Clothes recommendation method and device, storage medium and intelligent wardrobe
By obtaining and identifying user clothing recommendation requests in smart wardrobes, combining clothing information and user intentions, multiple recommendation methods are used to determine matching solutions, which solves the problem of low accuracy in clothing recommendations in the existing technology, and improves user experience and recommendation efficiency .
Patent Information
- Application Number
- CN202310523624.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-10
- Publication Date
- 2024-11-12
AI Technical Summary
Users spend a lot of time when choosing the right clothes, and the clothes recommendations of existing smart wardrobes are low, resulting in poor user experience.
By obtaining the user's clothing recommendation request, semantic recognition is carried out to determine the clothing recommendation intention, and use different recommendation methods to determine the matching plan in the smart wardrobe based on the intention and clothing information, including recommendations based on the dressing occasion, matching plan library or clothing description information. , and optimize recommendations based on user feedback and historical dressing behavior.
It improves the accuracy and efficiency of recommended clothes in smart wardrobe, saves users' time to choose, and improves users' user experience.
Smart Images

Figure CN118939863A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of information recommendation, and specifically relates to a clothing recommendation method, device, storage medium and smart wardrobe. Background Art
[0002] With the development of material life, people's demand for clothing is getting higher and higher, and there are more and more clothes in the wardrobe.
[0003] Choosing suitable clothes in the wardrobe often takes users a lot of time, and how to quickly match suitable clothes has become a problem for many users. Summary of the invention
[0004] In order to solve the above-mentioned problems in the prior art, the embodiments of the present application provide a clothing recommendation method, device, storage medium and smart wardrobe, which can quickly recommend clothing matching plans for users, save users' time in selecting clothes, and improve users' usage experience.
[0005] In a first aspect, an embodiment of the present application provides a clothing recommendation method, which is applied to a smart wardrobe, comprising:
[0006] Get the user's first clothing recommendation request;
[0007] Performing semantic recognition on the first clothing recommendation request to obtain the clothing recommendation intention of the user;
[0008] Determining a target recommendation method from multiple recommendation methods according to the clothing recommendation intention;
[0009] According to the clothing recommendation intention and the clothing information in the smart wardrobe, a clothing matching scheme is determined in the smart wardrobe using the target recommendation method; wherein the clothing information includes at least one of clothing style, clothing material, and clothing thickness;
[0010] The clothing matching plan is output.
[0011] Optionally, determining a target recommendation method from a plurality of recommendation methods according to the clothing recommendation intention includes:
[0012] If the clothing recommendation intention represents a dressing occasion and / or a dressing requirement, a first recommendation method is used as the target recommendation method, wherein the first recommendation method is a recommendation method for making clothing recommendations using a neural network model based on the clothing recommendation intention, environmental information, and current popular elements;
[0013] If the clothing recommendation intends to represent a target matching scheme, a second recommendation method is used as the target recommendation method, wherein the second recommendation method is a recommendation method for determining clothing corresponding to the target matching scheme from a matching scheme library;
[0014] If the clothing recommendation intends to represent clothing description information, a third recommendation method is used as the target recommendation method, and the third recommendation method is a recommendation method for calculating clothing in the smart wardrobe that matches the clothing description information.
[0015] Optionally, the target recommendation method is the first recommendation method, and after outputting the clothing matching plan, the method further includes:
[0016] If a second clothing recommendation request of the user is received within a preset time period, semantic recognition is performed on the first clothing recommendation request and the second clothing recommendation request to obtain a new clothing recommendation intention of the user;
[0017] According to the new clothing recommendation intention, re-determine the clothing matching plan in the smart wardrobe using the first recommendation method;
[0018] Output the re-determined clothing matching plan.
[0019] Optionally, after outputting the re-determined clothing matching solution, the method further includes:
[0020] If the user picks up clothes based on the re-determined clothing matching scheme, the re-determined clothing matching scheme, the clothing recommendation intention, environmental information, and the current popular elements are used to optimize the neural network model.
[0021] Optionally, determining that the user has an intention to take clothing from the smart clothing;
[0022] According to the time period to which the current time belongs, obtaining the user's dressing behavior in the historical time period;
[0023] Determining a clothing matching plan in the smart wardrobe according to the user's dressing behavior in a historical time period;
[0024] Output clothing matching plan.
