Bidding document manufacturing method and device

Abstract

The invention discloses a bidding document manufacturing method and device, relates to the technical field of artificial intelligence, can be used in the field of financial science and technology, and comprises the following steps: determining a bidding document template according to the type of a customer having a bidding document manufacturing requirement, and generating an initial bidding document; after a chapter selection command of a client on the bidding document is received, intelligent generation reminding information is generated; after an intelligent generation instruction determined by the client is received, key words input by the client are received; querying a knowledge base according to keywords input by a client, and screening out a plurality of keyword paragraphs in the knowledge base; matching the plurality of keyword paragraphs screened out from the knowledge base with a preset bidding document set to obtain keyword paragraphs in the knowledge base; associating the matched keyword paragraph with a chapter selected by the client and then adding the keyword paragraph to the selected chapter; and synthesizing all contents in the bidding document manufacturing template to form a bidding document. The method is high in accuracy and high in efficiency.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, can be used in the field of financial technology, and in particular to a bid document preparation method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] In the existing business in various fields, it is common to need to prepare bid response documents due to bidding by customers in various regions. When it comes to important business information in the bid documents, such as technical parameters, business qualifications, important industry cases of the bank, and references to similar bidding companies, the rapid retrieval, call and integration of the bank's knowledge base information and highly reusable modular information content is very important for the rapid preparation of the value of the bid documents.

[0004] In the prior art, the bid document deletes and modifies the template according to user needs, obtains screening conditions, adds the screened information into the bid document template and then generates the bid. The technical parameters of the bid document are inaccurate and incomplete after being deleted. In the process of bid preparation, information errors and omissions are prone to occur, which reduces the accuracy of the bid document. The bid document often requires staff to rework and revise it, which reduces the production efficiency of the bid document.

[0005] Therefore, a more accurate bid preparation solution is currently needed. Summary of the invention

[0006] The embodiment of the present invention provides a method for preparing a tender document, which can avoid information errors and omissions, improve the accuracy of the tender document, avoid rework and correction by staff, and improve the production efficiency of the tender document. The method includes:

[0007] Determine the tender template and generate the initial tender document according to the type of customer who needs tender preparation;

[0008] After receiving a chapter selection command from a client for a bidding document, generating intelligent generation reminder information, wherein the intelligent generation reminder information is used to remind the client whether to use the knowledge base to intelligently generate the content of the selected chapter;

[0009] After receiving the customer's confirmation to adopt the intelligent generation instruction, receiving the keywords input by the customer;

[0010] According to the keywords input by the customer, the knowledge base is queried to filter out multiple keyword paragraphs in the knowledge base;

[0011] Matching multiple keyword paragraphs in the filtered knowledge base with a preset tender document set to match the keyword paragraphs in the knowledge base;

[0012] Associating the matched keyword paragraphs with the chapter selected by the customer and adding them to the selected chapter;

[0013] After all chapters are completed and the synthesis instruction is received from the user, all contents in the bid making template are synthesized to form a bid document.

[0014] The embodiment of the present invention further provides a tender document production device, which can avoid information errors and omissions, improve the accuracy of tender documents, avoid rework and correction by staff, and improve the production efficiency of tender documents. The device includes:

[0015] The initial tender document generation module is used to determine the tender document template and generate the initial tender document according to the type of customer who has tender document production requirements;

[0016] A reminder information generation module, which is used to generate intelligent generation reminder information after receiving a command from a customer to select a chapter of a tender document, wherein the intelligent generation reminder information is used to remind the customer whether to use the knowledge base to intelligently generate the content of the selected chapter;

[0017] A keyword input module is used to receive keywords input by the customer after receiving the customer's confirmation to adopt the intelligent generation instruction;

[0018] The screening module is used to query the knowledge base according to the keywords input by the customer and screen out multiple keyword paragraphs in the knowledge base;

[0019] A matching module, used to match the multiple keyword paragraphs screened out from the knowledge base with a preset bid document set, and match the keyword paragraphs in the knowledge base;

[0020] An association module is used to associate the matched keyword paragraphs with the chapters selected by the customer and add them to the selected chapters;

[0021] The tender document forming module is used to synthesize all the contents in the tender document making template to form a tender document after the contents of all chapters are completed and the user's synthesis instruction is received.

