Virtual fitting method and device, equipment and medium
By matching fitting algorithms with different difficulty levels according to the source and level of the user terminal, the problem that the existing virtual fitting system cannot provide personalized services is solved, and the personalization and cost-efficiency optimization of the virtual fitting results are achieved.
Patent Information
- Application Number
- CN202310640731.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2024-12-03
AI Technical Summary
The existing virtual fitting system cannot provide personalized fitting services and cannot match appropriate fitting algorithms according to the needs and scenarios of different users, resulting in poor virtual fitting effects.
By obtaining the fitting request from the user terminal, the fitting scene category is determined based on the source of the user terminal, and the target fitting algorithm is obtained according to the scene routing system, and the fitting algorithm of different difficulty levels is matched to adapt to user needs and costs, providing personalized Virtual fitting results.
A fitting algorithm that matches different difficulty levels according to user type and level is realized, which improves the personalization of virtual fitting results and the matching of actual needs, improves efficiency and experience, and controls the cost of the algorithm.
Smart Images

Figure CN119066256A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of smart electrical appliances, and specifically relates to a virtual fitting method, device, equipment and medium. Background Art
[0002] With the development of technology, virtual fitting has begun to appear in people's sight and has become a hot new thing.
[0003] The existing virtual fitting system digitizes the human body and clothing, that is, converts the user's body image into a digital person, and puts various clothes, accessories, etc. on the digital person so that the user can see the effect of wearing various clothes, thereby reducing the trouble of trying on clothes multiple times for the user.
[0004] However, existing virtual fitting systems cannot provide more personalized services to different users. Summary of the invention
[0005] In order to solve the above-mentioned problems in the prior art, that is, to make a fine-grained division of the fitting algorithms, service scenarios, etc. involved in virtual fitting, so as to provide users with distinctive fitting services, the present application provides a virtual fitting method, device, equipment and medium.
[0006] In a first aspect, the present application provides a virtual fitting method, comprising:
[0007] Acquire a fitting request from a user terminal, wherein the fitting request includes a fitting scene and fitting information, and the fitting information includes human body information and / or clothing information;
[0008] Determining a target scene category of the fitting scene according to a source of the user terminal;
[0009] According to the scene routing system, a target fitting algorithm corresponding to the target scene category is obtained, wherein the scene routing system includes fitting algorithms of different algorithm difficulties;
[0010] The virtual fitting result is displayed according to the target fitting algorithm and the fitting information.
[0011] In a possible implementation, determining the target scene category of the fitting scene according to the source of the user terminal includes:
[0012] Determine, according to the source of the user terminal, the user type to which the user terminal belongs, the user type being a home user or a store user;
[0013] According to the user type, it is determined that the fitting scene is a home scene category or a store scene category.
[0014] In a possible implementation, obtaining the target fitting algorithm corresponding to the target scene category according to the scene routing system includes:
[0015] If the fitting request does not carry user information, a default fitting algorithm corresponding to the target scene category is obtained, wherein the difficulty of the fitting algorithm corresponding to the store scene category is higher than the difficulty of the fitting algorithm corresponding to the home scene category.
[0016] In a possible implementation, if the fitting request carries user information, the method further includes:
[0017] Acquire the user level according to the user information;
[0018] A target fitting algorithm is obtained according to the user level, the target scene category, the scene routing system and the algorithm mapping relationship, wherein the algorithm mapping relationship includes the correspondence between the scene categories of different user levels and the fitting algorithms in the scene routing system, and the lower the user level, the lower the difficulty of the corresponding fitting algorithm.
[0019] In a possible implementation, displaying a virtual fitting result according to the target fitting algorithm and the fitting information includes at least one of the following:
[0020] Obtaining a digital human model according to the human body information and the target fitting algorithm, and storing and displaying the digital human model;
[0021] Obtaining and displaying a clothing model according to the clothing information and the target fitting algorithm;
[0022] A virtual dressing model is obtained and displayed according to the human body information, the clothing information, and the target fitting algorithm.
