Method, device and equipment for assisting in article storage and storage medium

Abstract

The invention provides a method, device and equipment for assisting article storage and a storage medium, and the method comprises the steps: obtaining a first image of a to-be-stored article and a second image of a storage space, and carrying out the target detection of the first image and the second image, the method comprises the following steps: obtaining article information of an article to be stored in a first image and space information of a storage space in a second image, and generating a storage effect image on the basis of the article information of at least one article to be stored and the space information of at least one storage space, so that a user only needs to upload the image of the article to be stored and the space information of the storage space; therefore, the intelligent classification and storage suggestions can be obtained, the articles can be stored more conveniently and orderly, the article storage efficiency is improved, and the utilization rate of the storage space is increased.

Description

Technical Field

[0001] The present disclosure relates to artificial intelligence technology, and in particular to a method, device, equipment and storage medium for assisting item storage. Background Art

[0002] People often encounter situations where they need to store and organize items in their daily lives and work. For example, when moving after renting or buying a house, people need to pack and organize items in the old house, and then organize and organize the items in the room after moving them to the new house.

[0003] Currently, the storage of items requires manual design of storage methods and the placement of items. However, the layouts of new and old houses are often different. It takes a long time and effort to re-store items. In addition, if the storage layout design of the new house is unreasonable, it will make it inconvenient to take items and reduce space utilization. Summary of the invention

[0004] Embodiments of the present disclosure provide a method, device, equipment and storage medium for assisting item storage, so as to improve item storage efficiency and storage space utilization.

[0005] One aspect of an embodiment of the present disclosure provides a method for assisting item storage, comprising:

[0006] Acquire a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space;

[0007] Performing target detection on the first image and the second image respectively to obtain item information of the at least one item to be stored and spatial information of the at least one storage space, wherein the item information includes an item category of the item to be stored, and the spatial information includes a spatial category of the storage space;

[0008] Based on the item information of the at least one item to be stored and the space information of the at least one storage space, a storage effect image of the at least one storage space is generated, and the storage effect image is used to display the item storage solution of the corresponding storage space.

[0009] Optionally, after performing target detection on the first image and the second image respectively to obtain item information of at least one item to be stored and space information of at least one storage space, the method includes:

[0010] Based on the preset corresponding relationship between the item category and the space category, the items to be stored and the storage space are matched to obtain a mapping relationship between the at least one item to be stored and the at least one storage space.

[0011] Optionally, generating the storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space includes:

[0012] The item information of the at least one item to be stored, the space information of the at least one storage space, and the mapping relationship are input into a language model, and the storage effect image of the at least one storage space is generated through the language model.

[0013] Optionally, generating the storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space includes:

[0014] Determine at least one storage relationship combination based on the mapping relationship, wherein the storage relationship combination includes a target storage space and at least one target item to be stored in the target storage space;

[0015] The object information of the target object to be stored in each storage relationship combination and the space information of the target storage space are respectively input into the language model, and the storage effect image corresponding to each storage relationship combination is generated through the language model.

[0016] Optionally, generating the storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space includes:

[0017] Performing image preprocessing on the first image to separate the image content of each of the items to be stored, and obtaining a storage item map;

[0018] performing image preprocessing on the second image, erasing image content of non-storage space in the second image, and obtaining a storage space map;

[0019] The storage item map, the storage space map, the item information of the at least one item to be stored, the space information of the at least one storage space and the mapping relationship are input into a language model, and the storage effect image of the at least one storage space is generated through the language model.

[0020] Optionally, performing target detection on the first image and the second image respectively to obtain item information of at least one item to be stored and space information of at least one storage space includes:

[0021] Inputting the first image and the second image into a target detection model to obtain an object detection frame in the first image and a space detection frame in the second image;

[0022] The target detection model is used to perform target detection on the image information in the object detection frame and the space detection frame to obtain the item information and the space information.

[0023] Optionally, before inputting the first image and the second image into a target detection model to obtain an object detection frame in the first image and a space detection frame in the second image, the method further includes:

[0024] Standardizing the first image and the second image based on a standard scale, wherein the scale refers to a ratio between a distance on the image and a corresponding actual distance;

[0025] After inputting the first image and the second image into the target detection model and obtaining the object detection frame in the first image and the space detection frame in the second image, the method further includes:

[0026] Obtaining detection frame sizes of the object detection frame and the space detection frame;

[0027] The step of generating the storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space comprises:

[0028] The storage effect image of the at least one storage space is generated based on the item information of the at least one item to be stored, the space information of the at least one storage space, the mapping relationship and the detection frame size.

[0029] Optionally, the method further includes:

[0030] Obtain a model training set, wherein the model training set includes a first sample image corresponding to the sample object and a second sample image corresponding to the sample space;

[0031] The target detection model is trained based on the model training set, and the image database of the language model is updated.

[0032] Optionally, the performing model training on the target detection model based on the model training set includes:

[0033] Inputting the first sample image and the second sample image into the target detection model to obtain a sample recognition result;

[0034] Based on the sample recognition result, the sample item label of the first sample image and the sample space label of the second sample image, the target detection model is iteratively updated to adjust the model parameters, wherein the sample item label includes the item category of the sample item, and the sample space label includes the space category of the sample space.

