Household appliance recommendation method and device, electronic equipment and storage medium
Through the AI conversation interface, users can input home appliance needs and match and recommend, solving the problems of inefficiency and high cost in the home appliance selection process, and achieving efficient and accurate home appliance recommendations.
Patent Information
- Application Number
- CN202410970009.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-01
AI Technical Summary
There are problems of inefficient selection and high cost in the home appliance selection process, which leads to expensive communication costs and inefficient efficiency between designers and users.
Through the AI conversation interface, users can input home appliance demand information, match and recommend, filter and match home appliance products based on the home appliance demand information entered by the user, and generate decoration renderings to improve user selection efficiency and reduce communication costs.
It improves the efficiency of home appliance selection, reduces the selection cost, and effectively collects and judges user needs through AI interaction, improving the accuracy of recommendations.
Smart Images

Figure CN118886984A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of content recommendation, and in particular to a method for recommending home appliances, a device for recommending home appliances, an electronic device, and a computer-readable storage medium. Background Art
[0002] In modern society, with the development of technology and the diversification of consumer needs, the process of home appliance selection and home decoration design has become more and more complicated. In the traditional process, the communication cost between designers and users is high, which leads to inefficiency in the entire selection and design process, and the waste of time and resources has become a common problem. Summary of the invention
[0003] The embodiments of the present invention provide a method, device, electronic device and computer-readable storage medium for recommending home appliances, so as to solve or partially solve the problems of low selection efficiency and high cost in the process of selecting home appliances.
[0004] The embodiment of the present invention discloses a method for recommending household appliances, comprising:
[0005] Step 1: In response to the auxiliary instruction recommended by the home appliance, an AI conversation interface is displayed;
[0006] Step 2: outputting a home appliance demand collection message in the AI conversation interface, wherein the home appliance demand collection message is a message for guiding the user to input home appliance demand;
[0007] Step 3: in response to a content input operation for the home appliance demand collection message, acquiring home appliance demand information corresponding to the content input operation;
[0008] If the household appliance demand information does not meet the recommendation condition, return to step 2;
[0009] If the home appliance demand information meets the recommendation conditions, step 4 is executed to match home appliances according to the home appliance demand information, and the corresponding recommended home appliances are output in the AI conversation interface based on the matching results.
[0010] In some optional embodiments, it also includes:
[0011] In response to the first home improvement preview operation, an image is generated according to the home appliance demand information, and a corresponding first house decoration rendering is output in the AI conversation interface.
[0012] In some optional embodiments, it also includes:
[0013] Get the rough house image uploaded by the user;
[0014] Identify the rough housing image and obtain corresponding housing parameters;
[0015] In response to the second home improvement preview operation, an image is generated according to the house parameters and the recommended home appliances, and a corresponding house decoration rendering is output in the AI conversation interface.
[0016] In some optional embodiments, it also includes:
[0017] In response to an appliance selection operation for the recommended appliance, a first target appliance is selected from the recommended appliances, and the AI conversation interface is switched to an appliance details page corresponding to the first target appliance.
[0018] In some optional embodiments, in response to the content input operation for the home appliance demand collection message, acquiring the home appliance demand information corresponding to the content input operation includes:
[0019] In response to a text input operation for the home appliance demand information, acquiring a demand text corresponding to the text input operation, performing keyword extraction on the demand text, and obtaining corresponding demand keywords;
[0020] and / or, in response to a voice input operation for the home appliance demand information, acquiring a demand voice corresponding to the voice input operation, performing semantic recognition on the demand voice, and obtaining corresponding voice information;
[0021] and / or, in response to an image input operation for the household appliance demand information, acquiring a target image corresponding to the image input operation, performing content recognition on the target image, and obtaining corresponding demand parameters;
[0022] The demand keywords, the voice information and the demand parameters all include at least one of home appliance information, apartment type information, area information, building structure and resident user type.
[0023] In some optional embodiments, matching home appliances according to the home appliance demand information, and outputting corresponding recommended home appliances in the AI conversation interface based on the matching results, includes:
[0024] At least one recommended home appliance matching the home appliance information is screened out according to the apartment type information, the area information, the house structure, and the type of resident user, and the at least one recommended home appliance is output in the AI conversation interface.
[0025] In some optional embodiments, in response to the first home improvement preview operation, generating an image according to the home appliance demand information, and outputting the corresponding first house decoration effect picture in the AI conversation interface includes:
[0026] In response to the first home improvement preview operation, construct a scene according to the apartment type information, the house structure and the area information, and generate at least one corresponding first scene model;
[0027] Screening the recommended home appliances according to the area information and the type of resident user to obtain a second target home appliance matching the first scenario model;
[0028] Adding the second target home appliance to the first scene model, and adjusting the position and orientation of the second target home appliance according to the house structure, to obtain a first house decoration effect diagram corresponding to the home decoration demand message;
[0029] Output at least one of the first house decoration renderings in the AI conversation interface.
[0030] In some optional embodiments, the rough-finished house image includes at least one of a ruler and a reference figure, and the identifying the rough-finished house image and acquiring the corresponding house parameters includes:
[0031] Identify the ruler and / or the reference to obtain the room size corresponding to the rough house image;
[0032] Identify the illumination direction and shadow distribution in the rough-finished house image, and obtain orientation information corresponding to the rough-finished house image;
[0033] Identify the distance between the ceiling and the ground in the rough house image to obtain corresponding floor height information;
[0034] Features of the windows in the rough house image are extracted, and the window positions corresponding to the windows are obtained based on the extracted features.
[0035] In some optional embodiments, in response to the second home improvement preview operation, generating an image according to the house parameters and the recommended home appliances, and outputting a corresponding house decoration rendering in the AI conversation interface includes:
[0036] In response to the second home improvement preview operation, constructing a second scene model corresponding to the house parameters;
[0037] Filtering a third target home appliance matching the second scenario model from the recommended home appliances, and adding the third target home appliance to the second scenario model;
[0038] Adjust the position and orientation of the third target home appliance according to the house parameters to obtain a second house decoration effect diagram corresponding to the house parameters;
[0039] Output at least one of the second house decoration renderings in the AI conversation interface.
