Quantum key AI writing large model-based property data sharing method and system

Abstract

The invention discloses a property data sharing method and system based on a quantum key AI writing large model, and the method comprises the following steps: S1, collecting property data, generating a dynamic key through employing a quantum key, and carrying out the first encryption of a sensitive field; s2, performing secondary encryption in combination with the dynamic key and an AES-256 algorithm, and storing in a DM database; s3, constructing a user role key permission level to realize hierarchical permission control; s4, receiving a complaint and service request of a user, calling an AI writing large model to generate a structured report, and performing double encryption; s5, adding an access boundary token to the encrypted report, generating a shared data abstract, and uploading the shared data abstract to a dream database; s6, transmitting the shared data abstract to a property terminal, and calling AI clustering analysis to generate credit evaluation; and S7, performing quantum signature verification on the evaluation result, encrypting and distributing the evaluation result to a supervision platform and a property management terminal. According to the invention, data whole-process encryption, intelligent generation and secure sharing are realized, and the security, efficiency and cooperative capability are improved.

Description

Technical Field

[0001] The present invention relates to the field of information security and data sharing technology, and in particular to a property data sharing method and system based on a quantum key AI writing large model. Background Art

[0002] With the development of the digital economy and the improvement of residents' quality of life, traditional property management models are gradually failing to meet the high standards of service quality, responsiveness, and data security required by modern communities. In recent years, driven by policy initiatives, many property management companies have accelerated the development of digital platforms, attempting to improve management efficiency and user satisfaction through data sharing and system collaboration. However, in practice, traditional data processing architectures, security systems, and intelligent application capabilities generally exhibit significant limitations, becoming key obstacles to the intelligent transformation of property services.

[0003] In existing technologies, the collection, storage, and sharing of property data mostly rely on traditional information management platforms. These platforms usually use plain text transmission or use low-strength encryption algorithms (such as MD5, SHA-1, etc.) for data protection. Although they can achieve information recording and partial permission control at the basic level, they have almost no risk resistance when facing new attack methods such as quantum computing. The development of quantum computing has broken through the security assumptions of classical encryption mechanisms and can crack the core logic of symmetric or asymmetric encryption algorithms in a very short time, making sensitive fields in traditional property data systems, such as owner identity information, equipment operating status, complaint records, etc., face the risk of tampering, leakage, or even malicious tampering. In addition, most property management systems currently lack end-to-end secure transmission mechanisms, resulting in data being exposed to unauthorized access channels in multiple links such as collection, uploading, processing, and sharing.

[0004] Furthermore, existing property management systems rely heavily on manual data processing. This is especially true for high-frequency tasks like complaint handling, service response, credit evaluation, and information aggregation. Numerous reports, documents, and service records still require manual compilation and upload. This is not only inefficient but also prone to data omissions and human oversight, severely limiting the speed and accuracy of service responses. Due to a lack of structured data standards and intelligent processing capabilities, existing systems struggle to achieve unified information aggregation and automated analysis, forming efficient property management knowledge graphs and credit analysis models, and proactively identifying and meticulously responding to residents' demands.

[0005] In terms of data sharing and system collaboration, existing property platforms are mostly single-site or regional platforms. When connecting with government platforms (such as Anhui Affairs Network) and industry regulatory platforms (such as the real estate market regulatory platform), the following problems are common: First, the data interface security is poor and there is a lack of a dynamic encryption token mechanism, which makes it easy for data to be stolen or tampered with during cross-platform transmission; second, the interface protocol design is not unified, the data format is not standardized, and there is a lack of unified permission authentication logic, making it difficult to achieve hierarchical sharing and fine-grained authorization; third, there is a lack of standardized identity authentication and access control mechanisms between systems, resulting in security vulnerabilities such as unauthorized users accessing highly sensitive data, which can easily lead to security incidents such as owner privacy leaks and corporate data abuse. Especially in multi-terminal collaborative use scenarios, such as the increasingly complex interaction needs between property companies, residents, and government regulators, the existing system cannot support an integrated data flow link, resulting in a serious information island problem.

[0006] Furthermore, while quantum key distribution technology and AI writing models have matured in the fields of information security and automated text generation, no research has yet combined them for real estate service data sharing scenarios. QKD technology provides a theoretically untappable key transmission mechanism, suitable for establishing high-strength encryption systems, while AI writing models offer large-scale natural language generation capabilities, replacing manual tasks such as automated report generation and data semantic structuring. Unfortunately, existing property data platforms have not integrated these cutting-edge technologies into their core architecture, resulting in consistently low levels of system security and intelligent processing, making them unable to support the future demands of high-load, highly sensitive, and multi-dimensional data interaction in real estate service scenarios.

