Heating and cooling device recommendation method, apparatus, device, medium, and program product

Abstract

The application relates to a cold and warm equipment recommendation method, equipment, device, medium and program product, belongs to the field of intelligent household appliances, acquires regional climate parameters and building type parameters input by a user, the regional climate parameters and the building type parameters are demand data of the user for cold and warm equipment, multi-dimensional analysis is performed on the regional climate parameters and the building type parameters, historical demand data in a large database is matched, a matching result is generated, the large database is used for storing historical demand data of the user and corresponding matched cold and warm equipment, according to the matching result, a plurality of cold and warm equipment recommendation schemes are generated, and each recommendation scheme contains different equipment selection combinations; the method realizes the pertinence, diversity and rationality of cold and warm equipment recommendation, and improves recommendation efficiency and user demand adaptation degree.

Description

Technical Field

[0001] This application relates to the field of smart home appliances, and more particularly to a method, equipment, device, medium, and program product for recommending heating and cooling equipment. Background Technology

[0002] With the increasing demand for energy-efficient and comfortable buildings, users are paying more and more attention to the compatibility of heating and cooling equipment with their actual usage environment. Different regional climate conditions (such as extreme temperatures, humidity, and seasonal variations) and the characteristics of the building itself (such as structural type, insulation performance, orientation, and area) significantly affect the load requirements and operating efficiency of heating and cooling systems. However, ordinary users often lack the professional ability to accurately assess their own needs, leading to the selection of equipment that is too large, too small, or has mismatched energy efficiency, resulting in energy waste or a poor user experience.

[0003] In existing technologies, the recommendation of heating and cooling equipment often relies on the experience and judgment of sales personnel, simple parameter comparison tables, or standardized design manuals. Although some intelligent systems have introduced basic climate or building data, they usually only perform single-dimensional matching and lack comprehensive analysis of the coupled effects of multiple factors.

[0004] However, existing solutions are generally based on static rule bases, which makes it difficult to dynamically adapt to diverse and personalized scenario needs, resulting in highly homogenized recommendation results and low adaptation accuracy. Summary of the Invention

[0005] This application provides a method, equipment, device, medium, and program product for recommending heating and cooling equipment, in order to solve the problem that existing solutions are generally based on static rule bases, which are difficult to dynamically adapt to diverse and personalized scenario needs, resulting in serious homogenization of recommendation results and low adaptation accuracy.

[0006] In a first aspect, embodiments of this application provide a method for recommending heating and cooling equipment, the method comprising:

[0007] Obtain the regional climate parameters and building type parameters input by the user, which are the user's demand data for heating and cooling equipment;

[0008] The regional climate parameters and building type parameters are analyzed from multiple dimensions, and historical demand data in a large database is matched to generate matching results. The large database is used to store users' historical demand data and corresponding matching heating and cooling equipment.

[0009] Based on the matching results, multiple recommended solutions for heating and cooling equipment are generated, each containing different combinations of equipment selection.

[0010] In one possible implementation, the step of performing multi-dimensional analysis of the regional climate parameters and the building type parameters, matching them with historical demand data in a large database, and generating matching results includes:

[0011] The regional climate parameters and the building type parameters are decomposed and feature extracted to obtain multi-dimensional feature data.

[0012] The multi-dimensional feature data is matched with the feature dimensions of historical demand data in the large database to calculate feature similarity.

[0013] Based on the ranking results of the feature similarity, historical data that meet the preset threshold of feature similarity are selected to generate the matching results.

[0014] In one possible implementation, matching the multi-dimensional feature data with the feature dimensions of historical demand data in a large database and calculating feature similarity includes:

[0015] The feature dimensions of the multi-dimensional feature data and the historical demand data in the large database are respectively vector-modeled to construct a feature vector matrix;

[0016] The feature vector matrix is ​​calculated using a cosine similarity algorithm to determine the feature similarity between the historical demand data and the regional climate parameters and the building type parameters.

[0017] In one possible implementation, the matching result includes heating and cooling equipment parameters, operating efficiency, and suitable scenarios. The step of generating multiple recommended heating and cooling equipment solutions based on the matching result includes:

[0018] Based on the parameters of the heating and cooling equipment and the operating efficiency, a first recommended heating and cooling equipment scheme is generated.

[0019] Based on the parameters of the heating and cooling equipment and the suitable scenario, a second recommended heating and cooling equipment scheme is generated.

[0020] Based on the first recommended heating and cooling equipment scheme and the second recommended heating and cooling equipment scheme, multiple recommended heating and cooling equipment schemes are determined.

[0021] In one possible implementation, after generating multiple recommended heating and cooling equipment schemes based on the matching results, the method further includes:

[0022] The system receives user feedback on recommended solutions for heating and cooling equipment, and stores the feedback information, along with corresponding regional climate parameters, building type parameters, and recommended solutions, in the large database.

