Intelligent bidding assisting method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses an intelligent bidding auxiliary method and device, electronic equipment and a storage medium, and the method is applied to a back-end server, and comprises the steps: receiving initial bidding data of a bidding project which is sent by a front end and is submitted by a user; calling a data processing service, and performing format conversion and analysis on the initial bidding data; and calling a model reasoning service, and generating a bidding management file according to an analysis result and the supplementary bidding data of the bidding project. The technical scheme provided by the embodiment of the invention can be suitable for enterprise bidding scenes requiring high efficiency, accuracy and automation, and can solve the problems of low efficiency and frequent errors caused by complex and time-consuming bidding process and dependence on manual operation in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an intelligent bidding assistance method, device, electronic equipment and storage medium. Background Art

[0002] In the traditional bidding process, bidders usually face a series of complex and time-consuming operations, including a large number of document preparation, data analysis and information collation tasks. With the intensification of market competition, the efficiency and accuracy of the bidding process directly affect the competitiveness of enterprises. However, the existing bidding process mainly relies on manual operations, which not only significantly increases the workload of bidders, but also easily leads to errors caused by human negligence, thus seriously affecting the success rate of bidding.

[0003] Especially in the bidding of large projects, the preparation of bid documents requires processing a large amount of text and data, covering multiple aspects such as enterprise qualifications, technical solutions, quotation strategies, etc. This process places extremely high demands on the accuracy of information, the standardization of documents, and the formulation of bidding strategies. Mistakes in any link may lead to the failure of the bid, which in turn brings significant economic losses to the enterprise. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides an intelligent bidding assistance method, device, electronic device and storage medium to solve the problems in the prior art that the bidding process is complex and time-consuming, and relies on manual operation, resulting in low efficiency and frequent errors.

[0005] In a first aspect, an embodiment of the present invention provides an intelligent bidding assistance method, which is applied to a backend server, and the method includes:

[0006] Receive the initial bidding data of the bidding project submitted by the user sent by the front end;

[0007] Calling a data processing service to convert and parse the initial bidding data;

[0008] The model inference service is called to generate a bidding management document according to the parsing result and the supplementary bidding data of the bidding project.

[0009] Further, the initial bidding data includes an initial bidding document;

[0010] Calling data processing services to convert and parse the initial bidding data, including:

[0011] Call the data processing service to perform the following operations:

[0012] Converting the initial bidding document into a portable document format;

[0013] Perform layout recognition on the format-converted initial bidding documents and split them into structured text blocks, data tables, and graphic elements.

[0014] Furthermore, the method further comprises:

[0015] According to the different types of stored content, the following contents are stored in the corresponding storage areas in the data storage module: the initial bidding data, the analysis results of the data processing service, the intermediate data of the model reasoning service and the bidding management file.

[0016] Further, the unstructured data in the initial bidding data and the bidding management file are stored in the file storage system in the data storage module;

[0017] Storing the structured data in the initial bidding data, the parsing results of the data processing service, and the non-vectorized data in the intermediate data of the model reasoning service in the relational database in the data storage module;

[0018] The parsing result of the data processing service and the vectorized data in the intermediate data of the model reasoning service are stored in the vector database in the data storage module.

[0019] Furthermore, the model inference service is called to generate a bidding management document according to the parsing result and the supplementary bidding data of the bidding project, including:

[0020] Calling a pre-trained retrieval enhancement generation artificial intelligence model to extract set key vectorized data from the parsing results and the supplementary bidding data of the bidding project;

[0021] Call a pre-trained text generation artificial intelligence model to perform reasoning based on the set key vectorized data and the parsing results and the non-vectorized data in the supplementary bidding data of the bidding project to generate a bidding management document.

[0022] Furthermore, after calling the model inference service and generating a bidding management document according to the parsing result and the supplementary bidding data of the bidding project, the method further includes:

[0023] Sending the bidding management document to the front end for display;

[0024] Receive feedback from the front end regarding the bidding management document;

[0025] The model reasoning service is called to regenerate the bidding management document according to the feedback, the analysis results and the supplementary bidding data of the bidding project.

