset information of the target family.

[0150] In a specific application scenario, the asset information partitioning module is used to:

[0151] According to the multiple quadrants included in the Standard & Poor's chart, a corresponding rule base is configured, wherein the rule base corresponds to the asset category group and is used to store the mapping relationship between the asset category and the asset information thereof;

[0152] Taking each of the asset information as target asset information one by one;

[0153] Matching the target asset information with the asset information in the rule base, determining the asset category of the target asset information, and classifying the target asset information into corresponding asset category groups;

[0154] Each of the target asset information is divided into corresponding asset category groups.

[0155] In a specific application scenario, the asset information partitioning module is also used to:

[0156] Inputting the target asset information into a preset asset information classification model to determine a reference asset category of the target asset information;

[0157] If the reference asset category is consistent with the asset category determined according to the rule base, the current classification result of the target asset information is maintained;

[0158] If the reference asset category is inconsistent with the asset category determined according to the rule base, a prompt message for manual intervention verification is output to prompt manual intervention verification.

[0159] In specific application scenarios, the family asset allocation strategy generation module is used to:

[0160] If the asset balance is less than the first balance threshold, obtaining a first family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the first family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0161] If the asset balance is greater than or equal to the first balance threshold and less than the second balance threshold, obtaining a second family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the second family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0162] If the asset balance is greater than or equal to the second balance threshold and less than the third balance threshold, obtaining a third family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the third family asset allocation rule, so as to generate a family asset allocation strategy for the target family;

[0163] If the asset balance is greater than or equal to the third balance threshold, a fourth family asset allocation rule is obtained, and the current family asset allocation is adjusted to the family asset allocation in the fourth family asset allocation rule to generate a family asset allocation strategy for the target family.

[0164] In a specific application scenario, the asset categories include liquid asset categories, defensive asset categories, stable asset categories, and offensive asset categories.

[0165] The present application provides a device for generating a family asset allocation strategy, which first obtains the full asset information of a target family, wherein the full asset information includes multiple asset information, and the asset information is identified from an asset certificate image based on an image information recognition model, and / or extracted from voice information of each family member based on a voice information extraction model, wherein the image information recognition model is used to identify and process the asset information in the asset certificate image, and the voice information extraction model is used to extract and process the asset information from the voice information of the family members; secondly, the asset balance of the target family is calculated based on the full asset information; again, each of the asset information is divided into a corresponding asset category group, and the asset value of each of the asset category groups is calculated to account for the proportion of the total asset value of the full asset information, so as to obtain the current family asset ratio of the target family; finally, according to the asset balance, based on a preset family asset ratio rule, the current family asset ratio is adjusted to generate a family asset allocation strategy for the target family. Compared with the prior art, the embodiment of the present application utilizes an image information recognition model to recognize asset certificate images and utilizes a voice information extraction model to extract voice information from each family member to obtain the full asset information of the target family. Compared with manual sorting, it saves a lot of time, reduces labor costs, and improves efficiency, while avoiding the omission of asset information that may occur during manual sorting; further, based on the asset balance of the target family and the preset family asset allocation rules, a family asset allocation strategy is generated, which avoids reliance on the agent's own experience and expertise, reduces the influence of human subjectivity, and improves the reliability of the family asset allocation strategy.

[0166] According to an embodiment of the present application, a storage medium is provided, wherein the storage medium stores at least one executable instruction, and the computer executable instruction can execute the method for generating a configuration strategy for family assets in any of the above method embodiments.

[0167] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0168] Figure 6 A schematic diagram of the structure of a terminal provided according to an embodiment of the present application is shown. The specific embodiment of the present application does not limit the specific implementation of the computer device.

[0169] like Figure 6 As shown, the terminal may include: a processor (processor) 602 , a communication interface (Communications Interface) 604 , a memory (memory) 606 , and a communication bus 608 .

[0170] The processor 602 , the communication interface 604 , and the memory 606 communicate with each other via a communication bus 608 .

[0171] The communication interface 604 is used to communicate with other devices such as clients or other servers.

[0172] The processor 602 is used to execute the program 610, and specifically can execute the relevant steps in the above-mentioned embodiment of the method for generating a configuration strategy for family assets.

[0173] Specifically, the program 610 may include program codes, which include computer operation instructions.

[0174] The processor 602 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computer device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0175] The memory 606 is used to store the program 610. The memory 606 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0176] The program 610 may be specifically configured to enable the processor 602 to perform the following operations:

[0177] Acquire the full asset information of the target family, wherein the full asset information includes multiple asset information, and the asset information is identified from the asset voucher image based on the image information recognition model, and / or is extracted from the voice information of each family member based on the voice information extraction model, wherein the image information recognition model is used to identify the asset information in the asset voucher image, and the voice information extraction model is used to extract the asset information from the voice information of the family members;

[0178] Calculating the asset balance of the target family based on the full asset information;

[0179] Divide each of the asset information into a corresponding asset category group, and calculate the ratio of the asset value of each of the asset category groups to the total asset value of the full amount of asset information, to obtain the current family asset ratio of the target family;

[0180] According to the asset balance, based on a preset family asset allocation rule, the current family asset allocation is adjusted to generate a family asset allocation strategy for the target family.

