CN117151767B - Engineering cost assessment method and device - Google Patents
Engineering cost assessment method and device Download PDFInfo
- Publication number
- CN117151767B CN117151767B CN202311416515.5A CN202311416515A CN117151767B CN 117151767 B CN117151767 B CN 117151767B CN 202311416515 A CN202311416515 A CN 202311416515A CN 117151767 B CN117151767 B CN 117151767B
- Authority
- CN
- China
- Prior art keywords
- data
- pricing
- information
- model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 34
- 230000006870 function Effects 0.000 claims description 30
- 230000006978 adaptation Effects 0.000 claims description 26
- 239000000463 material Substances 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000009825 accumulation Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000007667 floating Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 230000009193 crawling Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 238000013075 data extraction Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 description 21
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 3
- 238000001035 drying Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000005477 standard model Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method obtains engineering information of an engineering to be evaluated, and obtains standard price data corresponding to the engineering to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various engineering object information capable of generating cost in the engineering to be evaluated; acquiring information price data of standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data; identifying original index features of standard price data through an intelligent matching algorithm, binding the identified original index features with corresponding information price data, and determining price rules of each original index feature by utilizing a dynamic rule model; the cost required by the project to be evaluated is calculated in real time according to the pricing rules, the standard price data and the information price data, and the problems of high workload and high error rate of manually evaluating the project cost in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of engineering cost evaluation, in particular to an engineering cost evaluation method and an engineering cost evaluation device.
Background
With the continuous maturation and scale expansion of the construction industry technology, the cost required for building an engineering is also higher and higher, and the cost varies from hundreds of millions to billions. In the project setting phase, a fee assessment is required, which is accomplished across hundreds of professions, design homes, and consultation companies, in concert. Therefore, tools are needed to quickly generate pricing data with uniform standards by using one key of existing pricing data to provide scientific and objective cost assessment basis. These tools will help to evaluate project costs prior to project legislation, while assessing the rationality of project cost usage during project implementation in order to make risk countermeasures ahead of time.
The existing engineering cost evaluation adopts quite huge flow, and involves the cooperative cooperation of hundreds of professions, design houses and consultation companies. According to the characteristics of each specialty, different design houses and consultation companies are responsible for corresponding engineering pricing assessment work, and then assessment results are collected to a total design house for summarized calculation, and are usually processed by using a traditional Excel tool.
Firstly, the cost evaluation mode has the problems of high randomness, high error probability and high auditing cost. And secondly, the cost evaluation process is highly dependent on manual judgment, unified standard and accurate data support are lacked, manual summarization and calculation are required to be easy to make mistakes, and the auditing cost is high. Moreover, development tool standards in various industries are not uniform, barriers are serious, universality and compatibility cannot be achieved, and secondary editing cost is high. In addition, the price conversion accuracy of the industry is not high, the price data generated by adopting modes such as average value, index and the like is only a trend, the accuracy is very low, and the price data has no reference value to projects with strict budget control requirements basically. Finally, the calculation of different indexes is single, and the technology of dynamically adapting to the pricing of different indexes according to service scenes, parameters and rules cannot be achieved.
Disclosure of Invention
The technical problem to be solved by the invention is to solve the problems of large workload and high error rate of engineering cost assessment manually in the prior art, thereby providing an engineering cost assessment method and device.
In a first aspect, an embodiment of the present disclosure provides an engineering cost evaluation method, including:
acquiring engineering information of an engineering to be evaluated, wherein the engineering information comprises rating standards, expense standards, regional categories, pricing methods, regional standards, budget types, standard prices and pricing types;
obtaining standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information capable of generating cost in the project to be evaluated;
acquiring information price data of the standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data;
identifying original index features of the standard price data through an intelligent matching algorithm, and binding the identified original index features with corresponding information price data, wherein the original index features comprise index types, index key attributes, index upper-lower relationships, rating standards, expense taking standards, regional attributes, regional standards, personnel and material numbering, personnel and material type and information price coding;
Determining a pricing rule of each original index feature by using a dynamic rule model;
and calculating the cost required by the project to be evaluated in real time according to the pricing rules, the standard price data and the information price data.
Optionally, the appointed manner includes obtaining from the internet and obtaining from an item pricing base, where the item pricing base is configured to store standard price data, and the obtaining the standard price data corresponding to the project to be evaluated according to the appointed manner includes: determining all target pricing data contained in the project to be evaluated, wherein the target pricing data comprises various project object information capable of generating fees in the project to be evaluated, the target pricing data comprises first target pricing data and second target pricing data, the first target pricing data is stored in the project pricing base, and the second target pricing data is not stored in the project pricing base; acquiring the first target pricing data from the project pricing base; acquiring the second target pricing data from the Internet; and carrying out standardization processing on the target pricing data through a dynamic adaptation model to obtain standard pricing data.
Optionally, the method further comprises: and storing the standard price data into an item price base.
Optionally, before acquiring the engineering information of the engineering to be evaluated, the method further comprises: generating a dynamic adaptation model; a dynamic rule model is generated.
Optionally, generating the dynamic adaptation model includes: according to service information, various model data are dynamically loaded from a basic model library, professional field characteristic information is extracted through a four-tuple model, sentence processing is carried out on the characteristic information to reduce noise, key information is extracted, a data set of a model training format is formed, the data set comprises a forward data set conforming to characteristics and a reverse data set not conforming to characteristics, the service information comprises service types, index types, list types and quota types, and the sentence processing comprises word segmentation, stop word removal and word stem conversion; vectorizing input data, describing global semantic information of a text, fusing the global semantic information with semantic information of a single word/word, encoding and decoding a professional field characteristic information sequence through a model transducer to capture context information of the input professional field characteristic information sequence, carrying out nonlinear transformation ReLU and advanced feature extraction through a full-connection layer, and outputting a professional field characteristic information combination value through Cos (a, b) a|a|b|; the Softmax function is used for mapping the output of the full-connection layer to probability distribution so as to evaluate the predicted professional name matching probability, classifying, measuring the error of a matching task by adopting a cross entropy loss function, continuously optimizing and training by a deep learning optimizer, gradually reducing the loss function until model training is finished, and storing the model; for each pair of specialty names (a, b), the probability p of the model output is used to calculate the loss function:
Where N is the number of samples in the batch, yi is the sample label, pi is the probability of matching the model output.
