CN109615412A - Cell average price predictor method, electronic device and storage medium - Google Patents
Cell average price predictor method, electronic device and storage medium Download PDFInfo
- Publication number
- CN109615412A CN109615412A CN201811286728.XA CN201811286728A CN109615412A CN 109615412 A CN109615412 A CN 109615412A CN 201811286728 A CN201811286728 A CN 201811286728A CN 109615412 A CN109615412 A CN 109615412A
- Authority
- CN
- China
- Prior art keywords
- historical
- average price
- price
- cell
- target cell
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012549 training Methods 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000006185 dispersion Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 10
- 238000012360 testing method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000009825 accumulation Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to prediction models, disclose a kind of cell average price predictor method, this method comprises: receiving the average price based on Target cell estimates request, obtain the historical record of Target cell within a preset time from default channel；Calculate separately the listed average price of the history of the Target cell within a preset time and history conclusion of the business average price；The history is listed in average price and history conclusion of the business average price input first community average price prediction model, the first average price of Target cell is obtained.The present invention is also disclosed that a kind of electronic device and computer storage medium.Using the present invention, the accuracy that cell average price is estimated can be improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method for estimating a mean price of a cell, an electronic device, and a computer-readable storage medium.
Background
The theoretical method for estimating the real estate has been fully verified for a long time in the past, and the market comparison method is the most effective real estate assessment model construction theory recognized at present, but the market comparison method has higher threshold, and is specifically shown in the following steps: first, there is a need to collect large, normal real estate transaction data. Second, the market comparison method must require that the rate be relatively stable.
The traditional market comparison method estimation model depends on subjective experience of evaluators excessively, so that estimation results are unreliable, moral risks are more likely to be caused, and benign development of real estate estimation industry is hindered. Meanwhile, the market comparison method assessment needs to collect, manage, analyze and display a large amount of human, social, economic and geographic data, the traditional manual management mode obviously cannot meet the processing requirements of house property assessment on a large amount of information, and the improvement of an assessment model and the establishment of an assessment information system by using a new technical means are an inevitable trend of the development of the assessment industry.
Disclosure of Invention
In view of the foregoing, the present invention provides a method, an electronic device and a computer-readable storage medium for estimating a mean price of a cell, which mainly aims to improve the accuracy of estimating the mean price of the cell.
In order to achieve the above object, the present invention provides a method for estimating a mean price of a cell, comprising:
s1, receiving a mean price estimation request based on a target cell, and acquiring a history record of the target cell in a preset time from a preset channel;
s2, respectively calculating the historical listing average price and the historical trading average price of the target cell in the preset time based on a preset analysis rule and the historical record; and
and S3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
Preferably, the method further comprises:
s4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
In addition, the present invention also provides an electronic device, comprising: the system comprises a memory and a processor, wherein the memory is stored with a cell average price estimating program which can run on the processor, and when the cell average price estimating program is executed by the processor, the following steps can be realized:
a1, receiving a mean price estimation request based on a target cell, and acquiring a history record of the target cell in a preset time from a preset channel;
a2, respectively calculating the historical listing average price and the historical trading average price of the target cell in a preset time based on a preset analysis rule and the historical record; and
and A3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
Preferably, when executed by the processor, the cell average price estimation program further implements the following steps:
and A4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
In addition, to achieve the above object, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a cell average price estimation program, and when the cell average price estimation program is executed by a processor, any step in the cell average price estimation method can be implemented.
According to the cell average price estimation method, the electronic device and the computer readable storage medium, historical data of each house source of a target cell is obtained, the historical listing/transaction price of each house source is analyzed and processed, the historical listing/transaction average price of the target cell is calculated, and the accuracy of the historical listing/transaction average price of the target cell is improved; estimating the average price of the target cell by utilizing a first cell average price estimation model based on the historical listing/bargaining average price of the target cell, and contributing to improving the accuracy of estimation of the average price of the cell; the accuracy of the average price estimation of the cell is further improved by performing secondary estimation on the estimation result of the average price estimation model of the first cell.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of a method for estimating average price of a cell according to the present invention;
FIG. 2 is a flowchart illustrating a method for estimating average price of a cell according to another preferred embodiment of the present invention;
FIG. 3 is a diagram of an electronic device according to a preferred embodiment of the present invention;
fig. 4 is a block diagram illustrating a preferred embodiment of the cell average price estimation process of fig. 3.