[0026] In a second aspect, an embodiment of the present invention provides an intelligent bidding assistance device, which is applied to a backend server, and the device includes:

[0027] A data receiving unit, used for receiving the initial bidding data of the bidding project submitted by the user and sent by the front end;

[0028] A data processing unit, used to call a data processing service to perform format conversion and analysis on the initial bidding data;

[0029] The file generation unit is used to call the model reasoning service and generate a bidding management file according to the parsing result of the data processing unit and the supplementary bidding data of the bidding project.

[0030] Further, the initial bidding data includes an initial bidding document;

[0031] The data processing unit is specifically used for:

[0032] The data processing service is called to perform the following operations: converting the initial bidding document into a portable document format; performing layout recognition on the initial bidding document after format conversion, and splitting it into structured text blocks, data tables and graphic elements.

[0033] Furthermore, the device also includes a storage unit, which is used to:

[0034] According to the different types of stored content, the following contents are stored in the corresponding storage areas in the data storage module: the initial bidding data, the analysis results of the data processing service, the intermediate data of the model reasoning service and the bidding management file.

[0035] Furthermore, the storage unit is specifically used for:

[0036] Storing the unstructured data in the initial bidding data and the bidding management file in the file storage system in the data storage module;

[0037] Storing the structured data in the initial bidding data, the parsing results of the data processing service, and the non-vectorized data in the intermediate data of the model reasoning service in the relational database in the data storage module;

[0038] The parsing result of the data processing service and the vectorized data in the intermediate data of the model reasoning service are stored in the vector database in the data storage module.

[0039] Furthermore, the file generation unit is specifically used for:

[0040] Calling a pre-trained retrieval enhancement generation artificial intelligence model to extract set key vectorized data from the parsing results and the supplementary bidding data of the bidding project;

[0041] Call a pre-trained text generation artificial intelligence model to perform reasoning based on the set key vectorized data and the parsing results and the non-vectorized data in the supplementary bidding data of the bidding project to generate a bidding management document.

[0042] Furthermore, the device also includes a file updating unit, which is used to:

[0043] Sending the bidding management document to the front end for display;

[0044] Receive feedback from the front end regarding the bidding management document;

[0045] The file generation unit is instructed to call a model reasoning service to regenerate a bidding management file according to the feedback, the parsing result and the supplementary bidding data of the bidding project.

[0046] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a housing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the housing, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the intelligent bidding assistance method described in the first aspect above.

[0047] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more central processors to implement the intelligent bidding assistance method described in the first aspect above.

[0048] The technical solution provided by the embodiment of the present invention realizes the comprehensive automation of the bidding process, significantly reducing the workload and burden of bidders. By using precise data analysis technology and advanced model reasoning capabilities, the solution effectively reduces errors caused by human factors and ensures the high precision and accuracy of bidding data. In addition, its efficient execution characteristics significantly accelerate the entire bidding process and effectively shorten the bidding cycle. More importantly, the solution can automatically generate standardized and professional bidding management documents based on the model, greatly improving the professionalism and competitiveness of the bidding solution, thereby increasing the winning rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A flowchart of an intelligent bidding assistance method provided in Embodiment 1 of the present invention;

[0051] Figure 2 An interactive schematic diagram of an example of an intelligent bidding assistance method provided in the first embodiment of the present invention;

[0052] Figure 3 A schematic diagram of the structure of an intelligent bidding assistance device provided in Embodiment 2 of the present invention;

[0053] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0055] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] The embodiments of the present invention deeply combine the bidding scenario and develop a vertical AI (artificial intelligence) intelligent application for specific business needs. The application can accurately process complex bidding requirements, quickly generate customized bidding management documents, improve the efficiency and success rate of the bidding process, and help enterprises gain an advantageous position in the fierce market competition. The following is a detailed description of each embodiment.

[0057] Embodiment 1

[0058] This embodiment provides an intelligent bidding assistance method, which can be applied to a backend server and specifically executed by a corresponding intelligent bidding assistance device, and is suitable for enterprise bidding scenarios that require high efficiency, accuracy and automation. Figure 1 , the method includes the following steps 101-103.

[0059] Step 101: Receive initial bidding data of a bidding project submitted by a user and sent by a front end.

