CN112990845A - Intelligent acquisition method for mapping market project - Google Patents
Intelligent acquisition method for mapping market project Download PDFInfo
- Publication number
- CN112990845A CN112990845A CN202110006800.4A CN202110006800A CN112990845A CN 112990845 A CN112990845 A CN 112990845A CN 202110006800 A CN202110006800 A CN 202110006800A CN 112990845 A CN112990845 A CN 112990845A
- Authority
- CN
- China
- Prior art keywords
- bid
- winning
- item
- data set
- project
- 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
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012216 screening Methods 0.000 claims abstract description 85
- 238000012549 training Methods 0.000 claims description 32
- 238000012360 testing method Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an intelligent acquisition method for mapping market projects. The intelligent acquisition method of the mapping market project comprises the following steps: receiving a data set of winning bid items; extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, amount and time attributes; and screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model. The technical problems that time and labor are wasted and data timeliness cannot be guaranteed due to the fact that the bidding project is manually screened out in the surveying and mapping are solved.
Description
Technical Field
The application relates to the field of surveying and mapping project data processing, in particular to an intelligent acquisition method for surveying and mapping market projects.
Background
The deep development of economic globalization and social informatization promotes the high-speed development of mapping equipment and mapping information technology, attracts a large number of technicians and enterprises to join in the mapping geographic information industry, and the rapid increase of the industry scale brings prosperous vitality for the development of the mapping geographic information industry and brings brand-new challenges for the management of the mapping geographic information department. Meanwhile, with the rapid development of modern technologies such as big data, artificial intelligence, cloud computing and the like, in recent years, people can obtain data from multiple parties in real time and safely, and how to effectively utilize big data resources and perform efficient supervision is a key problem to be solved by administrative departments in various regions urgently.
The surveying and mapping geographic information project is used as an important hand grip for surveying and mapping activity management, and has important significance for surveying and mapping qualification audit or surveying and mapping result quality supervision and inspection. Only by accurately mastering the dynamics of a surveying and mapping market, the cooperative supervision pattern of market autonomy, government supervision and social supervision which are mutually supported can be effectively formed, so that fairness, efficiency and vitality are managed, the competitive strength and market efficiency of market main bodies are promoted to be improved, and the sustainable and healthy development of the economy and the society is promoted.
The bidding and bidding are taken as an important ring for mapping the market behavior, the basic conditions of market bidding and government purchasing projects can be fully reflected, and therefore the bidding and bidding information can be mastered in time, so that the project source management and control effect can be effectively achieved. Because the bidding project is complicated, the supervision can be carried out more pertinently only by effectively screening the information and removing the projects which are irrelevant to mapping, have smaller scale, appear the condition of the drift and the like. However, by 12 months in 2020, statistics shows that nearly 200 ten thousand pieces of bidding project information are disclosed only in Jiangsu province in the current year, wherein nearly 10000 pieces of bidding project information related to mapping are time-consuming and labor-consuming if only manual screening is relied on, and timeliness of data cannot be guaranteed.
Aiming at the problems that time and labor are wasted and data timeliness cannot be guaranteed due to manual screening of a mapping bidding project in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The application mainly aims to provide an intelligent acquisition method for surveying and mapping market projects, and aims to solve the problems that time and labor are wasted when a bidding project is manually screened out, and data timeliness cannot be guaranteed.
In order to achieve the above object, according to one aspect of the present application, an intelligent acquisition method for mapping market items is provided.
The mapping market project intelligent acquisition method comprises the following steps: receiving a data set of winning bid items; extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, amount and time attributes; and screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model.
Further, receiving the data set of winning bid items comprises: and acquiring a data set of the bid-winning project from the third-party bid-bidding information publicizing platform by adopting a data interface.
Further, screening a target item set from the data set according to the first characteristic attribute through the trained item screening model includes: inputting the characteristic attributes into the project screening model; the item screening model judges whether the corresponding first bid-winning item is effective or not according to the first characteristic attribute; if the first winning bid item is valid, the first winning bid item is screened to the target item set.
Further, after the trained item screening model screens out the target item set from the data set according to the first characteristic attribute, the method further includes: and pushing the target project set to a supervision end through a short message or a data interface.
