Automatic matching and adjusting method based on contract elements

Abstract

The invention relates to the technical field of electronic contracts, and discloses an automatic matching and adjusting method based on contract elements, and the method comprises the steps: obtaining all financing and renting products and contract templates related to all financing and renting products, and building a financing and renting product and contract template storage library; obtaining financing demand elements of a user, and analyzing the financing demand elements into demand structure data; according to a relationship between the structure demand data and each financing and renting product, determining a preferred financing and renting product and a contract template; obtaining a preferred contract template, extracting a variable contract element field, and establishing a variable contract element field changed by the user according to the variable contract element field and a change instruction of the user; and generating a formal contract document according to a relationship between the variable contract element field and the optimal contract template, and performing an online signing process based on an electronic signing system. The contract management efficiency and the intelligent level are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of electronic contract technology, and more specifically, to an automated matching and adjustment method based on contract elements. Background Technology

[0002] In financial leasing transactions, contract drafting typically depends on the type of financing product and the user's specific financing needs, involving multiple elements such as financing amount, lease term, rental structure, and tax treatment. Traditional contract drafting processes rely heavily on manual selection of contract templates based on business experience, followed by the filling in or modification of contract element fields item by item. This results in low operational efficiency and a high error rate. Especially when facing diverse and customized financing needs, existing methods struggle to respond quickly, impacting contract signing efficiency and customer experience.

[0003] Currently, with the advancement of enterprise digital transformation, some platforms are attempting to introduce contract template libraries and business parameterized management models to pre-bind financing products with templates, thereby achieving a certain degree of contract content reuse. However, current technical means still have significant limitations: on the one hand, there is a lack of intelligent and precise matching mechanisms between financing products and user needs, resulting in low adaptability of recommended contract templates; on the other hand, users still need manual intervention when modifying contract elements, and it is impossible to automatically adjust and update contract fields based on user instructions. In addition, existing systems mainly generate paper contracts or semi-structured documents, and the electronic signing process still relies on manual triggering by third parties, failing to form a complete closed loop and making it difficult to meet the needs for online, automated, and intelligent processing of the entire contract process.

[0004] Therefore, there is an urgent need for an automated matching and adjustment method based on contract elements, which can provide intelligent support for the entire process from financing demand analysis, product matching, automatic filling of contract elements, to contract generation and online signing. Summary of the Invention

[0005] In view of this, the present invention proposes an automated matching and adjustment method based on contract elements, which aims to solve the problems of existing financial leasing contract systems in terms of intelligent product matching, automatic adjustment of contract elements, and full-process automation of contract generation and signing, making it difficult to efficiently respond to users' personalized needs and achieve intelligent closed-loop contract management.

[0006] This invention proposes an automated matching and adjustment method based on contract elements, comprising:

[0007] Obtain the contract templates for each financial leasing product and the contracts associated with each financial leasing product, and establish a repository for financial leasing products and contract templates;

[0008] Obtain the elements of users' financing needs and analyze them into demand structure data;

[0009] Based on the relationship between structural demand data and various financial leasing products, the preferred financial leasing products and contract templates are determined.

[0010] Obtain the preferred contract template and extract the variable contract element fields. Based on the variable contract element fields and the user's change instructions, create the variable contract element fields after the user's changes.

[0011] Based on the relationship between variable contract element fields and preferred contract templates, a formal contract document is generated, and an online signing process is conducted based on an electronic signature system.

[0012] Furthermore, when acquiring various finance lease products and their associated contract templates, and establishing a finance lease product and contract template repository, the following steps are included:

[0013] Obtain the structured parameters of each financial lease product and the corresponding contract template. The structured parameters of the financial lease product include the financing amount range, lease term, interest rate type, business type and repayment method.

[0014] Based on the relationships between financial leasing products, establish a contractual relationship between the structured parameters of financial leasing products and contract templates;

[0015] Obtain the distance metric between each contract association and construct the distance matrix between each contract association based on the distance metric;

[0016] Iterative clustering is performed on the relationships between the contract associations based on the distance matrix, and the clustering relationship between each financial leasing product and each contract template is obtained based on the clustering results.

[0017] Based on distance relationships, establish a database of financial leasing products and contract templates.

