CN113156864A - Subway project evaluation management system - Google Patents

Subway project evaluation management system Download PDF

Info

Publication number
CN113156864A
CN113156864A CN202110485663.7A CN202110485663A CN113156864A CN 113156864 A CN113156864 A CN 113156864A CN 202110485663 A CN202110485663 A CN 202110485663A CN 113156864 A CN113156864 A CN 113156864A
Authority
CN
China
Prior art keywords
unit
module
evaluation
rating
expert
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110485663.7A
Other languages
Chinese (zh)
Inventor
姜涛
赖步一
黄震
李平安
李勤
魏莹
孟祥宇
张永明
雷尉
陈亦文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Metro Group Co ltd
Original Assignee
Shenzhen Metro Group Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Metro Group Co ltd filed Critical Shenzhen Metro Group Co ltd
Priority to CN202110485663.7A priority Critical patent/CN113156864A/en
Publication of CN113156864A publication Critical patent/CN113156864A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/04Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G05B19/0428Safety, monitoring
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/20Pc systems
    • G05B2219/24Pc safety
    • G05B2219/24024Safety, surveillance

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Character Discrimination (AREA)

Abstract

The invention discloses a subway engineering evaluation and calibration management system which comprises a bidding document input end, an identification module, a review module, an alarm module, a central processing unit and a calibration result output end, wherein the bidding document input end is connected with the central processing unit; the bidding document input module is connected with the identification module; the identification module is connected with the review module; and a review module: for scoring the in-tender document; the alarm module receives abnormal data generated by the identification module and the review module; the calibration result output end is used for determining and publishing the scoring result, and is connected with the review module; the central processing unit is used for storing data. The invention can rapidly identify the information contained in the bidding document through the identification module, the alarm module ensures the fairness and justice in the bid evaluation process, and the combination of the identification module and the evaluation module avoids the bias of experts to subway engineering bidding enterprises and simultaneously improves the working efficiency.