[0035] Another aspect of the present disclosure provides a device for assisting in storing items, including:

[0036] An acquisition module, configured to acquire a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space;

[0037] a detection module, configured to perform target detection on the first image and the second image respectively, to obtain item information of the at least one item to be stored and spatial information of the at least one storage space, wherein the item information includes an item category of the item to be stored, and the spatial information includes a spatial category of the storage space;

[0038] A generation module is used to generate a storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space, wherein the storage effect image is used to display the item storage plan of the corresponding storage space.

[0039] Optionally, the device further comprises:

[0040] A matching module is used to match the items to be stored with the storage space based on a preset corresponding relationship between the item category and the space category, so as to obtain a mapping relationship between the at least one item to be stored and the at least one storage space.

[0041] Another aspect of the disclosed embodiment provides a system for assisting item storage, the system comprising a data input unit, a feature extraction unit, and a solution generation unit;

[0042] The data input unit is used to acquire a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space;

[0043] The feature extraction unit is used to perform target detection on the first image and the second image respectively to obtain item information of the at least one item to be stored and spatial information of the at least one storage space, wherein the item information includes the item category of the item to be stored, and the spatial information includes the spatial category of the storage space;

[0044] The solution generating unit is used to generate a storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space, wherein the storage effect image is used to display the item storage solution of the corresponding storage space.

[0045] Optionally, the system further includes an information matching unit;

[0046] The information matching unit is used to match the items to be stored and the storage space based on the preset corresponding relationship between the item category and the space category, so as to obtain a mapping relationship between the at least one item to be stored and the at least one storage space.

[0047] Another aspect of the present disclosure provides an electronic device, including:

[0048] Memory for storing computer programs;

[0049] The processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method described in the above aspects is implemented.

[0050] Another aspect of the embodiments of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in the above aspects is implemented.

[0051] Another aspect of the embodiments of the present disclosure provides a computer program, including computer program instructions, which implement the methods described in the above aspects when executed by a processor.

[0052] Based on the embodiments of the present disclosure, an intelligent auxiliary solution for item storage is provided, which obtains a first image of the item to be stored and a second image of the storage space, performs target detection on the first image and the second image respectively, identifies item information of the item to be stored in the first image and space information of the storage space in the second image, and generates a storage effect image based on the item information and space information. Users only need to upload images of the item to be stored and the storage space to obtain intelligent classification and storage suggestions, thereby making item storage more convenient and orderly, and improving item storage efficiency and storage space utilization.

[0053] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0055] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0056] Figure 1 A flowchart of an embodiment of the method for storing auxiliary items disclosed herein;

[0057] Figure 2 A flowchart of another embodiment of the method for storing auxiliary items disclosed herein;

[0058] Figure 3 A flowchart of another embodiment of the method for storing auxiliary items disclosed herein;

[0059] Figure 4 A schematic diagram of the structure of an embodiment of the device for assisting article storage disclosed in the present invention;

[0060] Figure 5 A schematic diagram of the structure of another embodiment of the device for assisting article storage disclosed in the present invention;

[0061] Figure 6 A schematic diagram of the structure of an embodiment of the system for assisting article storage disclosed in the present invention;

[0062] Figure 7 The figure is a schematic diagram of the structure of an application embodiment of the electronic device disclosed in the present invention. DETAILED DESCRIPTION

[0063] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0064] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0065] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0066] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0067] In addition, the term "and / or" in the present disclosure is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present disclosure generally indicates that the associated objects before and after are in an "or" relationship.

[0068] It should also be understood that the description of the various embodiments in the present disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0069] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0070] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0071] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0072] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0073] The embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0074] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0075] Please refer to Figure 1 , which shows a flow chart of a method for assisting item storage provided by an exemplary embodiment of the present disclosure. The method for assisting item storage in the embodiment of the present disclosure may be implemented by an electronic device that is deployed with a target detection model and a large language model. The embodiment includes the following steps:

[0076] Step 101 : acquiring a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space.

[0077] Optionally, the electronic device may be a background server, in which case the first image and the second image may be collected and uploaded by the user terminal; the electronic device may also be a user terminal, in which case the first image and the second image may be directly obtained from the memory.

[0078] The first image is obtained by photographing the items to be stored (such as photos or video screenshots), and the second image is obtained by photographing the storage space. Users can upload one or more first images, each of which may contain image information of one or more items to be stored; users can upload one or more second images, each of which may contain image information of one or more storage spaces. Storage space refers to a spatial structure composed of objects that can accommodate items, such as architectural spaces such as living rooms, kitchens, bedrooms, and bathrooms, or furniture spaces such as wardrobes, cabinets, and computer desks.

[0079] Schematically, the first image includes image a and image b, image a is obtained by photographing a vase, and image b is obtained by photographing kitchen utensils and tableware; the second image includes image c and image d, wherein image c is obtained by photographing a living room, and image d is obtained by photographing a kitchen.

[0080] In a possible implementation, in order to improve the accuracy of storage space recognition and obtain accurate spatial information, the user terminal may generate shooting prompt information, such as indicating shooting location, shooting angle and other shooting methods, so that the user can shoot the storage space according to the shooting prompt information to obtain a second image.

