CN110717841A - Sunshine analysis method, device, equipment and storage medium based on AutoEncoder - Google Patents
Sunshine analysis method, device, equipment and storage medium based on AutoEncoder Download PDFInfo
- Publication number
- CN110717841A CN110717841A CN201910959028.0A CN201910959028A CN110717841A CN 110717841 A CN110717841 A CN 110717841A CN 201910959028 A CN201910959028 A CN 201910959028A CN 110717841 A CN110717841 A CN 110717841A
- Authority
- CN
- China
- Prior art keywords
- building
- training
- autoencoder
- sunshine analysis
- analyzed
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 142
- 238000012549 training Methods 0.000 claims description 105
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a sunshine analysis method, a device, equipment and a storage medium based on an AutoEncode, wherein the sunshine analysis method based on the AutoEncode comprises the following steps: responding to the sunshine analysis request, and acquiring a building picture to be analyzed; convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset; through the Decoder in the preset AutoEncoder model, right wait to analyze the building characteristic and carry out the deconvolution, obtain wait to analyze the sunshine analysis result that the building characteristic corresponds, solved current sunshine analysis to the building and consumed time technical problem of a long time.
Description
Technical Field
The application relates to the technical field of sunshine analysis, in particular to a sunshine analysis method, a sunshine analysis device, sunshine analysis equipment and a storage medium based on an AutoEncoder.
Background
With the rapid development of the industrialization process, the city construction is rapidly promoted. The good sunshine condition is not only a reference factor for people to shop for buildings, but also a consideration factor for pricing of developers. Therefore, it is important to accurately calculate the sunshine duration of the building.
The prior building industry mostly adopts sunshine analysis software, and the method has the following defects: after a building information file is input, the sunshine duration of a building can be calculated only by clicking the running software for dozens of seconds to several minutes, and the calculation time is too long.
Disclosure of Invention
In view of this, the present application provides a sunshine analysis method, apparatus, device and storage medium based on an AutoEncoder, which solves the technical problem that the sunshine analysis of the existing building takes a long time.
The application provides a sunshine analysis method based on an AutoEncoder in a first aspect, which comprises the following steps:
responding to the sunshine analysis request, and acquiring a building picture to be analyzed;
convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset;
and carrying out deconvolution on the characteristics of the building to be analyzed through a Decoder in the preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
Optionally, the method further comprises:
responding to a model training request, and acquiring an AutoEncoder neural network, a training building picture and an actual sunshine analysis result corresponding to the training building picture;
the AutoEncoder neural network is used as a training network, the training building picture is used as an input parameter of the training network, and a training sunshine analysis result corresponding to the training building picture is obtained;
and adjusting the network parameters of the training network according to the error between the actual sunshine analysis result and the training sunshine analysis result, and determining a new training sunshine analysis result based on the adjusted training network until the error between the actual sunshine analysis result and the new training sunshine analysis result is smaller than a preset error threshold value, so as to obtain the preset AutoEncoder model.
Optionally, the acquiring of the training sunshine analysis result corresponding to the training building picture specifically includes:
and calculating a training sunshine analysis result corresponding to the training building picture based on sunshine analysis software.
Optionally, before the acquiring a picture of a building to be analyzed in response to the sunshine analysis request, the method further includes:
and converting the building file to be analyzed in the CAD format into the building file to be analyzed in the picture format to obtain the building picture to be analyzed.
Optionally, the sunshine analysis result specifically includes: sun length shadow label.
The second aspect of the present application provides a sunshine analytical equipment based on AutoEncoder, includes:
the first acquisition unit is used for responding to the sunshine analysis request and acquiring a building picture to be analyzed;
the first calculation unit is used for convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset;
and the second calculation unit is used for carrying out deconvolution on the characteristics of the building to be analyzed through a Decoder in the preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
Optionally, the method further comprises:
the second acquisition unit is used for responding to a model training request and acquiring an AutoEncoder neural network, a training building picture and an actual sunlight analysis result corresponding to the training building picture;
the third calculation unit is used for taking the AutoEncoder neural network as a training network and the training building picture as an input parameter of the training network to obtain a training sunshine analysis result corresponding to the training building picture;
and the adjusting unit is used for adjusting the network parameters of the training network according to the actual sunshine analysis result and the error between the training sunshine analysis results, and determining a new training sunshine analysis result based on the adjusted training network until the actual sunshine analysis result and the error between the new training sunshine analysis results are smaller than a preset error threshold value, so that the preset AutoEncoder model is obtained.
