Electronic bidding and procurement method and system

Abstract

The present invention provides an electronic bidding procurement method and system, the method comprising: obtaining a first bidding document, identifying text information in the first bidding document, and identifying keywords and data items in the first bidding document according to the text information; configuring screening conditions for keywords and data items, searching for text information of each bidding document according to the screened keywords and data items, and judging whether there are corresponding keywords and data items in the text information of the first bidding document; according to the screening conditions, obtaining a second bidding document that meets the keyword and data item requirements from the first bidding document; and manually reviewing the screened second bidding document.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic bidding and tendering, and in particular to an electronic bidding and tendering procurement method and system. Background Art

[0002] Currently, the existing bidding documents need to be manually reviewed. For core projects, there are a lot of bidding documents, which may reach thousands or even tens of thousands. A considerable part of these bidding documents may not meet the current bidding requirements because of core qualifications or data items. Therefore, these bidding documents can be directly removed without manual review. However, the existing bidding procurement methods all require manual review. In addition, because there are too many bidding documents, it may be necessary to comprehensively screen the appropriate number of copies based on the weight of the elements of each bidding document and then manually screen them. The existing screening methods all screen each bidding document manually. Therefore, a large amount of human resources are wasted on the query and retrieval of invalid bidding documents, resulting in slow progress of the entire project. Summary of the invention

[0003] One of the invention purposes of the present invention is to provide an electronic bidding procurement method and system, wherein the method and system are provided with a screening module, wherein the screening module can be configured with different screening data items and keywords, and further performs data item search and keyword search in each bid document for the configured screening data items and screening keywords, and retains the bidding documents that meet the data items and keywords, and deletes the bidding documents that do not meet the data items and keywords. This greatly reduces the manual reading operation of the bidding documents.

[0004] Another inventive object of the present invention is to provide an electronic bidding and procurement method and system, wherein the screening module of the method and system further configures weights for different data items and keywords, and after obtaining the corresponding keywords and data item contents, further assigns values ​​to the data items and keywords of each bid according to preset weights and performs weighted summation to obtain the matching value of the current bid, configures the corresponding matching threshold in the system, and retains the bid documents that are greater than or equal to the matching threshold, wherein the matching threshold is adjustable, so that a suitable number of bid documents can be quickly screened for manual review, thereby reducing the cost of manual review.

[0005] Another inventive object of the present invention is to provide an electronic bidding and procurement method and system, which classifies each data item and keyword, marks the sets of different keyword and data item classifications, and further counts the different keywords and data items in the marked classification sets. The number of data items and keywords in the corresponding marked classification sets can be used as screening criteria for the current bidding documents, thereby improving the quality of screening.

[0006] In order to achieve at least one of the above-mentioned invention objects, the present invention further provides an electronic bidding procurement method, the method comprising:

[0007] Acquire a first bidding document, identify text information in the first bidding document, and identify first keywords and data items in the first bidding document according to the text information;

[0008] Configuring the screening conditions of keywords and data items, searching the text information of each bidding document according to the screened first keywords and data items, and determining whether the corresponding first keywords and data items exist in the text information of the first bidding document;

[0009] According to the screening condition, obtaining a second bidding document that meets the first keyword and data item requirements from the first bidding document;

[0010] The screened second bidding document will be manually reviewed.

[0011] According to one of the preferred embodiments of the present invention, the first keyword type includes the bidder's qualification certificate, the bidder's honors, the bidder's award data, the bidder's business scope, the bidder's address, and the bidder's scientific and technological achievements; the data item types include the bidder's financial data items, the bidder's quotation data items, the bidder's scale data items, the bidder's R&D investment data items, and the bidder's R&D scientific and technological achievements transformation data items.

[0012] According to another preferred embodiment of the present invention, the keyword recognition method includes: the first keyword recognition method includes: configuring different first keywords and corresponding keyword synonyms, automatically searching each bidding document for the first keyword and the corresponding keyword synonyms through a search engine, and judging whether the corresponding first keyword and the corresponding keyword synonyms exist in the current bidding document. If so, marking the current bidding document with the first keyword; the first keywords and the corresponding keyword synonyms are pre-configured, and the text information of each bidding document is retrieved by all the first keywords and the corresponding keyword synonyms, and each bidding document is marked with the retrieved keywords.

