Home configuration method, device, equipment and medium

Abstract

The embodiment of the invention provides a home configuration method and device, equipment and a medium. The method comprises the following steps: acquiring home configuration demand information of a target user; according to the home configuration demand information of the target user and a preset data scoring rule, determining a data scoring level of the target user; obtaining a target recommendation model according to the data scoring level of the target user; determining target home configuration information according to the home configuration demand information of the target user and the target recommendation model; according to the method, the configuration scheme meeting the user requirements can be automatically and quickly generated, the configuration efficiency is remarkably improved, the user waiting time is shortened, the user requirements are accurately met, and the user experience and the satisfaction degree are improved.

Description

Technical Field

[0001] The present invention relates to the field of home furnishing technology, and in particular to a home furnishing configuration method, device, equipment and medium. Background Art

[0002] In the current era of rapid development of smart home, with the continuous advancement of technology and the increasing demand of consumers for quality of life, smart home products have gradually penetrated into people's daily lives, bringing users unprecedented convenience and comfort. However, the booming development of this field is also accompanied by a series of challenges, especially in the installation and configuration of smart home. Faced with a wide range of smart home products on the market and their complex and changing application scenarios, while enjoying the convenience brought by intelligence, users also face many troubles in the initialization process.

[0003] Traditionally, the installation of smart homes often requires professional installation and maintenance workers to perform a lot of manual configuration work, including but not limited to device selection, setting of linkage rules between devices, and personalized customization of scenes according to specific user needs. This process is not only time-consuming and labor-intensive, but also requires high professional skills of installation and maintenance workers, which invisibly increases labor costs and learning costs. In addition, due to the complexity of smart home systems and the diversity of user needs, configuration errors or omissions are prone to occur during the installation and maintenance process, resulting in the system not being able to operate normally.

[0004] This highly manual configuration method seriously hinders the rapid iteration and update of smart home products. Whenever a new technology or product comes out, maintenance workers need to relearn and master new configuration methods, which not only reduces work efficiency, but also limits the speed of popularization of smart home technology 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, device, equipment and medium that overcome the above problems or at least partially solve the above problems.

[0006] In order to solve the above problem, an embodiment of the present invention discloses a home configuration method, the method comprising:

[0007] Obtain home configuration requirement information of target users;

[0008] Determining the data scoring level of the target user according to the home configuration requirement information of the target user and the preset data scoring rules;

[0009] Obtaining a target recommendation model according to the data rating level of the target user;

[0010] Target home configuration information is determined according to the home configuration requirement information of the target user and the target recommendation model.

[0011] Optionally, the home configuration requirement information of the target user includes the home configuration requirement type of the target user and the home configuration reference information of the target user, and determining the data scoring level of the target user according to the home configuration requirement information of the target user and a preset data scoring rule includes:

[0012] The data scoring level of the target user is determined according to the type of home configuration requirement of the target user, the home configuration reference information of the target user and the preset data scoring rules.

[0013] Optionally, the home configuration requirement type of the target user includes personalized recommendation, the preset data scoring rule includes a first scoring rule, and determining the data scoring level of the target user according to the home configuration requirement type of the target user, the home configuration reference information of the target user and the preset data scoring rule includes:

[0014] In a case where the home configuration requirement type of the target user is personalized recommendation, the data scoring level of the target user is determined according to the home configuration reference information of the target user and the first scoring rule.

[0015] Optionally, the data scoring level includes a first scoring level, the target recommendation model includes a first recommendation model, and acquiring the target recommendation model according to the data scoring level of the target user includes:

[0016] When the data rating level of the target user is the first rating level, the first recommendation model is used as the target recommendation model.

[0017] Optionally, determining target home configuration information according to the home configuration requirement information of the target user and the target recommendation model includes:

[0018] In the case where the first recommendation model is used as the target recommendation model, determining candidate home configuration information according to the home configuration requirement information of the target user and the target recommendation model;

[0019] Outputting the candidate home configuration information to a user;

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

[0021] Determine target home configuration information according to the feedback information and the candidate home configuration information.

