Plant monitoring method, device, computer readable storage medium and electronic device

Abstract

Embodiments of the present application provide a plant monitoring method, device, computer readable storage medium and electronic device, the method comprising: acquiring a growth image sequence corresponding to a plant to be monitored; determining a health anomaly window from the growth image sequence, wherein the health anomaly window includes a growth image reflecting an abnormal growth state of the plant to be monitored in the growth image sequence; and outputting an abnormality analysis report of the plant to be monitored according to the health anomaly window and a maintenance log corresponding to the plant to be monitored. The technical solution of the embodiments of the present application can enable plant maintenance personnel to consult and analyze the abnormality and the root cause of the plant to be monitored through the abnormality analysis report without going to the plant planting site, thereby improving the convenience of the plant maintenance personnel in monitoring and identifying the growth evolution trend and the root cause of the plant.

Description

Technical Field

[0001] This application relates to the field of plant monitoring technology, and more specifically, to a plant monitoring method, apparatus, computer-readable storage medium, and electronic device. Background Technology

[0002] With the continuous development of science and technology, monitoring the evolution trend of plant growth and identifying the root cause of abnormalities when they are discovered has become crucial for implementing precise interventions and ensuring plant health and yield.

[0003] In related technologies, to monitor plant growth trends and diagnose abnormalities, plant maintenance personnel typically need to visit the planting site in person to identify and judge the situation through visual observation, manual inspection, and their own experience. However, in practical applications, this method suffers from drawbacks such as low efficiency, limited coverage, and delayed response.

[0004] Therefore, how to conveniently and accurately monitor the growth and evolution trends of plants and determine the root causes of their abnormalities has become an urgent problem to be solved. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of this application provide a plant monitoring method, apparatus, computer-readable storage medium, and electronic device, enabling plant maintenance personnel to review and analyze abnormal conditions and root causes of the monitored plants.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to one aspect of the embodiments of this application, a plant monitoring method is provided, comprising: acquiring a growth image sequence corresponding to a plant to be monitored; determining a health mutation window from the growth image sequence, wherein the health mutation window includes growth images in the growth image sequence that reflect an abnormal growth state of the plant to be monitored; and outputting an abnormality analysis report of the plant to be monitored based on the health mutation window and the maintenance log corresponding to the plant to be monitored.

[0008] According to one aspect of the embodiments of this application, a plant monitoring device is provided, comprising: an acquisition module configured to acquire a growth image sequence corresponding to a plant to be monitored; an identification module configured to determine a health mutation window from the growth image sequence, wherein the health mutation window includes growth images in the growth image sequence reflecting an abnormal growth state of the plant to be monitored; and an output module configured to output an abnormality analysis report of the plant to be monitored based on the health mutation window and the maintenance log corresponding to the plant to be monitored.

[0009] In some embodiments of this application, based on the foregoing scheme, the identification module is further configured to: traverse the growth images in the growth image sequence according to a preset step size to generate candidate growth windows; wherein, the candidate growth window includes the growth image obtained by traversing the growth image sequence according to the preset step size; determine the growth health information of the plant to be monitored under the candidate growth window; and use the candidate growth window as the health mutation window according to the growth health information.

[0010] In some embodiments of this application, based on the aforementioned scheme, the identification module is further configured to: determine whether the growth health information meets the preset abnormal rules; if it is determined to be yes, then the candidate growth window is used as the health mutation window; if it is determined to be no, then return to the step of traversing the growth images in the growth image sequence according to the preset step size, and take the next growth image corresponding to the candidate growth window in the growth image sequence as the traversal starting point.

[0011] In some embodiments of this application, based on the foregoing scheme, the identification module is further configured to: if, based on the growth health information, it is determined that the change in the health index corresponding to any growth image in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy the preset anomaly rule; wherein, the change in the health index refers to the change between the health index corresponding to the current growth image and the previous growth image in the growth image sequence; or; if, based on the growth health information, it is determined that the change in the health index corresponding to multiple growth windows in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy the preset anomaly rule; or; if, based on the growth health information, it is determined that the change in the health index corresponding to multiple consecutive growth windows in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy the preset anomaly rule.

