Bidding document quality evaluation method and device, equipment and storage medium

Abstract

The invention discloses a quality evaluation method, device and equipment for a bidding document and a storage medium, and the method comprises the steps: generating a page index container through the analysis of a file directory of a target bidding document, and generating a content vector container through the analysis of a file body of the target bidding document; based on an initial bid invitation directory tree, the page index container and the content vector container, generating a target bid invitation directory tree; based on the target bid invitation directory tree, performing content feature analysis on a target bid invitation file by adopting a large language model, and generating a bid invitation index container according to an analysis result returned by the large language model; and performing quality evaluation on a target bidding document based on the bidding index container. According to the technical scheme, the accuracy and the quality detection efficiency of the target bidding document are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for evaluating the quality of a bidding document. Background Art

[0002] When conducting project bidding, the quality of the bid documents largely determines whether the bidder will win the bid, so the document quality of the bid documents is particularly important.

[0003] At present, after the bidding documents are completed, they are manually reviewed to assess their quality and determine their defects. However, manual review is dependent on the meticulousness and historical experience of the evaluators, and it is difficult to find small defects and common defects in the bidding documents. Often, even a small oversight will lead to the project being rejected. Summary of the invention

[0004] The present invention provides a bidding document quality assessment method, device, equipment and storage medium to improve the document quality of the bidding document.

[0005] According to one aspect of the present invention, a method for evaluating the quality of a bidding document is provided, the method comprising:

[0006] By parsing the file directory of the target tender document, a page index container is generated, and by parsing the file body of the target tender document, a content vector container is generated; wherein the page index container is used to store the directory information of the target tender document, and the content vector container is used to store the text information of the target tender document;

[0007] Based on the initial bidding directory tree, the page index container and the content vector container, a target bidding directory tree is generated; wherein the initial bidding directory tree includes directory feature information of the bidding document; and the target bidding directory tree includes document text information of the target bidding document;

[0008] Based on the target bidding directory tree, a large language model is used to analyze the content characteristics of the target bidding document, and a bidding indicator container is generated according to the analysis result returned by the large language model; wherein the bidding indicator container is used to store the bidding indicator information indicated by the target bidding document;

[0009] Based on the bidding indicator container, a quality assessment is performed on the target bidding document.

[0010] According to another aspect of the present invention, there is provided a device for evaluating the quality of a bidding document, the device comprising:

[0011] The bidding parsing module is used to parse the file directory of the target bidding document to generate a page index container, and parse the file body of the target bidding document to generate a content vector container; wherein the page index container is used to store the directory information of the target bidding document, and the content vector container is used to store the text information of the target bidding document;

[0012] The bidding directory module is used to generate a target bidding directory tree based on the initial bidding directory tree, the page index container and the content vector container; wherein the initial bidding directory tree includes directory feature information of the bidding document; and the target bidding directory tree includes document text information of the target bidding document;

[0013] A bidding indicator module, used to analyze the content characteristics of the target bidding document using a large language model based on the target bidding directory tree, and generate a bidding indicator container according to the analysis result returned by the large language model; wherein the bidding indicator container is used to store the bidding indicator information indicated by the target bidding document;

[0014] The quality assessment module is used to perform quality assessment on the target bidding document based on the bidding indicator container.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor;

[0017] and a memory communicatively coupled to the at least one processor;

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the quality assessment method of the bidding document described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the quality assessment method for bidding documents described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the quality assessment method of a bidding document according to any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention performs directory parsing and text parsing on the target bidding document, and updates the initial bidding directory tree according to the parsing results to generate a target bidding directory tree, determines the directory features of the target bidding document, and determines the index information of the file content corresponding to the directory features of the target bidding document according to the target bidding directory tree, and performs automated quality inspection on the target bidding document according to the index information, thereby improving the accuracy of the target bidding document and the efficiency of quality inspection.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0024] Figure 1 is a flow chart of a method for evaluating the quality of a bidding document provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a method for evaluating the quality of a bidding document provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a flow chart of a method for evaluating the quality of a bidding document provided according to Embodiment 3 of the present invention;