[0040] The embodiment of the present invention further discloses a home appliance recommendation device, comprising:
[0041] An interface display module, for displaying an AI conversation interface in response to an auxiliary instruction recommended by the home appliance;
[0042] A message output module, configured to output a home appliance demand collection message in the AI conversation interface, wherein the home appliance demand collection message is a message for guiding a user to input home appliance demand;
[0043] An information collection module, configured to, in response to a content input operation for the home appliance demand collection message, obtain home appliance demand information corresponding to the content input operation;
[0044] A secondary collection module, configured to return to the step of outputting a home appliance demand collection message in the AI conversation interface if the home appliance demand information does not meet the recommendation condition;
[0045] The home appliance recommendation module is used to match home appliances according to the home appliance demand information if the home appliance demand information meets the recommendation conditions, and output the corresponding recommended home appliances in the AI conversation interface based on the matching results.
[0046] In some optional embodiments, it also includes:
[0047] The first rendering output module is used to respond to the first home improvement preview operation, generate an image according to the home appliance demand information, and output the corresponding first house decoration rendering in the AI conversation interface.
[0048] In some optional embodiments, it also includes:
[0049] An image acquisition module is used to acquire rough house images uploaded by users;
[0050] An image recognition module is used to recognize the rough house image and obtain corresponding house parameters;
[0051] The second rendering output module is used to respond to the second home improvement preview operation, generate an image according to the house parameters and the recommended home appliances, and output the corresponding house decoration rendering in the AI conversation interface.
[0052] In some optional embodiments, it also includes:
[0053] The details page display module is used to select a first target appliance from the recommended appliances in response to an appliance selection operation for the recommended appliances, and switch the AI conversation interface to an appliance details page corresponding to the first target appliance.
[0054] In some optional embodiments, the information collection module is specifically used to:
[0055] In response to a text input operation for the home appliance demand information, acquiring a demand text corresponding to the text input operation, performing keyword extraction on the demand text, and obtaining corresponding demand keywords;
[0056] and / or, in response to a voice input operation for the home appliance demand information, acquiring a demand voice corresponding to the voice input operation, performing semantic recognition on the demand voice, and obtaining corresponding voice information;
[0057] and / or, in response to an image input operation for the household appliance demand information, acquiring a target image corresponding to the image input operation, performing content recognition on the target image, and obtaining corresponding demand parameters;
[0058] The demand keywords, the voice information and the demand parameters all include at least one of home appliance information, apartment type information, area information, building structure and resident user type.
[0059] In some optional embodiments, the home appliance recommendation module is specifically used to:
[0060] At least one recommended home appliance matching the home appliance information is screened out according to the apartment type information, the area information, the house structure, and the type of resident user, and the at least one recommended home appliance is output in the AI conversation interface.
[0061] In some optional embodiments, the first effect diagram output module is specifically used to:
[0062] In response to the first home improvement preview operation, construct a scene according to the apartment type information, the house structure and the area information, and generate at least one corresponding first scene model;
[0063] Screening the recommended home appliances according to the area information and the type of resident user to obtain a second target home appliance matching the first scenario model;
[0064] Adding the second target home appliance to the first scene model, and adjusting the position and orientation of the second target home appliance according to the house structure, to obtain a first house decoration effect diagram corresponding to the home decoration demand message;
[0065] Output at least one of the first house decoration renderings in the AI conversation interface.
[0066] In some optional embodiments, the rough house image includes at least one of a ruler and a reference figure, and the image recognition module is specifically used for:
[0067] Identify the ruler and / or the reference to obtain the room size corresponding to the rough house image;
[0068] Identify the illumination direction and shadow distribution in the rough-finished house image, and obtain orientation information corresponding to the rough-finished house image;
[0069] Identify the distance between the ceiling and the ground in the rough house image to obtain corresponding floor height information;
[0070] Features of the windows in the rough house image are extracted, and the window positions corresponding to the windows are obtained based on the extracted features.
[0071] In some optional embodiments, the second effect diagram output module is specifically used to:
[0072] In response to the second home improvement preview operation, constructing a second scene model corresponding to the house parameters;
[0073] Filtering a third target home appliance matching the second scenario model from the recommended home appliances, and adding the third target home appliance to the second scenario model;
[0074] Adjust the position and orientation of the third target home appliance according to the house parameters to obtain a second house decoration effect diagram corresponding to the house parameters;
[0075] Output at least one of the second house decoration renderings in the AI conversation interface.
[0076] The embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
[0077] The memory is used to store computer programs;
[0078] The processor is used to implement the method described in the embodiment of the present invention when executing the program stored in the memory.
[0079] The embodiment of the present invention further discloses a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, enables the processors to execute the method described in the embodiment of the present invention.
[0080] The embodiments of the present invention include the following advantages:
[0081] In an embodiment of the present invention, when a user is selecting home appliances online, the terminal can assist the user in selecting home appliances through AI dialogue. By responding to the auxiliary instructions of the home appliance recommendation, the AI conversation interface is displayed, and the home appliance demand collection message is output in the AI conversation interface. The home appliance demand collection message is a message that guides the user to input the home appliance demand. When the user inputs the corresponding content, the terminal can respond to the content input operation for the home appliance demand collection message, obtain the home appliance demand information corresponding to the content input operation, and if the home appliance demand information does not meet the recommendation conditions, the home appliance demand is collected; if the home appliance demand information meets the recommendation conditions, the home appliance is matched according to the home appliance demand information, and the corresponding recommended home appliance is output in the AI conversation interface based on the matching result. Through the AI interaction method, the user's needs are effectively collected and the collected demand information is judged. If the conditions are met, suitable home appliances are recommended to the user based on the collected demand information, thereby improving the efficiency of the user in selecting home appliances and reducing the selection cost. At the same time, if the collected demand information does not meet the conditions, it is collected again, which can effectively improve the accuracy of the home appliance recommendation. BRIEF DESCRIPTION OF THE DRAWINGS
[0082] Figure 1 is a flowchart of steps of a method for recommending a household appliance provided in an embodiment of the present invention;
[0083] Figure 2 is a structural block diagram of a recommended device of a household appliance provided in an embodiment of the present invention;
[0084] Figure 3 It is a block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0085] 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.
[0086] As an example, in the traditional home appliance selection process, users often need to spend high communication costs, repeatedly communicate and modify with designers, etc., resulting in inefficient user selection of home appliances.
