GEOGRAPHICALLY EXTENDED RECORDING OF CROFT LOSSES

Abstract

A harvest loss correction system receives one or more harvest loss sensor signals indicating harvest loss by a harvesting machine. A correction component receives geographic context information from a set of geographic context detection components to determine the harvesting machine's geographic context. Based on this geographic context information, the correction component corrects the harvest loss sensor signals to produce a corrected loss signal that reflects the detected harvest loss, adjusted for the machine's mobile context. The corrected loss signal is then output to a device.

Description

AREA OF DESCRIPTION This description concerns agricultural data collection. In particular, this description concerns the use of geographical information to enhance crop loss recording in a harvesting machine. BACKGROUND There is a wide variety of different types of harvesting machines that harvest crops. Some of these machines have sensors designed to detect crop losses. Harvest loss sensors generate a sensor signal indicating the amount of crop lost during harvesting. For example, some modern agricultural operations use combine harvesters to harvest grain. It is common for combine harvesters to include loss sensors that capture a metric indicating the amount of crop lost during the harvesting process. These loss sensors can comprise a number of sensors that monitor grain loss at various parts of the combine. For instance, they might include a number of sieve box loss sensors that detect grain losses at the sieve box. They might also include a number of separator loss sensors that detect losses at the separator. A wide variety of sensor types exist.Such sensors can include, for example, shock sensors that count the grain impacts per unit of time (or per unit of distance traveled) to give an indication of the amount of grain lost. The above discussion is provided for general background information only, and it is not intended to be used as an aid in determining the scope of protection of the claimed subject matter. SUMMARY A harvest loss correction system receives one or more harvest loss sensor signals indicating harvest loss by a harvesting machine. A correction component receives geographic context information from a set of geographic context detection components to determine the harvesting machine's geographic context. Based on this geographic context information, the correction component corrects the harvest loss sensor signals to produce a corrected loss signal that reflects the detected harvest loss, adjusted for the machine's mobile context. The corrected loss signal is then output to a device. This summary is provided to present, in simplified form, a selection of concepts that are described in more detail below. This summary is not intended to identify key features or essential characteristics of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of protection of the claimed subject matter. The claimed subject matter is not limited to implementations that overcome some or all of the disadvantages noted in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a block diagram of an example of a crop loss correction architecture. Fig. 2 is a graphical representation of an example of a subsection of the architecture shown in Fig. 1, used on a combine harvester. Fig. 3 is a flowchart illustrating an example of generating a knowledge base used to correct crop loss sensor signals. Fig. 4 is a flowchart illustrating an example of the operation of the architecture shown in Fig. 1 in generating and outputting a corrected loss value. Fig. 5 is a block diagram of an example of a correction component. Fig. 6 is a flowchart illustrating an example of the operation of the grain loss correction system. Fig. 7 is a flowchart illustrating an example of the operation of a loss output system. Fig. 8 is a block diagram of an example of a remote server environment. Fig. 9, Fig. 10 to Fig.Figure 11 shows examples of mobile devices that can be used in the architectures shown in the preceding figures. Figure 12 is a block diagram of an example of a data processing environment that can be used in the architectures shown in the preceding figures. DETAILED DESCRIPTION For a better understanding of the principles of this disclosure, reference is now made to the examples illustrated in the drawings, which are described in specific language. However, it is understood that this is not intended to limit the scope of protection of the disclosure. Any modifications and further alterations to the described devices, systems, and methods, and any further application of the principles of this disclosure, are fully covered, as would normally be apparent to a person skilled in the art in the field to which the disclosure relates. In particular, it is fully covered that the features, components, and / or steps described in relation to one example can be combined with the features, components, and / or steps described in relation to others in this disclosure. As discussed above, many harvesting vehicles are equipped with loss sensors that detect the loss of harvested material during the harvesting process. If the harvesting vehicle is, for example, a grain harvester, the loss measurement is prone to inaccuracies. Furthermore, the accuracy of the sensors can depend on a wide variety of contextual information that specifies the harvesting machine's operating environment. This description therefore describes a system that captures a variety of different context features corresponding to a harvesting vehicle, the harvested crop, or other context features, and uses these context features to generate, for example, a corrected loss signal or a corrected loss value based on a loss sensor signal generated by a loss sensor. This description subsequently refers to a system that can perform sensor fusion to combine the outputs of several different context sensors and generate a sensor fusion correction output. Likewise, this description describes a system that can identify geographic and / or historical context information and generate a geographic or historical output signal.This description further details a system capable of acquiring various pressures as contextual information. These pressures can include barometric pressure or internal pressure within the harvester body to generate a pressure correction output signal. Based on the geographic and / or historical correction output, the sensor fusion correction output, and / or the pressure correction output, the system can select a specific loss correction system to correct a loss signal or value generated by shock sensors that detect grain fields on the material discharged from the harvester. Fig. 1 is a partly pictorial, partly schematic representation of the agricultural harvesting vehicle 100. The harvesting vehicle 100 comprises a vehicle body 102 and a harvesting head (or header) 104, which is connected to the vehicle body 102. The harvesting vehicle 100 includes an operator's compartment 101, inclined conveyor 106, a feed accelerator 108, and a threshing unit, generally indicated at 110. The inclined conveyor 106 and the feed accelerator 108 are part of a material handling system 125. The harvesting head 104 is pivotably coupled to the frame 103 of the non-harvesting header 102 along the pivot axis 105. One or more actuators 107 drive the movement of the harvesting head 104 about the axis 105 in the direction generally indicated by the arrow 109.The vertical position of the harvesting header 104 (harvesting header height) above the ground 111, on which the harvesting header 104 moves, can be controlled by actuating the actuator 107. Although not shown in Fig. 1, the agricultural harvesting vehicle 100 can also include one or more actuators that are actuated to apply an angle of inclination, a tilt angle, or both to the harvesting header 104 or sections of the harvesting header 104. The threshing unit 110 includes, for example, a threshing rotor 112 and a series of threshing concaves 114. The agricultural harvesting vehicle 100 further includes a separator 116. The agricultural harvesting vehicle 100 also includes a cleaning subsystem or sieve box (collectively referred to as cleaning subsystem 118), which includes a cleaning blower 120, a chaff sieve 122, and a fine sieve 124. The material handling subsystem 125 further includes an unloading drum 126, a return elevator 128, and a clean grain elevator 130. The clean grain elevator conveys clean grain into a clean grain tank 132. The harvesting vehicle 100 also includes a material transfer system comprising a conveying mechanism 134, a chute 135, and a discharge spout 136. The conveying mechanism 134 can be a variety of different types of conveying mechanisms, such as an auger or a blower. The conveying mechanism 134 is connected to the grain tank 132 and is driven (e.g., hydraulically, mechanically, or electrically, etc.) to convey material from the grain tank 132 through the unloading pipe 135 and the discharge spout 136. The unloading pipe 135 is rotatable away from the agricultural harvesting vehicle 100 through a series of positions (shown in the stowed position in Fig. 1) to align the discharge spout 136 relative to a material container (e.g., grain wagon, towed trailer, etc.) designed to receive the material.In some examples, the discharge spout 136 is also rotatable in order to adjust the direction of the crop flow exiting the discharge spout 136. The harvesting vehicle 100 also includes a residue handling system 138, which may comprise a chopper 140 and a spreader 142. The harvesting vehicle 100 also includes a drive system with a motor that drives ground-contacting traction components such as 144 or 144 and 145 to move the harvesting vehicle 100 across a work area such as a field (e.g., the ground 111). In some examples, a harvesting vehicle within the scope of this disclosure may have more than one of the aforementioned subsystems. In some examples, the harvesting vehicle 100 may have left and right cleaning systems, separators, etc., which are not shown in Fig. 1. In operation, and for overview purposes, the harvesting vehicle 100 moves through a field in the direction indicated by arrow 147. As the harvesting vehicle 100 moves, the harvesting header 104 engages with the crop plants to be harvested and separates the harvested material (e.g., the cob or the head) from the plants. The separated crop material is captured by a transverse screw conveyor 113, which conveys it to the center of the header 104. From there, a conveyor belt in the inclined conveyor 106 moves the separated crop material to the feed accelerator 108, which accelerates it into the threshing unit 110. The separated crop material is threshed by the rotor 112, which rotates it against threshing concaves 114. The threshed crop material is moved by a separator rotor in the separator 116, with some of the residue being conveyed by the discharge drum 126 to the residue sorting system 138. The residue transferred to the residue