Object searching method, electronic equipment and computer readable storage medium

Abstract

The invention discloses an object searching method, electronic equipment and a computer readable storage medium. The method comprises the steps that cloud equipment receives an object searching signaling from terminal equipment; wherein the object searching signaling is generated by the terminal equipment in response to an object searching operation of a user; and based on the object searching signaling, performing visual object searching in the to-be-searched area by using the large model. In this way, the object searching accuracy and efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent object-finding technology, and in particular to an object-finding method, an electronic device, and a computer-readable storage medium. Background Art

[0002] In people's daily life, there is always a need to find items. With the development of science and technology, in order to save the time spent by users in finding items, in the related art, a transmitting device is installed for the item. When the user needs to find the item, a signal is transmitted to the item through a handheld terminal. After receiving the transmission signal, the item responds through the transmitting device installed on the item. The response method includes emitting an audible and visual alarm signal, and the handheld terminal locates the item through the audible and visual alarm signal. The user finds the item based on the positioning result of the handheld terminal. However, in the process of finding items in the related art, not only the participation of the user is required, but also the object-finding mode is single, and the flexibility and accuracy are low. Summary of the invention

[0003] The main technical problem solved by the present application is to provide a method for finding objects, an electronic device and a computer-readable storage medium, which can improve the accuracy and efficiency of finding objects.

[0004] In order to solve the above technical problems, a technical solution adopted in the present application is: to provide a method for finding objects, the method comprising: a cloud device receives a finding object signaling from a terminal device; wherein the finding object signaling is generated by the terminal device in response to a user's finding object operation; based on the finding object signaling, a large model is used to perform visual finding in the area to be searched.

[0005] To solve the above technical problems, another technical solution adopted in the present application is: to provide a method for finding objects, the method comprising: the terminal device generates a finding object signaling in response to the user's finding object operation; and feeds back the finding object signaling to the cloud device, so that the cloud device performs visual finding in the area to be searched based on the finding object signaling using a large model.

[0006] In order to solve the above technical problems, another technical solution adopted by the present application is: to provide an electronic device, the electronic device includes a memory and a processor, the memory stores program instructions, and the program instructions can be executed to implement the above-mentioned method of finding objects.

[0007] In order to solve the above technical problem, another technical solution adopted by the present application is: providing a computer-readable storage medium, which is used to store program instructions, and the program instructions can be executed to implement the above-mentioned method of finding objects.

[0008] In the above technical solution, the large model has powerful data processing capabilities, so using the large model to perform visual search in the search area can improve the accuracy and efficiency of the search. In addition, by connecting to the cloud device, the local hardware device can have the ability to search with the help of the large model deployed on the cloud device, that is, the local hardware device can have the ability to search by connecting to the cloud device, which reduces the hardware performance requirements for the local hardware device and extends the service life of the local hardware device. Furthermore, the large model is deployed on the cloud device, and the cloud device has a large amount of computing resources, which can support the efficient operation of the large model and improve the response speed of the large model to the user's search needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a flowchart of an embodiment of the object-finding method provided by the present application;

[0010] Figure 2 yes Figure 1 The flowchart of step S12 is shown as an embodiment;

[0011] Figure 3 It is a flowchart of another embodiment of the object-finding method provided by the present application;

[0012] Figure 4 It is a structural schematic diagram of an embodiment of a searching device provided by the present application;

[0013] Figure 5 is a structural schematic diagram of another embodiment of the object-finding device provided by the present application;

[0014] Figure 6 It is a structural schematic diagram of an embodiment of an electronic device provided by the present application;

[0015] Figure 7 It is a structural schematic diagram of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0016] The scheme of the embodiment of the present application is described in detail below in conjunction with the accompanying drawings of the specification. In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are proposed so as to thoroughly understand the present application. The term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B, which may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" herein means two or more than two. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, which may represent any one or more elements selected from the set consisting of A, B, and C.

[0017] See also Figure 1 , Figure 1 It is a flow chart of an embodiment of the method for finding an object provided by the present application. It should be noted that if there are substantially the same results, the embodiments of the present application are not necessarily the same. Figure 1 The process sequence shown is limited. Figure 1 As shown, this embodiment includes:

[0018] Step S11: The cloud device receives the lost item signaling from the terminal device.

