A Cross-provincial Handling Method and System for Real Estate Registration Based on Artificial Intelligence

Abstract

A cross-provincial remote handling method and system for real estate registration based on artificial intelligence, which relates to the technical field of data processing; collecting registration materials and verification materials, using an OCR model to extract registration information, obtaining a confidence score in combination with the verification materials, constructing a federated intelligent collaboration model based on the local databases of different provinces, obtaining the material requirement sets of different provinces, judging whether the user needs to supplement materials, generating text conversion rules for different provinces according to the federated intelligent collaboration model, converting the registration information of different provinces to obtain conversion information, judging whether the user meets the registration conditions according to the conversion information, and generating corresponding evidence preservation records for the conversion information that meets the registration conditions; which is beneficial to reducing the time consumed by users for handling business offline and can significantly improve the efficiency of cross-provincial remote handling of business.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to a method and system for cross-provincial handling of real estate registration based on artificial intelligence. Background Art

[0002] Under the traditional real estate registration mode, applicants must go to the location of the real estate in person to handle relevant business, which causes great inconvenience to those applicants whose real estate is located in other places. With the increasing maturity of technologies such as artificial intelligence, image recognition, and natural language processing, these technologies can be applied to the field of real estate registration to achieve rapid recognition and digital processing of the paper materials submitted by applicants;

[0003] In the prior art, data between different registration agencies often cannot be shared while ensuring its privacy, and different provinces often have different material requirements and differences in text descriptions for the same business, which directly leads to low efficiency in cross-provincial handling of business and even makes it difficult to carry out. In view of the deficiencies of the prior art, the present invention provides a method and system for cross-provincial handling of real estate registration based on artificial intelligence. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for cross-provincial handling of real estate registration based on artificial intelligence.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A cross-provincial real estate registration system based on artificial intelligence includes the following modules:

[0006] A data verification module, which is used to collect the registration materials and verification materials of users, preprocess both of them respectively, extract the corresponding registration information from the registration materials by using an OCR model, and obtain the confidence score of the user in combination with the verification materials;

[0007] A data collaboration module, which is used to obtain the geographical information of registration agencies in different provinces, set up corresponding local databases, and construct a federal intelligent collaboration model for all provinces based on the local databases of different provinces;

[0008] A data conversion module, which is used to obtain the material requirement sets of different provinces, judge whether the user needs to supplement materials by using the material requirement sets, generate text conversion rules for different provinces based on the federal intelligent collaboration model, and convert the registration information of different provinces by using the text conversion rules to obtain conversion information;

[0009] A data archiving module, which is used to judge whether the user meets the registration conditions according to the obtained conversion information, and generate corresponding archiving records for the conversion information that meets the registration conditions.

[0010] Further, the process of collecting the user's registration materials and verification materials and preprocessing them respectively includes:

[0011] Set up an image acquisition unit to collect the user's registration materials through the image acquisition unit. The registration materials refer to the relevant images for real estate registration.

[0012] Set up a voice acquisition unit to collect the user's verification materials through the voice acquisition unit. The verification materials refer to the relevant voices for verifying the user's identity.

[0013] For the registration materials, remove the background noise of the registration materials through an adaptive threshold segmentation algorithm, and correct the tilt problem of the shooting angle using a distortion correction algorithm. For the verification materials, use a voiceprint separation technology to separate the environmental noise from the user's voiceprint, and extract the voice features of the user's voiceprint.

[0014] Further, the process of using an OCR model to extract the corresponding registration information from the registration materials and obtaining the confidence score of the user in combination with the verification materials includes:

[0015] Input the user's registration materials into the OCR model, use the OCR model to identify the text content related to real estate registration in the registration materials, and fill the identified text content into a preset registration form to generate the corresponding registration information.

[0016] Based on the pre-recorded voice information of the user, use voice recognition technology to obtain the confidence score between the user's verification materials and the voice information, set a corresponding confidence threshold, compare the user's confidence score with the confidence threshold. If the confidence score is greater than or equal to the confidence threshold, mark the user as having passed the voice verification.

