A method and system for generating a delivery service business form

Abstract

The present invention relates to the technical field of data processing and management, and specifically to a method and system for generating a delivery service business form. By introducing steps such as requirement analysis, data extraction and processing, and machine learning classification, the present invention realizes the automatic generation of delivery service business forms. This automated process significantly reduces manual intervention, improves the speed and accuracy of data processing, ensures the rapid and efficient generation of forms that meet requirements, and meets the timeliness requirements of business operations; through the automated form generation and data processing process, the present invention significantly reduces the dependence on manual operations and solves the problem of low efficiency in the traditional manual form filling and review processes. Through steps such as requirement analysis, data source configuration, data extraction, data preprocessing, and automatic form generation, this method can quickly respond to the business requirements of delivery services, shorten the response time of delivery services, and improve the overall work efficiency.

Description

Technical Field

[0001] The present invention relates to the field of data processing and management technology, and in particular to a method and system for generating a delivery service business form. Background Art

[0002] In modern finance and logistics, the accuracy and efficiency of delivery services are crucial. Delivery services involve multiple steps, including the physical delivery of goods, warehouse management, and the conversion of futures and spot goods. To support this complex business process, companies often need to generate and manage numerous delivery service forms. These forms not only contain critical delivery information such as delivery number, delivery date, security code, transaction price, and delivery quantity, but also require data accuracy and completeness.

[0003] However, existing technologies face several challenges in generating and managing delivery service business forms:

[0004] First, the generation of delivery service business forms under existing technologies often relies on manual labor, and its management process is inefficient: manual form filling and long review processes limit the business's ability to respond quickly.

[0005] Secondly, the data in the delivery service business forms under existing technologies is complex and difficult to integrate: the existing management system does not provide sufficient support for diverse data sources, resulting in inefficient data extraction and processing.

[0006] In view of the above problems, it is necessary to propose a method and system for generating a delivery service business form. Summary of the invention

[0007] The purpose of the present invention is to solve the problems existing in the background technology and to provide a method and system for generating a delivery service business form.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] In a first aspect, the present invention provides a method for generating a delivery service business form, comprising the following steps:

[0010] A method for generating a delivery service business form comprises the following steps:

[0011] Step 1: Demand analysis and form template design;

[0012] Conduct demand analysis on delivery service business and confirm the field requirements of various delivery service business forms required in the business process.

[0013] Get the delivery service type corresponding to the delivery service business form, including physical delivery, warehouse delivery, factory delivery and EFP.

[0014] As a preferred embodiment of the present invention, determine the field requirements in the delivery service business form according to the obtained delivery service type.

[0015] The said field requirements include field name, data type, field length, and whether it is required.

[0016] The said field names include delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method.

[0017] Each field name corresponds to a preset importance factor, providing a quantitative basis for the layout of the subsequent delivery service business form.

[0018] Each field name corresponds to a preset display space, ensuring that the field name, input box, and prompt information can be clearly displayed, avoiding overcrowding or excessive blank space.

[0019] The said data types include String, Number, and Date.

[0020] The said field length is the maximum character limit for string-type fields.

[0021] The said whether it is required refers to whether a certain field is a required item in the delivery service business form.

[0022] Determine the field requirements in the delivery service business form according to the obtained delivery service type.

[0023] Subsequently, design a form template according to the results of the requirements analysis, arrange the form fields according to the importance factors of each field name, and the arrangement rule is that the field name with the highest importance factor is arranged in the first column of the delivery service business form, the field name with the second highest importance factor is arranged in the second column of the delivery service business form, and so on.

[0024] Configure the column width for each column according to the preset display space.

[0025] Step 2: Data source configuration and data extraction;

[0026] Determine the data source of the delivery service business form and its data source parameters.

[0027] The said data source parameters include database type and connection information.

[0028] The said connection information includes DatabaseName, ServiceName, Hostname, PortNumber, Username, and Password.

[0029] According to the field requirements in the form template, retrieve the preset data extraction script and extract the required data from the data source.

[0030] Step 3: Data preprocessing and field matching;

[0031] Perform data cleaning and field matching on the extracted data, remove the duplicate parts in the captured data, and match the required data extracted from the data source with the preset field names.

[0032] The so-called data cleaning refers to removing duplicates from the extracted data.