[0022] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned bid making method when executing the computer program.

[0023] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned bid document preparation method is implemented.

[0024] In an embodiment of the present invention, a bid template is determined according to the type of customer who has a demand for bid preparation, and an initial bid document is generated; after receiving a command from the customer to select a chapter of the bid document, intelligent generation reminder information is generated, and the intelligent generation reminder information is used to remind the customer whether to use the knowledge base to intelligently generate the content of the selected chapter; after receiving the customer's confirmation to use the intelligent generation instruction, the customer input keywords are received; according to the keywords entered by the customer, multiple keyword paragraphs in the knowledge base are screened out; the multiple keyword paragraphs screened out in the knowledge base are matched with a preset bid document set to match the keyword paragraphs in the knowledge base; the matched keyword paragraphs are associated with the chapter selected by the customer and added to the selected chapter; after the contents of all chapters are completed and the user's synthesis instruction is received, all the contents in the bid preparation template are synthesized to form a bid document. Compared with the technical solution in the prior art in which the user directly deletes and modifies the template and directly puts the filtered information into the bid, the embodiment of the present invention filters out multiple keyword paragraphs in the knowledge base, matches them with the preset bid document set, determines more accurate keyword paragraphs in the knowledge base, and associates them, finally forming a bid document with higher accuracy, avoiding information errors and omissions, improving the accuracy of the bid, avoiding rework and correction by staff, and improving the production efficiency of the bid. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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. In the drawings:

[0026] Figure 1 is a flow chart of a method for preparing a bid document in an embodiment of the present invention;

[0027] Figure 2 A flowchart of matching keyword paragraphs in a knowledge base in an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of a tender document making device according to an embodiment of the present invention;

[0029] Figure 4 Another schematic diagram of the tender document making device in an embodiment of the present invention;

[0030] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0032] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0033] The inventors found that in the prior art, the bid template is deleted and modified according to user needs, the screening conditions are obtained, and the screened information is added to the bid template to generate the bid. The technical parameters of the bid are not accurate and complete after the deletions. The bid is not previewed and checked during the preparation process, which is prone to information errors and omissions, reducing the accuracy of the bid document. The bid document has not been searched, and the format integration and standardization require staff to rework and correct it, reducing the production efficiency of the bid document.

[0034] In the embodiment of the present invention, the preparation of the tender document is not limited to a specific field, and can be applied to various scenarios requiring bidding, such as finance, computers, etc., for example, it can be used in the bidding scenario of corporate annuities.

[0035] Figure 1 The flowchart of the bid document preparation method in an embodiment of the present invention includes:

[0036] Step 101, determining a tender document template according to the type of customer who has a tender document production requirement, and generating an initial tender document;

[0037] Step 102, after receiving a command from a client to select a chapter of a tender document, generating intelligent generation reminder information, wherein the intelligent generation reminder information is used to remind the client whether to use the knowledge base to intelligently generate the content of the selected chapter;

[0038] Step 103, after receiving the customer's confirmation to adopt the intelligent generation instruction, receiving the keywords input by the customer;

[0039] Step 104, querying the knowledge base according to the keywords input by the customer, and screening out multiple keyword paragraphs in the knowledge base;

[0040] Step 105, matching the multiple keyword paragraphs in the screened knowledge base with the preset tender document set to match the keyword paragraphs in the knowledge base;

[0041] Step 106, associating the matched keyword paragraph with the chapter selected by the customer and adding it to the selected chapter;

[0042] Step 107, after the contents of all chapters are completed and a synthesis instruction from the user is received, all contents in the tender document making template are synthesized to form a tender document.