[0017] Further, the process of obtaining the geographical information of the registration agencies in different provinces, setting up corresponding local databases, and constructing a federal intelligent collaboration model for all provinces based on the local databases of different provinces includes:

[0018] Collect the geographical information of the registration agencies in different provinces. The geographical information refers to the geographical locations of the registration agencies in each province, and use GIS technology to construct a GIS distribution map of the registration agencies in different provinces based on the collected geographical information.

[0019] Set up corresponding local databases at each registration agency. The local databases are used to store the registration materials, verification materials, and registration information of the users who have passed the voice verification at the corresponding registration agencies.

[0020] Deploy lightweight models at each registration agency to extract features from all registration materials in its local database, and use the FedAvg algorithm to aggregate the model parameters of the registration agencies in each province to form a unified federated intelligent collaborative model.

[0021] Further, the process of obtaining the material requirement sets of different provinces and using the material requirement sets to determine whether the user needs to supplement materials includes:

[0022] Obtain the business rule texts of the registration agencies in different provinces, focus on the key terms in the business rule texts of different provinces through the self-attention mechanism, and include the required materials in the key terms obtained in the material requirement sets of the registration agencies in the corresponding provinces;

[0023] Take the province where the user expects to conduct real estate registration as the target province, obtain the material requirement set of the user's target province, compare the current registration materials provided by the user with this material requirement set to determine whether there are missing registration materials, and if so, prompt the user to supplement the missing registration materials.

[0024] Further, the process of generating text conversion rules for different provinces according to the federated intelligent collaborative model and using the text conversion rules to convert the registration information of different provinces to obtain conversion information includes:

[0025] The text conversion rules are used to reflect the differences in the description texts used for the same data between different provinces. Deploy a target decoder in the lightweight model of the registration agency in the user's target province, deploy a shared encoder in the federated intelligent collaborative model, and initialize it and then send it to the lightweight model in the user's target province;

[0026] First, keep the parameters of the shared encoder unchanged, use the local database of the target province to train its target decoder to generate the target text, which is the description text used in the target province, and then keep the parameters of the target decoder unchanged, adjust the parameters of the shared encoder to make it adapt to the target text, and upload the shared encoder at this time to the federated intelligent collaborative model;

[0027] Obtain the registration information corresponding to the registration materials after the user supplements the materials, encode it through the shared encoder, and then decode it through the target decoder of the target province to obtain the conversion information.

[0028] Further, the process of judging whether the user meets the registration conditions according to the obtained conversion information and generating a corresponding deposit record for the conversion information that meets the registration conditions includes:

[0029] Construct corresponding blockchain distribution nodes according to the positional relationship between registration agencies in different provinces in the GIS distribution map, obtain the registration conditions of the target province of the user, and compare the conversion information of the user with the registration conditions of the user's target province;

[0030] If the registration conditions are met, conduct real estate registration for it, generate a deposit record, and upload the generated deposit record to each blockchain distribution node for storage. If not, do not conduct real estate registration for it and feedback the information of non - meeting the conditions to the user.

[0031] A cross - provincial real estate registration method based on artificial intelligence, comprising the following steps:

[0032] Step S1: Collect the registration materials and verification materials of the user, pre - process them separately, use the OCR model to extract the corresponding registration information according to the registration materials, and obtain the confidence score of the user in combination with the verification materials;

[0033] Step S2: Obtain the geographical information of registration agencies in different provinces, set corresponding local databases, and construct a federated intelligent collaboration model for all provinces according to the local databases of different provinces;

[0034] Step S3: Obtain the material requirement sets of different provinces, use the material requirement sets to judge whether the user needs to supplement materials, generate text conversion rules for different provinces according to the federated intelligent collaboration model, and use the text conversion rules to convert the registration information of different provinces to obtain conversion information;

