CN113095963A - Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium - Google Patents
Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113095963A CN113095963A CN202110452824.2A CN202110452824A CN113095963A CN 113095963 A CN113095963 A CN 113095963A CN 202110452824 A CN202110452824 A CN 202110452824A CN 113095963 A CN113095963 A CN 113095963A
- Authority
- CN
- China
- Prior art keywords
- cost data
- actual
- data
- predicted
- cost
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 20
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000009826 distribution Methods 0.000 claims abstract description 98
- 238000005070 sampling Methods 0.000 claims abstract description 75
- 238000004519 manufacturing process Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004590 computer program Methods 0.000 claims description 23
- 238000010586 diagram Methods 0.000 claims description 23
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 108091028043 Nucleic acid sequence Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a real estate cost data processing method, a real estate cost data processing device, a computer device and a storage medium. The method comprises the following steps: acquiring actual cost data and predicted cost data of each item in the historical real estate project, updating a pre-constructed cost prediction model by taking the actual cost data and the predicted cost data as sample data, and obtaining a posterior probability value of variance of each actual cost data; determining variance expected values of all the actual cost data by sampling the posterior probability values; determining a probability distribution graph of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the variance expectation values; determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted; and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data. By adopting the method, the reliability of the project target cost data can be improved.
Description
Technical Field
The present application relates to the field of machine learning technologies, and in particular, to a real estate cost data processing method, apparatus, computer device, and storage medium.
Background
With the continuous development of machine learning, machine learning is gradually applied to various fields of artificial intelligence, such as data mining, computer vision, natural language processing, biometric identification, search engines, medical diagnosis, credit card fraud detection, stock market analysis, DNA sequence sequencing, voice and handwriting recognition, strategic games, robots, and the like; the efficiency of data processing is improved through machine learning.
With the rapid development of the real estate industry, a plurality of large-scale real estate enterprises emerge. During the development process for a long time, these real estate enterprises accumulate a large amount of cost data; at present, most real estate enterprises form a set of closed-loop full-cost control system, namely after a project is invested to a place, the target cost of the project is measured and calculated while the profit requirement determined by an investment scheme is met, and the target cost is used as a bottom line for cost control in the project construction process so as to ensure that the final profit of the project can meet the requirement of the investment scheme. However, since there are many uncertainty factors in the project implementation, such as: the factors such as scheme design, engineering calculation amount and project management can cause inconsistency between the cost measurement and calculation in the early stage and the actually occurring cost, so that the reliability evaluation of the project target cost measurement and calculation is very important.
And the traditional target cost measurement predicts the project target cost according to factors such as scheme design, engineering calculation amount, project management and the like, so that the reliability of the predicted project target cost data is low.
Disclosure of Invention
In view of the above, it is desirable to provide a real estate cost data processing method, apparatus, computer device, and storage medium capable of improving project target cost data reliability.
A real estate cost data processing method, the method comprising:
acquiring actual cost data and predicted cost data of each item in a historical property project, and taking the actual cost data and the predicted cost data as sample data;
updating a pre-constructed cost prediction model through the sample data until the cost prediction model converges to obtain posterior probability values of the variances of the actual cost data;
sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result;
determining a probability distribution diagram of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the expected variance value;
determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted;
and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, the updating, by the sample data, the pre-constructed cost prediction model until the cost prediction model converges to obtain a posterior probability value of each variance of the actual cost data includes:
determining a posterior probability expression of the actual cost data according to the actual cost data and the predicted cost data; the posterior probability expression is determined according to a first relational expression and a second relational expression; the first relationship is determined from the actual cost data and the predicted cost data; the second relationship is determined based on a relative error between the actual cost data and the predicted cost data, and a variance of the actual cost data;
determining a prior probability expression of the variance;
and updating a pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model is converged to obtain the posterior probability value of each actual cost data variance.
In one embodiment, the sampling the posterior probability values and determining the expected variance value of each of the actual cost data according to the sampling result includes:
sampling the posterior probability value by a Markov chain Monte Carlo method to obtain a probability distribution diagram representing the variance of each actual cost data;
and integrating the variance based on the probability distribution diagram of the variance of the actual cost data to obtain the expected variance value of each actual cost data.