[0013] According to another preferred embodiment of the present invention, the data item identification method includes: configuring a second keyword corresponding to the data item, using a search engine to search from each bidding document whether the second keyword corresponding to the data item exists, if so, locating the position of the second keyword in the bidding document, and further searching for the closest numerical data in the subsequent text based on the positioning, binding the numerical data and the second keyword as the data item of the current text, and marking the bidding document with the second keyword; wherein a distance threshold for the number of characters to be searched is set, and if the number of characters between the current positioning position of the second keyword and the numerical data found in the subsequent text is greater than the distance threshold for the number of characters, the second keyword is discarded.

[0014] According to another preferred embodiment of the present invention, the method for screening bid documents includes: after obtaining the keywords and data items of each bid document, initially assigning values ​​to the keywords and data items respectively, further assigning weights to the first keywords and data items respectively, multiplying the initial assignments of the corresponding first keywords and data items by the corresponding weight assignments, and summing the products of the initial assignments and weight assignments of all the first keywords and data items of the current bid document to obtain a matching score for the current bid document.

[0015] According to another preferred embodiment of the present invention, the current matching score is processed as follows: the matching scores of all bidding documents are obtained, the maximum matching score and the minimum matching score of the bidding documents are obtained, normalization processing is performed according to the maximum matching score and the minimum matching score of the bidding documents, and all bidding documents after the normalization of the matching scores are sorted according to the score size, a matching threshold is set, and the bidding documents with matching scores greater than or equal to the matching threshold are retained for manual review.

[0016] According to another preferred embodiment of the present invention, the data item assignment method includes: setting a segmented initial assignment of the data item numerical data, and performing weight assignment according to the data item type corresponding to the second keyword of the data item, determining the segmented initial assignment value corresponding to the numerical data bound to the current second keyword, and multiplying the weight assignment corresponding to the bound second keyword to obtain a complete data item assignment.

[0017] According to another preferred embodiment of the present invention, all the marked first keywords and second keywords of the data items in all the bidding documents are obtained, the first keywords and the second keywords of the data items are classified to obtain different keyword classification sets, and the keyword classification sets are classified and labeled, and a keyword number threshold for each classification and labeling set is set. If the number of keywords in the classified and labeled set meets the keyword threshold, the bidding document that currently meets the threshold is retained for subsequent manual review.

[0018] In order to achieve at least one of the above-mentioned invention purposes, the present invention further provides an electronic bidding and procurement system, which executes the above-mentioned electronic bidding and procurement method.

[0019] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned electronic bidding and procurement method. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Shown is a schematic flow chart of an electronic bidding and procurement method of the present invention. DETAILED DESCRIPTION

[0021] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0022] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0023] Please combine Figure 1The present invention discloses a bidding procurement method and system, wherein the method mainly includes the following steps: first, it is necessary to obtain bidding documents prepared by different bidders, wherein the bidding documents are electronic documents, and the electronic document formats may include but are not limited to word and PDF, wherein the text in the bidding electronic documents is further recognized, wherein the recognition method may adopt text recognition models including but not limited to existing OCR, etc., after the text recognition of each bidding document is obtained, the bidding document is further processed, wherein the data processing content includes identifying keywords and data items in the text data of the bidding document, wherein the keywords and data items are preset according to the bidding requirements, such as necessary keywords related to the qualifications of the bidders, etc., and after the above keywords and data items are selected, the corresponding keywords are further searched in the bidding document, and if the corresponding keywords exist in the bidding document at this time, the bidding document is directly marked with the keywords found. At this time, the bidding document obtains a marked keyword, and the second keyword of the data item is further queried. If the current bidding document stores the second keyword of the data item and the second keyword of the bidding document is marked, further data processing is performed based on the marked keyword to determine whether the current bidding document meets the bidding requirements. The method and system of the present invention can identify, automatically judge and screen by themselves, so that the manual review cost of the bidding document can be greatly reduced.