[0007] Therefore, how to provide a property data sharing method and system based on the quantum key AI writing model is an urgent problem that needs to be solved by those skilled in the art. Summary of the Invention

[0008] One purpose of the present invention is to propose a property data sharing method and system based on the quantum key AI writing big model. The present invention fully integrates the quantum key distribution encryption mechanism and the artificial intelligence writing big model technology, constructs an end-to-end encrypted transmission and intelligent document generation process for multiple roles and multiple terminals, and describes in detail the entire process of property data from collection, encryption, authority control, automatic report generation, data summary packaging to credit assessment and distribution, realizing the full-process, full-role, and full-link data security sharing, and has the advantages of strong security, high intelligence, fast response efficiency and strong cross-platform collaboration capabilities.

[0009] According to an embodiment of the present invention, a property data sharing method based on a quantum key AI writing large model includes the following steps:

[0010] S1. Collect community property data through the terminal, use quantum key distribution technology to generate dynamic keys, and perform initial encryption on sensitive fields;

[0011] S2. Combine the dynamic key and AES-256 algorithm to perform a secondary encryption operation on the first encrypted field, and store the double encryption result in the DAMO database;

[0012] S3. Build a key permission hierarchy based on user roles, establish user permission access paths according to provincial, municipal, and street levels, and implement access control through a key binding mechanism to ensure that users at all levels have access to authorized data content;

[0013] S4. After receiving the complaint information and service request uploaded by the user, the AI writing model is called to automatically generate a structured report text and implement a double encryption strategy for the text content;

[0014] S5. Perform quantum session key encryption on the structured report text, attach an access boundary token, generate a shared data summary, upload it to the DAMO database, and enter the data distribution preparation stage;

[0015] S6. Package the shared data summary and access boundary token and transmit them to the property terminal. This triggers the AI writing model to perform cluster analysis on historical data and generate real-time credit assessment results.

[0016] S7. The credit assessment results are verified for integrity through quantum signatures, and encrypted distribution to designated regulatory platforms and property terminals is achieved through a token verification mechanism, realizing a data sharing link that is controllable throughout the entire process.

[0017] Optionally, the cell property data includes device coding data D e , Owner identity data D u , service interaction data D s .

[0018] Optionally, the S1 specifically includes:

[0019] S11. Collecting community property data through terminal equipment and performing pre-processing;

[0020] S12. Call the quantum key distribution mechanism to obtain the real-time session key K q , and bound to the current property data collection task identifier T i , forming a binding key pair (K q ,T i );

[0021] S13, encrypt the collected sensitive fields at the field level using the key K q Acts on the owner identity field D u and service interaction field Ds , forming the first encryption result:

[0022]

[0023] in, To use the quantum session key K q The encryption function is , || is the field concatenation operation, and C1 is the first encryption result.

[0024] Optionally, the preprocessing includes data cleaning and data conversion.

[0025] Optionally, the S2 specifically includes:

[0026] S21. Based on the first encryption result C1, extract the bound quantum session key K q , set the symmetric encryption key to K a , call the AES-256 encryption function, perform a secondary encryption operation on C1, and obtain the double encryption result of the sensitive field:

[0027]

[0028] in, To use the key K a The symmetric encryption function executed, C2 is the double encryption result;

[0029] S22. Write the double encryption result into the encrypted data table in the DAMO database and create a data mapping index I. m :

[0030] I m =Index(T i ,C2);

[0031] Among them, T i The current property data collection task identifier, Index(T i ,C2) represents the task identifier T i The index mapping relationship established with the double encryption result C2 is used for subsequent data retrieval and permission verification.

[0032] Optionally, the S3 specifically includes:

[0033] S31. Set the user role set R = {r1, r2, r3}, where r1 represents the provincial role, r2 represents the municipal role, and r3 represents the street role. Construct the permission level function for each role:

[0034]

[0035] Among them, W i For the role r iThe weight of the managed area, θ i is the sensitivity factor of the role-related data field, λ i is the corresponding user role authority coefficient;

[0036] S32, based on the authority level coefficient λ i Generate an authorization key and the user identity hash value H u and access token T a Bind, construct access control credential set Where Bind(·) represents the key binding operation function;

[0037] S33. When accessing the encrypted data table of the DAMO database, execute the credential verification function:

[0038]

[0039] Among them, V is the credential verification function, Verify(·) is the access verification function, and I m is the data mapping index, C2 is the double encryption result, if V=1, access is allowed, if V=0, access is denied.