In one embodiment, the sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data includes:
and sampling the actual total cost data by a Markov chain Monte Carlo method to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, the method further comprises:
acquiring sales revenue data of the real estate item to be forecasted;
determining a probability distribution map of incremental data for the production project to be forecasted based on the probability distribution map of actual total cost data reliability from the sales revenue data and the actual total cost data.
In one embodiment, the method further comprises:
generating the cost updating strategy data according to the probability distribution map of the value-added data;
updating the actual total cost data according to the cost update policy data.
A real estate cost data processing apparatus, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring actual cost data and predicted cost data of each item in a historical property project and taking the actual cost data and the predicted cost data as sample data;
the updating module is used for updating a pre-constructed cost prediction model through the sample data until the cost prediction model converges to obtain the posterior probability value of each actual cost data variance;
the first sampling module is used for sampling the posterior probability value and determining the variance expected value of each actual cost data according to the sampling result;
a first determining module for determining a probability distribution map of relative error values between actual cost data and predicted cost data for each entry in the historically produced project based on the expected variance values;
the second determining module is used for determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the property item to be predicted;
and the second sampling module is used for sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring actual cost data and predicted cost data of each item in a historical property project, and taking the actual cost data and the predicted cost data as sample data;
updating a pre-constructed cost prediction model through the sample data until the cost prediction model converges to obtain posterior probability values of the variances of the actual cost data;
sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result;
determining a probability distribution diagram of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the expected variance value;
determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted;
and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring actual cost data and predicted cost data of each item in a historical property project, and taking the actual cost data and the predicted cost data as sample data;
updating a pre-constructed cost prediction model through the sample data until the cost prediction model converges to obtain posterior probability values of the variances of the actual cost data;
sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result;
determining a probability distribution diagram of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the expected variance value;
determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted;
and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
According to the real estate cost data processing method, the real estate cost data processing device, the computer equipment and the storage medium, the pre-constructed cost prediction model is updated through the actual cost data and the prediction cost data of each item in the historical real estate project until the cost prediction model is converged, and the posterior probability value of each actual cost data variance is obtained; sampling the posterior probability values, determining a probability distribution map of a relative error value between actual cost data and predicted cost data of each item in a historical production project, further determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in a production project to be predicted, and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data; the reliability of the cost data of the historical production project is determined by machine learning according to the historical data of the historical production project, the actual total cost data of the project to be predicted is predicted based on the reliability of the historical data, and the reliability of the actual total cost data of the project to be predicted is improved.
Drawings
FIG. 1 is a diagram of an embodiment of a real estate cost data processing method;
FIG. 2 is a flow diagram illustrating a method for processing real estate cost data in one embodiment;
FIG. 3 is a schematic flow chart illustrating a method for processing real estate cost data in another embodiment;
FIG. 4 is a block diagram showing the structure of a data processing apparatus according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The real estate cost data processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 acquires actual cost data and predicted cost data of each item in the historical property project from the server 104, and takes the actual cost data and the predicted cost data as sample data; updating a pre-constructed cost prediction model through sample data until the cost prediction model is converged to obtain posterior probability values of all practical cost data variances; sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result; determining a probability distribution graph of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the variance expectation values; determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted; and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, there is provided a real estate cost data processing method, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
Wherein, the property project comprises a plurality of items, in other words, each property project comprises a plurality of detailed items (subjects), such as land cost, early stage project cost, subject building installation project, landscape, etc., and each item has forecast cost data and actual cost data; the predicted cost data is obtained by measuring and calculating according to the project scheme, the list manufacturing cost, the quota and other information. For example, a property project has a total of M entries, and the predicted cost data for each entry may be represented as Wi。
Specifically, the terminal receives a historical data acquisition instruction, the data instruction carries data attributes and a property item identifier, and actual cost data and predicted cost data of each item in a corresponding historical property item are acquired from the server according to the data attributes and the property item identifier; wherein the data attribute can be, but is not limited to, an entry identification of the property item.
And 204, updating the pre-constructed cost prediction model through the sample data until the cost prediction model is converged to obtain the posterior probability value of each actual cost data variance.