[0023] In one possible implementation, the regional climate parameters include the annual average temperature, extreme temperature and humidity values, and the duration of the heating and cooling season, and the building type parameters include the building type, building area, and insulation level of the building envelope.

[0024] Secondly, embodiments of this application provide a device for recommending heating and cooling equipment, the method comprising:

[0025] The acquisition module is used to acquire the regional climate parameters and building type parameters input by the user, which are the user's demand data for heating and cooling equipment;

[0026] The generation module is used to perform multi-dimensional analysis of the regional climate parameters and the building type parameters, match them with historical demand data in the big database, and generate matching results. The big database is used to store users' historical demand data and corresponding matching heating and cooling equipment.

[0027] The generation module is also used to generate multiple recommended solutions for heating and cooling equipment based on the matching results, with each recommended solution containing different combinations of equipment selection.

[0028] In one possible implementation, the heating and cooling equipment recommendation device further includes: an extraction module and a matching module;

[0029] The extraction module is used to perform dimensional decomposition and feature extraction on the regional climate parameters and the building type parameters respectively to obtain multi-dimensional feature data.

[0030] The matching module is used to match the multi-dimensional feature data with the feature dimensions of historical demand data in the big data database and calculate the feature similarity.

[0031] The generation module is further configured to filter historical requirement data whose feature similarity meets a preset threshold based on the sorting result of the feature similarity, and generate the matching result.

[0032] In one possible implementation, the heating and cooling equipment recommendation device further includes: a construction module and a calculation module;

[0033] The construction module is used to perform vector modeling on the feature dimensions of multi-dimensional feature data and historical demand data in the big data database respectively, and construct a feature vector matrix.

[0034] The calculation module is also used to calculate the feature vector matrix using a cosine similarity algorithm, and to calculate the feature similarity between the historical demand data and the regional climate parameters and the building type parameters.

[0035] In one possible implementation, the generation module is further configured to generate a first recommended cooling and heating device scheme based on the cooling and heating device parameters and the operating efficiency;

[0036] The generation module is also used to generate a second recommended cooling and heating device scheme based on the parameters of the cooling and heating device and the adaptation scenario.

[0037] The determining module is further configured to determine multiple recommended cooling and heating equipment schemes based on the first recommended cooling and heating equipment scheme and the second recommended cooling and heating equipment scheme.

[0038] In one possible implementation, the heating and cooling equipment recommendation device further includes: a receiving module;

[0039] The receiving module is used to receive user feedback on the recommended solutions for the heating and cooling equipment, and to associate and store the feedback information with the corresponding regional climate parameters, building type parameters, and recommended solutions in the big data database.

[0040] In one possible implementation, the determining module is further configured to include the regional climate parameters, such as the annual average temperature, extreme temperature and humidity values, and the duration of the heating and cooling season, and the building type parameters, such as the building type, building area, and insulation level of the building envelope.

[0041] Thirdly, embodiments of this application provide a recommended device for heating and cooling equipment, including: a receiver, a transmitter, a memory, and a processor;

[0042] Receiver, used to receive instructions and data;

[0043] A transmitter is used to send commands and data;

[0044] The memory stores computer-executed instructions;

[0045] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0046] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0047] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0048] The heating and cooling equipment recommendation method provided in this application acquires regional climate parameters and building type parameters input by users, performs multi-dimensional cross-analysis of these key data reflecting heating and cooling needs, and intelligently compares them with historical user needs and corresponding successfully matched heating and cooling equipment solutions accumulated in a large database. This generates multiple highly adaptable equipment recommendation schemes. Each scheme includes different equipment selection combinations, which not only enhances the recommendation's relevance (fitting specific usage scenarios), diversity (providing multiple feasible paths), and rationality (based on historical validation data), but also improves recommendation efficiency and the accuracy of matching user needs, thereby increasing user satisfaction and system energy efficiency. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0050] Figure 1 Flowchart of the recommended method for heating and cooling equipment provided in this application Figure 1 ;

[0051] Figure 2 Flowchart of the recommended method for heating and cooling equipment provided in this application Figure 2 ;

[0052] Figure 3 A schematic diagram of the recommended heating and cooling equipment device provided in this application;

[0053] Figure 4 A schematic diagram of the structure of the recommended heating and cooling equipment provided in this application.

[0054] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, other embodiments obtained by those skilled in the art without creative effort are all within the scope of protection of this application.

[0056] As people's demands for building energy efficiency and indoor comfort continue to increase, users are paying more and more attention to the suitability of heating and cooling equipment for their specific usage environment. Climate characteristics (such as extreme temperatures, humidity levels, and seasonal changes) and building attributes (including structural form, thermal insulation performance, orientation, and building area) jointly determine the load characteristics and operating efficiency of heating and cooling systems. However, ordinary consumers often lack professional knowledge and find it difficult to accurately assess their actual needs, easily leading to improper equipment selection, such as overcapacity, insufficient capacity, or mismatched energy efficiency, resulting in energy waste or a decline in user experience.

[0057] The current market's equipment recommendation methods mainly rely on the salesperson's subjective experience, simplified parameter comparison tables, or general design specifications.

[0058] However, existing technologies generally use static rule bases for decision-making, which lacks the ability to respond flexibly to dynamic and personalized scenarios, resulting in homogenized recommendation results and limitations in both adaptation accuracy and user experience.

[0059] To address the aforementioned issues, the heating and cooling equipment recommendation method provided in this application acquires user-input regional climate parameters and building type parameters, and performs multi-dimensional cross-analysis of these key data reflecting the user's actual needs for heating and cooling equipment. Subsequently, the system intelligently compares and matches the analysis results with historical user demand data accumulated in the built-in large database and successfully matched heating and cooling equipment solutions, generating highly relevant matching results. Taking into account factors such as energy efficiency, cost, and installation conditions, the system automatically generates multiple differentiated heating and cooling equipment recommendation schemes. This method not only improves the accuracy and personalization of recommendations but also enhances user flexibility by providing diverse options, thereby improving the efficiency and user satisfaction of heating and cooling equipment recommendations while ensuring rationality.

[0060] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0061] Figure 1 Flowchart of the recommended method for heating and cooling equipment provided in this application Figure 1 The implementing entity in this embodiment is a heating and cooling equipment recommendation system. For example... Figure 1 As shown, the method includes:

[0062] S101: Obtain the regional climate parameters and building type parameters input by the user. The regional climate parameters and building type parameters are the user's demand data for heating and cooling equipment.

[0063] Specifically, to obtain the regional climate parameters and building type parameters input by users, a standardized requirements collection template must first be pre-set, clearly listing the core fields to be collected. Then, users are guided to fill out the template through multiple channels, such as online forms, offline staff assistance with data entry, and intelligent voice interaction for transcription and processing, to ensure that the information provided by users is complete, accurate, and without missing any key fields. After collection, the data undergoes preliminary verification to remove invalid information (such as incorrectly entered area or unreasonable temperature ranges), ultimately resulting in standardized regional climate parameters and building type parameters.

[0064] For example, Mr. Zhang plans to install heating and cooling systems in his new house. The system sends him a standardized requirements collection form, which clearly requires him to fill in relevant core fields. Mr. Zhang fills it out according to his actual situation. After the staff verifies the information provided by Mr. Zhang and confirms that there are no errors or omissions, they organize this information into standardized regional climate parameters and building type parameters.

[0065] S102: Perform multi-dimensional analysis of regional climate parameters and building type parameters, match historical demand data in a large database, and generate matching results. The large database is used to store users' historical demand data and corresponding matching heating and cooling equipment.

[0066] Specifically, firstly, the acquired regional climate parameters and building type parameters are broken down to determine the analysis dimensions. Then, the system calls upon historical data from a large database and, according to a preset matching algorithm, compares the current user's multi-dimensional analysis results with the historical user's demand data one by one, filtering out historical demand records with similarity reaching a preset threshold. Simultaneously, it extracts the corresponding heating and cooling equipment selection information from these historical records.

[0067] For example, the system performs a multi-dimensional analysis of Mr. Zhang's regional climate parameters and building type parameters. Then, it accesses a large database, compares the data with historical requirements, and filters out records with a similarity of ≥80%. The system sorts these two historical records and their corresponding equipment information by similarity, marking differences (Ms. Wang's house is slightly larger, and her target summer temperature is slightly higher), thus generating a matching result.

[0068] S103: Based on the matching results, generate multiple recommended solutions for heating and cooling equipment, each of which includes different combinations of equipment selection.

[0069] Specifically, first, the system considers the user's current regional climate parameters and building type parameters. Then, it bases its analysis on historical equipment selections from the matching results. Finally, each solution is validated to ensure it meets all user constraints, and then compiled into a standardized recommendation document.

[0070] For example, based on Mr. Zhang's needs, three differentiated heating and cooling equipment recommendations are generated. All three recommendations meet all of Mr. Zhang's constraints and are differentiated in terms of brand, price, and user experience. The system compiles the equipment details, energy consumption, and advantages of each recommendation into a booklet and sends it to Mr. Zhang.

[0071] The heating and cooling equipment recommendation method provided in this application obtains regional climate parameters and building type parameters input by the user. These parameters represent the user's demand data for heating and cooling equipment. The method performs multi-dimensional analysis on these parameters, matches them with historical demand data in a large database, and generates matching results. The large database stores the user's historical demand data and corresponding matched heating and cooling equipment. Based on the matching results, multiple heating and cooling equipment recommendation schemes are generated, each containing different equipment selection combinations. This method achieves targeted, diverse, and reasonable heating and cooling equipment recommendations, improving recommendation efficiency and user demand adaptability.

[0072] Figure 2 Flowchart of the recommended method for heating and cooling equipment provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the recommended method for heating and cooling equipment is described in detail, and the method includes:

[0073] S201: Obtain the regional climate parameters and building type parameters input by the user. The regional climate parameters and building type parameters are the user's demand data for heating and cooling equipment.

[0074] Step S201 is similar to step S101, and will not be described again here.

[0075] Optional regional climate parameters include annual average temperature, extreme temperature and humidity values, and heating and cooling season duration; building type parameters include building unit type, building area, and insulation level of the building envelope.

[0076] Specifically, the system sets up specialized input items in the user input interface according to the refined parameter dimensions. Among them, the regional climate parameter needs to clearly distinguish the specific duration of the heating season and cooling season (the selectable range should be marked according to the local meteorological department's standards), and the extreme temperature and humidity values ​​need to distinguish between the lowest in winter and the highest in summer. In the building type parameter, the thermal insulation level of the building envelope provides options of Level 1, Level 2, and Level 3 according to national standards, and the apartment type provides options according to common types (one-bedroom to five-bedroom, villas, etc.). The building area supports manual input of values ​​and the unit of measurement. Users can complete the parameters according to the actual situation, and the unadded parameters can be temporarily saved with the default values.

[0077] For example, after a user enters basic parameters, the system prompts them to add more detailed parameters. The user then enters regional climate parameters (extreme maximum temperature of 32℃, heating season duration of 6 months, cooling season duration of 1 month) and building type parameters (insulation level of building envelope of grade II). The system integrates the added parameters to form the user's complete set of required parameters.

[0078] S202: Dimensional decomposition and feature extraction are performed on regional climate parameters and building type parameters respectively to obtain multi-dimensional feature data.

[0079] Specifically, a data preprocessing algorithm is used to first decompose the regional climate parameters into two sub-dimensions: temperature (annual average temperature, extreme temperature and humidity values) and season (duration of heating and cooling season). Core features of each sub-dimension are extracted (e.g., temperature difference and extreme value fluctuation range are extracted for the temperature dimension). Next, the building type parameters are decomposed into three sub-dimensions: scale (building area), unit type (unit structure), and insulation (insulation level of building envelope). Features of each sub-dimension are extracted (e.g., features related to unit area load are extracted for the scale dimension, and features related to heat transfer coefficient are extracted for the insulation dimension). Finally, all extracted features are integrated to form standardized multi-dimensional feature data, ensuring that each feature dimension is consistent and computable.

[0080] For example, the system processes the complete parameters input by the user, breaking down the regional climate parameters into temperature (annual average temperature -5℃, extreme temperature and humidity difference 60℃) and season (heating season 6 months, cooling season 1 month), extracting core features (heating season duration 50%, extreme temperature fluctuation 23℃); it also breaks down the building type parameters into size (120㎡, unit area load reference value 120W / ㎡), apartment type (three bedrooms, 1 master bedroom, 2 secondary bedrooms, 1 living room), and insulation (level 2 insulation, heat transfer coefficient 0.6W / (㎡·K)); finally, it integrates these to obtain multi-dimensional feature data.

[0081] S203: Match multi-dimensional feature data with the feature dimensions of historical demand data in a large database and calculate feature similarity.

[0082] Feature similarity is a quantitative indicator that measures the degree of similarity between current data and a certain historical data. The higher the similarity, the stronger the reference value of the historical data.

[0083] Specifically, the historical demand data in the large database is first preprocessed to ensure that its feature dimensions are consistent with the current user's multi-dimensional feature data (such as both including temperature features, building scale features, etc.); then, a feature matching algorithm is used to compare the current feature data with the corresponding feature dimensions of each historical data one by one to establish a matching association; then, through a preset similarity calculation model, the matching results are converted into quantitative similarity values ​​(the value ranges from 0 to 1, and the closer to 1, the higher the similarity).

[0084] For example, the system calls upon historical data stored in a large database to filter out 50 historical demand data related to "northern frigid regions, three-bedroom apartments, building area of ​​110-130㎡, and level 2 insulation." This ensures that the feature dimensions of these historical data (temperature, heating season length, building size, etc.) are consistent with the feature dimensions of the current user. Then, the current user's feature data (annual average temperature -5℃, heating season of 6 months, 120㎡, and level 2 insulation) is compared with the corresponding features of each historical data point. Through calculation, it is found that one historical data point with the characteristics of "northern frigid regions, three-bedroom apartments, 125㎡, level 2 insulation, annual average temperature -4.8℃, and heating season of 6 months" has the highest feature similarity of 0.92 with the current user, which is the highest among all historical data points.

[0085] Optionally, specific implementation methods for matching multi-dimensional feature data with the feature dimensions of historical demand data in a large database to calculate feature similarity include:

[0086] The feature dimensions of the multi-dimensional feature data and the historical demand data in the large database are respectively vector-modeled to construct a feature vector matrix;

[0087] The cosine similarity algorithm is used to calculate the feature similarity between historical demand data, regional climate parameters, and building type parameters.

[0088] Vector modeling refers to transforming unstructured, multi-dimensional feature data into a quantifiable and computable vector form. Each feature dimension corresponds to a component of the vector, and the feature vector matrix is ​​a matrix formed by integrating the current user's feature vector with all historical data feature vectors.

[0089] Cosine similarity algorithm is a commonly used similarity calculation method. It quantifies the degree of similarity between two vectors by calculating the cosine value of the angle between them. The smaller the angle, the larger the cosine value, and the higher the similarity.

[0090] Specifically, firstly, vector modeling is performed to determine the weights of all feature dimensions (weights are assigned based on the degree of influence of each feature on heating and cooling needs, such as assigning a higher weight to extreme temperatures than to the annual average temperature). The multi-dimensional feature data of the current user is transformed into a row vector, and the feature data of each historical demand data in the large database is also transformed into row vectors. All vectors are integrated to form a feature vector matrix (the number of rows is the number of historical data entries + 1, and the number of columns is the number of feature dimensions). Next, the cosine similarity algorithm is applied, using the current user's feature vector as a benchmark, to calculate the cosine value of its relationship with each historical feature vector in the matrix. The calculation formula is as follows: , where a is the current user feature vector and b is the historical feature vector; finally, the cosine similarity value between each historical data and the current user data is obtained, that is, the feature similarity.

[0091] For example, the system first performs vector modeling on the current user's feature data, determining the feature dimensions and weights (extreme minimum temperature weight 0.3, heating season length weight 0.2, building area weight 0.2, insulation level weight 0.3), transforming it into a feature vector a = (-28, 6, 120, 0.6); then, it transforms a historical data point with high similarity from the large database (extreme minimum temperature -27℃, heating season 6 months, 125㎡, insulation level 0.6) into a feature vector b = (-27, 6, 125, 0.6); and finally, it calculates the feature vector using a cosine similarity algorithm. Consistent with the previously calculated feature similarity, the cosine similarity of the other 49 historical data points was also calculated, forming a complete similarity list.

[0092] S204: Based on the ranking results of feature similarity, filter out historical data that meet the preset threshold of feature similarity and generate matching results.

[0093] The matching results include parameters of heating and cooling equipment, operating efficiency, and suitable scenarios.

[0094] Specifically, firstly, the similarity list is sorted from highest to lowest value, ensuring that the historical data with the highest similarity is listed first. Then, the system's preset similarity threshold is called (which can be adjusted according to the actual application scenario, generally set to 0.7-0.8), and the sorted historical data is compared one by one to filter out all historical data with similarity ≥ the threshold. Finally, information is extracted from the filtered historical data, and the parameters of the heating and cooling equipment (such as equipment model, power, cooling and heating capacity), operating efficiency (such as COP value, energy consumption index), and suitable scenarios (such as suitable user type, climate characteristics) corresponding to each data point are integrated to form a structured matching result, and the similarity value of each result is labeled.

[0095] For example, the system sorts 50 historical data entries from highest to lowest similarity, with a preset similarity threshold of 0.7. It then filters out 12 historical data entries with a similarity ≥ 0.7, among which the historical data entry with the highest similarity is still the one with 0.92. The system then extracts the core information from these 12 historical data entries to generate matching results. For example, the matching information corresponding to the historical data entry with a similarity of 0.92 is: heating and cooling equipment parameters (air source heat pump, model XXXX-01, heating capacity 30kW, input power 8.5kW), operating efficiency (COP value 3.5, winter heating energy consumption 12kWh / ㎡), and suitable scenario (northern cold regions, 120-130㎡ three-bedroom apartment, level 2 insulation housing, long-term low temperature environment in winter). All 12 matching results are heating and cooling equipment configurations for similar types of housing.

[0096] S205: Generate the first recommended cooling and heating equipment scheme based on the parameters and operating efficiency of the heating and cooling equipment.

[0097] Specifically, firstly, statistical analysis is performed on the parameters and operating efficiency of the heating and cooling equipment in the matching results to screen out equipment models with high operating efficiency (e.g., COP value ≥ 3.0) and high compatibility between equipment parameters and the current user's building size and climate conditions; then, based on the current user's actual needs (e.g., heating and cooling load, energy consumption budget), the parameters of the screened equipment are fine-tuned (e.g., adjusting the heating capacity of the equipment to 28-32kW based on a 120㎡ building area); finally, information such as equipment model, specific parameters, operating efficiency indicators, and estimated energy consumption costs is integrated to form the first recommended solution.

[0098] For example, the system analyzes 12 matching results and filters out 5 air source heat pump models with an operating efficiency COP value ≥ 3.0 and heating capacity suitable for a 120㎡ house. Considering the climate characteristics of the user's location in the cold northern region (long winters with low temperatures), the system prioritizes models with strong low-temperature adaptability and fine-tunes the equipment parameters (adjusting the heating capacity to 29kW to suit the heating load of a 120㎡ three-bedroom house). Finally, the system generates the first recommended solution: recommending an air source heat pump (model XXXX-02), with equipment parameters (heating capacity 29kW, input power 8.2kW, COP value 3.4 under low-temperature conditions), operating efficiency (winter heating energy consumption 11.8kWh / ㎡, annual energy saving of approximately 15%), and an estimated annual energy cost of 2832 yuan. The system also indicates that this solution is suitable for level-two insulated houses in the cold northern region, demonstrating outstanding energy-saving effects.

[0099] S206: Generate a second recommended cooling and heating system based on the parameters of the heating and cooling equipment and the applicable scenarios.

[0100] Specifically, the process begins by analyzing the matching scenarios in the results, filtering out historical data that highly matches the current user scenario (climate type, building type, insulation level), and analyzing the device's usage feedback and adaptation effects in similar scenarios. Then, the parameters of the heating and cooling equipment corresponding to this historical data are extracted, and combined with the current user's apartment structure (e.g., room layout of a three-bedroom apartment) and usage needs (e.g., whether individual room temperature control is required), the equipment parameters are optimized and adjusted (e.g., adding individual room temperature control function, adjusting the equipment installation location to suit the apartment type). Finally, information such as equipment model, specific parameters, scenario adaptation advantages, and user experience highlights are integrated to form a second recommended solution.

[0101] For example, from 12 matching results, the system filters out 8 historical data entries suitable for the scenario of "severe cold regions in the north, 120-130㎡ three-bedroom apartment, level 2 insulation". It focuses on the ease of installation and room-by-room temperature control effect of the equipment in this scenario. Based on the room layout of the user's three-bedroom apartment (master bedroom 15㎡, second bedroom 12㎡, second bedroom 10㎡, living room 35㎡), it selects an air source heat pump model that supports room-by-room temperature control and adjusts the equipment parameters (heating capacity 28kW, equipped with 4-way room-by-room temperature control module, suitable for multiple rooms). Finally, it generates a second recommended solution: a recommended air source heat pump (model XXXX-03D), with equipment parameters (heating capacity 28kW, input power 8.0kW, supports room-by-room temperature control, low-temperature start-up temperature -30℃), and scenario adaptation advantages (perfectly adapted to the low-temperature environment of winter in severe cold regions in the north, room-by-room temperature control can meet the temperature needs of different rooms, installation location suitable for the living room balcony, without occupying indoor space). It also notes that this solution is suitable for families with elderly people and children, as it is convenient to use and offers flexible temperature adjustment.

[0102] S207: Based on the first and second recommended cooling and heating equipment schemes, determine multiple recommended cooling and heating equipment schemes.

[0103] Specifically, firstly, the core differences and advantages of the first and second schemes are clearly defined, and both schemes are used as basic recommended schemes, retaining their complete equipment parameters, advantages, estimated costs, and other information. Then, combining the core features of the two schemes, 1-2 combined schemes are derived (such as combining the high efficiency and energy-saving advantages of the first scheme with the room-by-room temperature control function of the second scheme). At the same time, other suitable equipment models are selected from the matching results to supplement one alternative scheme, ensuring that the total number of recommended schemes is no less than 3. Finally, all recommended schemes are compiled, and the core advantages, applicable users, and estimated costs of each scheme are marked to form a unified list of multiple recommended schemes, which is convenient for users to compare and choose.

[0104] For example, the system uses the first scheme (XXXX-02, high efficiency and energy saving) and the second scheme (XXXX-03D, scene adaptation) as the basic schemes, retaining all the information of the two schemes. Then, a third combination scheme is derived: recommending an air source heat pump (model XXXX-02D), which combines the high efficiency and energy saving of the first scheme (COP value 3.4, annual energy consumption 11.8kWh / ㎡) and the room temperature control function of the second scheme, with equipment parameters (heating capacity 29kW, input power 8.3kW, supports room temperature control, low temperature start-up -30℃). A fourth alternative scheme is added (model ASHP-30, heating capacity 30kW, COP value 3.3, suitable for 120-130㎡ residences, no room temperature control, lower cost). Finally, four recommended schemes are formed, with the core advantages and estimated costs of each scheme marked, for users of 120㎡ three-bedroom apartments in the cold northern regions to choose according to their budget and usage needs.

[0105] S208: Receives user feedback on recommended solutions for heating and cooling equipment, and stores the feedback information, along with the corresponding regional climate parameters, building type parameters, and recommended solutions, in a large database.

[0106] Specifically, the system first receives user feedback through an interactive interface, setting standardized feedback options (such as "Select Option 1", "Select Option 2", "Reject all options, reason: 'Suggest adding a certain type of equipment model'"), while also supporting users to manually input custom feedback. Then, the system automatically extracts the user's core data (regional climate parameters, building type parameters, and multiple recommended options), associates and binds the feedback information with this data, and marks the feedback time and user preferences (such as prioritizing energy saving or prioritizing individual room temperature control). Finally, the complete associated data is stored in a large database in a unified format, updating the historical demand data in the database. When processing other similar user needs in the future, this feedback data can be called to optimize the recommendation results.

[0107] For example, a user in a frigid northern region with a 120㎡ three-bedroom apartment, after reviewing four recommended options, provides feedback: "I selected the third combination option (XXXX-02D). My core requirements are energy saving and individual room temperature control, and my budget is acceptable." The system automatically extracts the user's relevant data (regional climate parameters: annual average temperature -5℃, extreme minimum temperature -28℃, heating season of 6 months; building type parameters: three-bedroom, 120㎡, level 2 insulation; 4 recommended options), binds the feedback information to this data, and marks the feedback time and user preference (balancing energy saving and individual room temperature control). Then, the bound complete data is stored in a large database. Subsequently, when other users in frigid northern regions with similar requirements—around 120㎡ three-bedroom apartments, level 2 insulation, and a preference for energy saving and individual room temperature control—enter this feedback data and prioritize recommending similar combination options, improving the targeting and accuracy of the recommendations.

[0108] The heating and cooling equipment recommendation method provided in this application first obtains the regional climate parameters and building type parameters input by the user. These two types of parameters together constitute the user's core demand data for heating and cooling equipment. Then, the regional climate parameters and building type parameters are decomposed and feature extracted to obtain structured multi-dimensional feature data. Next, the multi-dimensional feature data is matched with the feature dimensions of historical demand data stored in a large database, and the feature similarity between the two is calculated. Then, based on the ranking result of feature similarity, historical demand data that meets a preset threshold is selected to generate a matching result. After that, a first heating and cooling equipment recommendation scheme is generated based on the heating and cooling equipment parameters and operating efficiency in the matching result. At the same time, a second heating and cooling equipment recommendation scheme is generated by combining the heating and cooling equipment parameters and suitable scenarios in the matching result. Finally, multiple heating and cooling equipment recommendation schemes containing different equipment selection combinations are determined based on these two schemes. Finally, the user's feedback information on the recommendation scheme is received, and the feedback information is associated with the corresponding regional climate parameters, building type parameters, and recommendation schemes and stored in a large database. This method realizes the targeting, diversity, and rationality of heating and cooling equipment recommendations, and effectively improves recommendation efficiency and user demand adaptability.

[0109] Figure 3 A schematic diagram of the recommended heating and cooling device provided in this application is shown below. Figure 3 As shown, the heating and cooling equipment recommendation device 300 provided in this embodiment includes:

[0110] The acquisition module 301 is used to acquire the regional climate parameters and building type parameters input by the user. The regional climate parameters and building type parameters are the user's demand data for heating and cooling equipment.

[0111] The generation module 302 is used to perform multi-dimensional analysis of regional climate parameters and building type parameters, match historical demand data in the big database, and generate matching results. The big database is used to store users' historical demand data and corresponding matching heating and cooling equipment.

[0112] The generation module 302 is also used to generate multiple recommended solutions for heating and cooling equipment based on the matching results, with each recommended solution containing different combinations of equipment selection.

[0113] In one possible implementation, the heating and cooling equipment recommendation device further includes: an extraction module 303 and a matching module 304;

[0114] The extraction module 303 is used to perform dimensional decomposition and feature extraction on regional climate parameters and building type parameters respectively to obtain multi-dimensional feature data;

[0115] The matching module 304 is used to match multi-dimensional feature data with the feature dimensions of historical demand data in a large database and calculate feature similarity.

[0116] The generation module 302 is also used to filter out historical data whose feature similarity meets a preset threshold based on the sorting results of feature similarity and generate matching results.

[0117] In one possible implementation, the heating and cooling equipment recommendation device further includes: a construction module 305 and a calculation module 306;

[0118] Module 305 is used to perform vector modeling on the feature dimensions of multi-dimensional feature data and historical demand data in the large database, and construct feature vector matrices.

[0119] The calculation module 306 is also used to calculate the feature vector matrix using the cosine similarity algorithm, and to calculate the feature similarity between historical demand data and regional climate parameters and building type parameters.

[0120] In one possible implementation, the heating and cooling equipment recommendation device further includes: a determination module 307;

[0121] The generation module 302 is also used to generate a first recommended cooling and heating equipment scheme based on the parameters and operating efficiency of the cooling and heating equipment;

[0122] The generation module 302 is also used to generate a second recommended cooling and heating device scheme based on the parameters of the cooling and heating devices and the applicable scenarios.

[0123] The determination module 307 is also used to determine multiple recommended cooling and heating equipment schemes based on the first recommended cooling and heating equipment scheme and the second recommended cooling and heating equipment scheme.

[0124] In one possible implementation, the heating and cooling equipment recommendation device further includes: a receiving module 308;

[0125] The receiving module 308 is used to receive feedback information from users regarding recommended solutions for heating and cooling equipment, and to associate and store the feedback information with the corresponding regional climate parameters, building type parameters, and recommended solutions in a large database.

[0126] In one possible implementation, the determining module 307 is also used for regional climate parameters including annual average temperature, extreme temperature and humidity values ​​and heating and cooling season duration, and building type parameters including building unit type, building area and building envelope insulation level.

[0127] Figure 4 A structural diagram of the recommended heating and cooling equipment provided in this application. (Example) Figure 4 As shown, this application provides a heating and cooling equipment recommendation device 400, which includes: a receiver 401, a transmitter 402, a processor 403, and a memory 404.

[0128] Receiver 401 is used to receive instructions and data;

[0129] Transmitter 402 is used to send commands and data;

[0130] Memory 404 is used to store instructions executed by the computer;

[0131] The processor 403 is used to execute computer execution instructions stored in the memory 404 to implement the various steps of the heating and cooling equipment recommendation method in the above embodiments. For details, please refer to the relevant descriptions in the foregoing embodiments of the heating and cooling equipment recommendation method.

[0132] Alternatively, the memory 404 can be either standalone or integrated with the processor 403.

[0133] When the memory 404 is set up independently, the electronic device also includes a bus for connecting the memory 404 and the processor 403.

[0134] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the heating and cooling equipment recommendation method performed by the aforementioned heating and cooling equipment recommendation device.

[0135] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method provided in any of the foregoing embodiments.

[0136] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0137] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for recommending heating and cooling equipment, characterized in that, The method includes: Obtain the regional climate parameters and building type parameters input by the user, whereby the regional climate parameters and building type parameters are the user's demand data for heating and cooling equipment; The regional climate parameters and building type parameters are analyzed from multiple dimensions, and historical demand data in a large database is matched to generate matching results. The large database is used to store users' historical demand data and corresponding matching heating and cooling equipment. Based on the matching results, multiple recommended solutions for heating and cooling equipment are generated, each containing different combinations of equipment selection.

2. The method according to claim 1, characterized in that, The process involves multi-dimensional analysis of the regional climate parameters and the building type parameters, matching them with historical demand data in a large database, and generating matching results, including: The regional climate parameters and the building type parameters are decomposed and feature extracted to obtain multi-dimensional feature data. The multi-dimensional feature data is matched with the feature dimensions of historical demand data in the large database to calculate feature similarity. Based on the ranking results of the feature similarity, historical data that meet the preset threshold of feature similarity are selected to generate the matching results.

3. The method according to claim 2, characterized in that, The step of matching the multi-dimensional feature data with the feature dimensions of historical demand data in the big data database and calculating feature similarity includes: The feature dimensions of the multi-dimensional feature data and the historical demand data in the large database are respectively vector-modeled to construct a feature vector matrix; The feature vector matrix is ​​calculated using a cosine similarity algorithm to determine the feature similarity between the historical demand data and the regional climate parameters and the building type parameters.

4. The method according to claim 1, characterized in that, The matching results include heating and cooling equipment parameters, operating efficiency, and suitable scenarios. Based on the matching results, multiple recommended heating and cooling equipment solutions are generated, including: Based on the parameters of the heating and cooling equipment and the operating efficiency, a first recommended heating and cooling equipment scheme is generated. Based on the parameters of the heating and cooling equipment and the suitable scenario, a second recommended heating and cooling equipment solution is generated; Based on the first recommended heating and cooling equipment scheme and the second recommended heating and cooling equipment scheme, multiple recommended heating and cooling equipment schemes are determined.

5. The method according to claim 1, characterized in that, After generating multiple recommended heating and cooling equipment schemes based on the matching results, the process further includes: The system receives user feedback on recommended solutions for heating and cooling equipment, and stores the feedback information, along with corresponding regional climate parameters, building type parameters, and recommended solutions, in the large database.

6. The method according to any one of claims 1-5, characterized in that, The regional climate parameters include the annual average temperature, extreme temperature and humidity values, and the duration of the heating and cooling season. The building type parameters include the building type, building area, and insulation level of the building envelope.

7. A device for recommending heating and cooling equipment, characterized in that, include: The acquisition module is used to acquire the regional climate parameters and building type parameters input by the user, which are the user's demand data for heating and cooling equipment; The generation module is used to perform multi-dimensional analysis of the regional climate parameters and the building type parameters, match them with historical demand data in the big database, and generate matching results. The big database is used to store users' historical demand data and corresponding matching heating and cooling equipment. The generation module is also used to generate multiple recommended solutions for heating and cooling equipment based on the matching results, with each recommended solution containing different combinations of equipment selection.

8. A recommended device for heating and cooling, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images