[0019] In this embodiment, the cloud device receives the object search instruction from the terminal device; wherein the object search signaling is generated by the terminal device in response to the object search operation of the user. Specifically, when the user needs to find an object, the user performs the object search operation, and the terminal device generates an object search instruction based on the user's object search operation and sends (or feeds back) to the cloud device. After receiving the object search instruction from the terminal device, the cloud device uses the large model to perform visual object search in the area to be searched.

[0020] In one embodiment, the terminal device may be a mobile phone, a computer, a tablet computer, etc. The user's search operation includes at least one of the following: the user inputs a voice including the information of the object to be found, the user inputs a text including the information of the object to be found, and the user inputs an image or video including the object to be found. The user can input the voice of the object to be found information into the terminal device to perform the search operation; the user can also type the text of the object to be found information on the terminal device to perform the search operation; the user can also upload the image or video of the object to be found on the terminal device to perform the search operation. In other words, the user's search operation is diverse in form and can be flexibly selected to improve the user experience.

[0021] The voice of the object to be found information and the text of the object to be found information mentioned above may include only the object to be found information, or may include both the object to be found information and the request to find the object. For example, taking the example of a user inputting text including the object to be found information: the user only inputs the text "shoes", then the user has only input the object to be found information; for another example, taking the example of a user inputting text including the object to be found information: the user inputs "I want to find my keys", then the user has simultaneously input the object to be found information and the request to find the object.

[0022] In addition, the images or videos of the objects to be found mentioned above may be images or videos of the objects to be found taken in the past, or may be taken in real time (generally, real-time shooting is suitable for pairs of objects, where one object is to be found and the other object that is not lost can be photographed and uploaded).

[0023] In other embodiments, the terminal device may be an IoT device, such as a camera, etc., and the user's object-finding operation includes at least one of the following: the user inputs a voice message including information about the object to be found, and the user performs a preset gesture. The user may input the information about the object to be found into the terminal device to perform the object-finding operation; the user may also perform the object-finding operation by performing a preset gesture. In other words, the user's object-finding operation is diverse and can be flexibly selected to improve the user experience.

[0024] In the case where the terminal device is an IoT device and the user's search operation is the user inputting voice information including the object to be found, the terminal device needs to have a sound receiving function; when the user speaks the voice content of the object to be found, the terminal device can collect the voice content spoken by the user and identify the collected voice content to determine whether the user is performing a search operation. In the case where the terminal device is an IoT device and the user's search operation is the user performing a preset gesture, the terminal device needs to have an image acquisition function; when the user performs a preset gesture, the terminal device can collect images or videos and identify the collected images or videos to determine whether the user is performing a search operation.

[0025] There is no limitation on the preset gesture for triggering the object search, and it can be set according to actual usage needs.

[0026] In other implementations, the connected client or third-party service may also be integrated through the API, SDK, etc. of the cloud device.

[0027] Step S12: Based on the object search signaling, use the large model to perform visual object search in the area to be searched.

[0028] In this embodiment, based on the object search instruction, the large model is used to perform visual object search in the area to be searched. After the cloud device receives the object search instruction from the terminal device, it will use the large model deployed thereon to perform visual object search in the area to be searched.

[0029] The large model has powerful data processing capabilities, so using the large model to perform visual search in the search area can improve the accuracy and efficiency of the search. In addition, by connecting to cloud devices, local hardware devices can have the ability to search with the help of the large model deployed on the cloud device, that is, the local hardware devices can have the ability to search by connecting to the cloud device, which reduces the hardware performance requirements for the local hardware devices and extends the service life of the local hardware devices. Furthermore, the large model is deployed on the cloud device, and the cloud device has a large amount of computing resources that can support the efficient operation of the large model and improve the response speed of the large model to the user's search needs.

[0030] It should be noted that the area to be searched can be an area specified by the user, or a part of or all areas in the current space. For example, taking the current space as a home (including a balcony, garden, living room, dining room, kitchen, and bedroom), the area to be searched is the balcony area and garden area specified by the user, or the area to be searched is all areas in the home.