[0060] In this step, the front end can be a web application or a mobile application. The front end displays a bidding management interactive interface, through which users submit initial bidding data for the bidding project, including: uploading initial bidding documents, entering initial bidding text information, and specific content may include: bidding documents, bidder qualification certificates, preliminary technical solution descriptions, performance cases, etc. A bidding project refers to a specific bidding activity or project. Each bidding project has its specific requirements and background information. In contrast to the front end, the back end server receives the initial bidding data for the bidding project submitted by the user through the front end bidding management interactive interface.

[0061] Step 102: Call the data processing service to convert and parse the initial bidding data.

[0062] This step is a key step in preprocessing the initial bidding data, which involves calling a dedicated data processing service to perform the following two tasks: format conversion and parsing. A data processing service refers to a service module designed specifically to process various types of data. It can be an independently deployed service or a functional module integrated in the back-end server, responsible for performing specific data processing tasks. Among them:

[0063] Format conversion, converting the initial bidding data into a standard format that can be further processed by the back-end server, ensuring that all input data has a unified structure to facilitate subsequent parsing and processing; conversion operations may include: converting unstructured or semi-structured text data into a structured format (such as JSON, XML); converting different types of file formats into a format suitable for back-end server processing;

[0064] Parsing: extracting the set useful information (such as company qualifications, personnel certificates, technical parameters, performance cases, etc.) from the converted initial bidding data and organizing it into a structure that is easy to understand and use; parsing operations may include: using natural language processing (NLP) technology to extract entities (such as names, organizations, dates, etc.) from text data; identifying data in tables and charts and converting them into structured forms; performing layout analysis to divide the document into different parts.

[0065] Exemplarily, the document processing service in the data processing service is called to perform the following operations: convert the initial bidding document into a portable document format; perform layout recognition on the initial bidding document after format conversion, and split it into structured text blocks, data tables, and graphic elements. In the process of implementing the above operations, the main goal is to convert the unstructured or semi-structured document content into structured information that is easy to understand and use, so as to facilitate subsequent information extraction and file generation. This process involves extracting various types of structured content from the converted document, including text blocks, data tables, and graphic elements.

[0066] In actual operation, OCR (Optical Character Recognition) technology and page layout analysis tools can be used. These tools can identify the location and hierarchy of various elements such as titles, paragraphs, lists, tables, and images in the document. Next, the identified text parts will be further subdivided into independent text blocks, which can be divided by paragraphs, sentences or keywords. For data tables, the data information in the table will be identified and extracted, and then the data will be converted into a structured format, such as CSV (Comma Separated Values) or JSON (JavaScript Object Notation), for subsequent further processing and analysis. At the same time, for graphic elements, graphic elements such as images and charts in the document will be identified and separated, while retaining the location information of these graphic elements and the text associated with them to ensure the integrity and accuracy of the document information.

[0067] The analysis results may include two types of data in terms of presentation form: vectorized data and non-vectorized data. In the embodiment of the present invention:

[0068] Vectorized data is structured data processed by vectorization, and is used as an information source to support similarity matching and reasoning of model reasoning services. Usually, this type of data may include: vectorized representation data converted from text content, feature vectors extracted from graphic elements, and numerical vectors converted from specific data and technical parameters in data tables;

[0069] Non-vectorized data refers to structured data that has not been vectorized. It is used for query, statistics, and analysis by subsequent model inference services to provide support for bidding decisions. Usually, this type of data may include: sentences and paragraphs in text content (which can be preliminarily analyzed by word segmentation, removal of stop words, etc.), key-value pairs or JSON format data obtained by converting data in data tables and CSV files, and graphic elements in documents that have been identified and separated, as well as their location information and associated text.

[0070] Step 103: Call the model reasoning service to generate a bidding management document according to the analysis result and the supplementary bidding data of the bidding project.

[0071] In this step, when calling the model inference service to generate the bid management document, in addition to the initial bid data, the supplementary bid data is also one of the key inputs. As a supplement to the initial bid data, the supplementary bid data is used to enhance and refine the initial bid data to ensure that the generated bid management document is more accurate, complete and competitive. The supplementary bid data may include multiple types of information and should be structured before being processed by the model inference service. It is also divided into two types of data: vectorized data and non-vectorized data. It should be noted that in order to ensure the refinement and consistency of the model input data, before calling the model inference service, the natural language processing (NLP) technology and text comparison tools can be used to identify and delete the redundant data in the parsing results of the initial bid data and the structured supplementary bid data.