The implementation, functional features and advantages of the objects of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a method for estimating average price of a cell. Referring to fig. 1, a flow chart of a method for estimating a mean price of a cell according to a first preferred embodiment of the present invention is shown. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the method for estimating the average cell price includes steps S1-S3:
s1, receiving a mean price estimation request based on the target cell, and acquiring the historical record of the target cell in the preset time from a preset channel, wherein the historical record comprises: history listing record and history transaction record.
The user submits a prediction request through the client, wherein the request comprises prediction targets: the target cell is equalized.
The preset channels in different cities may be different, and taking Shenzhen as an example, the preset channels include: chaine, szhome, zhongyuan, hometown, search house and other platforms.
Prior to step S1, the method further comprises: and presetting the priority levels of the plurality of preset channels. The priority of each channel is established by experts according to the credibility of each channel data, for example, the priority of the above 5 channels is: chain family > szhome > Zhongyuan > Jiajiashun > search for houses.
And the history records crawled from the preset channels are history listing records/history transaction records corresponding to different house sources in different cells.
In the present embodiment, step S1 includes: acquiring a history record of a designated area within preset time from a preset channel; and acquiring the description information of each historical record, and determining the historical record corresponding to the target cell according to the mapping relation between the predetermined description information and the cell.
The designated area includes the target cell, and the designated area is generally xx city xx area.
The description information includes location information describing the geographical location of the house source, for example, xx unit xx building xx number in xx district xx road xx period xx in xx city xx. And determining all history records corresponding to the target cell by using the description information of all history records.
All the history records corresponding to the target cell are history records corresponding to a plurality of house sources in the target cell.
And S2, respectively calculating the historical listing average price and the historical trading average price of the target cell in the preset time based on the preset analysis rule and the historical record.
In the present embodiment, step S2 includes:
respectively determining historical records corresponding to all house sources in the target cell according to the description information;
analyzing and determining the historical listing price and the historical trading price of each house source in the target cell within preset time; and
and calculating the historical listing average price and the historical bargaining average price of the target cell in the preset time.
The historical listing average price and the historical transaction average price of the target cell are closely related to the historical listing price and the historical transaction price of each set of house resources in the target cell. Therefore, firstly, the historical listing record and the historical deal record corresponding to each house source in the target cell are determined, then the historical listing price and the historical deal price of each house source are respectively determined, and finally, the historical listing average price and the historical deal average price of the target cell are calculated.
It should be noted that the present invention does not require the same house source to have both history listing records and history transaction records.
Preferably, the step of analyzing and determining the historical listing price and the historical trading price of each house source in the target cell within a preset time includes:
when the same house source in the target cell corresponds to a history listing record/history transaction record, reading the history listing price and the history transaction price in the history listing record/history transaction record as the history listing price and the history transaction price of the house source;
when the same house source in the target cell corresponds to a plurality of history listing records, acquiring a plurality of history listing prices corresponding to the plurality of history listing records;
when the plurality of historical listing prices are consistent, any one historical listing price is reserved as the historical listing price of the house source; or
And when the plurality of historical listing prices are inconsistent, taking the person with the highest channel priority as the historical listing price of the house source.
Assuming that a certain house source of a target cell is listed on 5 channels at the same time, 5 history listing records exist in the house source, namely the house source has 5 history listing prices. And when the 5 historical listing prices are the same, taking any one historical listing price as the historical listing price of the house source. And when the historical listing prices of the 5 house sources are different, acquiring the channel priority corresponding to each historical listing price, and selecting the historical listing price corresponding to the highest channel priority as the historical listing price of the house source.
In general, the same house source only corresponds to one historical transaction record, so that duplicate removal processing is not needed.
Through carrying out duplicate removal processing on the history records of all house sources in the target cell, a foundation is laid for the subsequent calculation of the historical listing average price and the historical bargaining average price of the target cell.
Preferably, the step of "calculating the historical listing average price and the historical bargaining average price of the target cell in the preset time" in this embodiment includes:
calculating the cell historical average price of a target cell within preset time, and respectively calculating the historical listing price of each house source in the target cell within the preset time and the deviation between a plurality of historical transaction prices and the cell historical average price;
filtering out historical listing prices with deviation larger than a first preset threshold value, and filtering out historical deal prices with deviation larger than a second preset threshold value; and
and respectively calculating the historical listing average price and the historical bargaining average price of the target cell at the t-th period according to the reserved historical listing price and the historical bargaining price.