sorting system 138 is chopped by the residue chopper 140 and spread on the field by the spreader 142. In other configurations, the residues are released in a swath from the agricultural harvesting vehicle 100. The grain falls into the cleaning subsystem 118. The chaff screen 122 separates some larger material particles from the grain, and the fine screen 124 separates some finer material particles from the clean grain. The clean grain falls onto a screw conveyor, which moves the grain to the inlet end of the clean grain elevator 130. The clean grain elevator 130 moves the clean grain upwards and stores it in the clean grain tank 132. Residues are removed from the cleaning subsystem 118 by an airflow generated by the cleaning blower 120. The cleaning blower 120 directs air upwards along an airflow path through the fine and chaff screens. The airflow transports residues backwards in the harvester 100 to the residue handling subsystem 138. The return elevator 128 directs the returned material back to the threshing unit 110, where it is threshed again. Alternatively, the returned material can also be directed to a separate re-threshing mechanism using a return elevator or other transport device, where it is also threshed again. The harvesting vehicle 100 can include a variety of sensors, some of which are shown in Fig. 1, such as position sensor 145, ground speed sensor 146, one or more separation loss sensors 148, a pure grain camera 150 and one or more loss sensors 152 provided in the cleaning subsystem 118, body pressure sensor 160, air pressure sensor 162, chaff volume sensor 164, non-grain (NCB) volume sensor 166, a crop property sensor, such as NKB moisture sensor MOG 168, crop moisture sensor 170, etc. The position sensor 145 can be a Global Navigation Satellite System (GNSS) receiver, a cellular triangulation system, a dead reckoning navigation system or another type of sensor that provides the location of the harvesting vehicle 100 in a global or local coordinate system. The ground speed sensor 146 detects the ground speed of the harvesting vehicle 100 above the ground 111. The ground speed sensor 146 can detect the ground speed of the harvesting vehicle 100 by measuring the rotational speed of the ground-contacting traction components (such as wheels or tracks), a drive shaft, an axle, or other components. In some cases, the ground speed can be detected using the input signal from other sensors, such as a position sensor 145, or the sensor 146 may be a Doppler velocity sensor or a variety of other systems or sensors that provide a ground speed reading. The ground speed sensors 146 may also include direction sensors such as a compass, a magnetometer, a gravimetric sensor, a gyroscope, or a GPS signal to determine the direction of travel in two or three dimensions in combination with the speed.If the harvesting vehicle 100 is located on a slope, its orientation relative to the slope is known in this way. An orientation of the harvesting vehicle 100 could be, for example, uphill, downhill, or parallel to the slope (e.g., tilted to one side or the other). The separation loss sensor 148 provides a signal indicating grain loss in the left and right separators, not shown separately in Fig. 1. The separation loss sensors 148 can be assigned to the left and right separators and can be impact sensors that count grain impacts per unit of time or per unit of distance traveled to provide an indication of the grain loss occurring at separator 110. Sensors 148 can provide separate grain loss signals or a combined or aggregated signal. In some cases, the detection of grain loss in the separators can also be achieved using a wide variety of different types of sensors. Loss sensors 152, for example, provide an output signal indicating the amount of grain loss on the right and left sides of the cleaning subsystem 118. In some examples, the sensors 152 are impact sensors that count the grain impacts per unit of time or per distance traveled to indicate the grain loss occurring in the cleaning subsystem 118. The impact sensors for the right and left sides of the cleaning subsystem 118 can provide individual signals or a combined or aggregated signal. In some examples, the sensors 152 can comprise a single sensor, unlike separate sensors provided for each cleaning subsystem 118. The clean grain camera 150, for example, observes the grain being conveyed or having been conveyed into the clean grain tank 132. The clean grain camera 150 can detect various parameters, such as the cleanliness of the grain located in or being conveyed to the clean grain tank 132. For example, the clean grain camera 150 can detect the amount of NKB that has mixed with the grain in or on its way to the clean grain tank 132. The body pressure sensor 160 detects the pressure inside the body of the harvester 100. The cleaning blower 120 can interact with a series of vents to increase or decrease the pressure inside the body of the harvester 100. When the blower speed increases and / or the vents are closed, the pressure inside the body of the harvester 100 increases. When the blower speed decreases and / or the vents are opened, the pressure decreases. The sensor 160 can be a diaphragm sensor or another type of sensor. The air pressure sensor 162 detects the air pressure in the vicinity of the harvesting vehicle 100. The chaff volume sensor 164 detects the volume of chaff processed by the harvesting vehicle 100 and generates an output signal indicating the measured volume. For example, the chaff volume sensor 164 can detect the volume of material on the sieve box 118. This volume indicates the amount of chaff in the system. Thus, the chaff volume sensor 164 can be an optical sensor that captures an image of the chaff on the sieve box 118 and processes this image to generate a volume output signal indicating the volume of the chaff. The chaff volume sensor 164 can also be a different type of contact or non-contact sensor. The NKB volume sensor 166 detects the volume of NKB processed by the harvesting vehicle 100 and generates an output signal indicating this volume. Thus, the NKB volume sensor 166 can detect the amount of material on the separator 110. The NKB volume sensor 166 can therefore be an optical sensor or another type of sensor that detects the volume of NKB on the separator 110. The harvesting vehicle 100 can include additional sensors that detect parameters of the harvested crop. These parameters can include moisture content or other characteristics. For example, the NKB moisture sensor 168 can be a capacitive sensor or another type of sensor that detects the moisture content of the NKB in the harvesting vehicle 100. The moisture sensor for the harvested material 170 can also be a capacitive sensor or another type of sensor that detects the moisture content of the grain harvested by the harvesting vehicle 100. The sensors can also include a wide variety of other sensors. For example, a grain weight sensor 171 can be used to collect a number of grains to obtain a grain weight metric (such as a thousand-grain weight value) that indicates the weight of a specific number of grains (e.g., one thousand grains). A collection chamber can be used to divert grains from the pure grain flowing through the elevator 130. An optical sensor or other sensor can be used to count the number of grains collected, and a scale or other measuring device can be used to measure the weight of the collected grains. Other methods for determining a grain weight value are also included here. Furthermore, the sensors can include a mass flow sensor that detects the mass flow of the material through the harvester 100.Such a sensor can detect the rotor pressure of rotor 112 or the mass of the material flowing through the pure grain elevator 130 or elsewhere. These and other sensors are included here. Furthermore, a grain flow sensor or yield sensor 133 can be arranged to detect the mass flow of the grain or the yield of the grain or other harvested crop. Sensor 133 can detect the pure grain flowing through the harvesting vehicle per unit of time. Sensor 133 can be, for example, a force-based system, a volume-based system, a torque-based system, an image acquisition and processing system, or a fusion system that uses the output signals of sensor 171 and a grain size sensor to generate a volume. Fig. 2 is a block diagram of an example of a crop loss correction architecture 200. The architecture 200 shows a mobile machine 102 that generates operator interfaces 204 for interaction by the user (or operator 206). The operator interfaces 204 can include displays, acoustic outputs, haptic outputs, etc. The operator interfaces 204 can also include a set of operator input mechanisms 208. The operator 206 interacts, for example, with the operator input mechanisms 208 to control and operate different sections of the mobile machine 100. The architecture 200 also shows that the mobile machine 100 can be connected to various remote systems 210. The operator 206 can also use other user input mechanisms 212 to interact with the mobile machine 100. The operator input mechanisms 208 can be displayed on the operator interface displays 204. These displays can be touch-sensitive indicators, icons, links, etc. Other operator input mechanisms 208 can be a whole range of user input mechanisms that can be used to control the machine 100. These can include switches, levers, pushbuttons, keyboards, pedals, steering wheels, joysticks, etc. In the example described here, some or all of the components represented in the mobile machine 100 can be located on the external machine, on a remote system (e.g., in the cloud), or distributed across different systems in different locations. It should also be noted that while the following discussion refers to a mobile machine 100 for harvesting grain, the machine 100 could also be a harvesting machine for other crops. In the example shown in Fig. 2, the mobile machine 100 comprises, for illustrative purposes (and purely by way of example), one or more processors or servers 214, a communication component 216, a control system 218, controlled systems 220, a user interface component 222, and a user interface device 224. The machine 100 also includes, for illustrative purposes, a grain loss correction system 226, context detection components 228, one or more grain loss sensors 230-232, and a variety of other sensors 234. The machine 100 may include a data storage device 235 that stores geographical features 237, historical loss features 239, and other elements 241. The actual grain loss correction system 226 includes, for example, a knowledge base 236 (which may include one or more loss correction models 243, one or more loss correction algorithms 245, one or more correction tables 247, and / or other elements), a correction component 238, a context processing system 291, and may include other elements 240. The controlled systems 220 can include, for example, electrical systems, mechanical systems, hydraulic systems, pneumatic systems, air-hydraulic systems, or other systems. These