[0022] Optionally, the home configuration requirement type of the target user includes public recommendation, the preset data scoring rule includes a second scoring rule, and determining the data scoring level of the target user according to the home configuration requirement type of the target user, the home configuration reference information of the target user and the preset data scoring rule includes:

[0023] In a case where the home configuration requirement type of the target user is public recommendation, the data scoring level of the target user is determined according to the home configuration reference information of the target user and the second scoring rule.

[0024] Optionally, the data scoring level includes a second scoring level, the target recommendation model includes a second recommendation model, and acquiring the target recommendation model according to the data scoring level of the target user includes:

[0025] When the data rating level of the target user is the second rating level, the second recommendation model is used as the target recommendation model.

[0026] Optionally, the method further comprises:

[0027] In the case where the second recommendation model is used as the target recommendation model, the demand information characteristics of the target user are obtained according to the home configuration demand information of the target user and the target recommendation model;

[0028] The step of determining target home configuration information according to the home configuration requirement information of the target user and the target recommendation model includes:

[0029] Target home configuration information is determined according to the home configuration demand information of the target user, the demand information characteristics and the target recommendation model.

[0030] Optionally, the data scoring level includes a third scoring level, the target recommendation model includes a third recommendation model, and acquiring the target recommendation model according to the data scoring level of the target user includes:

[0031] When the data rating level of the target user is the third rating level, the third recommendation model is used as the target recommendation model.

[0032] Optionally, the method further comprises:

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

[0034] The step of determining target home configuration information according to the home configuration requirement information of the target user and the target recommendation model includes:

[0035] Target home configuration information is determined according to the home configuration requirement information of the target user, the preset home configuration information topology map and the target recommendation model.

[0036] On the other hand, an embodiment of the present invention further discloses a home configuration device, the device comprising:

[0037] A demand information acquisition module is used to obtain the home configuration demand information of the target user;

[0038] A rating level acquisition module, used to determine the data rating level of the target user according to the home configuration requirement information of the target user and preset data rating rules;

[0039] A recommendation model acquisition module, used to acquire a target recommendation model according to the data rating level of the target user;

[0040] The target information acquisition module is used to determine the target home configuration information according to the home configuration requirement information of the target user and the target recommendation model.

[0041] Optionally, the home configuration requirement information of the target user includes the home configuration requirement type of the target user and the home configuration reference information of the target user, and the rating level acquisition module includes:

[0042] The demand scoring level acquisition submodule is used to determine the data scoring level of the target user according to the home configuration demand type of the target user, the home configuration reference information of the target user and the preset data scoring rules.

[0043] Optionally, the home configuration requirement type of the target user includes personalized recommendation, the preset data scoring rule includes a first scoring rule, and the requirement scoring level acquisition submodule includes:

[0044] The first scoring level acquisition unit is used to determine the data scoring level of the target user according to the home configuration reference information of the target user and the first scoring rule when the home configuration requirement type of the target user is personalized recommendation.

[0045] Optionally, the data scoring level includes a first scoring 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 use the first recommendation model as a target recommendation model when the data rating level of the target user is the first rating level.

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

[0048] A candidate information acquisition submodule, for determining candidate home configuration information according to the home configuration requirement information of the target user and the target recommendation model when the first recommendation model is used as the target recommendation model;

[0049] A candidate information output submodule, used to output the candidate home configuration information to the user;

[0050] A feedback information acquisition submodule, used to acquire feedback information of the target user regarding the candidate home configuration information;

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

[0052] Optionally, the home furnishing configuration requirement type of the target user includes public recommendation, the preset data scoring rule includes a second scoring rule, and the requirement scoring level acquisition submodule includes:

[0053] The second scoring level acquisition unit is used to determine the data scoring level of the target user according to the home configuration reference information of the target user and the second scoring rule when the home configuration requirement type of the target user is public recommendation.