[0031] In one embodiment, the large model is a large language model. The large language model has extensive common sense and advanced reasoning capabilities. When the large model is a large language model, it can interact with the user in a multimodal manner to improve the user experience.

[0032] Among them, the large language model includes but is not limited to GPT, LLAMA, Claude, kimi or Tongyi Qianwen, etc., which are not limited here.

[0033] See also Figure 2 , Figure 2 yes Figure 1 It should be noted that if there are substantially the same results, the embodiments of the present application are not limited to the above embodiments. Figure 2 The process sequence shown is limited. Figure 2 As shown, the object-searching signaling includes an object-searching request and information about the object to be found. This embodiment includes:

[0034] Step S21: In response to a request to find an object, an area image of a capture area of ​​an image capture device is acquired.

[0035] In this embodiment, in response to a request to find an object, a regional image of a collection area of ​​the image collection device is acquired, wherein the collection area of ​​the image collection device is a local area of ​​the area to be searched.

[0036] Specifically, the cloud device sends an image acquisition instruction to the image acquisition device. After receiving the image acquisition instruction, the image acquisition device will perform image acquisition on the acquisition area to obtain a regional image of the acquisition area of ​​the image acquisition device.

[0037] Step S22: Based on the information of the object to be found, the large model is used to identify the regional image to obtain the object finding result.

[0038] In this embodiment, based on the information of the object to be found, a large model is used to identify the regional image to obtain a search result; wherein the search result is used to indicate whether there is an object to be found in the acquisition area of ​​the image acquisition device.

[0039] There is no limitation on the algorithm or model for image recognition, and it can be set according to actual usage needs.

[0040] In one embodiment, the object search result indicates that there is no object to be found in the collection area of ​​the image acquisition device. After the area image is identified by a large model based on the information of the object to be found and the object search result is obtained, the collection area of ​​the image acquisition device is adjusted, and a new area image is obtained by using the adjusted image acquisition device. The area image is re-identified by using a large model based on the information of the object to be found to obtain the object search result. The collection area of ​​the image acquisition device is adjusted, and a new area image is obtained by using the adjusted image acquisition device and subsequent steps are repeated until the object search result indicates that there is an object to be found in the collection area of ​​the image acquisition device, or until the collection area of ​​the image acquisition device cannot be adjusted and a new area image is obtained.

[0041] That is to say, the cloud device will control the image acquisition device to capture and report multiple times, and the large model will perform multiple image recognitions until the object to be found is determined or the new area image cannot be obtained.

[0042] In one embodiment, the method of adjusting the acquisition area of ​​the image acquisition device includes at least one of the following: adjusting the focal length of the image acquisition device, adjusting the position of the image acquisition device, and adjusting the position of an obstruction in the current acquisition area of ​​the image acquisition device.

[0043] By adjusting the focal length of the image acquisition device, the image acquisition device is magnified, the acquisition area of ​​the image acquisition device is reduced (to a part of the original acquisition area), and the image is acquired in the reduced acquisition area. The acquired image has high clarity, accurate color reproduction, and rich details. It is used as a new regional image, which is conducive to the search of large models and can improve the accuracy and efficiency of the search. Specifically, when the search result indicates that the object to be found does not exist in the acquisition area of ​​the image acquisition device, the cloud device generates a zoom command and sends it to the image acquisition device, so that the image acquisition device adjusts its own focal length after receiving the zoom command.

[0044] The position of the image acquisition device is adjusted to adjust the acquisition area of ​​the image acquisition device, so that the image acquisition device can acquire regional images of different acquisition areas. After the regional images of different acquisition areas are reported to the cloud device, the large model can search for objects to be found in different acquisition areas, conduct a large-scale search for objects to be found, and improve the accuracy of finding objects.