[0033] The so-called field matching is implemented based on the support vector machine model.

[0034] The training and application process of the support vector machine is as follows:

[0035] S301: Data preparation;

[0036] Define the data set: Denote the data set extracted from the data source as D = {d1, d2,..., dn}, and each sample di contains multiple feature values representing the content of different fields;

[0037] S302: Text feature extraction. For each field sample di, extract text features, including the string length L(di) and the TF-IDF vectorized feature values ; where i = 1, 2,..., n.

[0038] Construct a feature vector for each field: . Where is the field name to which the field di belongs, including the delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method; where is the attribution label, indicating whether the field di belongs to the current field name. If so, has a value of 1; otherwise, it is 0.

[0039] S303: Establish a support vector machine model;

[0040] Use the support vector machine model to train the extracted features. The goal is to find an optimal hyperplane to maximize the margin between samples.

[0041] The support vector machine model is specifically: , where w is the weight vector; b is the bias term; where C is the penalty parameter, controlling the tolerance for misclassified attributions; where is the slack variable, used to handle non-linearly separable cases.

[0042] Set the constraint conditions: ; where is a feature mapping function for mapping the input feature vector to a high-dimensional space.

[0043] S304. Model training;

[0044] Set a set of predefined field sets, F = {f1, f2,..., fn} as training samples, where each field fi has a feature vector: . Among them are all the field names to which the field fi truly belongs and the values are all 1; use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training.

[0045] S305. Application of training results;

[0046] After the support vector machine model training is completed, use the trained support vector machine model to predict new data. For each new sample, input it into the trained support vector machine model to obtain its matching field name.

[0047] Step Four. Form generation and rendering;

[0048] Generate a specific form instance according to the form template and data. Use front-end technology to render the form.

[0049] Step Five. Form verification and error handling;

[0050] Perform duplicate value processing on the generated delivery service business form and merge duplicate rows. Define the unique identifier for each delivery as unique_id = TradeDate + SecurityCode + Buyername + SellerName. Among them, TradeDate is the hash value of the delivery date field; SecurityCode is the hash value of the delivery number field; Buyername is the hash value of the seller name field; SellerName is the hash value of the seller name field.

[0051] Subsequently, based on the unique detection of duplicate records, merge the rows with the same unique identifier in the delivery service business form.

[0052] Verify the generated delivery service business form to ensure the integrity and accuracy of the data. For the data that fails the verification, perform error handling and prompt the user to make corrections.

[0053] The specific process is as follows: Check each field to confirm whether there is an empty string or null. If so, highlight the field and output error.

[0054] Step 6: Form Storage and Distribution;

[0055] Store the generated delivery service business form in the database and file system for subsequent business processing. At the same time, distribute the delivery service business form to relevant personnel or systems to ensure the smooth progress of the business process.

[0056] The form distribution is achieved through email and message queue methods.

[0057] In a second aspect, the present invention provides a delivery service business form generation system, including a template design module, a database, a machine learning module, a field matching module, a verification and error handling module, and a storage and distribution module.

[0058] The template design module conducts a requirements analysis of the delivery service business and confirms the field requirements for various delivery service business forms required during the business process.

[0059] Obtain the delivery service types corresponding to the delivery service business form, including physical delivery, warehouse delivery, factory warehouse delivery, and futures for cash settlement.

[0060] As a preferred embodiment of the present invention, determine the field requirements in the delivery service business form according to the obtained delivery service types.

[0061] The said field requirements include field name, data type, field length, and whether it is required.

[0062] The said field names include delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method.

[0063] Each field name corresponds to a preset importance factor, providing a quantitative basis for the subsequent layout of the delivery service business form.

[0064] Each field name corresponds to a preset display space to ensure that the field name, input box, and prompt information can be clearly displayed, avoiding overcrowding or excessive blank space.

[0065] The said data types include String, Number, and Date.

[0066] The said field length is the maximum character limit for string-type fields.

[0067] The said whether it is required refers to whether a certain field is a required item in the delivery service business form.

[0068] Determine the field requirements in the delivery service business form according to the obtained delivery service types.

[0069] Subsequently, a form template is designed based on the requirements analysis results, and the form fields are arranged according to the importance factors of each field name. The arrangement rule is that the field name with the highest importance factor is arranged in the first column of the delivery service business form, the field name with the second highest importance factor is arranged in the second column of the delivery service business form, and so on.