[0040] Optionally, the S4 specifically includes:

[0041] S41, when the terminal receives the service request data packet, extracts the associated user ID U q , Service content field F q With timestamp T q , forming a request vector group [U q ||F q ||T q ], where || is a field concatenation operation;

[0042] S42. Input the request vector group into the AI writing model and combine it with the semantic label vector V of the double encryption result in the DAMO database. s , to generate structured report text:

[0043]

[0044] Among them, R f For structured report text, Gen AI (·) is the generation function corresponding to the AI writing large model, φ i is the weight coefficient of the neural unit in the i-th layer, W i is the weight matrix, b i is the bias term, σ is the nonlinear activation function, δ(V s ) is the content enhancement function of semantic tags on report text, and n is the number of layers of the AI writing model;

[0045] S43. Call the double encryption process for the generated structured report text and execute the joint encryption expression:

[0046]

[0047] Among them, C r Encrypt the result for the report text, To use the quantum session key K q The encryption function, To use the key K a The symmetric encryption function K q With K a They are session key and symmetric key respectively.

[0048] Optionally, the S5 specifically includes:

[0049] S51, based on the report text encryption result C r , calling the quantum session key encryption function Generate an encrypted identification code where ψ r Represents encrypted structured content bound to a quantum key;

[0050] S52. Construct access boundary token τ b =H(U q ||T q ||λ i ), where H(·) is the SHA-512 hash function, U q is the user ID, T q is the timestamp, λ i is the corresponding user role permission coefficient, || is the field splicing operation;

[0051] S53, combined shared data summary Ω d , and upload it to the buffer table to be distributed in the DM database:

[0052] Ω d =ψ r ||τ b ||χ f ;

[0053]

[0054] in, is the AES symmetric key K a Message authentication code function for data integrity verification.

[0055] Optionally, the S6 specifically includes:

[0056] S61, share the data summary Ωd With access boundary token τ b Packed into transmission entity package π p =Ω d ||τ b , transmitted to the property terminal through an encrypted channel, where || is a field splicing operation;

[0057] S62, call the AI writing model to extract the index mapping relationship based on the DAMO database Index (T i ,C2) formed by the historical encrypted data set Among them C 2,i is the i-th double-encrypted data record, and m is the total number of historical data records;

[0058] For each data C 2,i Perform decryption and extract the semantic label vector V s,i , after decryption, the semantic feature vector matrix M is formed s :

[0059] M s =[δ(V s,1 ),δ(V s,2 ),...,δ(V s,m )];

[0060] Among them, δ(V s,j ) represents the content enhancement function of the semantic label of the j-th record on the report text;

[0061] S63. Input the semantic feature vector matrix into the clustering function embedded in the AI writing model to generate real-time credit scoring results:

[0062]

[0063] Among them, β k is the clustering weight coefficient of the kth semantic record, σ is the ReLU activation function, W k is the weight matrix of the kth record, b k is the cluster bias vector, η is the score intervention factor, tanh(·) is the hyperbolic tangent function, U is the cluster directionality matrix, is the mean representation of the entire semantic vector matrix, Norm(·) is the result normalization function, Γ c Credit score results are generated in real time.

[0064] The property data sharing system based on the quantum key AI writing large model according to an embodiment of the present invention includes:

[0065] Data encryption module, used to collect property data and encrypt sensitive fields for the first time using quantum keys;

[0066] The storage encryption module is used to perform secondary encryption on sensitive fields by combining dynamic keys with the AES-256 encryption algorithm and store them in the DM database;

[0067] The permission control module is used to build key permission levels based on user roles, establish user permission access paths according to provincial, municipal, and street levels, and implement hierarchical access control;

[0068] The report generation module is used to receive user requests, call the AI writing model to automatically generate structured report text, and implement a double encryption strategy for the text content;

[0069] A summary generation module is used to perform quantum session key encryption processing on the structured report text, append an access boundary token, generate a shared data summary, and upload it to the dream database;

[0070] The cluster analysis module is used to transmit shared data summaries and call the AI writing model to cluster historical data to generate real-time credit assessment results;

[0071] The distribution verification module is used to verify the quantum signature of the credit assessment results and encrypt and distribute them to the supervision platform and property terminals.

[0072] The beneficial effects of the present invention are:

[0073] First, by introducing quantum key distribution technology, this invention implements a dynamic encryption protection mechanism for property service data throughout the entire process of collection, transmission, and storage, avoiding the security risks of traditional plaintext or low-intensity encryption methods in the face of quantum computing attacks. By constructing a multi-role key permission control path and binding access token mechanism, not only does it achieve granular encryption processing of sensitive fields, it also ensures that users at different levels can securely access data according to the scope of authorization, effectively reducing the risk of data leakage and illegal operations, and significantly improving the security strength and credibility of the data sharing process.