[0072] In specific implementation, the target artificial intelligence model can be selected according to the generation requirements of the bidding management document, and then the selected target artificial intelligence model can be used to generate the bidding management document after reasoning based on the analysis results and the supplementary bidding data of the bidding project. Among them, the target artificial intelligence model should at least have the ability to process text, data and generate corresponding files.

[0073] As a preferred implementation, first, a pre-trained retrieval enhancement generation artificial intelligence model is called to extract the set key vectorized data from the parsing results and the supplementary bidding data of the bidding project. Specifically, the extraction operation includes: according to the vectorized data of the requirements and technical specifications in the bidding documents, the most relevant vectorized data is retrieved from the historical bidding vectorized data as the first key vectorized data; the vectorized data of the bidder's qualification certificate, technical solution description, and performance case are used as the second key vectorized data. Secondly, the pre-trained text generation artificial intelligence model is called to infer the set key vectorized data and the non-vectorized data in the parsing results and the supplementary bidding data of the bidding project to generate a bidding management file. Among them, the bidding management file is not limited to the bid response file directly submitted to the tenderer, but also includes a series of management and planning documents that support the smooth progress of bidding activities, such as market research and competitor analysis reports, bidding strategies and timetables, risk assessment reports, cost estimates and budgets, etc.

[0074] The model reasoning service needs to process a large amount of input data. If all vectorized and non-vectorized data are used as input without distinction, and only one artificial intelligence model is used, the service processing speed will be slow, resource utilization will be low, model accuracy will be damaged, and scalability and flexibility will be limited. In the above preferred implementation, an artificial intelligence model is first used to extract the set key vectorized data, and then another artificial intelligence model is used to reason and generate bidding management documents in combination with non-vectorized data. This not only improves the efficiency, accuracy and interpretability of the system, but also optimizes resource utilization, improves flexibility, reduces redundancy and noise, and can generate high-quality, professional and competitive bidding documents while maintaining high efficiency, thereby significantly improving the success rate of bidding.

[0075] It should be noted that the bidding management document generated by the model reasoning service can only be a preliminary document framework and content. Further, based on the model reasoning results, build a complete framework for the bidding management document, including the cover, directory, and text; fill the preliminary content generated by the model reasoning service into the complete document framework; optimize and adjust the content according to the bidding requirements and project characteristics to ensure compliance with the provisions and requirements of the bidding documents; adjust the format of the bidding management document, including font, font size, paragraph spacing, etc., to ensure that the document is neat and easy to read; carefully proofread the document content to ensure that there are no typos or missing information.

[0076] Preferably, the back-end server is a large electronic device that integrates multiple services to achieve localized data storage and processing, ensure data security during the bidding process, effectively prevent data leakage and external attacks, and meet the company's strict requirements for data protection.

[0077] Furthermore, the intelligent bidding assistance method in this embodiment also includes:

[0078] According to the different types of stored content, the following contents are stored in the corresponding storage areas in the data storage module: initial bidding data, analysis results of data processing services, intermediate data of model reasoning services and the bidding management files.

[0079] Specifically, the unstructured data and the bidding management files in the initial bidding data are stored in the file storage system in the data storage module;

[0080] Storing structured data in the initial bidding data, as well as the parsing results of the data processing service and non-vectorized data in the intermediate data of the model reasoning service, into a relational database in the data storage module;

[0081] The parsing results of the data processing service and the vectorized data in the intermediate data of the model reasoning service are stored in the vector database in the data storage module.

[0082] By storing different types of data in storage areas that best suit their characteristics, data access speed and processing efficiency can be significantly improved, reducing the time and complexity of finding specific types of data in large amounts of mixed data.

[0083] On the basis of the above scheme, after calling the model reasoning service and generating the bidding management file according to the parsing result and the supplementary bidding data of the bidding project, the method further includes:

[0084] Send bidding management documents to the front end for display;

[0085] Receive feedback from the front end on bidding management documents;

[0086] The model reasoning service is called to regenerate the bidding management document according to the feedback, analysis results and supplementary bidding data of the bidding project.