[0087] In this regard, in the present invention, when the user is selecting home appliances online, the terminal can assist the user in selecting home appliances through AI dialogue. By responding to the auxiliary instructions of the home appliance recommendation, the AI conversation interface is displayed, and the home appliance demand collection message is output in the AI conversation interface. The home appliance demand collection message is a message to guide the user to input the home appliance demand. When the user inputs the corresponding content, the terminal can respond to the content input operation for the home appliance demand collection message, obtain the home appliance demand information corresponding to the content input operation, and if the home appliance demand information does not meet the recommendation conditions, the home appliance demand is collected; if the home appliance demand information meets the recommendation conditions, the home appliance is matched according to the home appliance demand information, and the corresponding recommended home appliance is output in the AI conversation interface based on the matching result. Through the AI interaction method, the user's needs are effectively collected and the collected demand information is judged. When the conditions are met, suitable home appliances are recommended to the user based on the collected demand information, thereby improving the efficiency of the user in selecting home appliances and reducing the selection cost. At the same time, when the collected demand information does not meet the conditions, it is collected again, which can effectively improve the accuracy of the home appliance recommendation.
[0088] Reference Figure 1 , shows a flowchart of a method for recommending household appliances provided in an embodiment of the present invention, which may specifically include the following steps:
[0089] Step 1: In response to the auxiliary instruction recommended by the home appliance, an AI conversation interface is displayed;
[0090] In an embodiment of the present invention, corresponding applications, applets, web pages, etc. can be run in the terminal, and online home appliance selection, home decoration design and other functions are provided to users through applications, applets, web pages, etc., so that users can select corresponding home appliances online based on their own needs, or simulate corresponding home decoration design effects, etc. The present invention is not limited to this.
[0091] Optionally, corresponding conversational robots can be deployed for applications, applets, web pages, etc. The conversational robots may include an application framework, a user interaction interface, and an API (Application Programming Interface) responsible for providing human-computer interaction pages, performing input and output, and integrating and connecting to other modules.
[0092] In addition, AI (Artificial Intelligence) language modules and AI drawing modules can also be deployed. The AI language module can be a neural network model deployed on the cloud, which can assist in providing basic language dialogue capabilities, supplement the data set according to the e-commerce direction, and then obtain a large language model enhanced with the e-commerce field through manual participation in data labeling, so that the AI language module can effectively assist in building a natural language dialogue with the user, analyze the user needs in the user input content, and convert it into keyword parameters that the AI conversation can use. For the AI drawing module, it can be developed based on the diffusion drawing module, using home decoration interior field images as training data sets, training for a variety of home decoration styles, and using the Embedding word embedding algorithm to increase the target product library, using a specific model to fix product features, and ensuring that the drawn electrical appliance image is a specific product. This module is responsible for generating images based on the data provided by the language model to assist users in selecting home appliances, and generating home decoration design renderings to assist users in understanding the decoration effects, etc. The present invention does not limit this.
[0093] It should be noted that in the embodiments of the present invention, an example is given in which a terminal runs a corresponding application program and displays a corresponding application interface through a graphical user interface of the terminal. A user can browse corresponding home appliances in the application interface, and during the browsing process, the user can enter corresponding auxiliary instructions in the application interface to trigger AI interaction, and the terminal can display a corresponding AI conversation interface in the graphical user interface. For auxiliary instructions, corresponding interactive controls can be provided in the application interface, and the user can enter control operations for the interactive controls, so that the terminal responds to the control operations for the interactive controls and displays a corresponding AI conversation interface in the graphical user interface, so as to assist the user in selecting home appliances, previewing home decoration designs, etc. through AI interaction.
[0094] Step 2: outputting a home appliance demand collection message in the AI conversation interface, wherein the home appliance demand collection message is a message for guiding the user to input home appliance demand;
[0095] After the terminal switches to the AI conversation interface, it can output the corresponding home appliance demand collection message in the AI conversation interface, and guide the user to input the home appliance demand through the home appliance demand message. For example, the terminal can output "Hello! Welcome to the smart home appliance recommendation system. In order to better serve you, please tell me what specific needs you have for home appliances?", "Please select or enter the type of home appliance you want to buy, such as: refrigerator, washing machine, air conditioner, TV, etc.", "What special requirements do you have for the functions of home appliances? For example: energy saving, intelligent control, large capacity, quiet, etc.", "Please let us know your budget range, which will help us recommend cost-effective home appliances for you", "To ensure that the size of the home appliance is suitable for your living space, please enter your desired size. "The dimensions of the area where home appliances are to be placed (length x width x height)", "Do you have a preferred home appliance brand? If so, please tell us so that we can provide you with more accurate recommendations", "Please describe the usage scenarios of home appliances, such as: home use, office, rental house, etc., which will affect the type of home appliances we recommend for you", etc. By outputting relevant information such as demand type, functional requirements, budget range, space size, brand preference, usage scenario, etc., the user is guided to enter the corresponding home appliance demand information in the AI conversation interface, thereby guiding the user to input by outputting the corresponding home appliance demand collection message, effectively reducing the user's communication cost, allowing the user to input content in a targeted manner, improving conversation efficiency, and thereby improving the user's efficiency in selecting home appliances.
[0096] Step 3: in response to a content input operation for the home appliance demand collection message, acquiring home appliance demand information corresponding to the content input operation;
[0097] For users, they can input corresponding content in the AI conversation interface according to the content guided by the home appliance demand collection message. The terminal can then respond to the content input operation for the home appliance demand collection message and obtain the home appliance demand information corresponding to the content input operation.
[0098] In some feasible implementations, the input of content may include at least text input, voice input, and image input, and corresponding interactive controls may be provided in the AI conversation interface, such as a text input box, a voice input control, and an image input control, so that users can select corresponding methods to input content according to their own needs. In a specific implementation, the terminal may respond to a text input operation for home appliance demand information, obtain a demand text corresponding to the text input operation, extract keywords from the demand text, and obtain corresponding demand keywords; and / or, respond to a voice input operation for home appliance demand information, obtain a demand voice corresponding to the voice input operation, perform semantic recognition on the demand voice, and obtain corresponding voice information; and / or, respond to an image input operation for home appliance demand information, obtain a target image corresponding to the image input operation, perform content recognition on the target image, and obtain corresponding demand parameters. Among them, the demand keywords, voice information, and demand parameters all include at least one of home appliance information, apartment type information, area information, house structure, and resident user type.