[0081] Step 102, performing target detection on the first image and the second image respectively, obtaining item information of at least one item to be stored and spatial information of at least one storage space, wherein the item information includes the item category of the item to be stored, and the spatial information includes the spatial category of the storage space.

[0082] In a possible implementation, target detection is performed on the first image and the second image respectively to extract the item information of each item to be stored and the spatial information of each storage space. Schematically, target detection can be performed using tools such as target detection models (such as regional convolutional neural network models) and classifiers in computer vision (such as support vector machines and random forest algorithms).

[0083] For example, through object detection, it is extracted that the item category of the items to be stored in image a is "decorations", and the space category of the storage space in image c is "living room".

[0084] For storage spaces with obvious functional features, such as a living room with a sofa or a bedroom with a bed and a wardrobe, accurate space information can be identified based on the second image. If the storage space is a completely empty room, the user can manually add a label to the second image to indicate the space category, so as to avoid the object detection model from making mistakes or failing to generate recognition results.

[0085] Step 103: generating a storage effect image of at least one storage space based on the item information of at least one item to be stored and the space information of at least one storage space.

[0086] The storage effect image is used to display the storage solution of the corresponding storage space. Specifically, the storage effect image can display the storage solution of classifying the items to be stored and placing them in each storage space through virtual items and virtual space. Alternatively, the storage effect image can be obtained by integrating the content in the first image and the second image uploaded by the user, so as to display the storage effect of the user's items stored in the user's room. Alternatively, based on the item information of at least one item to be stored and the space information of at least one storage space, a storage effect video of at least one storage space can be generated to display the storage solution in the form of a video.

[0087] In a possible implementation, description information about the items to be stored and the storage space is generated based on the item information and the space information, and the description information indicates that corresponding items to be stored are placed in the storage space, and a storage effect image is generated based on the description information.

[0088] In an embodiment of the present disclosure, an intelligent auxiliary solution for item storage is provided. By acquiring a first image of the item to be stored and a second image of the storage space, target detection is performed on the first image and the second image respectively, item information of the item to be stored in the first image and space information of the storage space in the second image are identified, and a storage effect image is generated based on the item information and space information. The user only needs to upload images of the item to be stored and the storage space to obtain intelligent classification and storage suggestions, thereby making item storage more convenient and orderly, and improving item storage efficiency and storage space utilization.

[0089] Optional, in the above Figure 1 Based on the illustrated embodiment, step 102 may include the following steps:

[0090] Based on the preset correspondence between the item category and the space category, the items to be stored and the storage space are matched to obtain a mapping relationship between the items to be stored and the storage space.

[0091] In a possible implementation, a preset correspondence between item categories and space categories may be pre-stored. For example, a TV and a coffee table correspond to the living room, and tableware and kitchenware correspond to the kitchen. After the item categories and space categories are extracted, the items to be stored and the storage space are matched based on the preset correspondence to obtain a mapping relationship between the items to be stored and the storage space.

[0092] In a possible implementation, the mapping relationship may be added to the description information and input into the language model, so that the language model generates storage effect images corresponding to all storage spaces at one time. Step 103 may include the following steps:

[0093] Step 103a: inputting the item information of at least one item to be stored, the space information of at least one storage space, and the mapping relationship into a language model, and generating a storage effect image of at least one storage space through the language model.

[0094] Based on the object information, space information and mapping relationship, the language model can generate storage effect images that classify the objects to be stored in various storage spaces. For example, if the mapping relationship includes pillows-bedroom and bowls-kitchen, the language model can generate storage effect images of pillows in the bedroom and bowls in the kitchen.

[0095] The description information including the item category, space category and mapping relationship can be input into the large language model, and the storage effect image can be generated by the Vincent graph module of the large language model. Optionally, the language model of the embodiment of the present disclosure can be implemented by using a pre-trained large language model, and the Vincent graph function can be used to generate the storage effect image based on the item information and space information. For example, if the text information "cat" is input, the large language model can generate an image containing a cat. A large language model (LLM) refers to a deep learning model trained with a large amount of text data. The Vincent graph and Vincent video functions of the large language model can generate corresponding images or videos based on the input description information. The language model in the embodiment of the present disclosure can be implemented by any large language model, for example, the Vincent video large model Sora can generate corresponding videos based on the input text information, the generative pre-trained transformer model (Chat Generative Pre-trainedTransformer, ChatGPT), etc. The embodiment of the present disclosure does not limit the specific model type used by the language model.

[0096] Based on this embodiment, the item information of each item to be stored, the spatial information of each storage space, and the mapping relationship between the items to be stored and the storage space can be input into the language model at one time. It only takes one time to input the recognized information and the mapping relationship into the language model, and the language model can generate storage effect images corresponding to all storage spaces at one time. This generation method is simple and fast, and the generation efficiency of the storage effect diagram is higher.

[0097] By adding a mapping relationship to the description information, the large language model can be instructed to generate a corresponding storage effect image according to the mapping relationship, for example, generating a storage effect image of placing a vase in a living room.

[0098] In another possible implementation, the items to be stored and the storage spaces may be grouped based on a mapping relationship, and a group of spatial information and item information of the items to be stored and the storage spaces may be input into the language model at one time, so that the language model generates a storage effect image corresponding to the storage space. The above step 103 may also include the following steps:

[0099] Step 103b: determining at least one storage relationship combination based on the mapping relationship, wherein the storage relationship combination includes a target storage space and at least one target item to be stored stored in the target storage space.