[0035] Step S4: Judge whether the user meets the registration conditions according to the obtained conversion information, and generate corresponding deposit records for the conversion information that meets the registration conditions.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] By using the federated algorithm to construct a federated intelligent collaboration model for all registration agencies according to the local databases of each registration agency, on the one hand, it can form a unified large model by integrating the data characteristics of all registration agencies, and on the other hand, it protects the data privacy of each registration agency;

[0038] By obtaining the material requirement sets of different provinces and comparing them with the registration materials provided by the user during the business handling process of the user, it can timely discover the missing registration materials of the user and remind the user to supplement them, which is beneficial to reducing the time consumed by the user for offline business handling;

[0039] By obtaining the text conversion rules between the province where the user is located and the target province, the registration information of the user can be converted into the descriptive text used in the target province, saving the cost of the user and the registration agency to convert by themselves, and significantly improving the efficiency of cross-provincial handling of business. Description of the Drawings

[0040] Figure 1 This is the schematic diagram of the present invention. Detailed Embodiment

[0041] As Figure 1 shown, a cross-provincial handling system for real estate registration based on artificial intelligence includes the following modules:

[0042] The data verification module is used to collect the user's registration materials and verification materials, preprocess the two respectively, extract the corresponding registration information from the registration materials by using the OCR model, and obtain the confidence score of the user in combination with the verification materials;

[0043] The data collaboration module is used to obtain the geographical information of the registration agencies in different provinces, set up the corresponding local databases, and construct the federal intelligent collaboration models of all provinces according to the local databases of different provinces;

[0044] The data conversion module is used to obtain the material requirement sets of different provinces, judge whether the user needs to supplement materials by using the material requirement sets, generate the text conversion rules of different provinces according to the federal intelligent collaboration model, and convert the registration information of different provinces by using the text conversion rules to obtain the conversion information;

[0045] The data evidence preservation module is used to judge whether the user meets the registration conditions according to the obtained conversion information, and generate the corresponding evidence preservation records for the conversion information that meets the registration conditions.

[0046] It should be further noted that in the specific implementation process, the process of collecting the user's registration materials and verification materials and preprocessing the two respectively includes:

[0047] Set up an image acquisition unit to collect the user's registration materials through the image acquisition unit. The registration materials refer to the relevant images provided by the user for real estate registration, including applicant certificates, agency materials, document of title source, tax payment certificates, and surveying and mapping data files;

[0048] Set up a voice acquisition unit to collect the user's verification materials through the voice acquisition unit. The verification materials refer to the relevant voices provided by the user for verifying their identity. In the embodiment of the present invention, the registration materials for real estate registration are in the form of images, and the verification materials for verifying the user's identity are in the form of voices;

[0049] Preprocess the collected registration materials and verification materials separately. For the registration materials, remove the background noise of the registration materials through an adaptive threshold segmentation algorithm, and use a distortion correction algorithm to correct the tilt problem of the shooting angle. For the verification materials, use a voice separation technology to separate the environmental noise and the user's voiceprint, extract the voice features of the user's voiceprint, and standardize them into 128-dimensional vectors.

[0050] It should be further noted that in the specific implementation process, the process of using the OCR model to extract the corresponding registration information according to the registration materials and obtaining the confidence score of the user in combination with the verification materials includes:

[0051] The full name of the OCR model is Optical Character Recognition, which is an optical character recognition model that converts the text in the image into editable text through computer vision technology. It can identify the text area in the image, convert the content of the text area into machine code, and optimize the recognition result based on semantic rules;

[0052] Input the user's registration materials into the OCR model, use the OCR model to recognize the text content related to real estate registration in the registration materials, such as fields like property certificate number, right holder, building area, etc., and fill the recognized text content into a preset registration form to generate the corresponding registration information;

[0053] Based on the pre-recorded voice information of the user, standardize the user's voice information into 128-dimensional vectors in the same way, use speech recognition technology to obtain the similarity between the user's verification materials and the voice information, denoted as the confidence score, set the corresponding confidence threshold, and compare the user's confidence score with the confidence threshold;

[0054] If the confidence score is greater than or equal to the confidence threshold, mark the user as passing the voice verification and perform subsequent processing on it. Conversely, if the confidence score is less than the confidence threshold, mark the user as failing the voice verification and do not perform subsequent processing on it.