[0018] Furthermore, when acquiring and analyzing users' financing needs into demand structure data, this includes:

[0019] Obtain the demand data from the financing demand elements, including the financing amount, lease term, and repayment method, and standardize the fields of the demand data;

[0020] Based on the enumeration value conversion logic, the required data after field standardization is converted into a structured data object;

[0021] The converted structured data is evaluated for completeness and validity, including:

[0022] If the evaluation result is greater than or equal to the configured preset threshold, then it is determined to be converted into a structured data object as the required structured data.

[0023] If the evaluation result is less than the preset threshold, it is determined that the converted structured data object is not the required structured data. Then, the required data after the field standardization processing based on the enumeration value conversion logic is transformed again until the evaluation result is greater than or equal to the preset threshold.

[0024] Furthermore, when standardizing the fields of the demand data, this includes:

[0025] Retrieve numeric fields for financing amount and lease term from the text input by the user, and perform format standardization and unit conversion;

[0026] Obtain the repayment method and business type from the text input by the user, and convert them into a preset enumeration code based on the preset mapping rules;

[0027] The system retrieves the input fields from the text content input by the user, extracts the semantics of the input fields based on fuzzy representation, and removes illegal characters and completes missing characters in the input fields according to the semantics of the input fields.

[0028] Furthermore, the evaluation of the completeness and validity of the transformed structured data includes:

[0029] Obtain the complete value of the transformed structured data, and determine the evaluation value based on the relationship between the complete value and the configured first and second preset complete values;

[0030] When the complete value is lower than the first preset complete value, the evaluation value is determined to be L1;

[0031] When the complete value is higher than or equal to the first preset complete value, and the complete value is lower than the first preset complete value, the evaluation value is determined to be L2;

[0032] When the complete value is higher than or equal to the second preset complete value, the evaluation value is determined to be L3;

[0033] Among them, the first preset complete value is less than the second preset complete value, and L1 < L2 < L3.

[0034] Furthermore, when the evaluation value is determined to be Li, i = 1, 2, 3, it includes:

[0035] Obtain the pass rate of the validity verification of the transformed structured data, and determine whether to adjust the evaluation value based on the relationship between the pass rate and the preset pass rate.

[0036] When the pass rate is lower than the preset pass rate, an adjustment coefficient is determined based on the difference between the pass rate and the preset pass rate, and the evaluation value is adjusted according to the adjustment coefficient.

[0037] If the pass rate is higher than or equal to the preset pass rate, then the evaluation value will not be adjusted.

[0038] Furthermore, when determining the adjustment coefficient based on the difference between the passing percentage and the preset passing percentage, the following factors are included:

[0039] The adjustment coefficient is determined based on the relationship between the percentage difference and the configured first and second preset percentage differences:

[0040] When the percentage difference is lower than the first preset percentage difference, the adjustment coefficient is determined to be M1;

[0041] When the percentage difference is higher than or equal to the first preset percentage difference and lower than the second preset percentage difference, the adjustment coefficient is determined to be M2.

[0042] When the percentage difference is higher than or equal to the second preset percentage difference, the adjustment coefficient is determined to be M3;

[0043] Among them, the first preset percentage difference is less than the second preset percentage difference, and M1 < M2 < M3 < 1.

[0044] Furthermore, when determining the optimal finance lease products and contract templates based on the relationship between structural demand data and various finance lease products, the following steps are taken:

[0045] The structural demand data is matched with the product elements of each financial leasing product, and the similarity score is obtained when the structural demand data is matched with the product elements of each financial leasing product.

[0046] Sort the similarity scores in reverse order, obtain the product element corresponding to the first-ranked similarity score, and determine the financial leasing product and contract template corresponding to the product element as the preferred financial leasing product and contract template.

[0047] Furthermore, when obtaining similarity scores for matching structural demand data with product elements of financial leasing products, the following are included:

[0048] The structural demand data and the product elements of the financial leasing products are vectorized separately, and the similarity between each structural demand field and the corresponding product field is obtained.

[0049] Based on Formula 1, the similarity scores of each dimension are weighted and summed to obtain the similarity score, where Formula 1 is shown below:

[0050]

[0051] Among them, w i For the weight of the i-th field, sim(d i ,p i) is the similarity function between the i-th structural requirement field and the i-th product field, n is the total number of structural requirement fields, and S is the similarity score.