[0100] Step 103c, inputting the object information of the target object to be stored in each storage relationship combination and the spatial information of the target storage space into the language model respectively, and generating the storage effect image corresponding to each storage relationship combination through the language model.

[0101] Optionally, a storage relationship combination includes a target storage space and at least one target object to be stored corresponding to the target storage space obtained based on the mapping relationship. One input of the language model includes the object information of the target object to be stored in a storage relationship combination and the space information of the target storage space.

[0102] Based on this embodiment, the storage space and the items to be stored can be grouped first, and the storage relationship combination is used as a unit. The item information of the target item to be stored in a storage relationship combination and the space information of the target storage space are input each time, so as to generate the storage effect image corresponding to each storage space in sequence. This generation method inputs the relevant description information of a group of storage relationship combinations into the language model at a time to generate a storage effect image corresponding to a storage space, which can avoid the phenomenon of image generation errors in the process of the language model generating the storage effect image (for example, the storage effect image of kitchen utensils stored in the bedroom), and improve the accuracy and practicality of the storage plan.

[0103] The above two methods of generating storage effect pictures both utilize the text map function of the language model to directly generate images based on text information, and the image content of the storage effect picture includes virtual items and virtual space generated by the language model. In another possible implementation, in order to improve the user experience and avoid the user from wasting too much energy when searching for the actual items to be stored by comparing the virtual items in the storage effect picture, the image content in the first image and the second image taken by the user can also be used to generate a storage effect picture, directly showing the actual effect of the user's items being stored in the user's room, thereby further improving the storage efficiency. The above step 103 can also include the following steps:

[0104] Step 103d: perform image preprocessing on the first image, separate the image content of each item to be stored, and obtain a storage item map.

[0105] Step 103e, performing image preprocessing on the second image, erasing image content of non-storage space in the second image, and obtaining a storage space map.

[0106] Step 103f, inputting the storage item map, the storage space map, the item information of at least one item to be stored, the space information of at least one storage space, and the mapping relationship into a language model, and generating a storage effect image of at least one storage space through the language model.

[0107] By adjusting the database of the language model, adding image information therein and training the language model, the language model can receive both image and text input information, and process the input image information based on the input text information to obtain an image that conforms to the text information.

[0108] After obtaining the first image and the second image, the first image can be preprocessed to separate the image content of each item to be stored, and each item to be stored can be cut out to obtain a storage item map; the second image can be preprocessed to erase the image content of the non-storage space in the second image. For example, after identifying the object in the second image, for the non-storage space part (such as the items that the user has already stacked in the storage space), based on the pixel value of the storage space part nearby, the non-storage space part can be erased to obtain a storage space map whose image content only contains the storage space. The storage item map, storage space map, item information, space information and mapping relationship are input into the language model, and the storage item map and the storage space map are fused according to the description text containing the item information, space information and mapping relationship by using the language model, and the storage effect image of at least one storage space is generated by the language model, and the items in the storage effect image are the items in the first image, and the storage space is the storage space in the second image.

[0109] Please refer to Figure 2, which shows a flow chart of a method for assisting item storage provided by another exemplary embodiment of the present disclosure. The method for assisting item storage in the embodiment of the present disclosure may be implemented by an electronic device that is deployed with a target detection model and a large language model. The embodiment includes the following steps:

[0110] Step 201 : acquiring a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space.

[0111] The specific implementation of step 201 can refer to the above step 101, and the embodiment of the present application will not be repeated here.

[0112] Step 202: Standardize the first image and the second image based on a standard scale.

[0113] In a possible implementation, the object detection model can extract the size of the items to be stored and the storage space in the image, so that the large language model generates a storage effect image based on the size. Since users may use different magnifications (or reductions) when photographing the items to be stored and the storage space, before inputting the images into the object detection model, the first image and the second image can be standardized to unify the ratio of the first image and the second image.

[0114] Optionally, since the change in the distance between the lens and the object during shooting will also cause the size of the object in the image to be different, in order to improve the accuracy of size extraction, image acquisition prompt information can be generated through the user terminal, for example, prompting the user to shoot all items to be stored and storage spaces at the same distance.

[0115] Step 203: input the first image and the second image into a target detection model to obtain an object detection frame in the first image and a space detection frame in the second image.

[0116] Step 204, obtaining the detection frame sizes of the object detection frame and the space detection frame.

[0117] In a possible implementation, an object detection model may be used to perform object detection on the first image and the second image. The object detection model may be implemented using a regional convolutional neural network (R-CNN) model, such as a Faster R-CNN model.

[0118] After the first image and the second image are input into the target detection model, the target detection model first determines the area in the image where there are objects or spatial structures, and then selects the objects in the first image through the object detection frame, and selects the spatial structures (such as walls, doors, and windows) in the second image through the space detection frame. The detection frame sizes of the object detection frame and the space detection frame are obtained through the target detection model, so that virtual objects and virtual spaces of corresponding sizes can be generated based on the detection frame sizes, and a more accurate storage solution can be provided.

[0119] Step 205: Perform target detection on the image information in the object detection frame and the space detection frame through the target detection model to obtain object information and space information.