[0055] It should be further noted that in the specific implementation process, the process of obtaining the geographical information of the registration agencies in different provinces and setting up the corresponding local databases, and constructing the federal intelligent collaborative model for all provinces based on the local databases of different provinces includes:

[0056] Collect the geographical information of the registration agencies in different provinces. The geographical information refers to the geographical locations of the registration agencies in each province, represented by longitude and latitude, and use GIS technology to construct the GIS distribution maps of the registration agencies in different provinces according to the collected geographical information;

[0057] A corresponding local database is set up at the geographical location of each registration agency. The local database is used to store the registration materials and verification materials of users who have passed voice verification at the corresponding registration agency, as well as the corresponding registration information.

[0058] At each registration agency, a corresponding lightweight model is deployed to extract features from all the registration materials in its local database. An update period is set, and every time an update period is reached, the model parameters of the registration agencies in each province, such as gradients and weights, are aggregated once using the FedAvg algorithm to form a unified feature model, denoted as the federated intelligent collaboration model.

[0059] The full name of the FedAvg algorithm is Federated Averaging, which is a commonly used algorithm in federated learning technology and is mainly used to solve the model training problem under distributed data. It can obtain a globally optimal model by iteratively exchanging model parameters between the local database and the central server without centralizing the data in each local database.

[0060] It should be further noted that in the specific implementation process, the process of obtaining the material requirement sets of different provinces and using the material requirement sets to determine whether users need to supplement materials includes:

[0061] Obtain the business rule texts of the registration agencies in different provinces, such as regulations documents, laws and regulations documents, etc. The business rule texts are used to reflect the material requirements necessary for the same registration business in different provinces.

[0062] Through the self-attention mechanism, focus on the key terms in the business rule texts of different provinces, such as the list of required materials, and incorporate the required materials in the obtained key terms into the material requirement sets of the registration agencies in the corresponding provinces. The material requirement sets of different provinces are different.

[0063] Take the province where the user expects to conduct real estate registration as the target province, obtain the material requirement set of the user's target province, and compare the current registration materials provided by the user with the material requirement set of the target province to determine whether there are missing registration materials. If there are missing materials, prompt the user to supplement the missing materials. If not, proceed with subsequent processing.

[0064] It should be further noted that in the specific implementation process, the process of generating text conversion rules for different provinces according to the federated intelligent collaboration model and using the text conversion rules to convert the registration information of different provinces to obtain conversion information includes:

[0065] Since the descriptive texts used by registration agencies in different provinces for the same data are different, to achieve cross-provincial handling of real estate registration, it is necessary to obtain the text conversion rules between different provinces, which are used to reflect the differences in the descriptive texts used by different provinces for the same data;

[0066] Deploy the target decoder in the lightweight model of the registration agency in the user's target province, deploy the shared encoder in the federated intelligent collaboration model, and after initializing it, send it to the lightweight model in the user's target province. First, keep the parameters of the shared encoder unchanged, and use the local database of the target province to train its target decoder to generate the target text, where the target text is the descriptive text used by the target province;

[0067] Then keep the parameters of the target decoder unchanged, adjust the parameters of the shared encoder to make it adapt to the target text, upload the shared encoder at this time to the federated intelligent collaboration model, obtain the registration information corresponding to the user's registration materials after supplementary materials, encode it through the shared encoder, and then decode it through the target decoder in the target province to obtain the corresponding conversion information.

