An image recognition method, device, electronic equipment and storage medium

Abstract

This invention discloses an image recognition method, apparatus, electronic device, and storage medium. The method includes: acquiring an image to be recognized, and recognizing license plate information in the image using a first recognition model; determining whether the image contains a target vehicle based on the license plate information; if so, determining the type of the target vehicle according to an item recognition instruction, and calling a second recognition model based on the item type to determine whether the target vehicle exists in the image. By implementing the technical solution provided by this invention, the problems of incorrect image recognition and increased computational burden caused by simultaneously recognizing multiple items in an image using multiple models can be solved; and the increased training complexity and reduced flexibility of model training caused by recognizing multiple items in an image using a single model can be addressed, thus improving the accuracy and efficiency of image recognition.

Description

Technical Field

[0001] This invention relates to computer technology, and more particularly to an image recognition method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of computer technology, it is possible to identify the object to be detected from an image by processing it.

[0003] In existing technologies, the object to be detected is typically considered the target, while other objects are considered distractors. A training set is then used to train a recognition model to identify the target object. However, in image recognition, it is usually necessary to identify multiple objects in an image. If multiple models are used for recognition simultaneously, other objects may become distractors when identifying one of the target objects, resulting in the image not being correctly identified. Furthermore, the simultaneous computation by multiple recognition models increases the computational burden.

[0004] If a single model is used to identify multiple items in an image, a training set containing multiple items in the same image is required for training. As the number of items increases, the complexity of training increases, and if any item changes, the entire model needs to be retrained, reducing the flexibility of model training. Summary of the Invention

[0005] This invention provides an image recognition method, apparatus, electronic device, and storage medium to improve the accuracy and efficiency of image recognition.

[0006] According to one aspect of the present invention, an image recognition method is provided, the method comprising:

[0007] Acquire an image to be identified, and identify the license plate information in the image to be identified using a first recognition model;

[0008] Based on the license plate information in the image, determine whether the image to be identified contains the target vehicle;

[0009] If included, the item type of the item to be identified is determined according to the item identification instruction, and the second identification model is invoked according to the item type to determine whether the item to be identified exists in the image to be identified.

[0010] According to another aspect of the present invention, an image recognition device is provided, the device comprising:

[0011] The license plate information recognition module is used to acquire an image to be recognized and to recognize the license plate information in the image to be recognized through a first recognition model;

[0012] The vehicle includes a determining module, used to determine whether the image to be identified contains the target vehicle based on the license plate information in the image;

[0013] The item presence determination module is used to determine the item type of the item to be identified according to the item identification instruction if the vehicle inclusion determination module determines that the vehicle includes the item, and to call the second identification model according to the item type to determine whether the item to be identified exists in the image to be identified through the second identification model.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the image recognition method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the image recognition method according to any embodiment of the present invention.

[0019] The technical solution provided in this embodiment acquires an image to be recognized and identifies the license plate information in the image using a first recognition model. Based on the license plate information, it determines whether the image contains a target vehicle, avoiding images unrelated to the target vehicle and improving the effectiveness of image recognition. If the image contains a target vehicle, the type of the item to be recognized is determined according to the item recognition instruction, and a second recognition model is invoked based on the item type to determine whether the item exists in the image. This allows for the separate invocation of the corresponding second recognition model for different item types to identify whether the image contains that type of item. This avoids the problem of multiple models simultaneously identifying one item while other items become interfering, preventing correct image recognition. It also avoids the increased computational burden caused by multiple recognition models performing calculations simultaneously. Each time a single type of item is identified, the accuracy of item recognition is improved and the computational burden is reduced when multiple items to be identified are contained in an image. Furthermore, when the types of items to be identified are increased, a second recognition model corresponding to that type can be trained separately and added. This solves the problem that when a single model is used to identify multiple items in an image, it is necessary to obtain a training set of multiple items in the same image for training. As the number of items increases, the training complexity increases, and if the items change, the entire model needs to be retrained, which reduces the flexibility of model training and improves the efficiency of image recognition.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] Figure 1 This is a flowchart of an image recognition method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of an image recognition method provided in Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of an image recognition device provided in Embodiment 3 of the present invention;

[0024] Figure 4 The diagram shows a schematic of an electronic device used to implement an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1 This is a flowchart of an image recognition method provided in Embodiment 1 of the present invention. This embodiment is applicable to recognizing items of a specified type in an image. The method can be executed by the image recognition device provided in this embodiment, which can be implemented in software and / or hardware. See also... Figure 1 The image recognition method provided in this embodiment includes:

[0029] Step 110: Obtain the image to be recognized and identify the license plate information in the image to be recognized using the first recognition model.