systems can perform harvesting functions, be controlled by settings, be controllable subsystems, and / or have a wide variety of other functions on the mobile machine 100. The context acquisition components 228 can include a variety of sensors that acquire information about the machine 100, crop characteristics, environmental characteristics, or other information that affects the accuracy of grain loss sensors 230-232 in detecting actual grain losses. The components 228 can therefore include sensors such as a machine condition sensor 242, machine orientation sensor 244, geoposition sensor 145, crop characteristic sensor 246, sieve box blower speed sensor 248, non-grain (NPK) moisture sensor 168, machine setting sensor 152, chaff volume sensor 164, NKB volume sensor 166, air pressure sensor 162, vehicle body pressure sensor 160, crop moisture sensor 170, grain weight sensor 171, and other elements or sensors 254. The mobile machine 100 can also include other elements 256. Before the functionality of Architecture 200 is described in more detail, a brief overview of some of its elements and their operation is provided. If the mobile machine 100 is a combine harvester, the grain loss sensors 230-232 can include one or more sieve box loss sensors 152, which are used to detect grain losses at the sieve box 118. The grain loss sensors 230-232 can also include one or more separation loss sensors 148, which are used to detect grain losses at the separator 110. The grain loss sensors 230-232 can also include a variety of other grain loss sensors. The grain loss correction system 226 receives, for example, the grain loss sensor signals from sensors 230-232. It should be noted that the grain loss sensor signals sometimes do not reflect the actual grain loss. The grain loss correction system 226 therefore corrects the grain loss and provides a corrected loss signal 260. The corrected loss signal thus represents the actual grain loss more accurately than, for example, the grain loss sensor signals from grain loss sensors 230-232. In generating the corrected loss signal 260, the grain loss correction system 226 receives contextual information from the context detection components 228. This information specifies the context of the mobile machine 100, the context of the crop, the context of the environment, and so on. As described in more detail below, the contextual information can encompass a wide variety of different information that may influence, impair, or correlate with the accuracy of the signals received by the grain loss sensors 230-232 in detecting the actual grain loss. The knowledge base 236 includes, for example, corrective components (e.g., models 243, algorithms 245, tables 247, etc.) that can be generated, configured, and / or trained by the context processing system 291.The corrective components can be used to correct the sensor signals received from sensors 230-232 in order to generate a corrected loss signal 260 based on the context of the mobile machine 100. For example, the corrective component 238 receives the context information and accesses the knowledge base 236 to make corrections to the sensor signals from sensors 230-232, thereby generating a corrected loss signal 260 that more accurately reflects the actual grain loss. (For example.) The signal 260 can then be supplied to a wide variety of different components. For example, the signal 260 can be supplied to a communication component 216, which transmits the signal to remote systems 210. The signal 260 can be supplied to the control system 218, which automatically generates control signals to control the various controlled systems 220 of the mobile machine 100 based on the corrected grain loss signal 260. The signal 260 can be supplied to an operator interface component 222, which controls the operator interface device 224 to display the corrected grain loss signal to the operator 206 via visual, acoustic, haptic, or other means. The machine setting sensor 252 can include one or more sensors designed to detect the various configurable settings of the machine 100. The machine orientation sensor 244 can include a wide variety of different types of sensors capable of detecting the orientation of the machine 100. The machine orientation sensor 244 can include a GNSS receiver, inertial measurement unit(s), accelerometer, etc. Crop property sensors 246 can include one or more sensors designed to detect a wide variety of different crop properties, such as crop type, grain hardness or brittleness, and other crop characteristics. The crop property sensor 246 can also be designed to detect crop properties while the crop is being processed by the machine 100.For example, the crop property sensor 246 can include a sensor for the grain feed rate. In one example, the sensor 246 is used in the elevator 130 and measures the mass flow through the elevator 130, providing an output signal that indicates the mass throughput. The mass throughput can be used to express the mass flow and yield in bushels per hour, tons per hectare, tons per hour, or other units of measurement. Other sensors have been described elsewhere. Before describing the overall operation of machine 100, a description follows of how the grain loss correction system 226 and the data storage 235 are designed to generate the corrected loss signal 260. Fig. 3 is a flowchart illustrating an example of the operational sequence of machine 100 and the context processing system 291 for generating the knowledge base 236 in the grain loss correction system 226 and for retrieving values ​​in the data storage 235. In one example, the values ​​or corrective components are retrieved from the knowledge base 236 and / or the data storage 235 without performing the operational sequence of Fig. 3, such as by downloading the values ​​and / or corrective components or otherwise obtaining the values. In another example, the process shown in Fig.The functional sequence shown in section 3 for retrieving values ​​and / or corrective components for the knowledge base 236 and / or the data storage 235 is performed and does not need to be repeated. These values ​​can also be loaded on other similar machines. To generate values ​​in the data storage 235 and the knowledge base 236, the machine 100 can first be designed to detect the actual grain loss. For example, in one instance, the machine 100 can be equipped with an attachment or a towed mechanism that collects all the material coming out of the machine 100. This material can then be weighed or otherwise analyzed to obtain a measure of the actual grain loss with a relatively high degree of accuracy. The machine 100 can then be operated in different contexts to determine how the grain loss detected by the grain loss sensors 148, 152 (230-232) differs from the actual grain loss in these different contexts. Besides using an attachment or a towed mechanism, there are many other approaches to detecting the actual grain loss, and these are only examples.This information can then be used by the context processing system 291 to generate corrective components in the knowledge base 236, which can be used by the correction component 238 to correct the grain loss sensor signals based on a current working context of the machine 100 and thus obtain the corrected loss signal 260. Similarly, geographical features 237, which describe the terrain traversed by the machine 100 during the measurement of the actual loss, can be captured and recorded. These geo-features can include a wide variety of characteristic features, such as the gradient and slope of the terrain, the geographical elevation of the terrain, the terrain-related grip (e.g., whether wheel slippage occurs), the moisture content of the terrain (e.g., whether the ground is muddy), and / or others from a wide variety of additional geo-features. Furthermore, loss characteristics can be recorded during a harvesting operation and stored for use during a subsequent harvesting operation. These loss characteristics, referred to as historical loss characteristics 239, thus indicate various characteristic features of the harvest loss recorded during a previous harvesting operation. Examples of historical loss characteristics 239 include historical, measured grain loss in a field, at specific locations in the field, in correlation with the geographical position of the machine 100 in the field, in correlation with various environmental characteristics, and / or in correlation with various terrain features, crop characteristics, machine characteristics, or other characteristics. Fig. 3 shows that the machine context is detected first, as indicated by block 251. In one example, the various different contexts detected are those that most strongly influence the accuracy of the grain loss detected by the grain loss sensors 230-232 (e.g., separation loss sensors 148 and sieve box loss sensors 152). A discussion of several examples of different contexts that will affect the accuracy of the detected grain loss follows. However, it is clear that these are only examples. The geographical position 253 of the mobile machine 100 can affect the accuracy of the grain loss sensors 230-232. For example, the grain loss sensors 230-232 may be more or less accurate at different altitudes, in different hemispheres, in different regions of a country (such as with fluctuating humidity in different regions), or based on other geographical characteristics. The accuracy of the loss sensors 230-232 can also be affected by the chaff volume 255 measured by the chaff volume sensor 164 and / or the NKB volume 257 measured by the NKB volume sensor 166. The accuracy of the loss sensors 230-232 can also be affected based on the barometric pressure 259 measured by sensor 162, the machine body pressure 261 measured by sensor 160, and crop characteristics such as crop moisture 263 measured by sensor 170.The accuracy of the loss sensors 230-232 can also be influenced by the weight of the harvested material (e.g. thousand grain weight) 265 detected by the sensor 171. The state of machine 100, specifically whether it is configured to chop the residues or to lay and distribute a swath behind it, can affect the accuracy of the sensor signals from the grain loss sensors. That is, the ability to accurately detect grain loss using the grain loss sensors 230-232 can change depending on whether the machine state is set to chopping or swath laying. The machine state sensor 242 can thus detect machine state 267. The 246 crop property sensor can also detect a variety of different properties of the currently harvested crop. Crop type 269 is one example of a property. The ability to accurately detect grain losses can vary depending on the crop type (e.g., corn, soybeans, wheat, barley, rapeseed, etc.). The crop type can be detected by the sensor or provided by the operator and used as contextual information. The grain feed rate 256 can also provide contextual information indicating the grain loss detection performance. The sensors 246 can therefore include a mass flow sensor that detects the grain