[0120] In a possible implementation, the first image and the second image are respectively input into an object detection model (e.g., an R-CNN model) for object detection. The object detection model first identifies the region where the object is located in the image and selects the region with a detection frame (object detection frame and space detection frame), then determines the specific features of the object in the detection frame, and outputs object information and space information.

[0121] Step 206: Generate a storage effect image of at least one storage space based on the item information of at least one item to be stored, the space information of at least one storage space, the mapping relationship, and the size of the detection frame.

[0122] Optionally, description information including item information, space information, mapping relationship and detection frame size is input into a large language model, so that the large language model generates a storage effect image after classification and storage according to the mapping relationship, space size and item size.

[0123] In the disclosed embodiment, by standardizing the first image and the second image, and obtaining the detection frame sizes of the items to be stored and the storage space in the image based on the object detection frame and the space detection frame, respectively, the large language model generates a storage effect image based on the corresponding detection frame sizes, and storage suggestions can be made based on accurate proportions, thereby improving the practicality of the storage suggestions and the utilization rate of the storage space.

[0124] Please refer to Figure 3 , which shows a flow chart of a method for assisting item storage provided by another exemplary embodiment of the present disclosure. The method for assisting item storage of the embodiment of the present disclosure may be implemented by an electronic device that is deployed with a target detection model and a large language model. Figure 1 Based on the embodiment shown, this embodiment also includes the following steps:

[0125] Step 301: Obtain a model training set, where the model training set includes a first sample image corresponding to a sample object and a second sample image corresponding to a sample space.

[0126] In a possible implementation, before applying the object detection model and the language model to assist in the storage of items (ie, before the above step 101), the collected item images and storage space images may be used as a model training set to adjust the model parameters.

[0127] For example, for the scenario of users moving, a large number of images of household items such as furniture and home appliances, as well as images of various types of home spaces such as bedrooms, kitchens, and living rooms can be put into the model training set.

[0128] Step 302: Perform model training on the target detection model based on the model training set, and update the image database of the language model.

[0129] Optionally, when obtaining the model training set, you can also obtain the model prediction set. After the model training is completed, use the prediction set to verify whether the model prediction result can meet the requirements (for example, the actual accuracy reaches the target accuracy). If not, continue iterative training.

[0130] In a possible implementation, the target detection model may be trained based on sample labels, and the large language model may use the model training set to update its database, so that the large language model can generate more accurate images based on the input text.

[0131] Step 302 may include the following steps:

[0132] Step 302a: input the first sample image and the second sample image into the target detection model to obtain a sample recognition result.

[0133] Step 302b, based on the sample recognition result, the sample item label of the first sample image and the sample space label of the second sample image, iteratively update the target detection model and adjust the model parameters. The sample item label includes the item category of the sample item, and the sample space label includes the space category of the sample space.

[0134] The sample item label is the correct item category of the sample item in the first sample image, and the sample space label is the correct space category of the sample space in the second sample image. Using the sample item label and sample space label and the sample recognition results output from each round of training, the model loss is calculated and the model parameters are adjusted until the model meets the training end conditions (for example, the number of training times reaches the preset number, or the model loss reaches the target loss).

[0135] In the disclosed embodiment, the target detection model is trained using a model training set, and the image database of a large language model is expanded to improve the accuracy of object recognition and image generation, thereby improving the practicality of storage suggestions.

[0136] In a possible application scenario, the method of assisting item storage provided by the above-mentioned disclosed embodiments can be used to assist users in item storage when moving. For example, after buying or renting a house, the user needs to pack and organize the original items in the old house, and after moving the items to the new house, the disordered items in the packed state need to be rearranged in the new house. However, the layout of the new house is usually not completely consistent with the old house. For example, the number of bedrooms in the new house is different from the number of bedrooms in the old house, and the number and position of storage furniture such as wardrobes, tables, and cabinets in the new house are different from those in the old house. Therefore, the user cannot store the items in the new house according to the original item storage method, and needs to re-plan and organize. If the item storage is completely based on the user's personal feelings, it will take a long time to plan the storage plan, and unreasonable storage will also lead to problems such as chaotic item placement and low space utilization. The method of assisting item storage provided by the above-mentioned disclosed embodiments can realize intelligent item classification and storage recommendation functions, can quickly identify the information of items and rooms and group items and rooms, and use the Wensheng map function of the large language model to generate storage effect images for user reference, providing reasonable storage suggestions. Users can store and arrange items according to the storage effect images, which improves the storage efficiency, saves time in planning storage plans, and can improve the space utilization of the house.

[0137] Please refer to Figure 4 , which shows a structural block diagram of an auxiliary article storage device provided by an exemplary embodiment of the present disclosure. The auxiliary article storage device of this embodiment includes:

[0138] An acquisition module 401 is used to acquire a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space;

[0139] The detection module 402 is used to perform target detection on the first image and the second image acquired by the acquisition module 401, respectively, to obtain item information of at least one item to be stored and spatial information of at least one storage space, wherein the item information may include, but is not limited to, the item category of the item to be stored, and the spatial information may include, but is not limited to, the spatial category of the storage space;

[0140] The generating module 403 is used to generate a storage effect image of at least one storage space based on the item information of at least one item to be stored and the space information of at least one storage space obtained by the detecting module 402, and the storage effect image is used to display the item storage plan of the corresponding storage space.