Taking the target cell P as an example, the historical listing prices and the historical trading prices of a plurality of house sources in the cell P in the same period are different. In order to remove abnormal values in the historical listing price and the historical transaction price of the cell P, for example, when the price is too high or too low, the deviation between the historical listing price and the historical transaction price of each house source in the cell P and the historical average price of the cell P needs to be determined, data with the deviation exceeding a preset range (for example, 40% and 30% are respectively used as a first preset threshold and a second preset threshold) is filtered, and then the remaining historical listing price and the historical transaction price are respectively averaged to obtain the historical listing average price and the historical transaction average price of the cell P in the previous month.
The first preset threshold and the second preset threshold can be adjusted according to requirements.
The historical listing prices and the historical trading average prices of a plurality of house sources in the target cell are filtered, so that a foundation is laid for accurately calculating the historical listing average prices and the historical trading average prices of the target cell.
Preferably, the cell historical average price is calculated according to the cell historical price of the target cell in the last month in a plurality of preset channels, and the cell historical price is directly obtained from the plurality of channels. In this embodiment, the step of calculating the cell history average price of the target cell within the preset time includes:
acquiring n cell historical prices of a target cell within preset time, and respectively calculating the discrete degrees of the n cell historical prices;
if the discrete degree meets a first preset condition, directly taking the average value of the historical prices of the n cells as the historical average price of the target cell within preset time; or
If the discrete degree does not meet the first preset condition, the maximum value and the minimum value in the historical prices of the n cells are removed, and the average value of the historical prices of the remaining (n-2) cells is taken as the historical average price of the target cell in the preset time.
Wherein n is the number of the preset channels. For example, the first preset condition may be: the relative standard deviations of the historical prices of the n cells are all less than or equal to 10%. The degree of dispersion of the n cell historical prices can be expressed in relative standard deviations. The discrete degree of the historical prices of the n cells is determined by calculating the relative standard deviation of the historical prices of the n cells, and the historical average price of the target cell in the last month is further calculated, so that the accuracy of the historical average price of the target cell is improved, and a foundation is laid for accurately estimating the average price of the cell.
However, in the process of acquiring the historical cell price data of the target cell in the last month from n preset channels, a situation that market data is missing may occur, that is, there may be no historical cell price data of the target cell in the last month in a certain channel. In this case, the cell history price corresponding to the highest priority one of the plurality of channels in which the cell history price of the target cell in the previous month exists is taken as the cell history price of the target cell in the previous month.
And S3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
Inputting the historical listing average price and the historical trading average price of the target cell in the previous month obtained in the above steps into a first cell average price estimation model, wherein the result output by the model is the predicted current cell average price of the target cell, and then sending the first average price in the estimation result to a user through a client.
In this embodiment, the first cell average price estimation model is obtained by training based on a multivariate gray-scale correlation prediction model, and the model training step includes:
determining sample data: acquiring historical listing average prices, historical bargaining average prices and cell historical average prices of a plurality of specified cells in a specified time interval (2017.12-2018.7) to generate sample data [ X, Y ];
for example, X ═ X [ (X)1a，x1b)，(x2a，x2b)，...，(xia，xib)]，Y＝[Y1，Y2，...，Yi]Wherein x isiaRepresenting a historical average bid, x, for six consecutive months (adjustable length of time series) for a given cell i within 2017.12-2018.7ibRepresenting the average of the historical bargain of a given cell i within 2017.12-2018.7 for six consecutive months (the length of the time series is adjustable), and xia，xibTime sequences corresponding to the historical listing average price and the historical bargaining average price are formed; y isiIndicating the cell history mean price for six consecutive months (time series consistent with X) for the given cell within 2017.12-2018.7. The calculation steps of the historical listing average price, the historical bargain average price and the cell historical average price are substantially the same as the steps described above, and are not described herein again.
Model training: dividing the sample data [ X, Y ] into a training set and a test set according to time (for example, sample data of two months close to the current time is used as the test set, and the rest sample data is used as the training set), and training the multivariate gray level correlation prediction model by using the sample data in the training set to obtain a first cell average price pre-estimation model; and testing the first cell average price estimation model by using the test set until a preset condition (for example, the error rate of model prediction is less than 10%) is met.
The multivariate gray-scale correlation prediction model formula in this embodiment is as follows:
wherein,representing a first order accumulation of the i-attributes of sequence X, k representing the kth data item,representing the first order cumulative estimate of the (k + 1) th term, a, b are parameters,the derivative of the first order accumulation is indicated.