feed rate in the elevator 130, or another type of sensor for detecting the grain feed rate. Furthermore, the machine can have 100 different configurations, and the machine configuration 258 can influence the ability to accurately detect grain loss. The machine 100 can be configured with different separator mechanisms 110, and the ability to accurately detect grain loss can vary depending on the mechanism used. The machine condition sensor 242 can therefore include a sensor that indicates the machine configuration 258. The various machine settings (which can be configured by the operator or automatically) can also affect the ability to accurately measure grain loss. Therefore, the machine settings 260 can be detected by the machine setting sensor 252. In one example, the blower speed 262 of the sieve box blower 120 also affects the accuracy of grain loss detection. An excessively high blower speed can, for instance, cause some of the grain to be thrown into the air along a path where it misses the sieve box loss sensors 152. This type of grain loss is therefore not detected. For this reason, a blower speed sensor 248 can provide an indication of the blower speed 262. The orientation 264 of the machine 100, detected by the machine orientation sensor 244, can also affect the ability to accurately detect grain loss. For example, if the machine exhibits a swaying or rolling characteristic (such as when harvesting on a side slope), this can lead to an uneven distribution of sieve box loss across the width of the machine. This can impair the accuracy of the grain loss sensors 230-232. Therefore, the machine orientation sensor 244 can detect the machine orientation 264. The moisture content of the grain can affect the ability to accurately detect grain loss. For example, if the grain has a high moisture content, a grain mat 100 can form as it passes through the machine. In this case, the amount of grain that passes through the mat and can be detected by sensors 230-232 can be affected. This can be exacerbated if the grain is relatively light, as in the case of wheat. The grain is then not detected but simply carried out of the machine 100 over the highly moist grain mat, and the corresponding grain loss is not detected by any of the sensors 230-232. Therefore, the grain moisture sensor 250 can detect the grain moisture 266, and the weight sensor 171 can detect the harvested grain weight 265, and the combination of these values ​​can be used to correct for the loss. Of course, various other context sensors 254 can also capture other context information 268. Likewise, different combinations of context information can be used to correct the detected loss. Some of these combinations are described elsewhere in this document. All this information can be used by the context processing system 291 to generate the knowledge base 236 and / or the data store 235. During machine context acquisition, the machine is operated and grain loss is recorded by the grain loss sensors 230-232 on the machine, as indicated by block 270. Actual grain loss is also recorded (or otherwise determined, such as by collecting the material ejected from machine 100 and counting the losses), as indicated by block 272. The recorded grain loss and the actual grain loss for the current machine context are then correlated by the context processing system 291 to identify any discrepancy between the recorded grain loss and the actual grain loss, as indicated by block 274. This process can be repeated for a variety of different contexts, allowing the relationship between the crop loss detection error and these different contexts to be established. Block 276 therefore determines whether further contexts need to be considered. If so, the machine context is switched to the next context to be considered at block 278, and processing returns to block 250. Once all the different machine contexts have been taken into account, the context processing system 291 processes the context information, the detected loss, and the actual loss to determine correlations that can be used to correct the detected loss and to obtain the corrected loss. The correlations are then used to generate the corrective components in the knowledge base 236. The corrective components in the knowledge base 236 are used to correct the grain loss sensor signal during the operation of the machine 100. The generation of the corrective components in the knowledge base 236 is specified by block 280. The generation of the corrective components can also be achieved using a wide variety of different methods. For example, the knowledge base 236 can contain a series of adjustment values ​​that are applied to the grain loss sensor signals to adapt the sensor signals according to the machine context. The generation of adjustment values ​​is represented by block 282. In this case, the correction component 238 receives the runtime context information from the components 228 during runtime and determines an adjustment value in the knowledge base 236 to adjust the grain loss sensor signals and thus generate the corrected loss signal 260. In another example, the corrective components in the knowledge base 236 can comprise a series of reference tables 247. The reference tables 247 can be used by the corrective component 238 to perform a series of references and mathematical operations based on the context information received from the components 228 and on changes to the context information. In another example, the corrective components in the knowledge base 236 comprise one or more static or dynamic interactive models 243. In this example, the corrective component 238 can access the interactive model 243 and submit the context information received from the components 228 and the sensor signal values ​​received from the grain loss sensors 230-232, and the model can return either a corrective value or the corrected loss signal 260. The context processing system 291 can generate one or more models 243 using a wide variety of techniques, such as linear regression, probabilistic model building, machine learning (including, but not limited to, deep learning, reinforcement learning, support vector machine learning, etc.), k-nearest neighbor learning, etc. In another example, the context processing system 291 generates or modifies one or more loss correction algorithms 245 based on the context information. The loss correction algorithms may, for example, have coefficients or other factors or configurable elements that can be changed during training. The generation or modification of the loss correction algorithms 245 is shown by block 293 in the flowchart of Fig. 3. In one example, the knowledge base 236 also contains a selection component (such as selection criteria, a selection algorithm, a selection model, etc.) that can be used to select a correction system, such as a system that executes or uses different models 243, algorithms 245, reference tables 247, or other corrective components that can be used by the correction component 238 to correct the loss signal generated by the loss sensors 230-232 during runtime and thus obtain the corrected loss signal 260. Thus, in certain contexts, the use of a probabilistic correction model 243 may be more accurate, while in other contexts, the use of an artificial neural network correction model 243 may be more accurate.Furthermore, it is possible that in one context the use of a first correction algorithm 245 is more accurate, while in another context the use of a different correction algorithm 245 is more accurate. Similarly, in one context the use of a first reference table 247 may be more accurate, while in another context the use of a different reference table 247 is more accurate. The criteria for selecting a corrective component in the knowledge base 236 or a set of corrective components can also be learned and incorporated into a selection algorithm or model that takes the captured context as input and generates an output indicating which model 243, which algorithm 245, which reference table 247, etc., should be used by the correction component 238 to generate the corrected loss signal 260. The context processing system 291 therefore generates or modifies, in an example, a set of selection criteria, a selection algorithm, and / or a selection model that are used to select the corrective component 243, 245, 247 at runtime. The generation or modification of these selection criteria, algorithms, and / or models is shown by block 295 in the flowchart of Fig. 3. All these and various other techniques 288 for generating the knowledge base 236 are included here. Fig. 4 is a flowchart illustrating an example of the operation of architecture 200 (shown in Fig. 2) when generating the corrected loss signal 260 during the operation of machine 100. It is initially assumed that machine 100 is currently performing a harvesting operation and that the grain loss sensors 230-232 are providing grain loss sensor signals. The grain loss correction system 226 thus detects the sensor loss signals, as indicated by block 300. It can be seen that the grain loss sensors 230-232 can comprise a single sensor 302 (or an aggregated single signal from several sensors) or that the sensors 230-232 comprise several sensors 304, each providing a single sensor signal. Of course, other combinations of sensors and sensor signals 306 can also be used. Correction component 238 acquires the machine context information provided by the one or more context acquisition components 228, as shown in block 308. Correction component 238 then uses this context information to access one or more corrective components in knowledge base 236, as shown in block 310. Correction component 238 can apply the corrective components in knowledge base 236 to obtain corrected loss values ​​that can be applied to the sensor signals, as shown in block 312. The correction component 238 then applies these corrective components to generate the corrected loss signal 260, as shown by block 314. As mentioned above, the corrective components can be adjustment values ​​applied to the detected loss values ​​to correct them. Such adjustment values ​​can be obtained, for example, from reference tables 247, from a correction model 243, from a correction algorithm 245, etc. The adjustments can then be implemented through a series of values ​​and calculations. The adjustment values ​​can be the actual corrected loss values ​​(such as values ​​received from an interactive correction model) or other values. The corrected loss signal 260 can be output to a variety of different systems or components for a variety of purposes. For example, signal 260 can be brought to the operator interface to inform the operator about the corrected grain loss and to enable interactive operation, as shown by block 316. If, for example, the corrected grain loss signal 260 exceeds a desired value, the control system 218 can offer the operator options for reducing grain loss. As an example, the grain loss can be displayed on an operator interface display, along with user input mechanisms