[0141] Optional, such as Figure 5As shown, it shows a structural block diagram of an auxiliary article storage device provided by another exemplary embodiment of the present disclosure. In a possible implementation, the auxiliary article storage device of the embodiment of the present disclosure further includes:

[0142] The matching module 501 is used to match the items to be stored with the storage space based on the preset corresponding relationship between the item category and the space category, so as to obtain a mapping relationship between the items to be stored and the storage space.

[0143] Optionally, in a possible implementation manner, the generating module 403 may also be used to:

[0144] The item information of at least one item to be stored obtained by the detection module 402, the space information of at least one storage space, and the mapping relationship obtained by the matching module 501 are input into the language model, and the storage effect image of at least one storage space is generated by the language model.

[0145] Optionally, in a possible implementation manner, the generating module 403 may also be used to:

[0146] Determine at least one storage relationship combination based on the mapping relationship obtained by the matching module 501, wherein the storage relationship combination includes a target storage space and at least one target item to be stored in the target storage space;

[0147] The object information of the target object to be stored in each storage relationship combination and the spatial information of the target storage space are respectively input into the language model, and the language model generates a storage effect image corresponding to each storage relationship combination.

[0148] Optionally, in a possible implementation manner, the generating module 403 may also be used to:

[0149] Performing image preprocessing on the first image acquired by the acquisition module 401, separating the image content of each of the items to be stored, and obtaining a storage item map;

[0150] Performing image preprocessing on the second image acquired by the acquisition module 401, erasing image content of non-storage space in the second image, and obtaining a storage space map;

[0151] The storage item map, the storage space map, the item information of at least one item to be stored obtained by the detection module 402, the space information of at least one storage space, and the mapping relationship obtained by the matching module 501 are input into the language model, and the storage effect image of at least one storage space is generated by the language model.

[0152] Optionally, in a possible implementation manner, the detection module 402 may also be used to:

[0153] Input the first image and the second image acquired by the acquisition module 401 into the target detection model to acquire the object detection frame in the first image and the space detection frame in the second image;

[0154] The target detection model is used to perform target detection on the image information in the object detection frame and the space detection frame to obtain the object information and space information.

[0155] Optional, such as Figure 5 As shown, in a possible implementation, the device for storing auxiliary items in the embodiment of the present disclosure further includes:

[0156] A processing module 502 is used to perform standardization processing on the first image and the second image acquired by the acquisition module 401 based on a standard scale, wherein the scale refers to the ratio between the distance on the image and the corresponding actual distance;

[0157] A measurement module 503 is used to obtain the detection frame sizes of the object detection frame and the space detection frame obtained by the detection module 402;

[0158] The generation module 403 may also be used to generate a storage effect image of at least one storage space based on the item information of at least one item to be stored, the space information of at least one storage space, the mapping relationship and the detection frame size obtained by the detection module 402 .

[0159] Optional, such as Figure 5 As shown, in a possible implementation, the device for storing auxiliary items in the embodiment of the present disclosure further includes:

[0160] A sample acquisition module 504 is used to acquire a model training set, where the model training set includes a first sample image corresponding to a sample object and a second sample image corresponding to a sample space;

[0161] The training module 505 is used to perform model training on the target detection model based on the model training set obtained by the sample acquisition module 504, and to update the image database of the language model.

[0162] Optionally, in a possible implementation manner, the training module 505 may also be used to:

[0163] Inputting the first sample image and the second sample image acquired by the sample acquisition module 504 into the target detection model to obtain a sample recognition result;

[0164] Based on the sample recognition result, the sample item label of the first sample image and the sample space label of the second sample image, the target detection model is iteratively updated to adjust the model parameters, wherein the sample item label includes the item category of the sample item, and the sample space label includes the space category of the sample space.

[0165] Please refer to Figure 6 , which shows a structural block diagram of a system for assisting item storage provided by an exemplary embodiment of the present disclosure. The system for assisting item storage provided by this embodiment includes a data input unit, a feature extraction unit and a solution generation unit.

[0166] The data input unit is used to obtain a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space.

[0167] The feature extraction unit is used to perform target detection on the first image and the second image acquired by the data input unit respectively, to obtain item information of at least one item to be stored and spatial information of at least one storage space, wherein the item information may, for example, include but is not limited to the item category of the item to be stored, and the spatial information may, for example, include but is not limited to the spatial category of the storage space.

[0168] The solution generation unit is used to generate a storage effect image of at least one storage space based on the item information of at least one item to be stored and the space information of at least one storage space obtained by the feature extraction unit. The storage effect image is used to display the item storage solution of the corresponding storage space.

[0169] The first image is obtained by photographing the items to be stored (such as photos or video screenshots), and the second image is obtained by photographing the storage space. Users can upload one or more first images, each of which may contain image information of one or more items to be stored; users can upload one or more second images, each of which may contain image information of one or more storage spaces. Storage space refers to a spatial structure composed of objects that can accommodate items, such as architectural spaces such as living rooms, kitchens, bedrooms, and bathrooms, or furniture spaces such as wardrobes, cabinets, and computer desks.