[0070] The database is the storage center of delivery business information and the data source of the delivery service business form.

[0071] The database includes several sub-databases, and the type of each sub-database includes MySQL, Oracle, RDBMS, and NoSQL

[0072] Each sub-database has a uniquely matched database name DatabaseName, service name ServiceName, hostname Hostname, port number PortNumber, username Username, and password Password.

[0073] According to the field requirements in the form template, a preset data extraction script is retrieved to extract the required data from the data source.

[0074] The machine learning module builds a support vector machine model for field name matching and conducts model training.

[0075] Define a data set, denote the data set extracted from the data source as D = {d1, d2,..., dn}, and each sample di contains multiple feature values representing the content of different fields;

[0076] For each field sample di, text features are extracted, including the string length L(di) and the TF-IDF vectorized feature values ; where i = 1, 2,..., n.

[0077] Construct a feature vector for each field: . Where is the field name to which the field di belongs, including the delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method; where is the attribution label indicating whether the field di belongs to the current field name. If so, the value of is 1; otherwise it is 0.

[0078] Use the support vector machine model to train the extracted features. The goal is to find an optimal hyperplane to maximize the interval between samples.

[0079] The support vector machine model is specifically: , where w is the weight vector; b is the bias term; where C is the penalty parameter that controls the tolerance for misclassified instances; where are slack variables used to handle non-linearly separable cases.

[0080] Set the constraint conditions: ; where is the feature mapping function used to map the input feature vector into a high-dimensional space.

[0081] Set a predefined set of fields, F = {f1, f2,..., fn} as training samples, where each field fi has a feature vector: . Among them, are all the field names to which the field fi truly belongs and all have values of 1; Use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training.

[0082] The field matching module retrieves the training results of the machine learning module, matches the fields extracted from the database one by one to the preset field names, and outputs the field names to which each field truly belongs .

[0083] The verification and error handling module performs duplicate value processing on the generated delivery service business form and merges duplicate rows. Define the unique identifier for each delivery, unique_id = TradeDate + SecurityCode + Buyername + SellerName. Where TradeDate is the hash value of the delivery date field; SecurityCode is the hash value of the delivery number field; Buyername is the hash value of the seller name field; SellerName is the hash value of the seller name field.

[0084] Subsequently, based on the unique detection of duplicate records, merge the rows with the same unique identifier in the delivery service business form.

[0085] Verify the generated delivery service business form to ensure the integrity and accuracy of the data. For the data that fails the verification, perform error handling and prompt the user to make corrections.

[0086] The specific process is as follows: Check each field to confirm whether there is an empty string or null. If so, highlight the field and output error.

[0087] The storage and distribution module stores the generated delivery service business form in the database and the file system for subsequent business processing. Meanwhile, the delivery service business form is distributed to relevant personnel or systems to ensure the smooth progress of the business process.

[0088] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0089] 1. By introducing steps such as requirement analysis, data extraction and processing, and machine learning classification, the present invention realizes the automatic generation of the delivery service business form. This automated process significantly reduces manual intervention, improves the speed and accuracy of data processing, and ensures that forms meeting requirements can be generated quickly and efficiently to meet the timeliness requirements of business operations.

[0090] 2. The present invention clarifies field requirements, data source configuration, and field matching, ensuring the standardization and consistency of the generated form. The setting of field names, data types, and whether they are required makes the form clear and comprehensive in structure, reduces the risk of errors caused by non-standard data, and enhances data integrity and accuracy.

[0091] 3. Through the automated form generation and data processing process, the present invention significantly reduces the dependence on manual operations and solves the problem of low efficiency in the traditional manual form filling and review processes. Through steps such as requirement analysis, data source configuration, data extraction, data preprocessing, and automatic form generation, this method can quickly respond to the business requirements of delivery services, shorten the response time of delivery services, and improve overall work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the drawings:

[0093] Figure 1 is the method flow chart of the present invention;

[0094] Figure 2 is the system block diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0095] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0096] Please refer to Figure 1 shown, a method for generating a delivery service business form includes the following steps:

[0097] Step 1. Requirement analysis and form template design;

[0098] Conduct a requirements analysis for the delivery service business, and confirm the field requirements of various delivery service business forms required in the business process.