[0043] Compared with the technical solution in the prior art in which the user directly deletes and modifies the template and directly puts the filtered information into the bid, the embodiment of the present invention filters out multiple keyword paragraphs in the knowledge base, matches them with the preset bid document set, determines more accurate keyword paragraphs in the knowledge base, and associates them, finally forming a bid document with higher accuracy, avoiding information errors and omissions, improving the accuracy of the bid, avoiding rework and correction by staff, and improving the production efficiency of the bid.

[0044] A detailed introduction is given below.

[0045] In step 101, a bid template is determined based on the type of customer who has a bid preparation requirement, and an initial bid document is generated; the structure of the bid template can be specially maintained, including maintaining the customer name, customer type, bid chapters, format, etc., and general bid editing refers to making bids, resetting content, saving content, editing corresponding chapter directories and chapter titles and other bid structure content, and adding and deleting chapters.

[0046] In one embodiment, before determining the bid document template according to the type of customer who has a bid document production requirement, the method further includes:

[0047] Determine whether the customer meets the requirements for tender preparation based on the customer name and type;

[0048] If not, a reminder message that the tender cannot be prepared is generated;

[0049] If so, determine the bid template based on the type of client who needs bid preparation.

[0050] During the specific implementation, some customers corresponding to the customer names have problems with funds, company ownership, etc. and cannot make bids. Therefore, they need to be screened out in advance, and a reminder message that the bid cannot be made is generated and sent to the customers.

[0051] In step 102, after receiving a command from a client to select a chapter of a tender document, intelligent generation reminder information is generated, wherein the intelligent generation reminder information is used to remind the client whether to use the knowledge base to intelligently generate the content of the selected chapter;

[0052] In specific implementation, if the customer decides not to use intelligent generation, he or she can edit or delete chapters by himself or herself. After saving the information, the relevant content can be matched and saved in the chapter, thus realizing customized operation.

[0053] In step 103, after receiving the customer's confirmation to adopt the intelligent generation instruction, receiving the keywords input by the customer;

[0054] In one embodiment, the method further comprises:

[0055] After receiving the intelligent generation instruction from the customer, the title of the selected chapter is parsed to obtain the keywords in the title;

[0056] According to the keywords entered by the customer, the knowledge base is queried, including:

[0057] Query the knowledge base based on the keywords entered by the customer and the keywords in the title.

[0058] The above embodiment provides another method for obtaining keywords to achieve more accurate hits on the knowledge base.

[0059] In step 104, the knowledge base is queried based on the keywords input by the customer, and multiple keyword paragraphs in the knowledge base are screened out;

[0060] In the knowledge base, you can enter keywords to search for existing knowledge base information. After searching for multiple keyword paragraphs, you can select the associated section after matching, and then retrieve the information content. The knowledge base is connected to a cloud device.

[0061] During specific implementation, the priorities of multiple keyword paragraphs may be determined, and the paragraphs may be outputted separately according to the priorities.

[0062] In one embodiment, the method further comprises:

[0063] Based on the generated tender documents, the knowledge base is updated to enrich the information within the knowledge base.

[0064] In step 105, the plurality of keyword paragraphs screened out in the knowledge base are matched with a preset bid document set to match the keyword paragraphs in the knowledge base;

[0065] See also Figure 2 , multiple keyword paragraphs in the knowledge base are filtered out and matched with the preset tender document set, and the keyword paragraphs in the knowledge base are matched, including:

[0066] Step 201, obtaining a preset tender document set for a tender document template;

[0067] Step 202, for each keyword paragraph of the bid document template, determine the key fields in the keyword paragraph;

[0068] Step 203, for each tender document, calculate the frequency vector of the tender document according to all the key fields of each keyword paragraph;

[0069] Step 204, calculating the frequency vector of the knowledge base according to the multiple keyword paragraphs in the knowledge base;

[0070] Step 205, taking the frequency vectors of the plurality of tender documents as a training set, and calculating the distance between the frequency vectors in the training set and the frequency vectors in the knowledge base;

[0071] Step 206: Use the distance as a training sample, input it into a support vector machine model, and output the keyword paragraph of the knowledge base.