[0024] Specifically, the present invention stores the text information identified by the above-mentioned bidding documents in sequence into a database, and performs a search for corresponding keywords through a database search engine. For example, the database may include but is not limited to a mysql database and an InnoDB database, etc. The present invention takes a mysql database as an example, wherein the identified bidding document text information is used to construct an index and a database table, and the corresponding keywords are searched through the database table and index. Since the construction method of the mysql database is a prior art, the present invention does not improve the database, so the present invention does not elaborate on how to construct the mysql database. The present invention defines the bidding document initially obtained as the first bidding document, the first bidding document includes multiple bidding documents, and the first keyword is pre-configured, wherein the main content of the first keyword includes but is not limited to: the bidder's qualification certificate, the bidder's honors, the bidder's award data, the bidder's business scope, the bidder's address, and the bidder's scientific and technological achievements. The first keyword is used to non-quantitatively explain the relevant qualifications of the bidder, such as whether the bidder has an engineering design qualification certificate for undertaking a construction project, a land development permit, a building installation permit, a fire certificate, etc., wherein the first keyword also includes the level of the above-mentioned relevant qualifications, such as the first-level qualification, second-level qualification and third-level qualification in the field of construction, etc., and the corresponding bidding honors can be, for example, different levels of architectural design awards, etc., and the corresponding scientific and technological achievements can be patents, copyrights, integrated circuit layouts, appearances, etc. The present invention configures the above-mentioned first keyword combination according to the requirements of the current bidding project itself. In other preferred embodiments of the present invention, corresponding approximate words are configured for each of the above-mentioned first keywords, such as the synonyms of the first-level construction qualification can be the first-level construction qualification, the first-level construction level, etc., and the text information stored in the mysql database is searched in turn through the above-mentioned first keywords and the corresponding keyword approximate words to determine whether the above-mentioned first keyword and the corresponding approximate keyword exist in each first bidding document. If so, the first keyword is used to mark the first bidding document to obtain the marked keyword, and the different first keywords of each bidding document are marked.

[0025] Further, the present invention also configures a data item, wherein the data item includes a second keyword and corresponding numerical data, wherein the second keyword and the numerical data in the data item are bound, wherein the type of the second keyword includes but is not limited to the bidder's financial data item, the bidder's quotation data item, the bidder's scale data item, the bidder's R&D investment data item, and the bidder's research and development technology achievement transformation data item. The numerical data includes single data and segmented data, wherein the single data is data greater than a certain value, and the segmented data is data in different numerical intervals. For example, the single data can be set to be greater than or equal to 8, and the segmented data can be set to [1,2], [5,6]. The present invention matches each first bidding document with respect to the second keyword and the corresponding numerical data, wherein the matching method specifically includes the following steps: first, the second keyword is identified from the first bidding document, wherein the second keyword includes but is not limited to: sales revenue, project quotation, enterprise scale, R&D investment, cash flow, number of patents, etc., and the above second keyword is a feature description word with corresponding numerical data. Therefore, after identifying the above second keyword, the present invention further locates the position of the second keyword in the bidding document and determines the character order in the text information where the second keyword is located. It should be noted that when the text information of the first bidding document is stored in the MySQL database, the character storage order of each word will be recorded, and the character storage order is executed according to the previous and next contents of the text information. Therefore, the present invention further locates the second keyword according to the character storage order of the text information. After obtaining the location information of the second keyword, further search for numerical data in the subsequent text content of the located second keyword position, and intercept the numerical data closest to the current second keyword position in the subsequent text content of the second keyword. For example, the text content can be: "At present, the R&D investment of our company is 132641201 yuan, and the sales revenue of the R&D project is 952142041 yuan." The numerical data closest to the subsequent location of the current second keyword "R&D investment" is: 132641201, and the second keyword "R&D investment" and "132641201" are further bound as the current data item content. In another preferred embodiment of the present invention, since the numerical data in the current data item content may have different numerical units, the present invention further identifies the last numerical unit of the numerical data that is closest to the subsequent numerical data of the second keyword, and converts the numerical unit into complete numerical data. For example, the numerical data obtained by locating the second keyword may be 130 million yuan. There is a numerical unit "100 million" after the numerical data 1.3, and the numerical unit is converted into 1*10 9 Numerical data, further multiply the numerical data of the numerical unit by the previous numerical data to get 1.3*10 9As the complete numerical data of the data item. Of course, in some other preferred embodiments of the present invention, there may be part of the text content is also numerical data, the present invention further identifies the numerical text of the Chinese content in the text content after the second keyword positioning, such as 130 million yuan, then the current "130 million" text content can be automatically identified and converted into the numerical data 1.3*10 9 The numerical data of the second keyword closest to the location obtained after the above processing is bound to the processed numerical data and the second keyword to form a complete data item.