[0074] Secondly, this invention combines a large AI writing model to automatically generate structured text for typical business scenarios such as property complaint handling, service response, and credit assessment, replacing the existing model that relied heavily on manual writing. By inputting user request data and encrypted historical data, the system can efficiently generate report text and combine semantic tags with clustering algorithms to form credit assessment results. This not only improves the response efficiency and processing accuracy of property management companies during the service process, but also significantly reduces delays and errors caused by manual operations, meeting the needs of intelligent and efficient business operations.

[0075] Finally, the present invention establishes a distribution mechanism with shared data summaries as the core, and combines quantum signatures with token verification to achieve cross-terminal encrypted distribution of structured reports and credit score results. While ensuring data integrity and verifiability, it achieves efficient data collaboration between the regulatory platform, property terminals, and residents, effectively solving the problems of inconsistent interfaces, inaccurate authority control, and untraceable data in cross-platform sharing in existing systems. Overall, the present invention has achieved a comprehensive breakthrough in data security, processing intelligence, and platform collaboration, providing an innovative technical path for promoting the development of the property management industry towards high security, high intelligence, and high collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0077] Figure 1 This is a flowchart of the property data sharing method based on the quantum key AI writing model proposed in the present invention. DETAILED DESCRIPTION

[0078] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0079] refer to Figure 1 The property data sharing method based on the quantum key AI writing model includes the following steps:

[0080] S1. Collect community property data through the terminal, use quantum key distribution technology to generate dynamic keys, and perform initial encryption on sensitive fields;

[0081] S2. Combine the dynamic key and AES-256 algorithm to perform a secondary encryption operation on the first encrypted field, and store the double encryption result in the DAMO database;

[0082] S3. Build a key permission hierarchy based on user roles, establish user permission access paths according to provincial, municipal, and street levels, and implement access control through a key binding mechanism to ensure that users at all levels have access to authorized data content;

[0083] S4. After receiving the complaint information and service request uploaded by the user, the AI writing model is called to automatically generate a structured report text and implement a double encryption strategy for the text content;

[0084] S5. Perform quantum session key encryption on the structured report text, attach an access boundary token, generate a shared data summary, upload it to the DAMO database, and enter the data distribution preparation stage;

[0085] S6. Package the shared data summary and access boundary token and transmit them to the property terminal. This triggers the AI writing model to perform cluster analysis on historical data and generate real-time credit assessment results.

[0086] S7. The credit assessment results are verified for integrity through quantum signatures, and encrypted distribution to designated regulatory platforms and property terminals is achieved through a token verification mechanism, realizing a data sharing link that is controllable throughout the entire process.

[0087] This invention achieves technological innovation in key links such as data collection, encrypted storage, permission access, intelligent generation, data distribution, intelligent analysis and security verification by constructing a full process of property data sharing with quantum key encryption as the core and AI writing big model as the driving force. It comprehensively improves the security, intelligence and coordination of property service data, breaks through the limitations of traditional systems in security protection, labor efficiency and system integration, and has significant application promotion value and industrial transformation potential.

[0088] In this embodiment, the community property data includes device coding data D e , Owner identity data D u , service interaction data D s .

[0089] By breaking down community property data into device coding data, owner identity data, and service interaction data, the present invention not only enhances the structuring of the data model, but also provides clear data dimension support for subsequent encryption processing, authority division, and semantic analysis.

[0090] In this embodiment, S1 specifically includes:

[0091] S11. Collecting community property data through terminal equipment and performing pre-processing;

[0092] S12. Call the quantum key distribution mechanism to obtain the real-time session key K q , and bound to the current property data collection task identifier T i , forming a binding key pair (K q ,T i );

[0093] S13, encrypt the collected sensitive fields at the field level using the key K q Acts on the owner identity field D u and service interaction field D s , forming the first encryption result:

[0094]

[0095] in, To use the quantum session key K q The encryption function is , || is the field concatenation operation, and C1 is the first encryption result.

[0096] The present invention collects community property data through the terminal and encrypts sensitive fields for the first time, ensuring that security protection is implemented at the data generation stage. The dynamic key generated by quantum key distribution technology is unpredictable and non-replicable, which can effectively prevent data from being monitored, tampered with or forged during the collection and initial transmission process, thereby improving the security and credibility of the data source.

[0097] In this embodiment, the preprocessing includes data cleaning and data conversion.