Optionally, identifying the original index feature of the standard price data through an intelligent matching algorithm, and binding the identified original index feature and the corresponding information price data includes: entering information price data according to standard specifications, crawling information price data of each specialty and each month from an engineering cost platform or each enterprise network by utilizing a crawler technology, detecting a text area based on an OCR model, combining a text detection and identification module, converting unstructured data of PDF and picture files into structured data, and standardizing the structured data; according to the personnel machine configuration rule, based on the BERT algorithm model, the optimal matching is found by adjusting the rule and the parameter configured by the optimizing system based on the unique identification code of the object, the association relation between the pricing data personnel machine and the information price data personnel machine is established, and the full coverage and the correctness of the association relation are ensured.
Optionally, before acquiring the engineering information of the engineering to be evaluated, generating the dynamic rule model includes: acquiring the lowest index data, caching, and traversing calculation in a professional dimension parallel reverse order by utilizing a cloud computing technology and adopting a divide-and-conquer idea; each task calculates a plurality of indexes in parallel through multiple threads, each thread calculates the materials of the indexes based on a rule algorithm model, rule definition is carried out on each type of materials, and the definition comprises basic coding definition, calculation parameter values, floating proportion, associated coding and calculation sequence; defining a calculation standard of each step, and combining a plurality of rules to form pricing data of the bottom layer indexes; after each thread finishes calculation, each task is traversed and summarized upwards by reverse order until each specialty finishes the pricing data, and the same-level and same-node data accumulation is carried out according to a complete tree structure, so that new pricing data of the target engineering is formed.
In a second aspect, an embodiment of the present disclosure provides an engineering cost evaluation apparatus, including:
the project information acquisition module is used for acquiring project information of the project to be evaluated, wherein the project information comprises rating standards, expense standards, region categories, pricing methods, region standards, budget types, standard prices and pricing types;
the standard price data acquisition module is used for acquiring standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information which can generate cost in the project to be evaluated;
the information price data acquisition module is used for acquiring information price data of the standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data;
the data matching module is used for identifying original index features of the standard price data through an intelligent matching algorithm, and binding the identified original index features with corresponding information price data, wherein the original index features comprise index types, index key attributes, index upper-lower relationships, quota standards, expense standards, regional attributes, regional standards, personnel and machine numbers, personnel and machine types and information price codes;
The pricing rule determining module is used for determining the pricing rule of each original index feature by using the dynamic rule model;
and the engineering cost evaluation module is used for calculating the cost required by the engineering to be evaluated in real time according to the pricing rule, the standard price data and the information price data.
In a third aspect, the disclosed embodiments of the invention also provide a computer device comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any of the possible implementations of the first aspect.
In a fourth aspect, the disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the first aspect, or any of the possible implementation manners of the first aspect.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
And constructing a unified data standard and an evaluation specification, and converting the data of different programming software into unified and standard pricing data by using a dynamic adaptation model. And identifying and binding original index features of the pricing data through an intelligent matching algorithm, so that the price of the bottommost index can be 100% matched and replaced. The method comprises the steps of establishing a dynamic rule model, depending on the rule model, dynamically identifying each index and material calculation rule, calculating pricing data in real time, meeting business requirements of different projects, different professions, different sources and the like, realizing engineering pricing automation, calculating pricing data in real time, completing project or professional pricing data generation in second level, enabling assessment results to be more refined and personalized, and saving manual error reduction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for engineering expense assessment provided by an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating another engineering cost assessment method provided by an embodiment of the present disclosure;
FIG. 3 is a functional block diagram of an engineering cost assessment device according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a computer device according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram showing a basic model library creation process in accordance with an embodiment of the present invention;
FIG. 6 is a schematic diagram of a dynamic adaptation model training process in accordance with an embodiment of the present disclosure;
fig. 7 shows a schematic diagram of the dynamic adaptation model application process in fig. 6.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying summary.
Example 1
As shown in fig. 1, a flowchart of an engineering cost evaluation method provided by an embodiment of the present disclosure includes:
s11: engineering information of the engineering to be evaluated is obtained, wherein the engineering information comprises rating standards, fee taking standards, regional categories, pricing methods, regional standards, budget types, standard prices and pricing types.
S12: and acquiring standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information capable of generating fees in the project to be evaluated.
S13: and acquiring information price data of the standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data.
S14: and identifying original index features of standard price data through an intelligent matching algorithm, and binding the identified original index features with corresponding information price data, wherein the original index features comprise index types, index key attributes, index upper-lower relationships, quota standards, cost taking standards, regional attributes, regional standards, personnel machine numbers, personnel machine types and information price codes.
S15: and determining the pricing rule of each original index feature by using a dynamic rule model.
S16: and calculating the cost required by the project to be evaluated in real time according to the pricing rules, the standard price data and the information price data.
It can be understood that the technical scheme provided by the embodiment constructs a unified data standard and an evaluation specification, and converts the data of different programming software into unified and standard pricing data by using a dynamic adaptation model. And identifying and binding original index features of the pricing data through an intelligent matching algorithm, so that the price of the bottommost index can be 100% matched and replaced. The method comprises the steps of establishing a dynamic rule model, depending on the rule model, dynamically identifying each index and material calculation rule, calculating pricing data in real time, meeting business requirements of different projects, different professions, different sources and the like, realizing engineering pricing automation, calculating pricing data in real time, completing project or professional pricing data generation in second level, enabling assessment results to be more refined and personalized, and saving manual error reduction.