Optionally, the method further comprises:
and the format conversion unit is used for converting the building file to be analyzed in the CAD format into the building file to be analyzed in the picture format to obtain the building picture to be analyzed.
The third aspect of the present application provides an sunshine analytical equipment based on an AutoEncoder based on the AutoEncoder, including: a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the sunshine analysis method based on the AutoEncoder according to the instruction of the program code.
A fourth aspect of the present application provides a storage medium for storing a program code for executing the sunshine analysis method based on the AutoEncoder of the first aspect.
According to the technical scheme, the method has the following advantages:
the application provides a sunshine analysis method based on an AutoEncoder, which comprises the following steps: responding to the sunshine analysis request, and acquiring a building picture to be analyzed; convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset; and performing deconvolution on the characteristics of the building to be analyzed through a Decoder in a preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
The traditional sunshine analysis software needs to perform a large amount of calculation again to obtain a sunshine analysis result every time one building picture to be analyzed is input, and the time is about tens of seconds to several minutes. In the application, the building picture to be analyzed can be subjected to convolution and deconvolution according to the preset AutoEncoder model, namely, the feature extraction and the operation of the sunshine analysis result according to the extracted features are respectively realized. The preset AutoEncoder model is preset at the moment, the sunshine analysis result can be quickly obtained by inputting the picture of the building to be analyzed to the model, the consumed time is about 50ms to 500ms, the calculation consumed time is greatly reduced compared with the prior consumed time, and the technical problem that the prior sunshine analysis of the building consumes longer time is solved.
Drawings
Fig. 1 is a schematic flow chart of a sunshine analysis method based on an AutoEncoder in an embodiment of the present application;
FIG. 2 is a schematic structural diagram of an Encoder Encoder in which an AutoEncoder model is preset in the embodiment of the present application;
FIG. 3 is a schematic structural diagram of a Decoder with preset AutoEncoder model in the embodiment of the present application;
fig. 4 is a schematic flow chart of a second embodiment of the sunshine analysis method based on the AutoEncoder in the embodiment of the present application;
FIG. 5 is a picture of a training building according to the second embodiment of the present application;
FIG. 6 is a graph showing the results of sunshine analysis in the training of the second embodiment of the present application;
FIG. 7 is a graph showing the results of actual sunshine analysis in example two of the present application;
fig. 8 is a schematic structural diagram of an embodiment of a sunshine analysis method and apparatus based on an AutoEncoder in the embodiment of the present application.
Detailed Description
In view of this, the embodiment of the present application provides a sunshine analysis method, apparatus, device and storage medium based on an AutoEncoder, which solve the technical problem that the sunshine analysis of a building takes a long time in the prior art.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art without any inventive work according to the embodiments of the present application are within the scope of the present application.
To facilitate understanding, please refer to fig. 1, where fig. 1 is a schematic flow diagram of a first embodiment of a sunshine analysis method based on an AutoEncoder in the embodiment of the present application, and as shown in fig. 1, the method specifically includes:
and step 101, responding to the sunshine analysis request, and acquiring a building picture to be analyzed.
It should be noted that, in this embodiment, when performing sunshine analysis on a building to be analyzed, a picture of the building to be analyzed corresponding to the building to be analyzed is first obtained.
It is understood that the building to be analyzed may be already built, and may also be to be built, and this embodiment is not limited in this respect. For the building to be analyzed after being built, the picture of the building to be analyzed can be obtained after being shot by a camera, and for the building to be analyzed to be built, the picture of the building to be analyzed can be drawn, and the like.
And 102, convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset.