[0025] Optionally, determining that the user has an intention to take clothing from the smart clothing includes:
[0026] Get the user's location information;
[0027] When it is determined according to the location information that the user is within a preset distance range and the current time belongs to any preset time period, it is determined that the user has the intention to take the clothes from the smart clothing.
[0028] Optionally, after outputting the clothing matching scheme, the method further includes:
[0029] If the action of the user opening the door of the smart wardrobe is recognized, the clothes corresponding to the clothing matching scheme are transmitted to the door of the smart wardrobe, and / or the clothes corresponding to the clothing matching scheme are illuminated by an indicator light.
[0030] In a second aspect, an embodiment of the present application provides a clothing recommendation device, which is applied to a smart wardrobe, comprising:
[0031] An acquisition module, used to acquire a user's first clothing recommendation request;
[0032] a recognition module, configured to perform semantic recognition on the first clothing recommendation request to obtain the clothing recommendation intention of the user;
[0033] A determination module, configured to determine a target recommendation method from a plurality of recommendation methods according to the clothing recommendation intention;
[0034] A recommendation module, configured to determine a clothing matching scheme in the smart wardrobe using the target recommendation method according to the clothing recommendation intention and the clothing information in the smart wardrobe; wherein the clothing information includes at least one of clothing style, clothing material, and clothing thickness;
[0035] An output module is used to output the clothing matching plan.
[0036] Optionally, the above-mentioned clothing recommendation device can be used to execute the washing machine fault reporting method described in any one of the first aspects.
[0037] In a third aspect, the present application provides a smart wardrobe, including: a memory and a processor;
[0038] The memory is used to store computer instructions; the processor is used to execute the computer instructions stored in the memory to implement any method in the first aspect.
[0039] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement any one of the methods in the first aspect.
[0040] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor.
[0041] The clothing recommendation method, device, storage medium and smart wardrobe provided in the embodiment of the present application obtain the user's first clothing recommendation request; perform semantic recognition on the first clothing recommendation request to obtain the user's clothing recommendation intention; determine a target recommendation method from multiple recommendation methods based on the clothing recommendation intention; determine a clothing matching scheme in the smart wardrobe using the target recommendation method based on the clothing recommendation intention and the clothing information in the smart wardrobe; and output the clothing matching scheme. By determining the clothing recommendation method that matches the user's clothing recommendation request to make clothing recommendations, the accuracy of the smart wardrobe's clothing recommendations can be improved, thereby improving the user's experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 It is a schematic diagram of a scenario provided by an embodiment of the present application;
[0043] Figure 2 This is a schematic diagram of the process of providing a clothing recommendation method in an embodiment of the present application. Figure 1 ;
[0044] Figure 3 This is a schematic diagram of the process of providing a clothing recommendation method in an embodiment of the present application. Figure 2 ;
[0045] Figure 4 is a schematic diagram of the structure of a clothing recommendation device provided in an embodiment of the present application;
[0046] Figure 5 It is a schematic diagram of the structure of the smart wardrobe provided in an embodiment of the present application. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.
[0048] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.
[0049] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0050] Before going out, users will choose the corresponding clothes according to the purpose of the trip. For example, going to a party, going to work, etc., the process of choosing clothes will consume a lot of time of users, especially for those who have difficulty in making choices, which will delay more time.
[0051] With the emergence of smart wardrobes, it has provided certain convenience for people to match clothes. However, the existing smart wardrobes have low accuracy in recommending clothes.
[0052] In view of this, an embodiment of the present application provides a clothing recommendation method, which is applied to a smart wardrobe. Through interaction with a user, the user's clothing recommendation intention is obtained, and a corresponding clothing recommendation method is determined according to the user's recommendation intention. Different recommendation intentions correspond to different clothing recommendation methods, and different clothing recommendation methods correspond to different clothing recommendation logics. This can improve the accuracy of clothing recommendations in the smart wardrobe, thereby enhancing the user experience.
[0053] The following specific embodiments are used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following specific embodiments can be implemented independently or in combination with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0054] Figure 1 A schematic diagram of a scenario provided in an embodiment of the present application, such as Figure 1 As shown, it includes a smart wardrobe body (wardrobe for short) 101, a sound collection device 102 and a display screen 103 arranged on the wardrobe 101.
