Construction method of energy equipment purchasing model based on large model and related device

Abstract

The invention provides an energy equipment purchasing model construction method based on a large model and a related device, and relates to the field of large models, and the method comprises the steps: extracting vectorized equipment related data of energy equipment from a database, taking the equipment related data as training data, employing the training data to train an initial purchasing prediction model, and obtaining a procurement prediction model; the input of the target test model is an equipment type and a basic parameter, the output of the target purchase prediction model is a performance index of each piece of equipment matched with the equipment type and the basic parameter, and then an evaluation model is adopted to evaluate and optimize the target purchase prediction model. And integrating the evaluated and optimized target purchase prediction model with the evaluation model to obtain a target purchase model, and realizing accurate recommendation of equipment required by the user through the target purchase model.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method for constructing an energy equipment procurement model based on a large model and related devices. Background Art

[0002] In order to ensure the smooth progress of the production process and promote the innovation of production technology, enterprises will update and introduce advanced production equipment from time to time. However, in the process of selecting these equipment, enterprises often rely too much on past experience and industry promotional materials, but fail to deeply explore and effectively utilize the valuable value contained in the data accumulated during the operation and maintenance of existing equipment. In addition, given that the amount of data of these enterprises is relatively limited, there may be a large deviation between the results of statistical analysis and the actual situation, thus affecting the accuracy of decision-making.

[0003] What is particularly important is that even if an enterprise has carefully selected seemingly suitable equipment, it can only negotiate the warranty period with the manufacturer based on common industry practices, and cannot accurately evaluate whether the current procurement plan truly meets its actual operational needs. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and a related device for constructing an energy equipment procurement model based on a large model, so as to realize automatic recommendation of energy equipment according to user needs.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A method for constructing an energy equipment procurement model based on a large model, comprising:

[0007] Extracting training data from a database, wherein the training data includes device-related data of the vectorized energy device;

[0008] The training data is used to train the initial purchase prediction model to obtain a target purchase prediction model, wherein the input of the target purchase prediction model is the device type and basic parameters, and the output is the identity information and performance indicators of each device matching the device type and basic parameters;

[0009] Acquire an evaluation model, wherein the evaluation model is used to evaluate and optimize output data of the target procurement prediction model;

[0010] The target procurement prediction model and the evaluation model are integrated to obtain a target procurement model.

[0011] Optionally, in the above-mentioned method for constructing an energy equipment procurement model based on a large model, before extracting training data from the database, the method further includes:

[0012] Collect the published equipment-related data of various energy equipment through the big model, and the equipment-related parameters include but are not limited to one or a combination of brand, specification model, rated parameters, defect rate, years of operation, energy efficiency, selling price, and maintenance cost;

[0013] Preprocessing the device-related data, wherein the preprocessing includes at least one or a combination of redundancy processing, data cleaning, processing missing values, and processing abnormal values;

[0014] Standardize or normalize the pre-processed device-related data;

[0015] Convert the standardized or normalized device-related data into vector form;

[0016] The device-related data converted into vector form is stored in the database.

[0017] Optionally, in the above-mentioned method for constructing an energy equipment procurement model based on a large model, after vectorizing the processed equipment-related data, the method further includes:

[0018] A combination feature of the vectorized device-related data is established, and the combination feature is stored in a training database as the device-related data.

[0019] Optionally, in the above-mentioned method for constructing an energy equipment procurement model based on a large model, the combined features include but are not limited to:

[0020] The combined characteristics of defect rate and years of operation, the combined characteristics of energy efficiency and years of operation, and the combined characteristics of maintenance costs and years of operation.

[0021] Optionally, in the above-mentioned method for constructing an energy equipment procurement model based on a large model, feedback data of output data of a target procurement prediction model fed back by a user is obtained;

[0022] The evaluation model is used to adjust the parameters and structure of the target procurement forecast model based on the feedback data and feedback mechanism to optimize the target procurement forecast model.

[0023] Optionally, in the above-mentioned method for constructing an energy equipment procurement model based on a large model, the identity information and performance indicators output by the target procurement prediction model include but are not limited to:

[0024] A combination of one or more of the equipment brand and specification model, defect rate estimate, energy efficiency coefficient estimate, maintenance cost estimate, and warranty period that match the equipment type and basic parameters.

[0025] Optionally, in the above-mentioned method for constructing an energy equipment procurement model based on a large model, after obtaining the target procurement model, the method further includes:

[0026] Obtaining demand data input by a user, wherein the demand data includes device type and basic parameters;

[0027] The target procurement model is used to process the demand data to obtain performance indicators of various recommended equipment;

[0028] The performance indicators of the various recommended devices are tabulated and the processing results are displayed on a display.

[0029] A device for constructing an energy equipment procurement model based on a large model, comprising:

[0030] A training data extraction unit, used to extract training data from a database, wherein the training data includes device-related data of the vectorized energy device;

[0031] A prediction model training unit, used to train the initial purchase prediction model using the training data to obtain a target purchase prediction model, wherein the input of the target purchase prediction model is the device type and basic parameters, and the output is the identity information and performance indicators of each device matching the device type and basic parameters;

[0032] An evaluation model acquisition unit, used to acquire an evaluation model, wherein the evaluation model is used to evaluate the output data of the target procurement prediction model;

[0033] The procurement model building unit is used to integrate the target procurement prediction model with the evaluation model to obtain a target procurement model.

[0034] A computer program product includes computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for constructing an energy equipment procurement model based on a large model as described in any one of the above.

[0035] An electronic device comprises at least one processor and a memory connected to the processor, wherein:

[0036] The memory is used to store computer programs;

[0037] The processor is used to execute the computer program so that the electronic device can implement the method for constructing an energy equipment procurement model based on a large model as described in any one of the above.

[0038] A computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enables the electronic device to implement a method for constructing an energy equipment procurement model based on a large model as described in any one of the above.

[0039] Based on the above technical scheme, the above scheme provided by the embodiment of the present invention extracts the device-related data of the quantized energy equipment from the database, uses the device-related data as training data, and uses the training data to train the initial procurement prediction model to obtain a target procurement prediction model. The input of the target test model is the equipment type and basic parameters, and the output of the target procurement prediction model is the performance indicators of each device matching the equipment type and basic parameters. Then, an evaluation model is used to evaluate and optimize the target procurement prediction model, and the target procurement prediction model after evaluation and optimization is integrated with the evaluation model to obtain a target procurement model. At this time, when the user needs to select energy equipment, the equipment type and basic parameters of the required energy equipment can be used as input data of the target procurement prediction model, and the target procurement prediction model can generate recommendation results based on the target procurement prediction model, and the user can then select the required energy equipment from the recommendation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 A schematic diagram of an implementation system architecture for a method for constructing an energy equipment procurement model based on a large model provided in this application;

[0042] Figure 2 A schematic diagram of a terminal structure provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of a server structure provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of a flow chart of a method for constructing an energy equipment procurement model based on a large model provided in an embodiment of the present application;

[0045] Figure 5 A schematic flow chart of a method for constructing an energy equipment procurement model based on a large model provided in another embodiment of the present application;

[0046] Figure 6 A schematic diagram of the structure of a device for constructing an energy equipment procurement model based on a large model provided in an embodiment of the present application;

[0047] Figure 7 The present application is a schematic diagram of the structure of an electronic device provided in an embodiment. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In order to overcome the above problems raised in the background technology, the present invention innovatively introduces a large-model-based energy equipment procurement solution. This solution deeply relies on the equipment operation and maintenance data provided by energy companies, and trains a target procurement model that specifically serves energy equipment procurement by conducting in-depth statistics and analysis on the operation and maintenance data of various types of equipment.

[0050] A big model is a big language model. A big language model refers to a large neural network model that uses deep learning technology, especially based on the Transformer architecture, and is trained from massive unlabeled text data through self-supervised learning. It contains tens of billions or even more parameters and can understand and generate natural language text.

[0051] When small and medium-sized energy companies input the equipment type and basic parameters of the equipment they want to purchase into the system applying this solution, the system can immediately activate this target procurement model, which will output the performance indicators of each equipment that matches the equipment type and basic parameters for the company. Specifically, the output of the model can include key information such as equipment brand, specifications, and important parameters such as defect rate, energy efficiency coefficient, and maintenance costs. These parameters will change dynamically as the equipment is put into operation. Based on these detailed data supports, the system can tailor the most suitable warranty period for the company, and ultimately generate a comprehensive and intelligent procurement solution.

[0052] Before implementing this solution, a database needs to be built in advance. The database contains detailed information about all energy equipment under energy enterprises, including key data such as brand name, specification model, rated parameters, defect rate statistics, years of operation, energy efficiency level, market sales price and maintenance cost. These data are cleverly converted into vector form through efficient and precise processing of the embedding layer, thus deriving complex features such as the correlation between defect rate and years of operation, the relationship between energy efficiency and years of operation, and the change of maintenance cost with years of operation.

[0053] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0054] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0055] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0056] The present application can be applied in the field of device detection, and the solution can be specifically but not limited to being applied in terminal devices or servers with data processing functions.

[0057] See also Figure 1 , Figure 1 A schematic diagram of a system architecture for implementing the method for constructing the energy equipment procurement model based on the large model is shown. The system may include a terminal 100 and a server 200. The terminal 100 is an intelligent terminal capable of data processing, and the server 200 may include one or more servers ( Figure 1In the example of including a server), the terminal 100 and the server 200 can be used alone or in cooperation with each other to implement the method for constructing the energy equipment procurement model based on the big model. When the two cooperate with each other, the terminal 100 is responsible for uploading the collected data, and the collected data may include data input by the user. These data may include the equipment type and basic parameters of the required energy equipment, and the type of energy equipment corresponding to the target procurement model to be created; the server then processes the data through internal program code to implement each step of the method for constructing the energy equipment procurement model based on the big model.

[0058] When the terminal 100 independently implements the method for constructing the energy equipment procurement model based on the large model, the program for the method for constructing the energy equipment procurement model based on the large model is directly written into the controller of the terminal 100, and after obtaining the data input by the user, these programs can be executed.

[0059] When the terminal 100 and the server 200 cooperate with each other to implement the method for constructing an energy equipment procurement model based on a large model, an application for collecting data based on user input data can be installed on the terminal 100. The above application and web page can provide an interface on which the user can input data. The terminal 100 can receive the user's input data and display it to the user through the interface, and then send the above user input data to the server 200. The server 200 can execute each step of the method for constructing an energy equipment procurement model based on a large model based on the received user input data, obtain simulation results, and return the simulation results to the terminal 100.

[0060] It should be understood that in some optional implementations, the terminal 100 can also complete by itself the actions for implementing the method for constructing a large-model-based energy equipment procurement model based on the received user input data without the need for server cooperation, and the embodiments of the present application are not limited thereto.

[0061] Next describe Figure 1 The product form of the mid-terminal 100;

[0062] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any limitation on this.

[0063] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0064] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0065] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), a trackball, a mouse, a joystick, etc. The user can determine the specific content of the real physical scene data of the vehicle that needs to be collected through the input unit 130.

[0066] The input device 132 can perform data interaction with the input digital device to obtain the user's input data.

[0067] The display unit 140 can be used to display the method for constructing the energy equipment procurement model based on the large model based on the user's input data, the information fed back by the server, various menus of the terminal 100, the interactive interface, the file display and / or the playback of any multimedia file. In the embodiment of the present application, the display unit 140 can be used to display the human-computer interaction interface, the execution result of the server or the terminal 100 executing the method for constructing the energy equipment procurement model based on the large model, etc.

[0068] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0069] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 (including the function of implementing the construction method of the energy equipment procurement model based on the large model and the collection of user input data) and processes data, thereby controlling the terminal as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor, memory, and other components may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0070] Among them, the memory 120 can be used to store software codes related to the method for constructing an energy equipment procurement model based on a large model, the processor 170 can execute the steps of the method for constructing an energy equipment procurement model based on a large model, and can also schedule other units (such as the above-mentioned input unit 130 and the display unit 140) to implement corresponding functions.

[0071] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0072] In this embodiment of the present application, the RF unit 110 may send the collected user input data to the server 200 , and receive the processing result sent by the server 200 .

[0073] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0074] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0075] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal 100 .

[0076] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0077] Next describe Figure 1 The product form of the server 200;

[0078] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0079] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0080] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0081] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a mechanical hard disk (HDD) or a solid state drive (SSD).

[0082] Among them, the memory 204 can be used to store software codes related to the method for constructing an energy equipment procurement model based on a large model, the processor 202 can execute the steps of the method for constructing an energy equipment procurement model based on a large model of the chip, and can also schedule other units to implement corresponding functions.

[0083] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0084] Based on the above framework structure, the present application also provides a device detection method. The device detection method of the embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0085] See also Figure 4 , the process of constructing the target procurement prediction model may include:

[0086] Step S101: extracting training data from a database, wherein the training data includes device-related data of a vectorized energy device.

[0087] In this solution, the training data can be stored in the database in advance. When the procurement forecast model needs to be built and trained, the training data can be directly retrieved from the database.

[0088] In this solution, a procurement forecast model can be constructed for each type of new energy equipment. The training data used in the construction and training of different procurement forecast models are training data consistent with the type of energy equipment. Therefore, in order to facilitate the rapid capture of training data, the training data can be grouped based on the type of energy equipment corresponding to the training data, and the training data belonging to the same type can be divided into the same group. When extracting training data, the corresponding training data group can be retrieved based on the type of energy equipment corresponding to the target procurement forecast model to be constructed.

[0089] For example, when the type of energy equipment required to build a target procurement prediction model is A, the training data set corresponding to A can be extracted from the database based on A.

[0090] Step S102: using the training data to train the initial procurement forecast model to obtain a target procurement forecast model, wherein the input of the target procurement forecast model is the equipment type and basic parameters, and the output is the performance indicators of each equipment matching the equipment type and basic parameters.

[0091] After obtaining the training data, the initial procurement model needs to be trained using the training data. Using the training data to train the initial procurement prediction model is a typical machine learning process. During the training process, the training data is divided into a training data set and a test data set. The ratio of the training data set is usually 70%-80%. The training data set is then used to train the selected initial procurement prediction model to obtain the target procurement prediction model.

[0092] In one embodiment, the performance indicators output by the target purchase prediction model include, but are not limited to: a combination of one or more of the equipment brand and specification model, defect rate estimate, energy efficiency coefficient estimate, maintenance cost estimate, and warranty period that match the equipment type and basic parameters. In addition to the above, users can also configure the output of the target purchase prediction model according to their own needs.

[0093] Step S103: obtaining an evaluation model, wherein the evaluation model is used to evaluate the output data of the target procurement prediction model.

[0094] In this step, an evaluation model is created. After the target purchase prediction model is trained, the training results are evaluated. At this time, the test set is used to evaluate the performance of the model. Common evaluation indicators include: mean square error (MSE): measures the average square error between the predicted value and the actual value, root mean square error (RMSE): the square root of MSE, which more intuitively represents the error size, mean absolute error (MAE): the average absolute error between the predicted value and the actual value, R² score: the goodness of fit of the regression model, the closer the value is to 1, the better the model performance. Then tune the model according to the evaluation results to improve performance. The optimization process can include hyperparameter tuning: use grid search, random search or Bayesian optimization methods to adjust the hyperparameters of the model. Feature selection optimization: further screen and optimize features to improve the performance of the model. Ensemble learning: use ensemble learning methods such as bagging and boosting to combine the prediction results of multiple models to improve overall performance.

[0095] Step S104: Integrate the target procurement prediction model and the evaluation model to obtain a target procurement model.

[0096] When the target procurement forecast model is evaluated by the evaluation model and the evaluation model is qualified, the qualified target procurement forecast model and the evaluation model are integrated together to form a comprehensive target procurement model for energy equipment. The purpose of integrating the target procurement forecast model with the evaluation model is to continuously optimize the target procurement forecast model based on the newly released energy equipment and actual usage effects in the subsequent process.

[0097] The scheme disclosed in the above-mentioned embodiment of the present application extracts the device-related data of the quantized energy equipment from the database, uses the device-related data as training data, and uses the training data to train the initial procurement prediction model to obtain a target procurement prediction model. The input of the target test model is the equipment type and basic parameters, and the output of the target procurement prediction model is the performance indicators of each device matching the equipment type and basic parameters. Then, an evaluation model is used to evaluate and optimize the target procurement prediction model, and the target procurement prediction model after evaluation and optimization is integrated with the evaluation model to obtain a target procurement model. At this time, when the user needs to select energy equipment, the equipment type and basic parameters of the required energy equipment can be used as input data of the target procurement prediction model, and the target procurement prediction model can generate recommendation results based on the target procurement prediction model, and the user can then select the required energy equipment from the recommendation results.

[0098] In the technical solution disclosed in this embodiment, before extracting training data from the database, it is necessary to add the equipment-related data of the energy equipment to the database. When collecting the equipment-related data of the energy equipment, data collection can be performed through a large model. The large model collects the equipment-related data of each published energy equipment through network data. The equipment-related parameters include but are not limited to a combination of one or more of brand, specification model, rated parameters, defect rate, years of operation, energy efficiency, selling price, and maintenance costs. Then, the equipment-related data is preprocessed, and the preprocessing at least includes a combination of one or more of redundant processing, data cleaning, processing missing values, and outlier processing, so that the equipment-related data entering the subsequent process is complete and reliable, and then the preprocessed equipment-related data is normalized or standardized. The embedding layer can use the embedding technology in deep learning to convert discrete features (such as brand, specification model) into continuous vectors. After obtaining the equipment-related data after normalization or standardization, the embedding layer is used to convert the equipment-related data after normalization or standardization into a vector form, and finally the equipment-related data in vector form is transferred and stored in the database. At this time, the training data can be retrieved from the database to train the model.

[0099] In this embodiment, considering that some new features of the equipment are related to the years of operation, in addition to using the above-mentioned equipment-related data as training items for the initial procurement prediction model, the combination of these features can also be used as training items to train the initial procurement prediction model. These combined features may include but are not limited to: combined features of defect rate and years of operation, combined features of energy efficiency and years of operation, and combined features of maintenance costs and years of operation. When training the initial procurement prediction model, the vectorized equipment-related data and the combined features are used together as training data to train the initial procurement prediction model.

[0100] After the target purchase prediction model is constructed, in order to make the output results of the target purchase prediction model more in line with user needs, in the subsequent use process, based on the feedback data of the output results of the target purchase prediction model (such as user feedback and the user's actual purchase data), the target purchase prediction model can be continuously optimized based on the feedback data and the feedback mechanism through the evaluation model, and the parameters and structure of the pre-model can be continuously adjusted to make the recommendation results of the target purchase prediction model more in line with user needs.

[0101] After creating the target procurement model, users can use the target procurement model. In the subsequent use of the target procurement forecast model, see Figure 5 , the use of this model includes:

[0102] Step S201: Acquire demand data input by a user, wherein the demand data includes device type and basic parameters;

[0103] In this step, the user can input the equipment type and basic parameters (rated parameters, etc.) of the equipment to be purchased through the human-computer interaction device.

[0104] Step S202: using the target procurement model to process the demand data to obtain performance indicators of various recommended devices.

[0105] The target procurement model is used to process the demand data to obtain various energy devices that match the demand data and performance indicators corresponding to these energy devices.

[0106] Step S203: tabulate the performance indicators of the recommended devices and display the processing results on a display.

[0107] In this step, in order to facilitate users to view the recommendation results, the generated procurement plan (performance indicators of each recommended device) can also be displayed to users. The plan includes data charts and text reports.

[0108] When displaying to users, a comprehensive score can be made based on the performance indicators and price of each device, and the scores can be sorted from high to low.

[0109] To facilitate user feedback, the system using the above method can also provide a user feedback interface, allowing users to evaluate and provide feedback on recommended solutions, while collecting user feedback data for further optimizing the target procurement model.

[0110] In this embodiment, corresponding to the above method, a device for constructing an energy equipment procurement model based on a large model is also provided. For the specific working content of each unit in the device, please refer to the content of the above method embodiment.

[0111] The following describes a device for constructing an energy equipment procurement model based on a large model provided in an embodiment of the present invention. The device for constructing an energy equipment procurement model based on a large model described below and the method for constructing an energy equipment procurement model based on a large model described above can refer to each other.

[0112] See also Figure 6 , the device may include:

[0113] A training data extraction unit 10, used to extract training data from a database, wherein the training data includes device-related data of the energy device after vectorization;

[0114] A prediction model training unit 20 is used to train the initial purchase prediction model using the training data to obtain a target purchase prediction model, wherein the input of the target purchase prediction model is the device type and basic parameters, and the output is the identity information and performance indicators of each device matching the device type and basic parameters;

[0115] An evaluation model acquisition unit 30, used to acquire an evaluation model, wherein the evaluation model is used to evaluate the output data of the target procurement prediction model;

[0116] The procurement model building unit 40 is used to integrate the target procurement prediction model and the evaluation model to obtain a target procurement model.

[0117] Corresponding to the above method, the above device may further include a user data acquisition unit for acquiring user input data.

[0118] The present application also provides an electronic device in an embodiment. Figure 7 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, car computers, etc. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0119] like Figure 7 As shown, the electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603, so as to implement the various steps of the above-mentioned method for constructing an energy equipment procurement model based on a large model. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0120] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0121] Also provided in an embodiment of the present application is a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any method for constructing a large-model-based energy equipment procurement model provided in an embodiment of the present application.

[0122] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any method for constructing a large-model-based energy equipment procurement model provided in an embodiment of the present application.

[0123] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0124] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0125] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0126] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for constructing an energy equipment procurement model based on a large model, characterized in that: include: Extracting training data from a database, wherein the training data includes device-related data of the vectorized energy device; The training data is used to train the initial purchase prediction model to obtain a target purchase prediction model, wherein the input of the target purchase prediction model is the device type and basic parameters, and the output is the identity information and performance indicators of each device matching the device type and basic parameters; Acquire an evaluation model, wherein the evaluation model is used to evaluate and optimize output data of the target procurement prediction model; The target procurement prediction model and the evaluation model are integrated to obtain a target procurement model.

2. The method for constructing a large-model-based energy equipment procurement model according to claim 1, characterized in that: Before extracting training data from the database, it also includes: Collect the published equipment-related data of various energy equipment through the big model, and the equipment-related parameters include but are not limited to one or a combination of brand, specification model, rated parameters, defect rate, years of operation, energy efficiency, selling price, and maintenance cost; Preprocessing the device-related data, wherein the preprocessing includes at least one or a combination of redundancy processing, data cleaning, processing missing values, and processing abnormal values; Standardize or normalize the pre-processed device-related data; Convert the standardized or normalized device-related data into vector form; The device-related data converted into vector form is stored in the database.

3. The method for constructing a large-model-based energy equipment procurement model according to claim 1, characterized in that: After vectorizing the processed device-related data, it also includes: A combination feature of the vectorized device-related data is established, and the combination feature is stored in a training database as the device-related data.

4. The method for constructing a large-model-based energy equipment procurement model according to claim 1, characterized in that: The combined features include but are not limited to: The combined characteristics of defect rate and years of operation, the combined characteristics of energy efficiency and years of operation, and the combined characteristics of maintenance costs and years of operation.

5. The method for constructing a large-model-based energy equipment procurement model according to claim 1, characterized in that: After obtaining the target procurement model, it also includes: Obtain feedback data of output data of the target purchase prediction model fed back by users; The evaluation model is used to adjust the parameters and structure of the target procurement forecast model based on the feedback data and feedback mechanism to optimize the target procurement forecast model.

6. The method for constructing a large-model-based energy equipment procurement model according to claim 1, characterized in that: The identity information and performance indicators output by the target procurement prediction model include but are not limited to: A combination of one or more of the equipment brand and specification model, defect rate estimate, energy efficiency coefficient estimate, maintenance cost estimate, and warranty period that match the equipment type and basic parameters.

7. The method for constructing a large-model-based energy equipment procurement model according to claim 1, characterized in that: After obtaining the target procurement model, it also includes: Obtaining demand data input by a user, wherein the demand data includes device type and basic parameters; The target procurement model is used to process the demand data to obtain performance indicators of various recommended equipment; The performance indicators of the various recommended devices are tabulated and the processing results are displayed on a display.

8. A device for constructing an energy equipment procurement model based on a large model, characterized in that: include: A training data extraction unit, used to extract training data from a database, wherein the training data includes device-related data of the vectorized energy device; A prediction model training unit, used to train the initial purchase prediction model using the training data to obtain a target purchase prediction model, wherein the input of the target purchase prediction model is the device type and basic parameters, and the output is the identity information and performance indicators of each device matching the device type and basic parameters; An evaluation model acquisition unit, used to acquire an evaluation model, wherein the evaluation model is used to evaluate the output data of the target procurement prediction model; The procurement model building unit is used to integrate the target procurement prediction model with the evaluation model to obtain a target procurement model.

9. A computer program product, characterized in that It includes computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the method for constructing an energy equipment procurement model based on a large model as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the method for constructing an energy equipment procurement model based on a large model as described in any one of claims 1 to 7.

Images