[0052] Furthermore, when obtaining the preferred contract template and extracting the variable contract element fields, and establishing the modified variable contract element fields based on the variable contract element fields and the user's change instructions, the process includes:

[0053] Based on the user's change instructions, extract the target contract fields and their corresponding change values;

[0054] Pre-extract the set of variable contract element fields from the contract template and locate the field items that match the target contract fields;

[0055] Write the changed values ​​into the corresponding contract fields and update the contract field value set to form the user-customized contract element data.

[0056] Compared with existing technologies, the advantages of this invention are as follows: By constructing an associated repository of financial leasing products and contract templates, centralized management and structured modeling of contract template resources are achieved, improving the efficiency of contract retrieval and reuse. Based on this, a structured financing demand element parsing mechanism is introduced, which can transform users' financing intentions into standardized data structures, facilitating accurate matching with element fields in the product library. This automatically determines the optimal financing solution and its corresponding contract template, significantly improving the intelligence and adaptability of the matching. Simultaneously, by extracting variable contract element fields from the contract templates and combining them with user change instructions for semantic parsing and field mapping, dynamic adjustment and personalized customization of contract content are achieved, reducing manual modification operations and improving the automation and flexibility of contract element adjustments. Furthermore, the system supports directly binding updated fields to contract templates, automatically generating formal contract documents, and linking with electronic signature systems, streamlining the entire process from demand input to contract signing, and constructing an efficient, intelligent, and closed-loop financial leasing contract processing mechanism. Attached Figure Description

[0057] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0058] Figure 1 A flowchart illustrating an automated matching and adjustment method based on contract elements provided in an embodiment of the present invention;

[0059] Figure 2This is a flowchart illustrating an automated matching and adjustment method based on contract elements, provided as an embodiment of the present invention. Detailed Implementation

[0060] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0061] like Figures 1-2 As shown, in some embodiments of this application, this embodiment provides an automated matching and adjustment method based on contract elements, including:

[0062] Step S100: Obtain the contract templates for each financial leasing product and the contract templates associated with each financial leasing product, and establish a financial leasing product and contract template repository.

[0063] Specifically, the process of acquiring various financial leasing products and their associated contract templates, and establishing a repository of financial leasing products and contract templates, includes: acquiring the structured parameters of each financial leasing product and its corresponding contract template. The structured parameters of each financial leasing product include the financing amount range, lease term, interest rate type, business type, and repayment method. Based on the relationships between the financial leasing products, a contractual relationship is established between the structured parameters of the financial leasing products and the contract templates. A distance metric is acquired between these contractual relationships, and a distance matrix is ​​established based on this metric. Iterative clustering is performed on the contractual relationships based on the distance matrix, and the clustering results are used to obtain the clustering relationship between each financial leasing product and each contract template. Finally, a repository of financial leasing products and contract templates is established based on the distance relationship.

[0064] Understandably, key business parameters of each financial leasing product (such as financing amount range, lease term, interest rate type, business type, and repayment method) are structured and modeled as the foundational feature vectors for subsequent analysis. Simultaneously, contract template information corresponding to each financial product is extracted, and a "contractual association formula" is constructed between product parameters and contract templates. This involves associating product features with templates to form a one-to-one, many-to-one, or many-to-many mapping rule expression. Subsequently, a "distance metric" is calculated for the contractual association formulas between different financial products. This distance can be based on vector space models (such as Euclidean distance, Manhattan distance, cosine similarity, etc.) or semantic similarity algorithms to measure the similarity of different products in contract element matching, thus forming a distance matrix between contractual association formulas. After constructing the distance matrix, clustering algorithms (such as K-means, hierarchical clustering, or density clustering) are further introduced to perform cluster analysis on the contractual association formulas, uncovering a group of highly similar financial products and their matched contract templates. This clustering result helps identify the applicability of general templates, merge similar contract types, and optimize the organization of contract template resources. Finally, based on the results of cluster analysis and the similarity relationships reflected in the distance matrix, a multi-level mapping relationship between financial leasing products and contract templates is established, and a well-structured and closely related product and template repository is constructed to provide a data foundation and intelligent support for subsequent product recommendations and contract generation.