The cost prediction model is established based on Bayesian theory and used for predicting the reliability of cost data; the cost prediction model may be expressed as:
σiis the variance of the actual cost data for each entry,
actual cost data for item i after N settlement/resolution of the item,
is σiK is a constant, Wpre,iAnd (4) calculating the predicted cost data of the item i according to the scheme, the list manufacturing cost, the quota and the like at the early stage of the project.
Specifically, a posterior probability expression of the actual cost data is determined according to the actual cost data and the predicted cost data; determining a prior probability expression of the variance; updating a pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model is converged to obtain posterior probability values of all practical cost data variances; wherein the posterior probability expression is determined according to a first relational expression satisfied by the actual cost data and the predicted cost data, and a second relational expression satisfied by a relative error and a variance between the actual cost data and the predicted cost data; that is, the posterior probability expression is determined based on the first relational expression and the second relational expression; the first relation is determined according to the actual cost data and the predicted cost data; the second relationship is determined based on a relative error between the actual cost data and the predicted cost data, and a variance of the actual cost data.
Wherein the actual cost data Wreal,iAnd predicted cost data Wpre,iThe first relation satisfied may be expressed as: wreal,i＝Wpre,i(1+εi)，εiRepresenting the relative error (%) between the actual cost data and the predicted cost data. Assumed error eiSatisfies the mean value of 0 and the varianceIs σiThe relative error and variance between the actual cost data and the predicted cost data satisfies a second relation of
The actual total cost data W for a production projecttotal,realCan be expressed as:
and step 206, sampling the posterior probability value, and determining the variance expectation value of each actual cost data according to the sampling result.
Specifically, the posterior probability value is sampled by a sampling method (which may be, but is not limited to, a markov chain monte carlo method), so as to obtain a probability distribution map representing variance of each actual cost data; data variance sigma based on actual costiThe probability distribution diagram carries out integral processing on the variance to obtain the variance expectation value sigma of each actual cost datai,mean。
At step 208, a probability distribution map of relative error values between actual cost data and predicted cost data for each entry in the historically produced project is determined based on the expected variance values.
Predicted cost data W of M entriespre,iAnd actual total cost data WtotalThe relationship between can be expressed as:
Specifically, the actual total cost data is sampled by a markov chain monte carlo method, and a probability distribution map representing the reliability of the actual total cost data is obtained.
In the real estate cost data processing method, a pre-constructed cost prediction model is updated through actual cost data and predicted cost data of each item in a historical real estate project until the cost prediction model is converged, and a posterior probability value of variance of each actual cost data is obtained; sampling the posterior probability values, determining a probability distribution map of a relative error value between actual cost data and predicted cost data of each item in a historical production project, further determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in a production project to be predicted, and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data; the reliability of the cost data of the historical production project is determined by machine learning according to the historical data of the historical production project, the actual total cost data of the project to be predicted is predicted based on the reliability of the historical data, and the reliability of the actual total cost data of the project to be predicted is improved.
In another embodiment, as shown in fig. 3, there is provided a real estate cost data processing method, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
And 304, updating the pre-constructed cost prediction model through the sample data until the cost prediction model is converged to obtain the posterior probability value of each actual cost data variance.
Specifically, a posterior probability expression of the actual cost data is determined according to the actual cost data and the predicted cost data; the posterior probability expression is determined by a first relation and a second relation, and the first relation is determined according to the actual cost data and the predicted cost data; the second relation is determined according to the relative error between the actual cost data and the predicted cost data and the variance of the actual cost data; by determining prior probability expression of variance, pre-constructed according to posterior probability expression and prior probability expressionUpdating the cost prediction model until the cost prediction model is converged to obtain the posterior probability value of each practical cost data variance, namely constructing the cost prediction model based on the Bayesian theory; wherein the total cost W of the production projecttotalAnd cost data W of M entries iiThe relationship between can be expressed as:
in actual practice, the actual cost data W for each item of the property itemreal,iAnd predicted cost data Wpre,iThe relation between can be expressed as Wreal,i＝Wpre,i(1+εi) (ii) a That is, the relationship between the production project set cost data and the predicted cost data for the M entries may be expressed as
εiThe relative error (%) between the two is shown, assuming error εiSatisfies the mean value of 0 and the variance of sigmaiIs a Gaussian distribution ofiSatisfy the requirement of
I.e. the actual total cost data Wtotal,realCan be expressed as:
according to bayesian formulation, the expression that can determine the posterior probability of the variance of the actual cost data can be expressed as:
according to Wreal,i＝Wpre,i(1+σi) And
can determine
The expression for a posteriori probability of (a) can be expressed as:
determining the value range [ sigma ] of the variancemin,σmax]And determining the prior probability expression of the variance according to the value range as follows:
the updated cost prediction model can be obtained according to the expression of the posterior probability and the prior probability expression of the variance as follows:
σiis the variance of the actual cost data for each entry,
actual cost data for item i after N settlement/resolution of the item,
is σiK is a constant, Wpre,iAnd (4) calculating the predicted cost data of the item i according to the scheme, the list manufacturing cost, the quota and the like at the early stage of the project.