[0054] Optionally, the data scoring level includes a second scoring 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 comprises:

[0057] A demand feature acquisition submodule, for acquiring the demand information features of the target user according to 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 comprises:

[0059] The second target information acquisition submodule is used to determine the target home configuration information according to the home configuration demand information of the target user, the demand information characteristics and the target recommendation model.

[0060] Optionally, the data scoring level includes a third scoring 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 use the third recommendation model as the target recommendation model when the data rating level of the target user is the third rating level.

[0062] Optionally, the device further comprises:

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

[0064] The target information acquisition module comprises:

[0065] The third target information acquisition submodule is used to determine the target home configuration information according to the home configuration requirement information of the target user, the preset home configuration information topology map and the target recommendation model.

[0066] Correspondingly, an embodiment of the present invention discloses an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the various steps of the above-mentioned home configuration method embodiment when executed by the processor.

[0067] Accordingly, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various steps of the above-mentioned home configuration method embodiment are implemented.

[0068] The embodiment of the present invention includes the following advantages: the embodiment of the present invention can automatically and quickly generate a configuration scheme that meets the user's needs by obtaining the user's home configuration needs and using data scoring rules and target recommendation models, significantly improving the configuration efficiency and shortening the user's waiting time. Through the preset data scoring rules and target recommendation models, the requirements for the professional skills of installation and maintenance personnel are reduced. Even non-professional users can easily complete the configuration under the guidance of the system, while ensuring the accuracy of the configuration results and reducing human errors. According to the specific needs of the user and the 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 the needs of the user and improve the user experience and satisfaction. In the field of smart home installation and configuration, multiple beneficial effects such as streamlining the configuration process and improving efficiency, reducing professional skill requirements and improving configuration accuracy, realizing personalized configuration and accurately meeting user needs, enhancing system flexibility and scalability, and improving user satisfaction and loyalty are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0070] Figure 2 is a flow chart of recommendation model training of a home configuration method embodiment of the present invention;

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

[0072] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0073] One of the core concepts of the embodiments of the present invention is to provide different recommendation models for different users to recommend home configurations by utilizing the data requirements and usage characteristics of different models, so that the recommendation process can be more personalized.

[0074] Reference Figure 1 , shows a flowchart of a method for configuring a home furnishing according to an embodiment of the present invention, which may specifically include the following steps:

[0075] Step 101, obtaining home configuration requirement information of a target user;

[0076] Obtaining information about the target user's home configuration needs is a key step in the process of home design, decoration or smart home system configuration. This step involves collecting and understanding the target user's (customer or end user) specific needs and expectations for their home environment.

[0077] In one example, the types of home configuration requirement information of the target user may be space layout, style preference, color matching, furniture selection, functional requirements, smart home requirements, budget constraints and time frame; the collection method may be various methods at both online and offline levels, which is not limited in the embodiments of the present invention.

[0078] Step 102, determining the data scoring level of the target user according to the home configuration requirement information of the target user and the preset data scoring rules;

[0079] Step 102 is a crucial step in the process of home configuration, design or upgrade; the preset data scoring rules are to objectively and quantitatively evaluate the home configuration demand information of the target user. These rules can be based on industry experience or business needs.

[0080] In one example, the preset data scoring rules can evaluate the home configuration requirement information provided by the target user through the following dimensions:

[0081] The data quality dimension evaluates the completeness, accuracy, consistency, and timeliness of the home configuration demand information provided by the target users.

[0082] The demand priority dimension sorts the target user's needs according to their importance and urgency, and determines which needs need to be met first.

[0083] Data volume dimension: evaluate whether the effective data volume of home configuration demand information provided by the target users is sufficient to support the data volume requirements of the evaluation model;

[0084] After collecting the target users' home configuration demand information and clarifying the preset data scoring rules, the next step is to score the users' demand information according to these rules and determine their data scoring levels.

[0085] In one example, the scoring process may be:

[0086] Clean, organize and standardize the target users' home configuration demand information to ensure the accuracy and consistency of the data.