[0099] Optionally, the home appliance information may be specific data related to home appliances, including the type of home appliances (such as refrigerators, washing machines, air conditioners, etc.), brands, models, functional features (such as energy saving, intelligent control, capacity, etc.), size specifications, price range, etc.; apartment type information refers to the layout and structure of the house, including the number of rooms (such as one bedroom and one living room, two bedrooms and one living room, etc.), the arrangement of the rooms (such as open or closed), and the orientation of the rooms (such as north-south permeability, east-west orientation, etc.); area information refers to the actual usable area of a house or a specific room, usually in square meters, etc.; house structure refers to the architectural structure and internal layout of the house, including the materials and structures of the walls, floors, and ceilings, as well as the partition methods between rooms and the locations of windows and doors in the house, etc.; resident user type refers to the characteristics of the user group using the house and home appliances, including the number of family members, age distribution, living habits, special needs (such as the elderly, children, pets, etc.). By collecting this information, corresponding home appliances can be accurately recommended to users.
[0100] In some examples, for text input operations, the user can input in the terminal: "I need an energy-efficient refrigerator suitable for a small apartment." After the terminal obtains the demand text, it extracts keywords and obtains demand keywords: "small apartment", "energy-efficient", "refrigerator", etc.; for voice input operations, the user can input by voice: "I want to buy a silent drum washing machine suitable for a family of three." After the terminal obtains the demand voice, it performs semantic recognition and obtains voice information: "silent", "drum washing machine", "family of three"; for image input operations, the user can upload an image containing a kitchen layout. After the terminal obtains the target image, it performs content recognition and obtains demand parameters: "kitchen layout", "refrigerator reserved space size", etc., so that through a variety of interactive methods, users can flexibly input content according to their own needs, thereby improving the flexibility and convenience of user operations.
[0101] In an embodiment of the present invention, for the content input by the user, after the terminal extracts the corresponding home appliance demand information according to the content input by the user, it can detect the existing home appliance demand information. If the home appliance demand information does not meet the recommendation conditions, it returns to step 2 and continues to output the corresponding home appliance demand guidance message in the AI conversation interface to continue collecting user needs; if the home appliance demand information meets the recommendation conditions, it executes step 4, matches the home appliances according to the home appliance demand information, and outputs the corresponding recommended home appliances in the AI conversation interface based on the matching results.
[0102] In some feasible implementations, the recommendation conditions may include one of the following: home appliance type, functional requirements, budget range, space size, apartment type information, resident user type, and installation conditions. That is, in the process of collecting user needs, the collected home appliance demand information includes at least part of the above information, such as home appliance type, functional requirements, budget range, etc. If the recommendation conditions are met, home appliance recommendations can be made based on the collected home appliance demand information; if the recommendation conditions are not met, the corresponding home appliance demand guidance message can continue to be output to guide the user to input content, so as to ensure the accuracy of the home appliance recommendation. Therefore, if the collected demand information does not meet the conditions, a second collection can be performed, which can effectively improve the accuracy of the home appliance recommendation.
[0103] When the recommendation conditions are met, the terminal can filter out at least one recommended home appliance that matches the home appliance information based on the apartment information, area information, house structure, and type of resident user, and output at least one recommended home appliance in the AI conversation interface. In a specific implementation, a recommendation system or rule engine can be designed to filter suitable home appliances. This may involve predefined rules, machine learning models, or deep learning models, depending on the complexity of the project. Specifically, a set of rules can be set, such as recommending appliances of appropriate sizes based on the size of the house, or recommending specific types of home appliances based on the house structure; then the corresponding model is trained, which learns the relationship between user needs and home appliance characteristics based on historical data to predict the best matching home appliances; then a deep neural network model is used, such as a natural language processing model (such as BERT) to understand and match the user's text input in order to recommend suitable home appliances, so that after obtaining information such as apartment information, area information, house structure, and type of resident user, this information can be input into the trained model to obtain recommended home appliances that match the home appliance information.
[0104] In one example, suppose a user wants to find a suitable refrigerator for his new home. The user's home is a two-bedroom, one-living-room apartment with a total area of 80 square meters. The kitchen space is limited. At the same time, the user has a two-year-old child. The user hopes that the refrigerator is both energy-saving and safe. The user can enter the corresponding content in the AI conversation interface. Based on the content entered by the user, the terminal can extract the corresponding home appliance demand information, such as "small size", "energy saving" and "child safety lock", etc. Then the terminal uses a matching algorithm to search for refrigerators that meet "small size", "energy saving" and "child safety lock" in the database. At the same time, the algorithm also considers whether the size of the refrigerator is suitable for the user's kitchen space and whether it meets the energy-saving standards. Then, based on the search results, the terminal can generate a recommendation list, which includes several refrigerators that meet the user's needs, such as a compact energy-saving refrigerator with a child safety lock function, etc., so as to effectively collect user needs through AI interaction and judge the collected demand information. If the conditions are met, the terminal recommends suitable home appliances to the user based on the collected demand information, thereby improving the efficiency of the user's selection of home appliances and reducing the selection cost.
[0105] In addition, after the terminal outputs recommended home appliances in the AI conversation interface based on the home appliance demand information, if the user wants to know the corresponding home appliances, the terminal can output a selection operation for the recommended home appliances. The terminal can respond to the home appliance selection operation for the recommended home appliances, select a first target home appliance from the recommended home appliances, and switch the AI conversation interface to the home appliance details page corresponding to the first target home appliance, so that the user can obtain detailed information of the corresponding home appliance through the home appliance details page.
[0106] In an embodiment of the present invention, the terminal can also generate an image according to the home appliance demand information in response to the first home improvement preview operation, and output the corresponding first house decoration rendering in the AI conversation interface. Specifically, after the terminal outputs the corresponding recommended home appliances in the AI conversation interface, if the user wants to further understand the house decoration effect corresponding to the home appliance demand message previously input, the corresponding home improvement preview operation can be input in the AI conversation interface, such as inputting messages such as "Based on the previous content, take a look at the corresponding decoration effect" in the AI conversation interface. The terminal can determine whether to trigger the home improvement preview through semantic recognition, keyword extraction, etc. If triggered, it can generate an image according to the collected home appliance demand information, and then output the corresponding house decoration rendering in the AI conversation interface. In the process of selecting home appliances, the terminal can also draw renderings according to the collected demand information to assist users in understanding different house decoration effects, so that users can better select home appliances.