[0065] Step S200: Obtain the user's financing needs elements and analyze them into demand structure data.

[0066] Specifically, when acquiring and analyzing the user's financing demand elements into demand structure data, the process includes: acquiring demand data from the financing demand elements, including financing amount, lease term, and repayment method, and standardizing the fields of the demand data; converting the standardized demand data into a structured data object based on enumeration value conversion logic; and evaluating the completeness and validity of the converted structured data, wherein: if the evaluation result is greater than or equal to a configured preset threshold, it is determined that the converted structured data object is demand structure data; if the evaluation result is less than the configured preset threshold, it is determined that the converted structured data object is not demand structure data, and a second transformation is performed on the standardized demand data based on enumeration value conversion logic until the evaluation result is greater than or equal to the configured preset threshold.

[0067] Specifically, the standardization of the demand data includes: obtaining numeric fields such as financing amount and lease term from the user's input text content, and standardizing their format and converting them to units; obtaining repayment method and business type from the user's input text content, and converting them into preset enumeration codes based on preset mapping rules; obtaining input fields from the user's input text content, and obtaining the semantics of the input fields based on fuzzy expressions, and removing illegal characters and filling in missing characters in the input fields according to the semantics of the input fields.

[0068] Specifically, the evaluation of the integrity and validity of the converted structured data includes: obtaining the complete value of the converted structured data, and determining the evaluation value based on the relationship between the complete value and the configured first and second preset complete values; when the complete value is lower than the first preset complete value, the evaluation value is determined to be L1; when the complete value is higher than or equal to the first preset complete value and lower than the first preset complete value, the evaluation value is determined to be L2; when the complete value is higher than or equal to the second preset complete value, the evaluation value is determined to be L3; wherein the first preset complete value is less than the second preset complete value, and L1 < L2 < L3.

[0069] Specifically, when the evaluation value is determined to be Li, i = 1, 2, 3, the process includes: obtaining the pass rate of the validity verification of the converted structured data, and determining whether to adjust the evaluation value based on the relationship between the pass rate and the preset pass rate; when the pass rate is lower than the preset pass rate, determining the adjustment coefficient based on the difference between the pass rate and the preset pass rate, and adjusting the evaluation value based on the adjustment coefficient; when the pass rate is higher than or equal to the preset pass rate, determining that the evaluation value will not be adjusted.

[0070] Specifically, when determining the adjustment coefficient based on the difference between the passing percentage and the preset passing percentage, the following steps are taken: The adjustment coefficient is determined based on the relationship between the percentage difference and the configured first preset percentage difference and second preset percentage difference: when the percentage difference is lower than the first preset percentage difference, the adjustment coefficient is determined to be M1; when the percentage difference is higher than or equal to the first preset percentage difference and lower than the second preset percentage difference, the adjustment coefficient is determined to be M2; when the percentage difference is higher than or equal to the second preset percentage difference, the adjustment coefficient is determined to be M3; wherein the first preset percentage difference is less than the second preset percentage difference, and M1 < M2 < M3 < 1.

[0071] Understandably, by extracting key financing requirement fields such as financing amount, lease term, and repayment method from user input, and employing differentiated processing strategies for different types of fields: for numeric fields (such as amount and term), format standardization and unit conversion are performed to ensure numerical consistency; for enumerated fields (such as repayment method and business type), natural language expressions are mapped to recognizable standard enumerated values ​​through defined mapping rules; for input fields with ambiguous or vague expressions, semantic understanding technologies (such as keyword recognition and semantic matching) are combined to remove illegal characters and complete the semantic meaning of the fields, thereby completing the standardization processing of the requirement fields. Next, the standardized fields will be further transformed into structured data objects based on enumerated value conversion logic. To ensure the accuracy and reliability of the transformation results, a dual verification mechanism of completeness and validity is introduced: First, based on the configured first and second preset completeness values, the completeness level of the structured data is evaluated, corresponding to evaluation values ​​L1, L2, and L3, respectively, to quantify the basic quality level of the data. Then, based on the percentage of each field in the structured data that passes the validity check, combined with a preset pass percentage threshold, it is determined whether the current evaluation value needs adjustment, and adjustment coefficients M1, M2, and M3 are introduced for correction. The determination of the adjustment coefficients is based on a tiered threshold system of percentage differences; the larger the percentage difference, the lower the data validity, and the smaller the assigned adjustment coefficient, thereby lowering the evaluation level of the structured object. Through this dual-dimensional evaluation system based on completeness value and validity percentage, dynamic quantification and corrective control of structured data quality are achieved.