that can be activated to view suggested operational changes that the operator can make to reduce grain loss. In this case, the operator can activate the user input mechanism and view the suggested operational changes.This is just one example of how the corrected loss signal 260 can be prepared for the operator and operator interaction. The corrected loss signal 260 can also be provided to the control system 218, where it can be used to automatically control one or more of the various controlled systems 220 of the machine 100 in order to reduce grain loss. The automatic process can occur without notifying the operator, with a message to the operator, after receiving confirmation from the operator, or in some other way. The corrected loss signal 260 can also be delivered via the communication component 216 to one or more remote systems 210. The remote systems 210 can display the grain loss in near real-time for a person operating the remote system 210, or the grain loss system can store the corrected loss signal 260 for further analysis, mapping, or for a variety of other reasons. The grain loss correction system 226 can also output the corrected loss signal 260 to other components or systems 318. In one example, the grain loss correction system 226 intermittently repeats the process of acquiring context using components 228 and generating the corrected loss signal 260. The grain loss correction system 226 can perform this process periodically, upon triggering by changing context information, or based on other criteria. For example, the context information indicates that when the operator starts harvesting with machine 100, the crop is relatively moist. However, later in the day or during harvesting, the crop or non-grain components may have dried out. Upon detecting such a contextual change, the system 226 can repeat the process of generating the corrected loss signal 260 based on the new context information. Block 320 indicates when it is time to repeat the correction process.If so, processing returns to block 300. If not, system 226 waits either until it is time to repeat the correction process or until the harvesting process is complete, as indicated by block 322. Fig. 5 is a block diagram that illustrates an example of the correction component 238 in more detail. In the example shown in Fig. 5, the correction component 238 comprises a crop identification component 324, a context / sensor fusion correction system 326, a geographic correction system 328, a pressure-based correction system 330, a loss output system 332, and other elements 334. The context / sensor fusion correction system 326 may include an NKB moisture / crop moisture fusion component 336, a chaff / NKB ratio component 338, an NKB / grain ratio component 340, a fusion output system 342, and other elements 344. The geographic correction system 328 may include a position identifier 346, a geographic feature extraction system 348, a past loss feature extraction system 350, a geographic output system 352 and other elements 354.The pressure-based correction system 330 can include an air pressure correction processor 356, a body pressure correction processor 358, a pressure output system 360, and other elements 362. The loss output system 332 can include a system selection processor 364, a model execution system 366, an algorithm execution system 368, a reference system 370, a corrected signal output system 372, and other elements 374. The model execution system 366 can include a model selection component 376 and model execution logic that executes one or more loss correction models 243, and other elements 380. The algorithm execution system 368 can include an algorithm selection system 382, ​​algorithm execution logic that executes one or more loss correction algorithms 245, and other elements 386. The reference system 370 can include a table selection component 388, one or more correction tables 247 and other elements 390. Before describing the overall functionality of Correction Component 238 in more detail, some of the elements within Correction Component 238 and their operation will first be discussed. Crop Identification Component 324 identifies the type of crop being harvested by Machine 100. Crop Identification Component 324 can identify the crop based on operator input from Operator 206, or by accessing an inventory card or inventory table that identifies the type of crop planted in the field being harvested by Machine 100. Crop Identification Component 324 can also be a sensor, such as an optical sensor, or another type of sensor that detects the crop being harvested. An optical sensor can capture an image of the crop, and an image processing function can process the image to identify the crop.The crop identification component 324 can also identify the currently harvested crop in other ways. The context / sensor fusion correction system can merge or combine context information or sensor signals, provided that the merged or combined signal values ​​exhibit a certain correlation to the error in the grain loss signals generated by the grain loss sensors 230-232. Based on this correlation, a fusion output can be provided to the loss output system 332 for use in generating the corrected loss signal 260. The NKB moisture / crop moisture fusion component 336 can combine or merge sensor signals generated by the NKB moisture sensor 168 and crop moisture sensor 170 to produce a fusion output. If a correlation exists between the NKB moisture and crop moisture and the error in the crop loss detected by the loss sensors 230-232, this correlation can be included in a fusion output that combines the output signals from the NKB moisture sensor 168 and crop moisture sensor 170.This fusion output can be output from fusion output system 342 to loss output system 332, which uses the fusion output to generate the corrected loss signal 260. The fusion output can also be combined with other sensor signals from other sensors or with other context data to generate a different fusion output. There can also be a correlation between the error in the loss sensor signal generated by the loss sensors 230-232 and a ratio of the volume or other quantity of chaff processed by the machine 100 to the volume or other quantity of NKB. It is evident that while volume is used as the quantity processed in the present discussion, the quantity could easily be processed in other forms, such as mass, weight, mass flow, etc., and volume is used as an example. The chaff / NKB ratio component 338 receives an input from the chaff volume sensor 164 and NKB volume sensor 166 and generates a ratio of the values ​​indicated by these sensors. This ratio can be combined with any other sensor signals or other contextual data to produce a fusion output, which is provided by the fusion output system 342 to the loss output system 332. A correlation can also be established between the error in the sensor signals generated by the grain loss sensors 230-232 and the ratio of the NKB volume to the grain volume processed by the machine 100. The NKB / grain ratio component 340 can receive an output signal from the NKB volume sensor 166, which indicates the NKB volume processed by the machine 100, and from a grain flow sensor or yield sensor 133 (or another sensor, such as a signal from a grain weight sensor 171), which indicates the volume, weight, or other unit of measurement of the grain processed by the machine 100. The NKB / grain ratio component 340 can generate a ratio of these two signal values ​​and provide this ratio to the fusion output system 342. This ratio can also be combined with other sensor signals from other sensors or with other contextual data to generate the fusion output.The fusion output system 342 can provide the fusion output to the loss output system 332 for use in generating the corrected loss signal 260. It also becomes apparent that any of the various other components 344 can combine other combinations of context data and / or sensor data, provided that the combination or fusion exhibits a correlation to the error in the grain loss signals generated by the grain loss sensors 230-232. The fusion output system 342 can generate an output indicating this context or sensor fusion to the loss output system 332 for use in generating the corrected loss signal 260. The geographic correction system 328 can identify the geographic location of machine 100 or its future location by detecting its direction of travel and route, and can identify or extract geographic features that may correlate with the error in the grain loss signals generated by the grain loss sensors 230-232. Likewise, the geographic correction system 328 can identify historical loss features observed or recorded in the past at the geographic location of machine 100. Based on the geographic features and / or the historical loss features, the geographic correction system 328 can generate an output to the loss output system 332, which can be used to generate the corrected loss signal 260. The position identifier 346 thus identifies the geographic location or geoposition of machine 100.The position identifier 346 can receive an input signal from the geoposition sensor 145 and identify the location of the machine 100 (or its future location) based on the input signal from sensor 145. The geo-feature extraction system 348 then extracts geographic features that may correlate with the error in the loss signal generated by the grain loss sensors 230-232. Once the geographic location of the machine 100 is known, the geo-feature extraction system 348 can access the data memory 235 to retrieve geographic features 237 that correlate with the error in the signal generated by sensors 230-232. These features may include the geographic elevation of the machine 100 at the detected location, the weather at that location, other environmental features at that location, the soil type at that location, the condition of the soil (whether it is dry, muddy, rocky, etc.), or other features.Geographic features 237 can also be obtained from another machine, a map, or another source. For example, a sprayer may have driven through the field and collected georeferenced data indicating the presence of weeds or other plants. The geographic feature extraction system 348 can process these features to produce an output for the geographic output system 352. The geographic output system 352 can generate or provide a geographic output that correlates with the error in the loss signal to the loss output system 332, which can then use the geographic output to generate the corrected loss signal 260. The historical loss feature extraction system 350 can use the position of machine 100 provided by the position identifier 346 and obtain historical loss features 239 from the data store 235 or from another source. The historical loss features 239 can indicate or correlate with the loss sensor signal generated by sensors 230-232 that was detected in the past at the recorded location of machine 100. The historical loss feature extraction system 350 can generate an output