[0107] In some feasible implementations, the terminal can respond to the first home improvement preview operation, construct a scene according to the apartment type information, house structure and area information, generate at least one corresponding first scene model, and then screen the recommended home appliances according to the area information and the type of resident users to obtain the second target home appliances that match the first scene model, and then add the second target home appliances to the first scene model, and adjust the position and orientation of the second target home appliances according to the house structure to obtain the first house decoration rendering corresponding to the home improvement demand message, and then output at least one first house decoration rendering in the AI conversation interface. In the process of selecting home appliances, the terminal can also draw renderings based on the collected demand information to assist users in understanding different house decoration effects, so that users can better select home appliances.
[0108] In one example, a user is planning to renovate a new house and hopes to use smart home technology to help him choose suitable home appliances and preview the house decoration renderings to make better decisions.
[0109] 1. Collect and process user information:
[0110] Users input apartment information (e.g. 3 bedrooms and 2 living rooms), house structure (floor, room layout), area information (square meters of each room) and resident user type (family members, living habits, etc.) through smart applications.
[0111] 2. Generate the first scene model:
[0112] Based on the information provided by the user, the terminal automatically generates a first scene model, including basic room layout and space allocation, such as generating a virtual 3D house model to show the basic structure and size of each room.
[0113] 3. Home appliance screening and matching:
[0114] Based on the house area information and the type of resident, the terminal starts to screen suitable home appliances. For example, for the living room area, according to the area and the preferences of family members, a TV with suitable size and function is selected as the second target home appliance.
[0115] 4. Add home appliances to the scene model:
[0116] The second target appliance (TV) is added to the first scene model. The terminal automatically places the TV in a suitable location in the living room and adjusts its orientation according to the house structure to ensure the best viewing experience.
[0117] 5. Generate decoration renderings:
[0118] Combined with the added home appliances and house structure information, the terminal generates the first house decoration renderings, including a virtual living room scene showing the actual effect after the TV is placed.
[0119] 6. Output to AI conversation interface:
[0120] The generated first house decoration renderings are output to the AI conversation interface of the smart application, where users can see the actual effect of the virtual living room and further decide whether it meets their needs.
[0121] In addition, users can also interact with the terminal in the AI conversational interface, such as requesting the replacement of home appliances, adjusting furniture layout, etc., so that the terminal can make adjustments based on feedback to ensure user satisfaction.
[0122] In an embodiment of the present invention, in addition to recommending home appliances and presenting home decoration design renderings based on the home appliance demand information obtained as mentioned above, the terminal can further collect house parameters input by the user, and then optimize the house decoration renderings based on the house parameters and home decoration demand information, so that the constructed house decoration renderings can be more in line with the actual needs of the user and ensure user experience.
[0123] In some feasible implementations, the terminal can obtain an image of a rough house uploaded by a user, then identify the image of the rough house, obtain the corresponding house parameters, and then, in response to a second home improvement preview operation, generate an image based on the house parameters and recommended home appliances, and output the corresponding house decoration renderings in the AI conversation interface. After collecting the user's demand for home appliances, the terminal can further obtain the house parameters input by the user, combine the home appliance demand information and the house parameters, and present a more targeted preview of the house decoration renderings, thereby improving the targetedness and accuracy of the house decoration renderings.
[0124] Among them, the image of the rough house includes at least one of a ruler and a reference, and the terminal can identify the ruler and / or the reference to obtain the room size corresponding to the image of the rough house, then identify the lighting direction and shadow distribution in the image of the rough house, obtain the orientation information corresponding to the image of the rough house, and then identify the distance between the ceiling and the ground in the image of the rough house to obtain the corresponding floor height information, and perform feature extraction on the windows in the image of the rough house, and obtain the window opening position corresponding to the window based on the extracted features.
[0125] In some examples, a user uploads an image of a rough house in the AI conversation interface. The image contains a ruler and a known reference object (such as a door frame), as well as the natural light and shadows of the room. The processing process may include: the terminal can use image processing technology to identify the ruler and door frame reference objects in the image, and calculate the actual size (length and width) of the room through the proportional relationship of the ruler and the known size of the door frame; the terminal can analyze the light direction and shadow distribution in the image, combine geographic information (such as the latitude and longitude of the location where the image was taken), and then use the sun angle calculation or machine learning model to determine the direction of the room (such as north-south, east-west); the terminal can identify the ceiling and the ground in the image and measure the distance between the two. The vertical distance between the two windows, and then combined with the perspective transformation of the image, the terminal calculates the floor height of the room; the terminal can extract features of the windows in the image, such as the shape, position and size of the windows, and based on the extracted features, the terminal determines the specific window position of the window (such as which wall of the room, the height from the ground, etc.), for example, room size: 5 meters long and 4 meters wide; orientation information: south; floor height information: 2.8 meters; window position: located on the south wall, 1 meter from the ground, the window size is 1.5 meters wide and 1.2 meters high, etc., so as to obtain the corresponding house parameters by identifying the image of the rough house, so that the terminal can determine the actual situation of the house based on the house parameters, thereby improving the accuracy and pertinence of the constructed house decoration renderings.
[0126] After obtaining the house parameters, the user can further input a home decoration preview operation based on the already input home appliance demand information and the image of the rough house, so that the terminal can respond to the second home decoration preview operation, build a second scene model corresponding to the house parameters, and then select a third target home appliance matching the second scene model from the recommended home appliances, add the third target home appliance to the second scene model, and then adjust the position and orientation of the third target home appliance according to the house parameters to obtain a second house decoration rendering corresponding to the house parameters, and then output at least one second house decoration rendering in the AI conversation interface. The terminal can then accurately screen and recommend qualified home appliances based on the house parameters and demand information input by the user, thereby improving the intelligence and personalization of the decoration plan. At the same time, it can achieve efficient response speed during the user preview process, ensuring the efficiency of user selection of home appliances.
[0127] It should be noted that the embodiments of the present invention include but are not limited to the above examples. It is understandable that those skilled in the art can also make settings according to actual needs under the guidance of the ideas of the embodiments of the present invention, and the present invention is not limited to this.
[0128] In an embodiment of the present invention, when a user is selecting home appliances online, the terminal can assist the user in selecting home appliances through AI dialogue. By responding to the auxiliary instructions of the home appliance recommendation, the AI conversation interface is displayed, and the home appliance demand collection message is output in the AI conversation interface. The home appliance demand collection message is a message that guides the user to input the home appliance demand. When the user inputs the corresponding content, the terminal can respond to the content input operation for the home appliance demand collection message, obtain the home appliance demand information corresponding to the content input operation, and if the home appliance demand information does not meet the recommendation conditions, the home appliance demand is collected; if the home appliance demand information meets the recommendation conditions, the home appliance is matched according to the home appliance demand information, and the corresponding recommended home appliance is output in the AI conversation interface based on the matching result. Through the AI interaction method, the user's needs are effectively collected and the collected demand information is judged. If the conditions are met, suitable home appliances are recommended to the user based on the collected demand information, thereby improving the efficiency of the user in selecting home appliances and reducing the selection cost. At the same time, if the collected demand information does not meet the conditions, it is collected again, which can effectively improve the accuracy of the home appliance recommendation.