[0023] In a possible implementation, before displaying the virtual fitting result according to the target fitting algorithm and the fitting information, the method further includes:
[0024] Outputting prompt information to the user terminal, wherein the prompt information is used to prompt the target fitting algorithm to display a virtual fitting effect;
[0025] Acquire, within a preset time period, processing operation information of the user terminal on the prompt information, wherein the processing operation information includes confirmation and modification;
[0026] If the processing operation information is confirmed, determining to adopt the target fitting algorithm;
[0027] If the processing operation information is modification, then a modified target fitting algorithm is obtained.
[0028] In a possible implementation, before displaying the virtual fitting result according to the target fitting algorithm and the fitting information, the method further includes:
[0029] Determining whether the target fitting algorithm is a charging algorithm;
[0030] If it is a charging algorithm, a fee order is generated according to the target scene category and the target fitting algorithm, wherein the target fitting algorithm has different fees in different scene categories;
[0031] Sending a fee order to the user terminal and receiving confirmation information of the fee order from the user terminal.
[0032] In a second aspect, the present application provides a virtual fitting device, comprising:
[0033] An acquisition module, configured to acquire a fitting request from a user terminal, wherein the fitting request includes a fitting scene and fitting information, and the fitting information includes human body information and / or clothing information;
[0034] A first processing module, configured to determine a target scene category of the fitting scene according to a source of the user terminal;
[0035] A second processing module is used to obtain a target fitting algorithm corresponding to the target scene category according to a scene routing system, wherein the scene routing system includes fitting algorithms of different algorithm difficulties;
[0036] The third processing module is used to display the virtual fitting result according to the target fitting algorithm and the fitting information.
[0037] In a third aspect, the present application provides a virtual fitting device, comprising: at least one processor and a memory;
[0038] Memory stores computer-executable instructions;
[0039] At least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the virtual fitting method as described above.
[0040] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the virtual fitting method as described above.
[0041] The virtual fitting method, device, equipment and medium provided by the present application include obtaining a fitting request from a user terminal, wherein the fitting request includes a fitting scene and fitting information, wherein the fitting information includes human body information and / or clothing information; determining the target scene category of the fitting scene according to the source of the user terminal; obtaining the target fitting algorithm corresponding to the target scene category according to the scene routing system, wherein the scene routing system includes fitting algorithms of different algorithmic difficulties; and displaying the virtual fitting result according to the target fitting algorithm and the fitting information. In the above method, fitting algorithms of different algorithmic difficulties are matched based on user terminals of different types of sources, so that the fitting requirements and algorithmic input costs are adapted to the algorithmic difficulty. The higher the fitting requirements and input costs, the more difficult the adapted algorithm is, and the virtual fitting result obtained thereby is more in line with the experience service under the specific fitting scenario. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0043] Figure 1A A schematic diagram of an application scenario provided for an embodiment of the present application;
[0044] Figure 1B An application process system diagram provided for an embodiment of the present application;
[0045] Figure 2 Flowchart 1 of a virtual fitting method provided in an embodiment of the present application;
[0046] Figure 3 A virtual fitting method process provided in the embodiment of the present application Figure 2 ;
[0047] Figure 4 A virtual fitting method process provided in the embodiment of the present application Figure 3 ;
[0048] Figure 5 A schematic diagram of the structure of a virtual fitting device provided by an embodiment of the present invention;
[0049] Figure 6 A hardware schematic diagram of a virtual fitting device provided in an embodiment of the present invention.
[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0051] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0052] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.
[0053] In the embodiments of the present application, the words "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.
[0054] With the development of science and technology and the accelerated pace of people's lives, people are eager to achieve efficient fitting, so as to match the clothes that suit them in advance and avoid the trouble of trying on clothes all the time. In virtual fitting technology, users only need to enter their own digital personal image, and then they can put various clothes and accessories that have been digitized in advance on the digital person, and they can find the clothes that suit them without having to try on clothes in person.
[0055] However, in the virtual fitting process, the existing virtual fitting system cannot provide more personalized fitting effects to different users.
[0056] Therefore, this application proposes a virtual fitting method, which provides fitting algorithms of different difficulty for user terminals of different types and levels. The higher the difficulty of the fitting algorithm, the closer the virtual fitting result is to reality, and the cost of the algorithm such as calculation and maintenance will be relatively high. For example, a simple fitting algorithm is provided to families with relatively low requirements, which can save costs while basically meeting the fitting needs; a high-difficulty fitting algorithm is provided to professional stores with higher requirements. On this basis, users of the same user type can be divided into levels, and users with low levels are matched with simple algorithms, and users with high levels are matched with difficult algorithms, so that the virtual fitting effect obtained by the fitting algorithm is more in line with the actual needs of users in specific scenarios.