[0099] Obtain the delivery service types corresponding to the delivery service business forms, including physical delivery, warehouse delivery, factory warehouse delivery, and futures-for-cash.

[0100] Furthermore, determine the field requirements in the delivery service business form according to the obtained delivery service types.

[0101] The said field requirements include field name, data type, field length, and whether it is mandatory.

[0102] The said field names include delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method.

[0103] Each field name corresponds to a preset importance factor, providing a quantitative basis for the subsequent layout of the delivery service business form.

[0104] Each field name corresponds to a preset display space to ensure that the field name, input box, and prompt information can be clearly displayed, avoiding overcrowding or excessive blank space.

[0105] The said data types include String, Number, and Date.

[0106] The said field length is the maximum character limit for string-type fields.

[0107] The said whether it is mandatory refers to whether a certain field is a mandatory item in the delivery service business form.

[0108] It should be noted that the field name is the unique identifier of each field in the delivery service business form, used to distinguish different fields.

[0109] Determine the field requirements in the delivery service business form according to the obtained delivery service types.

[0110] Subsequently, design a form template according to the requirements analysis results, and arrange the form fields according to the importance factors of each field name. The arrangement rule is that the field name with the highest importance factor is arranged in the first column of the delivery service business form, the field name with the second highest importance factor is arranged in the second column of the delivery service business form, and so on.

[0111] Configure the column width for each column according to the preset display space.

[0112] Step 2: Data source configuration and data extraction;

[0113] Determine the data source of the delivery service business form and its data source parameters.

[0114] The data source parameters include database type and connection information.

[0115] The database types include MySQL, Oracle, RDBMS, and NoSQL.

[0116] The connection information includes database name DatabaseName, service name ServiceName, hostname Hostname, port number PortNumber, username Username, and password Password.

[0117] According to the field requirements in the form template, retrieve the preset data extraction script and extract the required data from the data source.

[0118] Step 3: Data preprocessing and field matching;

[0119] Perform data cleaning and field matching on the extracted data, remove the duplicate parts in the captured data, and match the required data extracted from the data source with the preset field names.

[0120] The specific process of the data cleaning is as follows:

[0121] Through the formula Perform deduplication on the extracted data, where unique is the deduplication function. D is the set of all extracted data; where D' is the set of duplicate data, d is a certain field element in the data set; d' is the duplicate field element.

[0122] The specific process of the field matching is as follows:

[0123] S301: Data preparation;

[0124] Define the data set: Denote the data set extracted from the data source as D = {d1, d2,..., dn}, and each sample di contains multiple feature values representing the content of different fields;

[0125] S302: Text feature extraction. For each field sample di, extract text features, including string length L(di) and TF-IDF vectorization feature values ; where i = 1, 2,..., n.

[0126] Construct a feature vector for each field: . Where is the field name to which the field di belongs, including delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method; where It is an attribution label, indicating whether the field di belongs to the current field name. If so, the value is 1; otherwise it is 0.

[0127] S303. Establish a support vector machine model;

[0128] Use the support vector machine model to train the extracted features. The goal is to find an optimal hyperplane to maximize the margin between samples.

[0129] The support vector machine model is specifically: , where w is the weight vector; b is the bias term; where C is the penalty parameter, controlling the tolerance for misclassification; where is the slack variable, used to handle the non-linearly separable case.

[0130] Set the constraint conditions: ; where is the feature mapping function, used to map the input feature vector to a high-dimensional space.

[0131] S304. Model training;

[0132] Set a set of predefined field sets, F = {f1, f2,..., fn} as training samples, where each field fi has a feature vector: . Among them, are all the field names to which the field fi truly belongs and the values are all 1; Use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training.

[0133] S305. Application of training results;

[0134] After the support vector machine model training is completed, use the trained support vector machine model to predict new data. For each new sample, input it into the trained support vector machine model to obtain its matching field name.

[0135] It should be noted that the basic goal of the support vector machine model is to find a hyperplane that can maximize the margin, classify fields, and identify which specific field name it belongs to. The purpose of this process is to identify which category of information a certain field belongs to among delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method through machine learning, realize automated field matching and classification, reduce manual intervention, and improve the speed and efficiency of data processing.