[0072] In one embodiment, for each tender document, a frequency vector of the tender document is calculated based on all key fields of each keyword paragraph, including:

[0073] For each bid document, calculate the TF vector and IDF vector of each keyword paragraph based on all the key fields of the keyword paragraph;

[0074] According to the TF vector and IDF vector of the keyword paragraph, the TF-IDF vector of the tender document is calculated as the frequency vector of the tender document.

[0075] The TF-IDF model is introduced below.

[0076] Generally speaking, the more times a word appears in a document, the more important the word is. TF reflects the importance of the word within the document.

[0077]

[0078] The molecule n ij It represents the frequency of keyword i appearing in paragraph j. The denominator is the sum of the frequencies of all words in paragraph j, that is, the number of all keywords in paragraph j.

[0079] IDF reflects the importance of keywords between paragraphs. If a keyword only appears in a very small number of paragraphs, it means that the word is highly distinctive to the paragraph and the corresponding feature value is high.

[0080]

[0081] Where |D| represents the total number of paragraphs, and the denominator |D i | is the number of paragraphs containing keyword i.

[0082] In the embodiment of the present invention, taking enterprise annuity as an example, the keyword paragraphs of the bid template include: comprehensive accounting management strength, account management system, risk control capability, project service plan, and project account management service quotation.

[0083] A: Comprehensive accounting and management capabilities: key fields <company, brand, industry, structure, shareholders, personnel, concept, planning, indicators, penalties>;

[0084] B: Account management system: key fields <account, development, system, function, module, trustee, interaction, query, authority, management>;

[0085] C: Risk control capability: key fields <system, enterprise, annuity, fund, risk, accuracy, confidentiality, internal control, timeliness, process>;

[0086] D: Project service plan: key fields <service, plan, processing, suggestion, personalization, configuration, experience, disclosure, value-added, commitment>;

[0087] E: Project account management service quotation: key fields <quotation, management fee, funds, rate, payment, reconciliation, per person per household, monthly, quarterly, annual>.

[0088] Through the above two formulas, for each keyword paragraph, the tf value of each key field is calculated in turn, thereby constructing the vector TF, and the idf value of each field is calculated in turn to construct the vector IDF. In IDF, D=5,|D i | represents the number of paragraphs containing keyword i in the five keyword paragraphs. The TF and IDF of the key field in each keyword paragraph are multiplied to obtain the TF-IDF vector X of the bid document, which is used as the frequency vector of the bid document.

[0089] In one embodiment, the frequency vector of the knowledge base is calculated based on multiple keyword paragraphs in the knowledge base, including:

[0090] According to the key fields and multiple keyword paragraphs in the knowledge base, the TF vector of the knowledge base is calculated as the frequency vector of the knowledge base.

[0091] Set the knowledge base as the target vector, calculate the TF vector of each key field in the knowledge base in turn, and construct the target vector Y.

[0092] In the embodiment of the present invention, the Euclidean distance is used, the frequency vectors of multiple tender documents are used as training sets, and the distance between the frequency vectors in the training set and the frequency vectors in the knowledge base is calculated. The formula is as follows:

[0093]

[0094] Set n tender documents as the preset tender document set, and there are n training tender document vectors X n Since the knowledge base is single, the outer product of the target vector Y and the unit vector is: Calculate the training bid vector X n and the target vector Y in the knowledge base nThe distance d(x,y) is normalized to obtain the standardized distance d(x,y), which is the distance between the frequency vector in the training set and the frequency vector in the knowledge base. The training set corresponds to 5 keyword paragraphs A, B, C, D, and E. Five distances are calculated: d1(x,y), d2(x,y), d3(x,y), d4(x,y), and d5(x,y).