[0087] According to the preset data scoring rules, each requirement is scored item by item, and the user requirements are objectively and quantitatively evaluated. The calculation method can be weight calculation, function calculation, and linear calculation. The specific calculation method can be formulated according to business needs, and the embodiment of the present invention does not limit this.

[0088] Then, according to the scoring results, the user's data scores are divided into different levels. The grading method can be a percentile method, a natural breakpoint method, etc., which is not limited in the embodiment of the present invention. Through objective and quantitative scoring and grading, the user's needs and expectations can be better understood, so as to formulate a home configuration plan that better meets the user's wishes and improve the user's satisfaction and loyalty.

[0089] In one embodiment, the home configuration requirement information of the target user includes the home configuration requirement type of the target user and the home configuration reference information of the target user. Step 102 may include the following sub-steps:

[0090] Sub-step S11, determining the data scoring level of the target user according to the home configuration requirement type of the target user, the home configuration reference information of the target user and the preset data scoring rules.

[0091] The types of home configuration needs of target users refer to the specific types of needs of users for home configuration, such as mass needs or personalized needs. These types of needs reflect the users' comprehensive requirements and expectations for the home environment and their personalized pursuit.

[0092] The home configuration reference information of the target user refers to the home configuration cases, pictures, videos or text descriptions provided by the user for reference. This information helps to more intuitively understand the user's preferences and style, as well as their expectations for home configuration.

[0093] Through the above content, the embodiment of the present invention can comprehensively consider the home configuration demand types, reference information and preset data scoring rules of the target user, and provide strong support for subsequent home configuration work.

[0094] In one embodiment, the home configuration requirement type of the target user includes personalized recommendation, the preset data scoring rule includes a first scoring rule, and sub-step S11 may be:

[0095] Sub-step S111, when the home configuration requirement type of the target user is personalized recommendation, determining the data scoring level of the target user according to the home configuration reference information of the target user and the first scoring rule.

[0096] When the target user's home configuration demand type is personalized recommendation, the user needs to provide more and more valuable home configuration demand information. Therefore, the scoring rule at this time is set to the stricter first scoring rule. In the first scoring rule, the quality requirements for the data will be relatively high.

[0097] In one embodiment, the home configuration requirement type of the target user includes public recommendation, the preset data scoring rule includes a second scoring rule, and sub-step S111 may also be

[0098] In a case where the home configuration requirement type of the target user is public recommendation, the data scoring level of the target user is determined according to the home configuration reference information of the target user and the second scoring rule.

[0099] When the target user's home configuration requirement type is a general recommendation, the user needs to provide more and more valuable home configuration requirement information. Therefore, the scoring rule at this time is set to a relatively non-strict second scoring rule. In the second scoring rule, the quality requirements for the data will be relatively low.

[0100] Step 103, obtaining a target recommendation model according to the data rating level of the target user;

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

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

[0103] Sub-step S21, when the data rating level of the target user is the first rating level, using the first recommendation model as the target recommendation model.

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

[0105] MLP is a feed-forward artificial neural network that maps input to output through multiple fully connected layers and nonlinear activation functions. MLP consists of an input layer, several hidden layers, and an output layer. Each layer contains several neurons, and the neurons are connected by weights. Each neuron calculates the weighted sum of its input and weight, and then performs a nonlinear transformation through an activation function and outputs it to the next layer of neurons.

[0106] Reinforcement learning is a machine learning method that uses actions, rewards, and observations to update and optimize the training process through the interaction between the agent and the environment to maximize the cumulative reward. Reinforcement learning does not rely on labeled data, but uses reward signals as a guide to enable the agent to learn how to take actions through trial and error.

[0107] In one example, an MLP multi-layer perceptron-based algorithm model is regarded as an intelligent agent, which is responsible for recommending smart home configuration information based on the home configuration requirement information of the target user.