Description

Subway project evaluation management system
Technical Field
The invention relates to the field of management systems, in particular to a subway project evaluation management system.
Background
With the development of the urban economy in China, the population quantity of urban residents is continuously increased, the number of vehicles is also continuously increased, and the traffic transportation pressure in China is increased more and more. The increase of the number of vehicles in China not only easily causes traffic congestion, but also easily causes traffic accidents and harms the life safety of people, and the subway engineering construction can well relieve the traffic congestion and is convenient for people to go out.
At present, the subway engineering bid inviting purchase is a convenient, efficient, transparent and environment-friendly transaction activity, while the traditional bid inviting purchase item is performed in a paper file and manual bid evaluation mode, when a large bid inviting and bidding item is encountered, the manual bid evaluation not only takes a long time, but also easily causes the problems of hand mistake and bias, and further causes the deviation of the evaluation result.
Disclosure of Invention
The invention solves the technical problem and provides a quick and efficient subway project assessment standard management system.
In order to solve the above technical problems, a first aspect of the present invention provides a subway project evaluation management system, including: the system comprises a bidding document input end, an identification module, a review module, an alarm module and a calibration result output end;
the bidding document input module is used for uploading bidding documents of enterprises and is connected with the identification module;
the identification module is used for identifying the content of the enterprise bidding document and is connected with the review module;
the evaluation module is used for scoring the bidding document;
the alarm module is used for giving an alarm to the data which are abnormal in the violation behaviors of the experts and in the evaluation process of the experts, and the alarm module receives the abnormal data generated by the identification module and the evaluation module;
and the calibration result output end is used for determining and publishing the scoring result, and is connected with the review module.
And the central processing unit is used for storing the data of the identification module, the review module, the alarm module and the calibration result output end.
As a further scheme of the invention, the bidding document input module comprises enterprise business licenses, industry categories, company qualifications, financial statements, historical cooperative engineering projects, project quotations and engineering quality.
As a further scheme of the present invention, the recognition module includes a text recognition unit and a semantic recognition unit, the text recognition unit is configured to perform content recognition on the obtained bidding document, the semantic recognition unit extracts the meaning of the text, and the text recognition unit is connected to the semantic recognition unit.
As a further scheme of the invention, the evaluation module comprises an evaluation expert information unit, a evaluation standard unit and an evaluation scoring unit, wherein the evaluation standard unit is respectively connected with the semantic identification unit and the expert information unit, and the expert information unit is connected with the evaluation scoring unit. And in the auditing module, the expert scores the system according to the scoring standard, and compared with paper document examination, the method avoids the bias of the expert to subway engineering bidding enterprises and improves the working efficiency.
As a further scheme of the invention, the alarm module comprises a bid evaluation expert video unit and a bid evaluation expert scoring abnormity unit, and the bid evaluation expert scoring abnormity unit is connected with the bid evaluation scoring unit. The video unit of the bid evaluation expert is used for recording abnormal behaviors and sounds of the bid evaluation expert in the scoring process, and the scoring abnormal unit of the bid evaluation expert is used for recording abnormal scores of the bid evaluation expert in the scoring process.
As a further scheme of the invention, the calibration result output end comprises a bid evaluation report unit, an enterprise ranking unit and an announcement unit, wherein the bid evaluation report unit is connected with the bid evaluation expert information unit, and the enterprise ranking unit is connected with the bid evaluation expert unit. And the calibration result output end is used for displaying the bid winning condition of the bidding enterprises participating in the subway project.
As a further aspect of the present invention, the processing steps of the identification module are:
(1-1) converting the bidding document into an image through a camera, correcting the image and acquiring a text line in the image;
(1-2) checking a semantic recognition result of the text line to be recognized;
(1-3) constructing a neural network model, performing convolution on the text lines, dividing the text lines into a training set and a verification set, and calculating similarity data of the text lines corresponding to the semantic recognition results to be selected;
and (1-4) determining the final semantic recognition result of the text line from each semantic recognition result to be selected according to the similarity data of the semantic recognition results.
The text line is trained through the neural network, and the semantic recognition result is determined by calculating the similarity data of the text line corresponding to the semantic recognition result to be selected, so that the text line is optimized, the recognition accuracy is increased, and the bidding document content can be rapidly obtained by the expert for spelling, examination and evaluation.
As a further scheme of the invention, in the step (1-2), the text line and the semantic recognition result to be selected are subjected to word segmentation, the word segmentation is converted into a first word vector, and the semantic recognition result to be selected is converted into a second word vector; and calculating the similarity of the first word vector and the second word vector through cosine similarity.
According to the method, the similarity between the first word vector and the second word vector is calculated through cosine similarity, the text line is quantized through word segmentation by training, and the accuracy of image recognition is improved through cosine similarity calculation between the word vectors.
In a further aspect of the present invention, the cosine similarity is calculated according to the following formula:
Figure 100002_DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 775437DEST_PATH_IMAGE002
the first-time vector is represented by a vector,
Figure 870432DEST_PATH_IMAGE003
the vector of the second time is represented,
Figure 991972DEST_PATH_IMAGE004
representing a vector
Figure 955249DEST_PATH_IMAGE002
And vector
Figure 314686DEST_PATH_IMAGE003
The product of (a);
Figure 846161DEST_PATH_IMAGE005
and
Figure 48472DEST_PATH_IMAGE006
respectively represent vectors
Figure 956386DEST_PATH_IMAGE002
Sum vector
Figure 701488DEST_PATH_IMAGE003
The die of (1).
Compared with the prior art, the invention has the beneficial effects that: the invention can rapidly identify the information contained in the bidding document through the identification module, is convenient for experts to evaluate, can monitor the condition that the experts violate rules or score abnormally in the expert evaluation process in real time through the alarm module, ensures the fairness and the justice in the bidding process, shortens the scoring time by combining the identification module and the review module when the experts evaluate the bidding document, scores the experts in the review module according to the scoring standard on the system, and improves the working efficiency while avoiding the bias of the experts to subway engineering bidding enterprises compared with paper document review.
Drawings
Fig. 1 is a schematic structural diagram of a subway project evaluation management system according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a metro project evaluation management method according to an embodiment of the present invention.
Detailed Description
The following examples are further illustrative of the present invention and are not intended to be limiting thereof.