[0095] The training steps of the support vector machine model are as follows:

[0096] Given a training sample: D i ={(x1,d1),(x2,d2),...,(x n ,d n )},d∈{-1,1}, find the partitioning hyperplane w T x+b=0, where w=(w1,w2,...,w5) is the normal vector.

[0097] The distance from any point x in the sample space to the hyperplane (w, b) can be written as:

[0098] Training goal: find the dividing hyperplane with the “maximum margin”:

[0099] Training method: Use the Lagrange multiplier method to escape the key fields, with a match error as 1 and a match correct as 0. For example, the identified key fields A and B are successfully matched, while C, D, and E are all matched incorrectly. Then y n =(1,1,0,0,0).

[0100] Find the partitioning hyperplane f(x)=w T x+b.

[0101] Effect after training the model: Taking the comprehensive strength of account management as an example: First, the ten key fields specified in the tender document are identified. If the training is not sufficient, the explanation effect is not strong. Through the hyperplane f(x) = w T The key field identified after x+b appears in multiple keyword paragraphs in the knowledge base, resulting in failure to match the correct keyword paragraph.

[0102] After sufficient training, the bid document is judged by the support vector machine model, and key fields with strong explanations are screened out. These fields can correctly correspond to the corresponding keyword paragraphs in the knowledge base.

[0103] Input the bid document for verification, and the identified key fields can correspond to the correct five keyword paragraphs A, B, C, D, and E.

[0104] In step 106, the matched keyword paragraphs are associated with the chapter selected by the customer and added to the selected chapter;

[0105] In one embodiment, the method further comprises:

[0106] After receiving a chapter editing command from a customer, receiving the content of the chapter edited by the customer;

[0107] Verify the content of the received chapters;

[0108] After the verification fails, the errors in the content of the chapter are automatically corrected.

[0109] Through the above verification, the chapter errors found can be quickly corrected. The verification includes the rapid identification and marking of typos and grammatical errors. The traversal method is used during the verification. After the traversal is completed, an error is reported at the location where the exception occurs.

[0110] In one embodiment, the method further comprises:

[0111] After receiving a chapter deletion command from a client, deleting the chapter;

[0112] Verify the tender document after deleting the chapters;

[0113] If the verification fails, a deletion chapter exception reminder message is generated.

[0114] In one embodiment, the method further comprises:

[0115] Receiving a chapter preview instruction from a customer, generating a preview image of the corresponding chapter;

[0116] Receive the overall preview instruction from the customer and generate a preview image of the tender document.

[0117] In step 107, after the contents of all chapters are completed and a synthesis instruction is received from the user, all contents in the tender document making template are synthesized to form a tender document.

[0118] After the bid document is formed, normal editing and modification are supported.

[0119] In one embodiment, the method further comprises:

[0120] Verify the tender documents;

[0121] After verification, a reminder message for generating the tender is generated;

[0122] After verification fails, errors in the tender document are automatically corrected.

[0123] To summarize, in the method proposed in the embodiment of the present invention, a bid template is determined according to the type of customer with bid preparation requirements, and an initial bid document is generated; after receiving the customer's command to select a chapter of the bid document, intelligent generation reminder information is generated, and the intelligent generation reminder information is used to remind the customer whether to use the knowledge base to intelligently generate the content of the selected chapter; after receiving the customer's confirmation to use the intelligent generation instruction, the customer input keywords are received; according to the keywords entered by the customer, multiple keyword paragraphs in the knowledge base are screened out; the multiple keyword paragraphs screened out in the knowledge base are matched with a preset bid document set to match the keyword paragraphs in the knowledge base; the matched keyword paragraphs are associated with the chapter selected by the customer and added to the selected chapter; after the contents of all chapters are completed and the user's synthesis instruction is received, all the contents in the bid preparation template are synthesized to form a bid document. Compared with the technical solution in the prior art in which the user directly deletes and modifies the template and directly puts the filtered information into the bid, the embodiment of the present invention filters out multiple keyword paragraphs in the knowledge base, matches them with the preset bid document set, determines more accurate keyword paragraphs in the knowledge base, and associates them, finally forming a bid document with higher accuracy, avoiding information errors and omissions, improving the accuracy of the bid, avoiding rework and correction by staff, and improving the production efficiency of the bid.