[0072] Step S300: Based on the relationship between the structural demand data and various financial leasing products, determine the preferred financial leasing products and contract templates.

[0073] Specifically, when determining the preferred financial leasing products and contract templates based on the relationship between structural demand data and various financial leasing products, the process includes: matching structural demand data with the product elements of each financial leasing product, and obtaining a similarity score when matching structural demand data with the product elements of each financial leasing product; sorting the similarity scores in reverse order, obtaining the product element corresponding to the highest similarity score, and determining the financial leasing product and contract template corresponding to that product element as the preferred financial leasing products and contract templates.

[0074] Specifically, when obtaining a similarity score for matching structural demand data with product elements of financial leasing products, the process includes: vectorizing the structural demand data and product elements of financial leasing products respectively, and obtaining the similarity between each structural demand field and the corresponding product field; based on Formula 1, weighted summing of the similarities across dimensions to obtain the similarity score, where Formula 1 is shown below:

[0075]

[0076] Among them, w i For the weight of the i-th field, sim(d i ,p i ) is the similarity function between the i-th structural requirement field and the i-th product field, n is the total number of structural requirement fields, and S is the similarity score.

[0077] Understandably, by standardizing the user-input structural requirements data and the product elements of financial leasing products, and then vectorizing them into models, each field (such as financing amount, lease term, repayment method, interest rate type, etc.) is mapped to a numerical or computable vector representation, ensuring that different types of fields have a unified measurement basis. For each pair of structural requirement fields and product fields, a defined similarity function (such as normalized difference, enumerated value matching, text semantic similarity, etc.) is used to calculate the matching degree at the single-field level. After obtaining the similarity values ​​of each dimension, a weighted similarity scoring mechanism is introduced to sum the similarities of all fields. This scoring function comprehensively considers the importance of different fields in the matching (through weight adjustment) and the actual similarity between fields to generate a global matching score, which is used to quantify the fit between the current structural requirements and each financial leasing product. After obtaining the corresponding scores for all financial products, the scores are sorted from high to low, and the product with the highest score is selected as the optimal match. Subsequently, based on the contract template information bound to the product, the corresponding contract template is directly determined as the recommended output, forming a set of optimal financial leasing products and contract template matching results.

[0078] Step S400: Obtain the preferred contract template and extract the variable contract element fields. Based on the variable contract element fields and the user's change instructions, establish the variable contract element fields after the user's changes.

[0079] Specifically, when obtaining a preferred contract template and extracting variable contract element fields, and establishing the user-modified variable contract element fields based on the variable contract element fields and the user's change instructions, the process includes: extracting the target contract field and its corresponding change value based on the user's change instructions; pre-extracting the set of variable contract element fields of the contract template and locating the field items that match the target contract field; writing the change value into the corresponding contract field and updating the contract field value set to form the user-customized contract element data.

[0080] Understandably, after obtaining the contract template corresponding to the preferred financial leasing product, the template is structured and parsed to identify the set of variable contract element fields that can be replaced or filled in. These fields are typically embedded in the template as placeholders, tags, or preset formats to carry dynamic information directly related to business elements, such as lease term, rent amount, and repayment method. Next, the user's input change instruction is received, which may be presented in a structured format (such as form modification) or natural language. Through semantic analysis and keyword extraction technology, the target contract field (such as "lease term") and its corresponding change value (such as "36 months") can be identified from the user's instruction, thus clarifying the user's modification intention. Subsequently, the field item matching the target field in the extracted set of variable contract fields is located, completing semantic alignment and field mapping. This process ensures that the user's intention is accurately applied to the specific location in the contract template, avoiding misbinding or mismatch of fields. Finally, the parsed change value is written into the corresponding field, and the set of contract field values ​​is updated in real time, forming a complete, user-customized contract element data structure, laying the data foundation for subsequent contract generation and display.

[0081] Step S500: Generate a formal contract document based on the relationship between the variable contract element fields and the preferred contract template, and conduct an online signing process based on the electronic signature system.