According to the method for estimating the average price of the residential area, the historical listing price and the historical transaction price of each house source of the target residential area are obtained, the historical listing/transaction prices of each house source are analyzed and processed, the historical listing/transaction average price of the target residential area is calculated, and the accuracy of the historical listing/transaction average price of the target residential area is improved; and estimating the average price of the target cell by using the first cell average price estimation model based on the historical listing/bargaining average price of the target cell, thereby being beneficial to improving the accuracy of estimation of the average price of the cell.
Referring to fig. 2, a flow chart of a method for estimating average cell price according to another preferred embodiment of the present invention is shown. In this embodiment, the method includes: steps S1-S4. The contents of steps S1-S3 are the same as those in the above embodiments, and are not described herein again.
S4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
And the second average price is a secondary estimation result of the average price of the target cell, and the second average price in the estimation result is sent to the user through the client.
The training step of the second cell average price pre-estimation model is substantially the same as the training step of the first cell average price pre-estimation model, and the difference is that: x in the sample data is the historical trading average price, the historical listing average price and the first average price of a plurality of specified cells in a specified time interval (2017.12-2018.7). The first average price of the designated cells in the designated time interval is determined by the first cell average price pre-estimation model, which is not described herein again.
In the above embodiments, the historical deal price, the historical listing average price, and the like all refer to unit prices, not total prices.
In the method for estimating the average price of the target cell provided by the embodiment, the historical listing average price, the historical bargain average price and the first average price of the target cell are input into the second cell average price estimation model to perform secondary estimation on the target cell, so that the prediction result of the first cell estimation model is converged, and the accuracy of estimating the average price of the target cell is improved.
The invention also provides an electronic device.
Fig. 3 is a schematic diagram of an electronic device 1 according to a preferred embodiment of the invention.
In this embodiment, the electronic device 1 may be a server, a smart phone, a tablet computer, a portable computer, a desktop computer, or other terminal equipment with a data processing function, where the server may be a rack server, a blade server, a tower server, or a cabinet server.
The electronic device 1 includes a memory 11, a processor 12, and a network interface 13.
The memory 11 includes at least one type of readable storage medium, which includes a 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, and the like. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic apparatus 1 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic apparatus 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic apparatus 1.
The memory 11 may be used for storing not only the application software and various data installed in the electronic device 1, such as the cell average price estimation program 10, but also temporarily storing data that has been output or will be output.
The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip in some embodiments, and is used for running program codes stored in the memory 11 or Processing data, such as the cell average price estimation program 10.
The network interface 13 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the electronic apparatus 1 and other electronic devices. For example, the electronic device 1 receives a cell average price estimation request sent by a client (not shown in the figure) through the network interface 13, and feeds back an estimation result to the client through the network interface 13.
Fig. 3 only shows the electronic device 1 with the components 11-13, and it will be understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
Optionally, the electronic device 1 may further comprise a user interface, the user interface may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further comprise a standard wired interface, a wireless interface.
Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-controlled liquid crystal display, an Organic Light-Emitting Diode (OLED) touch screen, or the like. The display, which may also be referred to as a display screen or display unit, is used for displaying information processed in the electronic apparatus 1 and for displaying a visualized user interface.
In the embodiment of the electronic device 1 shown in fig. 3, the memory 11 as a computer storage medium stores the program code of the cell average price estimation program 10, and the processor 12 executes the program code of the cell average price estimation program 10 to implement the following steps:
a1, receiving a mean price estimation request based on a target cell, and acquiring a history record of the target cell in a preset time from a preset channel, wherein the history record comprises: history listing record and history transaction record.
The user submits a prediction request through the client, wherein the request comprises prediction targets: the target cell is equalized.
The preset channels in different cities may be different, and taking Shenzhen as an example, the preset channels include: chaine, szhome, zhongyuan, hometown, search house and other platforms.
Prior to step a1, the method further comprises: and presetting the priority levels of the plurality of preset channels. The priority of each channel is established by experts according to the credibility of each channel data, for example, the priority of the above 5 channels is: chain family > szhome > Zhongyuan > Jiajiashun > search for houses.
And the history records crawled from the preset channels are history listing records/history transaction records corresponding to different house sources in different cells.
In this embodiment, step a1 includes: acquiring a history record of a designated area within preset time from a preset channel; and acquiring the description information of each historical record, and determining the historical record corresponding to the target cell according to the mapping relation between the predetermined description information and the cell.
The designated area includes the target cell, and the designated area is generally xx city xx area.
The description information includes location information describing the geographical location of the house source, for example, xx unit xx building xx number in xx district xx road xx period xx in xx city xx. And determining all history records corresponding to the target cell by using the description information of all history records.