[0055] The wardrobe 101 may obtain the user's clothing recommendation request through the sound collection device 102 . When the wardrobe 101 receives the user's clothing recommendation request, it may search for a clothing matching solution matching the user's clothing recommendation in the wardrobe 101 .
[0056] When the wardrobe 101 determines the recommended clothing matching plan, the clothing matching plan can be displayed on the display screen 103 so that the user can view the recommended clothing matching plan.
[0057] When the user decides to adopt the recommended clothing matching solution, the wardrobe 101 can transmit the clothing corresponding to the clothing matching solution to the door opening of the wardrobe 101 so that the user can conveniently take the clothing when opening the door of the wardrobe 101.
[0058] In a possible implementation, if the user is not satisfied with the recommended clothing matching solution, the wardrobe 101 can re-recommend a clothing matching solution based on the user's feedback.
[0059] In the embodiment of the present application, wardrobe 101 can process and recommend clothing matching plans based on the user's clothing recommendation request.
[0060] In a possible implementation, wardrobe 101 may be connected to a corresponding server via a network, and wardrobe 101 may send the collected clothing recommendation requests of users to the server, and complete the recommendation of clothing matching solutions through the server.
[0061] The information of the clothes stored in the wardrobe 101 can be determined by scanning the wardrobe, or can be determined by uploading by the user through a terminal device. The embodiment of the present application does not limit the method of obtaining the information of the clothes in the wardrobe.
[0062] Below Figure 1 Taking the wardrobe in FIG. 1 as an example, the clothing recommendation method provided in the embodiment of the present application is described.
[0063] Figure 2 A schematic diagram of a clothing recommendation method provided in an embodiment of the present application, such as Figure 2 As shown, the following steps are included:
[0064] S201. Obtain the user's first clothing recommendation request.
[0065] Exemplarily, when the clothing recommendation function of the smart wardrobe is turned on, the smart wardrobe can enter the human-computer dialogue mode, and the smart wardrobe can obtain the voice information input by the user through the sound collection module, and use the voice information input by the user as the first clothing recommendation request.
[0066] S202: Perform semantic recognition on the first clothing recommendation request to obtain the clothing recommendation intention of the user.
[0067] In the embodiment of the present application, the user's clothing recommendation intention may be the result of semantic recognition of the first clothing recommendation request, which is used to characterize the type of clothing matching or matching scheme desired by the user.
[0068] For example, an artificial intelligence program may be built into the wardrobe. When the user's first clothing recommendation request is obtained, the artificial intelligence program may be used to perform semantic recognition on the user's first clothing recommendation request to obtain the user's clothing recommendation intention. For example, the artificial intelligence program may be an artificial intelligence program based on openAI technology, or an artificial intelligence program based on ChatGPT technology, and this embodiment of the application is not limited to this.
[0069] S203: Determine a target recommendation method from multiple recommendation methods according to the clothing recommendation intention.
[0070] In the embodiment of the present application, the target recommendation method is a recommendation method that matches the clothing recommendation intention.
[0071] For example, if the clothing recommendation intention is the user's desired dressing occasion, dressing requirements, etc., the target recommendation method can be to select a set of clothing matching solutions that meet the needs in the wardrobe according to the dressing occasion and dressing requirements. For example, if the user's clothing recommendation intention is to go to the gym and wear black clothes, the target recommendation method is to find black clothes that meet the fitness occasion in the wardrobe.
[0072] If the clothing recommendation is intended to describe specific information of the clothing, the target recommendation method is to infer the recommendation method of the clothing in the smart wardrobe that matches the clothing description information.
[0073] S204. According to the clothing recommendation intention and the clothing information in the smart wardrobe, determine a clothing matching plan in the smart wardrobe using the target recommendation method; wherein the clothing information includes at least one of clothing style, clothing material, and clothing thickness.
[0074] In the embodiment of the present application, the clothing information in the smart wardrobe can be determined by entering the clothing information into the wardrobe through image scanning and clothing chips, or by receiving information uploaded by the user through a smart terminal.
[0075] When determining the clothing recommendation intention, the smart wardrobe uses the target recommendation method to filter out clothing matching solutions that meet the clothing recommendation intention based on the clothing information in the wardrobe.
[0076] S205: Output the clothing matching plan.