[0026] It is worth mentioning that, since some second keywords may be an interpretation of themselves rather than an interpretation of numerical data, if the subsequent numerical data of the located second keyword is too far away from the second keyword, the current numerical data may not match the corresponding located second keyword. Therefore, the present invention further configures a character distance threshold to calculate the number of characters between the last character of the currently located second keyword and the closest numerical data found. In one of the preferred embodiments of the present invention, the closest numerical data also includes numerical data converted from text numerical values. When the calculated number of characters between the last character of the second keyword and the closest numerical data found is greater than the character distance threshold, it means that the current second keyword is not matched. The second keyword and the corresponding numerical data do not match, and the current second keyword and the corresponding numerical data are further discarded. For example: the character distance threshold is set to 5, and the text content is: "Currently, our company's R&D investment is large, and the sales revenue of the R&D project is 952142041 yuan." The located second keyword is "R&D investment", and the corresponding numerical data closest to the second keyword "R&D investment" is "952142041". At the same time, the number of characters between the current second keyword "R&D investment" and the numerical data "952142041" is calculated to be 13, of which the counted number of characters is greater than the character distance threshold 5. At this time, the current "R&D investment" and the retrieved numerical data "952142041" are discarded.

[0027] Furthermore, after obtaining the first keyword and the second keyword of each bidding document, the present invention respectively performs initial assignments on the first keyword and the second keyword, wherein all the first keywords are assigned a uniform value, for example, the first keyword can be uniformly assigned an initial value of 1, and weights are configured for different first keywords according to the actual needs of the bidding project. The second keyword can be assigned a segmented value or a single value according to the corresponding numerical data. For example, when the numerical data corresponding to the second keyword is a single numerical range, and the configured numerical data conforms to the numerical range, the current second keyword is assigned a single initial value of 1. If the current second keyword is a segmented numerical range, different segmented numerical values ​​can be assigned only segmented initial values, for example, [1,2], [5,6] can be assigned segmented values ​​of 1 and 2 in sequence, and the second keyword that meets the corresponding segmented numerical value is further assigned a segmented initial value. And according to the actual bidding needs, the corresponding second keyword is assigned a weight, and all the initial assignments of the first keyword are further multiplied by the corresponding weights, and the initial assignments of the second keyword are multiplied by the corresponding weights, and the multiplication results are accumulated and summed to obtain the matching value of the current bidding document. A matching degree threshold is further configured. If the calculated matching degree value is greater than the matching degree threshold, the corresponding bid document is retained as the second bid document.

[0028] The present invention can perform the following normalization and standardization operations on the matching values: obtain the matching scores of all bidding documents, obtain the maximum matching score and the minimum matching score of the bidding documents, perform normalization processing according to the maximum matching score and the minimum matching score of the bidding documents, and sort the bidding documents after the normalization processing of all matching scores according to the size of the scores, set a matching threshold, and retain the bidding documents with matching scores greater than or equal to the matching threshold for manual review.

[0029] In another preferred embodiment of the present invention, the bidding documents can be screened in the form of a data set: all the marked first keywords and second keywords of the data items in all the bidding documents are obtained, the first keywords and the second keywords of the data items are classified to obtain different keyword classification sets, and the keyword classification sets are classified and labeled, and a keyword number threshold for each classification and labeling set is set. If the number of keywords in the classified and labeled set meets the keyword threshold, the bidding documents that currently meet the threshold are retained for subsequent manual review.