based on the historical loss features 239. This historical loss output can be provided by the geographic output system 352 to the loss output system 332 for use in generating the corrected loss signal 260, either instead of, or in combination with, the output of the geographic feature extraction system 348. The pressure-based correction system 330 identifies and processes pressure readings that may correlate with the error in the loss sensor signals generated by the loss sensors 230-232. For example, the air pressure correction processor 356 can receive an input from the air pressure sensor 162 if the air pressure correlates with the loss sensor signal error. The body pressure correction processor 358 can receive a signal from the body pressure sensor 160 indicating the pressure inside the body of the machine 100 if the body pressure correlates with the loss sensor signal error. The print output system 360 can generate a print output based on the input signals from the air pressure correction processor 356 and / or body pressure correction processor 358. The print output can be provided to the loss output system 332 for use in generating the corrected loss signal 260. The system selection processor 364 receives the outputs from one or more of the systems 326, 328, and 330 and selects which error correction system 366, 368, or 370 should be used to generate the corrected loss signal 260. The system selection processor 364 can thus utilize the selection criteria stored in the knowledge base 236. The system selection processor 364 can execute a selection algorithm or model, or determine which of the systems 366, 368, and 370 should be used to correct the grain loss signals generated by the loss sensors 230–232, taking into account the context information and / or received input signals from one or more of the systems 326, 328, and 330. For example, a loss correction model 243 might be used in certain contexts, while a loss correction algorithm 245 or a correction table 247 might be used in other contexts.Based on the outputs of systems 326, 328 and / or 330 and / or based on context information, the system selection processor 364 thus selects one of systems 366, 368 and 370 to generate the corrected loss signal 260. When the processor 364 selects the model execution system 366, the model selection component 376 selects one or more of the loss correction models 243 to be executed to generate the corrected loss signal 260, based on context information or other input signals. The model selection component 376 can thus itself be a selection model, a selection algorithm, or another mechanism for deciding which loss correction model 243 should be executed to generate the corrected loss signal 260. The selection criteria used by the model selection component 376 can include context information or other information. Suppose that the system selection processor 364 selects the model execution system 366, and suppose that the model selection component 376 selects a specific loss correction model 243, then the model execution system 366 executes the selected loss correction model 243 based on input context information and / or input signals from one or more of the systems 326, 328, and 330. The output of the selected loss correction model 243 is provided to the corrected signal output system 372, which outputs the corrected loss signal to 260. When the algorithm execution system 368 is selected by the system selection processor 364, the algorithm selection system 382 selects one of several different loss correction algorithms 245, which can be executed in consideration of the current context or in consideration of the input signals from systems 326, 328, and / or 330. The algorithm execution system 368 then executes the selected loss correction algorithm 245 to correct the sensor signals output by the grain loss sensors 230-232. The loss correction algorithm 245 provides an output signal to the corrected signal output system 372, which generates or outputs the corrected loss signal 260. When the system selection processor 364 selects the reference system 370, the table selection component 388 selects one of several different correction tables 247. The reference system 370 retrieves correction values ​​from the selected correction table 247 based on context information or output from systems 326, 328, and / or 330. These correction values ​​can be output to the corrected signal output system 372, which outputs the corrected loss signal 260. Figure 6 is a flowchart illustrating an example of how the correction component 238 operates when acquiring or using context information and generating the corrected loss signal 260. First, it is assumed that the crop identification component 324 identifies the type of crop harvested by the machine 100. Crop type identification is shown in the flowchart of Figure 6 by block 392. The context / sensor fusion correction system 326 can perform context / sensor fusion processing to generate a fusion output, as shown by block 394. For example, the NKB moisture / crop moisture fusion component 336 can combine NKB moisture and crop moisture values, as shown by block 396. The chaff / NKB ratio component 338 can generate a chaff / NKB ratio, as shown by block 398. The NKB / grain ratio component 340 can calculate an NKB / grain ratio of 400.Any of the numerous other processing functions 344 can produce outputs that point to other mergings or combinations of sensors and contexts, as indicated by block 402. The Position Identifier 346 determines the geographic location, direction of travel, and / or route of the machine 100, as shown by Block 404. The Geographic Correction System 328 then performs geoposition-based correction processing to generate a geographic output, as shown by Block 406. Based on the identified geographic position or the determined location of the machine 100, the Geo-Feature Extraction System 348 extracts or calculates geographic loss features that can be used by the Loss Output System 332. The calculation or extraction of geographic loss features is shown in the flowchart of Figure 6 of Block 408. The Past Loss Feature Extraction System 350 also calculates or extracts historical loss features, as shown by Block 410.The geographic and / or historical loss characteristics can be used by the geographic output system 352 to generate a geographic output. Other components, as shown by block 412, can be used to identify geographic characteristics and / or historical loss characteristics. The pressure-based correction system 330 then detects pressures that can correlate with the error in the grain loss signal generated by sensors 230-232. The pressure detection is shown in the flowchart of Fig. 6 for block 414. The air pressure correction processor 356 receives an input signal from the air pressure sensor 162 indicating atmospheric pressure, as shown by block 416. The body pressure correction processor 358 can receive an input signal from the body pressure sensor 160 indicating the pressure inside the body of the machine 100, as shown by block 418. Other pressures can also be detected and provided to the pressure-based correction system 330, as shown by block 420. The pressure-based correction system 330 then performs pressure-based correction processing based on the detected pressures to generate a pressure output, as shown by block 422. The pressure output can correlate with the error in the grain loss signal generated by the grain loss sensors 230-232, and the pressure output can be provided to the loss output system 332. The loss output system 332 then generates a corrected loss value or a corrected loss signal 260 based on the fusion output of system 326, the geographic output of system 328, the print output of system 330, and / or other contextual information. The generation of a corrected loss value or a corrected loss signal 260 is shown in the flowchart of block 424 in Fig. 6. Figure 7 is a flowchart that illustrates in more detail an example of the operation of the loss output system 332. It is initially assumed that the system selection processor 364 processes context information in the output signals of systems 326, 328, and / or 330 to select a correction system for use in generating the corrected loss signal 260. The processing of the information for selecting a correction system is shown in the flowchart of Figure 7 for block 426. The selected correction system can be a model execution system 366, an algorithm execution system 368, a reference system 370, or a variety of other correction systems 372. Once the correction system is selected, this correction system can make any further selection decisions for generating the corrected loss signal 260. The execution of further selection decisions is shown in the flowchart of Fig. 7 of Block 428. For example, the model selection component 376 can perform a model selection to choose a loss correction model 243, as shown by Block 430. The algorithm selection system 382 can select a loss correction algorithm 245, as shown by Block 432. The table selection component 388 can select a reference table 247, as shown by Block 434, and other selection systems can make further selection decisions, as shown by Block 436. The selected correction system can also perform further configurations or modifications to generate a correction, as shown in Block 438. For example, the algorithm execution system 368 can configure the selected loss correction algorithm 245 with modified coefficients or other values, as shown in Block 440. The selected correction system can also be configured in other ways, as shown in Block 442. The loss output system 332 then executes the selected and configured correction system to generate the corrected loss value or corrected loss signal 260, as shown by block 444. The corrected signal output system 372 then outputs the corrected loss signal 260, as shown by block 446. It is thus evident that the present description describes a system that can use geographic information, historical information, or one of many combinations of contextual information to correct a grain loss sensor signal. The present description also describes a system that can use geographic information, historical information, and / or different combinations of sensor information as input for a loss correction model, for a loss correction algorithm, or for selecting a value from a reference table. The present description thus describes a system that significantly improves the accuracy of the loss signal generated in a harvesting vehicle and that takes into account a variety of different contexts and combinations of contextual information that correlate with the accuracy of the grain loss sensors. Processors and servers have been mentioned in this description. In this example, processors and servers comprise computer processors with associated memory and timing circuitry, which are not shown separately. The processors or servers are functional parts of the systems or devices to which they belong and are activated by the other components or elements in these