[0098] This invention introduces data cleaning and data conversion processes before data encryption processing, which helps to eliminate data redundancy, repair outliers and unify data formats, improve data quality and consistency from the source, provide high-quality input for subsequent encryption, storage and AI generation processes, and significantly reduce model deviations and processing errors caused by data clutter.

[0099] In this embodiment, S2 specifically includes:

[0100] S21. Based on the first encryption result C1, extract the bound quantum session key K q , set the symmetric encryption key to K a , call the AES-256 encryption function, perform a secondary encryption operation on C1, and obtain the double encryption result of the sensitive field:

[0101]

[0102] in, To use the key K a The symmetric encryption function executed, C2 is the double encryption result;

[0103] S22. Write the double encryption result into the encrypted data table in the DAMO database and create a data mapping index I. m :

[0104] I m =Index(T i ,C2);

[0105] Among them, T i The current property data collection task identifier, Index(T i ,C2) represents the task identifier T iThe index mapping relationship established with the double encryption result C2 is used for subsequent data retrieval and permission verification.

[0106] This invention combines dynamic keys with the AES-256 algorithm to perform secondary encryption on sensitive fields, implementing a dual encryption mechanism of "quantum key + symmetric encryption," significantly enhancing the data's resistance to cracking during storage. Writing encrypted data into the domestically produced DAMO database facilitates the construction of an independent and controllable data infrastructure environment while meeting national security standards for information innovation.

[0107] In this embodiment, S3 specifically includes:

[0108] S31. Set the user role set R = {r1, r2, r3}, where r1 represents the provincial role, r2 represents the municipal role, and r3 represents the street role. Construct the permission level function for each role:

[0109]

[0110] Among them, W i For the role r i The weight of the managed area, θ i is the sensitivity factor of the role-related data field, λ i is the corresponding user role authority coefficient;

[0111] S32, based on the authority level coefficient λ i Generate an authorization key and the user identity hash value H u and access token T a Bind, construct access control credential set Where Bind(·) represents the key binding operation function;

[0112] S33. When accessing the encrypted data table of the DAMO database, execute the credential verification function:

[0113]

[0114] Among them, V is the credential verification function, Verify(·) is the access verification function, and I m is the data mapping index, C2 is the double encryption result, if V=1, access is allowed, if V=0, access is denied.

[0115] The present invention establishes a key permission level based on user roles and implements access control through a key binding mechanism, ensuring that data access is only carried out within the authorized scope, truly realizing the "minimum available permission" principle, preventing unauthorized access and illegal operations, effectively isolating data boundaries between users of different roles, and improving the security and accuracy of data scheduling.

[0116] In this embodiment, the S4 specifically includes:

[0117] S41, when the terminal receives the service request data packet, extracts the associated user ID U q , Service content field F q With timestamp T q , forming a request vector group [U q ||F q ||T q ], where || is a field concatenation operation;

[0118] S42. Input the request vector group into the AI writing model and combine it with the semantic label vector V of the double encryption result in the DAMO database. s , to generate structured report text:

[0119]

[0120] Among them, R f For structured report text, Gen AI (·) is the generation function corresponding to the AI writing large model, φ i is the weight coefficient of the neural unit in the i-th layer, W i is the weight matrix, b i is the bias term, σ is the nonlinear activation function, δ(V s ) is the content enhancement function of semantic tags on report text, and n is the number of layers of the AI writing model;

[0121] S43. Call the double encryption process for the generated structured report text and execute the joint encryption expression:

[0122]

[0123] Among them, C r Encrypt the result for the report text, To use the quantum session key K q The encryption function, To use the key K a The symmetric encryption function K q With K a They are session key and symmetric key respectively.

[0124] The present invention inputs the complaint and service request data uploaded by users into the AI writing model, automatically generates structured reports, and implements a double encryption strategy, which not only improves the efficiency of report generation, but also ensures the confidentiality and non-tamperability of the text content, realizes a data processing path with both high efficiency and high security, and reduces the risk of errors caused by human participation.

[0125] In this embodiment, the S5 specifically includes:

[0126] S51, based on the report text encryption result C r , calling the quantum session key encryption function Generate an encrypted identification code where ψ r Represents encrypted structured content bound to a quantum key;

[0127] S52. Construct access boundary token τ b =H(U q ||T q ||λ i ), where H(·) is the SHA-512 hash function, U q is the user ID, T q is the timestamp, λ i is the corresponding user role permission coefficient, || is the field splicing operation;

[0128] S53, combined shared data summary Ω d , and upload it to the buffer table to be distributed in the DM database:

[0129] Ω d =ψ r ||τ b ||χ f ;

[0130]

[0131] in, is the AES symmetric key K a Message authentication code function for data integrity verification.