Further, the training of the project screening model comprises: receiving a sample data set of the bid winning item; extracting a second characteristic attribute from each bid-winning item in the sample data set, wherein the second characteristic attribute at least comprises bid-winning contents, units, money and time attributes; text truncation, filling and encoding operations are performed on the second characteristic attribute to obtain a vectorized mapping dictionary file; training, testing and verifying operations are performed according to the sample data set to obtain a weight and a deviation; and obtaining a project screening model based on the mapping dictionary file, the weight and the deviation.
In order to achieve the above object, according to another aspect of the present application, an intelligent acquisition device for mapping market items is provided.
The intelligent acquisition device for mapping market projects comprises: the receiving module is used for receiving a data set of the bid winning item; the extraction module is used for extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning content, units, amount and time attributes; and the screening module is used for screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model.
Further, after the trained item screening model screens out the target item set from the data set according to the first characteristic attribute, the method further includes: and pushing the target project set to a supervision end through a short message or a data interface.
Further, the training of the project screening model comprises: receiving a sample data set of the bid winning item; extracting a second characteristic attribute from each bid-winning item in the sample data set, wherein the second characteristic attribute at least comprises bid-winning contents, units, money and time attributes; text truncation, filling and encoding operations are performed on the second characteristic attribute to obtain a vectorized mapping dictionary file; training, testing and verifying operations are performed according to the sample data set to obtain a weight and a deviation; and obtaining a project screening model based on the mapping dictionary file, the weight and the deviation.
In order to achieve the above object, according to another aspect of the present application, there is provided a storage medium.
The storage medium is used for storing the mapping market project intelligent acquisition method.
To achieve the above object, according to another aspect of the present application, there is provided a server.
A server according to the present application, comprising: a memory and a processor for executing the mapping market project intelligent acquisition method stored in the memory.
In the embodiment of the application, a characteristic attribute extraction and model prediction mode is adopted, and a data set of a bid-winning project is received; extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, amount and time attributes; screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model; the purpose that the characteristic attribute is extracted and matched with the model prediction target item set to replace manual screening is achieved, time is saved, labor cost is reduced, the technical effect of data timeliness can be guaranteed, and the technical problems that time and labor are wasted and data timeliness cannot be guaranteed due to the fact that the bidding items are manually screened in surveying and mapping are solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic flow chart diagram of an intelligent acquisition method for mapping market projects according to an embodiment of the application;
FIG. 2 is a schematic structural diagram of an intelligent acquisition device for mapping market items according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a storage medium according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the invention and its embodiments and are not intended to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meanings of these terms in the present invention can be understood by those skilled in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meanings of the above terms in the present invention can be understood by those of ordinary skill in the art according to specific situations.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present invention, there is provided an intelligent acquisition method for mapping market projects, as shown in fig. 1, the method includes the following steps S101 to S103:
step S101, receiving a data set of a bid-winning project;
according to the embodiment of the present invention, preferably, the receiving the data set of the winning bid item includes:
and acquiring a data set of the bid-winning project from the third-party bid-bidding information publicizing platform by adopting a data interface.
In this embodiment, the server may access the third-party bid and bid information publishing platform through the data interface to establish communication, and thus, the server may actively or passively obtain a data set formed by all bid-winning items on the platform. Preferably, the server periodically obtains the data set formed by all winning bid items in the time period.
Step S102, extracting a first characteristic attribute from each bid-winning item in a data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, money and time attributes;
in the embodiment, each bid-winning item contains corresponding information, the content in the bid-winning item can be identified by combining a character identification technology and semantic identification, the content of each bid-winning item is determined according to an identification result, and the identified bid-winning content, unit, amount and time attributes are used as first characteristic attributes corresponding to a certain bid-winning item; and input parameter guarantee is provided for the screening of the bid-winning items.
And S103, screening a target item set from the data set according to the first characteristic attribute through the trained item screening model.
According to the embodiment of the present invention, preferably, the screening, by the trained item screening model, the target item set from the data set according to the first feature attribute includes:
inputting the characteristic attributes into the project screening model;
the item screening model judges whether the corresponding first bid-winning item is effective or not according to the first characteristic attribute;
if the first winning bid item is valid, the first winning bid item is screened to the target item set.