Example 1
Referring to fig. 1, an embodiment 1 of the present invention provides a subway project evaluation management system, including: the system comprises a bidding document input end 201, an identification module 202, a review module 203, an alarm module 204, a central processing unit 205 and a calibration result output end 206;
the bidding document input module is used for uploading bidding documents of enterprises, and is connected with the identification module 202;
the identification module 202 is used for identifying the content of the enterprise bidding document, and the identification module 202 is connected with the review module 203;
the evaluation module 203 is used for scoring the bidding document;
the alarm module 204 is used for giving an alarm to the data which is abnormal in the violation behaviors of the experts and in the evaluation process of the experts, and the alarm module 204 receives the abnormal data generated by the identification module 202 and the evaluation module 203;
the calibration result output end 206 is used for determining and publishing the scoring result, and the calibration result output end 206 is connected with the review module 203;
the central processor 205 is used for storing data of the identification module 202, the review module 203, the alarm module 204 and the calibration result output terminal 206.
Further, in the embodiment of the present invention, the bidding document input module includes an enterprise license, an industry category, a company qualification, a financial statement, a historical collaborative engineering project, a project quotation, and an engineering quality.
Further, in this embodiment of the present invention, the identification module 202 includes a text identification unit and a semantic identification unit, the text identification unit is configured to identify contents of the obtained bidding document, the semantic identification unit extracts meaning of the text, and the text identification unit is connected to the semantic identification unit.
Further, in the embodiment of the present invention, the review module 203 includes a bid evaluation expert information unit, a scoring standard unit, and a bid evaluation scoring unit, where the scoring standard unit is connected to the semantic identification unit and the expert information unit, respectively, and the expert information unit is connected to the bid evaluation scoring unit. The bid evaluation expert information unit comprises bid evaluation expert types, expert seniors and expert working experiences. And in the auditing module, the expert scores the system according to the scoring standard, and compared with paper document examination, the method avoids the bias of the expert to subway engineering bidding enterprises and improves the working efficiency. When scoring, the evaluation expert firstly evaluates the qualification of the enterprise company, carries out detailed evaluation on the enterprises with qualified qualification, carries out evaluation scoring on the detailed evaluation according to the evaluation standard unit for comparing the engineering quotation, the engineering quality, the enterprise scale and the like of the enterprises, and finally carries out total score calculation on the used system to obtain the ranking of the enterprise evaluation result.
Further, in the embodiment of the present invention, the alarm module 204 includes a bid evaluation expert video unit and a bid evaluation expert scoring exception unit, and the bid evaluation expert scoring exception unit is connected to the bid evaluation scoring unit. The video unit of the bid evaluation expert is used for recording abnormal behaviors and sounds of the bid evaluation expert in the scoring process, and the scoring abnormal unit of the bid evaluation expert is used for recording abnormal scores of the bid evaluation expert in the scoring process.
Further, in the embodiment of the present invention, the calibration result output end 206 includes an evaluation report unit, an enterprise ranking unit and an announcement unit, the evaluation report unit is connected to the evaluation expert information unit, and the enterprise ranking unit is connected to the evaluation expert unit.
The embodiment of the invention can rapidly identify the information contained in the bidding document through the identification module 202, is convenient for experts to evaluate, can monitor the condition that the experts violate rules or score abnormally in the process of evaluating the bidding documents in real time through the alarm module 204, ensures the fairness and justness in the process of evaluating the bidding documents, shortens the time of scoring by combining the identification module 202 and the evaluation module 203 when the experts evaluate the bidding documents, scores the experts in the evaluation module 203 on the system according to the scoring standard, and improves the working efficiency while avoiding the bias of the experts to subway engineering bidding enterprises compared with paper document review.
Further, the processing steps of the identification module 202 are as follows:
(1-1) converting the bidding document into an image through a camera, correcting the image and acquiring a text line in the image;
(1-2) checking a semantic recognition result of the text line to be recognized;
(1-3) constructing a neural network model, performing convolution on the text lines, dividing the text lines into a training set and a verification set, and calculating similarity data of the text lines corresponding to the semantic recognition results to be selected;
and (1-4) determining the final semantic recognition result of the text line from each semantic recognition result to be selected according to the similarity data of the semantic recognition results.
The text line is trained through the neural network, and the semantic recognition result is determined by calculating the similarity data of the text line corresponding to the semantic recognition result to be selected, so that the text line is optimized, the recognition accuracy is increased, and the bidding document content can be rapidly obtained by the expert for spelling, examination and evaluation.
Further, in the step (1-2) of the embodiment of the present invention, the text line and the result of the semantic recognition to be selected are subjected to word segmentation, and the word segmentation is converted into a first word vector, and the result of the semantic recognition to be selected is converted into a second word vector; and calculating the similarity of the first word vector and the second word vector through cosine similarity.
The similarity between the first word vector and the second word vector is calculated through cosine similarity, the text line is quantized through word segmentation by training, and the accuracy of image recognition is improved through calculation of cosine similarity between the word vectors.
As a further scheme of the present invention, the calculation formula of the cosine similarity is:
Figure 262919DEST_PATH_IMAGE007
wherein the content of the first and second substances,
Figure 93472DEST_PATH_IMAGE008
the first-time vector is represented by a vector,
Figure 539497DEST_PATH_IMAGE009
the vector of the second time is represented,
Figure 499625DEST_PATH_IMAGE010
representing a vector
Figure 107324DEST_PATH_IMAGE011
And vector
Figure 549806DEST_PATH_IMAGE012
The product of (a);
Figure 268363DEST_PATH_IMAGE013
and
Figure DEST_PATH_IMAGE014
respectively represent vectors
Figure 847112DEST_PATH_IMAGE015
Sum vector
Figure DEST_PATH_IMAGE016
The die of (1).
According to the invention, the similarity between the first word vector and the second word vector is calculated through cosine similarity, the word segmentation is converted through training, the quantization of text lines is realized, and the accuracy of similarity value calculation is improved through cosine similarity calculation between the word vectors.
According to the embodiment of the invention, the neural network is constructed, the text line is trained, the similarity of the text line to the semantic recognition result to be selected is calculated, and the recognition of the text line content is accurately and quickly realized.
The above detailed description is specific to possible embodiments of the present invention, and the above embodiments are not intended to limit the scope of the present invention, and all equivalent implementations or modifications that do not depart from the scope of the present invention should be included in the present claims.