Example 2
As shown in fig. 2, another method for evaluating engineering cost according to an embodiment of the present disclosure includes:
s21: a dynamic adaptation model is generated.
S22: a dynamic rule model is generated.
S23: engineering information of the engineering to be evaluated is obtained, wherein the engineering information comprises rating standards, fee taking standards, regional categories, pricing methods, regional standards, budget types, standard prices and pricing types.
S24: and acquiring standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information capable of generating fees in the project to be evaluated.
In some alternative embodiments, the specifying means includes obtaining from the internet and obtaining from a project pricing base, the project pricing base being configured to store standard pricing data, the obtaining standard pricing data corresponding to the project under evaluation in the specifying means including (not shown):
s241: determining all target pricing data contained in the project to be evaluated, wherein the target pricing data comprises various project object information capable of generating fees in the project to be evaluated, the target pricing data comprises first target pricing data and second target pricing data, the first target pricing data is stored in a project pricing base, and the second target pricing data is not stored in the project pricing base.
S242: first target pricing data is obtained from the project pricing base.
S243: second target pricing data is obtained from the internet.
S244: and carrying out standardization processing on the target pricing data through the dynamic adaptation model to obtain standard pricing data.
S25: and acquiring information price data of the standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data.
S26: and identifying original index features of standard price data through an intelligent matching algorithm, and binding the identified original index features with corresponding information price data, wherein the original index features comprise index types, index key attributes, index upper-lower relationships, quota standards, cost taking standards, regional attributes, regional standards, personnel machine numbers, personnel machine types and information price codes.
S27: and determining the pricing rule of each original index feature by using a dynamic rule model.
S28: and calculating the cost required by the project to be evaluated in real time according to the pricing rules, the standard price data and the information price data.
S29: and storing the standard price data into an item price calculating library.
In some alternative embodiments, S21 may be implemented by the following procedure (not shown in the figures):
s211: according to the service information, various model data are dynamically loaded from a basic model library, professional field characteristic information is extracted through a four-element model, sentence processing is carried out on the characteristic information to reduce noise, key information is extracted, a data set of a model training format is formed, the data set comprises a forward data set conforming to characteristics and a reverse data set not conforming to characteristics, the service information comprises service types, index types, list types and quota types, and sentence processing comprises word segmentation, stop word removal and word drying.
S212: the input data is vectorized and used for describing global semantic information of texts, the global semantic information is fused with semantic information of single words/words, a professional field characteristic information sequence is encoded and decoded through a model transducer to capture context information of the input professional field characteristic information sequence, nonlinear transformation ReLU and advanced feature extraction are carried out through a full-connection layer, and a professional field characteristic information combination value is output through Cos (a, b) |a|b|.
S213: the Softmax function is used for mapping the output of the full-connection layer to probability distribution so as to evaluate the predicted professional name matching probability, classifying, measuring the error of the matching task by adopting a cross entropy loss function, continuously optimizing and training by a deep learning optimizer, gradually reducing the loss function until model training is finished, and storing the model.
S214: for each pair of specialty names (a, b), the probability p of the model output is used to calculate the loss function:
where N is the number of samples in the batch, yi is the sample label, pi is the probability of matching the model output.
In some alternative embodiments, S26 may be implemented by the following procedure (not shown in the figures):
s261: information price data is input according to standard specifications, information price data of each specialty and each month is crawled from an engineering cost platform or each enterprise network by utilizing a crawler technology, text areas are detected based on an OCR model, and unstructured data of PDF and picture files are converted into structured data and standardized by combining with a text detection and identification module.
S262: according to the personnel machine configuration rule, based on the BERT algorithm model, the optimal matching is found by adjusting the rule and the parameter configured by the optimizing system based on the unique identification code of the object, the association relation between the pricing data personnel machine and the information price data personnel machine is established, and the full coverage and the correctness of the association relation are ensured.
Specifically, in some alternative embodiments, S22 includes (not shown in the figures):
s221: and acquiring the index data of the bottommost layer, caching, and traversing the calculation in a professional dimension parallel reverse order by utilizing a cloud computing technology and adopting a divide-and-conquer idea.
S222: each task calculates a plurality of indexes in parallel through multiple threads, each thread calculates the materials of the indexes based on a rule algorithm model, rule definition is carried out on each type of materials, and the definition comprises basic coding definition, calculation parameter values, floating proportion, associated coding and calculation sequence; defining a calculation standard of each step, and combining a plurality of rules to form pricing data of the bottom layer index.
S223: after each thread finishes calculation, each task is traversed and summarized upwards by reverse order until each specialty finishes the pricing data, and the same-level and same-node data accumulation is carried out according to a complete tree structure, so that new pricing data of the target engineering is formed.
It can be understood that the technical scheme provided by the embodiment constructs a unified data standard and an evaluation specification, and converts the data of different programming software into unified and standard pricing data by using a dynamic adaptation model. And identifying and binding original index features of the pricing data through an intelligent matching algorithm, so that the price of the bottommost index can be 100% matched and replaced. The method comprises the steps of establishing a dynamic rule model, depending on the rule model, dynamically identifying each index and material calculation rule, calculating pricing data in real time, meeting business requirements of different projects, different professions, different sources and the like, realizing engineering pricing automation, calculating pricing data in real time, completing project or professional pricing data generation in second level, enabling assessment results to be more refined and personalized, and saving manual error reduction.
Example 3
As shown in fig. 3, an embodiment of the present invention further provides another engineering cost evaluation apparatus, including:
the project information obtaining module 31 is configured to obtain project information of a project to be evaluated, where the project information includes rating criteria, fee-taking criteria, region category, fee-taking method, region criteria, budget type, standard price and fee type.