In this embodiment, the trained item screening model, in combination with the first characteristic attribute, has an effect of determining whether a certain winning bid item (i.e., a first target item) meets a standard; specifically, the item screening model can judge whether the bid-winning content is a flow mark or not by combining the bid-winning content attribute in the first characteristic attribute, so that the flow mark items can be screened out; the item screening model can judge whether the bid-winning units are related to surveying and mapping by combining the attributes of the bid-winning units in the first characteristic attributes, so that the initially screened bid-winning items can be further screened; the item screening model can judge whether the bid amount is too small by combining the bid amount attribute in the first characteristic attribute, so that the small-scale bid items can be screened; the item screening model can judge whether the winning bid time is overdue by combining the winning bid time attribute in the first characteristic attribute, so that winning bid items with the overdue period can be screened out. And screening each bid-winning item to a target item set through all the judgment.
Thus, multi-dimensional screening of the bid-winning items is realized, the left bid-winning items in the target item set are more accurate and more meet the requirements, and the method can be directly applied to supervision; the purpose that the characteristic attribute extraction is matched with the model to predict the target item set to replace manual screening is achieved, so that the technical effects of saving time, reducing labor cost and guaranteeing data timeliness are achieved.
From the above description, it can be seen that the present invention achieves the following technical effects:
in the embodiment of the application, a characteristic attribute extraction and model prediction mode is adopted, and a data set of a bid-winning project is received; extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, amount and time attributes; screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model; the purpose that the characteristic attribute is extracted and matched with the model prediction target item set to replace manual screening is achieved, time is saved, labor cost is reduced, the technical effect of data timeliness can be guaranteed, and the technical problems that time and labor are wasted and data timeliness cannot be guaranteed due to the fact that the bidding items are manually screened in surveying and mapping are solved.
According to the embodiment of the present invention, after the trained item screening model screens out the target item set from the data set according to the first feature attribute, the method further includes:
and pushing the target project set to a supervision end through a short message or a data interface.
After all the bid-winning items are judged, the target item set is pushed to a mobile phone or a computer of a supervisor through a short message or a data interface, so that the supervisor can carry out efficient supervision.
According to the embodiment of the present invention, preferably, the training of the item screening model includes:
receiving a sample data set of the bid winning item;
in another preferred embodiment, the training of the project screening model comprises:
and preprocessing the sample data set, and extracting attributes such as bid content, bid unit, bid amount and the like of each item text instance.
And (4) according to a rough set theory, performing attribute reduction by using the conditional information entropy, and calculating and screening a decision attribute (D).
And (4) performing text training on the sample data set with the reduced indexes by using a fastText frame as a text classification frame to obtain project screening model parameters.
In this embodiment, the server may access the third-party bid and bid information publishing platform through the data interface to establish communication, and thus, the server may actively or passively obtain a sample data set formed by all bid-winning items on the platform. Preferably, the server passively acquires a sample data set formed by massive bid-winning items.
Extracting a second characteristic attribute from each bid-winning item in the sample data set, wherein the second characteristic attribute at least comprises bid-winning contents, units, money and time attributes;
and preprocessing the sample data set, and extracting attributes such as bid content, bid-winning units, bid-winning amount, bid-winning time and the like of each item text instance. Training is performed based on these attributes.
Text truncation, filling and encoding operations are performed on the second characteristic attribute to obtain a vectorized mapping dictionary file;
specifically, text truncation and filling are performed on sample data, preprocessed data are read in, each record is truncated into a data (D) part and a label (L) part to form a data set D and a label set L, and the length of data required to be input in model training is fixed for the data set D. Therefore, the data with the length exceeding the specified limit is directly cut into a fixed length; and filling null values for data with insufficient length. After the steps of label extraction, text truncation and filling, the preprocessed data are converted into a data set D with a fixed length of a label set L.
And coding the words in all the texts, and storing the corresponding mapping relation as a dictionary file. The dictionary sets an upper data limit and words outside the dictionary will be assigned null values. After this process, the fixed length text is converted into a numerical vector for subsequent calculation.
For the dictionary file formed in the mapping process of establishing word encoding-text vectorization, file storage is needed to facilitate subsequent calling.
Training, testing and verifying operations are performed according to the sample data set to obtain a weight and a deviation; and obtaining a project screening model based on the mapping dictionary file, the weight and the deviation.