[0068] It should be further noted that in the specific implementation process, judging whether the user meets the registration conditions according to the obtained conversion information, and the process of generating the corresponding deposit record for the conversion information that meets the registration conditions includes:

[0069] Construct the corresponding blockchain distribution nodes according to the positional relationship between the registration agencies in different provinces in the GIS distribution map, and obtain the registration conditions of the user's target province, where the registration conditions are used to reflect the various data requirements necessary for real estate registration in the target province;

[0070] Compare the user's conversion information with the registration conditions of the user's target province. If the registration conditions are met, conduct real estate registration for it and generate the corresponding deposit record, and upload the generated deposit record to each blockchain distribution node for storage. If not, do not conduct real estate registration for it and feedback the information of non-compliance to the user.

[0071] The embodiments of the present invention also include a cross-provincial handling method for real estate registration based on artificial intelligence, including the following steps:

[0072] Step S1: Collect the user's registration materials and verification materials, preprocess them respectively, use the OCR model to extract the corresponding registration information according to the registration materials, and obtain the confidence score of the user in combination with the verification materials;

[0073] Step S2: Obtain the geographical information of the registration agencies in different provinces, set the corresponding local databases, and construct the federated intelligent collaboration model of all provinces according to the local databases of different provinces;

[0074] Step S3: Obtain the material requirement sets of different provinces, and use the material requirement sets to determine whether the user needs to supplement materials. Generate text conversion rules for different provinces according to the federal intelligent collaboration model, and use the text conversion rules to convert the registration information of different provinces to obtain conversion information;

[0075] Step S4: Determine whether the user meets the registration conditions according to the obtained conversion information, and generate corresponding evidence preservation records for the conversion information that meets the registration conditions.

[0076] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An artificial intelligence-based real estate registration inter-provincial system, characterized by: Includes the following modules: The data verification module is used to collect the user's registration materials and verification materials, pre-process them respectively, extract the corresponding registration information based on the registration materials using the OCR model, and obtain the user's confidence score in combination with the verification materials; The data collaboration module is used to obtain the geographic information of registration agencies in different provinces and set up corresponding local databases, and build a federal intelligent collaboration model for all provinces based on the local databases of different provinces; The data conversion module is used to obtain the material requirement sets of different provinces, and use the material requirement sets to determine whether the user needs to supplement the materials, generate text conversion rules for different provinces according to the federal intelligent collaborative model, and use the text conversion rules to convert the registration information of different provinces to obtain conversion information; A data evidence storage module is used to determine whether the user meets the registration conditions based on the acquired conversion information, and to generate corresponding evidence records for the conversion information that meets the registration conditions; The process of generating text conversion rules for different provinces and obtaining conversion information includes: The text conversion rules are used to reflect the differences in the description texts used for the same data between different provinces. The target decoder is deployed in the lightweight model of the registration agency in the user's target province, and the shared encoder is deployed in the federated intelligent collaborative model, which is initialized and sent to the lightweight model of the user's target province. First, keep the parameters of the shared encoder unchanged, use the local database of the target province to train the target decoder of the target province to generate the target text, where the target text is the description text used by the target province, then keep the parameters of the target decoder unchanged, adjust the parameters of the shared encoder to adapt it to the target text, and upload the shared encoder to the federated intelligent collaborative model; The registration information corresponding to the registration materials of the user after the supplementary materials is obtained, and it is encoded through a shared encoder, and then decoded through a target decoder of the target province to obtain conversion information.

2. According to claim 1, the inter-provincial real estate registration system based on artificial intelligence is characterized in that: The process of collecting registration materials and verification materials and pre-processing them separately includes: Setting an image acquisition unit, through which registration materials of the user are collected, wherein the registration materials refer to relevant images used for real estate registration; Setting a voice collection unit to collect verification materials of the user through the voice collection unit, wherein the verification materials refer to relevant voices used to verify the identity of the user; For registration materials, an adaptive threshold segmentation algorithm is used to remove background noise from registration materials, and a distortion correction algorithm is used to correct the tilt problem of the shooting angle. For verification materials, voiceprint separation technology is used to separate environmental noise from user voiceprints, and the voice features of user voiceprints are extracted.