[0012] In some embodiments of this application, based on the foregoing scheme, the output module is further configured to: obtain the maintenance operation set corresponding to the maintenance log under the health anomaly window; and output the anomaly analysis report according to the health anomaly window and the maintenance operation set.

[0013] In some embodiments of this application, based on the foregoing scheme, the output module is further configured to: filter abnormal maintenance operations related to the health mutation window from the maintenance operation set; and output the abnormal analysis report based on the health mutation window and the abnormal maintenance operation.

[0014] In some embodiments of this application, based on the foregoing scheme, the output module is further configured to: determine the image feature vector corresponding to the health mutation window and the text feature vector corresponding to each maintenance operation in the maintenance operation set; determine the similarity between each maintenance operation and the health mutation window based on the image feature vector and the text feature vector corresponding to each maintenance operation; and obtain maintenance operations from each maintenance operation whose similarity to the health mutation window reaches a preset similarity as the abnormal maintenance operations.

[0015] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, on which computer-readable instructions are stored, which, when executed by a computer's processor, cause the computer to perform the plant monitoring method as described in the above embodiments.

[0016] According to one aspect of the embodiments of this application, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device causes the electronic device to implement the plant monitoring method as described in the above embodiments.

[0017] In the technical solution of this application embodiment, a growth image sequence corresponding to the plant to be monitored is obtained, and then a health mutation window is determined from the growth image sequence. The health mutation window includes growth images in the growth image sequence that reflect abnormal growth status of the plant to be monitored. Then, based on the health mutation window and the maintenance log corresponding to the plant to be monitored, an anomaly analysis report of the plant to be monitored is output. This allows plant maintenance personnel to view and analyze the abnormal situation and root cause of the plant to be monitored through the anomaly analysis report without having to go to the plant planting site, thereby improving the convenience for plant maintenance personnel to monitor and identify the growth evolution trend and root cause of abnormalities of plants. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 This is a flowchart illustrating a plant monitoring method in an exemplary embodiment of this application; Figure 2 yes Figure 1 The flowchart of step S120 in the illustrated embodiment is shown in an example embodiment; Figure 3 yes Figure 1 The flowchart of step S130 in the illustrated embodiment is shown in an example embodiment; Figure 4 This is a block diagram illustrating a plant monitoring device in an exemplary embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of this application. Detailed Implementation

[0019] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0020] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0021] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0022] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0023] It should be noted that "multiple" in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0024] The technical solution of this application embodiment proposes a plant monitoring method, which is specifically referred to... Figure 1As shown. The method includes at least steps S110 to S130, which are described in detail below: In step S110, the growth image sequence corresponding to the plant to be monitored is obtained.

[0025] The plants to be monitored are those whose growth and evolution trends are currently being tracked. The growth image sequence includes growth images of the plants to be monitored at different time points.

[0026] In step S120, a healthy mutation window is determined from the growth image sequence.

[0027] In the embodiments of this application, after obtaining the growth image sequence corresponding to the plant to be monitored, a health mutation window can be determined from the growth image sequence. The health mutation window includes growth images in the growth image sequence that reflect abnormal growth status of the plant to be monitored.

[0028] Abnormal growth status refers to the growth state of the plant under monitoring caused by abnormal factors such as pests, water imbalance, chemical damage, or nutrient imbalance.

[0029] The method for determining the health mutation window from the growth image sequence can be flexibly set as needed. In some embodiments of this application, the health index corresponding to each growth image in the growth image sequence can be determined, and then the growth image with the lowest health index can be obtained from each growth image as the growth image in the health mutation window to obtain the health mutation window.

[0030] In order to determine the health index corresponding to the growth image, in some embodiments of this application, a visual model can be used to output the image feature vector corresponding to the growth image based on the growth image, and then a classification model can be used to output the health index corresponding to the growth image based on the image feature vector.

[0031] Visual models include VIT (Vision Transformer), ResNet (Residual Network), and ConvNeXt (Convolutional Next). Classification models include linear regression, support vector regression, and multilayer perceptron.

[0032] In some embodiments of this application, the growth images in the growth image sequence can be traversed sequentially to determine candidate growth images. Then, the change in the health index corresponding to the candidate growth image can be obtained. If the change in the health index reaches a preset change threshold, it indicates that the change in the health index of the plant under the candidate growth image is large, which means that the plant under the monitoring has an abnormal growth state. The candidate growth image can then be used as the growth image in the health mutation window to obtain the health mutation window.