[0082] Understandably, after updating the user-customized variable contract element fields, these structured field values ​​are mapped and filled into the preset field placeholder positions in the template, based on the selected preferred contract template. This process can be achieved through the template engine, automatically replacing the original placeholders for each field value according to the binding rules in the template (such as {{lease term}}, {repayment method}, etc.), thus instantiating the template. This mechanism ensures the accuracy and format integrity of the generated contract documents and supports batch and diversified generation of different versions of formal contracts. Secondly, the generated contract documents can be exported to a signable format, such as PDF or standard electronic contract format, and automatically associated with metadata such as contract number and signing date. To further achieve paperless circulation, the generated contract documents are pushed to the integrated electronic signature, which supports identity authentication of the contract signing parties, confirmation of signing intent, and timestamp recording, ensuring the legal validity and traceability of the contract signing process. Finally, in the signing stage, signing process control strategies can be set, such as sequence, multi-party signing, and review nodes, and the signing status can be monitored and reminded in real time through the process engine until the entire signing process is completed. Once signed, the contract information can be encrypted and archived, or it can be linked with business processes to trigger subsequent contract effectiveness and performance procedures.

[0083] In the above embodiments, by constructing an associated repository of financial leasing products and contract templates, centralized management and structured modeling of contract template resources are achieved, improving the efficiency of contract retrieval and reuse. Based on this, a structured financing demand element parsing mechanism is introduced, which transforms the user's financing intention into a standardized data structure, facilitating precise matching with element fields in the product library. This automatically determines the optimal financing solution and its corresponding contract template, significantly improving the intelligence and adaptability of the matching. Simultaneously, by extracting variable contract element fields from the contract template and combining them with the user's change instructions for semantic parsing and field mapping, dynamic adjustment and personalized customization of contract content are achieved, reducing manual modification operations and improving the automation and flexibility of contract element adjustments. Furthermore, the system supports directly binding updated fields to the contract template, automatically generating formal contract documents, and linking with the electronic signature system, streamlining the entire process from demand input to contract signing, and constructing an efficient, intelligent, and closed-loop financial leasing contract processing mechanism.

[0084] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0086] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for automated matching and adjustment based on contract elements, characterized in that, include: Obtain the contract templates for each financial leasing product and the contracts associated with each financial leasing product, and establish a repository for financial leasing products and contract templates; Obtain the elements of users' financing needs and analyze them into demand structure data; Based on the relationship between structural demand data and various financial leasing products, the preferred financial leasing products and contract templates are determined. Obtain the preferred contract template and extract the variable contract element fields. Based on the variable contract element fields and the user's change instructions, create the variable contract element fields after the user's changes. Based on the relationship between variable contract element fields and preferred contract templates, a formal contract document is generated, and an online signing process is conducted based on an electronic signature system.

2. The automated matching and adjustment method based on contract elements as described in claim 1, characterized in that, When acquiring various finance lease products and their associated contract templates, and establishing a repository of finance lease products and contract templates, the following should be included: Obtain the structured parameters of each financial lease product and the corresponding contract template. The structured parameters of the financial lease product include the financing amount range, lease term, interest rate type, business type and repayment method. Based on the relationships between financial leasing products, establish a contractual relationship between the structured parameters of financial leasing products and contract templates; Obtain the distance metric between each contract association and construct the distance matrix between each contract association based on the distance metric; Iterative clustering is performed on the relationships between the contract associations based on the distance matrix, and the clustering relationship between each financial leasing product and each contract template is obtained based on the clustering results. Based on distance relationships, establish a database of financial leasing products and contract templates.

3. The automated matching and adjustment method based on contract elements as described in claim 2, characterized in that, When acquiring and analyzing users' financing needs into demand structure data, this includes: Obtain the demand data from the financing demand elements, including the financing amount, lease term, and repayment method, and standardize the fields of the demand data; Based on the enumeration value conversion logic, the required data after field standardization is converted into a structured data object; The converted structured data is evaluated for completeness and validity, including: If the evaluation result is greater than or equal to the configured preset threshold, then it is determined to be converted into a structured data object as the required structured data. If the evaluation result is less than the preset threshold, it is determined that the converted structured data object is not the required structured data. Then, the required data after the field standardization processing based on the enumeration value conversion logic is transformed again until the evaluation result is greater than or equal to the preset threshold.