It should be noted that after the building picture to be analyzed is acquired, the building picture to be analyzed is input to an Encoder of a preset autoencor model shown in fig. 2, so that the Encoder performs convolution on the building picture to be analyzed, and the building feature to be analyzed corresponding to the building to be analyzed is obtained.
And 103, deconvoluting the characteristics of the building to be analyzed through a Decoder in a preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
It should be noted that after the building features to be analyzed are obtained, the building features to be analyzed are input to a Decoder of a preset AutoEncoder model shown in fig. 3, so that the ecoder Decoder performs deconvolution on the building features to be analyzed, and a sunshine analysis result corresponding to the building features to be analyzed, that is, a sunshine analysis result of a building picture to be analyzed is obtained.
The traditional sunshine analysis software needs to perform a large amount of calculation again to obtain a sunshine analysis result every time one building picture to be analyzed is input, and the time is about tens of seconds to several minutes. In the application, the building picture to be analyzed can be subjected to convolution and deconvolution according to the preset AutoEncoder model, namely, the feature extraction and the operation of the sunshine analysis result according to the extracted features are respectively realized. The preset AutoEncoder model is preset at the moment, the sunshine analysis result can be quickly obtained by inputting the picture of the building to be analyzed to the model, the consumed time is about 50ms to 500ms, the calculation consumed time is greatly reduced compared with the prior consumed time, and the technical problem that the prior sunshine analysis of the building consumes longer time is solved.
The above is an embodiment one of the sunshine analysis method based on the AutoEncoder provided in the embodiment of the present application, and the following is an embodiment two of the sunshine analysis method based on the AutoEncoder provided in the embodiment of the present application.
Referring to fig. 4, fig. 4 is a schematic flow chart of a second embodiment of the sunshine analysis method based on the AutoEncoder in the embodiment of the present application, as shown in fig. 4, specifically including:
It should be noted that the preset AutoEncoder model is obtained by training an AutoEncoder neural network, and before the AutoEncoder neural network is trained, the AutoEncoder neural network, a training building picture and an actual sunshine analysis result corresponding to the training building picture are obtained first.
It can be understood that the actual sunshine analysis result may be calculated based on sunshine analysis software, or may be calculated in other manners such as actual measurement or simulation, which are not described in this embodiment one by one, and the picture of the training building in this embodiment is shown in fig. 5, and after the picture is analyzed by the sunshine analysis software, the actual sunshine analysis result is shown in a shaded portion in a black square in fig. 6.
And step 402, taking the AutoEncoder neural network as a training network and the training building picture as an input parameter of the training network to obtain a training sunshine analysis result corresponding to the training building picture.
It should be noted that, the calculation of the training sunshine analysis result on the training building picture is also realized after the convolution by the Encoder and the deconvolution by the Decoder, and the process is the same as the related description in the building picture to be analyzed, which may be specifically referred to the above description, and is not repeated herein.
After the training building picture is calculated through the AutoEncoder neural network, the obtained training sunshine analysis result is shown as the shadow area of the black square in fig. 7, namely, the dark shadow color of the shadow area corresponds to the sunshine duration shadow label output by the AutoEncoder neural network, and the shorter the sunshine duration is.
And 403, adjusting network parameters of the training network according to the error between the actual sunshine analysis result and the training sunshine analysis result, and determining a new training sunshine analysis result based on the adjusted training network until the error between the actual sunshine analysis result and the new training sunshine analysis result is smaller than a preset error threshold value, so as to obtain a preset AutoEncoder model.
It should be noted that after the results shown in fig. 6 and 7 are obtained, the network parameters of the training network are adjusted according to the error between the actual sunshine analysis result and the training sunshine analysis result, and the new training sunshine analysis result is determined based on the adjusted training network until the error between the actual sunshine analysis result and the new training sunshine analysis result is smaller than the preset error threshold, so as to obtain the preset AutoEncoder model, which can improve the calculation accuracy of the sunshine analysis result obtained by the sunshine analysis method based on the AutoEncoder in this embodiment.