And the standard price data acquisition module 32 is used for acquiring standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information capable of generating fees in the project to be evaluated.
And an information price data acquisition module 33, configured to acquire information price data of the standard price data, where the information price data includes prices of various engineering objects in the standard price data.
The data matching module 34 is configured to identify, by using an intelligent matching algorithm, an original index feature of the standard price data, and bind the identified original index feature with corresponding information price data, where the original index feature includes an index type, an index key attribute, an index context, a rating standard, a cost standard, a regional attribute, a regional standard, a man-machine number, a man-machine type, and an information price code.
A pricing rule determination module 35 for determining a pricing rule for each of the original indicator features using a dynamic rule model.
The engineering cost assessment module 36 is configured to calculate the cost required by the engineering to be assessed in real time according to the pricing rule, the standard price data and the information price data.
In some alternative embodiments, the apparatus further comprises:
the dynamic adaptation model generation module 37 generates a dynamic adaptation model.
The dynamic rule model generation module 38 generates a dynamic rule model.
In some alternative embodiments, the apparatus further comprises:
a price repository updating module 39 for storing the standard price data into an item price repository.
In some alternative embodiments, the manner of designation includes obtaining from the Internet and from an item pricing library, and the data matching module 34 includes:
a pricing data determining sub-module 341, configured to determine all target pricing data included in the project to be evaluated, where the target pricing data includes various project object information capable of generating fees in the project to be evaluated, and the target pricing data includes first target pricing data and second target pricing data, where the first target pricing data is stored in the project pricing base, and the second target pricing data is not stored in the project pricing base.
A pricing base acquisition sub-module 342 for acquiring the first target pricing data from the item pricing base;
an internet obtaining sub-module 343, configured to obtain the second target pricing data from the internet;
And the normalization processing sub-module 344 is configured to normalize the target pricing data through the dynamic adaptation model to obtain standard pricing data.
In some alternative embodiments, the dynamic adaptation model generation module 37 includes:
the data extraction sub-module 371 is used for dynamically loading various model data from the basic model library according to service information, extracting professional field characteristic information through a four-tuple model, performing sentence processing on the characteristic information to reduce noise, extracting key information and forming a data set of a model training format, wherein the data set comprises a forward data set conforming to characteristics and a reverse data set not conforming to characteristics, the service information comprises service types, index types, list types and quota types, and the sentence processing comprises word segmentation, stop word removal and word drying.
The data processing sub-module 372 is configured to vectorize input data, describe global semantic information of text, fuse with semantic information of single word/word, encode and decode the professional field characteristic information sequence through the model transducer to capture context information of the input professional field characteristic information sequence, perform nonlinear transformation ReLU and advanced feature extraction through the full connection layer, and output the professional field characteristic information combination value through Cos (a, b) |a|b|.
The probability distribution sub-module 373 is configured to map the output of the full-connection layer to probability distribution by using the Softmax function, so as to evaluate the predicted professional name matching probability, classify the probability, measure the error of the matching task by using the cross entropy loss function, continuously optimize and train the model by using the deep learning optimizer, gradually reduce the loss function until the model training is finished, and save the model.
A loss function calculation sub-module 374 for calculating a loss function using the probability p of the model output for each pair of specialty names (a, b).
Where N is the number of samples in the batch, yi is the sample label, pi is the probability of matching the model output.
In some alternative embodiments, the data matching module 34 includes:
the OCR detection sub-module 341 is configured to enter information price data according to standard specifications, crawl information price data of each specialty and each month from an engineering cost platform or each enterprise network by using a crawler technology, detect text areas based on an OCR model, combine with a text detection and recognition module, convert unstructured data of PDF and picture files into structured data, and normalize the structured data.
The man-machine configuration sub-module 342 is configured to find an optimal match by adjusting rules and parameters configured by the optimization system based on the BERT algorithm model and relying on the unique identification code of the object according to man-machine configuration rules, establish an association relationship between the pricing data man-machine and the information price data man-machine, and ensure full coverage and correctness of the association relationship.
In some alternative embodiments, dynamic rule model generation module 38 includes:
the inverse traversal submodule 381 is used for acquiring the index data of the bottommost layer, caching the index data, and traversing calculation in a professional dimension parallel inverse sequence by utilizing a cloud computing technology and adopting a divide-and-conquer idea.
The computing sub-module 382 is configured to compute multiple indexes in parallel by multiple threads for each task, where each thread computes an algorithm model of the index based on rules for materials, and defines rules for each type of materials, and the definitions include basic code definition, computing parameter values, floating proportion, associated codes and computing sequence; defining a calculation standard of each step, and combining a plurality of rules to form pricing data of the bottom layer index.
And the data summarizing sub-module 383 is used for summarizing and calculating each task upwards through traversing in reverse order after each thread finishes calculation until each specialty finishes the pricing data, and carrying out peer-to-peer same-node data accumulation according to a complete tree structure, so that new pricing data of the target engineering is formed.
It can be understood that the technical scheme provided by the embodiment constructs a unified data standard and an evaluation specification, and converts the data of different programming software into unified and standard pricing data by using a dynamic adaptation model. And identifying and binding original index features of the pricing data through an intelligent matching algorithm, so that the price of the bottommost index can be 100% matched and replaced. The method comprises the steps of establishing a dynamic rule model, depending on the rule model, dynamically identifying each index and material calculation rule, calculating pricing data in real time, meeting business requirements of different projects, different professions, different sources and the like, realizing engineering pricing automation, calculating pricing data in real time, completing project or professional pricing data generation in second level, enabling assessment results to be more refined and personalized, and saving manual error reduction.
