A data processing system for a robotic arm system

Abstract

This application discloses a data processing system for a robotic arm system, which performs target recognition on first image information to obtain first recognition result information; and analyzes and processes the first recognition result information to obtain target recognition result information.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically to a data processing system. Background Technology

[0002] With the development of display technology, display devices have become an indispensable part of people's daily lives. Tendon-driven robotic arms are widely used in the production process of display devices. This process requires target identification of key components such as QR codes, screws, tape, terminals, and flexible flat cables on the backplate to enable efficient operation by the robotic arm. However, traditional identification methods have relatively low target recognition efficiency and require improvement in detection accuracy. Summary of the Invention

[0003] This application provides a data processing system.

[0004] In a first aspect, this application provides a method comprising:

[0005] Obtain the first image information;

[0006] Target recognition is performed on the first image information to obtain the first recognition result information;

[0007] The first identification result information is analyzed and processed to obtain the target identification result information.

[0008] Secondly, this application provides a system comprising:

[0009] The information acquisition module is used to acquire the first image information;

[0010] The target recognition module is used to perform target recognition on the first image information to obtain the first recognition result information;

[0011] The data processing module is used to analyze and process the first recognition result information to obtain the target recognition result information.

[0012] Thirdly, this application also provides an apparatus, the apparatus comprising:

[0013] One or more processors;

[0014] Memory; and

[0015] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor to implement the methods of any one of the first aspects.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps of the method in any of the first aspects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of a data processing system provided in an embodiment of the present invention;

[0019] Figure 2 This is a flowchart of one embodiment of the data processing method provided by the present invention;

[0020] Figure 3 This is a flowchart of a specific embodiment of target recognition of first image information provided by the present invention;

[0021] Figure 4 This is a schematic diagram of an embodiment of the first image information provided in this invention;

[0022] Figure 5 Yes Figure 4 A schematic diagram of the second image information obtained by segmenting the first image information shown;

[0023] Figure 6 This is a flowchart of a specific embodiment of the present invention for analyzing and processing the first identification result information;

[0024] Figure 7 This is a schematic diagram of another embodiment of the first image information provided in this invention;

[0025] Figure 8 Based on target recognition results information Figure 7 A schematic diagram of the fifth image information obtained by cropping the first image information shown;

[0026] Figure 9 It is a display interface diagram obtained by processing the target recognition result information;

[0027] Figure 10 This is a schematic block diagram of the data processing system provided in the embodiments of the present invention;

[0028] Figure 11 This is a schematic diagram of an embodiment of the computer device provided in this invention. Detailed Implementation

[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first," "second," "third," etc., may explicitly or implicitly include one or more features. In the description of this application, "at least one" means one or more, and "multiple" means two or more, unless otherwise stated.

[0031] This application provides a data processing method and system. Furthermore, the above-mentioned data processing method and system can be a data processing method and system for a robotic arm system, which will be described in detail below.

[0032] Please see Figure 1 , Figure 1 This is a schematic diagram of a data processing system provided in an embodiment of this application. The data processing system may include a computer device 100, such as... Figure 1 Computer equipment in the country.

[0033] In this embodiment, the computer device 100 can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0034] It is understood that the computer device 100 used in the embodiments of this application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and may also be one of the following: an augmented reality (AR) device, a mobile phone, a tablet computer, a laptop computer, etc.

[0035] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the data processing system may also include one or more other services, which are not limited here.

[0036] In addition, such as Figure 1 As shown, the data processing system may also include a memory 200 for storing data, such as feature information, such as first feature information, second feature information, etc., and image information, such as first image information, second image information, etc.

[0037] like Figure 2 The diagram shown is a flowchart of an embodiment of the data processing method in this application. The data processing method may include the following steps S201 to S203, as detailed below:

[0038] S201, Obtain the first image information.

[0039] In this embodiment of the application, the first image information is the image information obtained by taking a picture of the target to be identified through the imaging module. The target to be identified is the target object that needs to be identified. For example, the target to be identified can be the back panel of a display device, and the first image information can be the image information obtained by taking a picture of the back panel of the display device; the target to be identified can also be the control board inside a smart home appliance such as a refrigerator, air conditioner, or washing machine, and the first image information can be the image information obtained by taking a picture of the control board.

[0040] Optionally, the first image information can be image information acquired by the imaging module configured on the computer device itself, or image information acquired by the imaging module of other computer devices through means such as network, Bluetooth, and infrared. This embodiment does not limit this. For example, when the data processing method of this application is applied to a smartphone, the smartphone can directly acquire the first image information through its own configured imaging module. When the data processing method of this application is applied to a server, the server can acquire the first image information through the imaging module of the smartphone and obtain the first image information from the smartphone through means such as network, Bluetooth, and infrared.

[0041] S202. Perform target recognition on the first image information to obtain the first recognition result information.

[0042] In this embodiment, the first recognition result information is the recognition result information obtained by performing target recognition on the first image information. The first recognition result information includes object location information and object score information. The object location information can represent the position information of the object to be recognized in the second image information, and the object score information can represent the target category information to which the object to be recognized belongs and the score information under the target category information. The second image information is image information segmented from the first image information, and the second image information has fewer pixels than the first image information. For example, when the first image information is image information obtained by taking a picture of the back panel of a display device, the object to be recognized can be a key component of the back panel such as a QR code, screw, tape, terminal, or flexible flat cable. The object location information can be the bounding box information of the key components such as the QR code, screw, tape, terminal, or flexible flat cable in the second image information, and the object score information can be the target category information to which the key components such as the QR code, screw, tape, terminal, or flexible flat cable belong and the score information under the target category information.

[0043] Optionally, target recognition can be performed directly on the first image information, or the first image information can be segmented, and then target recognition can be performed on the segmented image information. In some embodiments, refer to Figure 3 As shown, the target recognition of the first image information in step S202 above to obtain the first recognition result information may include steps S301 to S304, as follows:

[0044] S301. The first image information is segmented to obtain multiple second image information.

[0045] In this embodiment, the segmentation process essentially involves grouping pixels with similar features in the image information, thereby dividing the image information into different meaningful regions. Multiple second image information segments are image information segmented from the first image information; that is, the second image information has fewer pixels than the first image information, but the number of pixels in the multiple second image information segments can be the same or different. For example, the first image information has a size of 3840×2160 pixels, and the multiple second image information segments have a size of 512×512 pixels. This embodiment segments the first image information to obtain multiple second image information segments, and then performs target recognition on each of the multiple second image information segments to obtain the first recognition result information. On the one hand, the number of pixels in the second image information is significantly reduced compared to the first image information, thereby reducing the consumption of computing resources and computing time. On the other hand, it can reduce the loss of details caused by the large size of the first image information, improving the accuracy of small target recognition.

[0046] Optionally, after obtaining the first image information, the first image information can be segmented according to a preset image size and segmentation step size, for example, Figure 4 The first image information shown can be obtained after segmentation processing. Figure 5 The diagram shows multiple second image information. Further, adjacent second image information in the segmented multiple second image information may have overlapping regions. Adjacent second image information refers to second image information that is positionally adjacent and not separated by other second image information. For example, there may be a 20% to 50% overlap between adjacent second image information. In this embodiment, by making adjacent second image information have overlapping regions during the segmentation process of the first image information, the loss of boundary information can be avoided, thus improving the accuracy of target recognition.