Claims (9)

1. A subway project rating and scale management system, comprising: the system comprises a bidding document input end, an identification module, a review module, an alarm module, a central processing unit and a calibration result output end;
the bidding document input module is used for uploading bidding documents of enterprises and is connected with the identification module;
the identification module is used for identifying the content of the enterprise bidding document and is connected with the review module;
the evaluation module is used for scoring the bidding document;
the alarm module is used for giving an alarm to the data which are abnormal in the violation behaviors of the experts and in the evaluation process of the experts, and the alarm module receives the abnormal data generated by the identification module and the evaluation module;
the calibration result output end is used for determining and publishing the scoring result, and the calibration result output end is connected with the review module;
and the central processing unit is used for storing the data of the identification module, the review module, the alarm module and the calibration result output end.
2. A subway project evaluation and management system as claimed in claim 1, wherein said bidding document input module includes enterprise license, industry category, company qualification, financial statement, historical collaborative project, project quotation, project quality.
3. The subway engineering assessment scale management system of claim 1, wherein said identification module comprises a text identification unit and a semantic identification unit, said text identification unit is connected to said semantic identification unit.
4. The system of claim 1, wherein the review module comprises a bid evaluation expert information unit, a bid evaluation standard unit and a bid evaluation scoring unit, the bid evaluation standard unit is respectively connected with the semantic recognition unit and the expert information unit, and the expert information unit is connected with the bid evaluation scoring unit.
5. The subway project rating and bidding management system as claimed in claim 1, wherein said alarm module comprises a video unit of rating expert for recording abnormal behavior and sound of rating expert during rating process, and a rating abnormal unit of rating expert for recording abnormal score during rating process, said rating abnormal unit of rating expert for bidding being connected to the rating unit of rating expert.
6. The system as claimed in claim 1, wherein the calibration result output end comprises a bid evaluation report unit, an enterprise ranking unit and a bulletin unit, the bid evaluation report unit is connected with the bid evaluation expert information unit, and the enterprise ranking unit is connected with the bid evaluation expert unit.
7. The subway project rating and scale management system as claimed in claim 1, wherein said identification module processes the steps of:
(1-1) converting the bidding document into an image through a camera, correcting the image and acquiring a text line in the image;
(1-2) checking a semantic recognition result of the text line to be recognized;
(1-3) constructing a neural network model, performing convolution on the text lines, dividing the text lines into a training set and a verification set, and calculating similarity data of the text lines corresponding to the semantic recognition results to be selected;
and (1-4) determining the final semantic recognition result of the text line from each semantic recognition result to be selected according to the similarity data of the semantic recognition results.
8. The subway engineering rating scale management system as claimed in claim 7, wherein in step (1-2), the text line and the semantic recognition result to be selected are participated, and the participated words are converted into a first word vector, and the semantic recognition result to be selected is converted into a second word vector; and calculating the similarity of the first word vector and the second word vector through cosine similarity.
9. The method according to claim 8, wherein the cosine similarity is calculated by the following formula:
Figure DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 51485DEST_PATH_IMAGE002
the first-time vector is represented by a vector,
Figure 847403DEST_PATH_IMAGE003
the vector of the second time is represented,
Figure 866174DEST_PATH_IMAGE004
representing a vector
Figure 137756DEST_PATH_IMAGE002
And vector
Figure 900175DEST_PATH_IMAGE003
The product of (a);
Figure 816179DEST_PATH_IMAGE005
and
Figure 740272DEST_PATH_IMAGE006
respectively represent vectors
Figure 499150DEST_PATH_IMAGE002
Sum vector
Figure 799681DEST_PATH_IMAGE003
The die of (1).
CN202110485663.7A 2021-04-30 2021-04-30 Subway project evaluation management system Pending CN113156864A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110485663.7A CN113156864A (en) 2021-04-30 2021-04-30 Subway project evaluation management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110485663.7A CN113156864A (en) 2021-04-30 2021-04-30 Subway project evaluation management system