systems, supporting their functionality. A number of user interfaces (UIs) were also discussed. UI displays can take a wide variety of forms and can incorporate a wide variety of user-operated input mechanisms. These user-operated input mechanisms can include, for example, text fields, checkboxes, icons, links, drop-down menus, search fields, and so on. Furthermore, the mechanisms can be activated in a variety of ways. For example, they can be activated using a point-and-click device (such as a trackball or mouse). They can also be activated using hardware buttons, switches, a joystick or keyboard, thumb switches, thumb pads, and so forth. Finally, they can be activated using a virtual keyboard or other virtual actuators.Furthermore, the mechanisms can be operated using touch gestures if the display screen on which the mechanisms are shown is a touch-sensitive display screen. Additionally, the mechanisms can be operated using voice commands if the device displaying the mechanisms has speech recognition components. Several data stores were also discussed. It should be noted that each data store can be subdivided into multiple data stores. All can be located locally within the systems accessing the data stores, all can be located remotely, or some can be local while others are located remotely. All of these configurations are included here. The figures also show a number of blocks, each with a specific functionality assigned to it. It should be noted that fewer blocks can be used, in which case the functionality is performed by fewer components. Conversely, more blocks can be used, in which case the functionality is distributed across more components. It should be noted that the above descriptions encompass a variety of different systems, components, generators, models, sensors, algorithms, identifiers, and / or logics. It is understood that such systems, components, generators, models, sensors, algorithms, identifiers, and / or logics consist of hardware elements (e.g., processors and associated memory or other processing components, some of which are described below) that perform the functions associated with these systems, components, generators, models, sensors, algorithms, identifiers, and / or logics. Furthermore, the systems, components, generators, models, sensors, algorithms, identifiers, and / or logics may consist of software that is loaded into memory and subsequently executed by a processor, server, or other data processing component, as described below.The systems, components, generators, models, sensors, algorithms, identifiers, and / or logic can also consist of various combinations of hardware, software, firmware, etc., some examples of which are described below. These are just a few examples of different structures that can be used to form the systems, components, generators, models, sensors, algorithms, identifiers, and / or logic described above. Other structures can also be used. Figure 8 is a block diagram of the agricultural system 200 shown in Figure 2, with the difference that this system communicates with elements in a remote server architecture 500. In one example, the remote server architecture 500 can provide computing, software, data access, and storage services that do not require end-user knowledge of the physical location or configuration of the system providing the services. In various examples, remote servers can provide services over a wide area network, such as the internet, using appropriate protocols. For example, remote servers can provide applications over a wide area network, and these applications can be accessed via a web browser or any other data processing component. The software or components shown in previous figures, as well as the corresponding data, can be stored on servers in a remote location.The data processing resources in a remote server environment can be concentrated at a remote data center or distributed locally. Remote server infrastructures can provide services across shared data centers, although they appear as a single access point to the user. Thus, the components and functions described here can be provided by a remote server at a remote location using a remote server architecture. Alternatively, the components and functions can be provided from a traditional server, installed directly on client devices, or made available in other ways. In the example shown in Fig. 8, some elements are similar to those shown in previous figures, and they are labelled similarly. Fig. 8 shows in particular that parts of the grain loss correction system 226 and data storage 235 and / or other systems 210 can be located at a remote server location 502. Therefore, the mobile agricultural machine 100 accesses these systems via the remote server location 502. Fig. 8 also shows another example of a remote server architecture. Fig. 8 also shows that some elements of the preceding figures are located at a remote server location 502, while others are not. For example, the data storage 235, parts of the speed control system, grain loss correction system 226, and / or other elements may be located at a location separate from location 502 and accessible via the remote server at location 502. Regardless of where the elements are located, access to the elements may be directly by the mobile agricultural machine 100, via a network (either a wide area network or a local area network), the elements may be hosted by a service at a remote location, or the elements may be provided as a service or be accessible via a connection service located at a remote location.Furthermore, the data can be stored in almost any location and temporarily accessed or forwarded to interested parties. All these architectures are included here. It should also be noted that the elements of previous figures, or parts thereof, can be arranged on a wide variety of different devices. Some of these devices include servers, desktop computers, laptop computers, tablet computers, or other mobile devices such as palmtop computers, mobile phones, smartphones, multimedia players, personal digital assistants, etc. Fig. 9 is a simplified block diagram of an illustrative example of a handheld or mobile computing device that can be used as a handheld device 16 by a user or client and in which the present system (or parts thereof) can be used. For example, a mobile device can be used in the operator's cab of agricultural machinery 100 for generating, processing, or displaying grain loss data. Figs. 9-11 are examples of handheld or mobile devices. Fig. 9 shows a general block diagram of the components of a client device 16, which can execute and / or interact with some of the components shown in the preceding figures. The device 16 provides a communication link 13 that enables the handheld device to communicate with other data processing equipment and, in some examples, provides a channel for automatically receiving information, such as by scanning. Examples of the communication link 13 include enabling communication via one or more communication protocols, such as wireless services used to provide cellular access to a network, and protocols that provide local wireless connections to networks. In other examples, applications can be received on a removable Secure Digital card (SD card) connected to an interface 15. The interface 15 and the communication links 13 communicate with a processor 17 (which can also represent processors or servers from previous FIG.) along a bus 19, which is also connected to a memory 21 and input / output (I / O) components 23, as well as a timer 25 and a location system 27. The I / O components 23 are provided in an example to enable input and output operations. The I / O components 23 for various examples of the device 16 can include input components such as buttons, touch sensors, optical sensors, microphones, touchscreens, proximity sensors, accelerometers, and orientation sensors, and output components such as a display device, a speaker, and / or a printer port. Other I / O components 23 can also be used. The timer 25, for example, includes a real-time clock component that outputs a time and date. It can also, for example, provide time control functions for the processor 17. The tracking system 27 includes, for example, a component that outputs a current geographic location of the device 16. It may, for example, include a receiver of a global positioning system (GPS receiver), a dead reckoning system, a cellular triangulation system, or another positioning system. The tracking system 27 may also, for example, include mapping software or navigation software that creates desired maps, navigation routes, and other geographic functions. Memory 21 stores an operating system 29, network settings 31, applications 33, application configuration settings 35, a data store 37, communication drivers 39, and communication configuration settings 41. Memory 21 can include all types of physical volatile and non-volatile computer-readable memory devices. Memory 21 can also include computer storage media (described below). Memory 21 stores computer-readable instructions which, when executed by the processor 17, cause the processor to perform computer-implemented steps or functions according to the instructions. The processor 17 can be activated by other components to support their functionality as well. Fig. 10 shows an example in which the device 16 is a tablet computer 600. In Fig. 10, the computer 600 is shown with a user interface display screen 602. The screen 602 can be a touchscreen or a pen-activated interface that receives input from a pen or stylus. The computer 600 can also use a virtual on-screen keyboard. Of course, the computer 600 could also be connected to a keyboard or other user input device via a suitable connection mechanism, for example, a wireless connection or a USB port. For illustrative purposes, the computer 600 can also receive voice input. Fig. 11 shows that the device can be a smartphone 71. The smartphone 71 has a touch-sensitive display 73 that shows icons or tiles or other user input mechanisms 75. The mechanisms 75 can be used by a user to run applications, make calls, perform data transfer operations, etc. In general, the smartphone 71 is based on a mobile operating system and offers more advanced computing and connectivity capabilities than a feature phone. It should be noted that other forms of devices 16 are possible. Figure 12 is an example of a data processing environment in which elements from previous figures, or parts thereof, may be used (for example). According to Figure 12, an example system for implementing some embodiments comprises a computing device in the form of a computer 810, programmed to operate as described above. Components of the computer 810 may, but are not limited to, include a processing unit 820 (which may include processors or servers from previous figures), a system memory 830, and a system bus 821, which couples various system components, including the system memory, to the processing unit 820. The system bus 821 may be one of several types of bus structures, including a memory bus or memory controller, a peripheral bus, and a local bus with any one of a variety of bus architectures.The memory and programs described with reference to the preceding figures can be used in corresponding parts of Fig. 12. The Computer 810 typically includes a variety of different computer-readable media. Computer-readable media can be any available media that the Computer 810 can access, including both volatile and non-volatile, removable and non-removable media. By way of example, and without limitation, computer-readable media can include computer storage media and communication media. Computer storage media are distinct from and do not include a modulated data signal or carrier wave. Computer storage media include hardware storage media, including both volatile and non-volatile, removable and non-removable media, implemented by any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data.Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory, or other storage technology; CD-ROM, DVD (Digital Versatile Discs), or other optical disc storage; magnetic cartridges, magnetic tape, magnetic disk storage, or other magnetic storage devices; or any other medium that can be used to store the desired information and that the Computer 810 can access. Communication media can embody computer-readable instructions, data structures, program modules, or other data in a transport mechanism and include any information delivery media. The term "modulated data signal" describes a signal in which one or more of its characteristics are set or modified to encode information in the signal. System memory 830 comprises computer storage media in the form of volatile and / or non-volatile memory, such as ROM (read-only memory) 831 and RAM (random access memory) 832. A BIOS (basic input / output system) 833, containing the basic routines that assist in the transfer of information between elements within the computer 810, for example, during startup, is typically stored in ROM 831. RAM 832 usually contains data and / or program modules that are directly accessible to and / or currently being processed by the processing unit 820. By way of example, and not as a limitation, Fig. 12 illustrates an operating system 834, application programs 835, other program modules 836, and program data 837. The Computer 810 may also include other removable / non-removable volatile / non-volatile computer storage media. By way of example only, Fig. 12 illustrates a hard disk drive 841, which reads from or writes to the non-removable non-volatile magnetic media, an optical disk drive 855, and a non-volatile optical disk 856. The hard disk drive 841 is typically connected to the system bus 821 via a non-removable memory interface, such as interface 840, and the optical disk drive 855 is typically connected to the system bus 821 via a removable memory interface, such as interface 850. Alternatively or additionally, the functionality described here can be implemented, at least partially, by one or more hardware logic components. Examples of usable hardware logic components include, but are not limited to, field-programmable gate arrays (FPGAs), application-specific integrated circuits (e.g., ASICs), application-specific standard products (e.g., ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), etc. The drives and their associated computer storage media, discussed above and illustrated in Fig. 12, provide storage for computer-readable instructions, data structures, program modules, and other data for the Computer 810. In Fig. 12, for example, the hard disk drive 841 is shown storing the operating system 844, the application programs 845, other program modules 846, and the program data 847. It should be noted that these components may be either identical to or different from the operating system 834, the application programs 835, the other program modules 836, and the program data 837. A user can input commands and information into the computer 810 via input devices such as a keyboard 862, a microphone 863, and a pointing device 861, such as a mouse, trackball, or touchpad. Other input devices (not shown) may include a joystick, gamepad, satellite dish, scanner, or the like. These and other input devices are often connected to the processing unit 820 via a user input interface 860 coupled to the system bus, but they may be connected via other interface and bus structures. A visual display 891 or other type of display device is also connected to the system bus 821 via an interface such as a video interface 890. In addition to the monitor, computers may also include other peripheral output devices, such as loudspeakers 897 and a printer 896, which may be connected via an output peripheral interface 895. The Computer 810 operates in a network environment with logic connections (such as a control unit network - CAN, local area network - LAN or wide area network - WAN) to one or more remotely located computers, such as a Remote Computer 880. When used in a LAN network environment, the computer 810 is connected to the LAN 871 via a network interface or adapter 870. When used in a WAN network environment, the computer 810 typically includes a modem 872 or other means for establishing communications over the WAN 873, such as the Internet. In a networked environment, program modules may be stored in a remote storage device. Figure 12 illustrates, for example, that remote application programs 885 may reside on a remote computer 880. It should also be noted that the various examples described herein can be combined in different ways. That is, parts of one or more examples can be combined with parts of one or more other examples. All of this is included here. Even if the subject matter has been described in a language specific to structural features and / or methodological actions, it is understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Instead, the specific features and processes described above are disclosed as exemplary forms of implementing the claims.

Claims

Computer-implemented method comprising: generating a loss signal indicating a detected crop loss recorded during a harvesting operation performed by a harvesting vehicle; detecting (404) a location corresponding to the harvesting vehicle; generating (408) a geographic context signal indicating a geographic context based on the detected location; and generating (424) a corrected loss signal based on the loss signal and the geographic context signal. Computer-implemented method according to claim 1, wherein generating a geographic context signal comprises: obtaining a set of geographic loss features that correlate with an error in the loss signal; and generating the geographic context signal based on the set of geographic loss features. A computer-implemented method according to claim 2, further comprising: obtaining a set of historical loss features corresponding to the detected location, wherein the set of historical loss features correlates with an error in the loss signal; and generating the geographic context signal based on the set of historical loss features. Computer-implemented method according to claim 1, wherein the detection of a location comprises: identifying a direction of travel of the harvesting vehicle; and identifying a route of the harvesting vehicle. Computer-implemented method according to claim 1, wherein generating a corrected loss signal comprises: selecting a correction system from a plurality of correction systems based on the geographic context signal; and generating the corrected loss signal with the selected correction system. Computer-implemented method according to claim 5, wherein selecting a correction system comprises: selecting a model execution system or an algorithm execution system or a reference system as the selected correction system. Computer-implemented method according to claim 1, wherein generating the corrected loss signal comprises: selecting a corrective component from a plurality of corrective components in a correction system, based on the geographic context signal; and generating the corrected loss signal with the selected corrective component. Computer-implemented method according to claim 7, wherein the correction system comprises a model execution system and wherein selecting a corrective component comprises: selecting a loss correction model from a plurality of different loss correction models. Computer-implemented method according to claim 7, wherein the correction system comprises an algorithm execution system and wherein selecting a corrective component comprises: selecting a loss correction algorithm from a plurality of different loss correction algorithms. Computer-implemented method according to claim 7, wherein the correction system comprises a reference system and wherein selecting a correcting component comprises: selecting a loss correction reference table from a plurality of different loss correction reference tables. Computer-implemented method according to claim 1, wherein generating a geographic context signal comprises: identifying a context element as at least one of elevation, environmental feature, crop feature, terrain feature or soil feature based on the detected location; and generating the geographic context signal based on the identified context element. Agricultural system comprising: a crop loss sensor (230) designed to generate a loss signal indicating a detected crop loss recorded during a harvesting operation performed by a harvesting vehicle; a geoposition sensor (145) designed to detect a location corresponding to the harvesting vehicle; a geographic correction system (328) designed to generate a geographic output signal, based on the detected location, indicating a geographic context; and a loss output system (332) designed to generate a corrected loss signal based on the loss signal and the geographic output signal. Agricultural system according to claim 12, wherein the geographic correction system comprises: a geographic feature extraction system designed to obtain a set of geographic loss features correlating with an error in the loss signal; and a geographic output system designed to generate the geographic output signal based on the set of geographic loss features. Agricultural system according to claim 12 and further comprising: a historical loss feature extraction system designed to obtain a set of historical loss features corresponding to the detected location, wherein the set of historical loss features correlates with an error in the loss signal, and wherein the geographic output system is designed to generate the geographic output signal based on the set of historical loss features. Agricultural system according to claim 12, wherein the loss output system comprises: a plurality of different correction systems; a system selection processor designed to select a correction system from the plurality of correction systems based on the geographical output signal; and a corrected signal output system designed to generate the corrected loss signal with the selected correction system.

Images