3. According to claim 2, the inter-provincial real estate registration system based on artificial intelligence is characterized in that: The process of extracting registration information based on registration materials and obtaining confidence scores includes: Input the user's registration materials into the OCR model, use the OCR model to recognize the text content related to real estate registration in the registration materials, and fill the recognized text content into the preset registration form to generate corresponding registration information; Based on the pre-entered user's voice information, voice recognition technology is used to obtain the confidence score between the user's verification materials and the user's voice information, a corresponding confidence threshold is set, and the user's confidence score is compared with the confidence threshold. If the confidence score is greater than or equal to the confidence threshold, the user is marked as having passed the voice verification.

4. According to claim 3, the inter-provincial real estate registration system based on artificial intelligence is characterized in that: The process of setting up a local database and building a federated intelligent collaboration model includes: Collecting geographic information of registration agencies in different provinces, the geographic information refers to the geographical location of registration agencies in each province, and using GIS technology to construct GIS distribution maps of registration agencies in different provinces based on the collected geographic information; A corresponding local database is set up at each registration agency, and the local database is used to store the registration materials, verification materials, and registration information of users who have passed the voice verification at the corresponding registration agency; A lightweight model is deployed at each registration agency to extract features from all registration materials in the local database of the registration agency. The FedAvg algorithm is used to aggregate the model parameters of the registration agencies in each province to form a unified federal intelligent collaborative model.

5. According to claim 4, the inter-provincial real estate registration system based on artificial intelligence is characterized in that: The process of obtaining material requirement sets from different provinces and determining whether users need additional materials includes: Obtain the business rules texts of registration agencies in different provinces, focus on the key clauses in the business rules texts of different provinces through the self-attention mechanism, and incorporate the necessary materials in the key clauses into the material requirement set of the registration agencies in the corresponding provinces; The province where the user expects to conduct real estate registration is taken as the target province, and the material requirement set of the user's target province is obtained. The various registration materials currently provided by the user are compared with the material requirement set to determine whether any registration materials are missing. If missing, the user is prompted to supplement the missing registration materials.

6. According to claim 5, the inter-provincial real estate registration system based on artificial intelligence is characterized in that: The process of determining whether the user meets the registration conditions and generating a record of the conversion information that meets the registration conditions includes: According to the location relationship between the registration agencies in different provinces in the GIS distribution map, the corresponding blockchain distribution nodes are constructed to obtain the registration conditions of the user's target province, and the user's conversion information is compared with the registration conditions of the user's target province; If the registration conditions are met, real estate registration will be carried out for it, and a proof record will be generated, and the generated proof record will be uploaded to each blockchain distribution node for storage. If it is not met, real estate registration will not be carried out for it, and information that the conditions are not met will be fed back to the user.

7. A method for inter-provincial real estate registration based on artificial intelligence, which is implemented based on the inter-provincial real estate registration system described in any one of claims 1 to 6, characterized in that: The method comprises: Step S1: Collect the user's registration materials and verification materials, pre-process them respectively, extract the corresponding registration information based on the registration materials using the OCR model, and obtain the user's confidence score in combination with the verification materials; Step S2: Obtain the geographic information of registration agencies in different provinces, set up corresponding local databases, and build a federal intelligent collaboration model for all provinces based on the local databases of different provinces; Step S3: Obtain material requirement sets of different provinces, and use the material requirement sets to determine whether the user needs to supplement materials, generate text conversion rules of different provinces according to the federal intelligent collaborative model, and use the text conversion rules to convert the registration information of different provinces to obtain conversion information; Step S4: Determine whether the user meets the registration conditions based on the acquired conversion information, and generate a corresponding evidence record for the conversion information that meets the registration conditions.

Images