And step 306, sampling the posterior probability value, and determining the variance expectation value of each actual cost data according to the sampling result.
Specifically, a posterior probability value is sampled by a Markov chain Monte Carlo method to obtain a probability distribution diagram representing the variance of each actual cost data; and integrating the variance based on the probability distribution diagram of the variance of the actual cost data to obtain the expected variance value of each actual cost data.
At step 308, a probability distribution map of relative error values between actual cost data and predicted cost data for each entry in the historically produced project is determined based on the expected variance values.
At step 310, actual total cost data is determined based on the probability distribution map of relative error values and the predicted cost data for each entry in the property item to be predicted.
At step 314, sales revenue data for the property project to be forecasted is obtained.
At step 316, a probability distribution map of incremental data for the property item to be forecasted is determined based on the sales revenue data and the actual total cost data based on the probability distribution map of actual total cost data reliability.
Specifically, determining incremental data of the local production project, namely income data of the local production project according to actual assembly data of the local production project to be predicted and corresponding sales income data; and determining the probability distribution map of each value-added data according to the probability distribution map representing the reliability of the actual total cost data, namely determining the reliability. Alternatively, the probability values for the maximum and/or minimum cost risk values may be determined based on the probability distribution map of the value added data and the cost control risk range of the real estate item.
Optionally, in an embodiment, the cost update policy data is generated according to a probability distribution map of the value added data; the actual total cost data is updated according to the cost update policy data. The method is characterized in that the method comprises the following steps of updating real estate project cost data in a mode of updating various items of real estate project schedule, management modes and the like according to a probability distribution diagram of value-added data, reducing cost prediction risk values, improving controllability of the project cost data and achieving reasonable distribution of resources; wherein the smaller the variance of the actual cost data and the relative error between the actual cost data and the predicted cost data, the smaller the cost prediction risk value; the greater the variance of the actual cost data and the relative error between the actual cost data and the predicted cost data, the greater the cost prediction risk value.
In the real estate cost data processing method, a cost prediction model is established based on a Bayesian theory, and the pre-established cost prediction model is updated according to the actual cost data and the prediction cost data of each item in the historical real estate project to obtain the posterior probability value of each actual cost data variance; determining the reliability of the historical cost data of each item in the historical production project by sampling the posterior probability value, further determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the production project to be predicted, and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data; the method comprises the steps of performing machine learning and secondary sampling according to historical data of historical property projects, determining the reliability of historical property project cost data, predicting actual total cost data of a property project to be predicted based on the reliability of the historical data, determining a risk value of the project cost data, and improving the reliability of the actual total cost data of the property project to be predicted.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in FIG. 4, there is provided a real estate cost data processing apparatus comprising: an acquisition module 402, an update module 404, a first sampling module 406, a first determination module 408, a second determination module 410, and a second sampling module 412, wherein:
an obtaining module 402, configured to obtain actual cost data and predicted cost data of each entry in the historical property item, where the actual cost data and the predicted cost data are used as sample data.
And an updating module 404, configured to update the pre-constructed cost prediction model through the sample data until the cost prediction model converges, so as to obtain a posterior probability value of each actual cost data variance.
And a first sampling module 406, configured to sample the posterior probability value, and determine an expected variance value of each actual cost data according to the sampling result.
A first determination module 408 determines a probability distribution map of relative error values between actual cost data and predicted cost data for each entry in the historically produced project based on the expected variance values.
A second determination module 410 for determining actual total cost data based on the probability distribution map of relative error values and the predicted cost data for each entry in the property project to be predicted.