Specifically, the data set is divided into a training set, a test set and a verification set according to a certain proportion. The training set is used for training network parameters, the testing set is used for testing training results, and the verification set is used for determining auxiliary parameters. After this process, the data set is divided into three parts for subsequent process invocation, and iterative training of the model begins.
Training the sample, calculating the deviation between the predicted value and the actual value, adjusting the weight of the network, saving the weight and the bias corresponding to the current network after the model iterates enough training turns according to the process, and exporting the trained model and a mapping dictionary for text vectorization for item screening and calling.
In a preferred embodiment, the input decision table DT ═ (U, C ═ D), where U is the domain of discourse, and C and D are the conditional and decision attribute sets, respectively. A relative reduction R of the decision table is output. The main steps are 1) solving the information entropy H (D) of the decision attribute D. 2) And calculating the mutual information I (C, D) of all the attribute sets C to the decision attribute set D in the decision table. 3) And solving the core attribute core. First, initialize kernel
For a ∈ C, f (x, D) ≠ f (y, D), and f (x, C-a) ≠ f (y, C-a), and a is the core attribute. 4) Let R be core, calculate the mutual information I (R, D) of the core attribute R pair decision attribute set D. 5) For a belongs to C-R, the mutual information quantity I (a, D) of the decision attribute set D is calculated, and the attribute which enables the mutual information quantity to be maximum, namely the attribute is the important attribute, is found out. Has R ═ R ^ a. 6) The mutual information amount I (R, D) of the pair of decision attribute sets D by the attribute set R at this time is calculated. When the information amount of the attribute set R is equal to that of all the attribute sets C, the algorithm is terminated; otherwise, go to step 5).
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided an apparatus for implementing the above intelligent acquisition method for mapping market items, as shown in fig. 2, the apparatus includes:
a receiving module 10, configured to receive a data set of bid-winning items;
according to the embodiment of the present invention, preferably, the receiving the data set of the winning bid item includes:
and acquiring a data set of the bid-winning project from the third-party bid-bidding information publicizing platform by adopting a data interface.
In this embodiment, the server may access the third-party bid and bid information publishing platform through the data interface to establish communication, and thus, the server may actively or passively obtain a data set formed by all bid-winning items on the platform. Preferably, the server periodically obtains the data set formed by all winning bid items in the time period.
An extracting module 20, configured to extract a first characteristic attribute from each bid-winning item in the data set, where the first characteristic attribute at least includes bid-winning content, unit, amount, and time attribute;
in the embodiment, each bid-winning item contains corresponding information, the content in the bid-winning item can be identified by combining a character identification technology and semantic identification, the content of each bid-winning item is determined according to an identification result, and the identified bid-winning content, unit, amount and time attributes are used as first characteristic attributes corresponding to a certain bid-winning item; and input parameter guarantee is provided for the screening of the bid-winning items.
And the screening module 30 is configured to screen out a target item set from the data set according to the first characteristic attribute through the trained item screening model.
According to the embodiment of the present invention, preferably, the screening, by the trained item screening model, the target item set from the data set according to the first feature attribute includes:
inputting the characteristic attributes into the project screening model;
the item screening model judges whether the corresponding first bid-winning item is effective or not according to the first characteristic attribute;
if the first winning bid item is valid, the first winning bid item is screened to the target item set.
In this embodiment, the trained item screening model, in combination with the first characteristic attribute, has an effect of determining whether a certain winning bid item (i.e., a first target item) meets a standard; specifically, the item screening model can judge whether the bid-winning content is a flow mark or not by combining the bid-winning content attribute in the first characteristic attribute, so that the flow mark items can be screened out; the item screening model can judge whether the bid-winning units are related to surveying and mapping by combining the attributes of the bid-winning units in the first characteristic attributes, so that the initially screened bid-winning items can be further screened; the item screening model can judge whether the bid amount is too small by combining the bid amount attribute in the first characteristic attribute, so that the small-scale bid items can be screened; the item screening model can judge whether the winning bid time is overdue by combining the winning bid time attribute in the first characteristic attribute, so that winning bid items with the overdue period can be screened out. And screening each bid-winning item to a target item set through all the judgment.
