A method and apparatus for data acquisition and processing targeting a preset object

Abstract

This application provides a method and apparatus for data acquisition and processing of a preset object. The method includes: receiving an image of the preset object sent by a terminal; the image of the preset object is an image acquired by the terminal in a preset activity area; recognizing the image to obtain feature information of the preset object; sending the feature information of the preset object and the corresponding image to a blockchain database; the blockchain database is used to store the feature information of the preset object and the corresponding image. Through automated acquisition and recognition of preset object data, the reliability and efficiency of data acquisition are achieved, and the on-chain operation of information credentials for the preset object ensures the validity of the data and provides valid information credentials for subsequent data processing.

Description

Technical Field

[0001] This application relates to the field of computer application technology, and in particular to a data acquisition method and a data acquisition device for a preset object, as well as a data processing method and a data processing device for a preset object. Background Technology

[0002] With societal development, an increasing number of means of production have been generated. Asset certification is a common service in social activities, allowing businesses to apply for loans based on certified assets, thereby expanding their operations.

[0003] In the agricultural context, for insurance companies or banks, the difficulty in accurately obtaining data on the scale of farmers' livestock farming poses a certain risk to lending to farmers, or they may choose not to lend to individual farmers (i.e., small investors). Therefore, lending to farmers has become an issue that needs to be addressed.

[0004] The existing methods for inventorying livestock assets on the market are as follows: one is operated by the borrowing farmers, for example, the borrowing farmers take photos of their own livestock and upload them, or directly fill in data on livestock information and upload it to record in a general information system; the other is that animal protection personnel or loan officers visit the borrowing farmers' homes to conduct on-site inspections and check the number of livestock raised by the borrowing farmers to verify the actual situation.

[0005] However, having borrowing farmers fill out and upload data regarding their own livestock raises concerns about the possibility of data exaggeration and falsification, resulting in low accuracy. Furthermore, since the uploaded data is from a standard information system, it is susceptible to tampering. In other words, data from general information systems cannot be effectively utilized in real-world financial scenarios. Secondly, having animal protection personnel or loan officers conduct on-site inspections and audits of borrowing farmers requires significant human resources and carries the risk of collusion between borrowing farmers and auditors to fabricate data, or the borrowing of livestock from neighbors or other sources to impersonate their own. Summary of the Invention

[0006] In view of the above problems, embodiments of this application are proposed to provide a data acquisition method and a corresponding data acquisition device for a preset object that overcomes or at least partially solves the above problems, as well as a data processing method and a corresponding data processing device for a preset object.

[0007] To address the aforementioned issues, this application discloses a data collection method for a preset object, applied in a cloud environment. The cloud environment is connected to both a terminal and a blockchain database. The method includes:

[0008] Receive an image of the preset object sent by the terminal;

[0009] The image for the preset object is an image captured by the terminal in a preset activity area;

[0010] The image is identified to obtain the feature information of the preset object;

[0011] The feature information and corresponding image of the preset object are sent to the blockchain database; the blockchain database is used to store the feature information and corresponding image of the preset object.

[0012] Optionally, the image for the preset object includes multiple frames of images captured by the terminal over multiple time periods; the feature information includes quantity information; the step of recognizing the image to obtain the feature information of the preset object includes:

[0013] The quantity information of the preset objects is identified from the multiple frames of images corresponding to each time period.

[0014] Optionally, sending the feature information and corresponding image of the preset object to the blockchain database includes:

[0015] Generate the current information credential from the currently received image of the preset object and the currently identified quantity information of the preset object;

[0016] Send the current information credential to the blockchain database.

[0017] This application also discloses a data processing method for a preset object, applied to a service platform, wherein the service platform is connected to a preset designated platform and a blockchain database, and the method includes:

[0018] Receive information retrieval requests for the preset object sent by the preset designated platform;

[0019] In response to the information acquisition request, the system retrieves the feature information of the preset object and its corresponding image from the blockchain database; the blockchain database includes the feature information of the preset object and its corresponding image.

[0020] The feature information of the preset object and the corresponding image are sent to the preset designated platform to perform the corresponding operation.

[0021] Optionally, the feature information includes quantity information; obtaining the quantity information of the preset object and the corresponding image from the blockchain database includes:

[0022] The information credentials of the preset object are obtained from the blockchain database; the information credentials include multiple sets of quantity information of the preset object and corresponding images.

[0023] Optionally, sending the feature information of the preset object and the corresponding image to the preset designated platform includes:

[0024] Determine whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions;

[0025] If the preset judgment condition is met, the quantity information of the preset object and the corresponding image are sent to the preset designated platform.

[0026] Optionally, the corresponding image of the preset object includes multiple frames of images collected over multiple time periods, and the quantity information of the preset object includes multiple quantity information identified from the multiple frames of images collected over multiple time periods; the step of determining whether the quantity information of the preset object and the corresponding image meet the preset determination conditions includes:

[0027] Determine whether multiple quantity information identified in multiple frames of images across multiple time periods falls within a preset quantity range;

[0028] If multiple quantity information identified in multiple frames of images across multiple time periods falls within the preset quantity range, then it is determined that the preset judgment condition is met.

[0029] Optionally, it also includes:

[0030] Monitor the quantity information and corresponding images of the preset objects sent to the preset designated platform, and then monitor the updated quantity information and corresponding images.

[0031] An anomaly notification is generated when at least one of the updated quantity information is detected, and / or an anomaly is detected in the image corresponding to at least one of the updated quantity information;

[0032] The exception notification is sent to the preset designated platform; the exception notification is used to report the exception data for the preset object to the preset designated platform.

[0033] This application also discloses a data acquisition device for a preset object, applied in a cloud, wherein the cloud is connected to a terminal and a blockchain database respectively, and the device includes:

[0034] An image receiving module is used to receive an image of the preset object sent by the terminal; the image of the preset object is an image captured by the terminal in a preset activity area.

[0035] An image recognition module is used to recognize the image and obtain the feature information of the preset object;

[0036] An image sending module is used to send the feature information of the preset object and the corresponding image to the blockchain database; the blockchain database is used to store the feature information of the preset object and the corresponding image.

[0037] Optionally, the image for the preset object includes multiple frames of images captured by the terminal over multiple time periods; the feature information includes quantity information; the image recognition module includes:

[0038] The image recognition submodule is used to identify the quantity information of the preset object from multiple frames of images corresponding to each time period.

[0039] Optionally, the image sending module includes:

[0040] The information credential generation submodule is used to generate the current information credential from the currently received image of the preset object and the currently identified quantity information of the preset object.

[0041] The information credential sending submodule is used to send the current information credential to the blockchain database.

[0042] This application also discloses a data processing device for a preset object, applied to a service platform, the service platform being connected to a preset designated platform and a blockchain database respectively, the device comprising:

[0043] The information acquisition request receiving module is used to receive information acquisition requests for the preset object sent by the preset designated platform;

[0044] An information acquisition request response module is used to respond to the information acquisition request and acquire the feature information of the preset object and the corresponding image from the blockchain database; the blockchain database includes the feature information of the preset object and the corresponding image.

[0045] The information sending module is used to send the feature information of the preset object and the corresponding image to the preset designated platform in order to perform corresponding operations.

[0046] Optionally, the feature information includes quantity information; the information acquisition request response module includes:

[0047] The information acquisition submodule is used to obtain information credentials for the preset object from the blockchain database; the information credentials include multiple sets of quantity information of the preset object and corresponding images.

[0048] Optionally, the information sending module includes:

[0049] The condition judgment submodule is used to determine whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions.

[0050] The information sending submodule is used to send the quantity information of the preset object and the corresponding image to the preset designated platform if the preset judgment condition is met.

[0051] Optionally, the corresponding image of the preset object includes multiple frames of images collected over multiple time periods, and the quantity information of the preset object includes multiple quantity information identified from the multiple frames of images collected over multiple time periods; the condition judgment submodule includes:

[0052] The condition judgment unit is used to determine whether multiple quantity information identified in multiple frames of images across multiple time periods falls within a preset quantity range.

[0053] The condition determination unit is used to determine that if multiple quantity information identified in multiple frames of images in multiple time periods is within the preset quantity range, the preset determination condition is met.

[0054] Optionally, it also includes:

[0055] The information monitoring submodule is used to monitor the quantity information and corresponding images of the preset objects sent to the preset designated platform and the updated quantity information and corresponding images thereafter.

[0056] An anomaly notification generation submodule is used to generate an anomaly notification when at least one of the updated quantity information is detected, and / or an anomaly occurs in the image corresponding to at least one of the updated quantity information;

[0057] An exception notification sending submodule is used to send the exception notification to the preset designated platform; the exception notification is used to provide feedback on the exception data for the preset object to the preset designated platform.

[0058] This application also discloses an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the steps of any of the data acquisition methods or data processing methods for a preset object.

[0059] This application also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the data acquisition methods or data processing methods for a preset object.

[0060] The embodiments of this application have the following advantages:

[0061] In this embodiment, the terminal periodically collects images of a preset object and uploads them to the cloud. The cloud then identifies the images to obtain the feature information of the preset object and uploads the identified feature information and the corresponding image as information credentials to the blockchain database. This allows the service platform to retrieve the information credentials from the blockchain database and send them to a designated platform to complete the corresponding data processing operations, provided the feature information of the preset object is stable. Automated collection and identification of preset object data ensures reliable and efficient data collection, and the on-chain operation of the preset object's information credentials guarantees data validity, providing valid information credentials for subsequent data processing. Attached Figure Description

[0062] Figure 1 This is a flowchart illustrating the steps of an embodiment of a data acquisition method for a preset object according to this application;

[0063] Figure 2 This is a flowchart illustrating the steps of an embodiment of a data processing method for a preset object according to this application;

[0064] Figure 3 This is an application scenario diagram of data acquisition and processing of a preset object in an embodiment of this application;

[0065] Figure 4 This is a structural block diagram of an embodiment of a data acquisition device for a preset object according to this application;

[0066] Figure 5 This is a structural block diagram of an embodiment of a data processing device for a preset object according to this application. Detailed Implementation

[0067] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0068] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover inclusion without exclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0069] One of the core concepts of this application embodiment is that after receiving an image containing a preset object sent by a terminal, the cloud can identify the image to obtain the quantity information of the preset object, and send the identified quantity information and the corresponding original image to the blockchain database to be stored as data credentials in the blockchain database; when the service platform receives an information retrieval request for the preset object sent by a preset designated platform, it can directly obtain multiple consecutive sets of quantity information for the preset object from the blockchain database storing the data credentials, and judge the stability of the multiple consecutive sets of quantity information. If the quantity information is stable, it sends information credentials to the preset designated platform for corresponding data processing operations.

[0070] Reference Figure 1 This document illustrates a flowchart of an embodiment of a data collection method for a preset object, applicable to a cloud environment. The cloud environment is connected to both a terminal and a blockchain database, and the method may specifically include the following steps:

[0071] Step 101: Receive an image of the preset object sent by the terminal; the image of the preset object is an image captured by the terminal in a preset activity area;

[0072] In one embodiment of this application, the cloud can receive an image of a preset object sent by a terminal. The image of the preset object can be an image captured by the terminal in a preset activity area of ​​the preset object, so that the cloud can perform image detection on the received image and save it to the blockchain database.

[0073] In practical applications, the terminal can periodically collect images or videos of the activity area of ​​a preset object and transmit them to the cloud to automate the data collection of the preset object. In the field of animal husbandry, the preset object can be livestock, such as pigs, cattle, and sheep. Correspondingly, the activity area of ​​the preset object can be the usual activity range of the livestock. In this case, the terminal used to collect images or videos can take pictures of the livestock from different angles within the activity range.

[0074] It should be noted that the terminal used to capture images or videos can be a camera device, or a terminal device with a camera component and camera function; and the video captured by the terminal can be a complete video stitched together from different angles, which is not limited in this application embodiment.

[0075] In a preferred embodiment, a communication connection can be established between the cloud and the terminal, allowing the cloud to receive images of a preset object sent by the terminal. This communication connection can be established through registration between the terminal and the cloud. Specifically, the terminal first obtains its own verification information from a registration server corresponding to the cloud, and then registers itself and its verification information with the cloud through the registration server. After registration, the cloud returns the registered verification information to the registered terminal through the registration server. Finally, the registered terminal can securely communicate with the cloud using the returned registered verification information. In this embodiment, the registered terminal can send the collected images to the cloud using the returned registered verification information, and the cloud can receive the images sent by the registered terminal through a triplet, allowing the cloud to act as a network node accessing the blockchain network where the blockchain database resides, and storing the received images in the blockchain database.

[0076] Step 102: Recognize the image to obtain the feature information of the preset object;

[0077] After receiving images of preset objects from terminals at regular intervals, the cloud can perform image detection to determine whether the preset objects exist in the images and identify their feature information. This allows for automated identification of the preset object data. The cloud can then send the identified feature information and the corresponding image to a blockchain database for storage. The identified feature information may include the quantity of the preset objects, as well as other information such as their quality.

[0078] In one embodiment of this application, the image for the preset object includes multiple frames of images captured by the terminal over multiple time periods; the feature information includes quantity information; step 102 may include the following sub-steps:

[0079] Sub-step S11 involves identifying the quantity information of the preset objects from the multiple frames of images corresponding to each time period.

[0080] In one embodiment of this application, the image of the preset object may include multiple frames of images collected by the terminal in multiple time periods. That is, the images collected in each time period may include the corresponding multiple frames of images. When recognizing the image of the preset object, the quantity information of the preset object can be identified from the multiple frames of images corresponding to each time period, so as to count and inventory the quantity information in the image of the preset object.

[0081] It should be noted that the time period for collecting the preset images can refer to collecting them once during a certain time period each day, or collecting them multiple times during multiple time periods each day. If the collection period is once a day, the quantity information of the preset objects can be identified from the multiple frames of images collected each day. If the collection period is multiple times a day, the quantity information of the preset objects in the multiple frames of images collected each day can be identified first, and then the quantity information of the preset objects collected that day can be determined based on the preset objects in the multiple frames of images collected each day. Finally, the quantity information of the preset objects in the multiple frames of images collected each day can be identified. This application does not impose any limitations on this aspect.

[0082] In this process, image recognition algorithms can be used to identify preset objects and obtain quantity information for those objects. In the livestock industry, a livestock feature database can be pre-established, containing the general outlines, facial features, and body behavior characteristics of various livestock. This allows image recognition algorithms to identify objects in images. If an identified object matches the feature information of a certain type of livestock in the database, it is determined to be a preset object, and the quantity information for that preset object can then be incremented by one.

[0083] In practical applications, since the images received by the cloud can be pictures or videos, there may be situations where the same preset object appears in different pictures or different video segments within the same time period. That is, the number of preset objects identified by the cloud through image detection or image recognition algorithms may be incorrect due to duplicate recognition of preset objects.

[0084] To avoid the aforementioned data errors, the cloud platform identifies the preset objects in the images from multiple frames corresponding to each time period through image detection or image recognition algorithms and obtains the original quantity information of the preset objects. Then, it performs data cleaning and other processing steps on the original quantity information to obtain valid data, thereby identifying the quantity information of the preset objects in the multiple frames corresponding to each time period, and thus obtaining the real data for the preset objects in each time period.

[0085] Specifically, the multiple frames corresponding to each time period for a preset object can be divided into multiple sets of frame images. Image detection or image recognition algorithms are then performed on each set of frame images to identify the preset object in each set. Target recognition boxes are then drawn for at least one preset object in each set. Data cleaning operations are then performed based on these target recognition boxes to obtain valid data for the target recognition boxes, thus revealing the true quantity information of the preset object. It should be noted that for terminals used to periodically collect images or videos of a preset object, assuming the preset object is livestock, the shooting angle must be aligned with the livestock's usual activity range. Therefore, each set of frame image data can record image data from different angles. In this case, it is permissible for a set of frame image data to lack a target recognition box. This indicates that no livestock exist within the activity range corresponding to that angle in the set of frame image data.

[0086] In one embodiment of this application, assuming that the preset images are collected once a day during a certain time period, the data cleaning operation based on the target recognition bounding boxes for the preset object in each set of images for the multiple frames corresponding to the certain time period may include the following steps:

[0087] (1) Obtain the target recognition box of the previous set of frame images and mark the target recognition box of the previous frame image;

[0088] In practical applications, after dividing the multi-frame images corresponding to each time period for the preset object into multiple groups of frame images, the frame images of each group can be acquired in frame order. Since target recognition boxes have been drawn for multiple preset objects in each group of frame images, the target recognition boxes of the previous group of frame images can be acquired first, and then the target recognition boxes of the previous group of frame images can be marked, so as to perform data cleaning operations on the quantity information of the preset objects based on the marking information of the target recognition boxes of each group of frame images.

[0089] One method for identifying target recognition boxes is to assign an identification ID or identification number to the target recognition box, so as to inventory or count the quantity information of preset objects corresponding to the target recognition box based on the identification information. It should be noted that the method for identifying target recognition boxes is not limited to the identification ID or identification number mentioned above, and the embodiments of this application do not impose such limitations.

[0090] (2) Determine whether there is a target recognition box with an identifier in the next set of frame images;

[0091] Specifically, after identifying the target bounding boxes in the previous set of frame images, the next set of frame images can be obtained based on the previous set of frame images. At this time, in order to perform a data cleaning operation similar to deduplication on the original quantity information of the preset objects, it can be determined whether there are identified target bounding boxes in the next set of frame images.

[0092] In practical applications, when identifying the target recognition box of the previous set of frame images with an identification ID or identification sequence number, the identification information can be directly added to the target recognition box of the previous set of frame images. This ensures that when the next set of frame images is acquired, the same target recognition box in the two sets of frame images has the same identification information.

[0093] It should be noted that in multiple sets of frame images, the previous set of frame images and the next set of frame images can be continuously judged to see if they have an identifier, until the judgment of the last set of frame images in the multiple frames of images collected in that time period is completed.

[0094] (3) If there is no labeled target recognition box in the next set of frame images, then the target recognition box in the next set of frame images is labeled;

[0095] One possible scenario is that when there is no labeled target recognition box in the next set of frame images, it means that there is no target recognition box in the next set of frame images that is the same as that in the previous set of frame images, that is, there is no preset object that is the same as that in the previous set of frame images.

[0096] In this case, there is no need to perform deduplication data cleaning on the original quantity information of the preset objects. Based on the identifier ID or identifier sequence number of the previous set of frame images, all target recognition boxes in the next set of frame images can be identified to complete the automatic recognition operation of the preset objects.

[0097] (4) If there is a labeled target recognition box in the next set of frame images, then the target recognition boxes other than the labeled target recognition box in the next set of frame images are labeled.

[0098] In addition to the situation in (3), a second situation can also occur: when there is a target recognition box with an identifier in the next set of frame images, it means that there is the same target recognition box in the next set of frame images as in the previous set of frame images, that is, there is the same preset object as in the previous frame image.

[0099] In this case, it is necessary to perform a data cleaning operation to remove duplicates from the original quantity information of the preset objects. First, target recognition boxes with identification information can be excluded. Then, based on the identification ID or identification sequence number of the previous set of frame images, the remaining target recognition boxes can be identified to complete the automatic identification and automatic deduplication of the preset objects.

[0100] (5) The number of the preset objects is obtained by using the identifiers of the target recognition boxes in each frame image.

[0101] The target recognition box of each frame image data is identified by identification ID or identification sequence number. After the data cleaning operation of deduplicating the number of preset objects corresponding to the target recognition box in each frame image data, the identification information can be directly obtained. According to the identification ID or identification sequence number in the identification information, the number of preset objects in each frame image data is obtained. This number information is the data after data cleaning of the original number information of preset objects in the images collected in that time period, which is the effective number information of preset objects collected every day.

[0102] It should be noted that the method for cleaning the original quantity information can also be achieved by monitoring the motion trajectory or position information of a preset object in the image, and this application embodiment does not limit this.

[0103] Step 103: Send the feature information of the preset object and the corresponding image to the blockchain database; the blockchain database is used to store the feature information of the preset object and the corresponding image.

[0104] After receiving images of a preset object from a terminal at regular intervals and identifying the object's feature information, the cloud can send the object's feature information and the corresponding original image to the blockchain database. This allows the blockchain database to store the object's feature information and the corresponding image, ensuring the validity of the object's feature information. In a preferred embodiment, after receiving images of a preset object and identifying the corresponding feature information from those images at regular intervals, the cloud can add an index identifier to the received images to match them with the identified feature information.

[0105] The images received by the cloud can be pictures or videos. The feature information identified for the preset object can include the quantity information of the preset object and other information, such as the quality information of the preset object. As an example, when the cloud receives a video image during a certain period of time, and the quantity information and other information of the preset object are identified from the video image, the cloud can add an index identifier A when storing the video image, and also add the same index identifier A to the identified quantity information and other information of the preset object, and save the video image, quantity information and other information with index identifier A to the blockchain database.

[0106] In one embodiment of this application, step 103 may include the following sub-steps:

[0107] Sub-step S21: Generate the current information credential from the currently received image of the preset object and the currently identified quantity information of the preset object;

[0108] Sub-step S22: Send the current information credential to the blockchain database.

[0109] In practical applications, the currently received image of the preset object and the currently identified quantity information of the preset object can be used as the current information credentials, and the current information credentials can be sent to the blockchain database so that the blockchain database can save the information credentials and ensure the validity of the quantity information of the preset object.

[0110] Among them, blockchain databases are a type of open, transparent, and traceable shared database, one of the advantages of which is that they can prevent the recorded data from being tampered with.

[0111] After the cloud sends information credentials for a predefined object to the blockchain database, the cloud essentially becomes a node within the blockchain network. The blockchain can then broadcast the newly recorded information credentials to all nodes within the network, including clients and servers, allowing them to receive and view these credentials. Finally, the cloud saves the information credentials to a specific block in the blockchain database and timestamps that block, automatically arranging all credentials in chronological order to ensure their immutability and validity. It's worth noting that the more information credentials the cloud sends to the blockchain database for a predefined object, the stronger the blockchain's guarantee of their immutability and validity.

[0112] In the embodiments of this application, after receiving an image containing a preset object sent by another terminal, the terminal can identify the image to obtain the quantity information of the preset object, and send the identified quantity information and the corresponding original image to the blockchain database as data credentials. Through automated collection and identification of preset object data, the reliability and efficiency of data collection are achieved, and the on-chain operation of the preset object information credentials ensures the validity of the data, providing valid information credentials for subsequent data processing.

[0113] Reference Figure 2 This document illustrates a flowchart of a data processing method for a preset object according to an embodiment of this application. The method is applied to a service platform connected to a preset designated platform and a blockchain database. Specifically, the method may include the following steps:

[0114] Step 201: Receive an information acquisition request for the preset object sent by the preset designated platform;

[0115] In one embodiment of this application, after recording feature information and corresponding images of a preset object in the blockchain database in the cloud, the service platform can receive an information acquisition request for the preset object sent by a preset designated platform, so as to respond to the information acquisition request and acquire the data required by the preset designated platform.

[0116] Step 202: Respond to the information acquisition request and obtain the feature information and corresponding image of the preset object from the blockchain database; the blockchain database includes the feature information and corresponding image of the preset object.

[0117] After receiving an information retrieval request from a designated platform, the service platform can directly obtain the required feature information and corresponding image of the target object from a blockchain database that stores the feature information and corresponding image of the target object. This allows the designated platform to perform corresponding data processing operations based on the retrieved target object data. The feature information of the target object may include quantity information and other information, such as the quality information of the target object.

[0118] In one embodiment of this application, the feature information includes quantity information; step 202 may include the following sub-steps:

[0119] Sub-step S31: Obtain the information credential of the preset object from the blockchain database; the information credential includes multiple sets of quantity information of the preset object and the corresponding image.

[0120] In practical applications, the cloud can save the quantity information of multiple preset objects and their corresponding images as multiple sets of information credentials to the blockchain database. The blockchain database can automatically arrange the multiple sets of information credentials in chronological order. The service platform can retrieve multiple sets of information credentials for preset objects from the blockchain database in the order of timestamps.

[0121] Specifically, the cloud acts as a node in the blockchain network, writing the quantity information of preset objects and their corresponding images to the blockchain database. The service platform can also connect to the blockchain network and act as another node. Because the blockchain database is open and transparent, the service platform can directly obtain and view the feature information of the preset objects and their corresponding images.

[0122] Step 203: Send the feature information of the preset object and the corresponding image to the preset designated platform to perform the corresponding operation.

[0123] In practical application scenarios, this application embodiment takes the livestock industry as an example. The aforementioned preset object can be livestock, such as pigs, cattle, and sheep. The service platform can be an asset application service platform. The preset designated platform can be a financial service platform of a financial institution such as a bank or insurance company. The corresponding operation can be a bank's lending operation or an animal insurance company's insurance operation. At this time, the asset application service platform can receive an information acquisition request for livestock quantity information sent by the financial service platform of the bank or insurance company, and obtain the livestock quantity information and corresponding images from the blockchain database, so that the bank or insurance company can provide services such as lending or insurance based on the livestock quantity information and corresponding images.

[0124] In one embodiment of this application, step 203 may include the following sub-steps:

[0125] Sub-step S41: Determine whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions;

[0126] In practical applications, in order to send the quantity information of preset objects and the corresponding images to a preset designated platform so that the preset designated platform can perform corresponding data processing operations based on the received quantity information of preset objects and the corresponding images, firstly, the quantity information of preset objects and the corresponding images can be judged to determine whether they meet the preset judgment conditions, so as to determine whether they are stable data required for the corresponding data processing.

[0127] In one embodiment of this application, the corresponding image of the preset object includes multiple frames of images collected over multiple time periods, and the quantity information of the preset object includes multiple quantity information identified from the multiple frames of images collected over multiple time periods; sub-step S41 may include the following sub-steps:

[0128] Sub-step S411: Determine whether the multiple quantity information identified in multiple frames of images across multiple time periods is within a preset quantity range;

[0129] Specifically, it can judge whether multiple quantity information identified in multiple frames of images across multiple time periods is within a preset quantity range. In other words, it can perform stability judgment on multiple quantity information corresponding to multiple frames of images collected across multiple time periods, so that a preset designated platform can perform corresponding data processing operations based on multiple quantity information.

[0130] Sub-step S412: If the multiple quantity information identified in the multiple frames of images in the multiple time periods is within the preset quantity range, then it is determined that the preset judgment condition is met.

[0131] In one embodiment of this application, if multiple quantity information identified in multiple frames of images over multiple time periods is within a preset quantity range, it can be determined that the multiple quantity information meets the preset judgment condition, that is, the multiple quantity information is within a stable range.

[0132] Specifically, whether multiple quantitative information items are within a preset range can be reflected in whether the changing trends of the multiple quantitative information items are stable and whether they stably reach a certain threshold.

[0133] In practical applications, the change values ​​of multiple consecutive quantitative information can be determined, and it can be judged whether the change values ​​are all less than a preset change value, that is, whether the change values ​​of each quantitative information are stable within a certain error. Suppose the acquired data are three consecutive quantitative information A to C, and the quantitative information of A, B, and C are 1002, 1005, and 1008 respectively. The preset change value (i.e., error) is 8. Then, the change value between A and B is 3, the change value between A and C is 6, and the change value between B and C is 3. The change values ​​of multiple consecutive quantitative information for the preset object are all less than the preset change value, which means that the acquired multiple consecutive quantitative information meet one of the indicators of tending to be stable.

[0134] It can also determine the values ​​of multiple consecutive quantity information and judge whether the values ​​of their quantity information all reach the preset quantity threshold, that is, judge whether the values ​​of each quantity information are stable above a certain threshold. Suppose the quantity information of A, B and C are 1002, 1005 and 1008 respectively, and the preset quantity threshold is 1000. Then, the values ​​of the quantity information of A to C all reach 1000. The multiple consecutive quantity information of the preset object all reach the preset quantity threshold, which means that the obtained multiple consecutive quantity information meet another indicator of tending to be stable.

[0135] Sub-step S42: If the preset judgment condition is met, then send the quantity information of the preset object and the corresponding image to the preset designated platform.

[0136] The acquired consecutive quantity information needs to simultaneously meet the above two indicators, indicating that the consecutive quantity information tends to be stable. At this time, multiple information vouchers containing consecutive quantity information for a preset object can be sent to a preset designated platform so that the preset designated platform can perform corresponding data processing operations based on the acquired data of the preset object.

[0137] In one embodiment of this application, step 203 may further include the following sub-steps:

[0138] Sub-step S51 involves monitoring the quantity information and corresponding images updated after sending the quantity information and corresponding images of the preset objects to the preset designated platform.

[0139] In one embodiment of this application, after the quantity information of multiple consecutive targets of a preset object is in a stable state, and multiple credentials containing the quantity information of multiple consecutive targets of the preset object are sent to a preset designated platform, the quantity information of the preset object subsequently written or saved in the blockchain database and the corresponding image can be continuously detected to determine whether there is abnormal data in the subsequently updated quantity information and the corresponding image.

[0140] Sub-step S52: When at least one of the updated quantity information is detected, and / or an anomaly occurs in the image corresponding to at least one of the updated quantity information; generate an anomaly notification.

[0141] Specifically, in one scenario, the change values ​​of quantity information and the numerical values ​​of quantity information among multiple consecutive updated quantity information can be judged. When it is detected that the change values ​​of quantity information for at least two consecutive objects are greater than the preset change value, that is, the change trend of multiple quantity information is unstable, and / or, at least two consecutive objects are less than the preset quantity threshold, it indicates that at least one quantity information in the subsequently updated quantity information is unstable, that is, a data anomaly has occurred.

[0142] In another scenario, an anomaly may occur in the image corresponding to the quantity information of the preset object. When it is detected that at least one original image corresponding to the quantity information in the blockchain database is blacked out, blurred, or missing, and / or at least one original image data does not match the quantity information, it indicates that at least one image in the subsequently updated images is abnormal.

[0143] It should be noted that when either of the above two situations occurs, it indicates an abnormal situation. In this case, an anomaly warning will be generated based on the anomaly and sent to a pre-defined designated platform. The anomaly warning may include the cause of the anomaly, the abnormal data, or a risk alert.

[0144] Sub-step S53: Send the exception notification to the preset designated platform; the exception notification is used to provide feedback on the exception data for the preset object to the preset designated platform.

[0145] In practical application scenarios, this application embodiment takes the livestock industry as an example. The aforementioned preset object can be livestock, such as pigs, cattle, and sheep. The service platform can be an asset application service platform, and the preset designated platform can be a financial service platform of a financial institution such as a bank or insurance company. The corresponding data processing operations can be the lending operations of a bank or the insurance work of an animal insurance company. The information certificate sent by the asset application service platform to the financial service platform can be a certificate used by the bank or animal insurance company for lending or insurance. When the asset application service platform detects an anomaly in the data on the quantity information of livestock, it can generate an anomaly notification. This anomaly notification can include abnormal data on livestock and an anomaly warning, and send the anomaly notification to the financial service platform. After receiving the anomaly notification sent by the asset service platform, the financial service platform of the bank or animal insurance company can conduct a systematic risk assessment of the anomaly. If the assessment result of the bank or animal insurance company is that there is a risk in lending or insurance, it can take measures such as stopping lending or insurance and collecting debts.

[0146] In this embodiment of the invention, the cloud sends the identified quantity information and the corresponding original image to the blockchain database to be stored as data credentials in the blockchain database. When the service platform receives an information acquisition request for a preset object from the designated platform, it can directly obtain multiple sets of quantity information for the preset object from the blockchain database where the data credentials are stored, and judge the stability of the multiple sets of quantity information. If the quantity information is stable, it sends information credentials to the designated platform for corresponding data processing operations.

[0147] Reference Figure 3 This diagram illustrates an application scenario of data collection and processing of a preset object according to an embodiment of this application, which is applied to scenarios where farmers borrow money from banks or purchase insurance from insurance companies.

[0148] In this agricultural scenario, banks or insurance companies can determine the scale of farmers' livestock farming through the following process, which is essentially the method for assessing the livestock assets of borrowers:

[0149] (1) Timed image acquisition: Multiple high-definition cameras can be installed at the farmers' breeding site. Under the premise of ensuring network stability, the shooting angle of the cameras can be aimed at the daily activity area of ​​the livestock. Multiple cameras can be set to correspond to multiple angles, and images or videos can be collected at a time every day.

[0150] (2) Inventory of original assets: The farmer's on-site camera can transmit the collected pictures or videos to the cloud at regular intervals. The cloud can then retain the pictures or videos and use image recognition algorithms to inventory the original assets of the livestock.

[0151] (3) Inventory of effective assets: Effective data can be obtained from the original asset quantity of livestock assets obtained by the algorithm inventory. The effective asset quantity can be obtained through data cleaning and other processing steps.

[0152] (4) On-chaining of valid asset quantity: The cloud can promptly upload the valid asset quantity obtained after data cleaning to the blockchain for storage, and can generate data certificates or information certificates for this transaction. The data certificate can be associated with the original image or video, and the information certificate can simultaneously store the valid asset quantity for this transaction and the corresponding image or video.

[0153] (5) After the asset information has been stable for several consecutive days, the asset application service can use the data certificate information stored in the blockchain, as well as the corresponding original pictures or videos, for bank lending or animal insurance company insurance work.

[0154] (6) When the asset application service detects an anomaly in the farmer's data, it can generate an anomaly notification based on the anomaly data and provide feedback to the bank or insurance company.

[0155] (7) After receiving an abnormal notification from the asset application service, the bank or insurance company can conduct a systematic risk assessment of the abnormal data of the farmer. If the bank or insurance company determines that there is a risk in lending or depositing money to the farmer, it can initiate loan suspension, insurance suspension or collection work against the farmer.

[0156] In this embodiment, unlike existing livestock asset inventory methods on the market, image detection is used daily to automatically collect data on farmers' livestock farming scenes. The image data is then parsed into livestock asset quantities. Furthermore, the asset quantities and corresponding images are stored as credentials on the blockchain, enabling automated collection and identification of livestock assets. This ensures the reliability and efficiency of livestock asset management. The on-chain storage of data or information credentials for livestock assets guarantees their validity, providing effective information credentials for bank lending or insurance company coverage. Secondly, the data on farmers' livestock assets can be monitored. When anomalies are detected, a systematic risk assessment can be conducted to protect the interests of banks or animal insurance companies.

[0157] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0158] Reference Figure 4 This diagram illustrates a structural block diagram of a data acquisition device embodiment for a preset object, applied in the cloud. The cloud is connected to both a terminal and a blockchain database, and may specifically include the following modules:

[0159] Image receiving module 401 is used to receive an image of the preset object sent by the terminal; the image of the preset object is an image captured by the terminal in a preset activity area;

[0160] Image recognition module 402 is used to recognize the image and obtain the feature information of the preset object;

[0161] The image sending module 403 is used to send the feature information of the preset object and the corresponding image to the blockchain database; the blockchain database is used to store the feature information of the preset object and the corresponding image.

[0162] In one embodiment of this application, the image for the preset object includes multiple frames of images captured by the terminal over multiple time periods; the feature information includes quantity information; the image recognition module 402 may include the following sub-modules:

[0163] The image recognition submodule is used to identify the quantity information of the preset object from multiple frames of images corresponding to each time period.

[0164] In one embodiment of this application, the image sending module 403 may include the following sub-modules:

[0165] The information credential generation submodule is used to generate the current information credential from the currently received image of the preset object and the currently identified quantity information of the preset object.

[0166] The information credential sending submodule is used to send the current information credential to the blockchain database.

[0167] Reference Figure 5 This diagram illustrates a structural block diagram of a data processing device embodiment for a preset object, applied to a service platform. The service platform is connected to a preset designated platform and a blockchain database, and may specifically include the following modules:

[0168] The information acquisition request receiving module 501 is used to receive the information acquisition request for the preset object sent by the preset designated platform;

[0169] The information acquisition request response module 502 is used to respond to the information acquisition request and acquire the feature information of the preset object and the corresponding image from the blockchain database; the blockchain database includes the feature information of the preset object and the corresponding image.

[0170] The information sending module 503 is used to send the feature information of the preset object and the corresponding image to the preset designated platform in order to perform corresponding operations.

[0171] In one embodiment of this application, the feature information includes quantity information; the information acquisition request response module 502 may include the following sub-modules:

[0172] The information acquisition submodule is used to obtain information credentials for the preset object from the blockchain database; the information credentials include multiple sets of quantity information of the preset object and corresponding images.

[0173] In one embodiment of this application, the information sending module 503 may include the following sub-modules:

[0174] The condition judgment submodule is used to determine whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions.

[0175] The information sending submodule is used to send the quantity information of the preset object and the corresponding image to the preset designated platform if the preset judgment condition is met.

[0176] In one embodiment of this application, the corresponding image of the preset object includes multiple frames of images collected over multiple time periods, and the quantity information of the preset object includes multiple quantity information identified from the multiple frames of images collected over multiple time periods; the condition judgment submodule may include the following units:

[0177] The condition judgment unit is used to determine whether multiple quantity information identified in multiple frames of images across multiple time periods falls within a preset quantity range.

[0178] The condition determination unit is used to determine that if multiple quantity information identified in multiple frames of images in multiple time periods is within the preset quantity range, the preset determination condition is met.

[0179] In one embodiment of this application, it further includes:

[0180] The information monitoring submodule is used to monitor the quantity information and corresponding images of the preset objects sent to the preset designated platform and the updated quantity information and corresponding images thereafter.

[0181] An anomaly notification generation submodule is used to generate an anomaly notification when at least one of the updated quantity information is detected, and / or an anomaly occurs in the image corresponding to at least one of the updated quantity information;

[0182] An exception notification sending submodule is used to send the exception notification to the preset designated platform; the exception notification is used to provide feedback on the exception data for the preset object to the preset designated platform.

[0183] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0184] This application also provides an electronic device, including:

[0185] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described embodiments of a data acquisition method or a data processing method for a preset object, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0186] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes described above for a data acquisition method or a data processing method for a preset object, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0187] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0188] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0189] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0190] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0192] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0193] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0194] The foregoing has provided a detailed description of a data acquisition method and a data acquisition device for a preset object, as well as a data processing method and a data processing device for a preset object. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and its core ideas. 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 data acquisition method for a preset object, characterized in that, The method is applied in the cloud, whereby the cloud is connected to both the terminal and a blockchain database, and includes: The terminal sends an image of the preset object; the image of the preset object is an image captured by the terminal from different angles in a preset activity area; the image of the preset object includes multiple frames of images captured by the terminal over multiple time periods. The multi-frame images corresponding to each time period of the preset object are divided into multiple groups of frame images, and each group of frame images is an image corresponding to a different angle. Obtain the target recognition box of the previous set of frame images and mark the target recognition box of the previous set of frame images. The target recognition box is drawn by drawing a preset object in each set of frame images. Determine whether there is a labeled target bounding box in the next set of frame images; If there is no labeled target recognition box in the next set of frame images, then the target recognition box in the next set of frame images is labeled. If there is a labeled target recognition box in the next set of frame images, then the target recognition boxes in the next set of frame images other than the labeled target recognition box are labeled; The number of the preset objects is obtained by using the identifiers of the target recognition boxes in each group of frame images; The quantity information of the preset objects and their corresponding images are sent to the blockchain database; the blockchain database is used to store the quantity information of the preset objects and their corresponding images.

2. The method according to claim 1, characterized in that, Sending the quantity information and corresponding image of the preset object to the blockchain database includes: Generate the current information credential from the currently received image of the preset object and the currently identified quantity information of the preset object; Send the current information credential to the blockchain database.

3. A data processing method for a preset object, characterized in that, Applied to a service platform, the service platform being connected to a pre-defined platform and a blockchain database, the method includes: Receive information retrieval requests for the preset object sent by the preset designated platform; In response to the information acquisition request, the system retrieves the quantity information of the preset objects and their corresponding images from the blockchain database. The blockchain database includes the quantity information of the preset objects and their corresponding images. The corresponding images of the preset objects include multiple frames collected over multiple time periods. The quantity information of the preset objects is obtained based on the identification of target boxes in each set of frame images. If the frame image is from the previous set of frame images, the target boxes in the previous set of frame images are identified; if the frame image is from the next set of frame images, the target boxes without the identification are identified. The target boxes are drawn from the preset objects in each set of frame images. Each set of frame images is divided from multiple frames corresponding to each time period, and each set of frame images corresponds to images from different angles. The quantity information of the preset objects and the corresponding images are sent to the preset designated platform to perform the corresponding operations.

4. The method according to claim 3, characterized in that, The step of obtaining the quantity information of the preset objects and their corresponding images from the blockchain database includes: The information credentials of the preset object are obtained from the blockchain database; the information credentials include multiple sets of quantity information of the preset object and corresponding images.

5. The method according to claim 4, characterized in that, Sending the quantity information of the preset objects and the corresponding images to the preset designated platform includes: Determine whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions; If the preset judgment condition is met, the quantity information of the preset object and the corresponding image are sent to the preset designated platform.

6. The method according to claim 5, characterized in that, The quantity information of the preset objects includes multiple quantity information identified from multiple frames of images collected from multiple time periods; The step of determining whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions includes: Determine whether multiple quantity information identified in multiple frames of images across multiple time periods falls within a preset quantity range; If multiple quantity information identified in multiple frames of images across multiple time periods falls within the preset quantity range, then it is determined that the preset judgment condition is met.

7. The method according to claim 5, characterized in that, Also includes: Monitor the quantity information and corresponding images of the preset objects sent to the preset designated platform, and then monitor the updated quantity information and corresponding images. When at least one of the updated quantity information is detected, and / or an anomaly occurs in the image corresponding to at least one of the updated quantity information, an anomaly notification is generated; the anomaly notification is sent to the preset designated platform; the anomaly notification is used to provide feedback on the abnormal data for the preset object to the preset designated platform.

8. A data acquisition device for a preset object, characterized in that, The device is applied in the cloud, wherein the cloud is connected to both the terminal and the blockchain database, and the device includes: An image receiving module is used to receive images of the preset object sent by the terminal; the images of the preset object are images captured by the terminal at different angles in a preset activity area; the images of the preset object include multiple frames of images captured by the terminal in multiple time periods; The image recognition module is used to divide multiple frames corresponding to each time period of the preset object into multiple groups of frames, each group of frames being images from different angles; to obtain the target recognition bounding box of the previous group of frames and to mark the target recognition bounding box of the previous group of frames, wherein the target recognition bounding box is drawn from the preset object in each group of frames; to determine whether there is a marked target recognition bounding box in the next group of frames; if there is no marked target recognition bounding box in the next group of frames, then the target recognition bounding box in the next group of frames is marked; if there is a marked target recognition bounding box in the next group of frames, then the target recognition bounding boxes in the next group of frames other than the marked target recognition bounding box are marked; and to use the marks of the target recognition bounding boxes in each group of frames to count the number of the preset object. An image sending module is used to send the quantity information of the preset objects and the corresponding images to the blockchain database; the blockchain database is used to store the quantity information of the preset objects and the corresponding images.

9. The apparatus according to claim 8, characterized in that, The image sending module includes: The information credential generation submodule is used to generate the current information credential from the currently received image of the preset object and the currently identified quantity information of the preset object. The information credential sending submodule is used to send the current information credential to the blockchain database.

10. A data processing device for a preset object, characterized in that, The device is applied to a service platform, which is connected to a pre-defined platform and a blockchain database, and includes: The information acquisition request receiving module is used to receive information acquisition requests for the preset object sent by the preset designated platform; An information acquisition request response module is used to respond to the information acquisition request and obtain the quantity information of the preset object and the corresponding image from the blockchain database; the blockchain database includes the quantity information of the preset object and the corresponding image. The information sending module is used to send the quantity information of the preset objects and the corresponding images to the preset designated platform in order to perform corresponding operations; The image corresponding to the preset object includes multiple frames of images collected over multiple time periods. The quantity information of the preset object is obtained based on the identification of the target recognition box in each group of frame images. If the frame image is the previous group of frame images, the target recognition box of the previous group of frame images is identified. If the frame image is the next group of frame images, the target recognition box without the identification is identified. The target recognition box is drawn from the preset object in each group of frame images. Each group of frame images is divided into multiple frames corresponding to each time period. Each group of frame images corresponds to images from different angles.

11. The apparatus according to claim 10, characterized in that, The information acquisition request and response module includes: The information acquisition submodule is used to obtain information credentials for the preset object from the blockchain database; the information credentials include multiple sets of quantity information of the preset object and corresponding images.

12. The apparatus according to claim 11, characterized in that, The information sending module includes: The condition judgment submodule is used to determine whether the quantity information of the preset objects and the corresponding images meet the preset judgment conditions. The information sending submodule is used to send the quantity information of the preset object and the corresponding image to the preset designated platform if the preset judgment condition is met.

13. The apparatus according to claim 12, characterized in that, The quantity information of the preset objects includes multiple quantity information identified from multiple frames of images collected from multiple time periods; The condition judgment submodule includes: The condition judgment unit is used to determine whether multiple quantity information identified in multiple frames of images across multiple time periods falls within a preset quantity range. The condition determination unit is used to determine that if multiple quantity information identified in multiple frames of images in multiple time periods is within the preset quantity range, the preset determination condition is met.

14. The apparatus according to claim 13, characterized in that, Also includes: The information monitoring submodule is used to monitor the quantity information and corresponding images of the preset objects sent to the preset designated platform and the updated quantity information and corresponding images thereafter. An anomaly notification generation submodule is used to generate an anomaly notification when at least one of the updated quantity information is detected, and / or an anomaly occurs in the image corresponding to at least one of the updated quantity information; An exception notification sending submodule is used to send the exception notification to the preset designated platform; the exception notification is used to provide feedback on the exception data for the preset object to the preset designated platform.

15. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the data acquisition method for a preset object as described in any one of claims 1 to 2 or the data processing method for a preset object as described in any one of claims 3 to 7.

16. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the data acquisition method for a preset object as described in any one of claims 1 to 2 or the data processing method for a preset object as described in any one of claims 3 to 7.

Images