[0132] The present invention encrypts structured reports through quantum session keys and attaches access boundary tokens to generate shared data summaries and enter the data distribution preparation stage. This ensures that the data to be distributed is fully marked and authenticated in terms of content security, access rights, and operation legitimacy, providing a mechanism to support subsequent trusted transmission and audit traceability.

[0133] In this embodiment, S6 specifically includes:

[0134] S61, share the data summary Ω d With access boundary token τ b Packed into transmission entity package π p =Ω d ||τ b , transmitted to the property terminal through an encrypted channel, where || is a field splicing operation;

[0135] S62, call the AI writing model to extract the index mapping relationship based on the DAMO database Index (T i ,C2) formed by the historical encrypted data set Among them C 2,i is the i-th double-encrypted data record, and m is the total number of historical data records;

[0136] For each data C 2,i Perform decryption and extract the semantic label vector V s,i , after decryption, the semantic feature vector matrix M is formed s :

[0137] M s =[δ(V s,1 ),δ(V s,2 ),...,δ(V s,m )];

[0138] Among them, δ(V s,j ) represents the content enhancement function of the semantic label of the j-th record on the report text;

[0139] S63. Input the semantic feature vector matrix into the clustering function embedded in the AI writing model to generate real-time credit scoring results:

[0140]

[0141] Among them, β k is the clustering weight coefficient of the kth semantic record, σ is the ReLU activation function, W k is the weight matrix of the kth record, b k is the cluster bias vector, η is the score intervention factor, tanh(·) is the hyperbolic tangent function, U is the cluster directionality matrix, is the mean representation of the entire semantic vector matrix, Norm(·) is the result normalization function, Γ c Credit score results are generated in real time.

[0142] The present invention packages the shared data summary and transmits it to the property terminal, and triggers the AI writing model to perform cluster analysis on historical data. It can accurately model based on historical service records, dynamically generate personalized credit assessment results, improve the intelligence level and risk control capabilities of property supervision, and realize the value transformation from data use to data insights.

[0143] The property data sharing system based on the quantum key AI writing model includes:

[0144] Data encryption module, used to collect property data and encrypt sensitive fields for the first time using quantum keys;

[0145] The storage encryption module is used to perform secondary encryption on sensitive fields by combining dynamic keys with the AES-256 encryption algorithm and store them in the DM database;

[0146] The permission control module is used to build key permission levels based on user roles, establish user permission access paths according to provincial, municipal, and street levels, and implement hierarchical access control;

[0147] The report generation module is used to receive user requests, call the AI writing model to automatically generate structured report text, and implement a double encryption strategy for the text content;

[0148] A summary generation module is used to perform quantum session key encryption processing on the structured report text, append an access boundary token, generate a shared data summary, and upload it to the dream database;

[0149] The cluster analysis module is used to transmit shared data summaries and call the AI writing model to cluster historical data to generate real-time credit assessment results;

[0150] The distribution verification module is used to verify the quantum signature of the credit assessment results and encrypt and distribute them to the supervision platform and property terminals.

[0151] Example 1:

[0152] To verify the feasibility of this invention, we applied it to a large-scale smart community property management platform. This community is a typical high-density residential complex with over 4,500 permanent residents and a property management area of over 500,000 square meters. The platform covers a wide range of equipment and terminals, including elevators, fire protection facilities, underground garages, and smart access control systems, generating an average of over 2,800 property interaction data points daily. The platform's services cover key scenarios such as owner complaints, facility repairs, credit ratings, payment records, and inspection records. The existing property management system had significant issues with security, efficiency, and collaboration.

[0153] First, the platform's original data protection mechanism used static keys and weak encryption algorithms, and only performed basic encryption on highly sensitive data such as owner identity information, contact information, and complaint content, resulting in three sensitive information leaks caused by internal authority violations in 2024. Secondly, the complaint and service processing process relies entirely on manual operations. Report generation requires manual writing, uploading, and approval, with an average processing cycle of 37 hours, which often results in repeated submission of residents' complaints and delayed service responses. Thirdly, when the platform connects with the superior supervision system, due to the lack of a unified authority boundary definition and interface encryption mechanism, the format error rate in the transmitted data is as high as 7.6%, and the accuracy and timeliness of key indicators cannot be guaranteed.