And when the error between the actual sunshine analysis result and the new training sunshine analysis result is smaller than a preset error threshold value, the new training sunshine analysis result is close to the actual sunshine analysis result, and therefore the training network at the moment is used as a preset AutoEncoder model.
It will be appreciated that the network parameters of the adjusted training network may include parameters of an Encoder and/or parameters of a Decoder.
It should be noted that, for the building file to be analyzed in the CAD format, the building file to be analyzed in the CAD format may be converted into the building file to be analyzed in the picture format through format conversion, so as to obtain a building picture to be analyzed, and the processing object of the sunshine analysis method based on the AutoEncoder in this embodiment is augmented.
And 405, responding to the sunshine analysis request, and acquiring a building picture to be analyzed.
It should be noted that the description of step 405 in this embodiment is the same as the description of step 101 in the first embodiment, and reference may be specifically made to the description of step 101, which is not repeated herein.
And 406, performing convolution on the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed.
It should be noted that the description of step 406 in this embodiment is the same as the description of step 102 in the first embodiment, and reference may be specifically made to the description of step 102, which is not repeated herein.
And 407, deconvoluting the characteristics of the building to be analyzed through a Decoder in a preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
It should be noted that the description of step 407 in this embodiment is the same as the description of step 103 in the first embodiment, and reference may be specifically made to the description of step 103, which is not repeated herein.
The traditional sunshine analysis software needs to perform a large amount of calculation again to obtain a sunshine analysis result every time one building picture to be analyzed is input, and the time is about tens of seconds to several minutes. In the application, the building picture to be analyzed can be subjected to convolution and deconvolution according to the preset AutoEncoder model, namely, the feature extraction and the operation of the sunshine analysis result according to the extracted features are respectively realized. The preset AutoEncoder model is preset at the moment, the sunshine analysis result can be quickly obtained by inputting the picture of the building to be analyzed to the model, the consumed time is about 50ms to 500ms, the calculation consumed time is greatly reduced compared with the prior consumed time, and the technical problem that the prior sunshine analysis of the building consumes longer time is solved.
The second embodiment of the sunshine analysis method based on the AutoEncoder provided by the embodiment of the present application is as follows.
Referring to fig. 8, fig. 8 is a schematic structural diagram of an embodiment of a sunshine analyzing apparatus based on an AutoEncoder in the embodiment of the present application, as shown in fig. 8, the sunshine analyzing apparatus specifically includes:
a first obtaining unit 801, configured to obtain a building picture to be analyzed in response to a sunshine analysis request;
the first calculating unit 802 is configured to perform convolution on a building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain a building feature to be analyzed, where the preset AutoEncoder model is preset;
and the second calculating unit 803 is configured to perform deconvolution on the building characteristics to be analyzed through a Decoder in the preset AutoEncoder model, so as to obtain a sunshine analysis result corresponding to the building characteristics to be analyzed.
Further, still include:
the second acquisition unit is used for responding to the model training request and acquiring the AutoEncoder neural network, the training building picture and the actual sunshine analysis result corresponding to the training building picture;
the third calculation unit is used for taking the AutoEncoder neural network as a training network and the training building picture as an input parameter of the training network to obtain a training sunshine analysis result corresponding to the training building picture;
and the adjusting unit is used for adjusting network parameters of the training network according to the error between the actual sunshine analysis result and the training sunshine analysis result, determining a new training sunshine analysis result based on the adjusted training network until the error between the actual sunshine analysis result and the new training sunshine analysis result is smaller than a preset error threshold value, and obtaining a preset AutoEncoder model.
Further, still include:
and the format conversion unit is used for converting the building file to be analyzed in the CAD format into the building file to be analyzed in the picture format to obtain the building picture to be analyzed.
The traditional sunshine analysis software needs to perform a large amount of calculation again to obtain a sunshine analysis result every time one building picture to be analyzed is input, and the time is about tens of seconds to several minutes. In the application, the building picture to be analyzed can be subjected to convolution and deconvolution according to the preset AutoEncoder model, namely, the feature extraction and the operation of the sunshine analysis result according to the extracted features are respectively realized. The preset AutoEncoder model is preset at the moment, the sunshine analysis result can be quickly obtained by inputting the picture of the building to be analyzed to the model, the consumed time is about 50ms to 500ms, the calculation consumed time is greatly reduced compared with the prior consumed time, and the technical problem that the prior sunshine analysis of the building consumes longer time is solved.