Thus, multi-dimensional screening of the bid-winning items is realized, the left bid-winning items in the target item set are more accurate and more meet the requirements, and the method can be directly applied to supervision; the purpose that the characteristic attribute extraction is matched with the model to predict the target item set to replace manual screening is achieved, so that the technical effects of saving time, reducing labor cost and guaranteeing data timeliness are achieved.
From the above description, it can be seen that the present invention achieves the following technical effects:
in the embodiment of the application, a characteristic attribute extraction and model prediction mode is adopted, and a data set of a bid-winning project is received; extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, amount and time attributes; screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model; the purpose that the characteristic attribute is extracted and matched with the model prediction target item set to replace manual screening is achieved, time is saved, labor cost is reduced, the technical effect of data timeliness can be guaranteed, and the technical problems that time and labor are wasted and data timeliness cannot be guaranteed due to the fact that the bidding items are manually screened in surveying and mapping are solved.
According to the embodiment of the present invention, after the trained item screening model screens out the target item set from the data set according to the first feature attribute, the method further includes:
and pushing the target project set to a supervision end through a short message or a data interface.
After all the bid-winning items are judged, the target item set is pushed to a mobile phone or a computer of a supervisor through a short message or a data interface, so that the supervisor can carry out efficient supervision.
According to the embodiment of the present invention, preferably, the training of the item screening model includes:
receiving a sample data set of the bid winning item;
in this embodiment, the server may access the third-party bid and bid information publishing platform through the data interface to establish communication, and thus, the server may actively or passively obtain a sample data set formed by all bid-winning items on the platform. Preferably, the server passively acquires a sample data set formed by massive bid-winning items.
Extracting a second characteristic attribute from each bid-winning item in the sample data set, wherein the second characteristic attribute at least comprises bid-winning contents, units, money and time attributes;
and preprocessing the sample data set, and extracting attributes such as bid content, bid-winning units, bid-winning amount, bid-winning time and the like of each item text instance. Training is performed based on these attributes.
Text truncation, filling and encoding operations are performed on the second characteristic attribute to obtain a vectorized mapping dictionary file;
specifically, text truncation and filling are performed on sample data, preprocessed data are read in, each record is truncated into a data (D) part and a label (L) part to form a data set D and a label set L, and the length of data required to be input in model training is fixed for the data set D. Therefore, the data with the length exceeding the specified limit is directly cut into a fixed length; and filling null values for data with insufficient length. After the steps of label extraction, text truncation and filling, the preprocessed data are converted into a data set D with a fixed length of a label set L
And coding the words in all the texts, and storing the corresponding mapping relation as a dictionary file. The dictionary sets an upper data limit and words outside the dictionary will be assigned null values. After this process, the fixed length text is converted into a numerical vector for subsequent calculation.
For the dictionary file formed in the mapping process of establishing word encoding-text vectorization, file storage is needed to facilitate subsequent calling.
Training, testing and verifying operations are performed according to the sample data set to obtain a weight and a deviation; and obtaining a project screening model based on the mapping dictionary file, the weight and the deviation.
Specifically, the data set is divided into a training set, a test set and a verification set according to a certain proportion. The training set is used for training network parameters, the testing set is used for testing training results, and the verification set is used for determining auxiliary parameters. After this process, the data set is divided into three parts for subsequent process invocation, and iterative training of the model begins.
Training the sample, calculating the deviation between the predicted value and the actual value, adjusting the weight of the network, saving the weight and the bias corresponding to the current network after the model iterates enough training turns according to the process, and exporting the trained model and a mapping dictionary for text vectorization for item screening and calling.
According to an embodiment of the present invention, as shown in fig. 3, there is further provided a storage medium for storing the above intelligent acquisition method for mapping market items; the same technical effect of the intelligent acquisition method of the mapping market project can be achieved.
According to an embodiment of the present invention, as shown in fig. 4, there is also provided a server; the server includes: a processor 200 and a memory 100, wherein the processor 200 is used for executing the mapping market project intelligent acquisition method stored in the memory 100; the same technical effect of the intelligent acquisition method of the mapping market project can be achieved.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An intelligent acquisition method for mapping market projects is characterized by comprising the following steps:
receiving a data set of winning bid items;
extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning contents, units, amount and time attributes;
and screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model.
2. The intelligent mapping market project acquisition method of claim 1, wherein receiving a dataset of winning bid projects comprises:
and acquiring a data set of the bid-winning project from the third-party bid-bidding information publicizing platform by adopting a data interface.