[0108] The target user's home configuration requirements are considered as 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, the type of layout, the light intensity, the user's historical purchase history, browsing history, etc. The recommendation decision made by the model this time is considered as an action, and the user's feedback information on this recommendation, such as like, average, dislike, etc., is considered as the reward for this action;

[0109] For example, when a user uses the system for the first time, he or she inputs basic home information such as space size, layout, etc., as well as the user's initial preferences and personal data. The MLP agent generates a preliminary recommendation strategy by processing and analyzing the environmental state. The agent recommends specific smart home configuration information to the user based on the recommendation strategy, such as recommending a smart lamp. After viewing the recommended information, the user expresses his or her satisfaction by scoring. The system converts user feedback into numerical rewards and feeds it back to the agent. The agent adjusts its recommendation strategy based on the reward signal, such as increasing or decreasing the weight of a certain type of recommendation, to optimize future recommendation effects. The embodiment of the present invention combines the powerful nonlinear modeling and generalization capabilities of MLP with the autonomous learning and optimization of reinforcement learning. By optimizing the parameters or strategies of MLP through reinforcement learning, MLP can perform higher performance when processing complex tasks. At the same time, MLP can also provide a rich candidate for state representation and action selection for reinforcement learning. In this way, a more personalized, efficient and satisfactory home configuration solution can be provided to users.

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

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

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

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

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

[0115] For example, CNN is used to extract features from the home space image in the home configuration requirement information provided by the target user, capturing local features such as furniture layout and color matching. Then, the extracted features are flattened into a one-dimensional vector and sent to the MLP for further processing. The MLP can generate personalized home configuration recommendations based on the preference data in the home configuration requirement information provided by the target user, such as the favorite style, color, etc. and the image features extracted by CNN. If the user likes a simple style and prefers white tones, the MLP can combine the spatial layout features extracted by CNN to recommend a white simple-style sofa to be placed in the center of the living room.

[0116] Combining MLP and CNN enables the recommendation model to recommend appropriate furniture layout solutions in smart home configuration recommendations by analyzing the image data of the home space to improve space utilization efficiency and aesthetics. Based on the user's preferences and the image information of the home space, the hybrid model can provide suggestions for style and color matching to make the home environment more harmonious and unified. Combining the user's personal preferences and the characteristics of the home space, the hybrid model can recommend appropriate smart home devices, such as smart lighting systems, smart curtains, etc., to improve the level of home intelligence. Therefore, the hybrid model has significant advantages in the field of smart home configuration recommendations, and can handle complex data relationships and generate recommendation results that meet user expectations.

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

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

[0119] In one example, when the home configuration requirement information provided by the target user is judged to be the third scoring level according to the preset data scoring rules, it means that the data quality provided by the user is too low or the data volume is very small. At this time, using a complex model may not produce ideal recommendation results. Therefore, it is more efficient and accurate to choose a simple basic model for home configuration recommendation.

[0120] Step 104: Determine target home configuration information based on the target user's home configuration requirement information 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, determining candidate home configuration information according to the home configuration requirement information of the target user and the target recommendation model;

[0123] Based on the target user's home configuration requirement information and the target recommendation model, a set of possible home configuration solutions is generated.

[0124] Sub-step S52, outputting the candidate home configuration information to the user;

[0125] The generated candidate home configuration information is displayed to the user for viewing and selection. The display form may be a graphical interface, virtual reality, augmented reality, etc., which is not limited in the embodiment of the present invention.

[0126] Sub-step S53, obtaining feedback information of the target user regarding the candidate home configuration information;

[0127] Collect users' evaluations and opinions on candidate home configuration information to further optimize recommendations.

[0128] Sub-step S54, determining target home configuration information according to the feedback information and the candidate home configuration information.

[0129] Based on user feedback, determine the final home configuration plan that meets user needs.

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

[0131] Acquire the target user's demand information characteristics according to the target user's home configuration demand information and the target recommendation model;

[0132] Use other deep learning algorithms to provide deeper feature extraction for the home configuration requirements information provided by the target users, so that the hybrid model can flexibly process various forms of data;

[0133] For example, CNN performs well in processing image data and can capture subtle features and spatial relationships in images; RNN (Recurrent Neural Network) is suitable for processing sequence data, such as user behavior sequences; Transformer has unique advantages in processing natural language text and long sequence data. Since Transformer, RNN and CNN are all existing technologies, they are not described in detail. It should be noted that the examples of RNN, CNN and Transformer are only for the convenience of understanding, and the selection of algorithms can be adjusted according to data and business needs, which should not be used as a limitation of the embodiments of the present invention.