[0124] In addition, after previewing and multiple checks and calibrations, information errors and omissions can be reduced, the accuracy of the tender documents can be improved, and the subsequent personalized production for customers can be assisted and synthesized at the same time to form personalized tender documents to meet customer needs.

[0125] The present invention also provides a tender document preparation device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to that of the tender document preparation method, the implementation of the device can refer to the implementation of the tender document preparation method, and the repeated parts will not be repeated.

[0126] Figure 3 The schematic diagram of the bid document preparation device in an embodiment of the present invention comprises:

[0127] The initial tender document generation module 301 is used to determine the tender document template and generate the initial tender document according to the type of customer who has the tender document production requirement;

[0128] The reminder information generation module 302 is used to generate intelligent generation reminder information after receiving a command from a client to select a chapter of a tender document, wherein the intelligent generation reminder information is used to remind the client whether to use the knowledge base to intelligently generate the content of the selected chapter;

[0129] The keyword input module 303 is used to receive keywords input by the customer after receiving the customer's confirmation to adopt the intelligent generation instruction;

[0130] The screening module 304 is used to query the knowledge base according to the keywords input by the customer and screen out multiple keyword paragraphs in the knowledge base;

[0131] A matching module 305 is used to match the multiple keyword paragraphs screened out from the knowledge base with a preset bid document set to match the keyword paragraphs in the knowledge base;

[0132] An association module 306 is used to associate the matched keyword paragraph with the chapter selected by the customer and add it to the selected chapter;

[0133] The tender document forming module 307 is used to synthesize all contents in the tender document making template to form a tender document after the contents of all chapters are completed and a synthesis instruction is received from the user.

[0134] See also Figure 4 In one embodiment, the device further comprises a customer checking module 308, which is used to:

[0135] Before determining the tender document template based on the type of customer who needs tender document preparation, determine whether the customer meets the tender document preparation requirements based on the customer name and customer type;

[0136] If not, a reminder message that the tender cannot be prepared is generated;

[0137] If so, determine the bid template based on the type of client who needs bid preparation.

[0138] In one embodiment, the keyword input module is further used to:

[0139] After receiving the intelligent generation instruction from the customer, the title of the selected chapter is parsed to obtain the keywords in the title;

[0140] According to the keywords entered by the customer, the knowledge base is queried, including:

[0141] Query the knowledge base based on the keywords entered by the customer and the keywords in the title.

[0142] In one embodiment, the matching module is further configured to:

[0143] Get a preset set of bid documents for bid templates;

[0144] For each keyword paragraph of the bid template, determine the key fields in the keyword paragraph;

[0145] For each tender document, the frequency vector of the tender document is calculated based on all the key fields of each keyword paragraph;

[0146] According to multiple keyword paragraphs in the knowledge base, a frequency vector of the knowledge base is calculated;

[0147] The frequency vectors of multiple tender documents are used as training sets, and the distance between the frequency vectors in the training set and the frequency vectors in the knowledge base is calculated;

[0148] The distance is used as a training sample, input into a support vector machine model, and the keyword paragraphs of the knowledge base are output.

[0149] In one embodiment, the matching module is further configured to:

[0150] For each bid document, calculate the TF vector and IDF vector of each keyword paragraph based on all the key fields of the keyword paragraph;

[0151] According to the TF vector and IDF vector of the keyword paragraph, the TF-IDF vector of the tender document is calculated as the frequency vector of the tender document.

[0152] In one embodiment, the matching module is further configured to:

[0153] According to the key fields and multiple keyword paragraphs in the knowledge base, the TF vector of the knowledge base is calculated as the frequency vector of the knowledge base.

