CN115186954A

CN115186954A - Green technology selection aid decision-making method and system based on multiple models

Info

Publication number: CN115186954A
Application number: CN202210402869.3A
Authority: CN
Inventors: 马杰; 李国建; 袁琦; 张翔; 张露露
Original assignee: Suzhou Zhierzhuo Digital Technology Co ltd; Suzhou Sicui Integrated Infrastructure Technology Research Institute Co ltd
Current assignee: Suzhou Zhierzhuo Digital Technology Co ltd; Suzhou Sicui Integrated Infrastructure Technology Research Institute Co ltd
Priority date: 2022-04-18
Filing date: 2022-04-18
Publication date: 2022-10-14

Abstract

The embodiment of the specification provides a green technology selection method and a green technology selection system based on a plurality of models, which belong to the technical field of green buildings, and the method comprises the steps of obtaining relevant information of a building project to be decided; acquiring technology related information of various green technologies; for each green technology, determining a model through the applicability corresponding to the green technology, and judging whether the green technology is suitable for the building project to be decided or not based on the relevant information of the building project to be decided and the technology relevant information of the green technology; if the applicability determination model judges that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model corresponding to the green technology; and determining at least one target green technology applied to the building project to be decided from the multiple green technologies based on the recommendation scores of the multiple green technologies.

Description

Green technology selection aid decision-making method and system based on multiple models

Technical Field

The specification relates to the field of green buildings, in particular to a green technology selection assistant decision-making method and system based on multiple models.

Background

The green technology is also called an environment-friendly technology or an ecological technology, and is a general term for technologies, processes or products for reducing environmental pollution, and reducing use of raw materials, natural resources and energy. In the design, construction and reconstruction of buildings, a great number of green technologies can be adopted, and simple technology stacking does not produce ideal economic benefit and cannot play the greatest role in the application process. Therefore, the decision of the green technology is particularly critical in the initial stage of the design stage, and the optimization of the green technology configuration can effectively improve the resource utilization rate and the project economy and reduce the carbon emission of the building. In the prior art, the experience level of designers is greatly depended on to evaluate whether various green technologies are adopted, so that the design is unreasonable, the energy-saving effect cannot be expected, and the resource is greatly wasted.

Therefore, it is required to provide a multi-model-based green technology selection aid decision method and system for improving the scientificity and comprehensiveness of a construction project in a scheme stage decision, further improving the resource utilization rate and the project economy of the construction project and reducing the carbon emission of the construction.

Disclosure of Invention

In order to solve the technical problems that in the prior art, it depends on experience level of designers greatly to evaluate whether each green technology is adopted, so that design is unreasonable easily, energy saving effect cannot be expected, and resource waste is greatly caused, one of embodiments of the present specification provides a green technology selection assistant decision-making method based on multiple models, including: acquiring relevant information of a building project to be decided, wherein the relevant information of the building project to be decided comprises basic information and technical implementation condition information of the building project to be decided; acquiring technology-related information of a plurality of green technologies, wherein the technology-related information comprises at least one necessary applicable condition of the green technologies; for each green technology, judging whether the green technology is suitable for the building project to be decided or not according to the applicability determination model corresponding to the green technology and the relevant information of the building project to be decided and the technology relevant information of the green technology; if the applicability determination model judges that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model corresponding to the green technology; determining at least one target green technology to apply to the building item to be decided from the plurality of green technologies based on the recommendation scores for the plurality of green technologies.

It can be understood that one of the embodiments of the present specification provides a green technology selection decision-making assisting method based on multiple models, where for each green technology, it is first determined, through its corresponding applicability, that the model is based on relevant information of a building item to be decided and technology-related information of the green technology, to determine whether the green technology is applicable to the building item to be decided, the green technology is first screened, to screen out at least one green technology that can be implemented on the building item to be decided, so as to reduce data volume for subsequent decision-making, and improve decision-making efficiency, and then for each green technology, it is evaluated, through its corresponding recommendation score, that the model is based on the relevant information of the building item to be decided and the technology-related information of the green technology, to determine a recommendation score of the green technology, and finally, based on recommendation scores of multiple green technologies, determine at least one target green technology applied to the building item to be decided from the multiple green technologies, without depending on experience level of designers, so that the decision-making of the building item is more scientific and comprehensive at a scheme stage decision-making, which improves resource utilization rate and economic performance of the building item, and reduces carbon emission of the building.

In some embodiments, the determining, by the recommendation score evaluation model, the recommendation score for the green technology based on the information related to the building item to be decided and the technology-related information for the green technology includes: acquiring an auxiliary evaluation information set, wherein the auxiliary evaluation information set comprises at least one auxiliary evaluation information of the attention degree of an owner to a special technology, the special investment amount level, the design team strength evaluation result, the supplier cooperation degree, the construction team strength evaluation result and the operation team strength evaluation result; and determining the recommendation score of the green technology based on the relevant information of the building item to be decided, the auxiliary evaluation information set and the technology relevant information of the green technology through a recommendation score evaluation model.

In some embodiments, the determining, by a recommendation score evaluation model, a recommendation score for the green technology based on the information related to the building item to be decided, the set of auxiliary evaluation information, and the technology-related information for the green technology includes: for each auxiliary evaluation information in the auxiliary evaluation information set, carrying out normalization processing on the auxiliary evaluation information to obtain an auxiliary evaluation score corresponding to the auxiliary evaluation information; and determining the recommendation score of the green technology by a recommendation score evaluation model based on the relevant information of the building item to be decided, the auxiliary evaluation score corresponding to each auxiliary evaluation information in the auxiliary evaluation information set and the technology relevant information of the green technology.

In some embodiments, the determining, by the recommendation score evaluation model, the recommendation score for the green technology based on the information related to the building item to be decided and the technology-related information for the green technology includes: establishing an initial machine learning model corresponding to the green technology; obtaining relevant information of a plurality of historical decided building items, establishing a plurality of training samples based on one part of the plurality of historical decided building items, and establishing a plurality of verification samples based on another part of the plurality of historical decided building items; training the initial machine learning model based on the plurality of training samples until the initial machine learning model meets a preset training end condition, and verifying the training end model based on the plurality of verification samples until the training end model meets a preset verification passing condition preset condition; taking an initial machine learning model which meets the preset training end condition and the preset verification passing condition preset condition after training as the recommendation score evaluation model; and determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through the recommendation score evaluation model.

In some embodiments, when the mean square error MSETR corresponding to the training samples calculated by the trained initial machine learning model meets a preset error threshold requirement or the iteration number of the initial machine learning model is greater than a preset iteration number threshold, the trained initial machine learning model meets the preset condition.

In some embodiments, an initial machine learning model corresponding to the green technology is established based on a BP neural network.

In some embodiments, said training the initial machine learning model based on the plurality of training samples comprises: repeatedly executing to obtain a training sample, performing forward propagation and inputting the training sample to the initial machine learning model, calculating an output error corresponding to the training sample, performing reverse propagation on the output error, adjusting a weight by adopting an Adam optimizer, and calculating a Mean Square Error (MSETR) of a training set until the MSETR corresponding to the training set meets the requirement of a preset error threshold or the iteration number of the initial machine learning model is greater than a preset iteration number threshold.

In some embodiments, said training the initial machine learning model based on the plurality of training samples until the initial machine learning model satisfies a preset condition comprises: a43, initializing the number NH of hidden layers of the initial machine learning model to be 1; a44, initializing the neuron number N of an input layer; a45, initializing a first layer hidden layer neuron number N1, wherein N1= N/2, and when the N/2 is not an integer, the first layer hidden layer neuron number N1 is an integer part of the N/2(ii) a A46, judging whether NH is larger than 1, if so, turning to the step A47, otherwise, turning to the step A48; a47, initializing a second layer hidden layer neuron number N2 as N1/2, wherein N2= N1/2, and when N1/2 is not an integer, the second layer hidden layer neuron number N2 is an integer part of N1/2; a48, training the current initial machine learning model based on the training samples, and if the mean square error MSE of the training samples _TR If the error is smaller than or equal to the threshold value delta, the step A55 is carried out, otherwise, the step A49 is carried out; a49, judging whether NH is larger than 1, if so, switching to the step A50, otherwise, switching to the step A51; a50 N2= N2+1, determining whether N2 is smaller than N1, if so, turning to step a48, otherwise, turning to step a51; a51 N1= N1+1, determining whether N1 is smaller than N, if so, turning to step a46, otherwise, turning to step a52; a52, judging whether N is less than or equal to 20 or not, if so, turning to the step A45, otherwise, turning to the step A53; a53, judging whether NH is less than or equal to 2 when NH = NH +1, if so, switching to step A44, otherwise, switching to step A54; a54, storing an initial machine learning model with the minimum mean square error MSEval of a plurality of verification samples, judging whether the training times are equal to a preset time limit value, if so, turning to A56 to avoid network training endless loop, otherwise, turning to A55; a55, calculating the mean square error MSEval of the verification samples through the current initial machine learning model, judging whether the MSEval is smaller than or equal to an error threshold value delta, if so, turning to the step A56, and if not, turning to the step A49; and A56, finishing training and generating the recommendation score evaluation model.

In some embodiments, an initialization value for the number of input-layer neurons is determined based on the basic information of the construction project to be decided, the auxiliary evaluation information set, and the technology-related information of the green technology.

In order to solve the technical problems that in the prior art, it depends on the experience level of designers greatly to evaluate whether each green technology is adopted, so that the design is unreasonable, the energy saving effect cannot be expected, and the resource is wasted greatly, one of the embodiments of the present specification provides a green technology selection assistant decision-making system based on multiple models, including: the system comprises a project information acquisition module, a project information acquisition module and a project management module, wherein the project information acquisition module is used for acquiring relevant information of a building project to be decided, and the relevant information of the building project to be decided comprises basic information and technical implementation condition information of the building project to be decided; the system comprises a technical information acquisition module, a processing module and a display module, wherein the technical information acquisition module is used for acquiring technical related information of a plurality of green technologies, and the technical related information comprises at least one necessary applicable condition of the green technologies; the green technology evaluation module is used for judging whether the green technology is suitable for the building project to be decided or not according to the applicability determination model corresponding to the green technology and the relevant information of the building project to be decided and the technology relevant information of the green technology for each green technology; if the applicability determination model judges that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model corresponding to the green technology; and the green technology decision module is used for determining at least one target green technology applied to the building item to be decided from the plurality of green technologies based on the recommendation scores of the plurality of green technologies.

One of the embodiments of the present specification provides a green technology selection aid decision method and system based on multiple models, which at least have the following beneficial effects:

(1) Firstly, whether a green technology is suitable for a building item to be decided is judged through a corresponding applicability determination model based on relevant information of the building item to be decided and technology relevant information of the green technology, the green technology is firstly screened, at least one green technology which can be implemented on the building item to be decided is screened out, the data volume of subsequent decision is reduced, the decision efficiency is improved, then for each green technology, a recommendation score of the green technology is determined through a corresponding recommendation score evaluation model based on the relevant information of the building item to be decided and the technology relevant information of the green technology, and finally, at least one target green technology applied to the building item to be decided is determined from multiple green technologies based on the recommendation scores of the multiple green technologies, so that the decision of the building item in a scheme stage is more scientific and comprehensive without depending on the experience level of designers, the resource utilization rate of the building item is improved, the economy of the item is improved, and the carbon emission of the building is reduced;

(2) The method comprises the following steps that the attach degree of an owner to a special technology, the special investment amount level, the design team strength evaluation result, the supplier cooperation degree, the construction team strength evaluation result, the operation team strength evaluation result and the like all influence the implementation effect of the green technology, so that when the recommendation of the green technology is determined, at least one auxiliary evaluation information of the attach degree of the owner to the special technology, the special investment amount level, the design team strength evaluation result, the supplier cooperation degree, the construction team strength evaluation result and the operation team strength evaluation result is added, and the building project can be more scientifically and comprehensively decided in a scheme stage.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a schematic diagram illustrating an application scenario of a multiple model-based green technology selection aid decision system according to some embodiments of the present disclosure;

FIG. 2 is a block schematic diagram of a multiple model-based green technology selection aid decision system in accordance with some embodiments of the present description;

FIG. 3 is an exemplary flow diagram of a multi-model based green technology selection aid decision method according to some embodiments herein;

FIG. 4 is a schematic illustration of basic information for a construction item X to be decided according to some embodiments herein;

FIG. 5 is a schematic illustration of technical implementation condition information for a construction item X to be decided according to some embodiments herein;

FIG. 6 is a schematic illustration of normalizing auxiliary evaluation information according to some embodiments of the present description;

FIG. 7 is a schematic representation of technology-related information for solar photovoltaic technology, ground source heat pump technology, and surface water source heat pump technology in accordance with some embodiments presented herein;

FIG. 8 is an exemplary flow diagram of a training process for a recommendation score evaluation model according to some embodiments shown herein;

FIG. 9 is an exemplary flow diagram illustrating the use of an Adam optimizer to adjust weights according to some embodiments of the present description;

FIG. 10a is a schematic flow diagram illustrating a portion of a process for generating a recommendation score evaluation model according to some embodiments of the present description;

FIG. 10b is another partial flow diagram illustrating the generation of a recommendation score evaluation model according to some embodiments of the present description.

In the figure, 110, a processing device; 120. a network; 130. a user terminal; 140. a storage device.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" are intended to cover only the explicitly identified steps or elements as not constituting an exclusive list and that the method or apparatus may comprise further steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Fig. 1 is a schematic diagram illustrating an application scenario of a multi-model-based green technology selection assistant decision system according to some embodiments of the present disclosure.

As shown in fig. 1, an application scenario may include a processing device 110, a network 120, a user terminal 130, and a storage device 140.

In some embodiments, the processing device 110 may be used to process information and/or data related to green technology selection aid decisions. For example, the processing device 110 may obtain relevant information of a building project to be decided and technology-related information of a plurality of green technologies, determine, for each green technology, a model according to the applicability corresponding to the green technology, and determine whether the green technology is suitable for the building project to be decided based on the relevant information of the building project to be decided and the technology-related information of the green technology; if the applicability determination model judges that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model corresponding to the green technology; and determining at least one target green technology applied to the building project to be decided from the multiple green technologies based on the recommendation scores of the multiple green technologies. Further description of the processing device 110 may be found in other sections of this application. For example, fig. 3 and its description.

In some embodiments, the processing device 110 may be regional or remote. For example, processing device 110 may access information and/or profiles stored in user terminal 130 and storage device 140 via network 120. In some embodiments, processing device 110 may be directly connected to user terminal 130 and storage device 140 to access information and/or material stored therein. In some embodiments, the processing device 110 may execute on a cloud platform. For example, the cloud platform may include one or any combination of a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, and the like.

In some embodiments, the processing device 110 may include a processor 210, and the processor 210 may include one or more sub-processors (e.g., a single core processing device or a multi-core processing device). Merely by way of example, a processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a programmable logic circuit (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, and the like or any combination thereof.

The network 120 may facilitate the exchange of data and/or information in an application scenario. In some embodiments, one or more components in an application scenario (e.g., processing device 110, user terminal 130, and storage device 140) may send data and/or information to other components in the application scenario via network 120. For example, the processing device 110 may obtain information related to the construction project to be decided, technical related information of a plurality of green technologies from the storage device 140 through the network 120. In some embodiments, the network 120 may be any type of wired or wireless network. For example, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a Local Area Network (LAN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, the like, or any combination thereof.

In some embodiments, the user terminal 130 may obtain information or data in an application scenario. For example, the user terminal 130 may obtain the determined at least one target green technology to apply to the construction project to be decided from the processing device 110 via the network 120. In some embodiments, the user terminal 130 may include one or any combination of a mobile device (e.g., a smartphone, a smartwatch, etc.), a tablet, a laptop, etc.

In some embodiments, storage device 140 may be connected to network 120 to enable communication with one or more components of an application scenario (e.g., processing device 110, user terminal 130, etc.). Application scenarios one or more components may access material or instructions stored in storage device 140 via network 120. In some embodiments, the storage device 140 may be directly connected or in communication with one or more components (e.g., processing device 110, user terminal 130) in an application scenario. In some embodiments, the storage device 140 may be part of the processing device 110.

It should be noted that the foregoing description is provided for illustrative purposes only, and is not intended to limit the scope of the present application. Many variations and modifications will occur to those skilled in the art in light of the teachings herein. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, the storage device 140 may be a data storage device comprising a cloud computing platform, such as a public cloud, a private cloud, a community and hybrid cloud, and the like. However, such changes and modifications do not depart from the scope of the present application.

FIG. 2 is a block diagram representation of a multi-model based green technology selection aid decision system in accordance with certain embodiments of the present disclosure.

As shown in fig. 2, a multi-model-based green technology selection assistant decision system may include a project information acquisition module, a technology information acquisition module, a green technology evaluation module, and a green technology decision module.

The project information acquisition module can be used for acquiring the relevant information of the building project to be decided, wherein the relevant information of the building project to be decided comprises the basic information and the technical implementation condition information of the building project to be decided.

The technical information acquisition module may be used to acquire technical-related information of a plurality of green technologies, wherein the technical-related information includes at least one necessary applicable condition of the green technologies.

The green technology evaluation module can be used for determining whether the green technology is suitable for the building project to be decided or not according to the applicability determination model corresponding to the green technology and the relevant information of the building project to be decided and the technology relevant information of the green technology for each green technology; and if the applicability determination model judges that the green technology is suitable for the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through the recommendation score evaluation model corresponding to the green technology.

The green technology decision module can be configured to determine at least one target green technology to apply to the construction project to be decided from the plurality of green technologies based on the recommendation score for the plurality of green technologies.

It should be noted that the above descriptions of the candidate item display and determination system and the modules thereof are only for convenience of description, and the description is not limited to the scope of the embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the project information obtaining module, the technical information obtaining module, the green technology evaluating module and the green technology deciding module disclosed in fig. 1 may be different modules in one system, or may be a module that realizes the functions of two or more modules. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present description.

FIG. 3 is an exemplary flow diagram of a multi-model based green technology selection aid decision method according to some embodiments described herein. As shown in fig. 3, a green technology selection aid decision method based on multiple models includes the following steps. In some embodiments, a multi-model based green technology selection aid decision method may be performed by a multi-model based green technology selection aid decision system or processing device 110.

And step 310, acquiring relevant information of the building project to be decided. In some embodiments, step 310 may be performed by the project information acquisition module.

The building project to be decided is a building project to be determined which green technologies are applied, wherein the green technologies can comprise a solar photovoltaic technology, a ground source heat pump technology, a surface water source heat pump technology and the like. The information related to the building item to be decided may be information related to the building item to be decided.

In some embodiments, the information related to the building item to be decided may include basic information of the building item to be decided, for example, a type of the item (e.g., office, mall, hotel, hospital, school, residence or industrial factory, etc.), a building area, a volume rate, a greening rate, a building density, a floor space, a location of the item, etc., and fig. 4 illustrates the basic information of the building item to be decided X by way of example.

In some embodiments, the information related to the building item to be decided may include technical implementation condition information, and the technical implementation condition information may represent information of the environment where the building item to be decided related to green technology implementation is located, for example, the total annual solar energy radiation amount, the climate zone where the building item to be decided is located, whether the geological condition for installing the ground source heat pump is satisfied, the distance from the surface flowing water body, and the like, and fig. 5 shows the technical implementation condition information of the building item to be decided X.

In some embodiments, the information related to the construction project to be decided may further include an auxiliary assessment information set, and the auxiliary assessment information set may include at least one auxiliary assessment information of a degree of the owner's attention to the special technology, a special investment amount level, a design team strength assessment result, a supplier cooperation degree, a construction team strength assessment result, and an operation team strength assessment result. It will be appreciated that the auxiliary evaluation information can have a very significant impact on whether green technology can introduce the building project to be decided. With reference to fig. 6, in some embodiments, since the auxiliary evaluation information is difficult to evaluate by objective values, the project information acquisition module may perform normalization processing on the auxiliary evaluation information, where the normalization processing includes multiple methods such as calculation based on big data, artificial survey evaluation, and so on, or a combination of multiple methods, and finally normalize each auxiliary evaluation information to a value of 1 to 5, so as to facilitate subsequent determination of at least one target green technology applied to the building project to be decided from multiple green technologies.

In some embodiments, the project information acquisition module may acquire information related to the construction project to be decided from the processing device 110, the user terminal 130, the storage device 140, or from an external data source via the network 120.

At step 320, technology-related information for a plurality of green technologies is obtained. In some embodiments, step 320 may be performed by a technical information acquisition module.

The technical-related information of the green technology may represent necessary conditions for implementing the green technology, for example, a minimum annual solar energy radiation amount, a minimum winter-summer load imbalance rate, geological condition requirements, a maximum distance from the surface flowing water body, and the like, for example, fig. 7 shows technical-related information of a solar photovoltaic technology, a ground source heat pump technology, and a surface water source heat pump technology, and it may be understood that technical-related information of different green technologies may be different.

It can be understood that, with the development of science and technology, the technical application conditions of the green technology are mostly gradually reduced, and therefore, the technical related information of the plurality of green technologies acquired by the technical information acquisition module can be updated along with the development of science and technology.

In some embodiments, the technology information acquisition module may acquire the technology-related information for the plurality of green technologies from the processing device 110, the user terminal 130, the storage device 140, or from an external data source via the network 120.

Step 330, determining whether the green technology is suitable for the building project to be decided based on the relevant information of the building project to be decided and the technology relevant information of the green technology through the applicability determination model corresponding to the green technology. In some embodiments, step 330 may be evaluated by a green technology.

The applicability determination model may be used to determine whether green technologies are applicable to the building project to be decided. It is to be understood that each green technology may correspond to a suitability determination model, for example, a solar photovoltaic technology corresponds to a suitability determination model (first suitability determination model), a ground source heat pump technology corresponds to a suitability determination model (second suitability determination model), and a ground surface water source heat pump technology corresponds to a suitability determination model (third suitability determination model).

In some embodiments, the applicability determination model may determine whether the green technology is applicable to the building item to be decided based on the relevant information of the building item to be decided and the technology-related information of the green technology. Furthermore, the applicability determination model may determine whether the green technology is applicable to the building item to be decided based on the technology implementation condition information of the building item to be decided and the technology-related information of the green technology. For example, the applicability determination model may determine whether the technical implementation condition information of the building project to be decided satisfies technical related information of a green technology, where the green technology is applicable to the building project to be decided if the technical implementation condition information of the building project to be decided satisfies the technical related information of the green technology, and the green technology is not applicable to the building project to be decided if the technical implementation condition information of the building project to be decided does not satisfy the technical related information of the green technology. For example, still taking fig. 7 as an example, regarding the green technology of the solar photovoltaic technology, the technology-related information includes total annual solar radiation amount >5000 MJ/square meter, the total annual solar radiation amount in the technology implementation condition information of the building item to be decided is 6000 MJ/square meter, and the total annual solar radiation amount is 6000 MJ/square meter, which satisfies that the total annual solar radiation amount >5000 MJ/square meter, the first applicability determination model may determine that the solar photovoltaic technology is applicable to the building item to be decided.

In some embodiments, the applicability determination model may be a machine learning model, the input of the applicability determination model is technology implementation condition information of the building item to be decided and technology related information of the green technology, the output of the applicability determination model is to determine whether the green technology is applicable to the building item to be decided, the green technology evaluation module may train the initial applicability determination model through a plurality of labeled training samples, where one training sample corresponds to one decided building item, the training samples may include the technology implementation condition information of the decided building item and the technology related information of the green technology, the label of the training sample may include whether the green technology is applicable to the decided building item, and the green technology evaluation module may obtain the label of the training sample through various ways, for example, through manual labeling, and for example, the green technology evaluation module may obtain the label from the storage device 140 or an external data source.

In some embodiments, the green technology evaluation module may train the initial suitability determination model multiple times in a common manner (e.g., gradient descent, etc.) until the trained initial suitability determination model satisfies a preset condition, and use the trained initial suitability determination model as a suitability determination model for determining whether the green technology is suitable for the building item to be decided. The preset condition may be that the loss function of the updated initial applicability determination model is smaller than a threshold, convergence, or that the number of training iterations reaches a threshold.

In some embodiments, the suitability determination model may include, but is not limited to, neural Networks (NN), decision Trees (DT), linear Regression (LR), and one or more combinations thereof.

It can be understood that the technical related information of the plurality of green technologies acquired by the technical information acquisition module can be updated along with the development of the science and technology, and therefore, when the technical related information of the green technologies is updated, the green technology evaluation module can acquire the sample data again to train the applicability determination model again so as to maintain the accuracy of the applicability determination model in judging whether the green technologies are suitable for the building project to be decided.

Step 340, if the applicability determination model determines that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through the recommendation score evaluation model corresponding to the green technology. In some embodiments, step 340 may be performed by the green technology assessment module.

The recommendation score evaluation model can be used for judging the suitability degree of the green technology applied to the building project to be decided. It is understood that each green technology may correspond to a recommendation score evaluation model, for example, a solar photovoltaic technology corresponds to a recommendation score evaluation model (a first recommendation score evaluation model), a ground source heat pump technology corresponds to a recommendation score evaluation model (a second recommendation score evaluation model), and a ground surface water source heat pump technology corresponds to a recommendation score evaluation model (a third recommendation score evaluation model).

In some embodiments, the green technology evaluation module may build an initial machine learning model for each green technology based on the BP neural network, the initial machine learning model being used for training to finally generate the recommendation score evaluation model.

In some embodiments, the determining, by the technology evaluation module, the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through the recommendation score evaluation model may include:

establishing an initial machine learning model corresponding to a green technology;

acquiring related information of a plurality of historical decided building items, establishing a training set based on one part of the plurality of historical decided building items, wherein the training set comprises a plurality of training samples, and establishing a verification set based on another part of the plurality of historical decided building items, and the verification set comprises a plurality of verification samples;

training the initial machine learning model based on a plurality of training samples until the initial machine learning model meets a preset training end condition, and verifying the training end model based on a plurality of verification samples until the training end model meets a preset verification passing condition;

taking an initial machine learning model which meets a preset training end condition and a preset verification passing condition after training as a recommendation score evaluation model;

and determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model.

In some embodiments, the green technology evaluation module trains the initial machine learning model based on a plurality of training samples, which may include: repeatedly executing to obtain a training sample, performing forward propagation and inputting the training sample to the initial machine learning model, calculating an output error corresponding to the training sample to enable the output error to be subjected to reverse propagation, adjusting a weight by adopting an Adam optimizer, and calculating a Mean Square Error (MSETR) of the training set until the MSETR corresponding to the training set meets the requirement of a preset error threshold or the iteration number of the initial machine learning model is greater than a preset iteration number threshold.

With reference to fig. 10a and fig. 10b, further, training the initial machine learning model based on a plurality of training samples until the initial machine learning model satisfies a preset condition includes:

a43, initializing the number NH of hidden layers of the initial machine learning model to be 1;

a44, initializing an input layer neuron number N, in some embodiments, the green technology evaluation module may determine an initialization value of the input layer neuron number based on the basic information of the building project to be decided, the auxiliary evaluation information set, and technology-related information of the green technology, for example, the basic information of the building project to be decided includes 7 parameters (i.e., project type, building area, volume ratio, greening rate, building density, floor area, and project location), the auxiliary evaluation information set includes 6 parameters (i.e., the degree of importance of the owner on the proprietary technology, the proprietary investment quota level, the design team strength evaluation result, the supplier cooperation degree, the construction team strength evaluation result, and the operation team strength evaluation result), the technology-related information of the green technology includes k parameters, and then the initialization input layer neuron number N =6 j +7 k, for example, for the green technology of the solar photovoltaic technology, the technology-related information includes 1 parameter (i.e., total solar energy radiation amount in year >5000MJ/, then the corresponding initialization input layer neuron number N =14;

a45, initializing a first-layer hidden-layer neuron number N1, wherein N1= N/2, when N/2 is not an integer, the first-layer hidden-layer neuron number N1 is an integer part of N/2, for example, when N is 15, N/2 is 7.5, then initializing the first-layer hidden-layer neuron number N1=7;

a46, judging whether NH is larger than 1, if so, switching to a step A47, otherwise, switching to a step A48;

a47, initializing a second layer hidden layer neuron number N2 to be N1/2, wherein N2= N1/2, when N1/2 is not an integer, the second layer hidden layer neuron number N2 is an integer part of N1/2, for example, when N1 is 7, N1/2 is 3.5, then initializing the second layer hidden layer neuron number N2=3;

a48, training the current initial machine learning model based on a plurality of training samples, if the mean square error MSETR of the training set is less than or equal to the error threshold value delta, turning to the step A55, otherwise, turning to the step A49;

a49, judging whether NH is larger than 1, if so, switching to the step A50, otherwise, switching to the step A51;

a50, making N2= N2+1, judging whether N2 is smaller than N1, if so, turning to a step a48, otherwise, turning to a step a51;

a51, making N1= N1+1, judging whether N1 is smaller than N, if so, turning to a step a46, otherwise, turning to a step a52;

a52, making N = N +1, judging whether N is less than or equal to 20, if so, turning to the step A45, otherwise, turning to the step A53;

a53, making NH = NH +1, determining whether NH is less than or equal to 2, if so, turning to a step a44, otherwise, turning to a step a54;

a54, storing an initial machine learning model with the minimum mean square error MSEval of a plurality of verification samples, judging whether the training times are equal to a preset time limit value, if so, turning to A56 to avoid network training dead loop, otherwise, turning to A55;

a55, calculating mean square errors MSEval of a plurality of verification samples through a current initial machine learning model, judging whether the MSEval is smaller than or equal to an error threshold value delta, if so, turning to the step A56, and if not, turning to the step A49;

and A56, training is finished, and a recommendation score evaluation model is generated, for example, the initial machine learning model with the minimum mean square error MSEval obtained from A54 is used as the recommendation score evaluation model, or the initial machine learning model with the MSEval obtained from A55 being less than or equal to an error threshold value delta is used as the recommendation score evaluation model.

It can be understood that rapid changes of construction projects and green technologies make a fixed network structure difficult to be applied to assistant decision for a long time, and in order to enhance the adaptability of the assistant decision process, the machine learning model construction method is adopted, so that the recommendation score evaluation model base can be updated by itself according to data changes (for example, the technology-related information of the green technologies is updated), and the recommendation score evaluation model base can adapt to many changes brought by technology changes and provide more accurate recommendation score results.

In some embodiments, the green-technology recommendation score output by the recommendation score evaluation model may be represented in any form, for example, by an integer between 1 and 10.

With reference to fig. 8, the training process of the recommendation score evaluation model includes the following steps:

b41, initializing a machine learning model;

b42, taking a training sample in a sample set, performing forward propagation input, calculating input and output of each hidden layer neuron, and calculating an output error, wherein the sample set comprises a training set and a verification set;

b43, reversely transmitting the error, and adjusting the weight by adopting an Adam optimizer;

b44, calculating the mean square error of the sample set;

b45, judging whether the mean square error of the sample set meets the requirement of a preset error threshold, if so, ending the training process, otherwise, turning to the step B46.

B46, judging whether the iteration number reaches the upper limit, if so, ending the training process, otherwise, turning to the step B42.

With reference to fig. 9, the process of adjusting the weights by using Adam optimizer includes the following steps:

b431, initializing an optimizer;

b432, calculating gradient values;

b433, updating the moment vector;

b434, calculating a moment vector for correcting the deviation;

b435, updating the weight;

b436, judging whether the weight value is converged, if so, ending the flow, otherwise, returning to the step B432.

Before training is started, the input data is first normalized to [0,1 ]]The range is used for accelerating the convergence speed of the training network; the network weight is (0, 1)]Initializing randomly, and activating a function to select a sigmoid function; iterative computation is performed by using an Adam (Adaptive moment estimation) optimizer, wherein the parameters of the optimizer are defaults, namely an initial learning rate alpha =0.001 and an exponential decay rate beta ₁ ＝0.9、β ₂ =0.999, constant ∈ =10 ^-8 。

And 350, determining at least one target green technology applied to the building project to be decided from the multiple green technologies based on the recommendation scores of the multiple green technologies. In some embodiments, step 350 may be performed by a green technology decision module.

In some embodiments, the green technology decision module may determine at least one target green technology to apply to the building item to be decided from the plurality of green technologies based on the recommendation score of the plurality of green technologies in any manner. For example, the green technology decision module may take a green technology having a recommendation score greater than a corresponding preset score threshold as the target green technology applied to the building item to be decided. Illustratively, the recommendation score of the solar photovoltaic technology calculated by the first recommendation score evaluation model is 7, and the preset score threshold corresponding to the solar photovoltaic technology is 6, the solar photovoltaic technology can be used as a target green technology applied to the building project to be decided.

In some embodiments, the green technology decision module may obtain the preset score threshold corresponding to each green technology from the processing device 110, the user terminal 130, the storage device 140, or from an external data source via the network 120.

It should be noted that the above description of a green multi-model based selection aid decision method is for illustration and explanation only, and does not limit the scope of the application of the present specification. Various modifications and alterations to a multi-model based green technology selection aid decision method will be apparent to those skilled in the art in light of the present disclosure. However, such modifications and variations are intended to be within the scope of the present description.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics may be combined as suitable in one or more embodiments of the specification.

Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features are required than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into the specification. Except where the application history document is inconsistent or contrary to the present specification, and except where the application history document is inconsistent or contrary to the present specification, the application history document is not inconsistent or contrary to the present specification, but is to be read in the broadest scope of the present claims (either currently or hereafter added to the present specification). It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments described herein. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. A green technology selection aid decision method based on multiple models is characterized by comprising the following steps:

acquiring relevant information of a building project to be decided, wherein the relevant information of the building project to be decided comprises basic information and technical implementation condition information of the building project to be decided;

acquiring technology-related information of a plurality of green technologies, wherein the technology-related information comprises at least one necessary applicable condition of the green technologies;

for each of the said green technologies, the green technology,

judging whether the green technology is suitable for the building project to be decided or not based on the relevant information of the building project to be decided and the technology relevant information of the green technology through a suitability determination model corresponding to the green technology;

if the applicability determination model judges that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model corresponding to the green technology;

determining at least one target green technology to apply to the building item to be decided from the plurality of green technologies based on the recommended scores of the plurality of green technologies.

2. The multi-model-based green technology selection aid decision method according to claim 1, wherein the recommendation score evaluation model determines the recommendation score of the green technology based on the information related to the building item to be decided and the technology-related information of the green technology, and comprises the following steps:

acquiring an auxiliary evaluation information set, wherein the auxiliary evaluation information set comprises at least one auxiliary evaluation information of the attention degree of an owner to a special technology, the special investment amount level, the design team strength evaluation result, the supplier cooperation degree, the construction team strength evaluation result and the operation team strength evaluation result;

and determining the recommendation score of the green technology based on the relevant information of the building item to be decided, the auxiliary evaluation information set and the technology relevant information of the green technology through the recommendation score evaluation model.

3. The multi-model-based green technology selection assistant decision method as claimed in claim 2, wherein the determining the recommendation score of the green technology based on the related information of the building item to be decided, the assistant evaluation information set and the technology related information of the green technology through the recommendation score evaluation model comprises:

for each of the secondary evaluation information in the secondary evaluation information set,

carrying out normalization processing on the auxiliary evaluation information to obtain an auxiliary evaluation score corresponding to the auxiliary evaluation information;

and determining the recommendation score of the green technology by a recommendation score evaluation model based on the relevant information of the building item to be decided, the auxiliary evaluation score corresponding to each auxiliary evaluation information in the auxiliary evaluation information set and the technology relevant information of the green technology.

4. The multi-model-based green technology selection aid decision method according to claim 3, wherein the determining of the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through the recommendation score evaluation model comprises:

establishing an initial machine learning model corresponding to the green technology;

obtaining relevant information of a plurality of historical decided building items, establishing a plurality of training samples based on one part of the plurality of historical decided building items, and establishing a plurality of verification samples based on another part of the plurality of historical decided building items;

training the initial machine learning model based on the training samples until the initial machine learning model meets a preset training end condition, and verifying the training end model based on the verification samples until the training end model meets a preset verification passing condition;

taking an initial machine learning model which meets the preset training end condition and the preset verification passing condition after training as the recommendation score evaluation model;

and determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through the recommendation score evaluation model.

5. The multi-model-based green technology selection aid decision method according to claim 4, wherein the trained initial machine learning model satisfies the preset condition when a mean square error MSETR corresponding to the training samples calculated by the trained initial machine learning model satisfies a preset error threshold requirement or an iteration number of the initial machine learning model is greater than a preset iteration number threshold.

6. The green technology selection aided decision making method based on multiple models as claimed in claim 5, wherein an initial machine learning model corresponding to the green technology is established based on a BP neural network.

7. The multi-model based green technology selection aid decision method of claim 6, wherein the training the initial machine learning model based on the plurality of training samples comprises:

repeatedly executing to obtain a training sample, performing forward propagation and inputting to the initial machine learning model, calculating an output error corresponding to the training sample, performing backward propagation on the output error, adjusting a weight by adopting an Adam optimizer, and calculating a mean square error MSETR of a training set until the mean square error MSETR corresponding to the training set meets a preset error threshold requirement or the iteration number of the initial machine learning model is greater than a preset iteration number threshold.

8. The multi-model-based green technology selection assistant decision method according to any one of claims 5-7, wherein the training the initial machine learning model based on the training samples until the initial machine learning model meets a preset condition comprises:

a44, initializing the number N of neurons in an input layer;

a45, initializing a first layer hidden layer neuron number N1, wherein N1= N/2, and when the N/2 is not an integer, the first layer hidden layer neuron number N1 is an integer part of the N/2;

a46, judging whether NH is larger than 1, if so, turning to the step A47, otherwise, turning to the step A48;

a47, initializing a second layer hidden layer neuron number N2 as N1/2, wherein N2= N1/2, and when N1/2 is not an integer, the second layer hidden layer neuron number N2 is an integer part of N1/2;

a48, training the current initial machine learning model based on the training samples, and if the mean square error MSE of the training samples _TR If the error is smaller than or equal to the threshold value delta, the step A55 is carried out, otherwise, the step A49 is carried out;

a50 If N2= N2+1, determining whether N2 is smaller than N1, if so, turning to step a48, otherwise, turning to step a51;

a51 N1= N1+1, determining whether N1 is smaller than N, if so, turning to step a46, otherwise, turning to step a52;

a52, judging whether N is less than or equal to 20 or not, if so, turning to the step A45, otherwise, turning to the step A53;

a53, NH = NH +1, judging whether NH is less than or equal to 2, if so, turning to step A44, otherwise, turning to step A54;

a55, calculating the mean square error MSEval of the verification samples through the current initial machine learning model, judging whether the MSEval is smaller than or equal to an error threshold value delta, if so, turning to the step A56, and if not, turning to the step A49;

and A56, finishing training and generating the recommendation score evaluation model.

9. The green technology selection assistant decision method based on multiple models as claimed in claim 8, wherein the initialization value of the input layer neuron number is determined based on the basic information of the building item to be decided, the assistant evaluation information set and the technology-related information of the green technology.

10. A green technology selection aid decision system based on multiple models, comprising:

the system comprises a project information acquisition module, a project information acquisition module and a project management module, wherein the project information acquisition module is used for acquiring relevant information of a building project to be decided, and the relevant information of the building project to be decided comprises basic information and technical implementation condition information of the building project to be decided;

the system comprises a technical information acquisition module, a data processing module and a data processing module, wherein the technical information acquisition module is used for acquiring technical related information of a plurality of green technologies, and the technical related information comprises at least one necessary applicable condition of the green technologies;

the green technology evaluation module is used for judging whether the green technology is suitable for the building project to be decided or not according to the applicability determination model corresponding to the green technology and the relevant information of the building project to be decided and the technology relevant information of the green technology for each green technology; if the applicability determination model judges that the green technology is applicable to the building item to be decided, determining the recommendation score of the green technology based on the relevant information of the building item to be decided and the technology relevant information of the green technology through a recommendation score evaluation model corresponding to the green technology;

and the green technology decision module is used for determining at least one target green technology applied to the building item to be decided from the plurality of green technologies based on the recommendation scores of the plurality of green technologies.