[0045] In a specific embodiment, the method of adjusting the acquisition area of ​​the image acquisition device includes adjusting the position of the image acquisition device; in this case, adjusting the acquisition area of ​​the image acquisition device is specifically: in response to the existence of a pan-tilt connected to the image acquisition device, controlling the pan-tilt to rotate to adjust the position of the image acquisition device. In the case of the pan-tilt, controlling the pan-tilt to rotate to drive the image acquisition device to rotate, thereby changing the position of the image acquisition device.

[0046] Specifically, in the case where there is a gimbal connected to the image acquisition device, when the object search result indicates that there is no object to be found in the acquisition area of ​​the image acquisition device, the cloud device generates a gimbal rotation command and sends it to the gimbal connected to the image acquisition device, so that after receiving the gimbal rotation command, the gimbal rotates according to its own field of view angle and rotation range, thereby driving the image acquisition device to rotate.

[0047] In other specific embodiments, the method of adjusting the acquisition area of ​​the image acquisition device includes adjusting the position of the image acquisition device; in this case, adjusting the acquisition area of ​​the image acquisition device is specifically: in response to the absence of a gimbal connected to the image acquisition device, feeding back to the user second guidance information including an indicated position, so as to guide the user to move the image acquisition device to the indicated position.

[0048] Specifically, in the absence of a pan-tilt head connected to the image acquisition device, when the object search result indicates that the object to be found does not exist in the acquisition area of ​​the image acquisition device, the cloud device generates second guidance information including an indicated position and feeds it back to the terminal device, so that the user can obtain the second guidance information through the terminal device and then move the image acquisition device to the indicated position, thereby adjusting the position of the image acquisition device.

[0049] The indication position is not limited, for example, it can be under the table in the middle of the living room, at the door, etc.

[0050] If there is an obstruction in the acquisition area of ​​the image acquisition device, part of the acquisition area will be blocked, resulting in the inability to obtain the regional image of the complete acquisition area. If the obstruction causes the obstructed area to not be searched, the accuracy of the search result may be affected. Therefore, by adjusting the position of the obstruction in the current acquisition area of ​​the image acquisition device, the regional image of the complete acquisition area can be collected, and the subsequent large model can search for objects in all parts of the acquisition area, thereby improving the accuracy of the search.

[0051] In a specific embodiment, the method of adjusting the acquisition area of ​​the image acquisition device includes adjusting the position of the obstruction in the current acquisition area of ​​the image acquisition device; at this time, adjusting the acquisition area of ​​the image acquisition device specifically includes: determining at least one obstruction existing in the current acquisition area; and feeding back to the user first guidance information including at least one obstruction information to be moved, so as to guide the user to change the position of each obstruction to be moved. The cloud device generates the first guidance information including the obstruction information to be moved and feeds it back to the terminal device, so that the user can obtain the obstruction that needs to be moved through the terminal device, and the user moves the obstruction to be moved, so as to obtain the regional image of the complete acquisition area, thereby improving the accuracy of finding objects.

[0052] For example, take the example of a trash can as the obstructing object to be moved: when the user obtains through the terminal device that the obstructing object to be moved is a trash can, the user will move the trash can away, thereby simultaneously obtaining the regional image of the area obstructed by the trash can and the regional image of the area not obstructed by the trash can. Subsequently, the object can be searched based on the regional image of the complete acquisition area, thereby improving the accuracy of the object search.

[0053] In a specific embodiment, determining at least one occluder in the current acquisition area specifically includes: obtaining the object category of each reference object in the current acquisition area; for each reference object in the current acquisition area, in response to the object category of the reference object being the same as any object category in a preset library, determining that the reference object is an occluder, wherein the preset library includes various object categories of occluders. In other words, a preset library is predefined, and the preset library includes categories of occluders. If the category of the reference object is consistent with any object category in the preset library, the reference object is defined as an occluder.

[0054] In one embodiment, when the object search result indicates that there is an object search result in the acquisition area of ​​the image acquisition device, it means that the object search has been found in the search area. At this time, the location of the object search will be fed back to the user, and the user will be informed of the object search result in a timely manner. In addition, the user will be confirmed whether the object search has been found, that is, the user will be confirmed again whether it has been completely found.