[0154] In one embodiment, the apparatus further includes an updating module 309, configured to:

[0155] Update the knowledge base based on the generated tender documents.

[0156] In one embodiment, the apparatus comprises an editing module 310 for:

[0157] After receiving a chapter editing command from a customer, receiving the content of the chapter edited by the customer;

[0158] Verify the content of the received chapters;

[0159] After the verification fails, the errors in the content of the chapter are automatically corrected.

[0160] In one embodiment, the editing module 310 is further configured to:

[0161] After receiving a chapter deletion command from a client, deleting the chapter;

[0162] Verify the tender document after deleting the chapters;

[0163] If the verification fails, a deletion chapter exception reminder message is generated.

[0164] In one embodiment, the apparatus further includes a preview module 311, configured to:

[0165] Receiving a chapter preview instruction from a customer, generating a preview image of the corresponding chapter;

[0166] Receive the overall preview instruction from the customer and generate a preview image of the tender document.

[0167] In one embodiment, the apparatus further comprises a testing module 312, configured to:

[0168] Verify the tender documents;

[0169] After verification, a reminder message for generating the tender is generated;

[0170] After verification fails, errors in the tender document are automatically corrected.

[0171] To summarize, in the device proposed in the embodiment of the present invention, a bid template is determined according to the type of customer with bid preparation requirements, and an initial bid document is generated; after receiving the customer's command to select a chapter of the bid document, intelligent generation reminder information is generated, and the intelligent generation reminder information is used to remind the customer whether to use the knowledge base to intelligently generate the content of the selected chapter; after receiving the customer's confirmation to use the intelligent generation instruction, the keywords entered by the customer are received; based on the keywords entered by the customer, multiple keyword paragraphs in the knowledge base are screened out; the multiple keyword paragraphs screened out in the knowledge base are matched with a preset bid document set to match the keyword paragraphs in the knowledge base; the matched keyword paragraphs are associated with the chapter selected by the customer and added to the selected chapter; after the contents of all chapters are completed and the user's synthesis instruction is received, all the contents in the bid preparation template are synthesized to form a bid document. Compared with the technical solution in the prior art in which the user directly deletes and modifies the template and directly puts the filtered information into the bid, the embodiment of the present invention filters out multiple keyword paragraphs in the knowledge base, matches them with the preset bid document set, determines more accurate keyword paragraphs in the knowledge base, and associates them, finally forming a bid document with higher accuracy, avoiding information errors and omissions, improving the accuracy of the bid, avoiding rework and correction by staff, and improving the production efficiency of the bid.

[0172] In addition, after previewing and multiple checks and calibrations, information errors and omissions can be reduced, the accuracy of the tender documents can be improved, and the subsequent personalized production for customers can be assisted and synthesized at the same time to form personalized tender documents to meet customer needs.

[0173] An embodiment of the present invention further provides a computer device, Figure 5 It is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 530, the above-mentioned bid making method is implemented.

[0174] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned bid document preparation method is implemented.

[0175] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0176] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0177] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0179] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for preparing a tender document, characterized in that: include: Determine the tender template and generate the initial tender document according to the type of customer who needs tender preparation; After receiving a chapter selection command from a client for a bidding document, generating intelligent generation reminder information, wherein the intelligent generation reminder information is used to remind the client whether to use the knowledge base to intelligently generate the content of the selected chapter; After receiving the customer's confirmation to adopt the intelligent generation instruction, receiving the keywords input by the customer; According to the keywords input by the customer, the knowledge base is queried to filter out multiple keyword paragraphs in the knowledge base; Matching multiple keyword paragraphs in the filtered knowledge base with a preset tender document set to match the keyword paragraphs in the knowledge base; Associating the matched keyword paragraphs with the chapter selected by the customer and adding them to the selected chapter; After all chapters are completed and the synthesis instruction is received from the user, all contents in the bid making template are synthesized to form a bid document.

2. The method according to claim 1, characterized in that Before determining the tender document template based on the type of client who needs tender document preparation, it also includes: Determine whether the customer meets the requirements for tender preparation based on the customer name and type; If not, a reminder message that the tender cannot be prepared is generated; If so, determine the bid template based on the type of client who needs bid preparation.

3. The method according to claim 1, characterized in that Also includes: After receiving the intelligent generation instruction from the customer, the title of the selected chapter is parsed to obtain the keywords in the title; According to the keywords entered by the customer, the knowledge base is queried, including: Query the knowledge base based on the keywords entered by the customer and the keywords in the title.

4. The method according to claim 1, characterized in that The multiple keyword paragraphs in the filtered knowledge base are matched with the preset tender document set to match the keyword paragraphs in the knowledge base, including: Get a preset set of bid documents for bid templates; For each keyword paragraph of the bid template, determine the key fields in the keyword paragraph; For each tender document, the frequency vector of the tender document is calculated based on all the key fields of each keyword paragraph; According to multiple keyword paragraphs in the knowledge base, a frequency vector of the knowledge base is calculated; The frequency vectors of multiple tender documents are used as training sets, and the distance between the frequency vectors in the training set and the frequency vectors in the knowledge base is calculated; The distance is used as a training sample, input into a support vector machine model, and the keyword paragraphs of the knowledge base are output.

5. The method according to claim 4, characterized in that For each tender document, the frequency vector of the tender document is calculated based on all the key fields of each keyword paragraph, including: For each bid document, calculate the TF vector and IDF vector of each keyword paragraph based on all the key fields of the keyword paragraph; According to the TF vector and IDF vector of the keyword paragraph, the TF-IDF vector of the tender document is calculated as the frequency vector of the tender document.

6. The method according to claim 4, characterized in that Based on multiple keyword paragraphs in the knowledge base, the frequency vector of the knowledge base is calculated, including: According to the key fields and multiple keyword paragraphs in the knowledge base, the TF vector of the knowledge base is calculated as the frequency vector of the knowledge base.

7. The method according to claim 1, characterized in that Also includes: Update the knowledge base based on the generated tender documents.

8. The method according to claim 1, characterized in that Also includes: After receiving a chapter editing command from a customer, receiving the content of the chapter edited by the customer; Verify the content of the received chapters; After the verification fails, the errors in the content of the chapter are automatically corrected.

9. The method according to claim 1, characterized in that Also includes: After receiving a chapter deletion command from a client, deleting the chapter; Verify the tender document after deleting the chapters; If the verification fails, a deletion chapter exception reminder message is generated.

10. The method according to claim 1, characterized in that Also includes: Receiving a chapter preview instruction from a customer, generating a preview image of the corresponding chapter; Receive the overall preview instruction from the customer and generate a preview image of the tender document.

11. The method according to claim 1, characterized in that Also includes: Verify the tender documents; After verification, a reminder message for generating the tender is generated; After verification fails, errors in the tender document are automatically corrected.

12. A bidding document making device, characterized in that: include: The initial tender document generation module is used to determine the tender document template and generate the initial tender document according to the type of customer who has tender document production requirements; A reminder information generation module, which is used to generate intelligent generation reminder information after receiving a command from a customer to select a chapter of a tender document, wherein the intelligent generation reminder information is used to remind the customer whether to use the knowledge base to intelligently generate the content of the selected chapter; A keyword input module is used to receive keywords input by the customer after receiving the customer's confirmation to adopt the intelligent generation instruction; The screening module is used to query the knowledge base according to the keywords input by the customer and screen out multiple keyword paragraphs in the knowledge base; A matching module, used to match the multiple keyword paragraphs screened out from the knowledge base with a preset bid document set, and match the keyword paragraphs in the knowledge base; An association module is used to associate the matched keyword paragraphs with the chapters selected by the customer and add them to the selected chapters; The tender document forming module is used to synthesize all the contents in the tender document making template to form a tender document after the contents of all chapters are completed and the user's synthesis instruction is received.

13. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images