[0077] In an embodiment of the present application, the smart wardrobe can output the clothing matching plan through the large screen of the wardrobe for the user to view, and / or send the clothing matching plan to the user's smart terminal for the user to view.
[0078] The clothing recommendation method provided in the embodiment of the present application obtains the user's first clothing recommendation request; performs semantic recognition on the first clothing recommendation request to obtain the user's clothing recommendation intention; determines a target recommendation method from multiple recommendation methods according to the clothing recommendation intention; determines a clothing matching scheme in the smart wardrobe using the target recommendation method according to the clothing recommendation intention and the clothing information in the smart wardrobe; and outputs the clothing matching scheme. By determining a clothing recommendation method that matches the user's clothing recommendation request to make clothing recommendations, the accuracy of the smart wardrobe's clothing recommendations can be improved, thereby improving the user's experience.
[0079] exist Figure 2 Based on the illustrated embodiment, the following will describe how to determine a target recommendation method from a plurality of recommendation methods according to the clothing recommendation intention.
[0080] According to the clothing recommendation intention, determining a target recommendation method from multiple recommendation methods includes the following possible implementation methods.
[0081] In a possible implementation, if the clothing recommendation intention represents the dressing occasion and / or dressing requirement, the first recommendation method is used as the target recommendation method, and the first recommendation method is a recommendation method for clothing recommendation using a neural network model based on the clothing recommendation intention, environmental information, and current popular elements.
[0082] For example, if the smart wardrobe determines that the clothing recommendation intention represents the dressing occasion and / or dressing requirement, for example, semantic recognition is performed on the first clothing recommendation request, and it is determined that the semantic recognition result includes the dressing occasion and / or dressing requirement, then the first recommendation method is selected as the target recommendation method. The dressing requirement may be the color, thickness, etc. desired by the user.
[0083] When the target recommendation method is the first recommendation method, the smart wardrobe can obtain the current environmental information and popular elements, input the clothing recommendation intention, environmental information, and current popular elements into the preset neural network model, and obtain the clothing matching plan output by the neural network model based on the clothing information in the smart wardrobe.
[0084] The environmental information may be weather information, season information, etc. at the current time; the current popular elements may be clothing elements in the popular dressing style at the current time period, such as popular colors, etc. The smart wardrobe may obtain the current popular elements on the network.
[0085] In a possible implementation, if the clothing recommendation intends to represent a target matching scheme, a second recommendation method is used as the target recommendation method, and the second recommendation method is a recommendation method for determining clothing corresponding to the target matching scheme from a matching scheme library.
[0086] Exemplarily, the smart wardrobe may also pre-store a plurality of clothing matching schemes set by users, and each matching scheme has a corresponding identifier.
[0087] If the smart wardrobe determines that the clothing recommendation intention is represented by the matching scheme identifier, the second recommendation method is used as the target recommendation method. For example, if the smart wardrobe recognizes that the clothing recommendation intention is matching scheme No. 2, the smart wardrobe can determine the clothing included in matching scheme No. 2 and output the corresponding clothing matching scheme.
[0088] In a possible implementation, if the clothing recommendation intends to represent clothing description information, a third recommendation method is used as the target recommendation method, and the third recommendation method is a recommendation method for calculating clothing in the smart wardrobe that matches the clothing description information.
[0089] For example, if the smart wardrobe determines that the clothing recommendation intent represents clothing description information, for example, the clothing description information is a black suit jacket and gray jeans, the smart wardrobe searches for clothing that meets the description information in the smart wardrobe according to the clothing description information and displays the matching solution.
[0090] To sum up, the smart wardrobe can recommend clothes in different ways according to the description information input by the user, which can improve the efficiency and accuracy of clothing recommendations.
[0091] Optionally, when the target recommendation method is the first recommendation method, if the user is not satisfied with the recommended matching scheme, the smart wardrobe can also adjust the recommended matching scheme according to the user's feedback.
[0092] Exemplarily, if a second clothing recommendation request from the user is received within a preset time period, semantic recognition is performed on the first clothing recommendation request and the second clothing recommendation request to obtain the user's new clothing recommendation intention; based on the new clothing recommendation intention, the first recommendation method is used to redetermine the clothing matching plan in the smart wardrobe; and the redetermined clothing matching plan is output.