[0136] Step Four. Form generation and rendering;

[0137] Generate a specific form instance based on the form template and data. Render the form using front-end technologies.

[0138] Use a template engine to combine the form template and data to generate a form instance in HTML format. Use the Bootstrap front-end framework for styling to improve the aesthetics and usability of the form.

[0139] Step Five: Form Validation and Error Handling;

[0140] Perform duplicate value processing on the generated delivery service business form and merge duplicate rows. Define a unique identifier for each delivery, unique_id = TradeDate + SecurityCode + Buyername + SellerName. Where TradeDate is the hash value of the delivery date field; SecurityCode is the hash value of the delivery number field; Buyername is the hash value of the seller name field; SellerName is the hash value of the seller name field.

[0141] Subsequently, based on the unique identifier, detect duplicate records in the delivery service business form and merge the rows with the same unique identifier.

[0142] Validate the generated delivery service business form to ensure the integrity and accuracy of the data. For data that fails validation, perform error handling and prompt the user to make corrections.

[0143] The specific process is as follows: Check each field to confirm whether there is an empty string or null. If so, highlight the field and output an error.

[0144] Step Six: Form Storage and Distribution;

[0145] Store the generated delivery service business form in the database and file system for subsequent business processing. At the same time, distribute the delivery service business form to relevant personnel or systems to ensure the smooth progress of the business process.

[0146] The form distribution is implemented through email and message queue methods.

[0147] Please refer to Figure 2 As shown, a delivery service business form generation system includes a template design module, a database, a machine learning module, a field matching module, a validation and error handling module, and a storage and distribution module.

[0148] The template design module conducts a requirements analysis of the delivery service business and confirms the field requirements for various delivery service business forms required during the business process.

[0149] Obtain the delivery service types corresponding to the delivery service business form, including physical delivery, warehouse delivery, factory warehouse delivery, and futures-for-cash.

[0150] Further, determine the field requirements in the delivery service business form according to the obtained delivery service types.

[0151] The said field requirements include field name, data type, field length, and whether it is required.

[0152] The said field names include delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method.

[0153] Each field name corresponds to a preset importance factor, providing a quantitative basis for the subsequent layout of the delivery service business form.

[0154] Each field name corresponds to a preset display space, ensuring that the field name, input box, and prompt information can be clearly displayed, avoiding overcrowding or excessive blank space.

[0155] The said data types include String, Number, and Date.

[0156] The said field length is the maximum character limit for string-type fields.

[0157] The said whether it is required refers to whether a certain field is a required item in the delivery service business form.

[0158] Determine the field requirements in the delivery service business form according to the obtained delivery service types.

[0159] Subsequently, design a form template according to the results of the requirements analysis, and arrange the form fields according to the importance factors of each field name. The arrangement rule is that the field name with the highest importance factor is arranged in the first column of the delivery service business form, the field name with the second highest importance factor is arranged in the second column of the delivery service business form, and so on.

[0160] The database is the storage center of delivery business information and the data source of the delivery service business form.

[0161] The database includes several sub-databases, and the type of each sub-database includes MySQL, Oracle, RDBMS, and NoSQL

[0162] Each sub-database has a uniquely matched database name DatabaseName, service name ServiceName, host name Hostname, port number PortNumber, user name Username, and password Password.

[0163] According to the field requirements in the form template, retrieve the preset data extraction script and extract the required data from the data source.

[0164] The machine learning module establishes a support vector machine model for field name matching and conducts model training.

[0165] Define a data set. Denote the data set extracted from the data source as D = {d1, d2,..., dn}. Each sample di contains multiple feature values representing the content of different fields.

[0166] For each field sample di, extract text features, including the string length L(di) and TF-IDF vectorization feature values. ; where i = 1, 2,..., n.

[0167] Construct a feature vector for each field: . Where is the field name to which the field di belongs, including the delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method; where is the attribution label indicating whether the field di belongs to the current field name. If so, the value of is 1; otherwise it is 0.

[0168] Use the support vector machine model to train the extracted features. The goal is to find an optimal hyperplane to maximize the margin between samples.

[0169] The support vector machine model is specifically: , where w is the weight vector; b is the bias term; where C is the penalty parameter that controls the tolerance for misclassification; where is the slack variable used to handle the non-linearly separable case.