[0055] In one embodiment, before performing visual object search in the search area based on the object search signaling using a large model, the object search signaling is also parsed; in response to the object search data obtained by the analysis, the object search data is analyzed to obtain the object search request and the information of the object to be found.

[0056] When the request signaling is structured data, the request signaling will strictly follow the format requirements and accurately describe the search request and the information of the object to be found. When the request signaling is unstructured data, the request signaling may only contain different types of request data such as text, images, videos, audio, etc. The request signaling will be parsed first to infer the user's search request so as to accurately find the object for the user's search need.

[0057] See also Figure 3 , Figure 3 It is a flow chart of another embodiment of the method for finding an object provided by the present application. It should be noted that if there are substantially the same results, the embodiments of the present application are not necessarily the same. Figure 3 The process sequence shown is limited. Figure 3 As shown, this embodiment includes:

[0058] Step S31: The terminal device generates a found-item signaling in response to the user's found-item operation.

[0059] Step S31 is similar to step S11. Please refer to the content of step S11 and will not be described again here.

[0060] Step S32: Feedback the object-finding signaling to the cloud device, so that the cloud device can perform visual object-finding in the area to be searched using the large model based on the object-finding signaling.

[0061] Step S32 is similar to step S12. Please refer to the content of step S12, which will not be repeated here.

[0062] See also Figure 4 , Figure 4 4 is a schematic diagram of a structure of an embodiment of a search device provided by the present application. The search device 40 includes a receiving module 41 and a search module 42. The receiving module 41 is used to receive a search signal from a terminal device; wherein the search signal is generated by the terminal device in response to a user's search operation; the search module 42 is used to perform visual search in the search area using a large model based on the search signal.

[0063] Among them, the above-mentioned object search signaling includes an object search request and information about the object to be found; the object search module 42 is used to perform visual object search in the area to be searched based on the object search signaling using a large model, including: in response to the object search request, obtaining a regional image of the acquisition area of ​​the image acquisition device; wherein the acquisition area of ​​the image acquisition device is a local area of ​​the area to be searched; based on the information of the object to be found, using the large model to identify the regional image to obtain a object search result; wherein the object search result is used to characterize whether there is an object to be found in the acquisition area of ​​the image acquisition device.

[0064] Among them, the above-mentioned object search result indicates that there is no object to be found in the collection area of ​​the image acquisition device; the object search module 42 is used to identify the regional image based on the information of the object to be found using a large model, and after obtaining the object search result, adjust the collection area of ​​the image acquisition device, obtain a new regional image using the adjusted image acquisition device, and re-execute the information of the object to be found, use the large model to identify the regional image to obtain the object search result, and repeatedly adjust the collection area of ​​the image acquisition device, obtain a new regional image using the adjusted image acquisition device and subsequent steps, until the obtained object search result indicates that there is an object to be found in the collection area of ​​the image acquisition device, or until the collection area of ​​the image acquisition device cannot be adjusted and a new regional image is obtained.

[0065] The method of adjusting the acquisition area of ​​the image acquisition device includes at least one of the following: adjusting the focal length of the image acquisition device, adjusting the position of the image acquisition device, and adjusting the position of an obstruction in the current acquisition area of ​​the image acquisition device.

[0066] Among them, the object-finding module 42 is used to adjust the acquisition area of ​​the image acquisition device in a manner including adjusting the position of the obstruction in the current acquisition area of ​​the image acquisition device; adjusting the acquisition area of ​​the image acquisition device includes: determining at least one obstruction existing in the current acquisition area; and feeding back to the user first guidance information including information of at least one obstruction to be moved, so as to guide the user to change the position of each obstruction to be moved.

[0067] Among them, the object-finding module 42 is used to determine at least one obstruction existing in the current collection area, including: obtaining the object category of each reference object existing in the current collection area; for each reference object existing in the current collection area, in response to the object category of the reference object being the same as any object category in a preset library, determining that the reference object is an obstruction; wherein the preset library includes various object categories that are obstructions.