[0093] When the user is not satisfied with the recommended matching scheme, he can input a second recommendation request through interaction with the smart wardrobe, and the smart wardrobe can combine the first clothing recommendation request and the second clothing recommendation to obtain the user's new recommendation intention. The new recommendation intention, environmental information, and current popular elements are input into the preset neural network model to obtain a new clothing matching scheme output by the neural network model based on the clothing information in the smart wardrobe. The neural network model can use a mature neural network model in the prior art, such as a deep neural network model and a convolutional neural network model.
[0094] Optionally, in a possible implementation, the smart wardrobe can provide the user with an evaluation page for the currently recommended clothing matching solution through a display screen. If the user is not satisfied with the current clothing matching solution recommendation, the user can directly provide feedback. After receiving the user's feedback, the smart wardrobe can enter the state of obtaining the user's second recommendation request. If the user is satisfied with the current recommendation solution, the subsequent process can be entered.
[0095] When determining the clothing matching scheme that satisfies the user, the smart wardrobe can determine the user's preferences based on the clothing matching scheme that satisfies the user. For example, if the user wants to change the color of the clothes in the first recommended matching scheme to light-colored clothes, the user prefers light colors. The smart wardrobe can update the neural network model based on the user's preferences to improve the accuracy of clothing recommendations.
[0096] Exemplarily, if the user picks up clothes based on the re-determined clothing matching scheme, the re-determined clothing matching scheme, the clothing recommendation intention, environmental information, and popular elements are used to optimize the neural network model.
[0097] The smart wardrobe can use the re-determined clothing matching plan as the expected output, and the clothing recommendation intention, environmental information, and popular elements as the input of the neural network model. According to the actual output and expected output of the neural network model, the neural network model is iteratively optimized to obtain the optimized neural network model. In subsequent clothing recommendations, the optimized neural network model is used for recommendation to improve the accuracy of clothing recommendations.
[0098] It is understandable that in the subsequent recommendation process, if there are still user dissatisfaction, the smart wardrobe can continue to optimize the neural network model.
[0099] Optionally, in some embodiments, when the smart wardrobe determines that the user is satisfied with the recommended clothing matching solution, the smart wardrobe can deliver the clothing to the door and / or perform
[0100] Exemplarily, if the action of the user opening the door of the smart wardrobe is recognized, the clothes corresponding to the clothing matching scheme are transmitted to the door of the smart wardrobe, and / or the clothes corresponding to the clothing matching scheme are illuminated by an indicator light.
[0101] The smart wardrobe may be provided with a transmission device and an indicator device, for example, a transmission device such as a hinged turntable and an indicator device such as a ray indicator light. When the smart wardrobe recognizes that the user has opened the door, the clothes corresponding to the clothing matching scheme may be transmitted to the door of the smart wardrobe through the transmission device such as a hinged turntable, and / or the clothes corresponding to the clothing matching scheme may be illuminated by an indicator light, so as to facilitate the user to find and take the corresponding clothes, thereby improving the user experience.
[0102] It is understandable that when the smart wardrobe determines the clothing information, it can also determine the location information of each piece of clothing, and when the clothing corresponding to the clothing matching plan is transmitted to the cabinet door, the location information of each piece of clothing can be updated.
[0103] Optionally, in some embodiments, when making clothing recommendations, the smart wardrobe may also make recommendations based on the user's role information to help different users in the family make recommendations.
[0104] For example, the smart wardrobe may be provided with an image acquisition device, such as a camera. When the smart wardrobe receives the user's first recommendation request, it may obtain the user's role information through the image acquisition device and make corresponding clothing recommendations based on the role information.
[0105] Optionally, in some embodiments, the smart wardrobe can also make clothing recommendations based on the user's historical dressing information according to the user's life patterns.
[0106] Exemplarily, it is determined that the user has the intention to take clothes from the smart clothing; based on the time period to which the current time belongs, the user's dressing behavior in the historical time period is obtained; based on the user's dressing behavior in the historical time period, a clothing matching plan is determined in the smart wardrobe, and the clothing matching plan is output.
[0107] The smart wardrobe can record the user's clothing matching plans at different time periods every day and use them as historical dressing behaviors, such as the clothing matching plans for weekday mornings, and the clothing matching plans for exercising in the evenings and on weekends.
[0108] When it is determined that the user intends to take clothes from the smart clothing, a clothing plan that meets the needs is recommended to the user. The user does not need to describe his or her dressing needs every time, thereby improving the user's usage experience.