[0170] Set the constraint conditions: ; where is the feature mapping function used to map the input feature vector to a high-dimensional space.

[0171] Set a predefined set of fields F = {f1, f2,..., fn} as training samples. Each field fi has a feature vector: . Where the are all the field names to which the field fi truly belongs and the values of are all 1; Use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training.

[0172] The field matching module retrieves the training results of the machine learning module, matches the fields extracted from the database one by one to the preset field names, and outputs the field names corresponding to the true attribution of each field. 。

[0173] The verification and error handling module performs duplicate value processing on the generated delivery service business form and merges duplicate rows. Define the unique identifier for each delivery unique_id = TradeDate + SecurityCode + Buyername + SellerName. Where TradeDate is the hash value of the delivery date field; SecurityCode is the hash value of the delivery number field; Buyername is the hash value of the seller name field; SellerName is the hash value of the seller name field.

[0174] Subsequently, based on the unique detection of duplicate records, merge the rows with the same unique identifier in the delivery service business form.

[0175] Verify the generated delivery service business form to ensure the integrity and accuracy of the data. For the data that fails the verification, perform error handling and prompt the user to make corrections.

[0176] The specific process is as follows: Check each field to confirm whether there is an empty string or null. If so, highlight the field and output error.

[0177] The storage and distribution module stores the generated delivery service business form in the database and the file system for subsequent business processing. At the same time, distribute the delivery service business form to relevant personnel or systems to ensure the smooth progress of the business process.

[0178] It should be understood that the terms "including" and "comprising" used in the specification and claims of this disclosure indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0179] It should also be understood that the terms used in this disclosure specification are only for the purpose of describing specific embodiments and are not intended to limit this disclosure. As used in this disclosure specification and claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in this disclosure specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations;

[0180] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only the specific embodiments. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A method for generating a delivery service business form, characterized in that: It includes the following steps: Step 1, Requirement analysis and form template design: Conduct requirement analysis on the delivery service business, and confirm the field requirements of various delivery service business forms required in the business process; Step 2, Data source configuration and data extraction; Determine the data source of the delivery service business form and its data source parameters. According to the field requirements in the form template, retrieve the preset data extraction script, and extract the required data from the data source; Step 3, Data preprocessing and field matching: Perform data cleaning and field matching on the extracted data, remove the duplicate parts in the captured data, and match the required data extracted from the data source with the preset field names; The specific process of data cleaning is: By formula Perform deduplication processing on the extracted data, where unique is the deduplication function; D is the set of all extracted data; D' is the set of duplicate data, d is a field element in the data set; d' is the duplicate field element; The specific process of field matching is: S301, Data preparation; Define the data set: Denote the data set extracted from the data source as D = {d1, d2,..., dn}, and each sample di contains multiple feature values, representing the content of different fields; S302. Text feature extraction. For each field sample di, extract text features, including the string length L(di) and the TF-IDF vectorization feature value ; where i = 1, 2,..., n; Construct a feature vector for each field: ; where is the field name to which the field di belongs, including the delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method; where is the attribution label, indicating whether the field di belongs to the current field name; if so, the value is 1; otherwise it is 0; S303, Establish a support vector machine model; Use the support vector machine model to train the extracted features; The goal is to find an optimal hyperplane to maximize the interval between samples; The support vector machine model is specifically as follows: , where w is the weight vector; b is the bias term; where C is the penalty parameter that controls the tolerance for misclassified instances; where is the slack variable, which is used to handle the case of non-linearly separable data; Set constraint conditions: ; where is a feature mapping function used to map the input feature vector to a high-dimensional space; S304, Model training; Set a set of predefined field sets, F = {f1, f2,..., fn} as training samples, where each field fi has a feature vector: ; among which are all the field names to which the field fi truly belongs and the values of all are 1; Use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training; S305, Application of training results; After the support vector machine model training is completed, use the trained support vector machine model to predict new data; For each new sample, input it into the trained support vector machine model to obtain its matching field name; Step 4, Form generation and rendering: Generate a specific form instance according to the form template and data; Use front-end technology to render the form; Step 5, Form verification and error handling; Perform duplicate value processing on the generated delivery service business form; Step 6, Form storage and distribution: Store the generated delivery service business form in the database and file system, and distribute the delivery service business form to relevant personnel or systems.