[0154] After the deployment of the present invention, a dynamic encryption mechanism based on quantum key distribution is integrated into the platform. All sensitive fields involving owner identity, device identification, and service interaction are first encrypted with a dynamic key during the collection process, and then double-encrypted with the AES-256 algorithm before being written into the domestically produced Dameng database, replacing the original static encryption scheme. The platform also performs cleaning and standardization conversion on the collected data, unifies the field format, and improves the accuracy of subsequent AI model processing. In processing complaint services, the system calls the AI writing large model to automatically extract key information and generate a structured report based on the text uploaded by the owner. The average processing time of the model is controlled within 1 second, and the accuracy rate reaches 98.4%. For example, in a complaint about damage to public lighting in mid-January 2025, the system identified keywords such as "fault type", "location", and "reporting time" from the text, automatically generated a maintenance information form and submitted it to the maintenance unit, and the final processing cycle was compressed to within 6 hours, significantly improving user satisfaction.

[0155] At the same time, the platform establishes a key permission level system based on user roles (platform administrator, property manager, and district supervisor). By binding key fingerprints to access tokens, hierarchical permission control is implemented. During data sharing, the system applies quantum key encryption to structured reports, attaches access boundary tokens, generates data summaries, and uploads them to the buffer database. This data summary is then packaged and transmitted to the supervisory end through a dynamic interface. The AI model is then triggered to perform cluster analysis and scoring of historical complaints and maintenance records, outputting the company's credit assessment results for supervisory review.

[0156] Since the deployment of this invention, the platform has completed a total of 82,379 structured data transmissions, generated more than 800 structured reports per day, shortened the complaint response cycle from an average of 37 hours to 6.4 hours, and reduced the service processing timeout rate from 21.7% to 4.5%. The credit assessment accuracy has increased from no intelligent identification to 96.8%, and the regulatory platform feedback unanimously believes that the assessment results are more valuable for reference. In addition, according to system records, during the period from January to February, the platform did not have any unauthorized data access and transmission errors, and the data integrity and security reached 100%. The following are the key operational data collected by the property platform in actual operation, reflecting the implementation effect of this invention:

[0157] Table 1 Statistics of application effects of smart community property management platform

[0158]

[0159]

[0160] To sum up, through the deployment and application of the present invention, not only high-intensity security protection of property service data is achieved, but also the overall processing efficiency and user experience of the platform are greatly improved, and practical problems such as weak data security, inefficient manual processing and cross-system sharing obstacles in traditional systems are solved, which fully verifies the practicality and scalability of this method in complex scenarios.

[0161] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A property data sharing method based on a quantum key AI writing model, characterized in that: The steps include: S1. Collect community property data through the terminal, use quantum key distribution technology to generate dynamic keys, and perform initial encryption on sensitive fields; S2. Combine the dynamic key and AES-256 algorithm to perform a secondary encryption operation on the first encrypted field, and store the double encryption result in the DAMO database; S3. Build a key permission hierarchy based on user roles, establish user permission access paths according to provincial, municipal, and street levels, and implement access control through a key binding mechanism to ensure that users at all levels have access to authorized data content; S4. After receiving the complaint information and service request uploaded by the user, the AI writing model is called to automatically generate a structured report text and implement a double encryption strategy for the text content; S5. Perform quantum session key encryption on the structured report text, attach an access boundary token, generate a shared data summary, upload it to the DAMO database, and enter the data distribution preparation stage; S6. Package the shared data summary and access boundary token and transmit them to the property terminal. This triggers the AI writing model to perform cluster analysis on historical data and generate real-time credit assessment results. S7. The credit assessment results are verified for integrity through quantum signatures, and encrypted distribution to designated regulatory platforms and property terminals is achieved through a token verification mechanism, realizing a data sharing link that is controllable throughout the entire process.

2. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: The community property data includes equipment coding data D e , Owner identity data D u , service interaction data D s .

3. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: Said S1 specifically includes: S11. Collecting community property data through terminal equipment and performing pre-processing; S12. Call the quantum key distribution mechanism to obtain the real-time session key K q , and bound to the current property data collection task identifier T i , forming a binding key pair (K q ,T i ); S13, encrypt the collected sensitive fields at the field level using the key K q Acts on the owner identity field D u and service interaction field D s , forming the first encryption result C1.

4. The property data sharing method based on the quantum key AI writing large model according to claim 3 is characterized in that: The preprocessing includes data cleaning and data conversion.

5. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: The S2 specifically includes: S21. Based on the first encryption result C1, extract the bound quantum session key K q , set the symmetric encryption key to K a , call the AES-256 encryption function, perform a secondary encryption operation on C1, and obtain the double encryption result C2 of the sensitive field; S22, write the double encryption result C2 into the encrypted data table in the DM database, and combine it with the current property data collection task identifier T i , establish data mapping index I m , used for subsequent data retrieval and permission verification.

6. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: The S3 specifically includes: S31. Set the user role set R = {r1, r2, r3}, where r1 represents the provincial role, r2 represents the municipal role, and r3 represents the street role. Construct the permission level function for each role: Among them, W i For the role r i The weight of the managed area, θ i is the sensitivity factor of the role-related data field, λ i is the corresponding user role authority coefficient; S32, based on the authority level coefficient λ i Generate an authorization key and the user identity hash value H u and access token T a Bind, construct access control credential set Where Bind(·) represents the key binding operation function; S33. When accessing the encrypted data table of the DAMO database, execute the credential verification function: Among them, V is the credential verification function, Verify(·) is the access verification function, and I m is the data mapping index, C2 is the double encryption result, if V=1, access is allowed, if V=0, access is denied.

7. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: The S4 specifically includes: S41, when the terminal receives the service request data packet, extracts the associated user ID U q , Service content field F q With timestamp T q , forming a request vector group [U q ||F q ||T q ], where || is a field concatenation operation; S42. Input the request vector group into the AI writing model and combine it with the semantic label vector V of the double encryption result in the DAMO database. s , to generate structured report text: Among them, R f For structured report text, Gen AI (·) is the generation function corresponding to the AI writing large model, φ i is the weight coefficient of the neural unit in the i-th layer, W i is the weight matrix, b i is the bias term, σ is the nonlinear activation function, δ(V s ) is the content enhancement function of semantic tags on report text, and n is the number of layers of the AI writing model; S43, calling the double encryption process for the generated structured report text to obtain the report text encryption result C r .

8. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: The S5 specifically includes: S51, based on the report text encryption result C r , calling the quantum session key encryption function Generate an encrypted identification code where ψ r Represents encrypted structured content bound to a quantum key; S52. Construct access boundary token τ b =H(U q ||T q ||λ i ), where H(·) is the SHA-512 hash function, U q is the user ID, T q is the timestamp, λ i is the corresponding user role permission coefficient, || is the field splicing operation; S53, combined shared data summary Ω d , and upload it to the buffer table to be distributed in the DM database: Oh d =ψ r ||t b ||x f ; in, is the AES symmetric key K a Message authentication code function for data integrity verification.

9. The property data sharing method based on the quantum key AI writing large model according to claim 1 is characterized in that: The S6 specifically includes: S61, share the data summary Ω d With access boundary token τ b Packed into transmission entity package π p =Ω d ||τ b , transmitted to the property terminal through an encrypted channel, where || is a field splicing operation; S62, call the AI writing model to extract the index mapping relationship based on the DAMO database Index (T i ,C2) formed by the historical encrypted data set Among them C 2,i is the i-th double-encrypted data record, and m is the total number of historical data records; For each data C 2,i Perform decryption and extract the semantic label vector V s,i , after decryption, the semantic feature vector matrix M is formed s : M s =[δ(V s,1 ),δ(V s,2 ),...,δ(V s,m )]; Among them, δ(V s,j ) represents the content enhancement function of the semantic label of the j-th record on the report text; S63. Input the semantic feature vector matrix into the clustering function embedded in the AI writing model to generate real-time credit scoring results: Among them, β k is the clustering weight coefficient of the kth semantic record, σ is the ReLU activation function, W k is the weight matrix of the kth record, b k is the cluster bias vector, η is the score intervention factor, tanh(·) is the hyperbolic tangent function, U is the cluster directionality matrix, is the mean representation of the entire semantic vector matrix, Norm(·) is the result normalization function, Γ c Credit score results are generated in real time.

10. A property data sharing system based on a quantum key AI writing large model, which executes the property data sharing method based on a quantum key AI writing large model according to any one of claims 1 to 9, characterized in that: include: Data encryption module, used to collect property data and encrypt sensitive fields for the first time using quantum keys; The storage encryption module is used to perform secondary encryption on sensitive fields by combining dynamic keys with the AES-256 encryption algorithm and store them in the DM database; The permission control module is used to build key permission levels based on user roles, establish user permission access paths according to provincial, municipal, and street levels, and implement hierarchical access control; The report generation module is used to receive user requests, call the AI writing model to automatically generate structured report text, and implement a double encryption strategy for the text content; A summary generation module is used to perform quantum session key encryption processing on the structured report text, append an access boundary token, generate a shared data summary, and upload it to the dream database; The cluster analysis module is used to transmit shared data summaries and call the AI writing model to cluster historical data to generate real-time credit assessment results; The distribution verification module is used to verify the quantum signature of the credit assessment results and encrypt and distribute them to the supervision platform and property terminals.

Images