All the history records corresponding to the target cell are history records corresponding to a plurality of house sources in the target cell.
And A2, respectively calculating the historical listing average price and the historical trading average price of the target cell in the preset time based on a preset analysis rule and the historical record.
In this embodiment, step a2 includes:
respectively determining historical records corresponding to all house sources in the target cell according to the description information;
analyzing and determining the historical listing price and the historical trading price of each house source in the target cell within preset time; and
and calculating the historical listing average price and the historical bargaining average price of the target cell in the preset time.
The historical listing average price and the historical transaction average price of the target cell are closely related to the historical listing price and the historical transaction price of each set of house resources in the target cell. Therefore, firstly, the historical listing record and the historical deal record corresponding to each house source in the target cell are determined, then the historical listing price and the historical deal price of each house source are respectively determined, and finally, the historical listing average price and the historical deal average price of the target cell are calculated.
It should be noted that the present invention does not require the same house source to have both history listing records and history transaction records.
Preferably, the step of analyzing and determining the historical listing price and the historical trading price of each house source in the target cell within a preset time includes:
when the same house source in the target cell corresponds to a history listing record/history transaction record, reading the history listing price and the history transaction price in the history listing record/history transaction record as the history listing price and the history transaction price of the house source;
when the same house source in the target cell corresponds to a plurality of history listing records, acquiring a plurality of history listing prices corresponding to the plurality of history listing records;
when the plurality of historical listing prices are consistent, any one historical listing price is reserved as the historical listing price of the house source; or
And when the plurality of historical listing prices are inconsistent, taking the person with the highest channel priority as the historical listing price of the house source.
Assuming that a certain house source of a target cell is listed on 5 channels at the same time, 5 history listing records exist in the house source, namely the house source has 5 history listing prices. And when the 5 historical listing prices are the same, taking any one historical listing price as the historical listing price of the house source. And when the historical listing prices of the 5 house sources are different, acquiring the channel priority corresponding to each historical listing price, and selecting the historical listing price corresponding to the highest channel priority as the historical listing price of the house source.
In general, the same house source only corresponds to one historical transaction record, so that duplicate removal processing is not needed.
Through carrying out duplicate removal processing on the history records of all house sources in the target cell, a foundation is laid for the subsequent calculation of the historical listing average price and the historical bargaining average price of the target cell.
Preferably, the step of "calculating the historical listing average price and the historical bargaining average price of the target cell in the preset time" in this embodiment includes:
calculating the cell historical average price of a target cell within preset time, and respectively calculating the historical listing price of each house source in the target cell within the preset time and the deviation between a plurality of historical transaction prices and the cell historical average price;
filtering out historical listing prices with deviation larger than a first preset threshold value, and filtering out historical deal prices with deviation larger than a second preset threshold value; and
and respectively calculating the historical listing average price and the historical bargaining average price of the target cell at the t-th period according to the reserved historical listing price and the historical bargaining price.
Taking the target cell P as an example, the historical listing prices and the historical trading prices of a plurality of house sources in the cell P in the same period are different. In order to remove abnormal values in the historical listing price and the historical transaction price of the cell P, for example, when the price is too high or too low, the deviation between the historical listing price and the historical transaction price of each house source in the cell P and the historical average price of the cell P needs to be determined, data with the deviation exceeding a preset range (for example, 40% and 30% are respectively used as a first preset threshold and a second preset threshold) is filtered, and then the remaining historical listing price and the historical transaction price are respectively averaged to obtain the historical listing average price and the historical transaction average price of the cell P in the previous month.
The first preset threshold and the second preset threshold can be adjusted according to requirements.
The historical listing prices and the historical trading average prices of a plurality of house sources in the target cell are filtered, so that a foundation is laid for accurately calculating the historical listing average prices and the historical trading average prices of the target cell.
Preferably, the cell historical average price is calculated according to the cell historical price of the target cell in the last month in a plurality of preset channels, and the cell historical price is directly obtained from the plurality of channels. In this embodiment, the step of calculating the cell history average price of the target cell within the preset time includes:
acquiring n cell historical prices of a target cell within preset time, and respectively calculating the discrete degrees of the n cell historical prices;
if the discrete degree meets a first preset condition, directly taking the average value of the historical prices of the n cells as the historical average price of the target cell within preset time; or
If the discrete degree does not meet the first preset condition, the maximum value and the minimum value in the historical prices of the n cells are removed, and the average value of the historical prices of the remaining (n-2) cells is taken as the historical average price of the target cell in the preset time.