Example 4
Based on the same technical concept, the embodiment of the application further provides a computer device, which comprises a memory 1 and a processor 2, as shown in fig. 4, the memory 1 stores a computer program, and the processor 2 implements the engineering cost evaluation method according to any one of the above when executing the computer program.
The memory 1 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 1 may in some embodiments be an internal storage unit of the engineering cost assessment system, such as a hard disk. The memory 1 may in other embodiments also be an external storage device of the engineering cost assessment system, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like. Further, the memory 1 may also include both an internal memory unit and an external memory device of the engineering cost evaluation system. The memory 1 may be used not only for storing application software installed in the engineering cost evaluation system and various types of data, such as codes of engineering cost evaluation programs, etc., but also for temporarily storing data that has been output or is to be output.
The processor 2 may in some embodiments be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor or other data processing chip for running program code or processing data stored in the memory 1, e.g. executing engineering cost assessment programs or the like.
It can be understood that the technical scheme provided by the embodiment constructs a unified data standard and an evaluation specification, and converts the data of different programming software into unified and standard pricing data by using a dynamic adaptation model. And identifying and binding original index features of the pricing data through an intelligent matching algorithm, so that the price of the bottommost index can be 100% matched and replaced. The method comprises the steps of establishing a dynamic rule model, depending on the rule model, dynamically identifying each index and material calculation rule, calculating pricing data in real time, meeting business requirements of different projects, different professions, different sources and the like, realizing engineering pricing automation, calculating pricing data in real time, completing project or professional pricing data generation in second level, enabling assessment results to be more refined and personalized, and saving manual error reduction.
In order to facilitate the reader to understand the technical scheme of the embodiment of the invention, the technical details in the scheme are described in detail below through specific examples.
Step one: and constructing a unified data standard and an evaluation standard, and converting the data of different programming software into unified and standard pricing data by using a dynamic adaptation model optimization method.
1. And establishing an index model, a list model, a quota model, a man-machine model and a fee taking model through a dynamic rule model and an intelligent recognition algorithm according to national and industry standards and specifications. Each model is structured in a tree structure, as shown in fig. 5, forming a complete base model library.
The specific flow is as follows:
1-1, the data source is from a plurality of channels, and corresponding files are downloaded from each channel, wherein the file format is Excel or PDF files and the like.
1-2, aiming at an Excel file, according to rules configured by a system, such as R (a 1) - > R (a 2) - > R (a 3) …, the configuration and application of the rules are carried out in real time, the output R of the previous step is transmitted to the next step through multi-level rule processing, the output R is used as the input of the next step, and the final output is a standard model after the processing is finished.
2-3, aiming at the PDF file, firstly converting the PDF file into an Excel file through an OCR recognition algorithm, then configuring and applying rules in real time according to the rules configured by the system, such as R (a 1) - > R (a 2) - > R (a 3) …, and transmitting the output R of the last step to the next step through multistage rule processing, wherein the output R of the last step is used as the input of the next step, and the final output is a standard model after the processing is finished. The dynamic rule model optimizes the breadth of the adaptive data source, optimizes the business rule, and flexibly adjusts in real time according to the business scene as required, thereby meeting the business requirement of future possibility and having high expansibility.
1-4, after being processed by a dynamic rule model, storing the processed data into a basic model library to form a description model of each column data model, wherein the model is expressed in a four-element form, such as: m (req, res, aux, base), wherein req is key information to be matched, res is information of a processing result including matching key information, unique identification and the like, aux is auxiliary information which can be a plurality of, is provided in an array form, and base is information configured according to industry experience and historical recognition conditions.
2. As shown in fig. 6, the system configures rules of a plurality of source channels defined in advance, such as data format, correspondence, hierarchy, and basic features. And then inputting pricing data of various channel sources with non-uniform data formats and specifications, and analyzing and converting the submitted data into data with uniform formats by a tool according to rules of system configuration. And then based on the BERT algorithm model, identifying and matching by relying on a basic project model library through a system configuration rule, finding out optimal similarity through continuously adjusting rules and parameters of system configuration, establishing a dynamic adaptation relationship, forming a tree structure model with a structural relationship, and thus establishing a project pricing library, wherein the project pricing library contains data from different channels, and the stored data formats and specifications are consistent.
The specific flow is as follows:
2-1, data preprocessing stage: according to the service types, index types, list types, quota types and the like, various model data are dynamically loaded from a basic model library, professional field characteristic information is extracted through a quadruple model, characteristics information such as word segmentation, stop word removal, word drying and the like are carried out on the characteristic information so as to reduce noise, key information is extracted, then a data set of a model training format is formed, and the data set comprises a forward data set conforming to characteristics and a reverse data set not conforming to the characteristics.
2-2, model training phase: vectorization is carried out on the input data, global semantic information for describing the text is used, and the input data is fused with semantic information of single characters/words. The domain-specific information sequence is then encoded and decoded by a model transducer to capture contextual information entered into the domain-specific information sequence. And then, carrying out nonlinear transformation ReLU and advanced feature extraction through a full connection layer, thereby providing richer information for matching judgment, and outputting the professional field characteristic information combination value through Cos (a, b).
2-3, model output stage: the Softmax function is used to map the output of the full connection layer to a probability distribution to evaluate the predicted specialty name match probability and classify. And measuring the error of the matching task by adopting a cross entropy loss function, continuously optimizing and training by a deep learning optimizer, gradually reducing the loss function until model training is finished, and storing the model.
2-4, for each pair of specialty names (a, b), calculate a loss function using the probability p of the model output:
；
where N is the number of samples in the batch, yi is the sample label (match 1, mismatch 0), pi is the match probability of the model output.