[0170] In a possible implementation, the first image and the second image are respectively input into the target detection model for target detection, and the object information of the object to be stored and the spatial information of the storage space are extracted. Schematically, the target detection model can be implemented using a pre-trained deep learning model. In a specific example, a regional convolutional neural network (R-CNN) model can be used, such as a FasterR-CNN model.

[0171] For example, the object detection model extracts that the item category of the items to be stored in image a is "decorations", and the space category of the storage space in image c is "living room".

[0172] The storage effect image is used to display the item storage solution of the corresponding storage space. Specifically, the storage effect image displays the storage solution of classifying the items to be stored and placing them in each storage space through virtual items and virtual space. Alternatively, the storage effect image can be obtained by integrating the content in the first image and the second image uploaded by the user, so as to display the storage effect of the user's items stored in the user's room. Alternatively, a language model can be used to generate a storage effect video of at least one storage space based on the item information of at least one item to be stored and the space information of at least one storage space, and the storage solution can be displayed in the form of a video.

[0173] In a possible implementation, description information about the items to be stored and the storage space is generated based on the item information and the space information, and the description information indicates that the corresponding items to be stored are placed in the storage space. The description information is input into the large language model to obtain a storage effect image. The storage effect image includes the virtual space corresponding to each storage space and the virtual items corresponding to each item to be stored. The user can organize and store the items to be stored in each storage space by referring to the storage method of the virtual items in the storage effect image in the virtual space.

[0174] Optionally, in a possible implementation manner, the system for assisting item storage provided by the embodiment of the present disclosure may further include an information matching unit;

[0175] The information matching unit is used to match the items to be stored and the storage space based on the preset corresponding relationship between the item category and the space category, and obtain a mapping relationship between at least one item to be stored and at least one storage space.

[0176] Optionally, in a possible implementation, the system for auxiliary item storage provided by the embodiment of the present disclosure may further include a data output unit, and the data output unit is used to output a storage effect diagram corresponding to each storage space.

[0177] Optionally, in a possible implementation manner, the above-mentioned solution generation unit may also be used for:

[0178] The item information of at least one item to be stored extracted by the feature extraction unit, the spatial information of at least one storage space, and the mapping relationship generated by the information matching unit are input into the language model, and the storage effect image of at least one storage space is generated through the language model.

[0179] Optionally, in a possible implementation manner, the above-mentioned solution generation unit may also be used for:

[0180] Determine at least one storage relationship combination based on the mapping relationship generated by the information matching unit, where the storage relationship combination includes a target storage space and at least one target item to be stored in the target storage space;

[0181] The object information of the target object to be stored in each storage relationship combination and the spatial information of the target storage space are respectively input into the language model, and the language model generates a storage effect image corresponding to each storage relationship combination.

[0182] Optionally, in a possible implementation manner, the above-mentioned solution generation unit may also be used for:

[0183] Performing image preprocessing on the first image acquired by the data input unit, separating the image content of each object to be stored, and obtaining a stored object map;

[0184] Performing image preprocessing on the second image acquired by the data input unit, erasing image content of non-storage space in the second image, and obtaining a storage space map;

[0185] The storage item map, the storage space map, the item information of at least one item to be stored extracted by the feature extraction unit, the space information of at least one storage space, and the mapping relationship generated by the information matching unit are input into the language model, and the storage effect image of at least one storage space is generated through the language model.

[0186] Optionally, in a possible implementation manner, the feature extraction unit may also be used for:

[0187] Inputting the first image and the second image acquired by the data input unit into the target detection model to acquire an object detection frame in the first image and a space detection frame in the second image;

[0188] The target detection model is used to perform target detection on the image information in the object detection frame and the space detection frame to obtain the object information and space information.

[0189] Optionally, in a possible implementation manner, the feature extraction unit may also be used for:

[0190] Standardizing the first image and the second image acquired by the data input unit based on a standard scale, wherein the scale refers to the ratio between the distance on the image and the corresponding actual distance;

[0191] Get the detection frame size of the object detection frame and the space detection frame;

[0192] The above scheme generation unit can also be used for:

[0193] A language model is used to generate a storage effect image of at least one storage space based on the item information of at least one item to be stored extracted by a feature extraction unit, the spatial information of at least one storage space, the mapping relationship generated by the information matching unit, and the detection frame size obtained by the feature extraction unit.

[0194] Optionally, in a possible implementation manner, the system for assisting item storage provided in the embodiment of the present application may further include a model training unit for:

[0195] Obtain a model training set, which may include but is not limited to a first sample image corresponding to a sample object and a second sample image corresponding to a sample space;

[0196] The target detection model is trained based on the model training set, and the image database of the language model is updated.

[0197] Optionally, in a possible implementation manner, the above-mentioned model training unit may also be used for:

[0198] Inputting the first sample image and the second sample image into the target detection model to obtain a sample recognition result;

[0199] Based on the sample recognition result, the sample item label of the first sample image and the sample space label of the second sample image, the target detection model is iteratively updated to adjust the model parameters, wherein the sample item label includes the item category of the sample item, and the sample space label includes the space category of the sample space.

[0200] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The parts of the same, similar or corresponding contents between the various embodiments can be referred to each other. Since the system, method, device, and equipment embodiments basically correspond to each other, the relevant parts can be referred to the description of the corresponding parts. The systems, methods, devices, and equipment of the embodiments of the present disclosure also correspond to each other in terms of specific implementation and beneficial technical effects. The relevant contents can be referred to each other and will not be repeated.