[0087] Specifically, the above process can be repeated to adjust and optimize the generated bidding management documents until the final requirements are met. Feedback can include opinions and suggestions from bidders, tenderers, and evaluation experts.

[0088] The following is a specific example to explain in detail the intelligent bidding assistance method provided by this embodiment. Figure 2 , the method comprises the following steps:

[0089] Step 1: The front end transmits the bidding document of a bidding project submitted by the user based on the bidding management interactive interface to the service control module on the back end server;

[0090] Step 2: The service control module on the back-end server calls the internal document processing service to convert and parse the bidding document; the parsing result is returned to the service control module and stored in the data storage module;

[0091] Step 3: The service control module on the back-end server calls the internal model reasoning service: generates a bidding management file after reasoning based on the analysis results and the supplementary bidding data of the bidding project; returns the bidding management file to the service control module and stores it in the data storage module at the same time;

[0092] Step 4: The service control module on the back-end server transmits the bidding management file to the front-end, and the front-end displays the bidding management file to the user through the bidding management interface;

[0093] Step 5: The front end transmits the feedback on the bidding management document submitted by the user based on the bidding management interactive interface to the service control module on the back end server;

[0094] Step 6: The service control module on the back-end server calls the internal model reasoning service: regenerates the bidding management file after reasoning based on the feedback, the analysis results and the supplementary bidding data of the bidding project; returns the new bidding management file to the service control module and stores it in the data storage module at the same time;

[0095] Repeat steps 4-6 above until the generated new bidding management document meets user requirements.

[0096] Embodiment 2

[0097] This embodiment provides an intelligent bidding assistance device, which is applied to a backend server and implemented by software and / or hardware to execute the intelligent bidding assistance method described in the embodiment of the present invention. Figure 3 , the device specifically includes the following units:

[0098] The data receiving unit 301 is used to receive the initial bidding data of the bidding project submitted by the user and sent by the front end;

[0099] The data processing unit 302 is used to call the data processing service to convert and parse the format of the initial bidding data;

[0100] The file generation unit 303 is used to call the model reasoning service to generate a bidding management file according to the parsing result of the data processing unit 302 and the supplementary bidding data of the bidding project.

[0101] Exemplarily, the initial bidding data includes an initial bidding document;

[0102] The data processing unit 302 is specifically configured to:

[0103] The data processing service is called to perform the following operations: converting the initial bidding document into a portable document format; performing layout recognition on the initial bidding document after format conversion, and splitting it into structured text blocks, data tables and graphic elements.

[0104] Furthermore, the intelligent bidding assistance device in this embodiment further includes a storage unit 300, which is used to:

[0105] According to the different types of stored content, the following contents are stored in the corresponding storage areas in the data storage module: the initial bidding data; the analysis results of the data processing service; the intermediate data of the model reasoning service and the bidding management file.

[0106] As a preferred implementation, the storage unit 300 is specifically used for:

[0107] Storing the unstructured data in the initial bidding data and the bidding management file in the file storage system in the data storage module;

[0108] Storing the structured data in the initial bidding data, the parsing results of the data processing service, and the non-vectorized data in the intermediate data of the model reasoning service in the relational database in the data storage module;

[0109] The parsing result of the data processing service and the vectorized data in the intermediate data of the model reasoning service are stored in the vector database in the data storage module.

[0110] Exemplarily, the file generating unit 303 is specifically used for:

[0111] Calling a pre-trained retrieval enhancement generation artificial intelligence model to extract set key vectorized data from the parsing results and the supplementary bidding data of the bidding project;

[0112] Call a pre-trained text generation artificial intelligence model to perform reasoning based on the set key vectorized data and the parsing results and the non-vectorized data in the supplementary bidding data of the bidding project to generate a bidding management document.

[0113] On the basis of the above scheme, the intelligent bidding auxiliary device in this embodiment further includes a file updating unit 304, which is used to:

[0114] Sending the bidding management document to the front end for display;

[0115] Receive feedback from the front end regarding the bidding management document;

[0116] The instruction file generating unit 303 calls the model reasoning service to regenerate the bidding management file according to the feedback, the parsing result and the supplementary bidding data of the bidding project.