[0068] Among them, the object-hunting module 42 is used to adjust the acquisition area of ​​the image acquisition device in a manner that includes adjusting the position of the image acquisition device; adjusting the acquisition area of ​​the image acquisition device includes: in response to the existence of a gimbal connected to the image acquisition device, controlling the rotation of the gimbal to adjust the position of the image acquisition device; or, in response to the absence of a gimbal connected to the image acquisition device, providing the user with feedback including second guidance information indicating the position, so as to guide the user to move the image acquisition device to the indicated position.

[0069] The object-finding module 42 is further configured to provide feedback to the user on the location of the object to be found in response to obtaining an object-finding result indicating that the object to be found exists in the acquisition area of ​​the image acquisition device; and to confirm with the user whether the object to be found is found.

[0070] Before performing visual object search in the search area using a large model based on the object search signaling, the object search module 42 is also used to: parse the object search signaling; in response to only obtaining object search data through the analysis, analyze the object search data to obtain the object search request and information about the object to be found.

[0071] Among them, the above-mentioned large model is a large language model, and the data type of the search data includes at least two of the following: text, image, video, and audio.

[0072] See also Figure 5 , Figure 5 1 is a schematic diagram of the structure of another embodiment of the object-finding device provided by the present application. The object-finding device 50 includes a generation module 51 and a feedback module 52. The generation module 51 is used to generate an object-finding signal in response to the user's object-finding operation; the feedback module 52 is used to feedback the object-finding signal to the cloud device, so that the cloud device can perform visual object-finding in the search area based on the object-finding signal using a large model.

[0073] Among them, the above-mentioned terminal device includes a client, and the above-mentioned user's search operation includes at least one of the following: the user inputs voice data including information of the object to be found, the user inputs text data including information of the object to be found, and the user inputs image data or video data including information of the object to be found; or, the terminal device includes an image acquisition device, and the user's search operation includes at least one of the following: the user inputs voice data including information of the object to be found, and the user performs a preset gesture.

[0074] Among them, the above-mentioned terminal device includes an image acquisition device, and the user's search operation includes the user performing a preset gesture; the generation module 51 is used to generate a search instruction in response to the user's search operation, including: in response to detecting that the user performs a preset gesture, generating inquiry information and feeding back the inquiry information to the user, wherein the inquiry information is used to inquire the user about the information of the object to be found; in response to receiving the user's inquiry feedback information, generating a search signal based on the inquiry feedback information.

[0075] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of an embodiment of an electronic device provided by the present application. The electronic device 60 includes a memory 61 and a processor 62 coupled to each other, and the processor 62 is used to execute program instructions stored in the memory 61 to implement the steps of any of the above-mentioned methods for finding objects. In a specific implementation scenario, the electronic device 60 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 60 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.

[0076] Specifically, the processor 62 is used to control itself and the memory 61 to implement the steps of any of the above-mentioned methods for finding objects. The processor 62 can also be called a CPU (Central Processing Unit). The processor 62 may be an integrated circuit chip with signal processing capabilities. The processor 62 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 62 can be implemented by an integrated circuit chip.

[0077] See also Figure 7 , Figure 7 It is a structural diagram of an embodiment of a computer-readable storage medium provided by the present application. The computer-readable storage medium 70 of the embodiment of the present application stores a program instruction 71, and when the program instruction 71 is executed, it implements the method provided by an embodiment of the object-finding method of the present application and any non-conflicting combination. Among them, the program instruction 71 can form a program file and be stored in the above-mentioned computer-readable storage medium 70 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) executes all or part of the steps of each implementation method of the present application. The aforementioned computer-readable storage medium 70 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, and a tablet.

[0078] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0079] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for finding an object, characterized in that: The method comprises: The cloud device receives a found-item signaling from a terminal device; wherein the found-item signaling is generated by the terminal device in response to a user's found-item operation; Based on the object-seeking signaling, a large model is used to perform visual object-seeking in the area to be searched.

2. The method according to claim 1, characterized in that The object search signaling includes an object search request and information about the object to be searched; and the method of performing visual object search in the area to be searched using a large model based on the object search signaling includes: In response to the object-finding request, acquiring a regional image of a collection area of ​​an image collection device; wherein the collection area of ​​the image collection device is a local area of ​​the area to be searched; Based on the information of the object to be found, the regional image is identified using the large model to obtain a finding result; wherein the finding result is used to indicate whether there is an object to be found in the acquisition area of ​​the image acquisition device.

3. The method according to claim 2, characterized in that The object search result indicates that the object to be found does not exist in the acquisition area of ​​the image acquisition device; After the large model is used to identify the regional image based on the information of the object to be found and a result of finding the object is obtained, the method further includes: Adjust the acquisition area of ​​the image acquisition device, use the adjusted image acquisition device to obtain a new image of the area, and re-execute the identification of the area image based on the information of the object to be found using the large model to obtain a search result, repeat the steps of adjusting the acquisition area of ​​the image acquisition device, using the adjusted image acquisition device to obtain a new image of the area and subsequent steps, until the search result obtained indicates that the object to be found exists in the acquisition area of ​​the image acquisition device, or until the acquisition area of ​​the image acquisition device cannot be adjusted and a new image of the area is obtained.

4. The method according to claim 3, characterized in that The manner of adjusting the acquisition area of ​​the image acquisition device includes at least one of the following: adjusting the focal length of the image acquisition device, adjusting the position of the image acquisition device, and adjusting the position of an obstruction in the current acquisition area of ​​the image acquisition device.

5. The method according to claim 4, characterized in that The method of adjusting the acquisition area of ​​the image acquisition device includes adjusting the position of the blocking object in the current acquisition area of ​​the image acquisition device; the adjusting the acquisition area of ​​the image acquisition device includes: Determine at least one obstruction existing in the current acquisition area; First guidance information including at least one piece of information of an obstruction to be moved is fed back to the user to guide the user to change the position of each of the obstructions to be moved.

6. The method according to claim 5, characterized in that The determining at least one obstruction existing in the current acquisition area includes: Acquire the object category of each reference object existing in the current acquisition area; For each reference object existing in the current acquisition area, in response to the object category of the reference object being the same as any object category in a preset library, the reference object is determined to be the occluder; wherein the preset library includes each object category of the occluder.

7. The method according to claim 4, characterized in that The method of adjusting the acquisition area of ​​the image acquisition device includes adjusting the position of the image acquisition device; the adjusting the acquisition area of ​​the image acquisition device includes: In response to the existence of a pan-tilt platform connected to the image acquisition device, controlling the pan-tilt platform to rotate so as to adjust the position of the image acquisition device; Alternatively, in response to the absence of a pan / tilt platform connected to the image acquisition device, second guidance information including an indicated position is fed back to the user to guide the user to move the image acquisition device to the indicated position.

8. The method according to claim 3, characterized in that The method further comprises: In response to obtaining a search result indicating that the object to be found exists in the acquisition area of ​​the image acquisition device, feeding back the position of the object to be found to a user; Confirm with the user whether the object to be found is found.

9. The method according to claim 2, characterized in that: Before performing visual object search in the to-be-searched area using the large model based on the object search signaling, the method further includes: Parsing the found-object signaling; In response to only obtaining the found object data through parsing, the found object data is analyzed to obtain the found object request and the information of the object to be found.

10. The method according to claim 9, characterized in that The large model is a large language model, and the data type of the object-finding data includes at least two of the following: text, image, video, and audio.

11. A method for finding an object, characterized in that: The method comprises: The terminal device generates a found object signaling in response to the user's found object operation; The object-finding signaling is fed back to the cloud device, so that the cloud device can perform visual object-finding in the area to be searched using a large model based on the object-finding signaling.

12. The method according to claim 11, characterized in that The terminal device includes an image acquisition device, the user's object-finding operation includes the user performing a preset gesture; and the generating of the object-finding instruction in response to the user's object-finding operation includes: In response to detecting that the user performs the preset gesture, generating query information and feeding back the query information to the user, wherein the query information is used to inquire the user about the object to be found; In response to receiving the query feedback information from the user, the found-object signaling is generated based on the query feedback information.

13. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores program instructions, and the program instructions can be executed to implement the object-finding method as described in any one of claims 1-12.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program instructions, and the program instructions can be executed to implement the object-finding method as described in any one of claims 1-12.

Images