[0201] In addition, an embodiment of the present disclosure further provides an electronic device, including:

[0202] Memory for storing computer programs;

[0203] The processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method for storing auxiliary items described in any of the above embodiments of the present disclosure is implemented.

[0204] Figure 7 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed in the present invention. Figure 7 The electronic device according to the embodiment of the present disclosure is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signals from them.

[0205] like Figure 7As shown, the electronic device includes one or more processors and memory.

[0206] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0207] The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the method of assisting item storage of each embodiment of the present disclosure described above and / or other desired functions.

[0208] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0209] In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

[0210] The output device can output various information to the outside, including the determined distance information, direction information, etc. The output device can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0211] Of course, to simplify, Figure 7 Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0212] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the method of auxiliary item storage according to various embodiments of the present disclosure described in the above part of this specification.

[0213] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0214] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method for storing auxiliary items according to various embodiments of the present disclosure described in the above part of this specification.

[0215] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0216] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0217] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0218] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0219] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0220] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0221] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0222] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0223] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for assisting article storage, characterized in that: include: Acquire a first image and a second image, wherein the first image includes an image of at least one item to be stored, and the second image includes an image of at least one storage space; Performing target detection on the first image and the second image respectively to obtain item information of the at least one item to be stored and spatial information of the at least one storage space, wherein the item information includes an item category of the item to be stored, and the spatial information includes a spatial category of the storage space; Based on the item information of the at least one item to be stored and the space information of the at least one storage space, a storage effect image of the at least one storage space is generated, and the storage effect image is used to display the item storage solution of the corresponding storage space.

2. The method according to claim 1, characterized in that: After performing target detection on the first image and the second image respectively to obtain the item information of the at least one item to be stored and the space information of the at least one storage space, the method includes: Based on the preset corresponding relationship between the item category and the space category, the items to be stored and the storage space are matched to obtain a mapping relationship between the at least one item to be stored and the at least one storage space.

3. The method according to claim 2, characterized in that The generating a storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space comprises: The item information of the at least one item to be stored, the space information of the at least one storage space, and the mapping relationship are input into a language model, and the storage effect image of the at least one storage space is generated through the language model.

4. The method according to claim 2, characterized in that: The generating a storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space comprises: Determine at least one storage relationship combination based on the mapping relationship, wherein the storage relationship combination includes a target storage space and at least one target item to be stored in the target storage space; The object information of the target object to be stored in each storage relationship combination and the space information of the target storage space are respectively input into the language model, and the storage effect image corresponding to each storage relationship combination is generated through the language model.

5. The method according to claim 2, characterized in that: The generating a storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space comprises: Performing image preprocessing on the first image to separate the image content of each of the items to be stored, and obtaining a storage item map; performing image preprocessing on the second image, erasing image content of non-storage space in the second image, and obtaining a storage space map; The storage item map, the storage space map, the item information of the at least one item to be stored, the space information of the at least one storage space and the mapping relationship are input into a language model, and the storage effect image of the at least one storage space is generated through the language model.

6. The method according to any one of claims 2 to 5, characterized in that: The performing target detection on the first image and the second image respectively to obtain the item information of the at least one item to be stored and the space information of the at least one storage space includes: Inputting the first image and the second image into a target detection model to obtain an object detection frame in the first image and a space detection frame in the second image; The target detection model is used to perform target detection on the image information in the object detection frame and the space detection frame to obtain the item information and the space information.

7. The method according to claim 6, characterized in that Before inputting the first image and the second image into the target detection model to obtain the object detection frame in the first image and the space detection frame in the second image, the method further includes: Standardizing the first image and the second image based on a standard scale, wherein the scale refers to a ratio between a distance on the image and a corresponding actual distance; After inputting the first image and the second image into the target detection model and obtaining the object detection frame in the first image and the space detection frame in the second image, the method further includes: Obtaining detection frame sizes of the object detection frame and the space detection frame; The step of generating the storage effect image of the at least one storage space based on the item information of the at least one item to be stored and the space information of the at least one storage space comprises: The storage effect image of the at least one storage space is generated based on the item information of the at least one item to be stored, the space information of the at least one storage space, the mapping relationship and the detection frame size.

8. The method according to claim 6, characterized in that Also includes: Obtain a model training set, wherein the model training set includes a first sample image corresponding to the sample object and a second sample image corresponding to the sample space; The target detection model is trained based on the model training set, and the image database of the language model is updated.

9. The method according to claim 8, characterized in that The performing model training on the target detection model based on the model training set includes: Inputting the first sample image and the second sample image into the target detection model to obtain a sample recognition result; Based on the sample recognition result, the sample item label of the first sample image and the sample space label of the second sample image, the target detection model is iteratively updated to adjust the model parameters, wherein the sample item label includes the item category of the sample item, and the sample space label includes the space category of the sample space.

10. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute a computer program stored in the memory, and when the computer program is executed, implement the method described in any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method described in any one of claims 1 to 9 is implemented.

12. A computer program comprising computer program instructions, characterized in that When the computer program instructions are executed by a processor, the method described in any one of claims 1 to 9 is implemented.

Images