[0057] Combine the following Figure 1A and Figure 1B , the application scenarios of this application are described.
[0058] Figure 1A A schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1A As shown, the scenario includes a user terminal 101 and a server 102 , and the execution subject in this embodiment is the server 102 .
[0059] The user terminal 101 may send a fitting request to the server 102 . The fitting request includes a specific fitting scene and fitting information. The fitting information may include human body information and / or clothing information.
[0060] The server 102 can receive a fitting request from the user terminal 101, and determine the type of fitting scene in the fitting request according to the source of the user terminal 101, and then match a fitting algorithm suitable for the type of difficulty according to the type of fitting scene in the scene routing system, and finally obtain a virtual fitting result according to the fitting algorithm and the specific requirements of the fitting information in the user terminal 101. The specific requirements may be a digital human model, a clothing model or a virtual dressing model.
[0061] Figure 1B This is an application process system diagram provided by the embodiment of the present application. Figure 1B As shown, the user terminal can be a user APP, fitting mirror, etc.; fitting service scenarios include digital human body, digital service, real-time fitting by real people, digital human body fitting and clothing recommendation, etc.; the scene routing system receives the call request of the service scene from above, obtains the call of the underlying algorithm function from below, encapsulates the algorithm processing results, and performs data escape and content adaptation according to the specific scene service receiving format of the service scene, and completes the delivery of the processing results to the scene service; at the basic algorithm level, according to the continuous increase of algorithm functions and the continuous precipitation of basic algorithm capabilities, the algorithm service architecture system has the characteristics of high scalability, high adaptability and standardized docking. Based on the continuously iterative algorithm technology system, it can continuously provide digital base capability support for scene service innovation, and provide users with new interactive experience through the touch points of the user interaction layer.
[0062] To sum up, the server side 102 matches fitting algorithms of different algorithm difficulties for different types of user terminals 101, so that the fitting requirements are adapted to the algorithm difficulty. The higher the fitting requirements, the more difficult the adapted algorithm is. The virtual fitting results obtained in this way are more in line with the experience service in the specific fitting scenario, achieving the optimal solution of efficiency, cost and experience.
[0063] 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.
[0064] Figure 2 Flowchart 1 of a virtual fitting method provided in an embodiment of the present application. Figure 2 As shown, the method is applied to the server side and includes:
[0065] S201. Obtain a fitting request from a user terminal, where the fitting request includes a fitting scene and fitting information, and the fitting information includes body information and / or clothing information.
[0066] In the above solution, the fitting request includes not only a specific fitting scenario, but also fitting information reflecting the needs of the user terminal. According to the fitting information, it can be known whether the current needs of the user terminal are for a human body model, a clothing model, or a combination of the two.
[0067] S202: Determine the user type of the user terminal according to the source of the user terminal, where the user type is a home user or a store user.
[0068] In this step, the user type can reflect the user's general requirements for fitting service results. Specifically, in home and store scenarios, due to the different groups of people faced, the required fitting service levels and the required fitting result accuracy are different.
[0069] S203. Determine, based on the user type, whether the fitting scene is a home scene category or a store scene category, wherein the fitting scene includes at least one of a digital human body, digital clothing, real-time fitting by a real person, fitting by a digital human body, or clothing recommendation.
[0070] In the above scheme, the fitting scene changes according to the fitting needs of the user terminal, but there are two main categories of fitting scenes, one is the home scene category for family users, and the other is the store scene category for a large number of consumers. Therefore, to distinguish between the two, it is necessary to combine the user type of the user terminal.
[0071] S204. Obtain a target fitting algorithm corresponding to the target scene category according to the scene routing system, wherein the scene routing system includes fitting algorithms of different algorithmic difficulties.
[0072] In the above scheme, the scene routing system includes a variety of fitting algorithms, which can be internal self-developed algorithms, external third-party capability algorithms and open source algorithms, etc. Exemplary algorithms include digital human algorithms, digital clothing modeling algorithms, digital clothing, digital human dressing algorithms, gesture recognition algorithms, speech recognition algorithms, GPT large model algorithms, accessories digitization algorithms, video background switching algorithms and motion capture algorithms, etc.