3. The intelligent mapping market project acquisition method of claim 1, wherein screening out a set of target projects from a data set according to the first feature attribute through the trained project screening model comprises:
inputting the characteristic attributes into the project screening model;
the item screening model judges whether the corresponding first bid-winning item is effective or not according to the first characteristic attribute;
if the first winning bid item is valid, the first winning bid item is screened to the target item set.
4. The intelligent mapping market project acquisition method according to claim 1, wherein after the trained project screening model screens out the target project set from the data set according to the first characteristic attribute, the method further comprises:
and pushing the target project set to a supervision end through a short message or a data interface.
5. The intelligent acquisition method for mapping market projects according to claim 1, wherein the training of the project screening model comprises:
receiving a sample data set of the bid winning item;
extracting a second characteristic attribute from each bid-winning item in the sample data set, wherein the second characteristic attribute at least comprises bid-winning contents, units, money and time attributes;
text truncation, filling and encoding operations are performed on the second characteristic attribute to obtain a vectorized mapping dictionary file;
training, testing and verifying operations are performed according to the sample data set to obtain a weight and a deviation;
and obtaining a project screening model based on the mapping dictionary file, the weight and the deviation.
6. An intelligent acquisition device for mapping market projects, comprising:
the receiving module is used for receiving a data set of the bid winning item;
the extraction module is used for extracting a first characteristic attribute from each bid-winning item in the data set, wherein the first characteristic attribute at least comprises bid-winning content, units, amount and time attributes;
and the screening module is used for screening out a target item set from the data set according to the first characteristic attribute through the trained item screening model.
7. The intelligent mapping market project acquisition device of claim 1, further comprising, after the trained project screening model screens out the target project set from the data set according to the first characteristic attribute:
and pushing the target project set to a supervision end through a short message or a data interface.
8. The intelligent acquisition device for mapping market items according to claim 1, wherein the training of the item screening model comprises:
receiving a sample data set of the bid winning item;
extracting a second characteristic attribute from each bid-winning item in the sample data set, wherein the second characteristic attribute at least comprises bid-winning contents, units, money and time attributes;
text truncation, filling and encoding operations are performed on the second characteristic attribute to obtain a vectorized mapping dictionary file;
training, testing and verifying operations are performed according to the sample data set to obtain a weight and a deviation;
and obtaining a project screening model based on the mapping dictionary file, the weight and the deviation.
9. A storage medium for storing the mapping market project intelligent acquisition method of any one of claims 1 to 5.
10. A server, comprising: memory and processor, characterized in that the processor is configured to execute the mapping market project intelligent acquisition method of any one of claims 1 to 5 stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110006800.4A CN112990845A (en) | 2021-01-04 | 2021-01-04 | Intelligent acquisition method for mapping market project |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110006800.4A CN112990845A (en) | 2021-01-04 | 2021-01-04 | Intelligent acquisition method for mapping market project |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112990845A true CN112990845A (en) | 2021-06-18 |
Family
ID=76345242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110006800.4A Pending CN112990845A (en) | 2021-01-04 | 2021-01-04 | Intelligent acquisition method for mapping market project |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990845A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388595A (en) * | 2018-01-31 | 2018-08-10 | 合肥和钧正策信息技术有限公司 | Enterprise bidding trade-off evaluation system based on big data analysis |
| CN109408825A (en) * | 2018-11-06 | 2019-03-01 | 杭州费尔斯通科技有限公司 | A kind of acceptance of the bid data extraction method based on name Entity recognition |