[0129] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the following examples are used for exemplary description:
[0130] The first step is to deploy the software and its operating environment. The AI model application mainly includes the following parts:
[0131] Chat boot, including application framework and user interface UI, is responsible for providing human-computer interaction pages, input and output, and integrating and accessing APIs of other modules;
[0132] The AI language module is based on a GPT-like model deployed in the cloud. It assists in providing basic language conversation capabilities and supplements the data set according to the directionality of the e-commerce field. Professional customer service personnel participate in data labeling to obtain a large language model with e-commerce field enhancements. This module mainly assists in building natural language conversations with users, analyzes the design requirements in the user input content, and converts them into keyword parameters available for AI painting.
[0133] The AI drawing model is developed based on the diffusion drawing model. It uses home interior images as training data sets and is trained for a variety of home decoration styles. It uses the Embedding word embedding algorithm to increase the company's product library and uses models such as Lora to fix the company's product features to ensure that the drawn appliance images are the company's products. This module is responsible for generating images based on the data provided by the language model to assist users in selecting home appliances.
[0134] Step 2: Connect this AI application to the mall. When users need to plan home decoration and select home appliances, they can enter this application. This application is designed to help users make decisions and preview the effects of home decoration and home appliance placement. (The corresponding interface interaction diagram can be designed here).
[0135] Step 3: The Boot robot communicates with the user, asking the user what kind of room they want to decorate. It supports users to input text / voice / photos, and the user can start describing the expected room size, decoration style, location of electrical appliances, etc.
[0136] For example, user A uses text input to describe his room, including the size of the room and the style he wants to decorate. The application collects information in the user's natural language and asks additional questions, such as what is the apartment type? Where is the window? Who will live in it? After several rounds of communication, AI ends the collection process and intelligently matches the home appliances that are closest to the user's needs based on the collected information. Finally, the information is converted into parameters related to AI image generation and transferred to the next module of this application; user B uploads an image of an undecorated rough house. AI obtains rough house information (size, orientation, floor height, window position, etc.) through perspective matching and other graphics detection methods. After obtaining the information, AI continues to ask additional questions, and then the same step is followed; user C communicates with AI through voice, and AI responds by voice, the same as above.
[0137] Step 4: The AI image generation module receives the aforementioned parameters for generation, uses VAE, embedding, LoRa and other tools to fix features, and finally generates the required room preview renderings and feeds them back to the user. After receiving the image, the customer makes selections and supplements. This step can be repeated many times to finally complete the selection of home appliances and home decoration planning, and jump to the mall page.
[0138] For example: the user selects a favorite plan from several reference plans given by AI and describes it through natural language (such as changing the color of the air conditioner, changing the style of the furniture, etc.). AI then uses the supplementary information to adjust the image and finally obtains a satisfactory plan rendering and selected home appliances.
[0139] Through the above process, user needs are effectively collected and the collected demand information is judged. If the conditions are met, suitable home appliances are recommended to users based on the collected demand information, which improves the efficiency of users in selecting home appliances and reduces the selection cost. At the same time, if the collected demand information does not meet the conditions, a second collection is performed to effectively improve the accuracy of home appliance recommendations.
[0140] It should be noted that VAE (Variational Autoencoder) is a generative model that can learn the potential distribution of data. Through VAE, you can map high-dimensional data (such as images, text, etc.) to a low-dimensional latent space and extract and fix features in this space. The processing process may include: Training VAE: Use your dataset to train the VAE model. VAE consists of an encoder and a decoder; Latent representation: Map the data to the latent space through the encoder to obtain the latent representation; Feature fixation: In the latent space, you can choose specific dimensions or features to fix, such as through regularization or constraints.
[0141] Embedding is a technique for mapping discrete variables (such as words, item IDs, etc.) to a continuous vector space. Through embedding, discrete features can be converted into continuous features and further processed. The corresponding processing process may include: training Embedding: using your dataset to train an embedding model, such as Word2Vec, GloVe, or BERT; feature extraction: extracting feature vectors from embedding; and feature fixation: selecting specific embedding dimensions or features to fix, such as through regularization or constraints.
[0142] LoRa (Low-Rank Adaptation) is a technology for model fine-tuning that reduces the number of parameters by introducing a low-rank structure in the model's weight matrix. This can be used to fix certain features or reduce overfitting. The corresponding process can include applying LoRa technology in a pre-trained model, such as in a Transformer model, and then through LoRa's low-rank structure, you can choose specific features to fix, such as by constraining the rank of the weight matrix.
[0143] 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.
[0144] Reference Figure 2 , shows a structural block diagram of a home appliance recommendation device provided in an embodiment of the present invention, which may specifically include the following modules:
[0145] The interface display module 201 is used to display an AI conversation interface in response to the auxiliary instruction recommended by the home appliance;
[0146] A message output module 202, configured to output a home appliance demand collection message in the AI conversation interface, wherein the home appliance demand collection message is a message for guiding a user to input home appliance demand;
[0147] The information collection module 203 is used to obtain the home appliance demand information corresponding to the content input operation in response to the content input operation of the home appliance demand collection message;
[0148] A secondary collection module 204, configured to return to the step of outputting a home appliance demand collection message in the AI conversation interface if the home appliance demand information does not meet the recommendation condition;
[0149] The home appliance recommendation module 205 is used to match home appliances according to the home appliance demand information if the home appliance demand information meets the recommendation conditions, and output the corresponding recommended home appliances in the AI conversation interface based on the matching results.
[0150] In some optional embodiments, it also includes:
[0151] The first rendering output module is used to respond to the first home improvement preview operation, generate an image according to the home appliance demand information, and output the corresponding first house decoration rendering in the AI conversation interface.
[0152] In some optional embodiments, it also includes:
[0153] An image acquisition module is used to acquire rough house images uploaded by users;
[0154] An image recognition module is used to recognize the rough house image and obtain corresponding house parameters;
[0155] The second rendering output module is used to respond to the second home improvement preview operation, generate an image according to the house parameters and the recommended home appliances, and output the corresponding house decoration rendering in the AI conversation interface.