2. The method for generating a delivery service business form according to claim 1, wherein The specific process of confirming the field requirements of various delivery service business forms required in the business process is: Obtain the delivery service type corresponding to the delivery service business form, including physical delivery, warehouse delivery, warehouse receipt delivery, and exchange for physicals; Determine the field requirements in the delivery service business form according to the obtained delivery service type; The said field requirements include field name, data type, field length, and whether it is required; The said field names include delivery number, delivery date, security code, trading price, delivery quantity, buyer name, seller name, and delivery method; Each field name corresponds to a preset importance factor, providing a quantitative basis for the subsequent layout of the delivery service business form; Each field name corresponds to a preset display space to ensure that the field name, input box, and prompt information can be clearly displayed, avoiding overcrowding or excessive blank space; The said data types include String, Number, and Date; The said field length is the maximum character number limit for string-type fields; The said whether it is required refers to whether a certain field is a required item in the delivery service business form; Determine the field requirements in the delivery service business form according to the obtained delivery service type; Subsequently, a form template is designed based on the results of the requirements analysis. The form fields are arranged according to the importance factors of each field name. The arrangement rule is that the field name with the highest importance factor is arranged in the first column of the delivery service business form, the field name with the second highest importance factor is arranged in the second column of the delivery service business form, and so on. The column width is configured for each column according to the preset display space.

3. A method for generating a delivery service business form according to claim 1, characterized in that: The specific data sources and their data source parameters are as follows: Database types, including MySQL, Oracle, RDBMS, and NoSQL; Connection information, including database name DatabaseName, service name ServiceName, hostname Hostname, port number PortNumber, username Username, and password Password.

4. A method for generating a delivery service business form according to claim 1, characterized in that The specific process of data cleaning for the extracted data is as follows: Through the formula Deduplicate the extracted data, where unique is the deduplication function; D is the set of all extracted data; D' is the set of duplicate data, d is a field element in the dataset; d' is the duplicate field element.

5. A method for generating a delivery service business form according to claim 1, characterized in that: Field matching for the extracted data is achieved through the training and application of a support vector machine; After the support vector machine model training is completed, the trained support vector machine model is used to predict new data. For each new sample, it is input into the trained support vector machine model to obtain the matching field name.

6. A method for generating a delivery service business form according to claim 5, characterized in that, The specific process of support vector machine training is as follows: Data preparation; define the dataset: Denote the dataset extracted from the data source as D = {d1, d2,..., dn}. Each sample di contains multiple feature values representing the content of different fields; Text feature extraction. For each field sample di, text features are extracted, including the string length L(di) and the TF-IDF vectorized feature values ; where i = 1, 2,..., n; Construct a feature vector for each field: ; where is the field name to which the field di belongs, including the delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method; where is the attribution label, indicating whether the field di belongs to the current field name; if so, the value is 1; otherwise it is 0; Establish a support vector machine model; Use the support vector machine model to train the extracted features; The goal is to find an optimal hyperplane to maximize the margin between samples; The specific support vector machine model is: , where w is the weight vector; b is the bias term; C is the penalty parameter, which controls the tolerance to the wrong classification; is a slack variable used to handle nonlinear separable situations; Set the constraint conditions: ; where is a feature mapping function used to map the input feature vector to a high-dimensional space; Model training; Set a set of predefined field collections, F = {f1, f2,..., fn} as training samples, where each field fi has a feature vector: ; among which are all the field names to which the field fi truly belongs and the values of all are 1; Use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training.

7. A method for generating a delivery service business form according to claim 1, characterized in that The specific process of duplicate value processing for the generated delivery service business form is as follows: Define the unique identifier for each delivery unique_id = TradeDate + SecurityCode + Buyername + SellerName; where TradeDate is the hash value of the delivery date field; SecurityCode is the hash value of the delivery number field; Buyername is the hash value of the seller name field; SellerName is the hash value of the seller name field; Subsequently, based on the unique detection of duplicate records, the rows with the same unique identifier are merged in the delivery service business form; Verify the generated delivery service business form to ensure the integrity and accuracy of the data. For the data that fails the verification, error handling is performed to prompt the user to make corrections; The specific process is as follows: Check each field to confirm whether there is an empty string or null. If so, highlight the field and output error.