[0073] In this embodiment, the algorithm is divided according to its difficulty, so that there are different levels of fitting algorithms in the scene routing system. Generally speaking, the greater the difficulty of the algorithm, the better the fitting results, but the higher the cost of calculation, maintenance, etc., therefore, for the family scene category, a fitting algorithm with lower difficulty is more suitable; and for the store scene category, since the store faces many consumers, not relatively fixed family members, the fitting services required in the store scene are more refined than those required in the family scene, and can provide consumers with a more realistic fitting effect, so the fitting algorithm matching store users is more difficult.
[0074] S205: Display virtual fitting results according to the target fitting algorithm and fitting information.
[0075] In this step, after determining the target fitting algorithm to be adopted, combined with the fitting information reflecting the user's needs, a virtual fitting result that meets the user's needs can be obtained. Specifically, when the fitting information is human body information, a digital human model can be obtained after calculation and simulation by the target fitting algorithm. After the digital human model is displayed, in order to facilitate the user to directly use the model in the future, the digital human model can be associated with the user information and stored; when the fitting information is clothing information, it means that the user needs to digitize the clothing at this time, and the clothing model can be obtained after calculation and simulation by the target fitting algorithm; when the fitting information is human body information and clothing information, it means that the user needs to obtain a virtual fitting effect at this time, and a virtual dressing model can be obtained after calculation and simulation by the target fitting algorithm.
[0076] In the embodiment of the present application, the user type is determined to be a home user or a store user based on the source of the user terminal. When the user type is a home user, the fitting scene is the corresponding home scene category; when the user type is a store user, the fitting scene is the corresponding store scene category. Then, based on the scene category, a fitting algorithm of appropriate difficulty is matched from the scene routing system. The fitting requirements of the home scene category are relatively low compared to those of the store scene category, and the investment in the algorithm cost is relatively small. Therefore, the fitting algorithm of the home scene category has a lower matching difficulty, and the fitting algorithm of the store scene category has a higher matching difficulty. Finally, according to the fitting algorithm and the fitting information reflecting the user's needs, a virtual fitting result that meets the user's needs can be obtained.
[0077] Combine the following Figure 3 The specific embodiments illustrate the implementation process of the target fitting algorithm corresponding to the target scene category obtained according to the scene routing system in the virtual fitting method of the present application.
[0078] Figure 3 A virtual fitting method process provided in the embodiment of the present application Figure 2 .like Figure 3 As shown, the method includes:
[0079] S301: Determine whether the fitting request carries user information.
[0080] In this step, the fitting request includes the fitting scene and fitting information. Different user types can be matched with fitting algorithms of different difficulty levels according to the fitting scene and the source of the user terminal. On this basis, the same user type can be further divided into levels, so it is necessary to divide the levels according to the user information.
[0081] S302: If yes, obtain the user level according to the user information.
[0082] S303, according to the user level, target scene category, scene routing system and algorithm mapping relationship, obtain the target fitting algorithm, wherein the algorithm mapping relationship includes the corresponding relationship between the scene category of different user levels and the fitting algorithm in the scene routing system. The lower the user level, the lower the difficulty of the corresponding fitting algorithm.
[0083] In the above scheme, different users in the same scene category may have different requirements for fitting and cost investment. Some users may not have high requirements for the authenticity of virtual fitting and are unwilling to invest a high cost. For such users, there is no need to match a high-cost, high-computing-power fitting algorithm; while for users who have high requirements for authenticity and are willing to invest a high cost in the algorithm, a high-difficulty fitting algorithm can be matched. In this embodiment, the user level is used as the definition standard. Users with low levels have low requirements for authenticity and tend to consume low costs, and a low-difficulty fitting algorithm is provided for them.
[0084] The scene routing system contains a variety of fitting algorithms, and it is necessary to map user levels to fitting algorithms so that low levels correspond to low difficulty and high levels correspond to high difficulty. As mentioned above, the difficulty of fitting algorithms corresponding to different scene categories is also different. Therefore, in terms of external relations, there are differences in fitting algorithms corresponding to different categories, and in terms of internal relations, there are also differences in fitting algorithms corresponding to users of different levels in the same category.