[0030] The image to be recognized is the image that requires subsequent image processing and can be provided by the image owner. The license plate information in the image to be recognized is identified using a first recognition model, which is a model capable of recognizing license plate information, such as an OCR model. This can be accomplished using the OpenCV (Open Source Computer Vision Library) image algorithm library. OpenCV is an open-source computer vision and machine learning library that provides interfaces in C++, C, and Python, and supports Windows, Linux, Android, and macOS platforms, improving the applicability of image recognition. The license plate information can be the license plate number information of the vehicle contained in the image.

[0031] For example, before the first recognition model processes the image to be recognized, it is first preprocessed. The preprocessing process may include: resampling the image to be recognized and converting it to grayscale to obtain a grayscale image; then using Gaussian smoothing to reduce noise in the image; next, performing opening operation morphological processing, Otsu thresholding, and Canny operator thresholding respectively; finally, calculating the aspect ratio of each contour contained in the image, retaining and cropping the contour that conforms to the aspect ratio of the license plate. After obtaining the license plate contour, each character within the license plate contour is segmented based on the K-means clustering algorithm. Finally, the first recognition model trained by sk-learn's support vector machine predicts the segmented characters, and finally outputs the recognized license plate number.

[0032] Step 120: Determine whether the image to be identified contains the target vehicle based on the license plate information in the image.

[0033] The target vehicle is a vehicle that meets preset conditions and is associated with the item to be identified. The preset conditions can be preset license plate conditions, such as the license plate containing a preset region, etc., which are not limited in this embodiment. The association between the target vehicle and the item to be identified can be that the target vehicle is needed to transport the item to be identified, etc., which are not limited in this embodiment.

[0034] Determining whether a target vehicle is contained in an image based on license plate information can involve checking whether the license plate information matches the preset license plate conditions of the target vehicle, such as determining whether the identified license plate number belongs to a preset region.

[0035] If the image to be identified does not contain the target vehicle, the subsequent steps can be stopped and a message will be displayed indicating that the target vehicle does not exist in the image.

[0036] Step 130: If included, determine the item type of the item to be identified according to the item identification instruction, and call the second identification model according to the item type to determine whether the item to be identified exists in the image to be identified through the second identification model.

[0037] If the image to be identified contains the target vehicle, the type of the item to be identified is determined according to the item identification instruction. The item identification instruction is used to determine the type of the item to be identified. The item identification instruction can be generated by inputting text, such as inputting the text "identify tarpaulin".

[0038] The item type of the item to be identified can be determined from the item identification instruction through keyword recognition, and the corresponding second identification model can be called according to the item type. The second identification model is used to identify specific types of items. For example, if the item type is a tarp, the second identification model can be a tarp identification model; if the item type is a trolley, the second identification model can be a trolley identification model.

[0039] The second recognition model can be a YOLOv5 model, and this embodiment is not limited to this. For example, the training process of the second recognition model for recognizing tarpaulins, ropes, and carts may include:

[0040] First, a large number of images containing the items to be identified (rain tarpaulin, rope, or cart) and images not containing these items are acquired as a training dataset, with the ratio of the two types of images being approximately 10:1. The item categories and locations of the items in these images are manually labeled. Then, the training set is used as input to the second recognition model, which predicts the items in the training images and their locations. The model error is calculated based on the predicted item categories and locations compared to the labeled true categories and locations. The error is then backpropagated along the model structure to further optimize the model parameters. Through continuous iteration of the above process, the error value gradually decreases until convergence is achieved, resulting in the final second recognition model.

[0041] In this embodiment, optionally, determining the item type of the item to be identified according to the item identification instruction includes:

[0042] Acquire the input voice and determine whether to generate an item recognition instruction based on the keyword information in the input voice;

[0043] If generated, the item type is determined based on the instruction type of the item identification command.

[0044] The input voice can be the voice entered according to the prompts. The voice signal is processed by the speech-to-text model and converted into text. The text is then matched with preset keywords to extract keyword information. The preset keywords can be related to the current recognition scenario. For example, if the current scenario is a cargo transportation order taking scenario, the keyword information can include rope, tarpaulin, cart, etc.

[0045] If the text does not match the preset keyword, an item recognition command cannot be generated. For example, if the extracted keyword is "building blocks" and this keyword is not included in the preset keywords, an item recognition command cannot be generated; a corresponding prompt can be given, such as indicating that the voice input is incorrect and asking for re-entry, etc. This embodiment does not impose any limitations on this.

[0046] If the text matches a preset keyword, an item recognition instruction is generated based on the extracted keyword information. For example, if the matched keyword is "rope," the generated item recognition instruction could be "recognize rope." The item type is determined based on the instruction type of the item recognition instruction. For example, if the instruction type is "recognize rope," the item type is determined to be rope.

[0047] The system determines whether to generate an object recognition command by inputting voice, eliminating the need for text input and improving the user experience. Furthermore, it determines whether to generate an object recognition command based on keyword information in the input voice, improving the relevance of the generated command and preventing the inability to call the corresponding secondary recognition model later.

[0048] In this embodiment, optionally, after determining whether an item to be identified exists in the image to be identified through the second recognition model, the method further includes:

[0049] If no item is to be identified, the prompting method is determined based on the item type;

[0050] If an item to be identified exists, then it is determined whether to identify the image again based on the item identification instruction, depending on whether the item identification instruction is obtained again.

[0051] If no item is to be identified, the prompting method is determined according to the item type. For example, if the item to be identified is a tarpaulin, and the second recognition model fails to identify the tarpaulin in the image to be identified, a corresponding prompt can be given, such as "Failed to identify tarpaulin, please upload a separate photo of the tarpaulin".

[0052] If an item to be identified exists, the system determines whether to re-identify the image based on the item identification command, depending on whether another item identification command is obtained. For example, if the item to be identified is a tarp, and the tarp is identified in the image by the second identification model, a message "Tarp identification successful" can be displayed. If another item identification command is obtained, the item type of the new item to be identified can be determined based on the newly obtained command, such as a stroller. In this case, the second identification model related to stroller identification can be called to re-identify the image. If no new item identification command is obtained, the identification process can be considered complete, or an unidentified item can be identified based on the current identification scenario and a prompt can be displayed. This embodiment does not impose any limitations on this.

[0053] If no item to be identified exists, the prompting method is determined based on the item type. This improves the relevance of the prompting method and facilitates timely correction of errors caused by mismatches between the item recognition command and the image to be identified, or by unclear images preventing recognition. This enhances the accuracy of item recognition. If an item to be identified exists, the system determines whether to re-identify the image based on the item recognition command, based on whether another item recognition command is obtained. This allows for the identification of multiple items from a single image without requiring multiple images, improving the efficiency and convenience of image recognition.

[0054] The technical solution provided in this embodiment acquires an image to be identified and identifies the license plate information in the image to be identified through a first recognition model; it determines whether the image to be identified contains the target vehicle based on the license plate information, thereby avoiding the image to be identified being an image unrelated to the target vehicle and improving the effectiveness of image recognition.

[0055] If the image to be identified contains the target vehicle, the item type is determined according to the item recognition instruction. Then, a second recognition model is invoked based on the item type to determine whether the item exists in the image. This allows for the separate invocation of the corresponding second recognition model for different item types to identify whether the image contains items of that type. This avoids the problem of multiple models simultaneously identifying items, where other items become interfering and prevent correct image recognition. For example, in freight transport order-taking scenarios, auxiliary tools such as ropes, tarpaulins, and trailers are often needed. Drivers might stack these auxiliary tools together for identification purposes. Since ropes, tarpaulins, and trailers are all items to be identified, tarpaulins and trailers become interfering when identifying ropes, and vice versa. Furthermore, this avoids the increased computational burden caused by multiple recognition models performing calculations simultaneously. By identifying only one type of item at a time, the accuracy of item recognition is improved and the computational burden is reduced when identifying multiple items within a single image.

[0056] Furthermore, when adding new types of items to be identified, a second recognition model corresponding to that type can be trained separately. This solves the problem of needing to obtain a training set of multiple items in the same image for training when identifying multiple items in an image using a single model. As the number of items increases, the training complexity increases, and if the items change, the entire model needs to be retrained, which reduces the flexibility of model training and improves the efficiency of image recognition.

[0057] Example 2

[0058] Figure 2 This is a flowchart of an image recognition method provided in Embodiment 2 of the present invention. This technical solution provides supplementary explanation of the process of determining whether a target vehicle is contained in an image to be recognized based on license plate information. Compared with the above solution, this solution is specifically optimized as follows: determining whether a target vehicle is contained in an image to be recognized based on license plate information includes:

[0059] Identify the target object and obtain its preset license plate information;

[0060] If the preset license plate information matches the license plate information in the image, then the image to be identified contains the target vehicle. Specifically, the flowchart of the image recognition method is as follows: Figure 2 As shown:

[0061] Step 210: Obtain the image to be recognized, and use the first recognition model to recognize the license plate information in the image to be recognized.

[0062] Step 220: Determine the target object and obtain the target object's preset license plate information.

[0063] The target object can be the object that initiates the image recognition request, such as an object awaiting order dispatch. The target object can initiate the image recognition request by logging into an account in a system capable of image recognition. This system can be an order dispatch system, and this embodiment does not impose any restrictions on this. The target user can pre-register an account in the order dispatch system and bind corresponding information, such as preset license plate information. This preset license plate information is the license plate information reserved by the target object, such as vehicle information for the vehicle used by the target object to perform tasks dispatched by the order dispatch system.

[0064] Step 230: If the preset license plate information matches the license plate information in the image, then it is determined that the image to be identified contains the target vehicle.

[0065] If the preset license plate information matches the license plate information in the image, it indicates that the image to be identified contains a vehicle with the preset license plate, i.e., it contains the target vehicle.

[0066] Step 240: If included, determine the item type of the item to be identified according to the item identification instruction, and call the second identification model according to the item type to determine whether the item to be identified exists in the image to be identified through the second identification model.

[0067] In this embodiment, optionally, after determining whether an item to be identified exists in the image to be identified through the second recognition model, the method further includes:

[0068] Obtain the item identification results and determine the dispatch type associated with the target object based on the item identification results;

[0069] The target pending orders for the target object are determined based on the order type and the candidate pending orders.

[0070] The item recognition result is the overall recognition result obtained after recognizing the image to be recognized. It can be obtained when the target user determines that the recognition process is over or after a preset time interval since the last item recognition result was obtained. This embodiment does not impose any restrictions on this.

[0071] For example, if a single item recognition command results in an image containing a tarpaulin, multiple item recognition commands may result in an image containing a tarpaulin, a rope, and a cart.

[0072] The dispatch type associated with the target object is determined based on the item identification results. The dispatch type can be determined according to the type of items identified in the item identification results. For example, if the item identification results include a cart, it indicates that the target object can perform a task that can be completed using a cart, so the dispatch type can be a task that can be completed using only a cart. If the item identification results include a cart and a rope, it indicates that the target object can perform a task that can be completed using both a cart and a rope, so the dispatch type can be a task that can be completed using only a cart, a task that can be completed using only a rope, or a task that can be completed using both a cart and a rope.

[0073] Candidate pending orders are all orders that have not been assigned. Orders that meet the dispatch type and other preset conditions among the candidate pending orders are identified as target pending orders, so that the target pending orders can be dispatched to the target objects in the future. Other preset conditions can be geographical conditions, time conditions, etc., which are not limited in this embodiment.

[0074] By acquiring the item identification results and determining the order type associated with the target object based on the item identification results, and by determining the target pending order for the target object based on the order type and candidate pending orders, the target pending order is made into an order that the target object can execute through the items it owns, thereby improving the effectiveness of determining the target pending order and improving the accuracy of order dispatch.

[0075] This invention identifies a target object and obtains its preset license plate information. If the preset license plate information matches the license plate information in the image, the image to be identified is determined to contain the target vehicle. This ensures that in scenarios requiring vehicles, such as freight transportation orders, the object to be identified and the target vehicle exist within the same image, guaranteeing that the image to be identified is a real photograph of the target object and improving the effectiveness of image recognition.

[0076] Example 3

[0077] Figure 3 This is a schematic diagram of an image recognition device provided in Embodiment 3 of the present invention. This device can be implemented in hardware and / or software, and can execute an image recognition method provided in any embodiment of the present invention, possessing the corresponding functional modules and beneficial effects of the method. Figure 3 As shown, the device includes:

[0078] The license plate information recognition module 310 is used to acquire an image to be recognized and to recognize the license plate information in the image to be recognized through a first recognition model.

[0079] The vehicle includes a determination module 320, which is used to determine whether the image to be identified contains the target vehicle based on the image license plate information;

[0080] The item presence determination module 330 is used to determine the item type of the item to be identified according to the item identification instruction if the vehicle inclusion determination module determines that the item is included, and to call the second identification model according to the item type, so as to determine whether the item to be identified exists in the image to be identified through the second identification model.

[0081] Based on the above technical solutions, optionally, the vehicle includes a determining module, including:

[0082] A license plate information acquisition unit is used to determine a target object and acquire preset license plate information of the target object;

[0083] The vehicle includes a determining unit, which determines that the target vehicle is contained in the image to be identified if the preset license plate information matches the image license plate information.

[0084] Based on the above technical solutions, optionally, the device further includes:

[0085] The dispatch type determination module is used to obtain the item identification result after the item existence determination module, and determine the dispatch type associated with the target object based on the item identification result;

[0086] The pending order determination module is used to determine the target pending order of the target object based on the dispatch type and the candidate pending orders.

[0087] Based on the above technical solutions, optionally, the item existence determination module includes:

[0088] The instruction generation and determination unit is used to acquire the input voice and determine whether to generate the item recognition instruction based on the keyword information in the input voice.

[0089] An item type determination unit is used to determine the item type based on the instruction type of the item identification instruction if the instruction generation determination unit determines that the instruction is generated.

[0090] Based on the above technical solutions, optionally, the device further includes:

[0091] The prompting module is used to determine the prompting method based on the item type if the item to be identified does not exist after the item existence confirmation module has been established.

[0092] The image recognition determination module is used to determine whether to recognize the image again according to the item recognition instruction if the item to be recognized exists, based on whether the item recognition instruction is obtained again.

[0093] Example 4

[0094] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0095] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0096] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0097] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as image recognition methods.

[0098] In some embodiments, the image recognition method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the image recognition method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the image recognition method by any other suitable means (e.g., by means of firmware).

[0099] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0101] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0103] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0104] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0105] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0106] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An image recognition method applied to a cargo transportation order-taking scenario, characterized in that, include: Acquire an image to be identified, and identify the license plate information in the image to be identified using a first recognition model; Based on the license plate information in the image, determine whether the image to be identified contains the target vehicle; If included, the input speech is acquired, and an item recognition instruction is generated based on the keyword information in the input speech, wherein the keyword information includes at least one of the following: rope, tarpaulin, cart; the item type of the item to be recognized is determined according to the instruction type of the item recognition instruction, and a second recognition model is invoked according to the item type to determine whether the item to be recognized exists in the image to be recognized through the second recognition model; Obtain the item identification result, and determine the dispatch type associated with the target object based on the item identification result, wherein the target object is the object to be dispatched; The target pending orders for the target object are determined based on the dispatch type and the candidate pending orders.

2. The method according to claim 1, characterized in that, Determining whether the image to be identified contains the target vehicle based on the license plate information in the image includes: Identify the target object and obtain the preset license plate information of the target object; If the preset license plate information matches the image license plate information, then it is determined that the target vehicle is contained in the image to be identified.

3. The method according to claim 1, characterized in that, After determining whether the object to be identified exists in the image to be identified using the second recognition model, the method further includes: If the item to be identified does not exist, the prompting method is determined based on the item type; If the item to be identified exists, then depending on whether the item identification instruction is obtained again, it is determined whether to identify the image to be identified again according to the item identification instruction.

4. An image recognition device, applied in a cargo transportation order-taking scenario, characterized in that, include: The license plate information recognition module is used to acquire an image to be recognized and to recognize the license plate information in the image to be recognized through a first recognition model; The vehicle includes a determining module, used to determine whether the image to be identified contains the target vehicle based on the license plate information in the image; The item presence determination module is used to acquire input voice if the vehicle presence determination module determines that the vehicle contains the item, and generate an item recognition instruction based on the keyword information in the input voice, wherein the keyword information includes at least one of the following: rope, tarpaulin, and cart; determine the item type of the item to be recognized based on the instruction type of the item recognition instruction, and call a second recognition model based on the item type to determine whether the item to be recognized exists in the image to be recognized through the second recognition model; The dispatch type determination module is used to obtain the item identification result and determine the dispatch type associated with the target object based on the item identification result, wherein the target object is the object to be dispatched; The pending order determination module is used to determine the target pending order of the target object based on the dispatch type and the candidate pending orders.

5. The apparatus according to claim 4, characterized in that, The vehicle includes a determining module, comprising: A license plate information acquisition unit is used to determine a target object and acquire preset license plate information of the target object; The vehicle includes a determining unit, which determines that the target vehicle is contained in the image to be identified if the preset license plate information matches the image license plate information.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the image recognition method according to any one of claims 1-3.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the image recognition method according to any one of claims 1-3.

Images