| CN109753660A (en) * | 2019-01-07 | 2019-05-14 | 福州大学 | A kind of acceptance of the bid webpage name entity abstracting method based on LSTM |
| CN110009242A (en) * | 2019-04-12 | 2019-07-12 | 网易（杭州）网络有限公司 | Tender Evaluation Method neural network based and device, storage medium |
| CN111047268A (en) * | 2018-10-11 | 2020-04-21 | 上海汽车集团股份有限公司 | Bidding method and device |
| CN111275374A (en) * | 2019-12-09 | 2020-06-12 | 佛山欧神诺云商科技有限公司 | Optimal carrier screening method, device and medium based on logistics bidding data |
| CN111507760A (en) * | 2019-03-21 | 2020-08-07 | 广州翔实工程咨询有限公司 | Method and system for screening reasonableness of bidding documents |
| CN111985752A (en) * | 2019-05-23 | 2020-11-24 | 北京京供民科技开发有限公司 | Bid information evaluation method and device |
-
2021
- 2021-01-04 CN CN202110006800.4A patent/CN112990845A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388595A (en) * | 2018-01-31 | 2018-08-10 | 合肥和钧正策信息技术有限公司 | Enterprise bidding trade-off evaluation system based on big data analysis |
| CN111047268A (en) * | 2018-10-11 | 2020-04-21 | 上海汽车集团股份有限公司 | Bidding method and device |
| CN109408825A (en) * | 2018-11-06 | 2019-03-01 | 杭州费尔斯通科技有限公司 | A kind of acceptance of the bid data extraction method based on name Entity recognition |
| CN109753660A (en) * | 2019-01-07 | 2019-05-14 | 福州大学 | A kind of acceptance of the bid webpage name entity abstracting method based on LSTM |
| CN111507760A (en) * | 2019-03-21 | 2020-08-07 | 广州翔实工程咨询有限公司 | Method and system for screening reasonableness of bidding documents |
| CN110009242A (en) * | 2019-04-12 | 2019-07-12 | 网易（杭州）网络有限公司 | Tender Evaluation Method neural network based and device, storage medium |
| CN111985752A (en) * | 2019-05-23 | 2020-11-24 | 北京京供民科技开发有限公司 | Bid information evaluation method and device |
| CN111275374A (en) * | 2019-12-09 | 2020-06-12 | 佛山欧神诺云商科技有限公司 | Optimal carrier screening method, device and medium based on logistics bidding data |
Non-Patent Citations (3)
| Title |
|---|
| MUNER, WFS (MUNER, WAN FAREZ SAINI): "A New Model for Multicriteria Risk-Based Tender Evaluation", ADVANCED SCIENCE LETTERS * |
| 卢睿: "基于粒子群算法的铁路工程投标项目择优决策研究", 铁道学报 * |
| 徐怡、余浩、刘刚、倪治伟: "基于粗糙集的影响大学生心理健康的研究", 《计算机技术与发展》, pages 1 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tsui et al. | Knowledge-based extraction of intellectual capital-related information from unstructured data | |
| Athawale et al. | Decision making for facility location selection using PROMETHEE II method | |
| CN110569322A (en) | Address information analysis method, device and system and data acquisition method | |
| CN111144723A (en) | Method and system for recommending people's job matching and storage medium | |
| CN112633962B (en) | Service recommendation method and device, computer equipment and storage medium | |
| CN110598070B (en) | Application type identification method and device, server and storage medium | |
| CN103123633A (en) | Generation method of evaluation parameters and information searching method based on evaluation parameters | |
| CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
| CN111105209A (en) | Job resume matching method and device suitable for post matching recommendation system | |
| CN111352962A (en) | Client portrait construction method and device | |
| CN110532301B (en) | Audit method, system and readable storage medium | |
| CN105225135A (en) | Potentiality customer recognition method and device | |
| CN110766438A (en) | Method for analyzing user behaviors of power grid users through artificial intelligence | |
| CN115423578B (en) | Bid bidding method and system based on micro-service containerized cloud platform | |
| CN114638498A (en) | ESG evaluation method, ESG evaluation system, electronic equipment and storage equipment | |
| Ha et al. | Job forecasting based on the patent information: a word embedding-based approach | |
| CN114218291A (en) | Portrait generation method, apparatus, device and storage medium based on target object | |
| CN111882224A (en) | Method and device for classifying consumption scenes | |
| CN116522131A (en) | Object representation method, device, electronic equipment and computer readable storage medium | |
| CN117522256A (en) | Purchasing screening method, system, storage medium and terminal based on supplier portrait | |
| CN112990845A (en) | Intelligent acquisition method for mapping market project | |
| CN115687788A (en) | Intelligent business opportunity recommendation method and system | |
| CN115099680A (en) | Risk management method, device, equipment and storage medium | |
| CN114092057A (en) | Project model construction method and device, terminal equipment and storage medium | |
| CN113190666A (en) | Industrial intellectual property analysis method, system, equipment and storage medium |
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 |