Wherein n is the number of the preset channels. For example, the first preset condition may be: the relative standard deviations of the historical prices of the n cells are all less than or equal to 10%. The degree of dispersion of the n cell historical prices can be expressed in relative standard deviations. The discrete degree of the historical prices of the n cells is determined by calculating the relative standard deviation of the historical prices of the n cells, and the historical average price of the target cell in the last month is further calculated, so that the accuracy of the historical average price of the target cell is improved, and a foundation is laid for accurately estimating the average price of the cell.
However, in the process of acquiring the historical cell price data of the target cell in the last month from n preset channels, a situation that market data is missing may occur, that is, there may be no historical cell price data of the target cell in the last month in a certain channel. In this case, the cell history price corresponding to the highest priority one of the plurality of channels in which the cell history price of the target cell in the previous month exists is taken as the cell history price of the target cell in the previous month.
And A3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
Inputting the historical listing average price and the historical trading average price of the target cell in the previous month obtained in the above steps into a first cell average price estimation model, wherein the result output by the model is the predicted current cell average price of the target cell, and then sending the first average price in the estimation result to a user through a client.
In this embodiment, the first cell average price estimation model is obtained by training based on a multivariate gray-scale correlation prediction model, and the model training step includes:
determining sample data: acquiring historical listing average prices, historical bargaining average prices and cell historical average prices of a plurality of specified cells in a specified time interval (2017.12-2018.7) to generate sample data [ X, Y ];
for example, X ═ X [ (X)1a，x1b)，(x2a，x2b)，...，(xia，xib)]，Y＝[Y1，Y2，...，Yi]Wherein x isiaRepresenting a historical average bid, x, for six consecutive months (adjustable length of time series) for a given cell i within 2017.12-2018.7ibIndicating six consecutive months (time) within 2017.12-2018.7 for a given cell iAdjustable length of sequence) and xia，xibTime sequences corresponding to the historical listing average price and the historical bargaining average price are formed; y isiIndicating the cell history mean price for six consecutive months (time series consistent with X) for the given cell within 2017.12-2018.7. The calculation steps of the historical listing average price, the historical bargain average price and the cell historical average price are substantially the same as the steps described above, and are not described herein again.
Model training: dividing the sample data [ X, Y ] into a training set and a test set according to time (for example, sample data of two months close to the current time is used as the test set, and the rest sample data is used as the training set), and training the multivariate gray level correlation prediction model by using the sample data in the training set to obtain a first cell average price pre-estimation model; and testing the first cell average price estimation model by using the test set until a preset condition (for example, the error rate of model prediction is less than 10%) is met.
The multivariate gray-scale correlation prediction model formula in this embodiment is as follows:
wherein,representing a first order accumulation of the i-attributes of sequence X, k representing the kth data item,first order accumulation representing the (k + 1) th termAdding the estimated values, a and b are parameters,the derivative of the first order accumulation is indicated.
The electronic device 1 provided in the above embodiment analyzes and processes the historical listing/deal price of each house source by obtaining the historical listing price and the historical deal price of each house source in the target cell, calculates the historical listing/deal average price of the target cell, and improves the accuracy of the historical listing/deal average price of the target cell; and estimating the average price of the target cell by using the first cell average price estimation model based on the historical listing/bargaining average price of the target cell, thereby being beneficial to improving the accuracy of estimation of the average price of the cell.
In other embodiments, when executed by the processor, the cell average price estimator further performs the following steps:
and A4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
And the second average price is a secondary estimation result of the average price of the target cell, and the second average price in the estimation result is sent to the user through the client.
The training step of the second cell average price pre-estimation model is substantially the same as the training step of the first cell average price pre-estimation model, and the difference is that: x in the sample data is the historical trading average price, the historical listing average price and the first average price of a plurality of specified cells in a specified time interval (2017.12-2018.7). The first average price of the designated cells in the designated time interval is determined by the first cell average price pre-estimation model, which is not described herein again.
In the above embodiments, the historical deal price, the historical listing average price, and the like all refer to unit prices, not total prices.
The electronic device 1 provided in the above embodiment inputs the historical listing average price, the historical winning average price, and the first average price of the target cell into the second cell average price estimation model to perform secondary estimation on the target cell, and converges the prediction result of the first cell estimation model, thereby improving the accuracy of target cell average price estimation.
Alternatively, in other embodiments, the cell average price estimation program 10 can be further divided into one or more modules, and the one or more modules are stored in the memory 11 and executed by one or more processors (in this embodiment, the processor 12) to implement the present invention, where the modules referred to in the present invention refer to a series of computer program instruction segments capable of performing specific functions. For example, referring to fig. 4, a block diagram of a preferred embodiment of the cell mean price estimation procedure 10 in fig. 3 is shown.