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

[0135] Sub-step S61, determining target home configuration information according to the home configuration demand information of the target user, the demand information characteristics and the target recommendation model.

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

[0137] Obtaining a preset home configuration information topology map; the home configuration information topology map is used to represent the corresponding relationship between user needs and home configuration information;

[0138] A topology map is a graphical structure that represents the relationship between elements. It can be used to describe the association and dependency between elements in a home configuration. In the third recommendation model, the topology map is used to simplify the problem space and quickly identify key nodes and paths, thereby improving the accuracy and efficiency of recommendations when the amount of data is limited. The acquisition of topology map data can be obtained through online questionnaires, professional data acquisition from companies in the industry, etc.

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

[0140] Sub-step S71, determining target home configuration information according to the home configuration requirement information of the target user, the preset home configuration information topology map and the target recommendation model.

[0141] In one embodiment, when the data volume of the target user's home configuration requirement information is sufficient and the data quality also meets the preset requirements, the model at this time is a hybrid model combining deep learning, reinforcement learning and MLP.

[0142] Based on the in-depth extraction of user demand characteristics, dynamic adjustments are made based on real-time user feedback through reinforcement learning to achieve the highest level of personalization and accurate recommendations.

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

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

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

[0146] Based on the dynamic adjustment of the recommendation strategy by the reinforcement learning model, the system uses MLP to make decisions on the final recommendation plan. MLP can generate an optimal smart home configuration plan for users based on the user demand characteristics extracted by the deep learning model and the recommendation strategy learned by the reinforcement learning model, taking into account multiple factors such as furniture compatibility, space utilization, cost-effectiveness, etc.

[0147] The embodiment of the present invention can automatically and quickly generate a configuration scheme that meets the user's needs by obtaining the user's home configuration needs and using data scoring rules and target recommendation models, significantly improving configuration efficiency and shortening user waiting time. Through the preset data scoring rules and target recommendation models, the requirements for the professional skills of installation and maintenance personnel are reduced. Even non-professional users can easily complete the configuration under the guidance of the system, while ensuring the accuracy of the configuration results and reducing human errors. According to the specific needs of the user and the 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 the needs of users and improve user experience and satisfaction. In the field of smart home installation and configuration, multiple beneficial effects such as streamlining of configuration processes and improvement of efficiency, reduction of professional skill requirements and improvement of configuration accuracy, realization of personalized configuration and accurate satisfaction of user needs, enhancement of system flexibility and scalability, and improvement of user satisfaction and loyalty are achieved.

[0148] Reference Figure 2 , showing a schematic diagram of recommendation model training of a home configuration method embodiment of the present invention;

[0149] First, we can obtain users' home usage preference data through online voting, questionnaires, device data collection, etc., and at the same time obtain users' usage data information from companies in the home furnishing industry.

[0150] The acquired data is cleaned by removing extreme values ​​and normalizing the data, deleting the data with missing or more anomalies, filling the data with the mean for the data with missing or fewer anomalies, and deduplicating the duplicate data to obtain the data set.

[0151] By integrating the data set, classifying it according to the preset dimensions required by the business, and standardizing the classified information, we can obtain the training set and validation set required for training the recommendation model. The model is trained and iterated using the training set and validation set. When the accuracy of the model reaches the preset threshold, the model is deployed on the server for users to use.

[0152] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0153] Reference Figure 3 , shows a structural block diagram of an embodiment of a home furnishing configuration device of the present invention, which may specifically include the following modules:

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

[0155] The scoring level acquisition module 202 is used to determine the data scoring level of the target user according to the home configuration requirement information of the target user and the preset data scoring rules;

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

[0157] The target information acquisition module 204 is used to determine the target home configuration information according to the home configuration requirement information of the target user and the target recommendation model.