[0109] The smart wardrobe can determine that the user has the intention to take clothes from the smart clothing as shown below.
[0110] Exemplarily, the user's location information is obtained; when it is determined based on the location information that the user is within a preset distance range and the current time belongs to any preset time period, it is determined that the user has the intention to take the clothes from the smart clothing.
[0111] Exemplarily, a user information collection device, such as an infrared device, may be provided in the smart wardrobe. When the user is within a preset distance range, it can be determined that the user is close to the smart wardrobe. If the current time belongs to any of multiple preset time periods, it can be determined that the user intends to take clothes from the smart clothes.
[0112] For example, when a user moves near a smart wardrobe on a weekday morning, the smart wardrobe can recommend the user's current clothing matching plan based on the user's historical dressing behavior on weekdays. The user does not need to describe the clothing matching every time, which improves the efficiency of clothing recommendations.
[0113] It can be understood that the function of recommending clothing based on the user's historical clothing information can be started at a specific time every day. During the rest of the time, when the smart wardrobe recommends clothing, it can make recommendations when it receives the user's first recommendation request, so as to reduce the power consumption of the smart wardrobe.
[0114] It is understandable that when making recommendations based on the user's historical dressing behavior, the user's role information may also be obtained, and subsequent clothing recommendations may be made based on the user's role information.
[0115] Figure 3 Schematic diagram of the process of the clothing recommendation method provided in the embodiment of the present application Figure 2 ,exist Figure 2 Based on the embodiment shown, the process of recommending clothing using the first recommendation method is described. Figure 3 As shown, the following steps are included:
[0116] S301: Obtain the user's first recommendation request.
[0117] S302: Determine clothing recommendation intention according to the first recommendation request.
[0118] S303: Determine the user's role information.
[0119] S304: Based on the clothing recommendation intention, environmental information, and current popular elements, a neural network model is used to make clothing recommendations, and a clothing matching plan is determined and output.
[0120] S305: Determine whether the user is satisfied with the current clothing matching plan.
[0121] S306: If not satisfied, obtain the user's second clothing recommendation request, and determine the user's new clothing recommendation intention based on the first clothing recommendation request and the second clothing recommendation request.
[0122] S307: Based on the new clothing recommendation intention, environmental information, and current popular elements, a neural network model is used to make clothing recommendations, and a new clothing matching plan is determined and output.
[0123] S308: If the user picks up clothes based on the re-determined clothing matching plan, the re-determined clothing matching plan and clothing recommendation intention are used to optimize the neural network model.
[0124] S309: If satisfied, upon recognizing the user's action of opening the door of the smart wardrobe, the clothes corresponding to the clothing matching solution are transmitted to the door of the smart wardrobe, and / or an indicator light is used to illuminate the clothes corresponding to the clothing matching solution.
[0125] It can be understood that the specific implementation method and effect of each step of the embodiment of the present application have been described in the above embodiment and will not be repeated here.
[0126] The embodiment of the present application also provides a clothing recommendation device.
[0127] Figure 4 This is a schematic diagram of the structure of the clothing recommendation device 400 provided in an embodiment of the present application, as shown in FIG. Figure 4 As shown, including:
[0128] The acquisition module 401 is used to acquire the user's first clothing recommendation request.
[0129] The recognition module 402 is used to perform semantic recognition on the first clothing recommendation request to obtain the clothing recommendation intention of the user.
[0130] The determination module 403 is used to determine a target recommendation method from multiple recommendation methods according to the clothing recommendation intention.
[0131] The recommendation module 404 is used to determine a clothing matching plan in the smart wardrobe using the target recommendation method according to the clothing recommendation intention and the clothing information in the smart wardrobe; wherein the clothing information includes at least one of clothing style, clothing material, and clothing thickness.
[0132] The output module 405 is used to output the clothing matching plan.
[0133] Optionally, the determination module 403 is also used to use the first recommendation method as the target recommendation method if the clothing recommendation intention represents a dressing occasion and / or dressing requirement. The first recommendation method is a recommendation method for making clothing recommendations using a neural network model based on the clothing recommendation intention, environmental information, and current popular elements.