And a second sampling module 412, configured to sample the actual total cost data to obtain a probability distribution map representing reliability of the actual total cost data.
In the real estate cost data processing device, a pre-constructed cost prediction model is updated through actual cost data and predicted cost data of each item in a historical real estate project until the cost prediction model converges, and a posterior probability value of variance of each actual cost data is obtained; sampling the posterior probability values, determining a probability distribution map of a relative error value between actual cost data and predicted cost data of each item in a historical production project, further determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in a production project to be predicted, and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data; the reliability of the cost data of the historical production project is determined by machine learning according to the historical data of the historical production project, the actual total cost data of the project to be predicted is predicted based on the reliability of the historical data, and the reliability of the actual total cost data of the project to be predicted is improved.
In another embodiment, a real estate cost data processing apparatus is provided that includes, in addition to an acquisition module 402, an update module 404, a first sampling module 406, a first determination module 408, a second determination module 410, and a second sampling module 412: the device comprises an acquisition module, a data processing module and a generation module, wherein:
and the acquisition module is used for acquiring the sales revenue data of the real estate item to be predicted.
And the data processing module is used for determining the probability distribution map of the incremental data of the project to be predicted according to the sales income data and the actual total cost data based on the probability distribution map of the reliability of the actual total cost data.
And the generating module is used for generating cost updating strategy data according to the probability distribution map of the value-added data.
In one embodiment, the update module is further configured to update the actual total cost data according to the cost update policy data.
In one embodiment, the updating module is further configured to update the pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model converges to obtain posterior probability values of the variances of the actual cost data.
In one embodiment, the first determining module is further configured to determine a posterior probability expression of the actual cost data based on the actual cost data and the predicted cost data; the posterior probability expression is determined according to the first relational expression and the second relational expression; the first relation is determined according to the actual cost data and the predicted cost data; the second relationship is determined based on a relative error between the actual cost data and the predicted cost data, and a variance of the actual cost data.
In an embodiment, the first sampling module 406 is further configured to sample the posterior probability values by a markov chain monte carlo method to obtain a probability distribution map representing variances of each actual cost data; and integrating the variance based on the probability distribution diagram of the variance of the actual cost data to obtain the expected variance value of each actual cost data.
In one embodiment, the second sampling module 412 is further configured to sample the actual total cost data by a markov chain monte carlo method to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, a cost prediction model is established based on Bayesian theory, and the pre-established cost prediction model is updated according to actual cost data and prediction cost data of each item in historical real estate projects to obtain posterior probability values of variances of each actual cost data; determining the reliability of the historical cost data of each item in the historical production project by sampling the posterior probability value, further determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the production project to be predicted, and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data; the method comprises the steps of performing machine learning and secondary sampling according to historical data of historical property projects, determining the reliability of historical property project cost data, predicting actual total cost data of a property project to be predicted based on the reliability of the historical data, determining a risk value of the project cost data, and improving the reliability of the actual total cost data of the property project to be predicted.
For specific limitations of the real estate cost data processing apparatus, reference can be made to the above limitations of the real estate cost data processing method, which are not described herein again. The various modules in the real estate cost data processing apparatus described above can be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a real estate cost data processing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring actual cost data and predicted cost data of each item in the historical property project, and taking the actual cost data and the predicted cost data as sample data;
updating a pre-constructed cost prediction model through sample data until the cost prediction model is converged to obtain posterior probability values of all practical cost data variances;
sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result;
determining a probability distribution graph of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the variance expectation values;
determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted;
and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining a posterior probability expression of the actual cost data according to the actual cost data and the predicted cost data; the posterior probability expression is determined according to the first relational expression and the second relational expression; the first relation is determined according to the actual cost data and the predicted cost data; the second relation is determined according to the relative error between the actual cost data and the predicted cost data and the variance of the actual cost data;
determining a prior probability expression of the variance;
and updating the pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model is converged to obtain the posterior probability value of each actual cost data variance.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
sampling posterior probability values by a Markov chain Monte Carlo method to obtain a probability distribution diagram representing the variance of each actual cost data;
and integrating the variance based on the probability distribution diagram of the variance of the actual cost data to obtain the expected variance value of each actual cost data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and sampling the actual total cost data by a Markov chain Monte Carlo method to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring sales revenue data of a real estate item to be forecasted;
based on the probability distribution map of actual total cost data reliability, a probability distribution map of incremental data for the production project to be forecasted is determined based on the sales revenue data and the actual total cost data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
generating cost updating strategy data according to the probability distribution map of the value-added data;
the actual total cost data is updated according to the cost update policy data.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring actual cost data and predicted cost data of each item in the historical property project, and taking the actual cost data and the predicted cost data as sample data;
updating a pre-constructed cost prediction model through sample data until the cost prediction model is converged to obtain posterior probability values of all practical cost data variances;
sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result;
determining a probability distribution graph of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the variance expectation values;
determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted;
and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a posterior probability expression of the actual cost data according to the actual cost data and the predicted cost data; the posterior probability expression is determined according to the first relational expression and the second relational expression; the first relation is determined according to the actual cost data and the predicted cost data; the second relation is determined according to the relative error between the actual cost data and the predicted cost data and the variance of the actual cost data;
determining a prior probability expression of the variance;
and updating the pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model is converged to obtain the posterior probability value of each actual cost data variance.