[0117] The intelligent bidding assistance device provided in this embodiment belongs to the same inventive concept as the aforementioned method embodiment. For technical details not described in this embodiment, please refer to the relevant description in the aforementioned method embodiment and will not be repeated here.

[0118] In summary, the technical solution provided by the embodiment of the present invention provides a highly intelligent and automated bidding assistance solution, which has the following advantages:

[0119] 1. Improve the efficiency of tender document generation

[0120] By combining AI (artificial intelligence) large language model and document processing module, it can automatically parse the bidding documents uploaded by users and quickly generate suggestions and drafts that meet the bidding requirements; compared with the traditional manual writing of bidding documents, the embodiment of the present invention greatly improves the speed of document generation and reduces the workload and error rate of manual operations;

[0121] 2. Intelligent bidding strategy customization

[0122] By using search enhancement generation technology, we can integrate historical bidding data, the company's existing bidding materials, bidding document analysis and other information, and intelligently match them through the vector database to provide customized bidding strategy suggestions. Such intelligent processing not only improves the targeting of bidding, but also helps users gain an advantageous position in the competition.

[0123] 3. Improve bidding success rate

[0124] By closely combining AI intelligent analysis, data retrieval and user feedback, the embodiments of the present invention can significantly improve the rationality of bidding strategies and the accuracy of document writing, thereby greatly improving the success rate of bidding; especially in large-scale projects with fierce competition, the role of intelligent assistance is particularly significant, helping users to quickly respond to complex bidding requirements;

[0125] 4. User-friendly interface and ease of operation

[0126] The embodiment of the present invention provides a user-friendly user interface, and the user can easily operate the entire system without having a deep technical background; the intuitive design of the interface and the intelligent processing capabilities of the system complement each other, greatly improving the user experience and lowering the technical threshold for bidding.

[0127] Figure 4 FIG. 1 is a schematic diagram of the structure of an embodiment of an electronic device of the present invention, which can implement the processes of the first and second embodiments of the present invention. Figure 4 As shown, the above-mentioned electronic device may include: a shell 41, a processor 42, a memory 43, a circuit board 44 and a power supply circuit 45, wherein the circuit board 44 is arranged inside the space enclosed by the shell 41, and the processor 42 and the memory 43 are arranged on the circuit board 44; the power supply circuit 45 is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory 43 is used to store executable program codes; the processor 42 runs the program corresponding to the executable program code by reading the executable program code stored in the memory 43, so as to execute the intelligent bidding assistance method described in any of the aforementioned embodiments.

[0128] The specific execution process of the above steps by the processor 42 and the steps further executed by the processor 42 by running the executable program code can be found in the description of the method embodiment of the present invention, which will not be repeated here.

[0129] The electronic device can be an electronic device with data processing capabilities that exists in various forms, such as a server that provides computing services. Its structure is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, manageability, etc.

[0130] Furthermore, an embodiment of the present invention also provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more central processors to implement the intelligent bidding assistance method described in the above embodiment.

[0131] It should be noted that in this article, relational terms such as first and second are only used to refer to

[0132] One entity or operation is distinguished from another entity or operation without necessarily requiring or implying that these

[0133] There is no such actual relationship or order between entities or operations. Furthermore, the terms "comprises", "includes" and "

[0134] "Including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article, or apparatus. In the absence of more limitations, an element defined by the phrase "including a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0135] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0136] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0137] In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0138] For the convenience of description, the above device is described by dividing the functions into various units / modules. Of course, when implementing the present invention, the functions of each unit / module can be implemented in the same or multiple software and / or hardware.

[0139] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0140] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An intelligent bidding assistance method, characterized in that: Applied to a backend server, the method comprises: Receive the initial bidding data of the bidding project submitted by the user sent by the front end; Calling a data processing service to convert and parse the initial bidding data; The model inference service is called to generate a bidding management document according to the parsing result and the supplementary bidding data of the bidding project.