[0134] Optionally, the determination module 403 is further configured to use a second recommendation method as the target recommendation method if the clothing recommendation intends to represent a target matching scheme, wherein the second recommendation method is a recommendation method for determining clothing corresponding to the target matching scheme from a matching scheme library.
[0135] Optionally, the determination module 403 is further used to use a third recommendation method as the target recommendation method if the clothing recommendation intends to represent clothing description information, and the third recommendation method is a recommendation method for calculating clothing in the smart wardrobe that matches the clothing description information.
[0136] Optionally, the recommendation module 404 is also used to perform semantic recognition on the first clothing recommendation request and the second clothing recommendation request to obtain the user's new clothing recommendation intention if a second clothing recommendation request from the user is received within a preset time period; redetermine the clothing matching plan in the smart wardrobe using the first recommendation method based on the new clothing recommendation intention; and output the redetermined clothing matching plan.
[0137] Optionally, the recommendation module 404 is also used to optimize the neural network model using the re-determined clothing matching scheme, the clothing recommendation intention, environmental information, and the current popular elements if the user picks up clothing based on the re-determined clothing matching scheme.
[0138] Optionally, the recommendation module 404 is also used to determine whether the user has the intention to take clothes from the smart clothing; obtain the user's dressing behavior in the historical time period according to the time period to which the current time belongs; determine a clothing matching plan in the smart wardrobe according to the user's dressing behavior in the historical time period; and output the clothing matching plan.
[0139] Optionally, the recommendation module 404 is also used to obtain the user's location information; when it is determined according to the location information that the user is within a preset distance range and the current time belongs to any preset time period, it is determined that the user has the intention to take clothes from the smart clothing.
[0140] Optionally, the output module 405 is also used to transmit the clothes corresponding to the clothing matching scheme to the door of the smart wardrobe if the action of the user opening the door of the smart wardrobe is recognized, and / or to illuminate the clothes corresponding to the clothing matching scheme with an indicator light.
[0141] The clothing recommendation device provided in the embodiment of the present application can execute the clothing recommendation method of any of the above-mentioned embodiments, and its principles and technical effects are similar and will not be repeated here.
[0142] It is understandable that the division of the modules of the clothing recommendation device provided in the embodiment of the present application is only a division of logical functions, and in actual implementation, they can be fully or partially integrated into one physical entity, or physically separated. Moreover, these modules can be all implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware.
[0143] The embodiment of the present application also provides a smart wardrobe.
[0144] Figure 5A schematic diagram of the structure of the smart wardrobe 500 provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the smart wardrobe 500 may include: at least one processor 501 , a memory 502 , and a communication interface 503 .
[0145] The memory 502 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.
[0146] The memory 502 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.
[0147] The processor 501 is used to execute the computer-executable instructions stored in the memory 502 to implement the actions of the clothing recommendation method described in the above method embodiment. The processor 501 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.
[0148] Optionally, the smart wardrobe 500 may further include a display device 504. The display device 504 may be coupled to the processor 501, and the processor 501 controls the display device 504 to display. The processor 501 controls the display device 504 to display a recommended clothing matching solution.
[0149] In specific implementation, if the communication interface 503, the memory 502 and the processor 501 are implemented independently, the display device 504, the communication interface 503, the memory 502 and the processor 501 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.
[0150] Optionally, in a specific implementation, if the communication interface 503, the memory 502 and the processor 501 are integrated on a chip, the communication interface 503, the memory 502 and the processor 501 can communicate through an internal interface.
[0151] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the technical solution of the above-mentioned clothing recommendation method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.
[0152] In one possible implementation, a computer-readable medium may include a random access memory (RAM), a read-only memory (ROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage device, or any other medium that is intended to carry or store the required program code in the form of instructions or data structures and can be accessed by a computer. Moreover, any connection is appropriately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of the medium. Disks and optical disks as used herein include optical disks, laser disks, optical disks, digital versatile disks (DVDs), floppy disks and Blu-ray disks, where disks usually reproduce data magnetically, while optical disks reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.
[0153] A computer program product is also provided in an embodiment of the present application, including a computer program. When the computer program is executed by a processor, the technical solution of the above-mentioned clothing recommendation method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.
[0154] In the specific implementation of the above-mentioned terminal device or server, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.
[0155] Those skilled in the art will appreciate that all or part of the steps of any of the above method embodiments may be completed by hardware associated with program instructions. The aforementioned program may be stored in a computer-readable storage medium, and when the program is executed, all or part of the steps of the above method embodiments are executed.