[0158] In one embodiment, the home configuration requirement information of the target user includes the home configuration requirement type of the target user and the home configuration reference information of the target user, and the rating level acquisition module includes:

[0159] The demand scoring level acquisition submodule is used to determine the data scoring level of the target user according to the home configuration demand type of the target user, the home configuration reference information of the target user and the preset data scoring rules.

[0160] In one embodiment, the home configuration requirement type of the target user includes personalized recommendation, the preset data scoring rule includes a first scoring rule, and the requirement scoring level acquisition submodule includes:

[0161] The first scoring level acquisition unit is used to determine the data scoring level of the target user according to the home configuration reference information of the target user and the first scoring rule when the home configuration requirement type of the target user is personalized recommendation.

[0162] In one embodiment, the data scoring level includes a first scoring 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 use the first recommendation model as a target recommendation model when the data rating level of the target user is the first rating level.

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

[0165] A candidate information acquisition submodule, for determining candidate home configuration information according to the home configuration requirement information of the target user and the target recommendation model when the first recommendation model is used as the target recommendation model;

[0166] A candidate information output submodule, used to output the candidate home configuration information to the user;

[0167] A feedback information acquisition submodule, used to acquire feedback information of the target user regarding the candidate home configuration information;

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

[0169] In one embodiment, the home configuration requirement type of the target user includes public recommendation, the preset data scoring rule includes a second scoring rule, and the requirement scoring level acquisition submodule includes:

[0170] The second scoring level acquisition unit is used to determine the data scoring level of the target user according to the home configuration reference information of the target user and the second scoring rule when the home configuration requirement type of the target user is public recommendation.

[0171] In one embodiment, the data scoring level includes a second scoring 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 comprises:

[0174] A demand feature acquisition submodule, for acquiring the demand information features of the target user according to 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 comprises:

[0176] The second target information acquisition submodule is used to determine the target home configuration information according to the home configuration demand information of the target user, the demand information characteristics and the target recommendation model.

[0177] In one embodiment, the data scoring level includes a third scoring 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 use the third recommendation model as the target recommendation model when the data rating level of the target user is the third rating level.

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

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

[0181] The target information acquisition module comprises:

[0182] The third target information acquisition submodule is used to determine the target home configuration information according to the home configuration requirement information of the target user, the preset home configuration information topology map and the target recommendation model.

[0183] The embodiment of the present invention can automatically and quickly generate a configuration scheme that meets the user's needs by obtaining the user's home configuration needs and using data scoring rules and target recommendation models, significantly improving configuration efficiency and shortening user waiting time. Through the preset data scoring rules and target recommendation models, the requirements for the professional skills of installation and maintenance personnel are reduced. Even non-professional users can easily complete the configuration under the guidance of the system, while ensuring the accuracy of the configuration results and reducing human errors. According to the specific needs of the user and the 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 the needs of users and improve user experience and satisfaction. In the field of smart home installation and configuration, multiple beneficial effects such as streamlining of configuration processes and improvement of efficiency, reduction of professional skill requirements and improvement of configuration accuracy, realization of personalized configuration and accurate satisfaction of user needs, enhancement of system flexibility and scalability, and improvement of user satisfaction and loyalty are achieved.

[0184] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0185] An embodiment of the present invention further provides an electronic device, including:

[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, the various processes of the above-mentioned home configuration method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0187] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned home configuration method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

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

[0189] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product 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 codes.

[0190] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0191] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0192] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0193] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0194] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0195] The above is a detailed introduction to a home configuration method, device, equipment and medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A home furnishing configuration method, characterized in that: The method comprises: Obtain home configuration requirement information of target users; Determining the data scoring level of the target user according to the home configuration requirement information of the target user and the preset data scoring rules; Obtaining a target recommendation model according to the data rating level of the target user; Target home configuration information is determined according to the home configuration requirement information of the target user and the target recommendation model.