Publications (1)

Publication Number Publication Date
CN113156864A true CN113156864A (en) 2021-07-23

Family

ID=76873164

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110485663.7A Pending CN113156864A (en) 2021-04-30 2021-04-30 Subway project evaluation management system

Country Status (1)

Country Link
CN (1) CN113156864A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106886862A (en) * 2017-04-15 2017-06-23 湖南新邦软件股份有限公司 One kind bid and purchase management system and method
CN111491135A (en) * 2020-04-16 2020-08-04 广东电网有限责任公司电力调度控制中心 Bidding evaluation monitoring system and bidding evaluation monitoring method
CN111932199A (en) * 2020-07-24 2020-11-13 广州云硕科技发展有限公司 Intelligent bid evaluation decision-making method and system
CN112434970A (en) * 2020-12-12 2021-03-02 广东电力信息科技有限公司 Qualification data verification method and device based on intelligent data acquisition
CN112488507A (en) * 2020-11-30 2021-03-12 广东电网有限责任公司 Expert classification portrait method and device based on clustering and storage medium
CN112632228A (en) * 2020-12-30 2021-04-09 深圳供电局有限公司 Text mining-based auxiliary bid evaluation method and system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106886862A (en) * 2017-04-15 2017-06-23 湖南新邦软件股份有限公司 One kind bid and purchase management system and method
CN111491135A (en) * 2020-04-16 2020-08-04 广东电网有限责任公司电力调度控制中心 Bidding evaluation monitoring system and bidding evaluation monitoring method
CN111932199A (en) * 2020-07-24 2020-11-13 广州云硕科技发展有限公司 Intelligent bid evaluation decision-making method and system
CN112488507A (en) * 2020-11-30 2021-03-12 广东电网有限责任公司 Expert classification portrait method and device based on clustering and storage medium
CN112434970A (en) * 2020-12-12 2021-03-02 广东电力信息科技有限公司 Qualification data verification method and device based on intelligent data acquisition
CN112632228A (en) * 2020-12-30 2021-04-09 深圳供电局有限公司 Text mining-based auxiliary bid evaluation method and system

Similar Documents

Publication Publication Date Title
CN110597964B (en) Double-recording quality inspection semantic analysis method and device and double-recording quality inspection system
Files et al. Lenders’ response to peer and customer restatements
CN112017040B (en) Credit scoring model training method, scoring system, equipment and medium
CN110750978A (en) Emotional tendency analysis method and device, electronic equipment and storage medium
CN113283795B (en) Data processing method and device based on two-classification model, medium and equipment
CN111144087A (en) Enterprise legal flow assistant decision-making system and method based on artificial intelligence
CN114819618A (en) Construction method of enterprise portrait model for assisting government investment decision
EP4044097A1 (en) System and method for determining and managing environmental, social, and governance (esg) perception of entities and industries through use of survey and media data
KR20210029326A (en) Apparatus and method for diagnosing soundness of company using unstructured financial information
CN112434862B (en) Method and device for predicting financial dilemma of marketing enterprises
CN110704803A (en) Target object evaluation value calculation method and device, storage medium and electronic device
CN116151840B (en) User service data intelligent management system and method based on big data
CN117114705A (en) Continuous learning-based e-commerce fraud identification method and system
CN114969498A (en) Method and device for recommending industrial faucet information
CN113156864A (en) Subway project evaluation management system
Hardeck et al. The impact of tax avoidance and environmental performance on tax disclosure in CSR reports
Fanani et al. The Effect of Managerial Ability and Tone of Earnings Announcements towards Market Reactions
CN117077682A (en) Document analysis method and system based on semantic recognition
CN115719058A (en) Content analysis method, electronic equipment and storage medium
CN115186657A (en) Error sensitive information detection method, device, computer equipment and storage medium
CN114741501A (en) Public opinion early warning method and device, readable storage medium and electronic equipment
Lee et al. Novel methods for resolving false positives during the detection of fraudulent activities on stock market financial discussion boards
CN112949963A (en) Employee service quality evaluation method and device, storage medium and intelligent equipment
Fadhilah et al. Gender Analysis of Individual Taxpayer Compliance: Impact of Tax Audit, Tax Amnesty, and E-Filling Implementation
Mamonov et al. An exploratory analysis of title II crowdfunding success

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20210723

RJ01 Rejection of invention patent application after publication