[0156] If the technical solution of the present application is implemented in the form of software and sold or used as a product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a computer program or several instructions. The computer software product enables a computer device (which can be a personal computer, a server, a network device, or a similar electronic device) to perform all or part of the steps of the method of the embodiment of the present application.
[0157] So far, the technical solutions of the present application have been described in conjunction with the embodiments shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.
Claims
1. A clothing recommendation method, characterized in that: Applied to a smart wardrobe, the method comprises: Get the user's first clothing recommendation request; Performing semantic recognition on the first clothing recommendation request to obtain the clothing recommendation intention of the user; Determining a target recommendation method from multiple recommendation methods according to the clothing recommendation intention; According to the clothing recommendation intention and the clothing information in the smart wardrobe, a clothing matching scheme is determined in the smart wardrobe using the target recommendation method; wherein the clothing information includes at least one of clothing style, clothing material, and clothing thickness; The clothing matching plan is output.
2. The method according to claim 1, characterized in that The step of determining a target recommendation method from a plurality of recommendation methods according to the clothing recommendation intention includes: If the clothing recommendation intention represents a dressing occasion and / or a dressing requirement, a first recommendation method is used as the target recommendation method, wherein the first recommendation method is a recommendation method for making clothing recommendations using a neural network model based on the clothing recommendation intention, environmental information, and current popular elements; If the clothing recommendation intends to represent a target matching scheme, a second recommendation method is used as the target recommendation method, wherein the second recommendation method is a recommendation method for determining clothing corresponding to the target matching scheme from a matching scheme library; If the clothing recommendation intends to represent clothing description information, a third recommendation method is used as the target recommendation method, and the third recommendation method is a recommendation method for calculating clothing in the smart wardrobe that matches the clothing description information.
3. The method according to claim 2, characterized in that The target recommendation method is the first recommendation method. After outputting the clothing matching scheme, the method further includes: If a second clothing recommendation request of the user is received within a preset time period, semantic recognition is performed on the first clothing recommendation request and the second clothing recommendation request to obtain a new clothing recommendation intention of the user; According to the new clothing recommendation intention, re-determine the clothing matching plan in the smart wardrobe using the first recommendation method; Output the re-determined clothing matching plan.
4. The method according to claim 3, characterized in that After outputting the re-determined clothing matching scheme, the method further includes: If the user picks up clothes based on the re-determined clothing matching scheme, the re-determined clothing matching scheme, the clothing recommendation intention, environmental information, and the current popular elements are used to optimize the neural network model.
5. The method according to claim 1, characterized in that The method further comprises: Determining that the user has an intention to take clothing from the smart clothing; According to the time period to which the current time belongs, obtaining the user's dressing behavior in the historical time period; Determining a clothing matching plan in the smart wardrobe according to the user's dressing behavior in a historical time period; Output clothing matching plan.
6. The method according to claim 5, characterized in that The determining that the user has an intention to take clothing from the smart clothing includes: Get the user's location information; When it is determined according to the location information that the user is within a preset distance range and the current time belongs to any preset time period, it is determined that the user has the intention to take the clothes from the smart clothing.
7. The method according to any one of claims 1 to 6, characterized in that: After outputting the clothing matching scheme, the method further includes: If the action of the user opening the door of the smart wardrobe is recognized, the clothes corresponding to the clothing matching scheme are transmitted to the door of the smart wardrobe, and / or the clothes corresponding to the clothing matching scheme are illuminated by an indicator light.
8. A clothing recommendation device, characterized in that: Applied to smart wardrobes, including: An acquisition module, used to acquire a user's first clothing recommendation request; a recognition module, configured to perform semantic recognition on the first clothing recommendation request to obtain the clothing recommendation intention of the user; A determination module, configured to determine a target recommendation method from a plurality of recommendation methods according to the clothing recommendation intention; A recommendation module, configured to determine a clothing matching scheme in the smart wardrobe using the target recommendation method according to the clothing recommendation intention and the clothing information in the smart wardrobe; wherein the clothing information includes at least one of clothing style, clothing material, and clothing thickness; An output module is used to output the clothing matching plan.
9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.
10. A smart wardrobe, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the method according to any one of claims 1 to 7.
