Request processing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a request processing method and device, equipment, a storage medium and a program product. The method comprises the steps of obtaining a target image associated with a target vehicle in response to a vehicle returning request for the target vehicle; detecting whether the target image comprises a group of preset objects, wherein the group of preset objects are suitable for being arranged in the physical area to represent that the physical area is a vehicle returning area; in response to the condition that the target image comprises at least one preset object, determining a fusion region by fusing a group of regions of the at least one object in the target image; generating a semantic graph corresponding to the target image, wherein the semantic graph at least indicates a first region and a fusion region of the target vehicle in the target image; determining whether the parking of the target vehicle meets a parking constraint based on the semantic graph; and providing a response to the vehicle return request based on a result of determining whether the target vehicle conforms to the parking constraint. According to the embodiment of the invention, the accuracy of identifying whether the vehicle returning process accords with the specification can be improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a method, apparatus, device, storage medium, and computer-generated product for request processing. Background Art

[0002] Shared vehicles have become an important mode of transportation. For example, in the case of two-wheeled vehicles such as shared bicycles, users can use their own portable devices (such as mobile phones) to conveniently control the vehicle and complete various operations such as unlocking, locking, paying, and account management. When users have finished using the shared bicycle, they need to return it. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for request processing is provided. The method includes: in response to a return request for a target vehicle, obtaining a target image associated with the target vehicle; detecting whether the target image includes a set of preset objects, wherein the set of preset objects is suitable for being set inside a physical area to characterize the physical area as a return area; in response to the target image including at least one preset object, determining a fused area by fusing a set of areas of at least one object in the target image; generating a semantic graph corresponding to the target image, the semantic graph at least indicating: a first area of ​​the target vehicle in the target image and a fused area; determining whether the parking of the target vehicle satisfies parking constraints based on the semantic graph; and providing a response to the return request based on the determination result of whether the target vehicle meets the parking constraints.

[0004] In a second aspect of the present disclosure, a device for request processing is provided. The device includes: an acquisition module, configured to acquire a target image associated with a target vehicle in response to a return request for a target vehicle; a detection module, configured to detect whether the target image includes a set of preset objects, wherein the set of preset objects is suitable for being set inside a physical area to characterize the physical area as a return area; a determination module, configured to determine a fusion area by fusing a set of areas of at least one object in the target image in response to the target image including at least one preset object; a generation module, configured to generate a semantic graph corresponding to the target image, the semantic graph at least indicating: a first area of ​​the target vehicle in the target image and a fusion area; a judgment module, configured to determine whether the parking of the target vehicle satisfies the parking constraints based on the semantic graph; and a response module, configured to provide a response to the return request based on the determination result of whether the target vehicle meets the parking constraints.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes: at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer executable instructions, wherein the computer executable instructions implement the method of the first aspect when executed by a processor.

[0008] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 shows an interaction diagram for request processing according to some embodiments;

[0012] Figure 3A and Figure 3B An example block diagram of generating a minimized semantic graph is shown;

[0013] Figure 4 A flowchart illustrating an example process for processing a vehicle return request according to some embodiments of the present disclosure;

[0014] Figure 5 A flowchart illustrating an example process of request processing according to some embodiments of the present disclosure;

[0015] Figure 6 A schematic structural block diagram showing an example apparatus for request processing according to some embodiments of the present disclosure; and

[0016] Figure 7 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0019] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0020] As used herein, a "unit", "operating unit" or "subunit" may consist of a machine learning model or network of any suitable structure. As used herein, a group of elements or similar expressions may include one or more such elements. For example, a "group of convolutional units" may include one or more convolutional units.

[0021] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0022] As briefly discussed above, shared vehicles have become an important mode of transportation. The shared vehicle service platform needs to assist users in returning the vehicle at designated locations, returning the vehicle in a parking space, and returning the vehicle in an orderly manner.

[0023] In some solutions, the user can take a photo of the vehicle through the user device and upload the photo. The shared vehicle platform identifies the location information of the customized parking line in the photo, and then determines the relative position and posture information between the shared vehicle and the customized parking line. If it meets the expected specifications, it is considered that the vehicle is parked in compliance with the requirements.

[0024] However, in the above scheme, since the judgment rule only depends on the customized parking line and the position of the shared vehicle, in this case, it is only effective for the return area consisting of two or more customized parking lines. In actual situations, when the photo provided by the user only includes one customized parking line, it is impossible to judge whether the parking of the target vehicle complies with the regulations.

[0025] The embodiment of the present disclosure proposes a request processing scheme. According to the scheme: in response to a return request for a target vehicle, a target image associated with the target vehicle is obtained; it is detected whether the target image includes a set of preset objects, wherein the set of preset objects is suitable for being set inside a physical area to characterize the physical area as a return area; in response to the target image including at least one preset object, a fusion area is determined by fusing a set of areas of at least one object in the target image; a semantic graph corresponding to the target image is generated, the semantic graph at least indicating: a first area of ​​the target vehicle in the target image and a fusion area; based on the semantic graph, it is determined whether the parking of the target vehicle meets the parking constraints; and based on the determination result of whether the target vehicle meets the parking constraints, a response to the return request is provided.