In an embodiment of the cell average price estimation program 10, the cell average price estimation program 10 only includes the receiving module 110, the calculating module 120 and the first estimation module 130, wherein:
a receiving module 110, configured to receive a mean-price estimation request based on a target cell, and obtain a history of the target cell within a preset time from a preset channel;
a calculating module 120, configured to calculate a historical listing average price and a historical settlement average price of the target cell within a preset time based on a preset analysis rule and the historical record, respectively; and
the first estimation module 130 is configured to input the historical listing average price and the historical deal average price into a first cell average price estimation model obtained based on multi-variable gray-scale association prediction model training, so as to obtain a first average price of the target cell.
In another embodiment of the cell average price estimation program 10, the cell average price estimation program 10 may further include a second estimation module 140.
The functions or operation steps implemented by the modules 110 and 140 are similar to those described above and will not be described in detail here.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a cell average price estimation program 10, and when executed by a processor, the cell average price estimation program 10 implements the following operations:
a1, receiving a mean price estimation request based on a target cell, and acquiring a history record of the target cell in a preset time from a preset channel;
a2, respectively calculating the historical listing average price and the historical trading average price of the target cell in a preset time based on a preset analysis rule and the historical record; and
and A3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
Preferably, when executed by the processor, the cell average price estimation program further implements the following steps:
and A4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
The embodiment of the computer readable storage medium of the present invention is substantially the same as the embodiment of the above-mentioned cell average price estimation method, and will not be described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. The word "comprising", when used in this specification, does not exclude the presence of other elements, materials, or methods, or steps, other than those listed.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the present specification and drawings, and which are directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for estimating average price of a cell is applied to an electronic device, and is characterized by comprising the following steps:
s1, receiving a mean price estimation request based on a target cell, and acquiring historical records of the target cell in a preset time from a preset channel, wherein the historical records comprise historical listing records and historical transaction records;
s2, respectively calculating the historical listing average price and the historical trading average price of the target cell in the preset time based on a preset analysis rule and the historical record; and
and S3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
2. The method of claim 1, further comprising:
s4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
3. The method for estimating average price of cells according to any of claims 1 or 2, wherein the step S1 includes:
acquiring a historical record of a designated area within preset time from a preset channel; and
and acquiring the description information of each historical record, and determining the historical record corresponding to the target cell according to the mapping relation between the predetermined description information and the cell.
4. The method of claim 3, wherein the step S2 includes:
respectively determining historical records corresponding to all house sources in the target cell according to the description information;
analyzing and determining the historical listing price and the historical trading price of each house source in the target cell within preset time; and
and calculating the historical listing average price and the historical bargaining average price of the target cell in the preset time.
5. The method of claim 4, wherein the step of analyzing and determining the historical listing price and the historical trading price of each house source in the target cell within a preset time comprises:
when the same house source in the target cell corresponds to a historical listing record/historical transaction record, reading the historical listing/transaction price in the historical listing record/historical transaction record as the historical listing/transaction price of the house source;
when the same house source in the target cell corresponds to a plurality of history listing records, acquiring a plurality of history listing prices corresponding to the plurality of history listing records;
when the plurality of historical listing prices are consistent, any one historical listing price is reserved as the historical listing price of the house source; or
And when the plurality of historical listing prices are inconsistent, taking the person with the highest channel priority as the historical listing price of the house source.
6. The method according to claim 4, wherein the step of calculating the historical listing average price and the historical winning average price of the target cell within a preset time comprises:
calculating the cell historical average price of a target cell within preset time, and respectively calculating the historical listing price of each house source in the target cell within the preset time and the deviation between a plurality of historical transaction prices and the cell historical average price;
filtering out historical listing prices with deviation larger than a first preset threshold value, and filtering out historical deal prices with deviation larger than a second preset threshold value; and
and respectively calculating the historical listing average price and the historical bargaining average price of the target cell at the t-th period according to the reserved historical listing price and the historical bargaining price.
7. The method of claim 6, wherein the step of calculating the cell history average price of the target cell within a preset time comprises:
obtaining a plurality of cell historical prices of a target cell within a preset time, and respectively calculating the dispersion degree of the plurality of cell historical prices;
if the discrete degree meets a first preset condition, directly taking the average value of the historical prices of the plurality of cells as the historical average price of the target cell within preset time; or
And if the discrete degree does not meet the first preset condition, eliminating the maximum value and the minimum value in the historical prices of the plurality of cells, and taking the average value of the historical prices of the remaining cells as the historical average price of the target cell in preset time.