In one embodiment, the computer program when executed by the processor further performs the steps of:
sampling posterior probability values by a Markov chain Monte Carlo method to obtain a probability distribution diagram representing the variance of each actual cost data;
and integrating the variance based on the probability distribution diagram of the variance of the actual cost data to obtain the expected variance value of each actual cost data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and sampling the actual total cost data by a Markov chain Monte Carlo method to obtain a probability distribution map representing the reliability of the actual total cost data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring sales revenue data of a real estate item to be forecasted;
based on the probability distribution map of actual total cost data reliability, a probability distribution map of incremental data for the production project to be forecasted is determined based on the sales revenue data and the actual total cost data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
generating cost updating strategy data according to the probability distribution map of the value-added data;
the actual total cost data is updated according to the cost update policy data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A real estate cost data processing method, characterized in that the method comprises:
acquiring actual cost data and predicted cost data of each item in a historical property project, and taking the actual cost data and the predicted cost data as sample data;
updating a pre-constructed cost prediction model through the sample data until the cost prediction model converges to obtain posterior probability values of the variances of the actual cost data;
sampling the posterior probability value, and determining the variance expected value of each actual cost data according to the sampling result;
determining a probability distribution diagram of relative error values between actual cost data and predicted cost data of each item in the historical production project according to the expected variance value;
determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the produced project to be predicted;
and sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
2. The method of claim 1, wherein said updating a pre-constructed cost prediction model with said sample data until said cost prediction model converges to obtain a posterior probability value for each of said actual cost data variances comprises:
determining a posterior probability expression of the actual cost data according to the actual cost data and the predicted cost data; the posterior probability expression is determined according to a first relational expression and a second relational expression; the first relationship is determined from the actual cost data and the predicted cost data; the second relationship is determined based on a relative error between the actual cost data and the predicted cost data, and a variance of the actual cost data;
determining a prior probability expression of the variance;
and updating a pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model is converged to obtain the posterior probability value of each actual cost data variance.
3. The method of claim 1, wherein the sampling the posterior probability values and determining expected variance values of the actual cost data according to the sampling results comprises:
sampling the posterior probability value by a Markov chain Monte Carlo method to obtain a probability distribution diagram representing the variance of each actual cost data;
and integrating the variance based on the probability distribution diagram of the variance of the actual cost data to obtain the expected variance value of each actual cost data.
4. The method of claim 1, wherein sampling the actual total cost data to obtain a probability distribution map that characterizes reliability of the actual total cost data comprises:
and sampling the actual total cost data by a Markov chain Monte Carlo method to obtain a probability distribution map representing the reliability of the actual total cost data.
5. The method of claim 1, further comprising:
acquiring sales revenue data of the real estate item to be forecasted;
determining a probability distribution map of incremental data for the production project to be forecasted based on the probability distribution map of actual total cost data reliability from the sales revenue data and the actual total cost data.
6. The method of claim 5, further comprising:
generating the cost updating strategy data according to the probability distribution map of the value-added data;
updating the actual total cost data according to the cost update policy data.