[0026] In this way, the embodiments of the present disclosure can detect the target image corresponding to the vehicle return request, determine from the target image at least one preset object used to characterize the physical area as the vehicle return area, and fuse the area corresponding to the at least one preset object in the target image to obtain a fused area. Further, the embodiments of the present disclosure can generate a semantic graph of the target image to indicate the fused area and the area where the target vehicle is located. Further, the embodiments of the present disclosure can determine whether the parking of the target vehicle meets the parking constraints based on the semantic graph, thereby making a corresponding response to the vehicle return request.

[0027] Therefore, the embodiments of the present disclosure can accurately identify preset objects in the target image that can characterize the physical area as a vehicle return area, and thus can use the semantic graph corresponding to the target image to accurately determine whether the target vehicle meets the parking regulations, thereby improving the accuracy of identifying whether the vehicle is parked in compliance with the regulations and the efficiency of processing vehicle return requests.

[0028] Various example implementations of the solution are described in detail below in conjunction with the accompanying drawings.

[0029] Example Environment

[0030] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. The environment 100 includes a target vehicle 130, a control terminal 110, a user 140, and a user device 120 used by the user 140.

[0031] In some embodiments, an application may be installed and run on the user device 120, and an interface may be presented for operation by the user 140. The user device 120 may be a terminal device on which a shared vehicle application is installed and run, including but not limited to a personal computer, a smart phone, a smart watch, a smart glasses, a smart helmet, a laptop, a tablet computer, a personal digital assistant, or any other appropriate portable electronic device.

[0032] In some embodiments, the target vehicle 130 is a shared vehicle, for example, a shared two-wheeled vehicle, a shared electric motorcycle, a shared car, or any other shared transportation vehicle that complies with laws and regulations. Further, the target vehicle 130 may include a central control unit, which may be configured to manage and control the functions of the target vehicle 130. In some embodiments, the central control unit may communicate with the control terminal 110 and the user device 120 respectively by wireless means as required.

[0033] In some implementations, the control terminal 110 may be a remote server. In this case, the control terminal 110 may be configured as a remote server that centrally manages and controls various shared vehicles including the target vehicle 130. For example, the control terminal 110 may at least manage and control the target vehicle 130 by communicating with a central control unit on the target vehicle 130.

[0034] In some embodiments, the control terminal 110 can be implemented with an independent server or a server cluster composed of multiple servers. In other words, the control terminal 110 can be one or a group of servers that provide service functions, or one or a group of virtual machines that can provide services. The present disclosure is not limited in the implementation form of the control terminal 110.

[0035] In some embodiments, at least part of the functions of the control terminal 110 may be implemented by the user equipment 120 .

[0036] like Figure 1As shown, the control end 110 may include a service platform 112 and an algorithm platform 114. In some embodiments, the service platform 112 may manage the service process between the target vehicle 130 and the user device 120, and manage and maintain the data generated during the shared bicycle service. The algorithm platform 114 can be used to implement operations with high computational complexity such as image processing and logical reasoning. In operation, the service platform 112 can call the interface of the algorithm platform 114 and send the data to be processed to the algorithm platform 114. Furthermore, the service platform 112 can receive the processing results returned by the algorithm platform 114 from the algorithm platform 114 to better implement the shared vehicle service.

[0037] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.

[0038] Example Process

[0039] Figure 2 A schematic diagram of a signaling flow 200 for processing a vehicle return request between the user equipment 140 and the control end 110 according to some embodiments of the present disclosure is shown. The signaling flow 200 may be implemented between the user equipment 120 and the control end 110.

[0040] It should be understood that in some embodiments, the control terminal 110 may be a remote server. After the user equipment 120 establishes communication with the remote server, information is transmitted through the signaling flow 200 .

[0041] In some embodiments, the control terminal 110 may be partially located in the user device 120 and partially located in the remote server. After the user device 120 establishes communication with the target vehicle 130 and the remote server, information is transmitted through the signaling flow 200 .

[0042] The signaling flow 200 is further described below through an embodiment. Figure 1 environment 100 for discussion.

[0043] like Figure 2 As shown, when the user 140 finishes using the vehicle, a return request is sent (205) through the user device 120. For example, when the user 140 triggers a control for requesting to return the vehicle or end the trip in the user interface presented by the shared vehicle application of the user device 120. Based on the triggering operation, the user device 120 sends a return request for the target vehicle 130 to the control end 110.