[0085] S304: If not, obtain a default fitting algorithm corresponding to the target scene category, wherein the difficulty of the fitting algorithm corresponding to the store scene category is higher than the difficulty of the fitting algorithm corresponding to the home scene category.
[0086] In this step, when there is no user information with user level, in order to coordinate the fitting authenticity requirements and cost investment willingness of different users, the default fitting algorithm is directly used.
[0087] In an embodiment of the present application, based on the above-mentioned embodiment which matches fitting algorithms of different difficulty levels according to different target scene categories, this embodiment further uses user level as a division standard in the same target scene category, and provides fitting algorithms of different difficulty levels for users of different levels, thereby meeting the user's requirements for fitting authenticity while complying with the user's willingness for cost consumption.
[0088] Combine the following Figure 4 The specific embodiments illustrate the implementation process of obtaining the virtual fitting result based on the target fitting algorithm confirmed by the user terminal in the virtual fitting method of the present application.
[0089] Figure 4 A virtual fitting method process provided in the embodiment of the present application Figure 3 .like Figure 4 As shown, the method includes:
[0090] S401: Output prompt information to a user terminal, where the prompt information is used to prompt a target fitting algorithm for a virtual fitting effect to be displayed.
[0091] In the above solution, before displaying the virtual fitting result to the user terminal, the user terminal may be asked to confirm the target fitting algorithm first, so as to avoid ignoring the user's demand for changing the target fitting algorithm.
[0092] S402: obtaining, within a preset time period, processing operation information of the user terminal on the prompt information, wherein the processing operation information includes confirmation and modification.
[0093] In this step, the processing operation of the user terminal is limited in time in this embodiment to prevent the user terminal from failing to confirm the target fitting algorithm for a long time, affecting the virtual fitting process and occupying resources. In the specific implementation process, if the user does not perform the corresponding processing operation for more than the preset time, it can be directly assumed that the processing operation information of the user terminal is confirmed, and directly enter the next process after the preset time.
[0094] S403: If the processing operation information is confirmed, determine to adopt the target fitting algorithm.
[0095] S404: If the processing operation information is modification, obtain a modified target fitting algorithm.
[0096] In the above solution, if the user terminal needs a target fitting algorithm, the target algorithm modified by the user terminal can be directly obtained, and then calculation simulation is performed according to the modified target fitting algorithm to obtain a virtual fitting result.
[0097] S405: Determine whether the target fitting algorithm is a charging algorithm.
[0098] S406: If it is a charging algorithm, a fee order is generated according to the target scene category and the target fitting algorithm, wherein the target fitting algorithm has different fees in different scene categories.
[0099] S407: Send the expense order to the user terminal, and receive confirmation information of the expense order from the user terminal.
[0100] As mentioned above, the difficulty of fitting algorithms used in different scene categories and for users of different levels is different. Therefore, according to the user level and scene category to which the user terminal belongs, a target fitting algorithm matching the user terminal can be obtained. In this embodiment, it is assumed that the user terminal can use the target fitting algorithm matching it for free. If you want to use a fitting algorithm with a higher difficulty, you need to pay the corresponding usage cost.
[0101] In this step, before obtaining the virtual fitting result according to the target fitting algorithm, it is necessary to first determine whether the user terminal can use the target fitting algorithm for free. If it cannot be used for free, it means that the target fitting algorithm is not a fitting algorithm that matches the user terminal at this time, and the user terminal needs to pay the usage fee before it can be used.
[0102] S408. Display virtual fitting results according to the target fitting algorithm and fitting information; or if it is not a paid algorithm, display virtual fitting results according to the target fitting algorithm and fitting information.
[0103] In the above scheme, the user terminal can use the target fitting algorithm after paying the fee order; when the target fitting algorithm is a free algorithm, it means that the target fitting algorithm is a fitting algorithm that matches the user terminal and can be used directly.
[0104] In the embodiment of the present application, before calculating the simulated virtual fitting result according to the target fitting algorithm, the user terminal can be asked about the willingness to use. If the user terminal recognizes the current target fitting algorithm, the target fitting algorithm is confirmed; if the user terminal does not recognize the current target fitting algorithm, the user terminal is asked to give the target fitting algorithm it wants. In order to prevent the user terminal from unauthorized use of the target fitting algorithm that does not match the user terminal, it is also necessary to determine whether the target fitting algorithm is charged. If it is charged, the user terminal needs to pay a certain fee before using the target fitting algorithm.