[0027] Figure 4 is a schematic diagram of the structure of a bidding document quality assessment device provided according to a fourth embodiment of the present invention;

[0028] Figure 5 The present invention is a schematic diagram of the structure of an electronic device for implementing the method for evaluating the quality of bidding documents according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 A flowchart of a method for evaluating the quality of a bidding document is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the quality of a bidding document to be bid is evaluated based on the published bidding document. The method can be executed by a bidding document quality evaluation device, which can be implemented in the form of hardware and / or software, and can be configured in various general-purpose computing devices. Figure 1 As shown, the method includes:

[0033] S110 , generating a page index container by parsing the file directory of the target bidding document, and generating a content vector container by parsing the file body of the target bidding document.

[0034] The target bidding document may refer to the bidding document published by the bidding party; the page index container may be used to store the directory information of the target bidding document, and the content vector container may be used for the text information of the target bidding document.

[0035] In the embodiment of the present invention, the target bidding document disclosed by the bidding party can be parsed, and the parsed content can be stored using a dual-slave metadata cache to improve the access efficiency to the target bidding document.

[0036] S120: Generate a target bidding directory tree based on the initial bidding directory tree, the page index container, and the content vector container.

[0037] The initial bidding directory tree may include directory feature information of the bidding documents, and the target bidding directory tree may include document text information of the target bidding documents. It should be noted that the target bidding directory tree is generated based on the initial bidding directory tree.

[0038] Optionally, in an embodiment of the present invention, the initial bidding directory tree can be generated according to a preset large language model. For example, a request message of "generate a directory of key elements of the bidding document" is input to the large language model, and an initial bidding directory tree of the bidding document is constructed according to the return result of the large language model, and the initial bidding directory tree is improved according to the file content of the target bidding document to generate a target bidding directory tree corresponding to the target bidding document. It should be noted that the initial index directory tree can be used to characterize the file format of the bidding document, that is, the necessary feature directory of the bidding document.

[0039] S130. Based on the target bidding directory tree, a large language model is used to analyze the content characteristics of the target bidding document, and a bidding indicator container is generated according to the analysis result returned by the large language model.

[0040] The bidding indicator container may store the bidding indicator information indicated by the target bidding document, and is used to indicate the format information and / or content information of the bidding document required by the target bidding document. For example, the bidding indicator information may refer to the bidding qualification requirement information, bid evaluation method information, and file directory information indicated in the target bidding document. It should be noted that the format information of the bidding document may refer to the file directory information of the bidding document.

[0041] Specifically, the nodes in the target bidding directory tree can be traversed, and according to the bidding index information stored in the node, the file content corresponding to the index bidding information in the target bidding can be determined, and then the large language model can be used to analyze the content characteristics of the file content, and the bidding index information corresponding to the file content can be returned and stored to generate a bidding index container. It should be noted that the bidding index container is a storage medium for storing bidding index information.

[0042] Optionally, based on the target bidding directory tree, a large language model is used to analyze the content features of the target bidding document, and a bidding indicator container is generated according to the analysis results returned by the large language model, including: traversing the nodes in the target bidding directory tree, if the storage object in the node is directory feature information, obtaining the bidding sub-content in the target bidding document corresponding to the directory feature information, and using the large language model to analyze the bidding sub-content to determine the bidding indicator corresponding to the bidding sub-content; if the storage object in the node is file information of the target bidding document, using the large language model to analyze the file information to determine the bidding indicator corresponding to the file information; storing the bidding indicators to generate a bidding indicator container.

[0043] Optionally, a query may be performed in the content vector container according to the catalog feature information to determine the bidding sub-content corresponding to the catalog feature information.

[0044] The tender sub-content may be the file content of the target tender document segmented according to the title information of the target tender document. The file information of the target tender document may refer to the vector normalized value of the tender sub-content.