[0044] Additionally, in some embodiments, the user may be guided to perform a photo-taking parking process. As an example, one or more of the following information may be presented in the user interface of the user device 120: prompt information prompting the user 140 to take a photo, an upload control for uploading a target image, and the like.

[0045] Next, the user device 120 may determine whether the authorization information / authorization for using the acquisition device of the user device 120 has been obtained. If the authorization information / authorization for using the acquisition device of the user device 120 has been obtained, the user is assisted in acquiring the target image including the target vehicle according to the target image acquisition interface presented. In response to the target image acquisition being completed, the acquired target image is uploaded to the control terminal 110.

[0046] Additionally, in order to assist the user 140 in taking better photos, auxiliary shooting information may be presented in the image acquisition interface. The auxiliary shooting information may be object recognition information. For example, during the framing process, parking markers such as vehicle identification, parking lines, parking guide signs, parking indication objects, etc. are marked by dotted / solid line boxes. In another example, the auxiliary shooting information may be shooting prompt information. For example, the user 140 is prompted with requirements that need to be met in order to capture the target image, including but not limited to the target image needing to capture the vehicle identification of the target vehicle. In yet another example, the auxiliary shooting information may be optimized shooting information, such as prompting the user to turn on the flash, etc. In response to the completion of the shooting, the target image is sent to the control terminal 110.

[0047] In some embodiments, the user device 120 receives an image acquisition instruction from the control end 110 , wherein the image acquisition instruction is generated based on determining that the target vehicle 130 is located in the parking area, and based on the image acquisition instruction, the acquisition of a target image related to the target vehicle 130 is prompted.

[0048] In some cases, the image captured by the user device 120 cannot meet the requirements of image recognition. According to some embodiments of the present disclosure, the control terminal 110 can prompt the user 140 to guide the user to capture a target image that meets the recognition requirements.

[0049] In some embodiments, the user device 120 collects a first image related to the target vehicle and sends the first image to the control terminal. Next, the user device 120 receives a prompt message from the control terminal 110 to instruct the client device to re-collect the image. In response to receiving the prompt message, the user device 120 re-collects a second image related to the target vehicle and sends the second image to the control terminal 110. The above process is executed repeatedly until the target image that meets the requirements is collected.

[0050] In some embodiments, the prompt information includes an image acquisition guide, which is determined based on the reason why the first image does not meet the image acquisition requirement, such as the target image is not clear enough, the target image does not include the vehicle identification information of the target vehicle, the target image does not capture the parking line information, etc.

[0051] Specifically, in some embodiments, the target image is collected by a client device that initiates a vehicle return request, and a first image related to the target vehicle 130 may be acquired as the target image.

[0052] In some embodiments, the control end 110 determines whether the first image meets the image acquisition requirements based on at least one of the following: whether a vehicle is recognized from the first image, whether at least one preset object is recognized from the first image, whether a vehicle logo is recognized from the first image, and whether the quality of the first image meets the quality requirements. If the control end 110 determines that the first image does not meet the image acquisition requirements, a prompt message is sent to the client device to instruct the client device to re-capture the image. Accordingly, if the control end 110 determines that the first image meets the image acquisition requirements, the first image is determined as the target image.

[0053] In some embodiments, the prompt information of the control terminal 110 includes an image acquisition guide, and the image acquisition guide is determined based on the reason why the first image does not meet the image acquisition requirement.

[0054] Accordingly, if it is determined that the target vehicle 130 is not in the parking area, the control end 110 can send parking area guidance information to the user device 120 to guide the user 140 to move the target vehicle to a nearby parking spot. As an example, the parking area guidance information can indicate one or more of the following information: the target vehicle 130 is not in the parking area, nearby parking area information, and information and distance from the latest parking area.

[0055] For the control end 110 , in response to the vehicle return request for the target vehicle 130 , the control end 110 acquires ( 215 ) a target image related to the target vehicle 130 .

[0056] In order to better understand the above process, we will combine Figure 3A and Figure 3B The process of generating the minimized semantic graph is further described. It should be understood that Figure 3A and Figure 3B The example operations discussed should not be construed as limitations on the present disclosure. Figure 3A is the target image 305. Figure 3B The generated semantic graph 335.

[0057] In some embodiments, the control terminal 110 may detect whether a set of preset objects is included in the target image 305. The set of preset objects is suitable for being set inside the physical area to characterize the physical area as a vehicle return area. As an example, the physical area may be understood as the ground (or ground surface), a table top, or other object surfaces.

[0058] In some embodiments, Figure 3A As shown, a group of preset objects may include a parking guide mark drawn inside the physical area. As an example, the parking guide mark may be, for example, a parking pattern mark 330-1. The parking pattern mark 330-1 is only an exemplary description, and the parking guide mark drawn inside the physical area may also be implemented as an arrow mark, etc. The present disclosure is not intended to limit the specific pattern content of the parking guide mark.