This embodiment also provides a sunshine analytical equipment based on AutoEncoder, includes: the storage is used for storing the program codes and transmitting the program codes to the processor; the processor is used for executing the sunshine analysis method based on the AutoEncode in the first embodiment or the second embodiment according to the instruction of the program code.
The embodiment of the application further provides a storage medium, wherein the storage medium is used for storing a program code, and the program code is used for executing the sunshine analysis method based on the AutoEncoder in the first embodiment or the second embodiment.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another grid network to be installed, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. With such an understanding, the technical solution of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A sunshine analysis method based on an AutoEncoder is characterized by comprising the following steps:
responding to the sunshine analysis request, and acquiring a building picture to be analyzed;
convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset;
and carrying out deconvolution on the characteristics of the building to be analyzed through a Decoder in the preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
2. The sunshine analysis method based on the AutoEncoder according to claim 1, further comprising:
responding to a model training request, and acquiring an AutoEncoder neural network, a training building picture and an actual sunshine analysis result corresponding to the training building picture;
the AutoEncoder neural network is used as a training network, the training building picture is used as an input parameter of the training network, and a training sunshine analysis result corresponding to the training building picture is obtained;
and adjusting the network parameters of the training network according to the error between the actual sunshine analysis result and the training sunshine analysis result, and determining a new training sunshine analysis result based on the adjusted training network until the error between the actual sunshine analysis result and the new training sunshine analysis result is smaller than a preset error threshold value, so as to obtain the preset AutoEncoder model.
3. The sunshine analysis method based on the AutoEncoder according to claim 2, wherein the obtaining of the training sunshine analysis result corresponding to the training building picture specifically comprises:
and calculating a training sunshine analysis result corresponding to the training building picture based on sunshine analysis software.
4. The sunshine analysis method based on the AutoEncoder according to claim 1, wherein before acquiring the building picture to be analyzed in response to the sunshine analysis request, the method further comprises:
and converting the building file to be analyzed in the CAD format into the building file to be analyzed in the picture format to obtain the building picture to be analyzed.
5. The sunshine analysis method based on the AutoEncoder according to claim 1, wherein the sunshine analysis result specifically comprises: sun length shadow label.
6. A sunshine analyzing device based on an AutoEncoder is characterized by comprising:
the first acquisition unit is used for responding to the sunshine analysis request and acquiring a building picture to be analyzed;
the first calculation unit is used for convolving the building picture to be analyzed through an Encoder in a preset AutoEncoder model to obtain the characteristics of the building to be analyzed, wherein the preset AutoEncoder model is preset;
and the second calculation unit is used for carrying out deconvolution on the characteristics of the building to be analyzed through a Decoder in the preset AutoEncoder model to obtain a sunshine analysis result corresponding to the characteristics of the building to be analyzed.
7. The sunshine analysis apparatus based on an AutoEncoder according to claim 6, further comprising:
the second acquisition unit is used for responding to a model training request and acquiring an AutoEncoder neural network, a training building picture and an actual sunlight analysis result corresponding to the training building picture;
the third calculation unit is used for taking the AutoEncoder neural network as a training network and the training building picture as an input parameter of the training network to obtain a training sunshine analysis result corresponding to the training building picture;
and the adjusting unit is used for adjusting the network parameters of the training network according to the actual sunshine analysis result and the error between the training sunshine analysis results, and determining a new training sunshine analysis result based on the adjusted training network until the actual sunshine analysis result and the error between the new training sunshine analysis results are smaller than a preset error threshold value, so that the preset AutoEncoder model is obtained.
8. The sunshine analysis apparatus based on an AutoEncoder according to claim 6, further comprising:
and the format conversion unit is used for converting the building file to be analyzed in the CAD format into the building file to be analyzed in the picture format to obtain the building picture to be analyzed.