[0156] In some optional embodiments, it also includes:
[0157] The details page display module is used to select a first target appliance from the recommended appliances in response to an appliance selection operation for the recommended appliances, and switch the AI conversation interface to an appliance details page corresponding to the first target appliance.
[0158] In some optional embodiments, the information collection module 203 is specifically used to:
[0159] In response to a text input operation for the home appliance demand information, acquiring a demand text corresponding to the text input operation, performing keyword extraction on the demand text, and obtaining corresponding demand keywords;
[0160] and / or, in response to a voice input operation for the home appliance demand information, acquiring a demand voice corresponding to the voice input operation, performing semantic recognition on the demand voice, and obtaining corresponding voice information;
[0161] and / or, in response to an image input operation for the household appliance demand information, acquiring a target image corresponding to the image input operation, performing content recognition on the target image, and obtaining corresponding demand parameters;
[0162] The demand keywords, the voice information and the demand parameters all include at least one of home appliance information, apartment type information, area information, building structure and resident user type.
[0163] In some optional embodiments, the home appliance recommendation module 205 is specifically used for:
[0164] At least one recommended home appliance matching the home appliance information is screened out according to the apartment type information, the area information, the house structure, and the type of resident user, and the at least one recommended home appliance is output in the AI conversation interface.
[0165] In some optional embodiments, the first effect diagram output module is specifically used to:
[0166] In response to the first home improvement preview operation, construct a scene according to the apartment type information, the house structure and the area information, and generate at least one corresponding first scene model;
[0167] Screening the recommended home appliances according to the area information and the type of resident user to obtain a second target home appliance matching the first scenario model;
[0168] Adding the second target home appliance to the first scene model, and adjusting the position and orientation of the second target home appliance according to the house structure, to obtain a first house decoration effect diagram corresponding to the home decoration demand message;
[0169] Output at least one of the first house decoration renderings in the AI conversation interface.
[0170] In some optional embodiments, the rough house image includes at least one of a ruler and a reference figure, and the image recognition module is specifically used for:
[0171] Identify the ruler and / or the reference to obtain the room size corresponding to the rough house image;
[0172] Identify the illumination direction and shadow distribution in the rough-finished house image, and obtain orientation information corresponding to the rough-finished house image;
[0173] Identify the distance between the ceiling and the ground in the rough house image to obtain corresponding floor height information;
[0174] Features of the windows in the rough house image are extracted, and the window positions corresponding to the windows are obtained based on the extracted features.
[0175] In some optional embodiments, the second effect diagram output module is specifically used to:
[0176] In response to the second home improvement preview operation, constructing a second scene model corresponding to the house parameters;
[0177] Filtering a third target home appliance matching the second scenario model from the recommended home appliances, and adding the third target home appliance to the second scenario model;
[0178] Adjust the position and orientation of the third target home appliance according to the house parameters to obtain a second house decoration effect diagram corresponding to the house parameters;
[0179] Output at least one of the second house decoration renderings in the AI conversation interface.
[0180] 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.
[0181] In addition, an embodiment of the present invention further provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned recommended method embodiment of the home appliance are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.
[0182] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned recommended method embodiment of the household appliance is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0183] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.
[0184] The electronic device 300 includes but is not limited to: a radio frequency unit 301, a network module 302, an audio output unit 303, an input unit 304, a sensor 305, a display unit 306, a user input unit 307, an interface unit 308, a memory 309, a processor 310, and a power supply 311. Those skilled in the art will appreciate that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In the embodiments of the present invention, the electronic device includes but is not limited to a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted terminal, a wearable device, and a pedometer.
[0185] It should be understood that in the embodiment of the present invention, the radio frequency unit 301 can be used for receiving and sending signals during information transmission or communication. Specifically, after receiving downlink data from the base station, it is sent to the processor 310 for processing; in addition, uplink data is sent to the base station. Generally, the radio frequency unit 301 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 301 can also communicate with the network and other devices through a wireless communication system.
[0186] The electronic device provides users with wireless broadband Internet access through the network module 302, such as helping users to send and receive emails, browse web pages, and access streaming media.
[0187] The audio output unit 303 can convert the audio data received by the RF unit 301 or the network module 302 or stored in the memory 309 into an audio signal and output it as sound. Moreover, the audio output unit 303 can also provide audio output related to a specific function performed by the electronic device 300 (for example, a call signal reception sound, a message reception sound, etc.). The audio output unit 303 includes a speaker, a buzzer, a receiver, etc.
[0188] The input unit 304 is used to receive audio or video signals. The input unit 304 may include a graphics processor (GPU) 3041 and a microphone 3042, and the graphics processor 3041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 306. The image frame processed by the graphics processor 3041 can be stored in the memory 309 (or other storage medium) or sent via the radio frequency unit 301 or the network module 302. The microphone 3042 can receive sound and can process such sound into audio data. The processed audio data can be converted into a format output that can be sent to a mobile communication base station via the radio frequency unit 301 in the case of a telephone call mode.
[0189] The electronic device 300 also includes at least one sensor 305, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 3061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 3061 and / or the backlight when the electronic device 300 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary, which can be used to identify the posture of the electronic device (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; the sensor 305 can also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be repeated here.
[0190] The display unit 306 is used to display information input by the user or information provided to the user. The display unit 306 may include a display panel 3061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.
[0191] The user input unit 307 can be used to receive input digital or character information, and to generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 307 includes a touch panel 3071 and other input devices 3072. The touch panel 3071, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 3071 or near the touch panel 3071 using any suitable object or accessory such as a finger, stylus, etc.). The touch panel 3071 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the contact point coordinates, and then sends it to the processor 310, receives the command sent by the processor 310 and executes it. In addition, the touch panel 3071 can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic waves. In addition to the touch panel 3071, the user input unit 307 may also include other input devices 3072. Specifically, other input devices 3072 may include but are not limited to a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here.
[0192] Further, the touch panel 3071 may be covered on the display panel 3061. When the touch panel 3071 detects a touch operation on or near it, it is transmitted to the processor 310 to determine the type of the touch event, and then the processor 310 provides a corresponding visual output on the display panel 3061 according to the type of the touch event. It can be understood that in one embodiment, the touch panel 3071 and the display panel 3061 are used as two independent components to implement the input and output functions of the electronic device, but in some embodiments, the touch panel 3071 and the display panel 3061 can be integrated to implement the input and output functions of the electronic device, which is not limited here.