[0059] In some embodiments, continue to refer to Figure 3A , a group of preset objects may include parking indication objects configured inside the physical area. As an example, the parking indication object may be, for example, indicator 331-1. As an example, indicator 331-1 may be, for example, a Bluetooth road stud. As an example, a Bluetooth road stud may be a device installed on the ground that can transmit signals and communicate with a powered device configured on the vehicle to determine the parking information of the vehicle (such as location information, parking direction, etc.). Indicator 331-1 here is also only an exemplary description. The parking indication object configured inside the physical area may also be implemented as a near field communication (NFC) device, for example. The present disclosure is not intended to limit the specific device or equipment corresponding to the parking indication object.

[0060] In some embodiments, continue to refer to Figure 3A In response to the target image 305 including at least one preset object, the control end 110 may determine the fusion area through a group of areas of the at least one object in the target image 305 .

[0061] In some embodiments, continue to refer to Figure 3A , the control terminal 110 may determine an area 330-2 of the parking pattern mark 330-1 in the target image 305. The control terminal 110 may determine an area 331-2 of the indicator 331-1 in the target image 305. Further, the control terminal 110 may determine a fusion area including the area 330-2 and the area 331-2.

[0062] In some embodiments, when the control end 110 detects that there is only one preset object in the target image, the fusion area determined by the control end 110 is the area corresponding to the preset object in the target image.

[0063] In some embodiments, continue to refer to Figure 3A , the control end 110 may determine at least one parking line mark in the target image 305. As an example, the control end 110 may determine an area 325 corresponding to at least one parking line mark in the target image 305. As an example, the control end 110 may jointly determine a vehicle return area 327 based on the fused area and the area 325 corresponding to at least one parking line.

[0064] In some embodiments, the control end 110 may also determine multiple types of objects in the target image that are suitable for constituting the physical boundary of the return area. As an example, the multiple types of objects that are suitable for constituting the physical boundary of the return area may include physical entities different from parking signs (e.g., parking line markings) drawn on the ground. As an example, the multiple types of objects that are suitable for constituting the physical boundary of the return area may jointly determine the return area with at least one preset object and / or parking line markings.

[0065] In some embodiments, the multiple types of objects may include: static obstacles. As an example, the static obstacles may include walls, grass / vegetation, fences, etc. As an example, the wall and at least one parking line mark may jointly determine the vehicle return area.

[0066] In some embodiments, the multiple types of objects may include: a road surface for non-parking purposes. As an example, the road surface for non-parking purposes may include, for example, a road edge, a blind path, etc. As an example, a road edge and at least one parking line mark may jointly determine a vehicle return area.

[0067] In some embodiments, Figure 3A As shown, the control terminal 110 can determine a reference area 310 corresponding to the fence in the target image 305 .

[0068] In some embodiments, the control end 110 may fuse multiple reference regions corresponding to multiple types of objects in the target image 305 to obtain reference fused regions corresponding to the multiple types of objects.

[0069] In some embodiments, continue to refer to Figure 3A , the control end 110 can determine the target vehicle 130 in the target image 305. As an example, the target image may include multiple vehicles (e.g., vehicle A and vehicle B), and the control end 110 can determine the area 315 corresponding to vehicle A and the area 320 corresponding to vehicle B in the target image 305. As an example, the control end 110 can determine the target vehicle 130 from multiple vehicles (e.g., vehicle A and vehicle B) based on vehicle information (e.g., vehicle identification) associated with the user device 120. As an example, the control end 110 can determine the target vehicle 130 from multiple vehicles (e.g., vehicle A and vehicle B) based on a preset position (e.g., the center position of the target image).

[0070] In some embodiments, continue to refer to Figure 3A , the control end 110 may first determine the vehicle identification of the target vehicle 130. In the exemplary operation, the control end 110 detects at least one candidate vehicle identification and the position of at least one candidate vehicle identification in the target image from the target image 305, and determines a target vehicle identification that matches the vehicle identification of the to-be-returned vehicle from the at least one candidate vehicle identification by comparing the at least one candidate vehicle identification with the vehicle identification list of the to-be-returned vehicle, as the vehicle identification of the target vehicle 130. Figure 3A The example target image 305 is shown including two candidate vehicle logos, namely, logo A 326 - 1 and logo B 326 - 2 .

[0071] The control end 110 may further obtain a vehicle identification list of the to-be-returned vehicles, for example, a vehicle identification list of all to-be-returned shared vehicles managed and maintained in the service platform 112. By comparison, the control end 110 determines that the identification A 326-1 is in the vehicle identification list of the to-be-returned shared vehicles, thereby using the identification A 326-1 as the vehicle identification of the target vehicle 130, and recording the position of the identification A 326-1 in the target image 130.