[0105] In summary, the virtual fitting method provided in the embodiments of the present application includes fitting algorithms of different difficulty levels in the same scene routing system, and maps the difficulty of the fitting algorithm with the fitting authenticity requirements and algorithm investment costs of the user terminal. The higher the fitting authenticity requirements and investment costs of the fitting scene category to which the user terminal belongs, the higher the corresponding fitting algorithm difficulty. Different user terminals in the same scene category have different fitting difficulties due to differences in user levels. This allows fitting algorithms of different scene categories and different user levels to be adapted when users experience the virtual fitting service, thereby achieving an optimal solution in terms of efficiency, cost and experience.
[0106] Figure 5 A schematic diagram of the structure of a virtual fitting device provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the virtual fitting device may include various functional modules for implementing the aforementioned virtual fitting method, and any functional module may be implemented in software and / or hardware.
[0107] For example, the virtual fitting device 50 may include: a first processing module 501 , a second processing module 502 , a third processing module 503 , a fourth processing module 504 and a fifth processing module 505 .
[0108] An acquisition module 501 is used to acquire a fitting request from a user terminal, where the fitting request includes a fitting scene and fitting information, where the fitting information includes human body information and / or clothing information;
[0109] A first processing module 502 is used to determine a target scene category of a fitting scene according to a source of a user terminal;
[0110] The second processing module 503 is used to obtain a target fitting algorithm corresponding to a target scene category according to a scene routing system, wherein the scene routing system includes fitting algorithms of different algorithmic difficulties;
[0111] The third processing module 504 is used to display the virtual fitting result according to the target fitting algorithm and the clothing information.
[0112] Optionally, the first processing module 502 can also be used to determine the user type to which the user terminal belongs based on the source of the user terminal, and the user type is a home user or a store user; based on the user type, determine the fitting scene as a home scene category or a store scene category, wherein the fitting scene includes at least one of a digital human body, digital clothing, real-time fitting by a real person, a digital human body fitting, or clothing recommendations.
[0113] Optionally, the second processing module 503 can also be specifically used for: if the fitting request does not carry user information, then obtaining a default fitting algorithm corresponding to the target scene category, wherein the difficulty of the fitting algorithm corresponding to the store scene category is higher than the difficulty of the fitting algorithm corresponding to the home scene category.
[0114] Optionally, the second processing module 503 can also be used to obtain the user level according to the user information if the fitting request carries user information; obtain the target fitting algorithm according to the user level, target scene category, scene routing system and algorithm mapping relationship, wherein the algorithm mapping relationship includes the correspondence between the scene categories of different user levels and the fitting algorithms in the scene routing system, and the lower the user level, the lower the difficulty of the corresponding fitting algorithm.
[0115] Optionally, the third processing module 504 can also be specifically used to: obtain a digital human model based on human body information and a target fitting algorithm, and store and display the digital human model; obtain and display a clothing model based on clothing information and a target fitting algorithm; obtain and display a virtual dressing model based on human body information and clothing information, as well as a target fitting algorithm.
[0116] Optionally, the third processing module 504 can also be used to output prompt information to the user terminal, where the prompt information is used to prompt the target fitting algorithm of the virtual fitting effect to be displayed; within a preset time period, obtain the user terminal's processing operation information on the prompt information, wherein the processing operation information includes confirmation and modification; if the processing operation information is confirmation, it is determined to adopt the target fitting algorithm; if the processing operation information is modification, the modified target fitting algorithm is obtained.
[0117] Optionally, the third processing module 504 can also be specifically used to: determine whether the target fitting algorithm is a charging algorithm; if it is a charging algorithm, generate a fee order based on the target scene category and the target fitting algorithm, wherein the target fitting algorithm has different fees under different scene categories; send the fee order to the user terminal, and receive confirmation information of the user terminal for the fee order.
[0118] The virtual fitting device is used to execute the technical solution provided by the aforementioned virtual fitting method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment and will not be repeated here.
[0119] The present application also provides an electronic device, comprising: at least one processor and a memory;
[0120] Memory stores computer-executable instructions;
[0121] At least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the virtual fitting method.