8. A delivery service business form generation system for implementing the delivery service business form generation method described in any one of claims 1-7, characterized in that, Including a template design module, a database, a machine learning module, a field matching module, a verification and error handling module, and a storage and distribution module; The template design module conducts a requirements analysis of the delivery service business to confirm the field requirements of various delivery service business forms required in the business process; Obtain the delivery service types corresponding to the delivery service business form, including physical delivery, warehouse delivery, factory warehouse delivery, and futures-for-cash; Determine the field requirements in the delivery service business form according to the obtained delivery service type; The said field requirements include field name, data type, field length, and whether it is mandatory; The said field names include delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method; Each field name corresponds to a preset importance factor, providing a quantitative basis for the layout of the subsequent delivery service business form; Each field name corresponds to a preset display space to ensure that the field name, input box, and prompt information can be clearly displayed, avoiding overcrowding or excessive blank space; The said data types include String, Number, and Date; The said field length is the maximum character limit for string-type fields; The said whether it is mandatory indicates whether a certain field is a mandatory item in the delivery service business form; Determine the field requirements in the delivery service business form according to the obtained delivery service type; Subsequently, design a form template according to the result of requirement analysis, and arrange the form fields according to the importance factors of each field name. The arrangement rule is that the field name with the highest importance factor is arranged in the first column of the delivery service business form, the field name with the second highest importance factor is arranged in the second column of the delivery service business form, and so on; The database is the storage center of delivery business information and the data source of the delivery service business form; The database includes several sub-databases, and the type of each sub-database includes MySQL, Oracle, RDBMS, and NoSQL Each sub-database has a uniquely matched database name DatabaseName, service name ServiceName, hostname Hostname, port number PortNumber, username Username, and password Password; According to the field requirements in the form template, retrieve the preset data extraction script and extract the required data from the data source; The machine learning module establishes a support vector machine model for field name matching and conducts model training; Define a data set, denote the data set extracted from the data source as D={d1, d2,..., dn}, and each sample di contains multiple feature values representing the content of different fields; For each field sample di, text features are extracted, including the string length L(di) and the TF-IDF vectorized feature values ; where i = 1, 2,..., n; Construct a feature vector for each field: ; where is the field name to which the field di belongs, including the delivery number, delivery date, security code, transaction price, delivery quantity, buyer name, seller name, and delivery method; where is the attribution label, indicating whether the field di belongs to the current field name; if so, the value is 1; otherwise it is 0; Use the support vector machine model to train the extracted features; The goal is to find an optimal hyperplane to maximize the interval between samples; The specific support vector machine model is: , where w is the weight vector; b is the bias term; C is the penalty parameter, which controls the tolerance to the wrong classification; is a slack variable used to handle nonlinear separable situations; Set constraint conditions: ; where is a feature mapping function used to map the input feature vector to a high-dimensional space; Set a set of predefined field sets, F = {f1, f2,..., fn} as training samples, where each field fi has a feature vector: ; among which are all the field names to which the field fi truly belongs and the values of all are 1; Use F = {f1, f2,..., fn} as training samples and input them into the support vector machine model for training; The field matching module retrieves the training results of the machine learning module, matches each field extracted from the database to a preset field name, and outputs the field names corresponding to the true ownership of each field ; The verification and error handling module performs duplicate value processing on the generated delivery service business form and merges duplicate rows; define the unique identifier for each delivery as unique_id = TradeDate + SecurityCode + Buyername + SellerName; where TradeDate is the hash value of the delivery date field; SecurityCode is the hash value of the delivery number field; Buyername is the hash value of the seller name field; SellerName is the hash value of the seller name field; Subsequently, based on the unique detection of duplicate records, merge the rows with the same unique identifier in the delivery service business form; Verify the generated delivery service business form to ensure the integrity and accuracy of the data; perform error handling on data that fails verification and prompt the user to make corrections; The specific process is: check each field to see if there is an empty string or null; if so, highlight the field and output an error; The storage and distribution module stores the generated delivery service business form in the database and file system to facilitate subsequent business processing; at the same time, it distributes the delivery service business form to relevant personnel or systems to ensure the smooth progress of the business process.

Images