2. The method according to claim 1, characterized in that The initial bidding data includes an initial bidding document; Calling data processing services to convert and parse the initial bidding data, including: Call the data processing service to perform the following operations: Converting the initial bidding document into a portable document format; Perform layout recognition on the format-converted initial bidding documents and split them into structured text blocks, data tables, and graphic elements.

3. The method according to claim 1, characterized in that The method further comprises: According to the different types of stored content, the following contents are stored in the corresponding storage areas in the data storage module: the initial bidding data, the analysis results of the data processing service, the intermediate data of the model reasoning service and the bidding management file.

4. The method according to claim 3, characterized in that Storing the unstructured data in the initial bidding data and the bidding management file in the file storage system in the data storage module; Storing the structured data in the initial bidding data, the parsing results of the data processing service, and the non-vectorized data in the intermediate data of the model reasoning service in the relational database in the data storage module; The parsing result of the data processing service and the vectorized data in the intermediate data of the model reasoning service are stored in the vector database in the data storage module.

5. The method according to claim 1, characterized in that: Call the model inference service to generate a bidding management document based on the analysis results and the supplementary bidding data of the bidding project, including: Calling a pre-trained retrieval enhancement generation artificial intelligence model to extract set key vectorized data from the parsing results and the supplementary bidding data of the bidding project; Call a pre-trained text generation artificial intelligence model to perform reasoning based on the set key vectorized data and the parsing results and the non-vectorized data in the supplementary bidding data of the bidding project to generate a bidding management document.

6. The method according to claim 1, characterized in that After calling the model inference service and generating a bidding management file according to the parsing result and the supplementary bidding data of the bidding project, the method further includes: Sending the bidding management document to the front end for display; Receive feedback from the front end regarding the bidding management document; The model reasoning service is called to regenerate the bidding management document according to the feedback, the analysis results and the supplementary bidding data of the bidding project.

7. An intelligent bidding assistance device, characterized in that: Applied to a backend server, the device comprises: A data receiving unit, used for receiving the initial bidding data of the bidding project submitted by the user and sent by the front end; A data processing unit, used to call a data processing service to perform format conversion and analysis on the initial bidding data; The file generation unit is used to call the model reasoning service and generate a bidding management file according to the parsing result of the data processing unit and the supplementary bidding data of the bidding project.

8. The device according to claim 7, characterized in that The initial bidding data includes an initial bidding document; The data processing unit is specifically used for: The data processing service is called to perform the following operations: converting the initial bidding document into a portable document format; performing layout recognition on the initial bidding document after format conversion, and splitting it into structured text blocks, data tables and graphic elements.

9. The device according to claim 7, characterized in that The device also includes a storage unit for: According to the different types of stored content, the following contents are stored in the corresponding storage areas in the data storage module: the initial bidding data, the analysis results of the data processing service, the intermediate data of the model reasoning service and the bidding management file.

10. The device according to claim 9, characterized in that The storage unit is specifically used for: Storing the unstructured data in the initial bidding data and the bidding management file in the file storage system in the data storage module; Storing the structured data in the initial bidding data, the parsing results of the data processing service, and the non-vectorized data in the intermediate data of the model reasoning service in the relational database in the data storage module; The parsing result of the data processing service and the vectorized data in the intermediate data of the model reasoning service are stored in the vector database in the data storage module.

11. The device according to claim 7, characterized in that The file generation unit is specifically used for: Calling a pre-trained retrieval enhancement generation artificial intelligence model to extract set key vectorized data from the parsing results and the supplementary bidding data of the bidding project; Call a pre-trained text generation artificial intelligence model to perform reasoning based on the set key vectorized data and the parsing results and the non-vectorized data in the supplementary bidding data of the bidding project to generate a bidding management document.

12. The device according to claim 7, characterized in that The device also includes a file updating unit, which is used to: Sending the bidding management document to the front end for display; Receive feedback from the front end regarding the bidding management document; Instruct the file generation unit to call the model reasoning service to regenerate the bidding management file according to the feedback, the parsing result and the supplementary bidding data of the bidding project.

13. An electronic device, characterized in that: The electronic device includes: a shell, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the shell, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program code; the processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the intelligent bidding assistance method described in any of the above claims 1-6.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more central processors to implement the intelligent bidding assistance method described in any of the above claims 1-6.

Images