[0033] Conversely, if it is determined that the change in the health index has not reached the preset change threshold, it indicates that the change in the health index of the plant under the candidate growth image is normal. Then, the process can return to the step of sequentially traversing the growth images in the growth image sequence, and take the next growth image corresponding to the candidate growth image in the growth image sequence as the starting point for traversal, thereby achieving the purpose of determining the health mutation window.

[0034] Here, the candidate growth image is the growth image obtained by traversing the growth image sequence. The change in health index refers to the change in the health index between the current growth image and the previous growth image in the growth image sequence. The change in health index corresponding to the candidate growth image is the change in the health index between the candidate growth image and the previous growth image in the growth image sequence.

[0035] In step S130, an anomaly analysis report of the plant to be monitored is output based on the health anomaly window and the maintenance log corresponding to the plant to be monitored.

[0036] In the embodiments of this application, after identifying the health mutation window from the growth image sequence, an anomaly analysis report of the plant to be monitored can be output based on the health mutation window and the corresponding maintenance log of the plant to be monitored. This allows plant maintenance personnel to review and analyze the abnormal situation and root cause of the plant to be monitored through the anomaly analysis report without having to go to the plant planting site in person, thereby improving the convenience for plant maintenance personnel to monitor and identify the growth evolution trend and root cause of abnormalities of plants.

[0037] The maintenance log includes a record of all maintenance operations performed on the plants to be monitored.

[0038] In some embodiments of this application, the abnormal analysis report of the monitored plant is output based on the health mutation window and the maintenance log corresponding to the monitored plant. This method can directly generate the abnormal analysis report based on the health mutation window and the maintenance log, so that plant maintenance personnel can view and analyze the abnormal situation and root cause of the abnormality of the monitored plant through the abnormal analysis report.

[0039] In some embodiments of this application, the method of outputting anomaly analysis reports of the monitored plants based on the health mutation window and the maintenance log corresponding to the monitored plants can also first filter out abnormal maintenance operations related to the health mutation window from the maintenance log, and then generate anomaly analysis reports based on the health mutation window and abnormal maintenance operations, so as to remove maintenance operations that are currently unrelated to health mutations from the maintenance log, thereby reducing the amount of data in the anomaly analysis report and further facilitating plant maintenance personnel to view and analyze the abnormal conditions and root causes of the monitored plants through the anomaly analysis report.

[0040] In some embodiments of this application, the method of filtering abnormal maintenance operations related to the health mutation window from the maintenance log can be as follows: First, determine the image feature vector corresponding to the health mutation window and the text feature vector corresponding to each maintenance operation in the maintenance log. Then, determine the similarity between each maintenance operation and the health mutation window based on the image feature vector and the text feature vector corresponding to each maintenance operation. Finally, obtain the maintenance operations from each maintenance operation in the maintenance log that have a similarity to the health mutation window that reaches a preset similarity as abnormal maintenance operations.

[0041] Determining the similarity between maintenance operations and health mutation windows based on image and text feature vectors can be achieved by calculating the cosine similarity between the image and text feature vectors, and using this cosine similarity as the similarity between the maintenance operations and the health mutation windows. Alternatively, it can be achieved by calculating the Euclidean distance between the image and text feature vectors, and using this Euclidean distance as the similarity between the maintenance operations and the health mutation windows. No particular restriction is imposed on this approach.

[0042] Secondly, before determining the similarity between the maintenance operation and the health mutation window based on the image feature vector and the text feature vector, in some embodiments of this application, the image feature vector and the text feature vector can be preprocessed to make the number of dimensions corresponding to the image feature vector and the text feature vector the same. Then, the similarity between the maintenance operation and the health mutation window is determined based on the preprocessed image feature vector and the text feature vector, which facilitates the calculation of the similarity between the maintenance operation and the health mutation window.

[0043] In addition, in some embodiments of this application, after generating an anomaly analysis report based on the health mutation window and abnormal maintenance operations, maintenance operations whose similarity to the health mutation window is within a preset similarity verification range can be obtained from each maintenance operation in the maintenance log as suspicious maintenance operations. Then, the anomaly analysis report is updated based on the suspicious maintenance operations to further facilitate plant maintenance personnel to view and analyze the abnormal conditions and root causes of the monitored plants through the anomaly analysis report.

[0044] See Figure 2, Figure 2 Is Figure 1 The flowchart of step S120 in an exemplary embodiment shown in the illustration is as follows. Figure 2 As shown, the process of determining the healthy mutation window from the growth image sequence may include steps S210 to S230, which are described in detail below: In step S210, the growth images in the growth image sequence are traversed according to a preset step size to generate candidate growth windows.

[0045] In embodiments of this application, in order to determine the healthy mutation window from the growth image sequence, the growth images in the growth image sequence can be traversed according to a preset step size to generate candidate growth windows. The candidate growth windows include the growth images currently traversed in the growth image sequence according to the preset step size.

[0046] The preset step size can be set to the number of images to be grown, such as 3 or 5 images. Correspondingly, the candidate growth window will include the 3 or 5 images obtained from the current image sequence. The preset step size can also be set to a time interval, such as 1 day or 7 days. In this case, the candidate growth window will include the images corresponding to 1 day or 7 days from the current image sequence. No restrictions are imposed.

[0047] In step S220, the growth health information of the plant to be monitored under the candidate growth window is determined.

[0048] In some embodiments of this application, in order to determine the growth health information of the plant to be monitored under the labeled window, the health feature vector corresponding to each growth image in the candidate growth window can be determined first, and then the health feature vector corresponding to each growth image in the candidate growth window can be used as the growth health information.

[0049] In some embodiments of this application, the health index corresponding to each growth image in the candidate growth window can be determined first, and then the health index corresponding to each growth image in the candidate growth window can be used as growth health information.

[0050] The method for determining the health index in the above process can be referred to in step S120, and will not be repeated here.

[0051] In step S230, candidate growth windows are selected as health mutation windows based on growth health information.

[0052] In the embodiments of this application, after determining the growth health information of the plant to be monitored under the candidate growth window, the candidate growth window can be used as the health mutation window based on the growth health information.

[0053] In some embodiments of this application, the process of using candidate growth windows as health mutation windows based on growth health information can involve determining whether the growth health information meets preset anomaly rules. If it does, the candidate growth window is used as a health mutation window. If it does not, the process returns to the step of traversing the growth images in the growth image sequence according to a preset step size, and the next growth image corresponding to the candidate growth window in the growth image sequence is used as the traversal starting point.

[0054] The method for determining whether growth health information meets preset anomaly rules can be flexibly configured as needed. In one example, if the health index corresponding to any growth image in the candidate growth window is determined to be lower than a preset index threshold based on the growth health information, then the growth health information is determined to meet the preset anomaly rules. In other words, the preset anomaly rules can include the logical rule that the health index corresponding to any growth image in the candidate growth window is lower than the preset index threshold.

[0055] In another example, if, based on growth health information, it is determined that the health index corresponding to multiple growth images within a candidate growth window is lower than a preset index threshold, then the growth health information is determined to satisfy a preset anomaly rule. In other words, the preset anomaly rule may also include the logical rule that determines the health index corresponding to multiple growth images within a candidate growth window is lower than a preset index threshold.

[0056] In another example, if growth health information determines that the health index corresponding to multiple consecutive growth images in a candidate growth window is lower than a preset index threshold, then the growth health information is determined to meet a preset anomaly rule. In other words, the preset anomaly rule may also include the logical rule that determines the health index corresponding to multiple consecutive growth images in a candidate growth window is lower than a preset index threshold.

[0057] In another example, if the change in the health index corresponding to any growth image within a candidate growth window reaches a preset change threshold based on growth health information, then the growth health information is determined to satisfy a preset anomaly rule. In other words, the preset anomaly rule may also include the logical rule that determines the change in the health index corresponding to any growth window within the candidate growth window reaches the preset change threshold.

[0058] In another example, if, based on growth health information, it is determined that multiple growth windows within a candidate growth window have health index changes that reach a preset change threshold, then the growth health information is determined to satisfy a preset anomaly rule. In other words, the preset anomaly rule may also include the logical rule that determines that multiple growth windows within a candidate growth window have health index changes that reach a preset change threshold.

[0059] In another example, if, based on growth health information, it is determined that within a candidate growth window, the change in the health index corresponding to each of multiple consecutive growth windows reaches a preset change threshold, then the growth health information is determined to satisfy a preset anomaly rule. In other words, the preset anomaly rule may also include the logical rule that determines that within a candidate growth window, the change in the health index corresponding to each of multiple consecutive growth windows reaches a preset change threshold.

[0060] In addition, the number of “multiple” and “consecutive multiple” mentioned in the above examples can be flexibly set according to the needs of plant maintenance personnel, and there is no limit here.

[0061] Through the above implementation method, the growth images in the growth image sequence are traversed according to a preset step size to generate candidate growth windows. Then, the growth health information of the plant to be monitored under the candidate growth window is determined. Subsequently, the candidate growth window is used as a health mutation window based on the growth health information. This allows the health mutation window to correspond to multiple growth images in the growth image sequence, which facilitates subsequent plant maintenance personnel to view and analyze the abnormal situation and root cause of the plant to be monitored through the health mutation window in the anomaly analysis report.

[0062] See Figure 3 , Figure 3 Is Figure 1 The flowchart of step S130 in the illustrated embodiment is shown in an exemplary embodiment. Figure 3 As shown, the process of outputting an anomaly analysis report for the monitored plant based on the health anomaly window and the corresponding maintenance log of the monitored plant may include steps S310 to S320, which are described in detail below: In step S310, the set of maintenance operations corresponding to the health anomaly window in the maintenance log is obtained.

[0063] The maintenance operation set includes all maintenance operations performed on the plants to be monitored, recorded in the maintenance log under the health anomaly window.

[0064] To obtain the set of maintenance operations corresponding to the health mutation window in the maintenance log, we can obtain the shooting time period corresponding to the growth image in the health mutation window, then obtain the maintenance operations recorded during the shooting time period from the maintenance log, and output the set of maintenance operations based on the obtained maintenance operations, thereby achieving the purpose of obtaining the set of maintenance operations.

[0065] In step S320, an anomaly analysis report is output based on the health anomaly window and the maintenance operation set.

[0066] In the embodiments of this application, in order to output an anomaly analysis report of the monitored plant based on the health anomaly window and the maintenance log corresponding to the monitored plant, after obtaining the set of maintenance operations corresponding to the maintenance log under the health anomaly window, the anomaly analysis report can be output based on the health anomaly window and the set of maintenance operations. This is to remove maintenance operations that are currently unrelated to the health anomaly window from the maintenance log, thereby reducing the amount of data in the anomaly analysis report. This makes it easier for plant maintenance personnel to view and analyze the abnormal situation and root cause of the monitored plant through the anomaly analysis report.

[0067] In some embodiments of this application, the method of outputting anomaly analysis reports based on the health mutation window and the maintenance operation set can also filter abnormal maintenance operations related to the health mutation window from the maintenance operation set, and then output anomaly analysis reports based on the health mutation window and abnormal maintenance operations, thereby further removing maintenance operations that are currently unrelated to the health mutation window from the maintenance log and reducing the amount of data in the anomaly analysis report.

[0068] In some embodiments of this application, the method for filtering abnormal maintenance operations related to the health mutation window from the maintenance operation set can be as follows: First, determine the image feature vector corresponding to the health mutation window and the text feature vector corresponding to each maintenance operation in the maintenance operation set. Then, determine the similarity between each maintenance operation and the health mutation window based on the image feature vector and the text feature vector corresponding to each maintenance operation. After that, obtain the maintenance operation whose similarity to the health mutation window reaches a preset similarity from each maintenance operation as the abnormal maintenance operation.

[0069] The process of determining the similarity between each maintenance operation and the health mutation window based on the image feature vector and the text feature vector corresponding to each maintenance operation can be referred to in step S130 above, and will not be repeated here.

[0070] In addition, after outputting the anomaly analysis report based on the health mutation window and abnormal maintenance operations, in some embodiments of this application, suspicious maintenance operations related to the health mutation window can be screened from the maintenance operation set, and then the anomaly analysis report can be updated based on the suspicious maintenance operations in the maintenance operation set, so as to further facilitate plant maintenance personnel to view and analyze the abnormal situation and root cause of the monitored plant through the anomaly analysis report.

[0071] In some embodiments of this application, a method for filtering suspicious maintenance operations related to the health mutation window from a set of maintenance operations is to select maintenance operations from each maintenance operation in the set of maintenance operations that have a similarity to the health mutation window within a preset similarity verification range as suspicious maintenance operations.

[0072] The following describes an embodiment of the apparatus described in this application, which can be used to perform the plant monitoring method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the plant monitoring method described in the above embodiments of this application.

[0073] Figure 4 A block diagram of a plant monitoring device 100 according to one embodiment of this application is shown.

[0074] Reference Figure 4 As shown, a plant monitoring device 100 according to an embodiment of this application includes: an acquisition module 110 configured to acquire a growth image sequence corresponding to a plant to be monitored; an identification module 120 configured to determine a health mutation window from the growth image sequence, wherein the health mutation window includes growth images in the growth image sequence that reflect an abnormal growth state of the plant to be monitored; and an output module 130 configured to output an abnormality analysis report of the plant to be monitored based on the health mutation window and the maintenance log corresponding to the plant to be monitored.

[0075] In some embodiments of this application, based on the aforementioned scheme, the identification module 120 is further configured to: traverse the growth images in the growth image sequence according to a preset step size to generate a candidate growth window; wherein, the candidate growth window includes the growth image obtained by traversing the growth image sequence according to the preset step size; determine the growth health information of the plant to be monitored under the candidate growth window; and use the candidate growth window as a health mutation window according to the growth health information.

[0076] In some embodiments of this application, based on the aforementioned scheme, the identification module 120 is further configured to: determine whether the growth health information meets the preset abnormal rules; if it is determined to be yes, then the candidate growth window is used as the health mutation window; if it is determined to be no, then return to the step of traversing the growth images in the growth image sequence according to the preset step size, and take the next growth image corresponding to the candidate growth window in the growth image sequence as the traversal starting point.

[0077] In some embodiments of this application, based on the foregoing scheme, the identification module 120 is further configured to: if, based on growth health information, it is determined that the change in the health index corresponding to any growth image in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy a preset anomaly rule; wherein, the change in the health index refers to the change between the health index corresponding to the current growth image and the previous growth image in the growth image sequence; or; if, based on growth health information, it is determined that the change in the health index corresponding to multiple growth windows in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy a preset anomaly rule; or; if, based on growth health information, it is determined that the change in the health index corresponding to multiple consecutive growth windows in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy a preset anomaly rule.

[0078] In some embodiments of this application, based on the foregoing scheme, the output module 130 is further configured to: obtain the maintenance operation set corresponding to the maintenance log under the health anomaly window; and output an anomaly analysis report based on the health anomaly window and the maintenance operation set.

[0079] In some embodiments of this application, based on the foregoing scheme, the output module 130 is further configured to: filter abnormal maintenance operations related to the health mutation window from the maintenance operation set; and output an abnormal analysis report based on the health mutation window and the abnormal maintenance operation.

[0080] In some embodiments of this application, based on the foregoing scheme, the output module 130 is further configured to: determine the image feature vector corresponding to the health mutation window and the text feature vector corresponding to each maintenance operation in the maintenance operation set; determine the similarity between each maintenance operation and the health mutation window based on the image feature vector and the text feature vector corresponding to each maintenance operation; and obtain maintenance operations from each maintenance operation whose similarity to the health mutation window reaches a preset similarity as abnormal maintenance operations.

[0081] It should be noted that the plant monitoring device 100 provided in the above embodiments and the plant monitoring method provided in the above embodiments belong to the same concept. The specific way in which each module and unit performs operations has been described in detail in the method embodiments, and will not be repeated here.

[0082] Embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions that, when executed by the processor, implement the plant monitoring method as described above.

[0083] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0084] It should be noted that, Figure 5 The computer system 900 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0085] like Figure 5 As shown, the computer system 200 includes a Central Processing Unit (CPU) 201, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 202 or programs loaded from storage portion 208 into Random Access Memory (RAM) 203, such as performing the methods described in the above embodiments. The RAM 203 also stores various programs and data required for system operation. The CPU 201, ROM 202, and RAM 203 are interconnected via a bus 204. An Input / Output (I / O) interface 205 is also connected to the bus 204.

[0086] The following components are connected to I / O interface 205: an input section 206 including a keyboard, mouse, etc.; an output section 207 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to I / O interface 205 as needed. Removable media 211, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 210 as needed so that computer programs read from them can be installed into storage section 208 as needed.

[0087] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 209, and / or installed from removable medium 211. When the computer program is executed by central processing unit (CPU) 201, it performs various functions defined in the system of this application.

[0088] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0090] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0091] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0092] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0093] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0094] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0095] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A plant monitoring method, characterized in that, The method includes: Obtain the growth image sequence corresponding to the plant to be monitored; A health mutation window is determined from the growth image sequence, wherein the health mutation window includes growth images in the growth image sequence that reflect abnormal growth states of the plant under monitoring; Based on the health anomaly window and the corresponding maintenance log of the plant to be monitored, an anomaly analysis report of the plant to be monitored is output.

2. The method according to claim 1, characterized in that, The step of determining the healthy mutation window from the growth image sequence includes: The growth images in the growth image sequence are traversed according to a preset step size to generate candidate growth windows; wherein, the candidate growth windows include the growth images obtained by traversing the growth image sequence according to the preset step size. Determine the growth health information of the plant to be monitored under the candidate growth window; The candidate growth window is used as the health mutation window based on the growth health information.

3. The method according to claim 2, characterized in that, The step of using the candidate growth window as the health mutation window based on the growth health information includes: Determine whether the growth health information meets the preset abnormality rules; If it is determined to be yes, then the candidate growth window is used as the healthy mutation window; If the result is negative, the process returns to the step of traversing the growth images in the growth image sequence according to a preset step size, and takes the next growth image corresponding to the candidate growth window in the growth image sequence as the starting point for traversal.

4. The method according to claim 3, characterized in that, Determining whether the growth health information meets preset abnormality rules includes: If, based on the growth health information, it is determined that the change in the health index corresponding to any growth image in the candidate growth window reaches a preset change threshold, then the growth health information is determined to satisfy the preset anomaly rule; wherein, the change in the health index refers to the change in the health index corresponding to the current growth image and the previous growth image in the growth image sequence. or; If, based on the growth health information, it is determined that there are multiple growth windows in the candidate growth window whose corresponding health index changes reach a preset change threshold, then the growth health information is determined to satisfy the preset abnormality rule. or; If, based on the growth health information, it is determined that there are multiple consecutive growth windows in the candidate growth window whose corresponding health index changes reach a preset change threshold, then the growth health information is determined to satisfy the preset abnormality rule.

5. The method according to claim 1, characterized in that, The process of outputting an anomaly analysis report for the monitored plant based on the health anomaly window and the corresponding maintenance log of the monitored plant includes: Obtain the set of maintenance operations corresponding to the maintenance log under the health anomaly window; The anomaly analysis report is output based on the health anomaly window and the maintenance operation set.

6. The method according to claim 5, characterized in that, The step of outputting the anomaly analysis report based on the growth image and the set of maintenance operations includes: Filter the abnormal maintenance operations related to the health anomaly window from the set of maintenance operations; The abnormality analysis report is output based on the health anomaly window and the abnormal maintenance operation.

7. The method according to claim 6, characterized in that, The step of determining the target maintenance operation from the set of maintenance operations includes: Determine the image feature vector corresponding to the health mutation window and the text feature vector corresponding to each maintenance operation in the maintenance operation set; The similarity between each maintenance operation and the health mutation window is determined based on the image feature vector and the text feature vector corresponding to each maintenance operation. From each of the aforementioned maintenance operations, the maintenance operation with a similarity to the health mutation window that reaches a preset similarity is selected as the abnormal maintenance operation.

8. A plant monitoring device, characterized in that, include: The acquisition module is configured to acquire the growth image sequence corresponding to the plant to be monitored; The identification module is configured to determine a health mutation window from the growth image sequence, wherein the health mutation window includes growth images in the growth image sequence that reflect an abnormal growth state of the plant under monitoring; The output module is configured to output an anomaly analysis report of the plant to be monitored based on the health anomaly window and the maintenance log corresponding to the plant to be monitored.

9. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that, when executed by a computer's processor, cause the computer to perform the plant monitoring method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the plant monitoring method as described in any one of claims 1 to 7.

Images