[0045] It should be noted that, in the embodiment of the present invention, the bidding indicator container can provide writing support for the target bidding document writers, and the writers can view the bidding indicator information stored in the bidding indicator container.

[0046] By traversing the target bidding directory tree, the bidding index of the target bidding document is further determined, the target bidding document is parsed, and a bidding index container is generated, thereby avoiding access to the target bidding document and improving the efficiency of obtaining the file information of the target bidding document.

[0047] S140. Based on the bidding indicator container, quality assessment is performed on the target bidding document.

[0048] Optionally, based on the bidding indicator container, a quality assessment is performed on the target bidding document, including: segmenting the target bidding document according to the title information of the target bidding document to generate bidding sub-contents; using the bidding sub-contents, the title information to which the bidding sub-contents belong, and the page number information corresponding to the title information as a container node to generate a bidding document content container; traversing the container nodes in the bidding document content container for the bidding indicator information indicated by each indicator node in the bidding indicator container to determine whether the indicator information exists in the bidding document content container; if so, the quality inspection of the target bidding document passes; if not, it indicates that there are defects in the target bidding document and an alarm is issued.

[0049] The bidding sub-content may refer to the file content generated after segmenting the target bidding document according to the title information of the target bidding document.

[0050] In an embodiment of the present invention, by verifying whether the bidding indicator information indicated by each indicator node in the bidding indicator container exists in the bidding document content container, the file format and / or file content of the target bidding document can be detected to determine whether the target bidding document meets the bidding requirements indicated by the target bidding document.

[0051] The technical solution of the embodiment of the present invention performs directory parsing and text parsing on the target bidding document, and updates the initial bidding directory tree according to the parsing results to generate a target bidding directory tree, determines the directory features of the target bidding document, and determines the index information of the file content corresponding to the directory features of the target bidding document according to the target bidding directory tree, and performs automated quality inspection on the target bidding document according to the index information, thereby improving the accuracy of the target bidding document and the efficiency of quality inspection.

[0052] Embodiment 2

[0053] Figure 2 This is a flowchart of a method for evaluating the quality of a bidding document provided in the second embodiment of the present invention. This embodiment further expands on the above embodiment and provides specific steps for parsing the file directory of the target bidding document to generate a page index container, and parsing the file body of the target bidding document to generate a content vector container. It should be noted that for the undetailed parts of the embodiment of the present invention, please refer to the relevant descriptions of other embodiments, which will not be repeated here. Figure 2 As shown, the method includes:

[0054] S210: Identify the file directory of the target bidding document, and determine the title information of the target bidding document and the page number information corresponding to the title information.

[0055] S220. Store the title information of the target bidding document and the page number information corresponding to the title information in a page index container in the form of a key-value pair.

[0056] S230. Determine the title level path of the title information of the target bidding document according to the subordinate relationship between the title information in the target bidding document.

[0057] S240, segmenting the target bidding document according to the title information of the target bidding document, generating bidding sub-contents corresponding to each title information, and performing vector normalization on the bidding sub-contents.

[0058] S250, establish a storage node for each title information in the target bidding document, and generate a content vector container. The storage node is used to store the title level path, the vector normalized value of the bidding sub-content, and the page number information corresponding to the title information, and the node identifier of the storage node is determined according to the title level path.

[0059] In an embodiment of the present invention, in order to parse the target bidding document, the appendix (i.e., the directory information) of the target bidding document can be identified, the title information of the target bidding document and the page number information corresponding to the title information can be determined, and key-value pair data can be generated with the title information as the key and the page number information corresponding to the title information as the value, and the key-value pair data can be stored to generate a page index container.

[0060] Furthermore, the subordinate relationship between the title information in the target tender document can be determined by identifying the appendix format of the target tender document. For example, there may be multiple sub-chapter titles under a chapter title, and the title level path of each title in the target tender document can be determined accordingly. For example, if there are sub-chapter a1, a2 and a3 under a chapter A, the title level path corresponding to a1 is A->a1. Exemplarily, the node identifier of the storage node corresponding to a1 in the content vector container is A->a1->the page number where a1 is located.