As shown in fig. 7, the dynamic adaptation model application procedure is as follows:
3-1, firstly receiving data files from different sources, wherein the data files comprise files developed by a plurality of manufacturers in industry or custom specifications at a service side, entering an adapter through a system import function, and automatically adopting corresponding realization processing by the adapter according to file content characteristic information.
3-2, each implementation process is configured and applied in real time according to a dynamic rule strategy, such as R (a 1) - > R (a 2) - > R (a 3) …, and through multistage rule processing, each step transmits the output R of the previous step to the next step to serve as the input of the next step. In the professional type rule processing process, a model engine is called to perform professional field matching, full matching is performed firstly, if the requirements are not met, then key information matching of the professional field is performed, the first three probability values meeting the requirements are selected according to the matching results, then hierarchical judgment is performed, and the most-meeting relation binding is selected, so that the application of the model is completed.
3-3, entering rule processing through the last step of the rule chain, and then entering corresponding information into a pricing base.
Step two: and identifying and binding original index features of the pricing data through an intelligent matching algorithm, so that the price conversion of the bottommost index is 100% matched.
1. Information price data is input according to standard specifications, and is used for price conversion. Crawling information price data of each specialty and each month from an engineering cost platform or each enterprise network by utilizing a crawler technology, detecting text areas based on an OCR model, combining with a text detection and identification module, converting unstructured data of PDF and picture files into structured data, and standardizing the structured data. The processing process is similar to the 1 st point of the step one, the difference is mainly that the crawler technology is added, and meanwhile, the processing rules aiming at the information price characteristic data are different.
2. According to the personnel machine configuration rule, based on the BERT algorithm model, the optimal matching is found by continuously adjusting and optimizing the rule and the parameter of the system configuration by depending on the unique identification code of the object, the association relation between the pricing data personnel machine and the information price data personnel machine is established, more than 90% of the matching can be ensured for the first time, then the association relation is further audited, the rule and the parameter are perfected, and the full coverage and the correctness of the association relation are ensured.
Step three: and a dynamic rule model is established, pricing data calculation is performed in real time, and business requirements of different projects, different professions, different sources and the like are met.
1. And finding the lowest index data to be calculated according to the selected condition and the relation formed by the step two, and caching. Then, the cloud computing technology is utilized to traverse computing in a parallel reverse order of a professional dimension, wherein the professional dimension can be tens or hundreds, and the parallel computing task can be divided into tens or hundreds.
2. Each task calculates a plurality of indexes in parallel through multiple threads, and each thread calculates the materials of the indexes based on a rule algorithm model. Rules can be flexibly configured and generated in real time; performing rule definition on each type of material, including basic code definition, calculating parameter values, floating proportion, associated codes and calculating sequence; then defining each step of calculation standard, combining multiple rules to form a complex execution flow. And finally, calculating the result to form pricing data of the bottom layer index. Through a dynamic rule model, the method can flexibly adapt to index data of different scenes, different professions and different sources, such as a track 89 number or a national iron 30 number.
3. After each thread completes the calculation, each task is summarized and calculated upwards through reverse sequence traversal. After each specialty finishes the pricing data, the peer-to-peer same node data accumulation is carried out according to a complete tree structure, so that new pricing data of the project is formed, the algorithm is very efficient, and the summarization is completed in millisecond level.
The disclosed embodiments also provide a computer readable storage medium having a computer program stored thereon, which when executed by a processor performs the steps of the engineering cost assessment method in the method embodiments described above. Wherein the storage medium may be a volatile or nonvolatile computer readable storage medium.
The computer program product of the engineering cost assessment method provided by the embodiment of the present invention includes a computer readable storage medium storing program code, where the program code includes instructions for executing the steps of the engineering cost assessment method in the method embodiment, and the details of the method embodiment may be referred to, and are not described herein.
The disclosed embodiments also provide a computer program which, when executed by a processor, implements any of the methods of the previous embodiments. The computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.
It should be noted that in the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise indicated, the meaning of "plurality" means at least two.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (6)
1. A method of engineering expense assessment, comprising:
acquiring engineering information of an engineering to be evaluated, wherein the engineering information comprises rating standards, expense standards, regional categories, pricing methods, regional standards, budget types, standard prices and pricing types;
obtaining standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information capable of generating cost in the project to be evaluated;
acquiring information price data of the standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data;
identifying original index features of the standard price data through an intelligent matching algorithm, and binding the identified original index features with corresponding information price data, wherein the original index features comprise index types, index key attributes, index upper-lower relationships, rating standards, expense taking standards, regional attributes, regional standards, personnel and material numbering, personnel and material type and information price coding;
Determining a pricing rule of each original index feature by using a dynamic rule model;
calculating the cost required by the project to be evaluated in real time according to the pricing rules, the standard price data and the information price data;
before acquiring the engineering information of the engineering to be evaluated, the method further comprises:
generating a dynamic adaptation model;
generating a dynamic rule model;
generating the dynamic adaptation model includes:
according to service information, various model data are dynamically loaded from a basic model library, professional field characteristic information is extracted through a four-tuple model, sentence processing is carried out on the characteristic information to reduce noise, key information is extracted, a data set of a model training format is formed, the data set comprises a forward data set conforming to characteristics and a reverse data set not conforming to characteristics, the service information comprises service types, index types, list types and quota types, and the sentence processing comprises word segmentation, stop word removal and word stem conversion;
vectorizing input data, fusing global semantic information for describing texts with semantic information of single words/words, coding and decoding a professional field characteristic information sequence through model conversion to capture context information of the input professional field characteristic information sequence, carrying out nonlinear transformation ReLU and advanced feature extraction through a full-connection layer, and outputting a professional field characteristic information combination value through Cos (a, b) a b;
The Softmax function is used for mapping the output of the full-connection layer to probability distribution so as to evaluate the predicted professional name matching probability, classifying, measuring the error of a matching task by adopting a cross entropy loss function, continuously optimizing and training by a deep learning optimizer, gradually reducing the loss function until model training is finished, and storing the model;
for each pair of specialty names (a, b), the probability p of the model output is used to calculate the loss function:
where N is the number of samples in the batch, yi is the sample tag, pi is the probability of matching the model output, i ϵ [1, N]；
The appointed mode comprises the steps of obtaining from the Internet and obtaining from an item pricing base, wherein the item pricing base is used for storing standard price data, and the step of obtaining the standard price data corresponding to the project to be evaluated according to the appointed mode comprises the following steps:
determining all target pricing data contained in the project to be evaluated, wherein the target pricing data comprises various project object information capable of generating fees in the project to be evaluated, the target pricing data comprises first target pricing data and second target pricing data, the first target pricing data is stored in the project pricing base, and the second target pricing data is not stored in the project pricing base;
Acquiring the first target pricing data from the project pricing base;
acquiring the second target pricing data from the Internet;
carrying out standardization processing on the target pricing data through a dynamic adaptation model to obtain standard pricing data;
generating the dynamic rule model includes:
acquiring the lowest index data, caching, and traversing calculation in a professional dimension parallel reverse order by utilizing a cloud computing technology and adopting a divide-and-conquer idea;
each task calculates a plurality of indexes in parallel through multiple threads, each thread calculates the materials of the indexes based on a rule algorithm model, rule definition is carried out on each type of materials, and the definition comprises basic coding definition, calculation parameter values, floating proportion, associated coding and calculation sequence; defining a calculation standard of each step, and combining a plurality of rules to form pricing data of the bottom layer indexes;
after each thread finishes calculation, each task is traversed and summarized upwards by reverse order until each specialty finishes the pricing data, and the same-level and same-node data accumulation is carried out according to a complete tree structure, so that new pricing data of the target engineering is formed.
2. The engineering cost assessment method according to claim 1, further comprising:
And storing the standard price data into an item price base.
3. The engineering cost assessment method according to claim 2, wherein identifying the original index features of the standard price data by an intelligent matching algorithm, and binding the identified original index features and the corresponding information price data comprises:
entering information price data according to standard specifications, crawling information price data of each specialty and each month from an engineering cost platform or each enterprise network by utilizing a crawler technology, detecting a text area based on an OCR model, combining a text detection and identification module, converting unstructured data of PDF and picture files into structured data, and standardizing the structured data;
according to the personnel machine configuration rule, based on the BERT algorithm model, the optimal matching is found by adjusting the rule and the parameter configured by the optimizing system based on the unique identification code of the object, the association relation between the pricing data personnel machine and the information price data personnel machine is established, and the full coverage and the correctness of the association relation are ensured.
4. An engineering cost assessment apparatus, comprising:
the project information acquisition module is used for acquiring project information of the project to be evaluated, wherein the project information comprises rating standards, expense standards, region categories, pricing methods, region standards, budget types, standard prices and pricing types;
The standard price data acquisition module is used for acquiring standard price data corresponding to the project to be evaluated according to a specified mode, wherein the standard price data comprises standard forms of various project object information which can generate cost in the project to be evaluated;
the information price data acquisition module is used for acquiring information price data of the standard price data, wherein the information price data comprises prices of various engineering objects in the standard price data;
the data matching module is used for identifying original index features of the standard price data through an intelligent matching algorithm, and binding the identified original index features with corresponding information price data, wherein the original index features comprise index types, index key attributes, index upper-lower relationships, quota standards, expense standards, regional attributes, regional standards, personnel and machine numbers, personnel and machine types and information price codes;
the pricing rule determining module is used for determining the pricing rule of each original index feature by using the dynamic rule model;
the engineering cost assessment module is used for calculating the cost required by the engineering to be assessed in real time according to the pricing rule, the standard price data and the information price data;
The apparatus further comprises:
the dynamic adaptation model generation module is used for generating a dynamic adaptation model;
the dynamic rule model generation module is used for generating a dynamic rule model;
the dynamic adaptation model generation module comprises:
the data extraction sub-module is used for dynamically loading various model data from a basic model library according to service information, extracting professional field characteristic information through a four-tuple model, carrying out sentence processing on the characteristic information to reduce noise, extracting key information and forming a data set of a model training format, wherein the data set comprises a forward data set conforming to characteristics and a reverse data set not conforming to characteristics, the service information comprises service types, index types, list types and quota types, and the sentence processing comprises word segmentation, stop word removal and word stem removal;
the data processing sub-module is used for vectorizing input data, describing global semantic information of a text, fusing the global semantic information with semantic information of a single word/word, encoding and decoding a professional field characteristic information sequence through a model Transformer so as to capture context information of the input professional field characteristic information sequence, carrying out nonlinear transformation ReLU and advanced feature extraction through a full-connection layer, and outputting a professional field characteristic information combination value through Cos (a, b) a b;
The probability distribution sub-module is used for mapping the output of the full connection layer to probability distribution by the Softmax function so as to evaluate the predicted professional name matching probability, classify the probability, measure the error of the matching task by adopting the cross entropy loss function, continuously optimize and train by the deep learning optimizer, gradually reduce the loss function until the model training is finished, and store the model;
a loss function calculation sub-module for calculating a loss function using the probability p of the model output for each pair of specialty names (a, b);
where N is the number of samples in the batch, yi is the sample tag, pi is the probability of matching the model output, i ϵ [1, N]；
The specified mode comprises acquisition from the Internet and acquisition from an item pricing base, and the data matching module comprises: a pricing data determining sub-module for determining all target pricing data contained in the project to be assessed, the target pricing data including various project object information capable of generating fees in the project to be assessed, the target pricing data including first target pricing data stored in the project pricing base and second target pricing data not stored in the project pricing base; a pricing base acquisition sub-module for acquiring the first target pricing data from the project pricing base; the Internet acquisition sub-module is used for acquiring the second target pricing data from the Internet; the normalization processing sub-module is used for performing normalization processing on the target pricing data through the dynamic adaptation model to obtain standard pricing data;
The dynamic rule model generation module comprises: the inverse traversal sub-module is used for acquiring the index data of the bottommost layer, caching the index data, and traversing and calculating in a professional dimension parallel inverse sequence by utilizing a cloud computing technology and adopting a divide-and-conquer idea; the calculation sub-module is used for calculating a plurality of indexes in parallel by each task through multiple threads, calculating the algorithm model of the indexes based on rules of materials by each thread, defining rules of materials of each type, and defining a sequence comprising basic coding definition, calculation parameter values, floating proportion, associated coding and calculation; defining a calculation standard of each step, and combining a plurality of rules to form pricing data of the bottom layer indexes; and the data summarizing sub-module is used for summarizing and calculating each task upwards through traversing in reverse order after each thread finishes calculation until each specialty finishes the pricing data, and carrying out peer-to-peer same-node data accumulation according to a complete tree structure, so that new pricing data of the target engineering is formed.
5. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the engineering cost assessment method of any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the engineering cost assessment method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311416515.5A CN117151767B (en) | 2023-10-30 | 2023-10-30 | Engineering cost assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311416515.5A CN117151767B (en) | 2023-10-30 | 2023-10-30 | Engineering cost assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117151767A CN117151767A (en) | 2023-12-01 |
| CN117151767B true CN117151767B (en) | 2024-02-23 |
Family
ID=88884743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311416515.5A Active CN117151767B (en) | 2023-10-30 | 2023-10-30 | Engineering cost assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117151767B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875725B (en) * | 2024-03-13 | 2024-08-02 | 湖南三湘银行股份有限公司 | Information processing system based on knowledge graph |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934536A (en) * | 2017-03-01 | 2017-07-07 | 广东中建普联科技股份有限公司 | Construction industry quantities valuation listings data autocoding and recognition methods and system |
| CN109658131A (en) * | 2018-11-29 | 2019-04-19 | 国网福建省电力有限公司 | The method for carrying out cost evaluation based on power grid typical cost data |
| CN110309132A (en) * | 2019-05-08 | 2019-10-08 | 广东中建普联科技股份有限公司 | A kind of ration standard method of priced bill of quantities |
| CN112785257A (en) * | 2021-01-15 | 2021-05-11 | 广州市新誉工程咨询有限公司 | Engineering cost operation evaluation method and system based on BIM technology |
| CN113033983A (en) * | 2021-03-15 | 2021-06-25 | 武汉东之林科技有限公司 | Assessment method before base station investment plan |
-
2023
- 2023-10-30 CN CN202311416515.5A patent/CN117151767B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934536A (en) * | 2017-03-01 | 2017-07-07 | 广东中建普联科技股份有限公司 | Construction industry quantities valuation listings data autocoding and recognition methods and system |
| CN109658131A (en) * | 2018-11-29 | 2019-04-19 | 国网福建省电力有限公司 | The method for carrying out cost evaluation based on power grid typical cost data |
| CN110309132A (en) * | 2019-05-08 | 2019-10-08 | 广东中建普联科技股份有限公司 | A kind of ration standard method of priced bill of quantities |
| CN112785257A (en) * | 2021-01-15 | 2021-05-11 | 广州市新誉工程咨询有限公司 | Engineering cost operation evaluation method and system based on BIM technology |
| CN113033983A (en) * | 2021-03-15 | 2021-06-25 | 武汉东之林科技有限公司 | Assessment method before base station investment plan |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117151767A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114168716B (en) | Deep learning-based automatic engineering cost extraction and analysis method and device | |
| CN117151767B (en) | Engineering cost assessment method and device | |
| CN112163553B (en) | Material price accounting method, device, storage medium and computer equipment | |
| CN112257413B (en) | Address parameter processing method and related equipment | |
| CN115547466B (en) | Medical institution registration and review system and method based on big data | |
| CN109766416A (en) | A kind of new energy policy information abstracting method and system | |
| CN109872775A (en) | A kind of document mask method, device, equipment and computer-readable medium | |
| CN115952298A (en) | Supplier performance risk analysis method and related equipment | |
| CN116152843A (en) | Category identification method, device and storage medium for contract template to be filled-in content | |
| CN118037294B (en) | Financial certificate generation method and device based on business form data | |
| CN117648093A (en) | RPA flow automatic generation method based on large model and self-customized demand template | |
| CN117874206B (en) | Query method for natural language identification and Chinese word segmentation of high-efficiency data asset based on large model | |
| CN117435777B (en) | Automatic construction method and system for industrial chain map | |
| CN117851860A (en) | Method for automatically generating data classification grading template | |
| CN112988982A (en) | Autonomous learning method and system for computer comparison space | |
| CN117193823A (en) | Code workload assessment method, system and equipment for software demand change | |
| CN116244421A (en) | Method, device, equipment and readable storage medium for matching project names | |
| CN115688729A (en) | Power transmission and transformation project cost data integrated management system and method thereof | |
| CN111274404B (en) | Small sample entity multi-field classification method based on man-machine cooperation | |
| CN113077108A (en) | Data prediction system for power material configuration requirements | |
| CN105824871A (en) | Picture detecting method and equipment | |
| CN117473170B (en) | Intelligent contract template recommendation method and device based on code characterization and electronic equipment | |
| Khaki | Natural Language Processing using Deep Learning for Classifying Water Infrastructure Procurement Records and Calculating Unit Costs | |
| CN114595675A (en) | Method and device for tracking difference content between documents and electronic equipment | |
| CN117332286A (en) | System, method and device for data mapping verification |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |