Information generation method, apparatus, and computer-readable storage medium

Abstract

The application provides an information generation method and device and a computer readable storage medium, relates to the technical field of agriculture, and can determine the PPFD of a plant in a three-dimensional space. The method comprises the following steps: acquiring three-dimensional point cloud data of a target plant and multispectral data of the target plant; determining a first photosynthetic photon flux density (PPFD) according to the three-dimensional point cloud data, and determining a second PPFD according to the multispectral data; and determining a target PPFD of the target plant in the three-dimensional space according to the first PPFD, the second PPFD and a target weight.

Description

Technical Field

[0001] This application relates to the agricultural field, and more particularly to information generation methods, apparatus and computer-readable storage media. Background Technology

[0002] In agriculture, the regulation of the light environment is crucial for plant growth. To ensure plant growth, it is necessary to determine the plant's photoluminescence factor (PPFD) so that the PPFD can be adjusted using lighting tools.

[0003] Therefore, determining the PPFD of plants has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides an information generation method, apparatus, and computer-readable storage medium capable of determining the PPFD of plants in three-dimensional space.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, an information generation method is provided, characterized in that the method includes: acquiring three-dimensional point cloud data and multispectral data of a target plant; determining a first PPFD based on the three-dimensional point cloud data, and determining a second PPFD based on the multispectral data; and determining a target PPFD of the target plant in three-dimensional space based on the first PPFD, the second PPFD, and the target weight.

[0007] The process involves acquiring three-dimensional point cloud data of the target plant's three-dimensional structural layer and multispectral data of the target plant. Then, the first photosynthetic photon flux density (PPFD) is determined based on the three-dimensional point cloud data, and the second PPFD is determined based on the multispectral data. Finally, the target PPFD of the target plant in three-dimensional space is determined based on the first PPFD, the second PPFD, and the target weight. On the one hand, the three-dimensional point cloud data can reflect the influence of the target plant's own structure on light distribution; on the other hand, the multispectral data can take into account the spectral characteristics of different light sources and the spectral composition of ambient light. Therefore, the obtained target PPFD can more realistically reflect the actual light exposure of the plant in complex light environments, thus enabling the determination of the target PPFD of the target plant in three-dimensional space.

[0008] In conjunction with the first aspect, in some embodiments of the first aspect, determining the target PPFD of the target plant in three-dimensional space based on the first PPFD, the second PPFD, and the target weight includes: using the sum of the first product and the second product as the target PPFD of the target plant in three-dimensional space; the first product is the product of the first PPFD and the target weight, the second product is the product of the second PPFD and the first difference, and the first difference is the difference between 1 and the target weight.

[0009] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: acquiring multiple first data sets for each plant in at least one plant; the first data sets include a third PPFD, a fourth PPFD, and a fifth PPFD of the plant under a preset light intensity, wherein the third PPFD is a PPFD determined based on the plant's three-dimensional point cloud data, the fourth PPFD is a PPFD determined based on the plant's multispectral data, and the fifth PPFD is the plant's true PPFD, and the preset light intensity corresponding to each first data set is different; for each of the multiple original weights, determining a sixth PPFD corresponding to each first data set; the sixth PPFD is the sum of a third product and a fourth product, wherein the third product is the product of the third PPFD in the first data set and the original weight, and the fourth product is the product of the fourth PPFD in the first data set and a second difference, wherein the second difference is the difference between 1 and the original weight; determining a target weight based on multiple second data sets for each of the multiple original weights; the second data sets include the sixth PPFD and the fifth PPFD corresponding to the sixth PPFD.

[0010] A first data set is obtained for each plant in at least one plant, including a third, fourth, and fifth PPFD of the plant under a preset light intensity. Then, for each of the multiple original weights, a sixth PPFD corresponding to each first data set is determined. The sixth PPFD is the sum of the third and fourth products. The third product is the product of the third PPFD in the first data set and the original weight, and the fourth product is the product of the fourth PPFD in the first data set and the second difference, where the second difference is the difference between 1 and the original weight. Subsequently, a target weight is determined based on multiple second data sets for each of the multiple original weights. Since the second data sets include the sixth PPFD and the corresponding fifth PPFD, the third PPFD is the PPFD determined based on the plant's 3D point cloud data, the fourth PPFD is the PPFD determined based on the plant's multispectral data, and the fifth PPFD is the plant's true PPFD. Each second data set corresponds to a different preset light intensity, allowing the target weight to be determined based on different light intensities and different plants, thereby improving the accuracy of the determined target weight.

[0011] In conjunction with the first aspect, in certain embodiments of the first aspect, determining a target weight based on multiple second data sets for each of the multiple original weights includes: for each second data set of each original weight, using the difference between the sixth PPFD and the corresponding fifth PPFD as a third difference; for each of the multiple original weights, determining the mean square error of the multiple third differences of the original weights; iteratively calculating the target weight based on the mean square errors corresponding to the multiple original weights and the Nelder-Mead algorithm; the mean square error corresponding to the target weight is less than the mean square error corresponding to any one of the original weights.

[0012] For each second dataset with each original weight, the difference between the sixth PPFD and the corresponding fifth PPFD is used as the third difference. For each original weight, the mean square error of the multiple third differences of the original weights is determined. Based on the mean square errors corresponding to the multiple original weights and the Nelder-Mead algorithm, the target weight is determined through iterative calculation. Since the mean square error corresponding to the target weight is smaller than the mean square error corresponding to any original weight, the Nelder-Mead algorithm can perform iterative calculation to search for the optimal target weight within a wider range of weight values. In each iteration, the weights are adjusted according to certain rules based on the current weight value and mean square error, attempting to find a smaller mean square error. This allows for a gradual approach to the global optimum, rather than being limited to multiple original weights, thus obtaining a more accurate target weight and improving the accuracy of determining the PPFD of the target plant.

[0013] In conjunction with the first aspect, in some embodiments of the first aspect, determining the target weight by iterative calculation based on the mean squared errors corresponding to multiple original weights and the Nelder-Mead algorithm includes: determining the initial weight by iterative calculation based on the mean squared errors corresponding to multiple original weights and the Nelder-Mead algorithm; the mean squared error corresponding to the initial weight is less than the mean squared error corresponding to any one of the original weights; performing a two-tailed t-test based on the initial weight to obtain the test result; and if the test result indicates that the test has passed, using the initial weight as the target weight.

[0014] The initial weights are determined by iterative calculation using the mean squared errors of multiple original weights and the Nelder-Mead algorithm. The mean squared error of the initial weights is less than the mean squared error of any one of the original weights. A two-tailed t-test is performed based on the initial weights to obtain the test results. If the test results indicate that the test is passed, the result is reliable and the optimized target weights are effective. Using the initial weights as the target weights can improve the accuracy of the determined target weights.

[0015] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: acquiring the actual growth curve of the target plant's environmental data and target growth data within a target time period; determining that the target plant's growth is abnormal when the similarity between the actual growth curve and the standard growth curve is less than a preset similarity threshold; and determining growth recommendation information for the target plant based on the environmental data.

[0016] Obtain the actual growth curve of the target plant's environmental data and target growth data within the target time period; determine the target plant's growth abnormality if the similarity between the actual growth curve and the standard growth curve is less than a preset similarity threshold; determine the target plant's growth recommendations based on the environmental data.

[0017] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: visualizing the target PPFD of the target plant to obtain a PPFD cloud map of the target plant in three-dimensional space.

[0018] By visualizing the target PPFD (Photometric Photogrammetry File) image, growers can intuitively see the light distribution within the three-dimensional space of the plant. Based on the PPFD cloud map, growers can accurately determine which areas are under-lit, and thus adjust the position and intensity of supplemental lighting fixtures to achieve precise supplemental lighting.

[0019] Secondly, an information generation apparatus is provided for implementing the information generation method of the first aspect described above. This information generation apparatus includes modules, units, or means corresponding to the above method. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions.

[0020] In conjunction with the second aspect, in some embodiments of the second aspect, the information generation apparatus includes: the apparatus includes: an acquisition module and a processing module; the acquisition module is used to acquire three-dimensional point cloud data of the target plant and multispectral data of the target plant; the three-dimensional point cloud data is used to indicate the three-dimensional structure of the target plant; the processing module is used to determine a first PPFD based on the three-dimensional point cloud data, and to determine a second PPFD based on the multispectral data; the processing module is further used to determine a target PPFD of the target plant in three-dimensional space based on the first PPFD, the second PPFD, and the target weight.

[0021] Thirdly, an information generation apparatus is provided, comprising: at least one processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method provided by the first aspect and any possible implementation thereof.

[0022] Fourthly, a computer-readable storage medium is provided, which, when executed by a processor of an information generation apparatus, enables the information generation apparatus to perform the method provided by the first aspect and any possible implementation thereof.

[0023] Fifthly, a computer program product containing instructions is provided that, when run on a computer, enables the computer to perform the methods provided in the first aspect and any possible implementation thereof.

[0024] The technical effects of any one of the second to fifth aspects can be found in the technical effects of the different embodiments of the first aspect described above, and will not be repeated here. Attached Figure Description

[0025] Figure 1 A schematic diagram of the architecture of an information generation system provided in this application;

[0026] Figure 2 A schematic diagram illustrating the working principle of a lidar provided in this application;

[0027] Figure 3 A schematic diagram of the multispectral range provided in this application;

[0028] Figure 4 A flowchart illustrating an information generation method provided in this application;

[0029] Figure 5 A flowchart illustrating yet another information generation method provided in this application;

[0030] Figure 6 A flowchart illustrating yet another information generation method provided in this application;

[0031] Figure 7 A flowchart illustrating yet another information generation method provided in this application;

[0032] Figure 8 A flowchart illustrating yet another information generation method provided in this application;

[0033] Figure 9 A schematic diagram of the structure of an information generation device provided in this application;

[0034] Figure 10 This is a schematic diagram of another information generation device provided in this application. Detailed Implementation

[0035] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0036] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0037] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0038] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0039] It is understood that in this application, "when," "if," and "if" all refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require that there must be a judgment action when implemented, nor do they imply any other limitations.

[0040] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0041] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments and implementation methods of the various embodiments in this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the implementation methods of the various embodiments are consistent and can be mutually referenced. The technical features in different embodiments and between the implementation methods of the various embodiments can be combined according to their inherent logical relationships to form new embodiments, implementation methods, implementation methods, or implementation approaches. The following embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0042] Figure 1 This is a schematic diagram of the architecture of an information generation system provided in this application. The technical solutions of the embodiments of this application can be applied to... Figure 1 The information generation system shown can be deployed in a greenhouse where plants are grown, such as... Figure 1 As shown, the information generation system 10 includes an information generation device 11, a lidar 12, a multispectral camera 13, a display device 14, and a lighting controller 15.

[0043] The information generation device 11 is connected to the lidar 12, the multispectral camera 13, the display device 14, and the lighting controller 15, respectively. The information generation device 11 is used to execute the information generation method provided in this application.

[0044] The lidar 12 is used to generate three-dimensional point cloud data of the plants. Figure 2 A schematic diagram illustrating the working principle of a lidar provided in this application is shown below. Figure 2 As shown, the lidar 12 emits a laser to illuminate the plant, and the plant reflects the laser. The lidar 12 can receive the laser reflected by the plant and then generate three-dimensional point cloud data of the plant.

[0045] For example, taking a rectangular greenhouse with an area of ​​500 square meters as an example, the LiDAR 12 is installed at the center of the greenhouse top, so that its scanning range can cover the entire plant area of ​​the greenhouse. A comprehensive calibration is performed weekly, including angle calibration and distance calibration. In daily operation, the LiDAR operates at a frequency of 15 Hz and a scanning speed of 0.1 mm. 3 The system uses high-resolution scanning to obtain high-precision 3D point cloud data of the plants in the greenhouse.

[0046] Furthermore, during the sowing period, UHF RFID tags conforming to the EPC Gen2 standard and storing 24-bit genetic codes can be implanted near the seeds of each plant. As the plants grow to a certain stage, industrial touch terminals, such as the Advantech TPC-1581H industrial tablet, can be installed at the edge of the planting area. Their high resolution and high refresh rate can clearly capture plant growth data, such as leaf unfolding and color changes. The industrial tablet transmits the collected data to the information generation device 11 in real time via an internal network.

[0047] Multispectral camera 13 is used to generate multispectral data of plants. Figure 3 A schematic diagram of the multispectral range provided in this application, such as Figure 3 As shown, light in the 380nm-780nm wavelength range can be called visible light, and light in the 780nm-1700nm wavelength range can be called near-infrared light. The multispectral camera 13 can determine the distribution of stomata on plant leaves by emitting light in the 450nm wavelength range, the concentration of chlorophyll in plant leaves by emitting light in the 680nm wavelength range, and the water content of plants by emitting light in the 950nm wavelength range.

[0048] For example, inside a greenhouse, multispectral cameras are strategically installed based on the height and distribution of the plants. For instance, using tomato plants as an example, multiple cameras are positioned at regular intervals about 1 meter above the plant to ensure comprehensive acquisition of spectral information from different parts of the plant. A hardware triggering mechanism synchronizes the multispectral cameras with the lidar, with a time deviation of less than 10 μs. The multispectral cameras cover the 380-1700 nm wavelength band, with a spectral resolution of 3 nm, enabling the acquisition of the tomato plant's reflection and absorption characteristics under different spectra.

[0049] The number of display devices 14 can be one or more. For example, display devices 14 can be mobile terminals with displays, AR glasses, etc.

[0050] A dedicated app is deployed on the mobile terminal, which supports tracing plant data throughout its entire growth cycle by scanning UHF RFID tags. Users can obtain detailed data on the plant from sowing to harvest by scanning the tag or entering the plant's identification information, including environmental data, growth data, and agricultural operation records. This data is presented intuitively on the terminal's display screen in the form of charts and graphs, facilitating data analysis and decision-making for growers.

[0051] AR glasses, such as the Microsoft HoloLens 3, can achieve millimeter-level spatial matching between virtual information and actual physical plants. Before use, AR glasses undergo rigorous calibration and configuration. Through data interaction with other devices, virtual information such as real-time plant growth status, supplemental lighting recommendations based on light field analysis, and pest and disease warnings are precisely overlaid onto the actual plants. This provides growers with an intuitive and convenient information display, helping them to more accurately understand the plant's condition and make informed decisions. For example, when inspecting a greenhouse with strawberry plants, growers wearing AR glasses can see the real-time growth indicators of each strawberry plant and adjust the lighting accordingly based on supplemental lighting recommendations.

[0052] Furthermore, the AR glasses integrate a pest and disease recognition model, which identifies signs of pests and diseases by photographing plants. If pests or diseases are detected, corresponding control measures are provided based on the type of pest or disease, such as biological control or chemical control.

[0053] The number of lighting controllers 15 can be one or more. The lighting controller 15 can receive instructions to control the lighting fixtures.

[0054] Furthermore, the information generation system 10 may also include a light sensor and a temperature sensor. The light sensor can sense the light data inside the greenhouse, and the temperature sensor can sense the temperature inside the greenhouse.

[0055] The temperature sensor integrates an encryption module supporting the AES-256 algorithm. Temperature is crucial for plant growth, making the data security of the temperature sensor paramount. When unauthorized tampering of the temperature sensor is detected, an anti-tamper self-destruct mechanism immediately activates, destroying sensitive data stored within the sensor. The encryption module is inspected and updated quarterly to ensure its security.

[0056] Furthermore, the information generation system 10 may also include a storage device (not shown in the figure) that can store data from various devices. The storage device can use the InfluxDB spatiotemporal database to store the data. In the database, the timestamp accuracy is set to ±1ms, and the spatial coordinate accuracy is set to ±0.1mm. For example, when recording light data for a plant at a certain growth stage, not only the accurate time is recorded, but also the specific location of the light sensor in the greenhouse. A light environment-growth trait association index table is established by writing scripts, such as recording changes in plant growth rate and leaf number under different light intensities. The database is backed up weekly, and invalid data is cleaned up regularly to optimize database performance.

[0057] The database can be encrypted using the national standard SM9 algorithm for asymmetric encryption. An operation log blockchain storage system should be established to record all database operations, such as data insertion, modification, and deletion. If data is tampered with, the blockchain's timestamps and chain structure can quickly detect the tampering. The blockchain storage system should be regularly maintained and upgraded to ensure its reliability and the security and integrity of the plant data.

[0058] Furthermore, to enable data transmission between different devices in the information generation system 10, a Time-Sensitive Networking (TSN) protocol can be used to build the data transmission network for the information generation system 10. In terms of network architecture design, the network topology is planned according to the greenhouse layout and equipment distribution to ensure smooth data transmission. Simultaneously, a CRC32 checksum is added to each data packet. The checksum is calculated at the data sending end and appended to the data packet. After receiving the data packet, the receiving end recalculates the checksum and compares it with the received checksum. If the two are inconsistent, the receiving end immediately requests the sending end to retransmit the data, thereby ensuring the accuracy of data transmission and strictly controlling the bit error rate to less than 10^-12. In addition, the network is monitored in real time. Dedicated network monitoring software or equipment is used to promptly detect and address network faults, latency issues, and other problems, ensuring that the end-to-end latency is always less than 10ms.

[0059] During data transmission over the data transmission network, the MQTT over TLS 1.3 protocol can be used. Two-way certificate authentication is configured on both the server and client sides to ensure the authenticity of both parties' identities. A timestamp watermark is added to each data packet to prevent replay attacks. Data transmission traffic is monitored in real time using network traffic analysis tools. If an abnormal increase in data traffic is detected within a certain time period, it is immediately analyzed to determine if a network attack is occurring, and timely preventative measures are taken.

[0060] In practical applications, the information generation method provided in this application embodiment can be applied to the information generation device 11, or to the devices included in the information generation device 11.

[0061] The information generation method provided in this application embodiment will be described below with reference to the accompanying drawings, taking the application of the information generation method to the information generation device 11 as an example.

[0062] Figure 4 A flowchart illustrating an information generation method provided in this application is shown below. Figure 4 As shown, the method includes the following steps:

[0063] S401, The information generation device acquires the three-dimensional point cloud data and multispectral data of the target plant.

[0064] It should be noted that the 3D point cloud data is used to reflect the 3D structure of the target plant.

[0065] The target plant can be strawberry, lettuce, cotton, or other kinds of plants. This application does not impose any specific restrictions on this.

[0066] As one possible implementation method, combined with Figure 1 The information generation device sends instructions to the lidar, which then begins operation to obtain three-dimensional point cloud data of the target plant. The lidar then sends feedback information, including the three-dimensional point cloud data of the target plant, to the information generation device. Correspondingly, the information generation device receives the feedback information from the lidar and obtains the three-dimensional point cloud data of the target plant.

[0067] The information generation device sends a command to the multispectral camera. Upon receiving the command, the multispectral camera begins operation and obtains multispectral data of the target plant. The multispectral camera then sends feedback information, including the multispectral data of the target plant, to the information generation device. Correspondingly, the information generation device receives the feedback information from the multispectral camera and obtains the multispectral data of the target plant.

[0068] It should be noted that after acquiring the three-dimensional point cloud data and multispectral data of the target plant, the information generation device can time-align the time corresponding to the three-dimensional point cloud data with the time corresponding to the multispectral data. The time alignment deviation is less than or equal to 10 μs.

[0069] It should be noted that the specific scheme for time alignment can refer to existing schemes, and will not be described in this application.

[0070] S402, the information generation device determines the first photosynthetic photon flux density (PPFD) based on the three-dimensional point cloud data, and determines the second PPFD based on the multispectral data.

[0071] As one possible implementation, the information generation device performs steps such as photon flux distribution simulation, photon flux to PPFD conversion, and spatial aggregation based on three-dimensional point cloud data to obtain the first PPFD.

[0072] The information generation device performs steps such as radiation correction, reflectivity calculation, photosynthetically active radiation estimation, canopy light interception rate calculation, PPFD distribution modeling, pixel-level PPFD mapping, and time dynamic analysis based on multispectral data to obtain the second PPFD.

[0073] It should be noted that the specific details of this possible implementation method can be found in existing solutions, and will not be elaborated upon in this application.

[0074] S403, the information generation device determines the target PPFD of the target plant in three-dimensional space based on the first PPFD, the second PPFD and the target weight.

[0075] As one possible implementation, the information generation device uses the sum of the first product and the second product as the target PPFD of the target plant in three-dimensional space.

[0076] The first product is the product of the first PPFD and the target weight, and the second product is the product of the second PPFD and the first difference, where the first difference is the difference between 1 and the target weight.

[0077] For example, the information generation device determines the target PPFD of the target plant based on the following relationship:

[0078] PPFD final =α·PPFD lidar+ (1-α)·PPFD spectral

[0079] Among them, PPFD lidar Indicates the first PPFD, PPFD spectral Indicates the second PPFD, PPFD final Let PPFD represent the target weights, and α represent the target weights. The first product is α·PPFD. lidar The second product is (1-α)·PPFD spectral .

[0080] Based on steps S401-S403, three-dimensional point cloud data of the target plant's three-dimensional structural layer and multispectral data of the target plant are acquired. Then, the first photosynthetic photon flux density (PPFD) is determined based on the three-dimensional point cloud data, and the second PPFD is determined based on the multispectral data. Finally, the target PPFD of the target plant in three-dimensional space is determined based on the first PPFD, the second PPFD, and the target weight. On the one hand, the three-dimensional point cloud data can reflect the influence of the target plant's own structure on light distribution; on the other hand, the multispectral data can take into account the spectral characteristics of different light sources and the spectral composition of ambient light. Therefore, the obtained target PPFD can more realistically reflect the actual light exposure of the plant in complex light environments, thus enabling the determination of the target PPFD of the target plant in three-dimensional space.

[0081] S404. The information generation device performs visualization processing on the target PPFD of the target plant to obtain a PPFD cloud map of the target plant in three-dimensional space.

[0082] As one possible implementation, the information generation device uses graphics processing software, such as the relevant image processing toolbox in MATLAB, to convert the target PPFD into a 3D PPFD cloud image. Through color encoding, areas of high PPFD intensity are displayed in red, and areas of low intensity are displayed in blue.

[0083] Based on S404, by visualizing the target PPFD (Photogrammetric Photogrammetry), growers can intuitively see the light distribution within the three-dimensional space of the plant. Growers can accurately determine which areas are under-lit based on the PPFD cloud map, and thus adjust the position and intensity of supplemental lighting fixtures to achieve precise supplemental lighting.

[0084] The above is a general description of the information generation method provided in this application. The following will provide a further description of the information generation method provided in this application in conjunction with the accompanying drawings.

[0085] In one design, Figure 5 A flowchart illustrating another information generation method provided in this application is shown below. Figure 5 As shown, the information generation method provided in this application may further include the following steps:

[0086] S501, The information generation device acquires multiple first data sets for each plant in at least one plant.

[0087] The first dataset includes the third, fourth, and fifth PPFDs of the plant under a preset light intensity. The third PPFD is a PPFD determined based on the plant's three-dimensional point cloud data, the fourth PPFD is a PPFD determined based on the plant's multispectral data, and the fifth PPFD is the plant's actual PPFD. Each first dataset corresponds to a different preset light intensity.

[0088] It should be noted that at least one plant can be of the same species or different species. For example, taking the number of at least one plant as 20, the 20 plants can include 20 species, 19 species, one species, or two species. This application does not impose any specific restrictions in this regard.

[0089] As one possible implementation, 20 common and representative economic crops are provided, and 5 different preset light intensities are set, ranging from 200 to 1000 μmol / m². 2 / s. 400 sets of experimental conditions were assigned according to the L25(5^6) orthogonal array.

[0090] The information generation device sends instructions to the lidar and multispectral camera every 5 minutes for each plant under each light intensity to obtain the plant's three-dimensional point cloud data and multispectral data. The third PPFD is determined based on the three-dimensional point cloud data, and the fourth PPFD is determined based on the multispectral data.

[0091] Meanwhile, the information generation device sends a command to the PPFD sensor every 5 minutes for each plant under each light intensity to obtain the plant's fifth PPFD. The PPFD sensor can then measure the plant's true PPFD.

[0092] It should be noted that the determination of the third PPFD based on 3D point cloud data, the determination of the fourth PPFD based on multispectral data, and the specific description of the PPFD sensor can be found in existing solutions, and will not be described further in this application.

[0093] S502, the information generation device determines the sixth PPFD corresponding to each of the multiple original weights for each of the first data sets.

[0094] Wherein, the sixth PPFD is the sum of the third product and the fourth product, the third product is the product of the third PPFD in the first data set and the original weight, the fourth product is the product of the fourth PPFD in the first data set and the second difference, and the second difference is the difference between 1 and the original weight.

[0095] As one possible implementation, taking the implementation provided by S501 as an example, the information generation device sets multiple original weights, each of which ranges from 0 to 1.

[0096] For each of the multiple original weights, and for each of the multiple first data sets in S501, the information generation device multiplies the third PPFD in the first data set with the original weight to obtain a third product. The information generation device multiplies the fourth PPFD in the first data set with the second difference (i.e., the difference between 1 and the original weight) to obtain a fourth product. The information generation device adds the third product and the fourth product to obtain the sixth PPFD corresponding to each first data set.

[0097] S503, the information generation device determines the target weight based on multiple second data sets for each of the multiple original weights.

[0098] The second data set includes the sixth PPFD and the fifth PPFD corresponding to the sixth PPFD.

[0099] It should be noted that after determining the sixth PPFD corresponding to a first data set for each of the multiple original weights, the information generation device can use the sixth PPFD and the fifth PPFD in the first data set corresponding to the sixth PPFD as a second data set of the original weights.

[0100] As one possible implementation, the information generation device takes the difference between the sixth PPFD and the corresponding fifth PPFD as the third difference for each second data set of each original weight. Then, for each original weight, it determines the mean square error of the multiple third differences of the original weight. Subsequently, it performs iterative calculation based on the mean square errors corresponding to the multiple original weights and the Nelder-Mead algorithm to determine the target weight. The mean square error corresponding to the target weight is less than the mean square error corresponding to any one of the original weights.

[0101] It should be noted that for a detailed description of this possible implementation method, please refer to the relevant description in the subsequent sections of the specific implementation method of this application, which will not be described here.

[0102] Based on steps S502-S503, a first data set is acquired for each plant in at least one plant, including a third, fourth, and fifth PPFD of the plant under a preset light intensity. Then, for each of the multiple original weights, a sixth PPFD corresponding to each first data set is determined. The sixth PPFD is the sum of the third and fourth products. The third product is the product of the third PPFD in the first data set and the original weight, and the fourth product is the product of the fourth PPFD in the first data set and the second difference, where the second difference is the difference between 1 and the original weight. Subsequently, a target weight is determined based on multiple second data sets for each of the multiple original weights. Since the second data sets include the sixth PPFD and the corresponding fifth PPFD, and the third PPFD is determined based on the plant's 3D point cloud data, the fourth PPFD is determined based on the plant's multispectral data, and the fifth PPFD is the plant's true PPFD, the preset light intensity corresponding to each second data set is different. This allows for the determination of the target weight based on different light intensities and different plants, thereby improving the accuracy of the determined target weight.

[0103] In one design, Figure 6 A flowchart illustrating an information generation method provided in this application is shown below. Figure 6 As shown, S503 provided in this application specifically includes the following steps:

[0104] S601, for each second data set of each original weight, the information generation device takes the difference between the sixth PPFD and the corresponding fifth PPFD as the third difference.

[0105] As one possible implementation, the information generation device, for each second data set of each original weight, subtracts the sixth PPFD from the corresponding fifth PPFD to obtain a third difference value, and then obtains multiple third differences values ​​for each original weight.

[0106] S602, the information generation device determines the mean square error of multiple third differences of the original weights for each of the multiple original weights.

[0107] As one possible implementation, the information generation device determines the mean square error of multiple third differences for each original weight based on the following relationship:

[0108] MSE=Σa 2 / n

[0109] Where MSE represents the mean squared error of an original weight, a represents the third difference of the original weight, and n indicates the number of third differences of the original weight.

[0110] S603, the information generation device determines the target weight by iteratively calculating the mean square error corresponding to multiple original weights and the Nelder-Mead algorithm.

[0111] The mean squared error corresponding to the target weight is less than the mean squared error corresponding to any of the original weights.

[0112] As one possible implementation, the information generation device iteratively calculates the initial weights based on the mean squared errors corresponding to multiple original weights and the Nelder-Mead algorithm; the mean squared error corresponding to the initial weights is less than the mean squared error corresponding to any one of the original weights; a two-tailed t-test is performed on the initial weights to obtain the test result; if the test result indicates that the test has passed, the initial weights are used as the target weights.

[0113] It should be noted that for a detailed description of this possible implementation method, please refer to the relevant description in the subsequent sections of the specific implementation method of this application, which will not be described here.

[0114] As another possible implementation, the information generation device iteratively calculates the target weight based on the mean square error corresponding to multiple original weights and the Nelder-Mead algorithm; the mean square error corresponding to the target weight is less than the mean square error corresponding to any one of the original weights.

[0115] It should be noted that the specific details of this possible implementation method can be found in existing solutions, and will not be described further in this application.

[0116] Based on S601-S603, for each second data set of each original weight, the difference between the sixth PPFD and the corresponding fifth PPFD is used as the third difference. For each original weight, the mean square error of multiple third differences of the original weight is determined. The target weight is determined by iterative calculation based on the mean square error of multiple original weights and the Nelder-Mead algorithm. Since the mean square error of the target weight is smaller than the mean square error of any original weight, the Nelder-Mead algorithm can perform iterative calculation to search for the optimal target weight in a wider range of weight values. In each iteration, the weight is adjusted according to certain rules based on the current weight value and mean square error, trying to find a smaller mean square error. This can gradually approach the global optimum, rather than being limited to multiple original weights, thus obtaining a more accurate target weight and improving the accuracy of determining the PPFD of the target plant.

[0117] In one design, Figure 7 A flowchart illustrating another information generation method provided in this application is shown below. Figure 7 As shown in the detailed embodiments of this application, S603 may specifically include the following steps:

[0118] S701, the information generation device determines the initial weights by iteratively calculating the mean square error corresponding to multiple original weights and the Nelder-Mead algorithm.

[0119] The mean squared error corresponding to the initial weight is less than the mean squared error corresponding to any original weight.

[0120] It should be noted that the specific details of this possible implementation method can be found in existing solutions, and will not be described further in this application.

[0121] S702. The information generation device performs a two-tailed t-test based on the initial weights to obtain the test results.

[0122] As one possible implementation, the information generation device performs a two-tailed t-test to calculate the p-value for each set of iteration results. If the p-value is less than 0.01 and the iteration result is within the 95% confidence interval, the test result is determined to be a pass; otherwise, the test result is determined to be a fail.

[0123] S703. When the detection result indicates that the detection has passed, the information generation device uses the initial weight as the target weight.

[0124] Furthermore, if the inspection result indicates that the inspection has failed, the information generating device sends a message indicating that the inspection has failed to the display device, so that the display device displays the inspection result.

[0125] Based on S701-S703, the initial weights are determined by iterative calculation using the mean squared errors corresponding to multiple original weights and the Nelder-Mead algorithm. The mean squared error corresponding to the initial weights is less than the mean squared error corresponding to any one of the original weights. A two-tailed t-test is performed based on the initial weights to obtain the test results. If the test results indicate that the test has passed, it means that the results are reliable and the optimized target weights are effective. Using the initial weights as the target weights can improve the accuracy of the determined target weights.

[0126] In one design, Figure 8 A flowchart illustrating another information generation method provided in this application is shown below. Figure 8 As shown, the information generation method provided in this application may also include the following steps:

[0127] S801, The information generation device acquires the actual growth curve of the target plant's environmental data and target growth data within the target time period.

[0128] It should be noted that environmental data may include data such as temperature, humidity, and light intensity, while target growth data may include data such as plant height and leaf condition. This application does not impose specific restrictions on these data.

[0129] As one possible implementation, the information generation device receives environmental data from various environmental sensors, such as temperature sensors, humidity sensors, and light sensors, and receives data from equipment monitoring the growth of the target plant to obtain target growth data, and further generates the actual growth curve.

[0130] It should be noted that the specific method for generating the actual growth curve can refer to existing methods, and will not be described in this application.

[0131] S802. When the similarity between the actual growth curve and the standard growth curve is less than a preset similarity threshold, the information generation device determines that the target plant is growing abnormally.

[0132] It should be noted that the similarity threshold can be 80% or 90%, and of course, other values ​​are also possible. This application does not impose any specific restrictions on this.

[0133] As one possible approach, the information generation device compares the actual growth curve with a preset standard growth curve to obtain the similarity between the two. If the similarity is less than a preset similarity threshold, the target plant is identified as having abnormal growth.

[0134] S803, The information generation device determines growth recommendation information for the target plant based on environmental data.

[0135] As one possible approach, the information generation device utilizes an established light environment-growth trait correlation index table to analyze the relationship between light environment data and growth data. If the light intensity is below the standard and the target plant grows slowly, it may be due to insufficient light affecting photosynthesis. In this case, it is recommended to adjust the position of supplemental lighting, increase the duration of light exposure, or increase the light intensity. By analyzing multispectral data, it can be determined whether the target plant is lacking specific nutrients. For example, if the spectrum shows low chlorophyll content, it may be due to nitrogen deficiency, and the solution is to apply nitrogen fertilizer appropriately.

[0136] Based on S801-S803, the actual growth curve of the target plant's environmental data and target growth data within the target time period is obtained; if the similarity between the actual growth curve and the standard growth curve is less than a preset similarity threshold, the target plant's growth is determined to be abnormal; growth suggestions for the target plant are determined based on the environmental data.

[0137] The foregoing mainly describes the solutions provided by the embodiments of this application from the perspective of an information generation device executing an information generation method. To achieve the above functions, the information generation device includes hardware structures and / or software modules corresponding to each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0138] This application embodiment can divide the information generation device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation. Furthermore, "module" here can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0139] When using functional module division Figure 9 A schematic diagram of an information generation device is shown. Figure 9 As shown, the information generation device 90 includes an acquisition module 901 and a processing module 902.

[0140] In some embodiments, the information generation device 90 may further include a storage module. Figure 9 (Not shown in the image) is used to store program instructions and data.

[0141] The acquisition module 901 is used to acquire three-dimensional point cloud data and multispectral data of the target plant; the three-dimensional point cloud data is used to indicate the three-dimensional structure of the target plant; the processing module 902 is used to determine the first PPFD based on the three-dimensional point cloud data and the second PPFD based on the multispectral data; the processing module 902 is also used to determine the target PPFD of the target plant in three-dimensional space based on the first PPFD, the second PPFD and the target weight.

[0142] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0143] When the functions of the above modules are implemented in hardware... Figure 10 A schematic diagram of yet another information generation device is shown. For example... Figure 10 As shown, the information generation device 100 includes a processor 1001, a memory 1002, and a bus 1003. The processor 1001 and the memory 1002 can be connected via the bus 1003.

[0144] The processor 1001 is the control center of the information generation device 100. It can be a single processor or a collective term for multiple processing elements. For example, the processor 1001 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0145] As one embodiment, processor 1001 may include one or more CPUs, for example Figure 10 CPU0 and CPU1 are shown in the diagram.

[0146] The memory 1002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0147] As one possible implementation, the memory 1002 can exist independently of the processor 1001. The memory 1002 can be connected to the processor 1001 via the bus 1003 and is used to store instructions or program code. When the processor 1001 calls and executes the instructions or program code stored in the memory 1002, it can implement the information generation method provided in the embodiments of this application.

[0148] In another possible implementation, the memory 1002 can also be integrated with the processor 1001.

[0149] Bus 1003 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0150] It should be pointed out that, Figure 10 The structure shown does not constitute a limitation on the information generation device 100. Except... Figure 10 In addition to the components shown, the information generation device 100 may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0151] As an example, combined Figure 9 The functions implemented by the acquisition module 901 and the processing module 902 in the information generation device 90 are the same as those of the acquisition module 901 and the processing module 902. Figure 10 The processor 1001 in it has the same function.

[0152] Optional, such as Figure 10 As shown, the information generation device 100 provided in this application embodiment may further include a communication interface 1004.

[0153] The communication interface 1004 is used to connect with other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. The communication interface 1004 may include a receiving unit for receiving data and a transmitting unit for sending data.

[0154] In one possible implementation, the communication interface 1004 in the information generation apparatus 100 provided in this application embodiment can also be integrated into the processor 1001, and this application embodiment does not specifically limit this.

[0155] As a possible product form, the information generation device of this application embodiment can also be implemented using one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0156] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0157] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed, causes a computer to perform the various steps in the method flow shown in the above method embodiments.

[0158] Embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform the various steps in the method flow shown in the above-described method embodiments.

[0159] This application provides a chip system, including: a processor and an interface circuit; the interface circuit is used to receive computer programs or instructions and transmit them to the processor; the processor is used to execute the computer programs or instructions so that the chip system performs each step in the method flow shown in the above method embodiments.

[0160] The computer-readable storage medium may 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 computer-readable storage media (a non-exhaustive list) include: 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), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in a purpose-specific ASIC. In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0161] Since the information generation apparatus, computer-readable storage medium, and computer program product provided in this embodiment can be applied to the information generation method provided in this embodiment, the technical effects they can achieve can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0162] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0163] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. An information generation method, characterized in that, The method includes: Acquire the three-dimensional point cloud data and multispectral data of the target plant; Based on 3D point cloud data, photon flux distribution simulation, photon flux to PPFD conversion and spatial aggregation are performed to obtain the first PPFD; Based on multispectral data, radiation correction, reflectance calculation, photosynthetically active radiation estimation, canopy light interception rate calculation, PPFD distribution modeling, pixel-level PPFD mapping, and time dynamic analysis are performed to obtain the second PPFD; the target PPFD of the target plant in three-dimensional space is determined according to the first PPFD, the second PPFD, and the target weight.

2. The method according to claim 1, characterized in that, The step of determining the target PPFD of the target plant in three-dimensional space based on the first PPFD, the second PPFD, and the target weight includes: The sum of the first product and the second product is taken as the target PPFD of the target plant in three-dimensional space; the first product is the product of the first PPFD and the target weight, and the second product is the product of the second PPFD and the first difference, where the first difference is the difference between 1 and the target weight.

3. The method according to claim 2, characterized in that, The method further includes: Obtain multiple first data sets for each plant in at least one plant; the first data set includes a third PPFD, a fourth PPFD, and a fifth PPFD of the plant under a preset light intensity, wherein the third PPFD is a PPFD determined based on the plant's three-dimensional point cloud data, the fourth PPFD is a PPFD determined based on the plant's multispectral data, and the fifth PPFD is the plant's true PPFD, and the preset light intensity is different for each first data set; For each of the multiple original weights, a sixth PPFD is determined for each first data set; the sixth PPFD is the sum of the third product and the fourth product, the third product is the product of the third PPFD in the first data set and the original weight, the fourth product is the product of the fourth PPFD in the first data set and the second difference, and the second difference is the difference between 1 and the original weight. The target weight is determined based on multiple second data sets for each of the multiple original weights; the second data sets include a sixth PPFD and a fifth PPFD corresponding to the sixth PPFD.

4. The method according to claim 3, characterized in that, Determining the target weight based on multiple second data sets for each of the multiple original weights includes: For each second data set with each original weight, the difference between the sixth PPFD and the corresponding fifth PPFD is taken as the third difference. For each of the multiple original weights, determine the mean square error of multiple third differences of the original weights; The target weight is determined by iterative calculation using the mean squared errors corresponding to multiple original weights and the Nelder-Mead algorithm; the mean squared error corresponding to the target weight is less than the mean squared error corresponding to any one of the original weights.

5. The method according to claim 4, characterized in that, The step of determining the target weight by iterative calculation using the mean squared error corresponding to multiple original weights and the Nelder-Mead algorithm includes: The initial weights are determined by iterative calculation using the mean squared errors corresponding to multiple original weights and the Nelder-Mead algorithm; the mean squared error corresponding to the initial weights is less than the mean squared error corresponding to any one of the original weights. A two-tailed t-test was performed based on the initial weights to obtain the test results; If the test result indicates that the test has passed, the initial weight shall be used as the target weight.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Obtain the actual growth curve of the target plant's environmental data and target growth data within the target time period; If the similarity between the actual growth curve and the standard growth curve is less than a preset similarity threshold, the target plant is determined to have abnormal growth. Growth recommendations for the target plant are determined based on the environmental data.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: The target PPFD of the target plant is visualized to obtain a PPFD cloud map of the target plant in three-dimensional space.

8. An information generation device, characterized in that, The information generation apparatus includes: a processor coupled to a memory for storing programs or instructions, which, when executed by the processor, cause the apparatus to perform the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, they cause the computer to perform the method as described in any one of claims 1 to 7.

10. A computer program product comprising instructions that, when run on a computer, enable the computer to perform the method as described in any one of claims 1 to 7.

Images