[0122] Figure 6Schematic diagram of the hardware of the electronic device provided by the embodiment of the present invention. Figure 6 As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. The device 60 also includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.
[0123] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 performs the above virtual fitting method.
[0124] The specific implementation process of the processor 601 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0125] In the above Figure 6 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.
[0126] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.
[0127] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0128] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the virtual fitting method as described above is implemented.
[0129] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0130] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0131] The division of the units is only a logical function division, and there may be other divisions 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.
[0132] 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.
[0133] 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.
[0134] 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, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0135] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0136] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, 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, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A virtual fitting method, characterized in that: include: Acquire a fitting request from a user terminal, wherein the fitting request includes a fitting scene and fitting information, and the fitting information includes human body information and / or clothing information; Determining a target scene category of the fitting scene according to a source of the user terminal; According to the scene routing system, a target fitting algorithm corresponding to the target scene category is obtained, wherein the scene routing system includes fitting algorithms of different algorithm difficulties; The virtual fitting result is displayed according to the target fitting algorithm and the fitting information.
2. The method according to claim 1, characterized in that The determining, according to the source of the user terminal, the target scene category of the fitting scene includes: Determine, according to the source of the user terminal, the user type to which the user terminal belongs, the user type being a home user or a store user; According to the user type, it is determined that the fitting scene is a home scene category or a store scene category.
3. The method according to claim 2, characterized in that The step of obtaining a target fitting algorithm corresponding to the target scene category according to the scene routing system includes: If the fitting request does not carry user information, a default fitting algorithm corresponding to the target scene category is obtained, wherein the difficulty of the fitting algorithm corresponding to the store scene category is higher than the difficulty of the fitting algorithm corresponding to the home scene category.
4. The method according to claim 3, characterized in that If the fitting request carries user information, the method further includes: Acquire the user level according to the user information; A target fitting algorithm is obtained according to the user level, the target scene category, the scene routing system and the algorithm mapping relationship, wherein the algorithm mapping relationship includes the correspondence between the scene categories of different user levels and the fitting algorithms in the scene routing system, and the lower the user level, the lower the difficulty of the corresponding fitting algorithm.
5. The method according to claim 1, characterized in that The displaying of the virtual fitting result according to the target fitting algorithm and the fitting information includes at least one of the following: Obtaining a digital human model according to the human body information and the target fitting algorithm, and storing and displaying the digital human model; Obtaining and displaying a clothing model according to the clothing information and the target fitting algorithm; A virtual dressing model is obtained and displayed according to the human body information, the clothing information, and the target fitting algorithm.
6. The method according to claim 1, characterized in that Before displaying the virtual fitting result according to the target fitting algorithm and the fitting information, the method further includes: Outputting prompt information to the user terminal, wherein the prompt information is used to prompt the target fitting algorithm to display a virtual fitting effect; Acquire, within a preset time period, processing operation information of the user terminal on the prompt information, wherein the processing operation information includes confirmation and modification; If the processing operation information is confirmed, determining to adopt the target fitting algorithm; If the processing operation information is modification, then a modified target fitting algorithm is obtained.
7. The method according to claim 1, characterized in that Before displaying the virtual fitting result according to the target fitting algorithm and the fitting information, the method further includes: Determining whether the target fitting algorithm is a charging algorithm; If it is a charging algorithm, a fee order is generated according to the target scene category and the target fitting algorithm, wherein the target fitting algorithm has different fees in different scene categories; Sending a fee order to the user terminal and receiving confirmation information of the fee order from the user terminal.
8. A virtual fitting device, characterized in that: include: An acquisition module, configured to acquire a fitting request from a user terminal, wherein the fitting request includes a fitting scene and fitting information, and the fitting information includes human body information and / or clothing information; A first processing module, configured to determine a target scene category of the fitting scene according to a source of the user terminal; A second processing module is used to obtain a target fitting algorithm corresponding to the target scene category according to a scene routing system, wherein the scene routing system includes fitting algorithms of different algorithm difficulties; The third processing module is used to display the virtual fitting result according to the target fitting algorithm and the fitting information.
9. A virtual fitting device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the virtual fitting method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the virtual fitting method according to any one of claims 1 to 7 are implemented.