2. The home configuration method according to claim 1, characterized in that: The home configuration requirement information of the target user includes the home configuration requirement type of the target user and the home configuration reference information of the target user. The determining the data scoring level of the target user according to the home configuration requirement information of the target user and the preset data scoring rules includes: The data scoring level of the target user is determined according to the type of home configuration requirement of the target user, the home configuration reference information of the target user and the preset data scoring rules.

3. The home configuration method according to claim 2, characterized in that: The home configuration requirement type of the target user includes personalized recommendation, the preset data scoring rule includes a first scoring rule, and determining the data scoring level of the target user according to the home configuration requirement type of the target user, the home configuration reference information of the target user and the preset data scoring rule includes: In a case where the home configuration requirement type of the target user is personalized recommendation, the data scoring level of the target user is determined according to the home configuration reference information of the target user and the first scoring rule.

4. The home configuration method according to claim 3, characterized in that: The data scoring level includes a first scoring level, the target recommendation model includes a first recommendation model, and acquiring the target recommendation model according to the data scoring level of the target user includes: When the data rating level of the target user is the first rating level, the first recommendation model is used as the target recommendation model.

5. The home configuration method according to claim 4, characterized in that: The step of determining target home configuration information according to the home configuration requirement information of the target user and the target recommendation model includes: In the case where the first recommendation model is used as the target recommendation model, determining candidate home configuration information according to the home configuration requirement information of the target user and the target recommendation model; Outputting the candidate home configuration information to a user; Obtaining feedback information from the target user regarding the candidate home configuration information; Determine target home configuration information according to the feedback information and the candidate home configuration information.

6. The home configuration method according to claim 2, characterized in that: The home configuration requirement type of the target user includes public recommendation, the preset data scoring rule includes a second scoring rule, and determining the data scoring level of the target user according to the home configuration requirement type of the target user, the home configuration reference information of the target user and the preset data scoring rule includes: In a case where the home configuration requirement type of the target user is public recommendation, the data scoring level of the target user is determined according to the home configuration reference information of the target user and the second scoring rule.

7. The home configuration method according to claim 6, characterized in that: The data scoring level includes a second scoring level, the target recommendation model includes a second recommendation model, and acquiring the target recommendation model according to the data scoring level of the target user includes: When the data rating level of the target user is the second rating level, the second recommendation model is used as the target recommendation model.

8. The home configuration method according to claim 7, characterized in that: The method further comprises: In the case where the second recommendation model is used as the target recommendation model, the demand information characteristics of the target user are obtained according to the home configuration demand information of the target user and the target recommendation model; The step of determining target home configuration information according to the home configuration requirement information of the target user and the target recommendation model includes: Target home configuration information is determined according to the home configuration demand information of the target user, the demand information characteristics and the target recommendation model.

9. The home configuration method according to claim 6, characterized in that: The data scoring level includes a third scoring level, the target recommendation model includes a third recommendation model, and acquiring the target recommendation model according to the data scoring level of the target user includes: When the data rating level of the target user is the third rating level, the third recommendation model is used as the target recommendation model.

10. The home configuration method according to claim 9, characterized in that: The method further comprises: When the third recommendation model is used as the target recommendation model, a preset home configuration information topology map is obtained; the home configuration information topology map is used to represent the corresponding relationship between user needs and home configuration information; The step of determining target home configuration information according to the home configuration requirement information of the target user and the target recommendation model includes: Target home configuration information is determined according to the home configuration requirement information of the target user, the preset home configuration information topology map and the target recommendation model.

11. A home furnishing device, characterized in that: The device comprises: A demand information acquisition module is used to obtain the home configuration demand information of the target user; A rating level acquisition module, used to determine the data rating level of the target user according to the home configuration requirement information of the target user and preset data rating rules; A recommendation model acquisition module, used to acquire a target recommendation model according to the data rating level of the target user; The target information acquisition module is used to determine the target home configuration information according to the home configuration requirement information of the target user and the target recommendation model.

12. 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 when the computer program is executed by the processor, the steps of the home configuration method according to any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the home configuration method according to any one of claims 1 to 10 are implemented.

Images