[0181] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device of the above-mentioned method for generating a configuration strategy for household assets, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0182] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0183] The method and system of the present application may be implemented in many ways. For example, the method and system of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present application may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0184] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0185] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for generating a family asset allocation strategy, characterized in that: include: Acquire the full asset information of the target family, wherein the full asset information includes multiple asset information, and the asset information is identified from the asset voucher image based on the image information recognition model, and / or is extracted from the voice information of each family member based on the voice information extraction model, wherein the image information recognition model is used to identify the asset information in the asset voucher image, and the voice information extraction model is used to extract the asset information from the voice information of the family members; Calculating the asset balance of the target family based on the full asset information; Divide each of the asset information into a corresponding asset category group, and calculate the ratio of the asset value of each of the asset category groups to the total asset value of the full amount of asset information, to obtain the current family asset ratio of the target family; According to the asset balance, based on a preset family asset allocation rule, the current family asset allocation is adjusted to generate a family asset allocation strategy for the target family.

2. The method according to claim 1, characterized in that The image information recognition model includes an optical character recognition sub-model and a text recognition sub-model. The acquisition of the full asset information of the target family includes: Obtain images of each asset certificate of the target family; Taking each of the asset credential images as a target asset credential image; Extracting the text contained in the target asset voucher image based on the optical character recognition sub-model and converting it into a text format to obtain the text information contained in the target asset voucher image; Recognize the text information based on the text recognition sub-model, and extract the asset information contained in the target asset voucher image from the text information; The asset information in each target asset voucher image is integrated to obtain the full asset information of the target family.

3. The method according to claim 1, characterized in that The voice information extraction model includes a voice-to-text sub-model and an information recognition sub-model. The acquisition of the full asset information of the target family includes: Get voice messages from each family member; Taking each of the voice information as target voice information one by one; Converting the target voice information into a text format based on the voice-to-text sub-model to obtain text information contained in the target voice information; Based on the information recognition sub-model, the text information is sequentially subjected to text classification processing, named entity recognition processing, and relationship extraction processing to obtain the asset information contained in the target voice information; The asset information in each target voice message is integrated to obtain the full asset information of the target family.

4. The method according to claim 1, characterized in that: The dividing each asset information into corresponding asset category groups includes: According to the multiple quadrants included in the Standard & Poor's chart, a corresponding rule base is configured, wherein the rule base corresponds to the asset category group and is used to store the mapping relationship between the asset category and the asset information thereof; Taking each of the asset information as target asset information one by one; Matching the target asset information with the asset information in the rule base, determining the asset category of the target asset information, and classifying the target asset information into corresponding asset category groups; Each of the target asset information is divided into corresponding asset category groups.

5. The method according to claim 4, characterized in that The dividing each asset information into corresponding asset category groups further includes: Inputting the target asset information into a preset asset information classification model to determine a reference asset category of the target asset information; If the reference asset category is consistent with the asset category determined according to the rule base, the current classification result of the target asset information is maintained; If the reference asset category is inconsistent with the asset category determined according to the rule base, a prompt message for manual intervention verification is output to prompt manual intervention verification.

6. The method according to claim 1, characterized in that According to the asset balance, based on the preset family asset allocation rule, the current family asset allocation ratio is adjusted to obtain the family asset allocation strategy of the target family, including: If the asset balance is less than the first balance threshold, obtaining a first family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the first family asset allocation rule, so as to generate a family asset allocation strategy for the target family; If the asset balance is greater than or equal to the first balance threshold and less than the second balance threshold, obtaining a second family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the second family asset allocation rule, so as to generate a family asset allocation strategy for the target family; If the asset balance is greater than or equal to the second balance threshold and less than the third balance threshold, obtaining a third family asset allocation rule, and adjusting the current family asset allocation to the family asset allocation in the third family asset allocation rule, so as to generate a family asset allocation strategy for the target family; If the asset balance is greater than or equal to the third balance threshold, a fourth family asset allocation rule is obtained, and the current family asset allocation is adjusted to the family asset allocation in the fourth family asset allocation rule to generate a family asset allocation strategy for the target family.

7. The method according to claim 1, characterized in that The asset categories include liquid asset categories, defensive asset categories, stable asset categories, and offensive asset categories.

8. A device for generating a family asset allocation strategy, characterized in that: include: An asset information acquisition module, used to acquire the full asset information of the target family, wherein the full asset information includes multiple asset information, and the asset information is identified from the asset voucher image based on an image information recognition model, and / or is extracted from the voice information of each family member based on a voice information extraction model, wherein the image information recognition model is used to identify the asset information in the asset voucher image, and the voice information extraction model is used to extract the asset information from the voice information of the family members; An asset balance calculation module, used to calculate the asset balance of the target family based on the full asset information; An asset information division module is used to divide each asset information into corresponding asset category groups, and calculate the proportion of the asset value of each asset category group to the total asset value of the full asset information, so as to obtain the current family asset ratio of the target family; The family asset allocation strategy generating module is used to adjust the current family asset allocation ratio according to the asset balance and based on the preset family asset allocation rule to generate the family asset allocation strategy of the target family.

9. A storage medium, wherein at least one executable instruction is stored in the storage medium, characterized in that: The executable instructions enable the processor to execute operations corresponding to the method for generating a configuration strategy for family assets according to any one of claims 1 to 7.

10. A terminal, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, wherein the executable instruction enables the processor to execute operations corresponding to the method for generating a configuration strategy for family assets according to any one of claims 1 to 7.

Images