8. An electronic device, comprising: the storage is stored with a cell average price estimating program which can run on the processor, and when the cell average price estimating program is executed by the processor, the following steps can be realized:
a1, receiving a mean price estimation request based on a target cell, and acquiring a history record of the target cell in a preset time from a preset channel;
a2, respectively calculating the historical listing average price and the historical trading average price of the target cell in a preset time based on a preset analysis rule and the historical record; and
and A3, inputting the historical listing average price and the historical bargaining average price into a first cell average price estimation model obtained based on multivariate gray level correlation prediction model training to obtain a first average price of the target cell.
9. The electronic device of claim 8, wherein the cell average price estimator, when executed by the processor, further performs the steps of:
and A4, inputting the historical listing average price, the historical bargain average price and the first average price of the target cell in preset time into a second cell average price estimation model obtained based on wavelet neural network training to obtain a second average price of the target cell.
10. A computer-readable storage medium, comprising a cell average price estimation program, which when executed by a processor, can implement the steps of the cell average price estimation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811286728.XA CN109615412A (en) | 2018-10-31 | 2018-10-31 | Cell average price predictor method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811286728.XA CN109615412A (en) | 2018-10-31 | 2018-10-31 | Cell average price predictor method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109615412A true CN109615412A (en) | 2019-04-12 |
Family
ID=66002695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811286728.XA Pending CN109615412A (en) | 2018-10-31 | 2018-10-31 | Cell average price predictor method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109615412A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919866A (en) * | 2021-09-27 | 2022-01-11 | 北京字节跳动网络技术有限公司 | Model training method, advertisement putting method, device, equipment and storage medium |
-
2018
- 2018-10-31 CN CN201811286728.XA patent/CN109615412A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919866A (en) * | 2021-09-27 | 2022-01-11 | 北京字节跳动网络技术有限公司 | Model training method, advertisement putting method, device, equipment and storage medium |
| CN113919866B (en) * | 2021-09-27 | 2024-02-13 | 抖音视界有限公司 | Model training method, advertisement putting device, model training equipment, advertisement putting equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111782943B (en) | Information recommendation method, device, equipment and medium based on historical data record | |
| CN113032682B (en) | Collaborative filtering-based product recommendation method, device, equipment and storage medium | |
| WO2018103718A1 (en) | Application recommendation method and apparatus, and server | |
| CN110349039B (en) | Complaint risk assessment method, system, computer device and readable storage medium | |
| US20210035126A1 (en) | Data processing method, system and computer device based on electronic payment behaviors | |
| CN109756368B (en) | Method and device for detecting abnormal change of equipment, computer readable storage medium and terminal | |
| CN111177568B (en) | Object pushing method based on multi-source data, electronic device and storage medium | |
| US10909145B2 (en) | Techniques for determining whether to associate new user information with an existing user | |
| CN109615414A (en) | House property predictor method, device and storage medium | |
| CN110807547A (en) | Method and system for predicting family population structure | |
| KR101860457B1 (en) | Method for analyzing weather affect and apparatus for executing the method | |
| CN110610431A (en) | Intelligent claim settlement method and intelligent claim settlement system based on big data | |
| CN110766184A (en) | Order quantity prediction method and device | |
| CN108985501B (en) | Index feature extraction-based stock index prediction method, server and storage medium | |
| CN110969261B (en) | Encryption algorithm-based model construction method and related equipment | |
| CN114219664A (en) | Product recommendation method and device, computer equipment and storage medium | |
| US20190251604A1 (en) | Predicting after-rehab value of a real-estate property based on rehab-packages | |
| CN110659954A (en) | Cheating identification method and device, electronic equipment and readable storage medium | |
| CN107798125B (en) | Access judgment method, system, equipment and storage medium based on intimacy model | |
| CN109615412A (en) | Cell average price predictor method, electronic device and storage medium | |
| CN113094602A (en) | Hotel recommendation method, system, equipment and medium | |
| CN111784042A (en) | Power utilization node safety risk prediction method and device and storage medium | |
| CN109636437A (en) | Cell average price predictor method, electronic device and storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| Carstens et al. | Navigating the unknown: model selection in phylogeography: Models of population structure: tools for thinkers |
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: 20190412 |
|
| WD01 | Invention patent application deemed withdrawn after publication |