7. A real estate cost data processing apparatus, characterized in that the apparatus comprises:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring actual cost data and predicted cost data of each item in a historical property project and taking the actual cost data and the predicted cost data as sample data;
the updating module is used for updating a pre-constructed cost prediction model through the sample data until the cost prediction model converges to obtain the posterior probability value of each actual cost data variance;
the first sampling module is used for sampling the posterior probability value and determining the variance expected value of each actual cost data according to the sampling result;
a first determining module for determining a probability distribution map of relative error values between actual cost data and predicted cost data for each entry in the historically produced project based on the expected variance values;
the second determining module is used for determining actual total cost data according to the probability distribution map of the relative error value and the predicted cost data of each item in the property item to be predicted;
and the second sampling module is used for sampling the actual total cost data to obtain a probability distribution map representing the reliability of the actual total cost data.
8. The apparatus of claim 7, further comprising:
the first determining module is further used for determining a posterior probability expression of the actual cost data according to the actual cost data and the predicted cost data; the posterior probability expression is determined according to a first relational expression and a second relational expression; the first relationship is determined from the actual cost data and the predicted cost data; the second relationship is determined based on a relative error between the actual cost data and the predicted cost data, and a variance of the actual cost data;
the updating module is further used for updating a pre-constructed cost prediction model according to the posterior probability expression and the prior probability expression until the cost prediction model converges to obtain posterior probability values of the actual cost data variances.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110452824.2A CN113095963A (en) | 2021-04-26 | 2021-04-26 | Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110452824.2A CN113095963A (en) | 2021-04-26 | 2021-04-26 | Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113095963A true CN113095963A (en) | 2021-07-09 |
Family
ID=76680412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110452824.2A Pending CN113095963A (en) | 2021-04-26 | 2021-04-26 | Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095963A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113744884A (en) * | 2021-09-30 | 2021-12-03 | 西南政法大学 | Student health data early warning and intervention method and system |
-
2021
- 2021-04-26 CN CN202110452824.2A patent/CN113095963A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113744884A (en) * | 2021-09-30 | 2021-12-03 | 西南政法大学 | Student health data early warning and intervention method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126668B (en) | Spark operation time prediction method and device based on graph convolution network | |
| US20190057284A1 (en) | Data processing apparatus for accessing shared memory in processing structured data for modifying a parameter vector data structure | |
| US10146531B2 (en) | Method and apparatus for generating a refactored code | |
| CN112910710B (en) | Network flow space-time prediction method and device, computer equipment and storage medium | |
| CN112465011A (en) | Project risk prediction method and system based on project research and development process | |
| CN112733997A (en) | Hydrological time series prediction optimization method based on WOA-LSTM-MC | |
| CN108182633A (en) | Loan data processing method, device, computer equipment and storage medium | |
| CN113392229A (en) | Supply chain relation construction and prediction method, device, equipment and storage medium | |
| CN108764553B (en) | User scale prediction method and device and computer equipment | |
| CN113095963A (en) | Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium | |
| CN112232886B (en) | Electricity price probability prediction method, system, computer equipment and storage medium | |
| CN114187009A (en) | Feature interpretation method, device, equipment and medium of transaction risk prediction model | |
| CN117454668A (en) | Method, device, equipment and medium for predicting failure probability of parts | |
| CN113689020A (en) | Service information prediction method, device, computer equipment and storage medium | |
| CN111008311A (en) | Complex network node importance evaluation method and device based on neighborhood weak connection | |
| Soria et al. | How efficient deep-learning object detectors are? | |
| CN115827877A (en) | Proposal auxiliary combination method, device, computer equipment and storage medium | |
| CN115759742A (en) | Enterprise risk assessment method and device, computer equipment and storage medium | |
| CN116188174A (en) | Insurance fraud detection method and system based on modularity and mutual information | |
| CN109829745A (en) | Business revenue data predication method, device, computer equipment and storage medium | |
| CN109767263A (en) | Business revenue data predication method, device, computer equipment and storage medium | |
| WO2020167156A1 (en) | Method for debugging a trained recurrent neural network | |
| CN115481785A (en) | Transformer state prediction method and device based on oil temperature and computer equipment | |
| CN114660468A (en) | Retired battery state of charge prediction method and device and electronic equipment | |
| CN113743448A (en) | Model training data acquisition method, model training method and device |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210709 |
|
| WD01 | Invention patent application deemed withdrawn after publication |