[0061] The technical solution of the embodiment of the present invention generates a page index container by performing directory recognition on the target bidding document, generates bidding sub-contents by segmenting the target bidding document, and aligns and normalizes the vectors to generate content vector containers, and stores the target bidding document through dual-slave meta-cache data, thereby improving the access rate of the target bidding document and improving data fault tolerance.

[0062] Embodiment 3

[0063] Figure 3 This is a flowchart of a method for evaluating the quality of a bidding document provided in the third embodiment of the present invention. This embodiment further expands on the above embodiment and provides specific steps for generating a target bidding directory tree based on an initial bidding directory tree, a page index container, and a content vector container. It should be noted that for the undetailed parts of the embodiment of the present invention, reference can be made to the relevant descriptions of other embodiments, which will not be repeated here. Figure 3 As shown, the method includes:

[0064] S310: generate a page index container by parsing the file directory of the target bidding document, and generate a content vector container by parsing the file body of the target bidding document.

[0065] S320: Generate an initial bidding directory tree of the bidding document using a large language model, and traverse the title information in the page index container to determine whether the title information exists in the initial bidding directory tree.

[0066] In an embodiment of the present invention, a query request in the file format of a tender document can be issued to a large language model, and the query request can be used to request a directory section necessary for the tender document, and an initial tender directory tree can be generated according to the request result returned by the large language model; then, the title information in the page index container can be traversed, and a query can be performed in the initial tender directory tree according to the title information to determine whether the title information is stored in the initial tender directory tree.

[0067] S330. If it does not exist in the initial bidding directory tree, a large language model is used to obtain the file content features corresponding to the title information in the bidding document, determine the storage node corresponding to the file content features in the content vector container, and update the initial bidding directory tree according to the file information of the target bidding document stored in the storage node to generate a target bidding directory tree.

[0068] Optionally, if the file content feature does not exist in the content vector container, the file content feature can be vector normalized, and the vector value of the normalized file feature vector is stored in the initial bidding directory tree, and the initial bidding directory tree is updated; if the file content feature exists in the content vector container, the initial bidding directory tree is updated according to the vector normalized value of the bidding sub-content stored in the content vector container corresponding to the file content feature.

[0069] S340. Based on the target bidding directory tree, a large language model is used to analyze the content characteristics of the target bidding document, and a bidding indicator container is generated according to the analysis results returned by the large language model.

[0070] S350. Based on the bidding indicator container, perform quality assessment on the target bidding document.

[0071] Optionally, based on the bidding indicator container, the target bidding document is subjected to quality assessment, which also includes: traversing the indicator nodes in the bidding indicator container to determine the bidding qualification standards for the bidder indicated in the target bidding document; determining the bidding sub-content corresponding to the bidding qualification standards in the bidding document content container; verifying whether the bidding sub-content meets the bidding qualification standards, and if so, determining that the target bidding document meets the bidding qualifications indicated in the target bidding document.

[0072] Specifically, the indicator nodes in the bidding indicator container can be traversed to determine the indicator nodes in the indicator bidding container used to store the bidding qualification standards of the bidder; and the bidding document content container can be traversed to determine the bidding sub-content corresponding to the bidder's own qualifications, and the bidder's own qualification information indicated by the bidding sub-content and the bidding qualification standards described by the indicator nodes in the indicator bidding container can be verified to determine whether the bidder has the bidding qualifications.

[0073] Optionally, the indicator nodes in the bidding indicator container can be traversed to determine the indicator node in the indicator bidding container for storing the bid evaluation indicators, and the target bidding document can be self-checked according to at least one bid evaluation indicator described by the indicator node to determine the self-check score, and the self-check results can be visualized and feedback can be provided.

[0074] Optionally, if there are pictures in the bidding sub-content, the pictures in the bidding sub-content can be further recognized to obtain text information recorded in the pictures, so as to obtain more comprehensive bidding information in the bidding sub-content and improve the accuracy of the quality assessment results of the target bidding document.

[0075] The technical solution of the embodiment of the present invention pre-generates an initial bidding directory tree of the bidding document through a large language model, and then updates the bidding directory tree according to the page index container and the content vector container to generate a target bidding directory tree carrying all directory feature information of the target bidding document, thereby improving the generation rate of the target index directory tree and ensuring the integrity of the file information in the target bidding document.

[0076] Embodiment 4

[0077] Figure 4 This is a schematic diagram of a bidding document quality assessment device provided by the fourth embodiment of the present invention. Figure 4 As shown, the device comprises:

[0078] The bidding parsing module 410 is used to parse the file directory of the target bidding document to generate a page index container, and parse the file body of the target bidding document to generate a content vector container; wherein the page index container is used to store the directory information of the target bidding document, and the content vector container is used to store the text information of the target bidding document;

[0079] The bidding directory module 420 is used to generate a target bidding directory tree based on the initial bidding directory tree, the page index container and the content vector container; wherein the initial bidding directory tree includes directory feature information of the bidding document; and the target bidding directory tree includes document text information of the target bidding document;

[0080] The bidding indicator module 430 is used to analyze the content characteristics of the target bidding document using a large language model based on the target bidding directory tree, and generate a bidding indicator container according to the analysis result returned by the large language model; wherein the bidding indicator container is used to store the bidding indicator information indicated by the target bidding document;

[0081] The quality assessment module 440 is used to perform quality assessment on the target bidding document based on the bidding indicator container.

[0082] The technical solution of the embodiment of the present invention performs directory parsing and text parsing on the target bidding document, and updates the initial bidding directory tree according to the parsing results to generate a target bidding directory tree, determines the directory features of the target bidding document, and determines the index information of the file content corresponding to the directory features of the target bidding document according to the target bidding directory tree, and performs automated quality inspection on the target bidding document according to the index information, thereby improving the accuracy of the target bidding document and the efficiency of quality inspection.

[0083] Optionally, the bidding analysis module 410 includes:

[0084] The bidding catalogue identification unit is used to identify the file catalogue of the target bidding document, determine the title information of the target bidding document and the page number information corresponding to the title information;

[0085] The page index container unit is used to store the title information of the target bidding document and the page number information corresponding to the title information in the page index container in the form of key-value pairs;

[0086] A title path generating unit, used for determining a title hierarchical path of the title information of the target bidding document according to the subordinate relationship between the title information in the target bidding document;

[0087] A bidding segmentation unit, used to segment the target bidding document according to the title information of the target bidding document, generate bidding sub-contents corresponding to each title information, and perform vector normalization on the bidding sub-contents;

[0088] The content vector container unit is used to establish a storage node for each title information in the target bidding document and generate a content vector container; wherein the storage node is used to store the title level path, the vector normalized value of the bidding sub-content and the page number information corresponding to the title information, and the node identifier of the storage node is determined according to the title level path.

[0089] Optionally, the bidding catalog module 420 includes:

[0090] An initial directory unit, used to generate an initial bidding directory tree of the bidding document using a large language model, and to traverse the title information in the page index container to determine whether the title information exists in the initial bidding directory tree;

[0091] The target directory generation unit is used to use a large language model to obtain the file content features corresponding to the title information in the bidding document if it does not exist in the initial bidding directory tree, determine the storage node corresponding to the file content features in the content vector container, and update the initial bidding directory tree according to the file information of the target bidding document stored in the storage node to generate a target bidding directory tree.

[0092] Optionally, the quality assessment module 440 includes:

[0093] A bidding segmentation unit, used for segmenting the target bidding document according to the title information of the target bidding document to generate bidding sub-contents;

[0094] A bidding container generating unit, used to use the bidding sub-content, the title information to which the bidding sub-content belongs, and the page number information corresponding to the title information as a container node to generate a bidding document content container;

[0095] The quality assessment unit is used to traverse the container nodes in the bidding document content container for the bidding indicator information indicated by each indicator node in the bidding indicator container, and determine whether the indicator information exists in the bidding document content container; if so, the quality detection of the target bidding document passes.

[0096] Optionally, the quality assessment module 440 further includes:

[0097] A bidding qualification unit, used to traverse the indicator nodes in the bidding indicator container to determine the bidding qualification standards for the bidders indicated in the target bidding document;

[0098] The bidding qualification verification unit is used to determine the bidding sub-content corresponding to the bidding qualification standard in the bidding document content container; verify whether the bidding sub-content meets the bidding qualification standard, and if so, determine that the target bidding document meets the bidding qualification indicated by the target bidding document.

[0099] Optionally, the bidding indicator module 430 includes:

[0100] A target directory traversal unit is used to traverse the nodes in the target bidding directory tree, and if the storage object in the node is directory feature information, obtain the bidding sub-content corresponding to the directory feature information in the target bidding document, and use a large language model to analyze the bidding sub-content to determine the bidding index corresponding to the bidding sub-content;

[0101] The indicator container generation unit is used to analyze the file information using a large language model if the storage object in the node is the file information of the target bidding document, determine the bidding indicator corresponding to the file information; store the bidding indicator and generate a bidding indicator container.

[0102] The bidding document quality assessment device provided in the embodiment of the present invention can execute the bidding document quality assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0103] Embodiment 5

[0104] Figure 5 A schematic diagram of the structure of an electronic device 510 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0105] like Figure 5 As shown, the electronic device 510 includes at least one processor 511, and a memory connected to the at least one processor 511 in communication, such as a read-only memory (ROM) 512, a random access memory (RAM) 513, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 511 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 512 or the computer program loaded from the storage unit 518 to the random access memory (RAM) 513. In the RAM 513, various programs and data required for the operation of the electronic device 510 can also be stored. The processor 511, the ROM 512, and the RAM 513 are connected to each other via a bus 514. An input / output (I / O) interface 515 is also connected to the bus 514.

[0106] A number of components in the electronic device 510 are connected to the I / O interface 515, including: an input unit 516, such as a keyboard, a mouse, etc.; an output unit 517, such as various types of displays, speakers, etc.; a storage unit 518, such as a disk, an optical disk, etc.; and a communication unit 519, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 519 allows the electronic device 510 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The processor 511 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 511 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 511 executes the various methods and processes described above, such as a quality assessment method for a bidding document.

[0108] In some embodiments, the quality assessment method of the bid document may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 518. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 510 via the ROM 512 and / or the communication unit 519. When the computer program is loaded into the RAM 513 and executed by the processor 511, one or more steps of the quality assessment method of the bid document described above may be performed. Alternatively, in other embodiments, the processor 511 may be configured to execute the quality assessment method of the bid document by any other appropriate means (e.g., by means of firmware).

[0109] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0111] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0113] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0114] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0115] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0116] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the quality of a bidding document, characterized in that: include: By parsing the file directory of the target tender document, a page index container is generated, and by parsing the file body of the target tender document, a content vector container is generated; wherein the page index container is used to store the directory information of the target tender document, and the content vector container is used to store the text information of the target tender document; Based on the initial bidding directory tree, the page index container and the content vector container, a target bidding directory tree is generated; wherein the initial bidding directory tree includes directory feature information of the bidding document; and the target bidding directory tree includes document text information of the target bidding document; Based on the target bidding directory tree, a large language model is used to analyze the content characteristics of the target bidding document, and a bidding indicator container is generated according to the analysis result returned by the large language model; wherein the bidding indicator container is used to store the bidding indicator information indicated by the target bidding document; Based on the bidding indicator container, a quality assessment is performed on the target bidding document.

2. The method according to claim 1, characterized in that The method of generating a page index container by parsing the file directory of the target tender document and generating a content vector container by parsing the file body of the target tender document includes: Identify the file directory of the target bidding document, determine the title information of the target bidding document and the page number information corresponding to the title information; The title information of the target bidding document and the page number information corresponding to the title information are stored in the page index container in the form of key-value pairs; Determine the title level path of the title information of the target bidding document according to the subordinate relationship between the title information in the target bidding document; Segmenting the target bidding document according to the title information of the target bidding document, generating bidding sub-contents corresponding to each title information, and performing vector normalization on the bidding sub-contents; A storage node is established for each title information in the target bidding document to generate a content vector container; wherein the storage node is used to store the title level path, the vector normalized value of the bidding sub-content and the page number information corresponding to the title information, and the node identifier of the storage node is determined according to the title level path.

3. The method according to claim 1, characterized in that The step of generating a target bidding directory tree based on the initial bidding directory tree, the page index container and the content vector container includes: Generate an initial bidding directory tree of the bidding document using a large language model, and traverse the title information in the page index container to determine whether the title information exists in the initial bidding directory tree; If it does not exist in the initial bidding directory tree, a large language model is used to obtain the file content features corresponding to the title information in the bidding document, determine the storage node corresponding to the file content features in the content vector container, and update the initial bidding directory tree according to the file information of the target bidding document stored in the storage node to generate the target bidding directory tree.

4. The method according to claim 1, characterized in that The step of performing quality assessment on the target bidding document based on the bidding indicator container includes: Segmenting the target bidding document according to the title information of the target bidding document to generate bidding sub-contents; The bidding sub-content, the title information to which the bidding sub-content belongs, and the page number information corresponding to the title information are used as a container node to generate a bidding document content container; For the bidding indicator information indicated by each indicator node in the bidding indicator container, traverse the container nodes in the bidding document content container to determine whether the indicator information exists in the bidding document content container; If it exists, the quality inspection of the target bidding document passes.

5. The method according to claim 1, characterized in that: The step of performing quality assessment on the target bidding document based on the bidding indicator container further includes: Traversing the indicator nodes in the bidding indicator container to determine the bidding qualification standards for the bidders indicated in the target bidding document; Determine the bidding sub-content corresponding to the bidding qualification standard in the bidding document content container; check whether the bidding sub-content meets the bidding qualification standard, and if so, determine that the target bidding document meets the bidding qualification indicated by the target bidding document.

6. The method according to claim 1, characterized in that The method of using a large language model to analyze the content characteristics of the target bidding document based on the target bidding directory tree, and generating a bidding indicator container according to the analysis result returned by the large language model, includes: Traversing the nodes in the target bidding directory tree, if the storage object in the node is directory feature information, obtaining the bidding sub-content corresponding to the directory feature information in the target bidding document, and using a large language model to analyze the bidding sub-content to determine the bidding indicator corresponding to the bidding sub-content; If the storage object in the node is the file information of the target bidding document, the large language model is used to analyze the file information to determine the bidding indicators corresponding to the file information; the bidding indicators are stored to generate a bidding indicator container.

7. A bidding document quality assessment device, characterized in that: include: The bidding parsing module is used to parse the file directory of the target bidding document to generate a page index container, and parse the file body of the target bidding document to generate a content vector container; wherein the page index container is used to store the directory information of the target bidding document, and the content vector container is used to store the text information of the target bidding document; The bidding directory module is used to generate a target bidding directory tree based on the initial bidding directory tree, the page index container and the content vector container; wherein the initial bidding directory tree includes directory feature information of the bidding document; and the target bidding directory tree includes document text information of the target bidding document; A bidding indicator module, used to analyze the content characteristics of the target bidding document using a large language model based on the target bidding directory tree, and generate a bidding indicator container according to the analysis result returned by the large language model; wherein the bidding indicator container is used to store the bidding indicator information indicated by the target bidding document; The quality assessment module is used to perform quality assessment on the target bidding document based on the bidding indicator container.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the quality assessment method for bid documents described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the quality assessment method of a bidding document according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the quality assessment method of the bidding document as described in any one of claims 1 to 6.

Images