[0072] In some embodiments, the above process can be implemented by the vehicle identification matching function in the algorithm platform 114. Specifically, the algorithm platform 114 matches the vehicle identification list of all vehicles to be returned in the system with one or more vehicle identifications identified in the target image uploaded by the user to ensure that the vehicle to be returned appears in the photo. In some embodiments, the algorithm platform 114 takes the vehicle identifications of all vehicles to be returned in the system and the one or more vehicle identifications identified in the target image uploaded by the user as input, matches the two, and outputs the identified vehicle identification of the vehicle to be returned and the position of the vehicle identification in the target image.

[0073] As discussed above, the control end 110 can segment the target image 305 to identify the various objects in the target image 305. In the embodiment of the present disclosure, the position of the target vehicle 130 in the target image 305 can be located according to the position of the vehicle logo of the target vehicle in the target image and the segmentation result of the target image. In operation, the algorithm platform 114 can take the position of the vehicle logo of the target vehicle 130 in the target image 305 and the segmentation result of the target image as input, and take the position of the target vehicle 130 in the target image 305 as output. For further reference, Figure 3AAs discussed above, the control terminal 110 can determine that the identifier A 326-1 is the vehicle identifier of the target vehicle 130, and can determine the position of the identifier A 326-1 in the target image 305. Based on the above information, the control terminal 110 can determine the position of the identifier A 326-1 in the target image 305. Figure 3A Further, based on the above positioning information, the control end 110 can determine the target vehicle 130 in the semantic graph 330 .

[0074] In some embodiments, the control end 110 can process the target image 305 by utilizing the recognition model to detect whether the target image 305 includes at least one preset object in a set of preset objects. Further, the control end 110 can determine at least one area corresponding to the at least one preset object in the target image 305 in response to the target image 305 including at least one preset object. As an example, the recognition model can be implemented as a machine learning model with image recognition or segmentation capabilities. The present disclosure is not intended to limit the specific content and training process of the recognition model. In some embodiments, the process of the recognition model processing the target image can be a process of identifying a set of preset objects in the target image at the pixel level based on image segmentation technology, which can sometimes also be called scene recognition. Specifically, the target image uploaded by the user 140 is used as input, and the segmentation result of a set of preset objects at the pixel level is used as output.

[0075] In some embodiments, the control end 110 may process the target image by using a recognition model or other preset models to identify whether the target image 305 contains the aforementioned stop line mark, multiple types of objects and / or target vehicle 130. Further, the control end 110 may determine the area corresponding to the stop line mark, multiple types of objects and / or target vehicle 130 in the target image in response to the target image including the stop line mark, multiple types of objects and / or target vehicle 130.

[0076] In some embodiments, the control end 110 may generate (220) a semantic map corresponding to the target image based on the determined fusion area, the reference area 310, and the area corresponding to the target vehicle 130 in the target image 305. The semantic map indicates at least the first area and the fusion area of ​​the target vehicle 130 in the target image 305.

[0077] In some embodiments, the semantic map may further indicate a second area of ​​the target image where a parking line is marked. The parking line mark may be used to indicate a boundary of a vehicle return area.

[0078] In some embodiments, Figure 3BAs shown, the semantic graph 335 may include a fusion region 355, a region 340 corresponding to the fence, a first region 345 corresponding to the target vehicle 130, and a second region 350 corresponding to the stop line mark. As an example, the fusion region 355 is composed of Figure 3A Determined by area 330-2 and area 331-2 in .

[0079] As an example, a semantic graph is a highly abstract representation of a target image. Compared to using the target image itself, using a semantic graph can directly exclude background image information that is not related to the target vehicle at the input level, greatly reducing the algorithm's reliance on the amount and diversity of data, and significantly improving the algorithm's anti-interference ability and making the algorithm more interpretable.

[0080] Next, based on the semantic graph, the control end 110 determines ( 225 ) whether the parking of the target vehicle 130 satisfies the parking constraints.

[0081] In some embodiments, the control terminal 110 may provide a semantic graph to the classification model to obtain a classification label generated by the classification model. Further, the control terminal 110 may determine whether the parking of the target vehicle satisfies the parking constraint based on the classification label.

[0082] In some embodiments, the process of training the classification model by the control terminal 110 may include: obtaining a semantic graph sample set. The semantic graph sample set may include multiple training semantic graphs corresponding to the annotated parking information. Further, the control terminal 110 may train the classification model based on the multiple training semantic graphs and the annotated parking information.

[0083] In some embodiments, the training semantic graph may be generated based on a training image including at least one preset object from a set of preset objects. As an example, the training semantic graph may be generated based on a training image including a Bluetooth road stud. As an example, multiple training semantic graphs may include a preset reference area corresponding to at least one object from a set of preset objects. As an example, multiple training semantic graphs may include a preset reference area with a wall. As an example, multiple training semantic graphs may include a preset area or a preset fusion area with a parking pattern logo, a Bluetooth road stud, or an NFC device.

[0084] In some embodiments, the classification model is used to output a target classification label from a plurality of preset classification labels based on the semantic graph, and the plurality of preset classification labels correspond to different types of parking information.

[0085] In some embodiments, the parking information may indicate the parking orientation of the target vehicle 130. As an example, the parking orientation of the target vehicle 130 may indicate, for example, the parking angle of the target vehicle 130 relative to the parking line mark.

[0086] In some embodiments, the parking information may indicate the positional relationship between the target vehicle 130 and the return area. As an example, the positional relationship between the target vehicle 130 and the return area may include, for example, the target vehicle 130 is parked in the return area, the target vehicle 130 is parked outside the return area, and part of the target vehicle 130 (e.g., half of the vehicle body, etc.) is parked in the return area.

[0087] In some embodiments, the control end 110 may determine whether the parking of the target vehicle satisfies the parking constraint based on the parking information. As an example, the first parking information may indicate, for example, that the parking orientation of the target vehicle 130 is perpendicular to the parking line mark, and the target vehicle 130 is parked inside the return area. The control end 110 may determine, based on the first parking information, that the parking of the target vehicle 130 satisfies the parking constraint. As an example, the second parking information may indicate, for example, that the parking orientation of the target vehicle 130 is not perpendicular to the parking line mark (for example, deviating from a preset angle). The control end 110 may determine, based on the second parking information, that the parking of the target vehicle 130 does not satisfy the parking constraint. As an example, the third parking information may indicate, for example, that the target vehicle 130 is parked outside the return area or partially (for example, less than two-thirds of the vehicle body) is parked in the return area. The control end 110 may determine, based on the third parking information, that the parking of the target vehicle 130 does not satisfy the parking constraint.

[0088] It should be understood that the above parking constraints are merely exemplary. It should be understood that in other embodiments, other parking constraints may also be included. The embodiments of the present disclosure are not limited in terms of the specific content of the parking constraints.

[0089] In some embodiments, different areas may have different parking constraints. For example, area A has provisions for parking constraint 1 and parking constraint 2, while area B has provisions for parking constraint 2. In view of this, in some embodiments, in response to a return request for the target vehicle 130, the control end 110 may obtain the location information of the target vehicle 130, and further determine the parking constraints associated with the location information.

[0090] Finally, the control end 110 provides (230) a response to the vehicle return request to the user device 120 based on the determination result of whether the target vehicle 130 satisfies the parking constraint.

[0091] In some embodiments, the control end 110 may generate a first response in response to the target vehicle 130 satisfying the parking constraint to complete the vehicle return request.

[0092] In some embodiments, the control end 110 may generate a second response in response to the target vehicle 130 not satisfying the parking constraint to trigger providing guidance information. The guidance information may indicate a parking method that satisfies the parking constraint.

[0093] Additionally, the guidance information may be used to guide the adjustment of the parking orientation of the target vehicle to comply with the parking constraints. Alternatively or additionally, the guidance information may also be used to guide the movement of the target vehicle into the return area to comply with the parking constraints.

[0094] Through the above process, it is possible to effectively identify whether the return process of the target vehicle 130 meets the parking regulations, which not only improves the efficiency of parking management, but also reduces the cost of parking management.

[0095] In order to better understand the above process, we will combine Figure 4 The above operation is further described. It should be understood that Figure 4 The example operations discussed should not be construed as limitations on the present disclosure.

[0096] In some embodiments, Figure 4 , which shows a flowchart 400 of an example process for processing a vehicle return request according to some embodiments of the present disclosure.

[0097] In box 401, the algorithm platform 114 acquires the target image. In box 402, the algorithm platform 114 identifies the vehicle identification in the target image, for example, based on optical character recognition (OCR) technology. In box 404, the algorithm platform 114 determines the vehicle identification of the to-be-returned vehicle and the position of the vehicle identification in the target image based on the vehicle identification list of the to-be-returned vehicles in the system and the vehicle identification identified in the target image. In box 407, the algorithm platform locates the to-be-returned vehicle in the target image.

[0098] After acquiring the target image, the algorithm platform 114 also performs scene recognition on the target image, that is, recognizes multiple objects in the target image. In block 406, the algorithm platform 114 may determine the position information of the target vehicle, the preset object, and all the parking lines.

[0099] At block 408 , the algorithm platform 114 may generate a semantic graph. Based on the generated semantic graph, at block 409 , the algorithm platform 114 may identify the positional relationship and orientation of the target vehicle and the vehicle return area.

[0100] In blocks 409 - 1 and 409 - 2 , the algorithm platform 114 may obtain the position relationship and orientation recognition results. Based on this, in block 410 , the algorithm platform 114 may send the recognition results to the service platform 112 so that the service platform 112 may record and / or process the return request.

[0101] Through the above process, it can help accurately identify the parking process of shared vehicles for return requests, and effectively identify whether the front direction of the vehicle to be returned, the position relationship with the return area (for example, the degree of entry into the fence), etc. meet the parking constraints. In addition, by performing image segmentation on the target image, the vehicle, preset objects and various known parking lines in the target image can be identified, thereby guiding users to park in a standardized manner and avoiding illegal parking such as reverse and horizontal parking.

[0102] Furthermore, according to the method disclosed herein, various preset objects (e.g., Bluetooth studs, NFC devices, parking guide patterns, etc.) set within the physical area are comprehensively considered, thereby improving the efficiency and accuracy of identifying whether the parking of the vehicle complies with parking regulations when processing a vehicle return request.

[0103] Example Process

[0104] Figure 5 A flow chart illustrating a process 500 of request processing according to some embodiments of the present disclosure is shown.

[0105] It should be understood that process 500 can be implemented on the service side (eg, control terminal 110 ) or on the terminal side (eg, user equipment 120 , in which case user equipment 120 includes a functional module for implementing process 500 ).

[0106] Next, for the sake of convenience of description only, the process 500 is described by taking the process 500 at the control terminal 110 as an example.

[0107] In block 510 , the control end 110 acquires a target image associated with the target vehicle in response to a vehicle return request for the target vehicle.

[0108] In block 520 , the control end 110 detects whether the target image includes a set of preset objects, wherein the set of preset objects is suitable for being arranged inside the physical area to characterize the physical area as a vehicle return area.

[0109] In block 530 , in response to the target image including at least one preset object, the control end 110 determines a fusion region by fusing a group of regions of the at least one object in the target image.

[0110] In block 540 , the control end 110 generates a semantic map corresponding to the target image, where the semantic map at least indicates: a first region and a fusion region of the target vehicle in the target image.

[0111] In block 550 , the control end 110 determines whether the parking of the target vehicle satisfies the parking constraints based on the semantic graph.

[0112] At block 560 , the control terminal 110 provides a response to the vehicle return request based on the determination result of whether the target vehicle complies with the parking constraint.

[0113] In some embodiments, the set of preset objects includes: parking guidance signs drawn inside the physical area; and / or parking indication objects configured inside the physical area.

[0114] In some embodiments, based on the semantic graph, determining whether the parking of the target vehicle satisfies the parking constraints includes: providing the semantic graph to a classification model; obtaining a classification label generated by the classification model; and determining whether the parking of the target vehicle satisfies the parking constraints based on the classification label.

[0115] In some embodiments, the classification label indicates at least one of the following: a positional relationship between the target vehicle and the vehicle return area; and a parking orientation of the target vehicle.

[0116] In some embodiments, the classification model is trained based on the following process: obtaining a semantic graph sample set, the semantic graph sample set including a plurality of training semantic graphs corresponding to the annotated parking information; and training the classification model based on the plurality of training semantic graphs and the annotated parking information.

[0117] In some embodiments, the training semantic graph is generated based on a training image including at least one preset object from a set of preset objects.

[0118] In some embodiments, the semantic map further indicates that a parking line is marked in a second area of ​​the target image, and the parking line is used to indicate a boundary of a vehicle return area.

[0119] In some embodiments, based on a determination result of whether the target vehicle satisfies the parking constraints, providing a response to a vehicle return request includes: in response to the target vehicle satisfying the parking constraints, generating a first response to complete the vehicle return request; and in response to determining that the target vehicle does not satisfy the parking constraints, generating a second response to trigger providing guidance information, wherein the guidance information indicates a parking method that satisfies the parking constraints.

[0120] Example devices and equipment

[0121] Figure 6 A schematic structural block diagram of an apparatus 600 for request processing according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented as or included in the control terminal 110 or the user equipment 120. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware or any combination thereof.

[0122] like Figure 6As shown, the device 600 includes an acquisition module 610, which is configured to acquire a target image associated with the target vehicle in response to a return request for the target vehicle; a detection module 620, which is configured to detect whether the target image includes a group of preset objects, wherein the group of preset objects is suitable for being set inside a physical area to characterize the physical area as a return area; a determination module 630, which is configured to determine a fusion area by fusing a group of areas of at least one object in the target image in response to the target image including at least one preset object; a generation module 640, which is configured to generate a semantic map corresponding to the target image, the semantic map at least indicating: a first area of ​​the target vehicle in the target image and a fusion area; a judgment module 650, which is configured to determine whether the parking of the target vehicle satisfies the parking constraints based on the semantic map; and a response module 660, which is configured to provide a response to the return request based on the determination result of whether the target vehicle meets the parking constraints.

[0123] In some embodiments, the set of preset objects includes: parking guidance signs drawn inside the physical area; and / or parking indication objects configured inside the physical area.

[0124] In some embodiments, the determination module 650 is further configured to: provide a semantic graph to the classification model; obtain a classification label generated by the classification model; and determine whether the parking of the target vehicle satisfies the parking constraints based on the classification label.

[0125] In some embodiments, the classification label indicates at least one of the following: a positional relationship between the target vehicle and the vehicle return area; and a parking orientation of the target vehicle.

[0126] In some embodiments, the classification model is trained based on the following process: obtaining a semantic graph sample set, the semantic graph sample set including a plurality of training semantic graphs corresponding to the annotated parking information; and training the classification model based on the plurality of training semantic graphs and the annotated parking information.

[0127] In some embodiments, the training semantic graph is generated based on a training image including at least one preset object from a set of preset objects.

[0128] In some embodiments, the semantic map further indicates that a parking line is marked in a second area of ​​the target image, and the parking line is used to indicate a boundary of a vehicle return area.

[0129] In some embodiments, the response module 660 is further configured to: generate a first response in response to the target vehicle satisfying the parking constraints to complete the vehicle return request; and generate a second response in response to determining that the target vehicle does not satisfy the parking constraints to trigger the provision of guidance information, wherein the guidance information indicates a parking method that satisfies the parking constraints.

[0130] Figure 71 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7 The electronic device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 700 may include or be implemented as Figure 6 Device 600.

[0131] like Figure 7 As shown, the electronic device 700 is in the form of a general-purpose computing device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capabilities of the electronic device 700.

[0132] The electronic device 700 typically includes a plurality of computer storage media. Such media may be any available media accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the electronic device 700.

[0133] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0134] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0135] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 700, or communicate with any device that allows the electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0136] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0137] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0138] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0139] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0140] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0141] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the marketplace, or to enable other persons of ordinary skill in the art to understand the disclosure herein.

Claims

1. A method for request processing, comprising: In response to a vehicle return request for a target vehicle, acquiring a target image associated with the target vehicle; detecting whether the target image includes a set of preset objects, wherein the set of preset objects is suitable for being arranged inside a physical area to characterize the physical area as a vehicle return area; In response to the target image including at least one preset object, determining a fusion area by fusing a group of areas of the at least one object in the target image; Generate a semantic map corresponding to the target image, wherein the semantic map at least indicates: a first area of ​​the target vehicle in the target image and the fusion area; Based on the semantic graph, determining whether the parking of the target vehicle satisfies parking constraints; as well as A response to the vehicle return request is provided based on a determination of whether the subject vehicle complies with the parking constraints.

2. The method according to claim 1, wherein the set of preset objects comprises: a parking guidance sign drawn inside the physical area; and / or A parking indicator object is arranged inside the physical area.

3. The method according to claim 1, wherein based on the semantic graph, determining whether the parking of the target vehicle satisfies parking constraints comprises: providing the semantic graph to a classification model; Obtaining a classification label generated by the classification model; as well as Based on the classification label, it is determined whether the parking of the target vehicle satisfies the parking constraint.

4. The method of claim 3, wherein the classification label indicates at least one of the following: The positional relationship between the target vehicle and the vehicle return area; The parking orientation of the target vehicle.

5. The method of claim 3, wherein the classification model is trained based on the following process: Acquire a semantic graph sample set, wherein the semantic graph sample set includes a plurality of training semantic graphs corresponding to the annotated parking information; and The classification model is trained based on the plurality of training semantic graphs and the labeled parking information. 6 . The method according to claim 5 , wherein the training semantic graph is generated based on a training image including at least one preset object in the set of preset objects.

7. The method of claim 1, wherein the semantic graph further indicates: A parking line mark is located in a second area of ​​the target image, and the parking line mark is used to indicate a boundary of the vehicle return area.

8. The method of claim 1 , wherein providing a response to the vehicle return request based on a determination of whether the target vehicle satisfies parking constraints comprises: In response to the target vehicle satisfying the parking constraint, generating a first response to complete the vehicle return request; as well as In response to determining that the target vehicle does not satisfy the parking constraint, a second response is generated to trigger providing guidance information indicating a parking manner that satisfies the parking constraint.

9. An apparatus for request processing, comprising: an acquisition module, configured to acquire a target image associated with the target vehicle in response to a vehicle return request for the target vehicle; a detection module configured to detect whether the target image includes a set of preset objects, wherein the set of preset objects is suitable for being arranged inside a physical area to characterize the physical area as a vehicle return area; a determination module configured to determine a fusion area by fusing a group of areas of the at least one object in the target image in response to the target image including at least one preset object; A generating module is configured to generate a semantic map corresponding to the target image, wherein the semantic map at least indicates: a first area of ​​the target vehicle in the target image and the fusion area; A judgment module is configured to determine whether the parking of the target vehicle satisfies parking constraints based on the semantic graph; as well as The response module is configured to provide a response to the vehicle return request based on a determination result of whether the target vehicle complies with the parking constraint.

10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 8.

Images