4. The automated matching and adjustment method based on contract elements as described in claim 3, characterized in that, When standardizing the fields of the requirement data, the following steps are included: Retrieve numeric fields for financing amount and lease term from the text input by the user, and perform format standardization and unit conversion; Obtain the repayment method and business type from the text input by the user, and convert them into a preset enumeration code based on the preset mapping rules; The system retrieves the input fields from the text content input by the user, extracts the semantics of the input fields based on fuzzy representation, and removes illegal characters and completes missing characters in the input fields according to the semantics of the input fields.

5. The automated matching and adjustment method based on contract elements as described in claim 4, characterized in that, When evaluating the completeness and validity of the transformed structured data, the following should be included: Obtain the complete value of the transformed structured data, and determine the evaluation value based on the relationship between the complete value and the configured first and second preset complete values; When the complete value is lower than the first preset complete value, the evaluation value is determined to be L1; When the complete value is higher than or equal to the first preset complete value, and the complete value is lower than the first preset complete value, the evaluation value is determined to be L2; When the complete value is higher than or equal to the second preset complete value, the evaluation value is determined to be L3; Among them, the first preset complete value is less than the second preset complete value, and L1 < L2 < L3.

6. The automated matching and adjustment method based on contract elements as described in claim 5, characterized in that, When the evaluation value is determined to be Li, i = 1, 2, 3, it includes: Obtain the pass rate of the validity verification of the transformed structured data, and determine whether to adjust the evaluation value based on the relationship between the pass rate and the preset pass rate. When the pass rate is lower than the preset pass rate, an adjustment coefficient is determined based on the difference between the pass rate and the preset pass rate, and the evaluation value is adjusted according to the adjustment coefficient. If the pass rate is higher than or equal to the preset pass rate, then the assessment value will not be adjusted.

7. The automated matching and adjustment method based on contract elements as described in claim 6, characterized in that, When determining the adjustment coefficient based on the difference between the passing percentage and the preset passing percentage, the following are included: The adjustment coefficient is determined based on the relationship between the percentage difference and the configured first and second preset percentage differences: When the percentage difference is lower than the first preset percentage difference, the adjustment coefficient is determined to be M1; When the percentage difference is higher than or equal to the first preset percentage difference and lower than the second preset percentage difference, the adjustment coefficient is determined to be M2. When the percentage difference is higher than or equal to the second preset percentage difference, the adjustment coefficient is determined to be M3; Among them, the first preset percentage difference is less than the second preset percentage difference, and M1 < M2 < M3 < 1.

8. The automated matching and adjustment method based on contract elements as described in claim 1, characterized in that, When determining the optimal finance lease product and contract template based on the relationship between structural demand data and various finance lease products, the following should be included: The structural demand data is matched with the product elements of each financial leasing product, and the similarity score is obtained when the structural demand data is matched with the product elements of each financial leasing product. Sort the similarity scores in reverse order, obtain the product element corresponding to the first-ranked similarity score, and determine the financial leasing product and contract template corresponding to the product element as the preferred financial leasing product and contract template.

9. The automated matching and adjustment method based on contract elements as described in claim 8, characterized in that, When matching structural demand data with product elements of financial leasing products, similarity scoring includes: The structural demand data and the product elements of the financial leasing products are vectorized separately, and the similarity between each structural demand field and the corresponding product field is obtained. Based on Formula 1, the similarity scores of each dimension are weighted and summed to obtain the similarity score, where Formula 1 is shown below: Among them, w i Let sim(d) be the weight of the i-th field. i ,p i ) is the similarity function between the i-th structural requirement field and the i-th product field, n is the total number of structural requirement fields, and S is the similarity score.

10. The automated matching and adjustment method based on contract elements as described in claim 1, characterized in that, When obtaining the preferred contract template and extracting the variable contract element fields, and establishing the modified variable contract element fields based on the variable contract element fields and the user's change instructions, the process includes: Based on the user's change instructions, extract the target contract fields and their corresponding change values; Pre-extract the set of variable contract element fields from the contract template and locate the field items that match the target contract fields; Write the changed values ​​into the corresponding contract fields and update the contract field value set to form the user-customized contract element data.

Images