9. The utility model provides a sunshine analytical equipment based on AutoEncode which characterized in that includes: a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the AutoEncoder-based sunshine analysis method according to any one of claims 1 to 5 according to instructions of the program code.
10. A storage medium characterized by storing a program code for executing the AutoEncoder-based sunshine analysis method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910959028.0A CN110717841A (en) | 2019-10-10 | 2019-10-10 | Sunshine analysis method, device, equipment and storage medium based on AutoEncoder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910959028.0A CN110717841A (en) | 2019-10-10 | 2019-10-10 | Sunshine analysis method, device, equipment and storage medium based on AutoEncoder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110717841A true CN110717841A (en) | 2020-01-21 |
Family
ID=69211357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910959028.0A Pending CN110717841A (en) | 2019-10-10 | 2019-10-10 | Sunshine analysis method, device, equipment and storage medium based on AutoEncoder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110717841A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664953A (en) * | 2018-05-23 | 2018-10-16 | 清华大学 | A kind of image characteristic extracting method based on convolution self-encoding encoder model |
| CN109409014A (en) * | 2018-12-10 | 2019-03-01 | 福州大学 | The calculation method of shining time per year based on BP neural network model |
| CN110174714A (en) * | 2019-05-24 | 2019-08-27 | 南京大学 | Street spacial sight sunshine time mass measurement method and system based on machine learning |
-
2019
- 2019-10-10 CN CN201910959028.0A patent/CN110717841A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664953A (en) * | 2018-05-23 | 2018-10-16 | 清华大学 | A kind of image characteristic extracting method based on convolution self-encoding encoder model |
| CN109409014A (en) * | 2018-12-10 | 2019-03-01 | 福州大学 | The calculation method of shining time per year based on BP neural network model |
| CN110174714A (en) * | 2019-05-24 | 2019-08-27 | 南京大学 | Street spacial sight sunshine time mass measurement method and system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112465748B (en) | Crack identification method, device, equipment and storage medium based on neural network | |
| CN112857669B (en) | Fault detection method, device and equipment of pressure sensor and storage medium | |
| CN110874591B (en) | Image positioning method, device, equipment and storage medium | |
| CN111650453A (en) | Power equipment diagnosis method and system based on windowing characteristic Hilbert imaging | |
| CN110728333B (en) | Sunshine duration analysis method and device, electronic equipment and storage medium | |
| CN116167932A (en) | Image quality optimization method, device, equipment and storage medium | |
| CN115660233A (en) | Photovoltaic power prediction method and device, electronic equipment and storage medium | |
| CN112613425B (en) | Target identification system for small sample underwater image | |
| CN110717841A (en) | Sunshine analysis method, device, equipment and storage medium based on AutoEncoder | |
| CN116152609B (en) | Distributed model training method, system, device and computer readable medium | |
| CN109285160B (en) | Image matting method and system | |
| CN108427742B (en) | Power distribution network reliability data restoration method and system based on low-rank matrix | |
| CN112380967B (en) | Spatial artificial target spectrum unmixing method and system based on image information | |
| CN115345832A (en) | Image detection model training method and device and readable storage medium | |
| CN113505844A (en) | Label generation method, device, equipment, storage medium and program product | |
| CN114170515A (en) | Power distribution network equipment abnormity type detection method | |
| CN112651987A (en) | Method and system for calculating grassland coverage of sample | |
| CN113656279B (en) | Code odor detection method based on residual network and metric attention mechanism | |
| CN112990304B (en) | Semantic analysis method and system suitable for power scene | |
| CN114638851B (en) | Image segmentation method, system and storage medium based on generation countermeasure network | |
| CN113158632B (en) | Table reconstruction method for CAD drawing and computer readable storage medium | |
| CN112019839A (en) | Android smart television application automatic testing method | |
| CN115309808A (en) | Big data analysis method and system based on artificial intelligence | |
| CN117197479A (en) | Image analysis method, device, computer equipment and storage medium applying corn ear outer surface | |
| CN115690103A (en) | Product appearance detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |