A home configuration method, apparatus, device and medium

Abstract

Embodiments of the present application provide a home configuration method, device, equipment and medium, the method comprises: obtaining the home configuration demand information of a target user; determining the data score level of the target user according to the home configuration demand information of the target user and preset data score rules; obtaining the target recommendation model according to the data score level of the target user; determining the target home configuration information according to the home configuration demand information of the target user and the target recommendation model; the configuration scheme meeting the user demand can be automatically and quickly generated, the configuration efficiency is significantly improved, the user waiting time is shortened, the user demand is accurately met, and the user experience and satisfaction are improved.

Description

A method, apparatus, device, and medium for home configuration Technical Field

[0001] This invention relates to the field of home furnishing technology, and in particular to a home furnishing configuration method, apparatus, device, and medium. Background Technology

[0002] In the current era of rapid development of smart homes, with continuous technological advancements and consumers' increasing demands for quality of life, smart home products have gradually permeated people's daily lives, bringing users unprecedented convenience and comfort. However, this booming development is also accompanied by a series of challenges, especially in the installation and configuration of smart homes. Faced with a dazzling array of smart home products on the market and their complex and ever-changing application scenarios, users, while enjoying the convenience brought by smart technology, also face many difficulties during the initial setup process.

[0003] Traditionally, smart home installation often requires a significant amount of manual configuration work from professional installers and maintenance technicians. This includes, but is not limited to, selecting devices, setting up inter-device linkage rules, and customizing scenarios based on specific user needs. This process is not only time-consuming and labor-intensive but also demands a high level of expertise from the installers and maintenance technicians, thus increasing labor and learning costs. Furthermore, due to the complexity of smart home systems and the diversity of user needs, configuration errors or omissions are prone to occur during installation and maintenance, leading to system malfunctions.

[0004] This heavy reliance on manual configuration severely hinders the rapid iteration and updates of smart home products. Whenever a new technology or product emerges, installation and maintenance workers need to relearn and master the new configuration methods, which not only reduces work efficiency but also limits the speed of smart home technology adoption and the improvement of user experience. Summary of the Invention

[0005] In view of the above problems, embodiments of the present invention are proposed to provide a home configuration method, apparatus, device and medium that overcomes or at least partially solves the above problems.

[0006] To address the aforementioned problems, this invention discloses a home furnishing configuration method, the method comprising:

[0007] Obtain information on the home furnishing needs of target users;

[0008] Based on the target user's home furnishing needs and preset data scoring rules, determine the target user's data scoring level;

[0009] Based on the target user's data rating level, obtain the target recommendation model;

[0010] Based on the target user's home furnishing needs and the target recommendation model, the target home furnishing information is determined.

[0011] Optionally, the target user's home furnishing needs information includes the types of home furnishing needs of the target user and the target user's home furnishing reference information. The step of determining the target user's data rating level based on the target user's home furnishing needs information and preset data rating rules includes:

[0012] Based on the types of home furnishing needs of the target user, the target user's home furnishing reference information, and the preset data scoring rules, the data scoring level of the target user is determined.

[0013] Optionally, the types of home furnishing needs of the target user include personalized recommendations, and the preset data scoring rules include a first scoring rule. Determining the data scoring level of the target user based on the types of home furnishing needs, the target user's home furnishing reference information, and the preset data scoring rules includes:

[0014] When the target user's home furnishing needs are classified as personalized recommendations, the target user's data rating level is determined based on the target user's home furnishing reference information and the first rating rule.

[0015] Optionally, the data rating level includes a first rating level, the target recommendation model includes a first recommendation model, and obtaining the target recommendation model based on the target user's data rating level includes:

[0016] If the target user's data rating level is the first rating level, then the first recommendation model is used as the target recommendation model.

[0017] Optionally, determining the target home furnishing configuration information based on the target user's home furnishing configuration needs and the target recommendation model includes:

[0018] When the first recommendation model is used as the target recommendation model, candidate home configuration information is determined based on the target user's home configuration needs information and the target recommendation model.

[0019] Output the candidate home furnishing configuration information to the user;

[0020] Obtain feedback information from the target user regarding the candidate home furnishing configuration information;

[0021] Based on the feedback information and the candidate home furnishing configuration information, the target home furnishing configuration information is determined.

[0022] Optionally, the types of home furnishing needs of the target user include public recommendations, and the preset data scoring rules include a second scoring rule. Determining the data scoring level of the target user based on the types of home furnishing needs, the target user's home furnishing reference information, and the preset data scoring rules includes:

[0023] If the target user's home furnishing needs are based on general recommendations, the target user's data rating level is determined according to the target user's home furnishing reference information and the second rating rule.

[0024] Optionally, the data rating level includes a second rating level, the target recommendation model includes a second recommendation model, and obtaining the target recommendation model based on the target user's data rating level includes:

[0025] If the target user's data rating level is the second rating level, the second recommendation model will be used as the target recommendation model.

[0026] Optionally, the method further includes:

[0027] When the second recommendation model is used as the target recommendation model, the target user's demand information features are obtained based on the target user's home furnishing configuration demand information and the target recommendation model.

[0028] The step of determining the target home furnishing configuration information based on the target user's home furnishing configuration needs and the target recommendation model includes:

[0029] Based on the target user's home furnishing configuration needs, the characteristics of the needs, and the target recommendation model, the target home furnishing configuration information is determined.

[0030] Optionally, the data rating level includes a third rating level, the target recommendation model includes a third recommendation model, and obtaining the target recommendation model based on the target user's data rating level includes:

[0031] If the target user's data rating level is the third rating level, then the third recommendation model will be used as the target recommendation model.

[0032] Optionally, the method further includes:

[0033] When the third recommendation model is used as the target recommendation model, a preset home furnishing configuration information topology map is obtained; the home furnishing configuration information topology map is used to represent the correspondence between user needs and home furnishing configuration information.

[0034] The step of determining the target home furnishing configuration information based on the target user's home furnishing configuration needs and the target recommendation model includes:

[0035] The target home configuration information is determined based on the target user's home configuration needs information, the preset home configuration information topology map, and the target recommendation model.

[0036] On the other hand, embodiments of the present invention also disclose a home configuration device, the device comprising:

[0037] The demand information acquisition module is used to acquire the home furnishing configuration demand information of target users;

[0038] The rating level acquisition module is used to determine the data rating level of the target user based on the target user's home configuration needs information and preset data rating rules;

[0039] The recommendation model acquisition module is used to acquire the target recommendation model based on the data rating level of the target user;

[0040] The target information acquisition module is used to determine the target home configuration information based on the target user's home configuration needs information and the target recommendation model.

[0041] Optionally, the target user's home furnishing needs information includes the types of home furnishing needs of the target user and the target user's home furnishing reference information; the rating level acquisition module includes:

[0042] The demand rating level acquisition submodule is used to determine the data rating level of the target user based on the types of home configuration needs of the target user, the home configuration reference information of the target user, and the preset data rating rules.

[0043] Optionally, the target user's home furnishing configuration needs include personalized recommendations, the preset data scoring rules include a first scoring rule, and the needs scoring level acquisition submodule includes:

[0044] The first rating level acquisition unit is used to determine the data rating level of the target user based on the target user's home configuration reference information and the first rating rule when the target user's home configuration needs are personalized recommendations.

[0045] Optionally, the data rating level includes a first rating level, the target recommendation model includes a first recommendation model, and the recommendation model acquisition module includes:

[0046] The first model acquisition submodule is used to select the first recommendation model as the target recommendation model when the data rating level of the target user is a first rating level.

[0047] Optionally, the target information acquisition module includes:

[0048] The candidate information acquisition submodule is used to determine candidate home configuration information based on the target user's home configuration needs information and the target recommendation model when the first recommendation model is used as the target recommendation model;

[0049] The candidate information output submodule is used to output the candidate home configuration information to the user;

[0050] The feedback information acquisition submodule is used to acquire feedback information from the target user regarding the candidate home configuration information;

[0051] The first target information acquisition submodule is used to determine the target home configuration information based on the feedback information and the candidate home configuration information.

[0052] Optionally, the target user's home furnishing configuration needs include popular recommendations, the preset data scoring rules include a second scoring rule, and the needs scoring level acquisition submodule includes:

[0053] The second rating level acquisition unit is used to determine the data rating level of the target user based on the target user's home configuration reference information and the second rating rule, when the target user's home configuration needs are classified as general recommendations.

[0054] Optionally, the data rating level includes a second rating level, the target recommendation model includes a second recommendation model, and the recommendation model acquisition module includes:

[0055] The second model acquisition submodule is used to use the second recommendation model as the target recommendation model when the data rating level of the target user is the second rating level.

[0056] Optionally, the device further includes:

[0057] The demand feature acquisition submodule is used to acquire the demand information features of the target user based on the home configuration demand information of the target user and the target recommendation model when the second recommendation model is used as the target recommendation model.

[0058] The target information acquisition module includes:

[0059] The second target information acquisition submodule is used to determine the target home configuration information based on the target user's home configuration needs information, the features of the needs information, and the target recommendation model.

[0060] Optionally, the data rating level includes a third rating level, the target recommendation model includes a third recommendation model, and the recommendation model acquisition module includes:

[0061] The third model acquisition submodule is used to select the third recommendation model as the target recommendation model when the target user's data rating level is the third rating level.

[0062] Optionally, the device further includes:

[0063] The topology map acquisition submodule is used to acquire a preset home furnishing configuration information topology map when the third recommendation model is used as the target recommendation model; the home furnishing configuration information topology map is used to represent the correspondence between user needs and home furnishing configuration information;

[0064] The target information acquisition module includes:

[0065] The third target information acquisition submodule is used to determine the target home configuration information based on the target user's home configuration requirements, the preset home configuration information topology map, and the target recommendation model.

[0066] Accordingly, this invention discloses an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various steps of the above-described home configuration method embodiments.

[0067] Accordingly, embodiments of the present invention disclose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the various steps of the above-described home configuration method embodiments.

[0068] The embodiments of this invention offer the following advantages: By acquiring users' home configuration needs and utilizing data scoring rules and target recommendation models, these embodiments can automatically and quickly generate configuration schemes that meet user requirements, significantly improving configuration efficiency and shortening user waiting time. The preset data scoring rules and target recommendation models reduce the professional skills required of installation and maintenance personnel. Even non-professional users can easily complete the configuration under the system's guidance, ensuring the accuracy of the configuration results and reducing human error. Based on the user's specific needs and data scoring level, the most suitable target recommendation model is selected to generate a personalized home configuration scheme. This personalized configuration method can more accurately meet user needs, improving user experience and satisfaction. In the field of smart home installation and configuration, this invention achieves multiple beneficial effects, including simplified configuration processes and improved efficiency, reduced professional skill requirements and improved configuration accuracy, realization of personalized configuration and precise satisfaction of user needs, enhanced system flexibility and scalability, and increased user satisfaction and loyalty. Attached Figure Description

[0069] Figure 1 is a flowchart of a home furnishing configuration method according to an embodiment of the present invention;

[0070] Figure 2 is a flowchart of the recommended model training process according to an embodiment of the home furnishing configuration method of the present invention;

[0071] Figure 3 is a structural block diagram of an embodiment of a home configuration device of the present invention. Detailed Implementation

[0072] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0073] One of the core concepts of this invention is to utilize the data requirements and usage characteristics of different models to provide different recommendation models for home furnishing configurations for different users, thereby making the recommendation process more personalized.

[0074] Referring to Figure 1, a flowchart of an embodiment of the home furnishing configuration method of the present invention is shown, which may specifically include the following steps:

[0075] Step 101: Obtain the home furnishing configuration needs information of the target users;

[0076] Obtaining information on the home configuration needs of target users is a crucial step in the home design, renovation, or smart home system configuration process. This step involves collecting and understanding the specific needs and expectations of target users (customers or end users) regarding their home environment.

[0077] In one example, the types of home furnishing needs information for the target user can include spatial layout, style preferences, color matching, furniture selection, functional requirements, smart home requirements, budget constraints, and timeframes; the collection methods can be various methods at both online and offline levels, and this embodiment of the invention does not limit them.

[0078] Step 102: Determine the data rating level of the target user based on the target user's home configuration needs information and preset data scoring rules;

[0079] Step 102 is a crucial step in the home furnishing, design, or upgrade process; the pre-set data scoring rules are designed to objectively and quantitatively assess the target user's home furnishing needs. These rules can be derived from industry experience or from business requirements.

[0080] In one instance, pre-defined data scoring rules can evaluate the home furnishing needs information provided by target users through the following dimensions:

[0081] In terms of data quality, we assess the completeness, accuracy, consistency, and timeliness of the home furnishing needs information provided by target users.

[0082] In terms of demand priority, the demands of the target users are ranked according to their importance and urgency to determine which demands need to be met first.

[0083] In terms of data volume, we assess whether the effective amount of home furnishing configuration needs information provided by the target users is sufficient to support the data volume requirements of the evaluation model.

[0084] After collecting information on the home furnishing needs of the target users and clarifying the preset data scoring rules, the next step is to score the users' needs based on these rules and determine their data score level.

[0085] In one example, this scoring process could be:

[0086] The home furnishing needs information of target users is cleaned, organized, and standardized to ensure the accuracy and consistency of the data.

[0087] Based on preset data scoring rules, each requirement is scored item by item, providing an objective and quantitative assessment of user needs. The calculation method can be weighted calculation, function calculation, or linear calculation; the specific calculation method can be determined according to business needs, and this embodiment of the invention does not limit it.

[0088] Then, based on the rating results, the user's data rating is divided into different levels. The grading method can be percentile method, natural breakpoint method, etc., and this embodiment of the invention does not limit this method. Through objective and quantitative rating and grading, it is possible to better understand the user's needs and expectations, thereby developing home furnishing configuration solutions that better suit the user's preferences, and improving user satisfaction and loyalty.

[0089] In one embodiment, the target user's home furnishing configuration requirements information includes the types of home furnishing configuration requirements of the target user and the target user's home furnishing configuration reference information. Step 102 may include the following sub-steps:

[0090] Sub-step S11: Determine the data rating level of the target user based on the types of home furnishing needs of the target user, the home furnishing reference information of the target user, and the preset data rating rules.

[0091] The types of home furnishing needs of target users refer to the specific categories of their needs for home furnishings, such as general needs or personalized needs. These types of needs reflect users' comprehensive requirements and expectations for their home environment, as well as their pursuit of individuality.

[0092] Home furnishing reference information for target users refers to home furnishing examples, pictures, videos, or text descriptions provided by users for reference. This information helps to more intuitively understand users' preferences and styles, as well as their expectations for home furnishing.

[0093] Through the above, the embodiments of the present invention can comprehensively consider the types of home furnishing needs of target users, reference information, and preset data scoring rules, providing strong support for subsequent home furnishing work.

[0094] In one embodiment, the target user's home furnishing needs include personalized recommendations, the preset data scoring rules include a first scoring rule, and sub-step S11 may be:

[0095] Sub-step S111: If the target user's home configuration needs are personalized recommendations, determine the target user's data rating level based on the target user's home configuration reference information and the first rating rule.

[0096] When the target user's home furnishing needs are personalized recommendations, the user needs to provide more and more valuable information about their home furnishing needs. Therefore, the scoring rules are set to a stricter first scoring rule, which places relatively high demands on the quality of the data.

[0097] In one embodiment, the target user's home furnishing needs include popular recommendations, the preset data scoring rules include a second scoring rule, and sub-step S111 may also be...

[0098] If the target user's home furnishing needs are based on general recommendations, the target user's data rating level is determined according to the target user's home furnishing reference information and the second rating rule.

[0099] When the target user's home furnishing needs are based on general recommendations, the user needs to provide more and more valuable information about their home furnishing needs. Therefore, the scoring rules are set to a relatively less strict second scoring rule, in which the requirements for data quality are relatively lower.

[0100] Step 103: Obtain the target recommendation model based on the target user's data rating level;

[0101] Different target recommendation models will be used for different data levels, further improving the flexibility of this method and meeting users' personalized needs.

[0102] In one embodiment, the data rating level includes a first rating level, the target recommendation model includes a first recommendation model, and step 103 may include the following sub-steps:

[0103] Sub-step S21: If the target user's data rating level is the first rating level, the first recommendation model is used as the target recommendation model.

[0104] In one example, the first recommendation model could be a hybrid model combining a multilayer perceptron (MLP) and reinforcement learning.

[0105] MLP (Multi-Layered Programmable LP) is a feedforward artificial neural network that maps inputs to outputs through multiple fully connected layers and non-linear activation functions. An MLP consists of an input layer, several hidden layers, and an output layer. Each layer contains several neurons connected by weights. Each neuron calculates a weighted sum of its input and weights, then performs a non-linear transformation through an activation function before outputting it to the next layer of neurons.

[0106] Reinforcement learning is a machine learning method that uses the interaction between an agent and its environment to update and optimize the training process, maximizing cumulative rewards through actions, rewards, and observations. Reinforcement learning does not rely on labeled data; instead, it uses reward signals as guidance, enabling the agent to learn how to take actions through trial and error.

[0107] In one example, the algorithm model based on the MLP multilayer perceptron is regarded as an agent, which is responsible for recommending smart home configuration information based on the target user's home configuration needs.

[0108] The target user's home furnishing needs are considered the environment for reinforcement learning. For example, the state of the environment can be represented by a set of feature vectors, such as the size of the home space, layout type, light intensity, user's historical purchase records, browsing history, etc. The recommendation decision made by the model in this instance is regarded as an action, and the user's feedback information on this recommendation, such as liking, neutral, or disliking, is regarded as a reward for this action.

[0109] For example, when a user uses the system for the first time, they input basic home information such as space size, layout, initial preferences, and personal data. The MLP agent processes and analyzes the environmental state to generate a preliminary recommendation strategy. Based on this strategy, the agent recommends specific smart home configurations, such as a smart light fixture. After viewing the recommendations, the user expresses their satisfaction by rating the information. The system converts user feedback into numerical rewards and feeds them back to the agent. The agent adjusts its recommendation strategy based on the reward signals, such as increasing or decreasing the weight of certain types of recommendations, to optimize future recommendation performance. This invention combines the powerful nonlinear modeling and generalization capabilities of MLP with the autonomous learning and optimization of reinforcement learning. By using reinforcement learning to optimize the parameters or strategies of the MLP, it can enable the MLP to exhibit higher performance when handling complex tasks. Simultaneously, the MLP can also provide reinforcement learning with rich state representations and action selection candidates. In this way, more personalized, efficient, and satisfactory home configuration solutions can be provided to users.

[0110] In one embodiment, the data rating level includes a second rating level, the target recommendation model includes a second recommendation model, and step 103 may further include the following sub-steps:

[0111] Sub-step S31: If the data rating level of the target user is the second rating level, the second recommendation model is used as the target recommendation model.

[0112] In one example, the second recommendation model could be a hybrid model combining MLP and other deep learning algorithms.

[0113] In one example, the second recommendation model could be a hybrid model combining MLP and Convolutional Neural Networks (CNN);

[0114] CNN is a deep learning model particularly well-suited for processing data with a grid-like topology, such as images. It achieves efficient feature extraction and learning of complex visual patterns from image data through components such as convolutional layers, pooling layers, and fully connected layers.

[0115] For example, a CNN can be used to extract features from home space images provided by a target user's home furnishing needs, capturing local features such as furniture layout and color scheme. Then, the extracted features are flattened into one-dimensional vectors and fed into a Multi-Level Processing (MLP) for further processing. The MLP can then generate personalized home furnishing recommendations based on the user's preferences, such as preferred styles and colors, and the image features extracted by the CNN. For instance, if a user prefers a minimalist style and white tones, the MLP can combine the spatial layout features extracted by the CNN to recommend a white, minimalist sofa to place in the center of the living room.

[0116] Combining MLP and CNN enables recommendation models in smart home configuration recommendations to analyze image data of the home space and suggest suitable furniture layouts to improve space utilization efficiency and aesthetics. Based on user preferences and image information of the home space, the hybrid model can provide style and color matching suggestions to create a more harmonious and unified home environment. By combining user personal preferences and the characteristics of the home space, the hybrid model can recommend suitable smart home devices, such as smart lighting systems and smart curtains, to enhance the overall intelligence of the home. Therefore, the hybrid model has significant advantages in the field of smart home configuration recommendations, capable of handling complex data relationships and generating recommendation results that meet user expectations.

[0117] In one embodiment, the data rating level includes a third rating level, the target recommendation model includes a third recommendation model, and step 103 may further include the following sub-steps:

[0118] Sub-step S41: If the data rating level of the target user is the third rating level, the third recommendation model is used as the target recommendation model.

[0119] In one example, when the home furnishing needs information provided by the target user is judged to be at the third rating level according to the preset data scoring rules, it means that the data provided by the user is of low quality or very little quantity. In this case, using a complex model may not produce ideal recommendations. Therefore, choosing a simple basic model for home furnishing recommendations will be more efficient and accurate.

[0120] Step 104: Determine the target home furnishing configuration information based on the target user's home furnishing configuration needs and the target recommendation model.

[0121] In one embodiment, when the first recommendation model is used as the target recommendation model, step 104 may include the following steps:

[0122] Sub-step S51: Determine candidate home furnishing configuration information based on the target user's home furnishing configuration needs information and the target recommendation model;

[0123] Based on the target user's home furnishing needs and the target recommendation model, a set of possible home furnishing configuration schemes are generated.

[0124] Sub-step S52: Output the candidate home configuration information to the user;

[0125] The generated candidate home furnishing configuration information is displayed to the user for viewing and selection. The display format can be through a graphical interface, virtual reality, augmented reality, etc., and this embodiment of the invention does not limit the specific method used.

[0126] Sub-step S53: Obtain feedback information from the target user regarding the candidate home furnishing configuration information;

[0127] Collect user feedback and opinions on candidate home furnishing options to further optimize recommendations.

[0128] Sub-step S54: Determine the target home configuration information based on the feedback information and the candidate home configuration information.

[0129] Based on user feedback, a final home furnishing configuration plan that meets user needs is determined.

[0130] In one embodiment, when the second recommendation model is used as the target recommendation model, the method may further include:

[0131] Based on the target user's home furnishing configuration needs and the target recommendation model, obtain the target user's needs information features;

[0132] By utilizing other deep learning algorithms to extract deeper features from the home furnishing configuration needs provided by the target users, the hybrid model can flexibly process various forms of data.

[0133] For example, CNNs excel at processing image data, capturing subtle features and spatial relationships within images; RNNs (Recurrent Neural Networks) are well-suited for processing sequential data, such as user behavior sequences; and Transformers have unique advantages in processing natural language text and long sequence data. Since Transformers, RNNs, and CNNs are all existing technologies, they will not be elaborated upon further. It should be noted that the examples of RNNs, CNNs, and Transformers are provided for ease of understanding; the selection of algorithms can be adjusted according to data and business needs, and should not be construed as a limitation of this invention.

[0134] Step 104 may also include the following sub-steps:

[0135] Sub-step S61: Determine the target home configuration information based on the target user's home configuration requirements, the characteristics of the requirements, and the target recommendation model.

[0136] In one embodiment, when a third recommendation model is used as the target recommendation model, the method further includes:

[0137] Obtain a preset home furnishing configuration information topology diagram; the home furnishing configuration information topology diagram is used to represent the correspondence between user needs and home furnishing configuration information.

[0138] A topology graph is a graphical structure representing the relationships between elements. It can be used to describe the connections and dependencies between various elements in a home furnishing layout. In third-party recommendation models, topology graphs are used to simplify the problem space and quickly identify key nodes and paths, thereby improving the accuracy and efficiency of recommendations with limited data. Topology graph data can be obtained through online surveys, professional data acquisition from companies within the industry, and other methods.

[0139] Step 104 may also include the following sub-steps

[0140] Sub-step S71: Determine the target home configuration information based on the target user's home configuration requirements information, the preset home configuration information topology map, and the target recommendation model.

[0141] In one embodiment, when the amount of data on the target user's home configuration needs is sufficient and the data quality meets the preset requirements, the model is a hybrid model combining deep learning, reinforcement learning, and MLP.

[0142] Based on the deep extraction of user needs and characteristics, reinforcement learning is used to dynamically adjust according to real-time user feedback, achieving the highest level of personalization and accurate recommendations.

[0143] In one example, the process could be:

[0144] First, the system uses deep learning models such as CNN and RNN to extract deep features from users' home configuration needs, such as house floor plans, furniture layouts, and user preferences. These features include the size, shape, and lighting conditions of the house, the user's preferred furniture style and color, and the user's functional requirements for smart home devices.

[0145] After extracting user needs features, the system uses a reinforcement learning model to dynamically adjust based on real-time user feedback. For example, if a user repeatedly rejects a certain style of furniture recommendation, the system may reduce the frequency of recommending that style of furniture and instead recommend furniture that better suits the user's preferences.

[0146] Based on the dynamic adjustment of recommendation strategies by the reinforcement learning model, the system utilizes MLP to make decisions on the final recommendation scheme. MLP can generate an optimal smart home configuration scheme for users by comprehensively considering various factors such as furniture compatibility, space utilization, and cost-effectiveness, based on user demand features extracted by the deep learning model and recommendation strategies learned by the reinforcement learning model.

[0147] This invention, by acquiring users' home configuration needs and utilizing data scoring rules and target recommendation models, can automatically and quickly generate configuration schemes that meet user requirements, significantly improving configuration efficiency and shortening user waiting time. Through preset data scoring rules and target recommendation models, the professional skills required of installation and maintenance personnel are reduced. Even non-professional users can easily complete the configuration under the system's guidance, while ensuring the accuracy of the configuration results and reducing human error. Based on the user's specific needs and data scoring level, the most suitable target recommendation model is selected to generate a personalized home configuration scheme. This personalized configuration method can more accurately meet user needs, improving user experience and satisfaction. In the field of smart home installation and configuration, this invention achieves multiple beneficial effects, including simplified configuration processes and improved efficiency, reduced professional skill requirements and improved configuration accuracy, realization of personalized configuration and precise satisfaction of user needs, enhanced system flexibility and scalability, and increased user satisfaction and loyalty.

[0148] Referring to Figure 2, a schematic diagram of the recommendation model training of an embodiment of the home configuration method of the present invention is shown;

[0149] Firstly, user home furnishing preference data can be obtained through online voting, questionnaires, and device data tracking. Simultaneously, user usage data information can be obtained from companies within the home furnishing industry.

[0150] The acquired data is cleaned by removing extreme values ​​and normalizing. Data with many missing or abnormal values ​​is deleted, data with few missing or abnormal values ​​is imputed by mean, and duplicate data is deduplicated to obtain the dataset.

[0151] By integrating the dataset and classifying it according to preset dimensions required by the business, the classified information is standardized to obtain the training and validation sets needed to train the recommendation model. The model is then trained iteratively using the training and validation sets. Once the model's accuracy reaches a preset threshold, it is deployed on a server for user use.

[0152] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0153] Referring to Figure 3, a structural block diagram of an embodiment of the home configuration device of the present invention is shown, which may specifically include the following modules:

[0154] The demand information acquisition module 201 is used to acquire the home furnishing configuration demand information of the target user;

[0155] The rating level acquisition module 202 is used to determine the data rating level of the target user based on the target user's home configuration needs information and preset data rating rules;

[0156] The recommendation model acquisition module 203 is used to acquire a target recommendation model based on the data rating level of the target user;

[0157] The target information acquisition module 204 is used to determine the target home configuration information based on the target user's home configuration needs information and the target recommendation model.

[0158] In one embodiment, the target user's home furnishing needs information includes the types of home furnishing needs of the target user and the target user's home furnishing reference information; the rating level acquisition module includes:

[0159] The demand rating level acquisition submodule is used to determine the data rating level of the target user based on the types of home configuration needs of the target user, the home configuration reference information of the target user, and the preset data rating rules.

[0160] In one embodiment, the target user's home furnishing configuration needs include personalized recommendations, the preset data scoring rules include a first scoring rule, and the needs scoring level acquisition submodule includes:

[0161] The first rating level acquisition unit is used to determine the data rating level of the target user based on the target user's home configuration reference information and the first rating rule when the target user's home configuration needs are personalized recommendations.

[0162] In one embodiment, the data rating level includes a first rating level, the target recommendation model includes a first recommendation model, and the recommendation model acquisition module includes:

[0163] The first model acquisition submodule is used to select the first recommendation model as the target recommendation model when the data rating level of the target user is a first rating level.

[0164] In one embodiment, the target information acquisition module includes:

[0165] The candidate information acquisition submodule is used to determine candidate home configuration information based on the target user's home configuration needs information and the target recommendation model when the first recommendation model is used as the target recommendation model;

[0166] The candidate information output submodule is used to output the candidate home configuration information to the user;

[0167] The feedback information acquisition submodule is used to acquire feedback information from the target user regarding the candidate home configuration information;

[0168] The first target information acquisition submodule is used to determine the target home configuration information based on the feedback information and the candidate home configuration information.

[0169] In one embodiment, the target user's home furnishing needs include general recommendations, the preset data scoring rules include a second scoring rule, and the needs scoring level acquisition submodule includes:

[0170] The second rating level acquisition unit is used to determine the data rating level of the target user based on the target user's home configuration reference information and the second rating rule, when the target user's home configuration needs are classified as general recommendations.

[0171] In one embodiment, the data rating level includes a second rating level, the target recommendation model includes a second recommendation model, and the recommendation model acquisition module includes:

[0172] The second model acquisition submodule is used to use the second recommendation model as the target recommendation model when the data rating level of the target user is the second rating level.

[0173] In one embodiment, the device further includes:

[0174] The demand feature acquisition submodule is used to acquire the demand information features of the target user based on the home configuration demand information of the target user and the target recommendation model when the second recommendation model is used as the target recommendation model.

[0175] The target information acquisition module includes:

[0176] The second target information acquisition submodule is used to determine the target home configuration information based on the target user's home configuration needs information, the features of the needs information, and the target recommendation model.

[0177] In one embodiment, the data rating level includes a third rating level, the target recommendation model includes a third recommendation model, and the recommendation model acquisition module includes:

[0178] The third model acquisition submodule is used to select the third recommendation model as the target recommendation model when the target user's data rating level is the third rating level.

[0179] In one embodiment, the device further includes:

[0180] The topology map acquisition submodule is used to acquire a preset home furnishing configuration information topology map when the third recommendation model is used as the target recommendation model; the home furnishing configuration information topology map is used to represent the correspondence between user needs and home furnishing configuration information;

[0181] The target information acquisition module includes:

[0182] The third target information acquisition submodule is used to determine the target home configuration information based on the target user's home configuration requirements, the preset home configuration information topology map, and the target recommendation model.

[0183] This invention, by acquiring users' home configuration needs and utilizing data scoring rules and target recommendation models, can automatically and quickly generate configuration schemes that meet user requirements, significantly improving configuration efficiency and shortening user waiting time. Through preset data scoring rules and target recommendation models, the professional skills required of installation and maintenance personnel are reduced. Even non-professional users can easily complete the configuration under the system's guidance, while ensuring the accuracy of the configuration results and reducing human error. Based on the user's specific needs and data scoring level, the most suitable target recommendation model is selected to generate a personalized home configuration scheme. This personalized configuration method can more accurately meet user needs, improving user experience and satisfaction. In the field of smart home installation and configuration, this invention achieves multiple beneficial effects, including simplified configuration processes and improved efficiency, reduced professional skill requirements and improved configuration accuracy, realization of personalized configuration and precise satisfaction of user needs, enhanced system flexibility and scalability, and increased user satisfaction and loyalty.

[0184] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0185] This invention also provides an electronic device, comprising:

[0186] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described home configuration method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here.

[0187] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described home configuration method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0188] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0189] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0190] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0191] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0192] These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable terminal equipment, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0193] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0194] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0195] The present invention has provided a detailed description of a home configuration method, apparatus, device, and medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A home furnishing configuration method, characterized in that, The method includes: acquiring home furnishing configuration needs information of a target user; determining the data rating level of the target user based on the home furnishing configuration needs information and preset data rating rules; determining a target recommendation model in a preset recommendation model based on the data rating level of the target user; and determining target home furnishing configuration information based on the home furnishing configuration needs information of the target user and the target recommendation model. The home furnishing configuration needs information of the target user includes the types of home furnishing configuration needs of the target user and home furnishing configuration reference information of the target user. The step of determining the data rating level of the target user based on the home furnishing configuration needs information and preset data rating rules includes: determining the data rating level of the target user based on the types of home furnishing configuration needs of the target user, the home furnishing configuration reference information of the target user, and the preset data rating rules.

2. The home furnishing configuration method according to claim 1, characterized in that, The target user's home furnishing needs include personalized recommendations, and the preset data scoring rules include a first scoring rule. The step of determining the target user's data scoring level based on the target user's home furnishing needs, the target user's home furnishing reference information, and the preset data scoring rules includes: when the target user's home furnishing needs are personalized recommendations, determining the target user's data scoring level based on the target user's home furnishing reference information and the first scoring rule.

3. The home furnishing configuration method according to claim 2, characterized in that, The data rating level includes a first rating level, the target recommendation model includes a first recommendation model, and the step of determining the target recommendation model from the preset recommendation models based on the target user's data rating level includes: when the target user's data rating level is the first rating level, using the first recommendation model as the target recommendation model.

4. The home furnishing configuration method according to claim 3, characterized in that, The step of determining the target home furnishing configuration information based on the target user's home furnishing configuration needs information and the target recommendation model includes: when using the first recommendation model as the target recommendation model, determining candidate home furnishing configuration information based on the target user's home furnishing configuration needs information and the target recommendation model; outputting the candidate home furnishing configuration information to the user; obtaining feedback information from the target user regarding the candidate home furnishing configuration information; and determining the target home furnishing configuration information based on the feedback information and the candidate home furnishing configuration information.

5. The home furnishing configuration method according to claim 1, characterized in that, The target user's home furnishing needs include popular recommendations, and the preset data scoring rules include a second scoring rule. The step of determining the target user's data scoring level based on the target user's home furnishing needs, the target user's home furnishing reference information, and the preset data scoring rules includes: when the target user's home furnishing needs are popular recommendations, determining the target user's data scoring level based on the target user's home furnishing reference information and the second scoring rule.

6. The home furnishing configuration method according to claim 5, characterized in that, The data rating level includes a second rating level, the target recommendation model includes a second recommendation model, and the step of determining the target recommendation model from the preset recommendation models based on the target user's data rating level includes: when the target user's data rating level is the second rating level, using the second recommendation model as the target recommendation model.

7. The home furnishing configuration method according to claim 6, characterized in that, The method further includes: when using the second recommendation model as the target recommendation model, obtaining the target user's demand information features based on the target user's home furnishing configuration demand information and the target recommendation model; the step of determining the target home furnishing configuration information based on the target user's home furnishing configuration demand information and the target recommendation model includes: determining the target home furnishing configuration information based on the target user's home furnishing configuration demand information, the demand information features, and the target recommendation model.

8. The home furnishing configuration method according to claim 5, characterized in that, The data rating level includes a third rating level, the target recommendation model includes a third recommendation model, and the step of determining the target recommendation model from the preset recommendation models based on the target user's data rating level includes: when the target user's data rating level is the third rating level, using the third recommendation model as the target recommendation model.

9. The home furnishing configuration method according to claim 8, characterized in that, The method further includes: obtaining a preset home configuration information topology map when the third recommendation model is used as the target recommendation model; the home configuration information topology map is used to represent the correspondence between user needs and home configuration information; the step of determining the target home configuration information based on the target user's home configuration needs information and the target recommendation model includes: determining the target home configuration information based on the target user's home configuration needs information, the preset home configuration information topology map and the target recommendation model.

10. A home furnishing device, characterized in that, The device includes: a demand information acquisition module for acquiring home furnishing configuration demand information of a target user; a rating level acquisition module for determining the data rating level of the target user based on the home furnishing configuration demand information and preset data rating rules; a recommendation model acquisition module for determining a target recommendation model from preset recommendation models based on the data rating level of the target user; and a target information acquisition module for determining target home furnishing configuration information based on the home furnishing configuration demand information of the target user and the target recommendation model. The home furnishing configuration demand information of the target user includes the types of home furnishing configuration demands and the home furnishing configuration reference information of the target user. The rating level acquisition module includes: a demand rating level acquisition submodule for determining the data rating level of the target user based on the types of home furnishing configuration demands, the home furnishing configuration reference information, and preset data rating rules.

11. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the home configuration method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the home configuration method as described in any one of claims 1-9.

Images