[0030] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, 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 above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0031] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0032] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. An electronic bidding procurement method, characterized in that: The method comprises: Acquire a first bidding document, identify text information in the first bidding document, and identify first keywords and data items in the first bidding document according to the text information; specifically: The data item identification method comprises: configuring a second keyword corresponding to the data item, using a search engine to search from each bidding document whether the second keyword corresponding to the data item exists, if so, locating the position of the second keyword in the bidding document, and further searching for the closest numerical data in the subsequent text according to the location, binding the numerical data and the second keyword as the data item of the current text, and marking the bidding document with the second keyword; wherein a character distance threshold of the number of characters to be searched is set, and if the number of characters between the current second keyword location and the numerical data found in the subsequent text is greater than the character distance threshold of the number of characters, the second keyword is discarded; Configure a screening condition for keywords and data items, search for text information of each bidding document according to the first keyword and data item screened by the screening condition, and determine whether the corresponding first keyword and data item exist in the text information of the first bidding document; According to the screening condition, a second bidding document that meets the first keyword and data item requirements is obtained from the first bidding document; and the screened second bidding document is manually reviewed; The types of the first keywords include the bidder's qualification certificate, the bidder's honors, the bidder's award data, the bidder's business scope, the bidder's address, and the bidder's scientific and technological achievements; the types of the data items include the bidder's financial data items, the bidder's quotation data items, the bidder's scale data items, the bidder's R&D investment data items, and the bidder's R&D scientific and technological achievements transformation data items; The screening method of the first bidding document includes: after obtaining the keywords and data items of each bidding document, initially assigning values ​​to the keywords and data items respectively, further assigning weights to the keywords and data items respectively, multiplying the initial assignments of the corresponding keywords and data items by the corresponding weight assignments, summing the products of the initial assignments and weight assignments of all keywords and data items in the current bidding document to obtain a matching score of the current bidding document; the data item assignment method includes: setting a segmented initial assignment of the numerical data of the data item, and assigning weights according to the data item type corresponding to the second keyword of the data item, determining the segmented initial assignment value corresponding to the numerical data bound to the current second keyword, and multiplying the weight assignments corresponding to the bound second keyword to obtain a complete data item assignment.

2. An electronic bidding procurement method according to claim 1, characterized in that: The first keyword recognition method includes: configuring different first keywords and corresponding keyword synonyms, automatically searching each bidding document for the first keyword and the corresponding keyword synonyms through a search engine, judging whether the corresponding first keyword and the corresponding keyword synonyms exist in the current bidding document, and if so, marking the current bidding document with the first keyword; the first keywords and the corresponding keyword synonyms are pre-configured, the text information of each bidding document is retrieved by all the first keywords and the corresponding keyword synonyms, and each bidding document is marked with the retrieved keywords.

3. The electronic bidding procurement method according to claim 1, characterized in that: The matching score of the current bid document is processed as follows: the matching scores of all first bid documents are obtained, the maximum matching score and the minimum matching score of the first bid document are obtained, normalization is performed according to the maximum matching score and the minimum matching score of the first bid document, and all the first bid documents after the normalization of the matching scores are sorted according to the score size, a matching threshold is set, and the second bid documents with matching scores greater than or equal to the matching threshold are retained for manual review.

4. The electronic bidding procurement method according to claim 1, characterized in that: Obtain all the marked keywords and second keywords of the data items in all the first bidding documents, classify the keywords and second keywords of the data items to obtain different keyword classification sets, classify and annotate the keyword classification sets, set a keyword number threshold for each classification annotated set, and if the number of keywords in the classified classification annotated set meets the keyword number threshold, retain the currently satisfied second bidding document for subsequent manual review.

5. An electronic bidding and procurement system, characterized in that: The system executes an electronic bidding and procurement method as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement an electronic bidding and procurement method as described in any one of claims 1 to 4.

Images