[0047] S302. Normalize the multiple second image information to obtain multiple third image information.

[0048] In this embodiment, normalization essentially involves adjusting and transforming the pixel values ​​of image information to give them specific statistical characteristics or conform to a certain distribution, thus facilitating subsequent image processing and analysis. Optionally, when normalizing multiple second image information pieces, the pixel value of each pixel in each second image information piece can be obtained, and the pixel value of each pixel can be normalized to obtain multiple third image information pieces. By normalizing the second image information, recognition errors caused by differences in pixel value ranges between different images can be avoided, improving the accuracy of the recognition results.

[0049] Optionally, the normalization process for the pixel value of each pixel can be expressed as: P represents the normalized pixel value corresponding to the i-th pixel in the second image information. i δ represents the original pixel value corresponding to the i-th pixel in the second image information, and δ represents the eleventh parameter. Optionally, the eleventh parameter varies with the range of pixel values ​​in the second image information. For example, if the range of pixel values ​​in the second image information is [0, 255], then δ = 255.

[0050] S303. Scale the multiple third image information separately to obtain multiple fourth image information.

[0051] In this embodiment, scaling is essentially a process of adjusting the image size to adapt to different application scenarios by changing the number of pixels and spatial distribution of the image. By scaling multiple third image information separately, multiple third image information can be adjusted to a uniform image size, thereby ensuring input consistency and improving the computational efficiency of the target recognition model.

[0052] S304. Input multiple fourth image information into the target recognition model, and output the first recognition result information through the target recognition model.

[0053] In this embodiment, the target recognition model is a pre-trained neural network model for target recognition of multiple fourth image information. Optionally, the target recognition model is obtained by training a first network model using training samples. The first network model can be a model for target recognition such as YOLO (You Only Look Once), SSD (Single Shot MultiBoxDetector), or DETR (Detection Transformer). Optionally, the basic training parameters for training the target recognition model are shown in Table 1.

[0054] Table 1 Basic training parameters of the target recognition model

[0055]

[0056]

[0057] In some embodiments, training samples are obtained through the following steps: acquiring first sample image information and labeling the sample objects in the first sample image information with their positions and categories; segmenting the first sample image information according to a preset image size and segmentation size to obtain second sample image information; and determining the labeling information corresponding to the sample objects in the second sample image information and the second sample image information as training samples. For example, 100 backplane images can be acquired by a camera module, and the coordinate positions and categories of different types of electronic components can be manually labeled. Then, the backplane images can be segmented into 512×512 image information with an overlap ratio of 20%-50%. The segmented image information and the corresponding labeling information of the electronic components are the training samples.

[0058] S203. Analyze and process the first identification result information to obtain the target identification result information.

[0059] In this embodiment, the target recognition result information is the final recognition result information obtained by analyzing and processing the first recognition result information. The target recognition result information represents the position information of the object to be identified in the first image information and the target category information to which the object belongs. The object to be identified includes QR codes, and / or screws, and / or tape, and / or terminals, and / or flexible flat cables. This embodiment obtains the first recognition result information by performing target recognition on the first image information, and then analyzes and processes the first recognition result information to obtain the target recognition result information. This enables automatic target recognition, improving the efficiency and accuracy of target recognition.

[0060] In some embodiments, the first identification result information includes object location information and object score information, referring to Figure 6 As shown, the analysis and processing of the first identification result information in step S203 to obtain the target identification result information may include steps S401 to S402, as follows:

[0061] S401. Based on the object location information and the object score information, determine the first location information and the second location information corresponding to the first location information.

[0062] In this embodiment, the first recognition result information includes object location information and object score information. The object location information can represent the location information of the object to be identified in the second image information, and the object score information can represent the target category information to which the object to be identified belongs and the score information under the target category information. The object location information includes multiple third location information, and the object score information includes first score information corresponding to each third location information. The first location information is the location information where the first score information corresponding to the multiple third location information satisfies a first condition. The second location information is the third location information where the feature value of the first feature information corresponding to the multiple third location information, excluding the first location information, is greater than a first threshold. The first feature information represents the degree of overlap between the regions corresponding to the first location information and other third location information.

[0063] In some embodiments, the step of determining first location information and second location information corresponding to the first location information based on object location information and object score information specifically includes: determining first location information from multiple third location information based on first score information corresponding to each third location information; determining first feature information corresponding to each of multiple fourth location information based on the first location information; and filtering multiple fourth location information based on the first feature information to obtain second location information corresponding to the first location information.

[0064] In this embodiment, the first location information is the location information in which the corresponding first score information among a plurality of third location information satisfies the first condition. The location information in which the corresponding first score information satisfies the first condition can be the location information with the largest score value of the corresponding first score information, or the location information in which the corresponding first score information satisfies the first condition can be the location information in which the score value of the corresponding first score information is greater than the fourth threshold. This embodiment does not limit this.

[0065] Furthermore, the multiple fourth location information refers to other location information besides the first location information among the multiple third location information. For example, the multiple third location information includes location information A, location information B, and location information C. If the first location information is location information A, then the multiple fourth location information is location information B and location information C. The second location information is the fourth location information whose corresponding first feature information has a feature value greater than a first threshold among the multiple fourth location information (i.e., other location information besides the first location information among the multiple third location information). The first threshold can be set according to actual needs. For example, the first threshold can be set to 0.5, then the second location information is the fourth location information whose corresponding first feature information has a feature value greater than 0.5.

[0066] In this embodiment, the first feature information can characterize the degree of overlap between the region corresponding to each fourth position information and the region corresponding to the first position information. The first characteristic information can be the ratio of the area of ​​the intersection region between the first position information and each fourth position information to the area of ​​the region corresponding to the first position information. Alternatively, the first feature information can also be the ratio of the area of ​​the intersection region between the first position information and each fourth position information to the area of ​​the region corresponding to each fourth position information. The intersection region refers to the region where the region corresponding to the first position information and the region corresponding to each fourth position information overlap. For example, if the first position information and the fourth position information A correspond to set A and set B respectively, then the intersection region corresponding to the first position information and the fourth position information A is a set composed of all elements that belong to both set A and set B. This embodiment uses the first feature information for target recognition, which ensures that small targets are not ignored when they partially overlap with large targets, thus improving the accuracy of small target recognition.

[0067] In some embodiments, the step of determining the first feature information corresponding to each of the plurality of fourth location information based on the first location information specifically includes: determining the second feature information corresponding to each fourth location information based on the first location information and each fourth location information; performing calculation processing on the first location information to obtain the third feature information; performing calculation processing on each fourth location information to obtain the fourth feature information corresponding to each fourth location information; and determining the first feature information corresponding to each fourth location information based on the second feature information, the third feature information, and the fourth feature information.

[0068] In this embodiment, the third feature information can characterize the area of ​​the region corresponding to the first position information, and the fourth feature information can characterize the area of ​​the region corresponding to each fourth position information. In this embodiment, the first position information and the fourth position information can be calculated and processed separately using the vector cross product method to obtain the third feature information and the fourth feature information, or the Gaussian area formula can be used to calculate and process the first position information and the fourth position information to obtain the third feature information and the fourth feature information. For details, please refer to the prior art, and this embodiment will not be elaborated here.

[0069] In this embodiment of the application, the second feature information is used to characterize the area of ​​the intersection region between the first position information and each fourth position. In some embodiments, the step of determining the second feature information corresponding to each fourth position information based on the first position information and each fourth position information specifically includes: analyzing and processing the first position information and each fourth position information to obtain the fifth position information corresponding to each fourth position information; and determining the second feature information corresponding to each fourth position information based on the fifth position information.

[0070] In this embodiment, the fifth position information is used to characterize the position of the intersection region corresponding to the first position information and the fourth position information. The fifth position information includes a first position value, a second position value, a third position value, and a fourth position value. The first position value is the maximum horizontal coordinate of the intersection region corresponding to the first and fourth position information; the second position value is the minimum horizontal coordinate of the intersection region corresponding to the first and fourth position information; the third position value is the maximum vertical coordinate of the intersection region corresponding to the first and fourth position information; and the fourth position value is the minimum vertical coordinate of the intersection region corresponding to the first and fourth position information. Optionally, the step of determining the second feature information corresponding to each fourth position information based on the fifth position information specifically includes: analyzing and processing the first and second position values ​​to obtain the fifth position value; analyzing and processing the first parameter and the fifth position value to obtain the sixth position value; analyzing and processing the third and fourth position values ​​to obtain the seventh position value; analyzing and processing the second parameter and the seventh position value to obtain the eighth position value; and analyzing and processing the sixth and eighth position values ​​to obtain the second feature information corresponding to each fourth position information.

[0071] In some embodiments, the fifth position value is obtained by analyzing and processing the first position value and the second position value using a first analysis model. The first analysis model is: S1 = γ1*x1 - γ2*x2, where S1 represents the fifth position value, x1 represents the first position value, x2 represents the second position value, γ1 represents the third parameter, and γ2 represents the fourth parameter.

[0072] In this embodiment, the third and fourth parameters can be set according to actual needs. In some embodiments, 0<γ1≤1, 0<γ2≤1. Optionally, γ1=1, γ2=1, then the first analysis model is: S1=x1-x2.

[0073] In some embodiments, the sixth position value is obtained by analyzing and processing the first parameter and the fifth position value through a second analysis model, wherein the second analysis model is: S2 = np.maximum(α, S1), S2 represents the sixth position value, α represents the first parameter, and np.maximum(·) means returning the larger value between α and S1.

[0074] In this embodiment, the first parameter can be set according to actual needs. In some embodiments, 0≤α<1. Optionally, α=0, then the second analysis model is: S2=np.maximum(0,S1). By taking the larger value between 0 and S1, the sixth position value S2 can be avoided from being negative.

[0075] In some embodiments, the seventh position value is obtained by analyzing and processing the third position value and the fourth position value through a third analysis model, wherein the third analysis model is: S3 = γ3*y1 - γ4*y2, where S3 represents the seventh position value, y1 represents the third position value, y2 represents the fourth position value, γ3 represents the fifth parameter, and γ4 represents the sixth parameter.

[0076] In this embodiment, the fifth and sixth parameters can be set according to actual needs. In some embodiments, 0<γ3≤1, 0<γ4≤1. Optionally, γ3=1, γ4=1, then the first analysis model is: S3=y1-y2.

[0077] In some embodiments, the eighth position value is obtained by analyzing and processing the second parameter and the seventh position value through a fourth analysis model, wherein the fourth analysis model is: S4 = np.maximum(β, S3), where S4 represents the eighth position value, β represents the second parameter, and np.maximum(·) means returning the larger value between β and S3.

[0078] In this embodiment, the second parameter can be set according to actual needs. In some embodiments, 0≤β<1. Optionally, β=0, then the second analysis model is: S4=np.maximum(0,S3). By taking the larger value between 0 and S3, the eighth position value S4 can be avoided from being negative.

[0079] In some embodiments, the second feature information is obtained by analyzing and processing the sixth position value and the eighth position value through the fifth analysis model, wherein the fifth analysis model is: s5=γ5*S2*γ6*S4, S5 represents the second feature information, γ5 represents the seventh parameter, and γ6 represents the eighth parameter.

[0080] In this embodiment, the seventh and eighth parameters can be set according to actual needs. In some embodiments, 0<γ5≤1, 0<γ6≤1. Optionally, γ5=1, γ6=1, then the fifth analysis model is: S5=S2*S4.

[0081] In some embodiments, the step of determining the first feature information corresponding to each fourth location information based on the second, third, and fourth feature information specifically includes: if the feature value corresponding to the third feature information is greater than or equal to the feature value corresponding to the fourth feature information, the fourth feature information is determined as the fifth feature information; and / or, if the feature value corresponding to the third feature information is less than the feature value corresponding to the fourth feature information, the third feature information is determined as the fifth feature information; and the second and fifth feature information are analyzed and processed to obtain the first feature information corresponding to each fourth location information. This embodiment of the application, by selecting the smaller area from the third and fourth feature information to determine the first feature information, ensures that small targets are not ignored when partially overlapping with large targets, thereby improving the accuracy of small target identification.

[0082] In some embodiments, the first feature information is obtained by analyzing and processing the second and fifth feature information using a sixth analysis model, wherein the sixth analysis model is: S6 represents the first feature information, S7 represents the fifth feature information, γ7 represents the ninth parameter, and γ8 represents the tenth parameter.

[0083] In this embodiment, the ninth and tenth parameters can be set according to actual needs. In some embodiments, 0 < γ7 ≤ 1, 0 < γ8 ≤ 1. Optionally, γ7 = 1, γ8 = 1, then the fifth analysis model is:

[0084] S402. Based on the first location information, the second location information, and the object location information, determine the target recognition result information.

[0085] In this embodiment, the first location information and the second location information corresponding to the first location information are determined based on the object location information and the object score information. The target recognition result information is determined based on the first location information, the second location information and the object location information. This can avoid the problem of inaccurate recognition results caused by repeated recognition of the same target during target recognition and improve the accuracy of target recognition results.

[0086] In some embodiments, the step of determining target recognition result information based on first location information, second location information, and object location information specifically includes: determining sixth location information based on first location information and second location information; determining sixth location information based on first location information, second location information, and updated object location information; and determining the sixth location information and the second score information corresponding to the sixth location information as target recognition result information.

[0087] In this embodiment, the sixth position information is the position information that needs to be retained by filtering the object position information based on the first position information and the second position information. The second score information is the score information corresponding to the sixth position information in the object score information. This embodiment determines the sixth position information based on the first position information, the second position information and the updated object position information, which can avoid the problem of inaccurate recognition results caused by repeated recognition of the same target during target recognition and improve the accuracy of target recognition results.

[0088] In some embodiments, the step of determining the sixth location information based on the first location information, the second location information, and the updated object location information specifically includes: determining the sixth location information based on the first location information and the second location information; determining the seventh location information and the eighth location information corresponding to the seventh location information based on the updated object location information and the object score information; determining the seventh location information as the new first location information and the eighth location information as the new second location information, and continuing to perform the step of updating the object location information based on the first location information and the second location information to obtain the updated object location information, until the number of third location information contained in the updated object location information is less than or equal to the second threshold.

[0089] In this embodiment, when updating the object location information based on the first and second location information, the first and second location information can be removed from the object location information. This reduces the amount of object location information, thereby reducing the computational load in subsequent iterations and improving the efficiency of target recognition. The second threshold can be set according to actual needs. For example, the second threshold can be set to 0, so that the iteration process ends when the object location information no longer contains the third location information. This allows all the location information that needs to be retained to be filtered out from the object location information, improving the accuracy of the target recognition result.

[0090] Furthermore, the seventh location information is the location information where the first score information corresponding to the updated object location information satisfies the first condition, and the eighth location information is the location information where the overlap between the region corresponding to the seventh location information and the updated object location information is greater than the first threshold. The step of determining the seventh location information and the eighth location information corresponding to the seventh location information based on the updated object location information and object score information is the same as the step of determining the first location information and the second location information corresponding to the first location information based on the object location information and object score information in the aforementioned step S401. Specifically, refer to the aforementioned step S401; this embodiment will not repeat the details here. This embodiment determines the final location information to be retained through multiple iterative iterations, which can avoid the problem of inaccurate recognition results caused by repeated recognition of the same target during target recognition, thereby improving the accuracy of target recognition results.

[0091] In some embodiments, the step of determining the sixth position information based on the first position information and the second position information specifically includes: determining at least one ninth position information from the second position information based on the third score information corresponding to the second position information; determining the first position information as the sixth position information if the feature value of the third feature information corresponding to the first position information is greater than or equal to the feature value of the fifth feature information corresponding to each ninth position information; and / or determining the sixth position information from at least one ninth position information if the feature value of the third feature information corresponding to the first position information is less than the feature value of the fifth feature information corresponding to any ninth position information.

[0092] In this embodiment of the application, at least one ninth position information is a second position information whose score value of the corresponding third score information is greater than a third threshold. The third score information is the score information corresponding to the ninth position information in the object score information. The third threshold can be set according to actual needs. For example, the third threshold can be set to 0.8, then at least one ninth position information is a second position information whose score value of the corresponding third score information is greater than 0.8.

[0093] Furthermore, the third feature information can characterize the area of ​​the region corresponding to the first location information, and the fifth feature information can characterize the area of ​​the region corresponding to each ninth location information. The process for determining the third feature information has been discussed in the preceding steps. The process for determining the fifth feature information is the same as that for the third feature information, and can be referred to the aforementioned process for determining the third feature information. This embodiment will not repeat the details here. In this embodiment, if the feature value of the third feature information corresponding to the first location information is greater than or equal to the feature value of the fifth feature information corresponding to each ninth location information, it indicates that the area of ​​the region corresponding to the first location information is greater than or equal to the area of ​​the region corresponding to each ninth location information. In this case, the first location information is determined as the location information to be retained. Conversely, if the feature value of the third feature information corresponding to the first location information is less than the feature value of the fifth feature information corresponding to any ninth location information, it indicates that there is a ninth location information among at least one ninth location information whose corresponding area is greater than the area of ​​the region corresponding to the first location information. In this case, the sixth location information is determined from at least one ninth location information. That is, the sixth location information is the location information with the larger corresponding area among the first and ninth location information. By selecting the location information with the larger area among the first and ninth location information as the sixth location information, the accuracy of target recognition can be improved.

[0094] Optionally, when determining the sixth position information from at least one ninth position information, the ninth position information with the largest corresponding area among the at least one ninth position information can be determined as the sixth position information, or any ninth position information whose corresponding area is greater than the area of ​​the corresponding area of ​​the first position information can be selected as the sixth position information. This embodiment does not limit this.

[0095] In some embodiments, after analyzing and processing the first recognition result information to obtain target recognition result information, the process includes: cropping the first image information based on the target recognition result information to obtain fifth image information; and performing recognition processing on the fifth image information to obtain image recognition result information.

[0096] In this embodiment of the application, when cropping the first image information based on the target recognition result information, the position information of the object to be recognized in the first image information can be determined from the target recognition result information. Based on the position information of the object to be recognized in the first image information, the first image information is cropped to obtain the fifth image information containing the object to be recognized. For example, referring to... Figure 7 and Figure 8 As shown, it is necessary to... Figure 7 When recognizing the barcode selected in the middle frame, the aforementioned steps S201 to S203 can be used to obtain... Figure 7The target recognition result information is then used to determine the selected barcode within the target recognition result information. Figure 7 The location information in the image is used to crop the first image information, thus obtaining... Figure 8 The image shown contains the fifth image information, which includes a barcode.

[0097] Furthermore, after obtaining the fifth image information, algorithms such as template matching, feature extraction, and deep learning can be used to process and recognize the fifth image information, thereby obtaining image recognition results. For example, when the fifth image information is a region image containing a barcode, a template matching algorithm can be used to process and recognize the fifth image information, thereby obtaining the barcode information.

[0098] In some embodiments, after analyzing and processing the first identification result information to obtain target identification result information, the method further includes: outputting the target identification result information; receiving a user's adjustment instruction for the target identification result information; and adjusting the target identification result information based on the adjustment instruction, thereby enabling operations such as adding, deleting, or modifying the target identification result information. For example, refer to... Figure 9 As shown, plotting the target recognition results onto the display interface yields the following results: Figure 9 The interface shown allows you to add, delete, or modify target recognition results. Clicking the "Save" button will save the modified results to the appropriate path. To modify the saved results again, click the "Open File" button to display them on the interface once more.

[0099] In summary, the data processing method provided in this implementation scheme obtains first image information, performs target recognition on the first image information to obtain first recognition result information, and analyzes and processes the first recognition result information to obtain target recognition result information. This scheme achieves automatic target recognition and avoids the problem of inaccurate recognition results caused by repeated recognition of the same target, thus improving the efficiency and accuracy of target recognition. Furthermore, segmenting the first image information to obtain multiple second image information, and performing target recognition on each of the multiple second image information to obtain the first recognition result information, reduces the consumption of computing resources and computing time, and improves the accuracy of small target recognition. Even further, determining the first position information and the corresponding second position information based on object position information and object score information, and determining the target recognition result information based on the first position information, second position information, and object position information, ensures that small targets are not ignored when partially overlapping with large targets, further improving the accuracy of small target recognition.

[0100] To better implement the data processing method in the embodiments of this application, a data processing system is also provided in the embodiments of this application, such as... Figure 10 As shown, the data processing system 600 includes:

[0101] Information acquisition module 610 is used to acquire first image information;

[0102] The target recognition module 620 is used to perform target recognition on the first image information to obtain first recognition result information;

[0103] The data processing module 630 is used to analyze and process the first recognition result information to obtain the target recognition result information.

[0104] In this embodiment of the application, target recognition is performed on the first image information to obtain the first recognition result information, and then the first recognition result information is analyzed and processed to obtain the target recognition result information. This can realize automatic target recognition and avoid the problem of inaccurate recognition results caused by repeated recognition of the same target, thereby improving the efficiency and accuracy of target recognition.

[0105] In some embodiments of this application, the first identification result information includes object location information and object score information. The data processing module 630 analyzes and processes the first identification result information to obtain target identification result information, including:

[0106] Based on object location information and object score information, determine the first location information and the second location information corresponding to the first location information;

[0107] Based on the first location information, the second location information, and the object location information, the target recognition result information is determined.

[0108] In some embodiments of this application, the object location information includes multiple third location information, and the object score information includes first score information corresponding to each third location information. The data processing module 630 determines the first location information and the second location information corresponding to the first location information based on the object location information and the object score information, including:

[0109] Based on the first score information corresponding to each third position information, the first position information is determined from multiple third position information;

[0110] Based on the first location information, the first feature information corresponding to each of the multiple fourth location information is determined; the multiple fourth location information are other location information besides the first location information among the multiple third location information.

[0111] Based on the first feature information, multiple fourth position information are filtered to obtain the second position information corresponding to the first position information; the second position information is the fourth position information whose feature value of the corresponding first feature information is greater than the first threshold.

[0112] In some embodiments of this application, the data processing module 630 determines, based on the first location information, the first feature information corresponding to each of the plurality of fourth location information, including:

[0113] Based on the first position information and each fourth position information, determine the second feature information corresponding to each fourth position information;

[0114] The first location information is processed to obtain the third feature information; the third feature information is used to characterize the area of ​​the region corresponding to the first location information.

[0115] Each fourth location information is processed to obtain the fourth feature information corresponding to each fourth location information; the fourth feature information is used to characterize the area of ​​the region corresponding to each fourth location information.

[0116] Based on the second feature information, the third feature information, and the fourth feature information, the first feature information corresponding to each fourth position information is determined.

[0117] In some embodiments of this application, the data processing module 630 determines the second feature information corresponding to each fourth location information based on the first location information and each fourth location information, including:

[0118] The first position information and each fourth position information are analyzed and processed to obtain the fifth position information corresponding to each fourth position information; the fifth position information is used to characterize the position of the intersection region corresponding to the first position information and the fourth position information.

[0119] Based on the fifth position information, determine the second feature information corresponding to each fourth position information; and / or,

[0120] The data processing module 630 determines the first feature information corresponding to each fourth location information based on the second feature information, the third feature information, and the fourth feature information, including:

[0121] If the feature value corresponding to the third feature information is greater than or equal to the feature value corresponding to the fourth feature information, the fourth feature information is determined as the fifth feature information; and / or,

[0122] If the feature value corresponding to the third feature information is less than the feature value corresponding to the fourth feature information, the third feature information is determined as the fifth feature information;

[0123] The second and fifth feature information are analyzed and processed to obtain the first feature information corresponding to each fourth position information.

[0124] In some embodiments of this application, the fifth location information includes a first location value, a second location value, a third location value, and a fourth location value. Based on the fifth location information, the data processing module 630 determines the second feature information corresponding to each fourth location value, including:

[0125] The first and second position values ​​are analyzed and processed to obtain the fifth position value;

[0126] The first parameter and the fifth position value are analyzed and processed to obtain the sixth position value;

[0127] The third and fourth position values ​​are analyzed and processed to obtain the seventh position value;

[0128] The second parameter and the seventh position value are analyzed and processed to obtain the eighth position value;

[0129] The sixth and eighth position values ​​are analyzed and processed to obtain the second feature information corresponding to each fourth position information.

[0130] In some embodiments of this application, the fifth position value is obtained by analyzing and processing the first position value and the second position value using a first analysis model;

[0131] The first analysis model is: S1 = γ1*x1 - γ2*x2, where S1 represents the fifth position value, x1 represents the first position value, x2 represents the second position value, γ1 represents the third parameter, and γ2 represents the fourth parameter.

[0132] The sixth position value is obtained by analyzing and processing the first parameter and the fifth position value using the second analysis model;

[0133] The second analysis model is: S2 = np.maximum(α, S1), where S2 represents the sixth position value, α represents the first parameter, and np.maximum(·) represents returning the larger value between α and s1;

[0134] The seventh position value is obtained by analyzing and processing the third and fourth position values ​​using the third analysis model;

[0135] The third analysis model is: s3=γ3*y1-γ4*y2, where S3 represents the seventh position value, y1 represents the third position value, y2 represents the fourth position value, γ3 represents the fifth parameter, and γ4 represents the sixth parameter.

[0136] The eighth position value is obtained by analyzing and processing the second parameter and the seventh position value through the fourth analysis model;

[0137] The fourth analysis model is: S4 = np.maximum(β, S3), where S4 represents the value at the eighth position, β represents the second parameter, and np.maximum(·) means returning the larger of β and S3;

[0138] The second feature information is obtained by analyzing and processing the sixth and eighth position values ​​through the fifth analysis model;

[0139] The fifth analysis model is: S5 = γ5 * S2 * γ6 * S4, where S5 represents the second feature information, γ5 represents the seventh parameter, and γ6 represents the eighth parameter.

[0140] The first feature information is obtained by analyzing and processing the second and fifth feature information through the sixth analysis model;

[0141] The sixth analytical model is as follows: S6 represents the first feature information, S7 represents the fifth feature information, γ7 represents the ninth parameter, and γ8 represents the tenth parameter.

[0142] In some embodiments of this application, the data processing module 630 determines target recognition result information based on the first location information, the second location information, and the object location information, including:

[0143] The object location information is updated based on the first location information and the second location information to obtain the updated object location information;

[0144] Based on the first location information, the second location information, and the updated object location information, the sixth location information is determined;

[0145] The sixth position information and the second score information corresponding to the sixth position information are determined as the target recognition result information.

[0146] In some embodiments of this application, the data processing module 630 determines the sixth location information based on the first location information, the second location information, and the updated object location information, including:

[0147] Based on the first and second location information, the sixth location information is determined;

[0148] Based on the updated object location information and object score information, determine the seventh location information and the eighth location information corresponding to the seventh location information;

[0149] The seventh position information is determined as the new first position information and the eighth position information is determined as the new second position information. The process of updating the object position information based on the first and second position information is continued until the number of third position information contained in the updated object position information is less than or equal to the second threshold.

[0150] In some embodiments of this application, the data processing module 630 determines the sixth location information based on the first location information and the second location information, including:

[0151] Based on the third score information corresponding to the second position information, at least one ninth position information is determined from the second position information; at least one ninth position information is a second position information whose score value of the corresponding third score information is greater than a third threshold.

[0152] If the feature value of the third feature information corresponding to the first position information is greater than or equal to the feature value of the fifth feature information corresponding to each ninth position information, the first position information is determined as the sixth position information;

[0153] If the feature value of the third feature information corresponding to the first position information is less than the feature value of the fifth feature information corresponding to any ninth position information, the sixth position information is determined from at least one ninth position information.

[0154] In some embodiments of this application, the target recognition module 620 performs target recognition on the first image information to obtain first recognition result information, including:

[0155] The first image information is segmented to obtain multiple second image information;

[0156] Multiple second image informations are normalized separately to obtain multiple third image informations;

[0157] Multiple third image informations are scaled separately to obtain multiple fourth image informations;

[0158] Multiple fourth image information are input into the target recognition model, and the target recognition model outputs the first recognition result information.

[0159] In some embodiments of this application, after the data processing module 630 analyzes and processes the first identification result information to obtain the target identification result information, the data processing module 630 is further used for:

[0160] The first image information is cropped based on the target recognition result information to obtain the fifth image information;

[0161] The fifth image information is processed to obtain the image recognition result information.

[0162] In some embodiments of this application, the first image information is the image information obtained by the imaging module taking a picture of the target to be identified; the target to be identified includes the back panel of the display device and / or the control board of the smart terminal;

[0163] The first recognition result information includes object location information and object score information; the object location information represents the location information of the object to be recognized in the second image information; the object score information represents the target category information to which the object to be recognized belongs and the score information under the target category information.

[0164] The target recognition result information represents the position information of the object to be identified in the first image information and the target category information to which the object to be identified belongs; the object to be identified includes QR codes, and / or screws, and / or tape, and / or terminals, and / or flexible flat cables;

[0165] The second image information has fewer pixels than the first image information;

[0166] The object location information includes multiple third location information, and the object score information includes the first score information corresponding to each third location information. The first location information is the location information in which the first score information among the multiple third location information satisfies the first condition.

[0167] The second location information is the fourth location information whose feature value corresponding to the first feature information is greater than the first threshold; the first feature information represents the degree of overlap between each fourth location information and the region corresponding to the first location information.

[0168] The fourth location information is the location information other than the first location information among multiple third location information;

[0169] The fifth location information represents the location of the intersection region corresponding to the first and fourth location information;

[0170] The intersection region is the region that overlaps between the region corresponding to the first location information and the region corresponding to the fourth location information.

[0171] The sixth location information is the location information with the larger area corresponding to the first and ninth location information;

[0172] The ninth position information is the second position information whose score value of the corresponding third score information is greater than the third threshold; the third score information is the score information corresponding to the ninth position information in the object score information.

[0173] The seventh location information is the location information in the updated object location information that corresponds to the first score information and satisfies the first condition;

[0174] The eighth location information is the location information in the updated object location information where the overlap between the region corresponding to the seventh location information and the region is greater than the first threshold.

[0175] This application embodiment also provides a computer device, the computer device including:

[0176] One or more processors;

[0177] Memory; and

[0178] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor from the steps of the data processing method in any of the embodiments described above.

[0179] This application also provides a computer device, such as... Figure 11 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0180] The computer device may include components such as a processor 801 with one or more processing cores, a memory 802 with one or more computer-readable storage media, a power supply 803, and an input unit 804. Those skilled in the art will understand that... Figure 11 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0181] The processor 801 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 802, and by calling data stored in the memory 802, thereby providing overall monitoring of the computer device. Optionally, the processor 801 may include one or more processing cores; optionally, the processor 801 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 801.

[0182] The memory 802 can be used to store software programs and modules. The processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 with access to the memory 802.

[0183] The computer device also includes a power supply 803 that supplies power to the various components. Optionally, the power supply 803 can be logically connected to the processor 801 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 803 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0184] The computer device may also include an input unit 804, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0185] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 801 in the computer device loads the executable files corresponding to the processes of one or more application programs into the memory 802 according to the following instructions, and the processor 801 runs the application programs stored in the memory 802 to realize various functions, as follows:

[0186] Obtain the first image information;

[0187] Target recognition is performed on the first image information to obtain the first recognition result information;

[0188] The first identification result information is analyzed and processed to obtain the target identification result information.

[0189] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0190] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the data processing methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps:

[0191] Obtain the first image information;

[0192] Target recognition is performed on the first image information to obtain the first recognition result information;

[0193] The first identification result information is analyzed and processed to obtain the target identification result information.

[0194] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0195] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0196] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0197] The data processing methods, systems, computer devices, and computer-readable storage media provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method, characterized in that, include: Obtain the first image information; Target recognition is performed on the first image information to obtain first recognition result information; The first identification result information is analyzed and processed to obtain the target identification result information.

2. The method according to claim 1, characterized in that, The first identification result information includes object location information and object score information; The step of analyzing and processing the first identification result information to obtain target identification result information includes: Based on the object location information and the object score information, determine the first location information and the second location information corresponding to the first location information; Based on the first location information, the second location information, and the object location information, the target recognition result information is determined.

3. The method according to claim 2, characterized in that, The object location information includes multiple third location information, and the object score information includes first score information corresponding to each of the third location information; The step of determining the first location information and the second location information corresponding to the first location information based on the object location information and the object score information includes: Based on the first score information corresponding to each of the third location information, the first location information is determined from the plurality of third location information; Based on the first location information, first feature information corresponding to each of the plurality of fourth location information is determined; the plurality of fourth location information are other location information besides the first location information among the plurality of third location information. Based on the first feature information, multiple fourth position information are filtered to obtain second position information corresponding to the first position information; the second position information is the fourth position information whose feature value of the corresponding first feature information is greater than a first threshold.

4. The method according to claim 3, characterized in that, The step of determining the first feature information corresponding to each of the plurality of fourth location information based on the first location information includes: Based on the first location information and each of the fourth location information, determine the second feature information corresponding to each of the fourth location information; The first location information is processed to obtain third feature information; the third feature information is used to characterize the area of ​​the region corresponding to the first location information. Each of the fourth location information is calculated and processed to obtain the fourth feature information corresponding to each of the fourth location information; the fourth feature information is used to characterize the area of ​​the region corresponding to each of the fourth location information. Based on the second feature information, the third feature information, and the fourth feature information, the first feature information corresponding to each of the fourth location information is determined.

5. The method according to claim 4, characterized in that, The step of determining the second feature information corresponding to each of the fourth location information based on the first location information and each of the fourth location information includes: The first location information and each of the fourth location information are analyzed and processed to obtain the fifth location information corresponding to each of the fourth location information; the fifth location information is used to characterize the location of the intersection region corresponding to the first location information and the fourth location information. Based on the fifth location information, determine the second feature information corresponding to each of the fourth location information; and / or, The step of determining the first feature information corresponding to each of the fourth location information based on the second feature information, the third feature information, and the fourth feature information includes: If the feature value corresponding to the third feature information is greater than or equal to the feature value corresponding to the fourth feature information, the fourth feature information is determined as the fifth feature information; and / or, If the feature value corresponding to the third feature information is less than the feature value corresponding to the fourth feature information, the third feature information is determined as the fifth feature information; The second feature information and the fifth feature information are analyzed and processed to obtain the first feature information corresponding to each of the fourth position information.

6. The method according to claim 5, characterized in that, The fifth location information includes a first location value, a second location value, a third location value, and a fourth location value; The step of determining the second feature information corresponding to each of the fourth location information based on the fifth location information includes: The first position value and the second position value are analyzed and processed to obtain the fifth position value; The first parameter and the fifth position value are analyzed and processed to obtain the sixth position value; The third and fourth position values ​​are analyzed and processed to obtain the seventh position value; The second parameter and the seventh position value are analyzed and processed to obtain the eighth position value; The sixth position value and the eighth position value are analyzed and processed to obtain the second feature information corresponding to each of the fourth position information.

7. The method according to claim 6, characterized in that, The fifth position value is obtained by analyzing and processing the first position value and the second position value using the first analysis model; Wherein, the first analysis model is: S1=γ1*x1-γ2*x2, s1 represents the fifth position value, x1 represents the first position value, x2 represents the second position value, γ1 represents the third parameter, and γ2 represents the fourth parameter; The sixth position value is obtained by analyzing and processing the first parameter and the fifth position value through the second analysis model; The second analysis model is: S2 = np.maximum(α, S1), where S2 represents the sixth position value, α represents the first parameter, and np.maximum(·) represents returning the larger value between α and S1. The seventh position value is obtained by analyzing and processing the third position value and the fourth position value through the third analysis model; The third analysis model is: S3 = γ3*y1 - γ4*y2, where S3 represents the seventh position value, y1 represents the third position value, y2 represents the fourth position value, γ3 represents the fifth parameter, and γ4 represents the sixth parameter. The eighth position value is obtained by analyzing and processing the second parameter and the seventh position value through the fourth analysis model; The fourth analysis model is: S4 = np.maximum(β, S3), where S4 represents the eighth position value, β represents the second parameter, and np.maximum(·) means returning the larger value between β and S3; The second feature information is obtained by analyzing and processing the sixth position value and the eighth position value through the fifth analysis model; The fifth analysis model is: S5 = γ5 * S2 * γ6 * S4, where S5 represents the second feature information, γ5 represents the seventh parameter, and γ6 represents the eighth parameter. The first feature information is obtained by analyzing and processing the second feature information and the fifth feature information through the sixth analysis model; The sixth analytical model is as follows: S6 represents the first feature information, S7 represents the fifth feature information, γ7 represents the ninth parameter, and γ8 represents the tenth parameter.

8. The method according to claim 2, characterized in that, The step of determining the target recognition result information based on the first location information, the second location information, and the object location information includes: The object location information is updated based on the first location information and the second location information to obtain the updated object location information. Based on the first location information, the second location information, and the updated object location information, the sixth location information is determined; The sixth position information and the second score information corresponding to the sixth position information are determined as target recognition result information.

9. The method according to claim 8, characterized in that, The step of determining the sixth location information based on the first location information, the second location information, and the updated object location information includes: Based on the first location information and the second location information, the sixth location information is determined; Based on the updated object location information and object score information, determine the seventh location information and the eighth location information corresponding to the seventh location information; The seventh location information is determined as the new first location information and the eighth location information is determined as the new second location information. The step of updating the object location information based on the first location information and the second location information to obtain the updated object location information continues until the number of third location information contained in the updated object location information is less than or equal to the second threshold.

10. The method according to claim 9, characterized in that, The step of determining the sixth location information based on the first location information and the second location information includes: Based on the third score information corresponding to the second position information, at least one ninth position information is determined from the second position information; the at least one ninth position information is a second position information whose corresponding third score information score value is greater than a third threshold. If the feature value of the third feature information corresponding to the first location information is greater than or equal to the feature value of the fifth feature information corresponding to each of the ninth location information, the first location information is determined as the sixth location information; and / or, If the feature value of the third feature information corresponding to the first position information is less than the feature value of the fifth feature information corresponding to any of the ninth position information, the sixth position information is determined from at least one of the ninth position information.

11. The method according to claim 1, characterized in that, The step of performing target recognition on the first image information to obtain first recognition result information includes: The first image information is segmented to obtain multiple second image information; The second image information is normalized to obtain the third image information. The multiple third image informations are scaled to obtain multiple fourth image informations; Multiple pieces of the fourth image information are input into the target recognition model, and the target recognition model outputs the first recognition result information.

12. The method according to any one of claims 1 to 11, characterized in that, After analyzing and processing the first identification result information to obtain the target identification result information, the process includes: Based on the target recognition result information, the first image information is cropped to obtain the fifth image information; The fifth image information is processed to obtain image recognition result information.

13. The method according to any one of claims 1 to 11, characterized in that, The first image information is the image information obtained by taking a picture of the target to be identified through the imaging module; the target to be identified includes the back panel of the display device and / or the control board of the smart terminal. The first recognition result information includes object location information and object score information; the object location information represents the location information of the object to be identified in the second image information; the object score information represents the target category information to which the object to be identified belongs and the score information under the target category information. The target recognition result information represents the location information of the object to be identified in the first image information and the target category information to which the object to be identified belongs; the object to be identified includes QR codes, and / or screws, and / or tape, and / or terminals, and / or flexible flat cables; The second image information has fewer pixels than the first image information; The object location information includes multiple third location information, and the object score information includes first score information corresponding to each of the third location information. The first location information is the location information in which the first score information among the multiple third location information satisfies a first condition. The second location information is the fourth location information whose feature value corresponding to the first feature information is greater than the first threshold; the first feature information represents the degree of overlap between each of the fourth location information and the region corresponding to the first location information. The fourth location information is other location information among the multiple third location information, excluding the first location information; The fifth location information represents the location of the intersection region corresponding to the first location information and the fourth location information; The intersection region is the region that overlaps between the region corresponding to the first location information and the region corresponding to the fourth location information. The sixth location information is the location information with the larger area corresponding to the first location information and the ninth location information; The ninth position information is the second position information whose score value of the corresponding third score information is greater than the third threshold; the third score information is the score information corresponding to the ninth position information in the object score information; The seventh location information is the location information in the updated object location information that corresponds to the first score information and satisfies the first condition; The eighth location information is the location information in the updated object location information where the degree of overlap between the region corresponding to the seventh location information and the seventh location information is greater than the first threshold.

14. A system, characterized in that, include: The information acquisition module is used to acquire the first image information; The target recognition module is used to perform target recognition on the first image information to obtain first recognition result information; The data processing module is used to analyze and process the first recognition result information to obtain target recognition result information; Optionally, the first recognition result information includes object location information and object score information. The data processing module analyzes and processes the first recognition result information to obtain target recognition result information, including: Based on the object location information and the object score information, determine the first location information and the second location information corresponding to the first location information; Based on the first location information, the second location information, and the object location information, the target recognition result information is determined; Optionally, the object location information includes multiple third location information, the object score information includes first score information corresponding to each of the third location information, and the data processing module determines the first location information and the second location information corresponding to the first location information based on the object location information and the object score information, including: Based on the first score information corresponding to each of the third location information, the first location information is determined from the plurality of third location information; Based on the first location information, first feature information corresponding to each of the plurality of fourth location information is determined; the plurality of fourth location information are other location information besides the first location information among the plurality of third location information. Based on the first feature information, multiple fourth position information are filtered to obtain second position information corresponding to the first position information; the second position information is the fourth position information whose feature value of the corresponding first feature information is greater than a first threshold. Optionally, the data processing module determines, based on the first location information, first feature information corresponding to each of the plurality of fourth location information, including: Based on the first location information and each of the fourth location information, determine the second feature information corresponding to each of the fourth location information; The first location information is processed to obtain third feature information; the third feature information is used to characterize the area of ​​the region corresponding to the first location information. Each of the fourth location information is calculated and processed to obtain the fourth feature information corresponding to each of the fourth location information; the fourth feature information is used to characterize the area of ​​the region corresponding to each of the fourth location information. Based on the second feature information, the third feature information, and the fourth feature information, determine the first feature information corresponding to each of the fourth location information; Optionally, the data processing module determines the second feature information corresponding to each of the fourth location information based on the first location information and each of the fourth location information, including: The first location information and each of the fourth location information are analyzed and processed to obtain the fifth location information corresponding to each of the fourth location information; the fifth location information is used to characterize the location of the intersection region corresponding to the first location information and the fourth location information. Based on the fifth location information, determine the second feature information corresponding to each of the fourth location information; and / or, The data processing module determines the first feature information corresponding to each of the fourth location information based on the second feature information, the third feature information, and the fourth feature information, including: If the feature value corresponding to the third feature information is greater than or equal to the feature value corresponding to the fourth feature information, the fourth feature information is determined as the fifth feature information; and / or, If the feature value corresponding to the third feature information is less than the feature value corresponding to the fourth feature information, the third feature information is determined as the fifth feature information; The second feature information and the fifth feature information are analyzed and processed to obtain the first feature information corresponding to each of the fourth position information; Optionally, the fifth location information includes a first location value, a second location value, a third location value, and a fourth location value. Based on the fifth location information, the data processing module determines second feature information corresponding to each of the fourth location values, including: The first position value and the second position value are analyzed and processed to obtain the fifth position value; The first parameter and the fifth position value are analyzed and processed to obtain the sixth position value; The third and fourth position values ​​are analyzed and processed to obtain the seventh position value; The second parameter and the seventh position value are analyzed and processed to obtain the eighth position value; The sixth position value and the eighth position value are analyzed and processed to obtain the second feature information corresponding to each of the fourth position information; Optionally, the fifth position value is obtained by analyzing and processing the first position value and the second position value using a first analysis model; Wherein, the first analysis model is: S1=γ1*x1-γ2*x2, s1 represents the fifth position value, x1 represents the first position value, x2 represents the second position value, γ1 represents the third parameter, and γ2 represents the fourth parameter; The sixth position value is obtained by analyzing and processing the first parameter and the fifth position value through the second analysis model; The second analysis model is: S2 = np.maximum(α, S1), where S2 represents the sixth position value, α represents the first parameter, and np.maximum(·) represents returning the larger value between α and S1. The seventh position value is obtained by analyzing and processing the third position value and the fourth position value through the third analysis model; The third analysis model is: S3 = γ3*y1 - γ4*y2, where S3 represents the seventh position value, y1 represents the third position value, y2 represents the fourth position value, γ3 represents the fifth parameter, and γ4 represents the sixth parameter. The eighth position value is obtained by analyzing and processing the second parameter and the seventh position value through the fourth analysis model; The fourth analysis model is: S4 = np.maximum(β, S3), where S4 represents the eighth position value, β represents the second parameter, and np.maximum(·) means returning the larger value between β and S3; The second feature information is obtained by analyzing and processing the sixth position value and the eighth position value through the fifth analysis model; The fifth analysis model is: S5 = γ5 * S2 * γ6 * S4, where S5 represents the second feature information, γ5 represents the seventh parameter, and γ6 represents the eighth parameter. The first feature information is obtained by analyzing and processing the second feature information and the fifth feature information through the sixth analysis model; The sixth analytical model is as follows: S6 represents the first feature information, S7 represents the fifth feature information, γ7 represents the ninth parameter, and γ8 represents the tenth parameter; Optionally, the data processing module determines target recognition result information based on the first location information, the second location information, and the object location information, including: The object location information is updated based on the first location information and the second location information to obtain the updated object location information. Based on the first location information, the second location information, and the updated object location information, the sixth location information is determined; The sixth position information and the second score information corresponding to the sixth position information are determined as target recognition result information; Optionally, the data processing module determines sixth location information based on the first location information, the second location information, and the updated object location information, including: Based on the first location information and the second location information, the sixth location information is determined; Based on the updated object location information and object score information, determine the seventh location information and the eighth location information corresponding to the seventh location information; The seventh position information is determined as the new first position information and the eighth position information is determined as the new second position information. The step of updating the object position information based on the first position information and the second position information to obtain the updated object position information continues until the number of third position information contained in the updated object position information is less than or equal to the second threshold. Optionally, the data processing module determines the sixth location information based on the first location information and the second location information, including: Based on the third score information corresponding to the second position information, at least one ninth position information is determined from the second position information; the at least one ninth position information is a second position information whose corresponding third score information score value is greater than a third threshold. If the feature value of the third feature information corresponding to the first location information is greater than or equal to the feature value of the fifth feature information corresponding to each of the ninth location information, the first location information is determined as the sixth location information; and / or, If the feature value of the third feature information corresponding to the first position information is less than the feature value of the fifth feature information corresponding to any of the ninth position information, the sixth position information is determined from at least one of the ninth position information. Optionally, the target recognition module performs target recognition on the first image information to obtain first recognition result information, including: The first image information is segmented to obtain multiple second image information; The second image information is normalized to obtain the third image information. The multiple third image informations are scaled to obtain multiple fourth image informations; The fourth image information is input into the target recognition model, and the first recognition result information is output through the target recognition model. Optionally, after the data processing module analyzes and processes the first recognition result information to obtain the target recognition result information, the data processing module is further configured to: Based on the target recognition result information, the first image information is cropped to obtain the fifth image information; The fifth image information is processed to obtain image recognition result information; Optionally, the first image information is image information obtained by taking a picture of the target to be identified through the imaging module; the target to be identified includes the back panel of the display device and / or the control board of the smart terminal; The first recognition result information includes object location information and object score information; the object location information represents the location information of the object to be identified in the second image information; the object score information represents the target category information to which the object to be identified belongs and the score information under the target category information. The target recognition result information represents the location information of the object to be identified in the first image information and the target category information to which the object to be identified belongs; the object to be identified includes QR codes, and / or screws, and / or tape, and / or terminals, and / or flexible flat cables; The second image information has fewer pixels than the first image information; The object location information includes multiple third location information, and the object score information includes first score information corresponding to each of the third location information. The first location information is the location information in which the first score information corresponding to the multiple third location information satisfies a first condition. The second location information is the fourth location information whose feature value corresponding to the first feature information is greater than the first threshold; the first feature information characterizes the degree of overlap between each fourth location information and the region corresponding to the first location information; The fourth location information is other location information among the multiple third location information, excluding the first location information; The fifth location information represents the location of the intersection region corresponding to the first location information and the fourth location information; The intersection region is the region that overlaps between the region corresponding to the first location information and the region corresponding to the fourth location information. The sixth location information is the location information with the larger corresponding area between the first location information and the ninth location information; The ninth position information is the second position information whose score value of the corresponding third score information is greater than the third threshold; the third score information is the score information corresponding to the ninth position information in the object score information; The seventh location information is the location information in the updated object location information where the corresponding first score information satisfies the first condition; The eighth location information is the location information in the updated object location information where the overlap between the region corresponding to the seventh location information and the location information is greater than the first threshold.

15. A device, characterized in that, The device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to perform the steps of the method according to any one of claims 1 to 13.

Images