[0193] The interface unit 308 is an interface for connecting an external device to the electronic device 300. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, etc. The interface unit 308 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within the electronic device 300 or may be used to transmit data between the electronic device 300 and an external device.
[0194] The memory 309 can be used to store software programs and various data. The memory 309 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 309 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0195] The processor 310 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 309 and calling data stored in the memory 309, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 310 may include one or more processing units; preferably, the processor 310 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 310.
[0196] The electronic device 300 may also include a power supply 311 (such as a battery) for supplying power to each component. Preferably, the power supply 311 may be logically connected to the processor 310 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system.
[0197] In addition, the electronic device 300 includes some functional modules not shown, which will not be described in detail here.
[0198] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or 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 device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0199] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0200] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.
[0201] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0202] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0203] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0204] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0205] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0206] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.
[0207] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A method for recommending household appliances, characterized in that: include: Step 1: In response to the auxiliary instruction recommended by the home appliance, an AI conversation interface is displayed; Step 2: outputting a home appliance demand collection message in the AI conversation interface, wherein the home appliance demand collection message is a message for guiding the user to input home appliance demand; Step 3: in response to a content input operation for the home appliance demand collection message, acquiring home appliance demand information corresponding to the content input operation; If the household appliance demand information does not meet the recommendation condition, return to step 2; If the home appliance demand information meets the recommendation conditions, step 4 is executed to match home appliances according to the home appliance demand information, and the corresponding recommended home appliances are output in the AI conversation interface based on the matching results.
2. The method according to claim 1, characterized in that: Also includes: In response to the first home improvement preview operation, an image is generated according to the home appliance demand information, and a corresponding first house decoration rendering is output in the AI conversation interface.
3. The method according to claim 1, characterized in that: Also includes: Get the rough house image uploaded by the user; Identify the rough housing image and obtain corresponding housing parameters; In response to the second home improvement preview operation, an image is generated according to the house parameters and the recommended home appliances, and a corresponding house decoration rendering is output in the AI conversation interface.
4. The method according to claim 1, characterized in that Also includes: In response to an appliance selection operation for the recommended appliance, a first target appliance is selected from the recommended appliances, and the AI conversation interface is switched to an appliance details page corresponding to the first target appliance.
5. The method according to claim 1, characterized in that The step of obtaining, in response to a content input operation for the home appliance demand collection message, home appliance demand information corresponding to the content input operation includes: In response to a text input operation for the home appliance demand information, acquiring a demand text corresponding to the text input operation, performing keyword extraction on the demand text, and obtaining corresponding demand keywords; and / or, in response to a voice input operation for the home appliance demand information, acquiring a demand voice corresponding to the voice input operation, performing semantic recognition on the demand voice, and obtaining corresponding voice information; and / or, in response to an image input operation for the household appliance demand information, acquiring a target image corresponding to the image input operation, performing content recognition on the target image, and obtaining corresponding demand parameters; The demand keywords, the voice information and the demand parameters all include at least one of home appliance information, apartment type information, area information, building structure and resident user type.
6. The method according to claim 5, characterized in that The performing home appliance matching according to the home appliance demand information, and outputting corresponding recommended home appliances in the AI conversation interface based on the matching result, includes: At least one recommended home appliance matching the home appliance information is screened out according to the apartment type information, the area information, the house structure, and the type of resident user, and the at least one recommended home appliance is output in the AI conversation interface.
7. The method according to claim 5 or 6, characterized in that: In response to the first home improvement preview operation, generating an image according to the home appliance demand information, and outputting the corresponding first house decoration effect picture in the AI conversation interface, including: In response to the first home improvement preview operation, construct a scene according to the apartment type information, the house structure and the area information, and generate at least one corresponding first scene model; Screening the recommended home appliances according to the area information and the type of resident user to obtain a second target home appliance matching the first scenario model; Adding the second target home appliance to the first scene model, and adjusting the position and orientation of the second target home appliance according to the house structure, to obtain a first house decoration effect diagram corresponding to the home decoration demand message; Output at least one of the first house decoration renderings in the AI conversation interface.
8. The method according to claim 3, characterized in that The rough-finished house image includes at least one of a ruler and a reference, and the identifying the rough-finished house image and obtaining corresponding house parameters include: Identify the ruler and / or the reference to obtain the room size corresponding to the rough house image; Identify the illumination direction and shadow distribution in the rough-finished house image, and obtain orientation information corresponding to the rough-finished house image; Identify the distance between the ceiling and the ground in the rough house image to obtain corresponding floor height information; Features of the windows in the rough house image are extracted, and the window positions corresponding to the windows are obtained based on the extracted features.
9. The method according to claim 8, characterized in that In response to the second home improvement preview operation, generating an image according to the house parameters and the recommended home appliances, and outputting a corresponding house decoration rendering in the AI conversation interface, including: In response to the second home improvement preview operation, constructing a second scene model corresponding to the house parameters; Filtering a third target home appliance matching the second scenario model from the recommended home appliances, and adding the third target home appliance to the second scenario model; Adjust the position and orientation of the third target home appliance according to the house parameters to obtain a second house decoration effect diagram corresponding to the house parameters; Output at least one of the second house decoration renderings in the AI conversation interface.
10. A device for recommending household appliances, characterized in that: include: An interface display module, for displaying an AI conversation interface in response to an auxiliary instruction recommended by the home appliance; A message output module, configured to output a home appliance demand collection message in the AI conversation interface, wherein the home appliance demand collection message is a message for guiding a user to input home appliance demand; An information collection module, configured to, in response to a content input operation for the home appliance demand collection message, obtain home appliance demand information corresponding to the content input operation; A secondary collection module, configured to return to the step of outputting a home appliance demand collection message in the AI conversation interface if the home appliance demand information does not meet the recommendation condition; The home appliance recommendation module is used to match home appliances according to the home appliance demand information if the home appliance demand information meets the recommendation conditions, and output the corresponding recommended home appliances in the AI conversation interface based on the matching results.
11. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the method according to any one of claims 1 to 9 when executing the program stored in the memory.
12. A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 9.
Citation Information
Cited By
Information processing method and device, equipment and storage medium
CN119781888A
Home configuration method, device, equipment and medium
CN119916701A
Intelligent material recommendation method and system based on image communication
CN120856940A
