Method and System for efficient Operation of Agricultural Machines

Field of the Invention

The present disclosure relates to a system, apparatus, preferably a server, and methods for supporting usage of an agricultural machinery as well as a corresponding computer program.

Background of the Invention

The agriculture industry like every other industry is undergoing a rapid change due to climate change and digitalization. Accordingly, one can see an increasing demand for techniques optimizing the operation of for example agricultural machineries. One way of achieving higher efficiency is finding the optimal configuration for the agricultural machinery under certain circumstances (e.g., weather conditions, crop type etc.) to achieve certain goals (e.g., higher production while reducing the impact on the environment). Finding such an optimal configuration is further aggravated by constantly changing national and international law regulations (e.g., admissible spray height, maximum amount of used chemicals etc.). Most of the time, finding this optimal configuration is based on the experience gained by an expert for operating the agricultural machinery. Other methods try to develop a type of recommendation system which the user of the agricultural machinery can use to benefit from a predicted optimal configuration. However, these methods have drawbacks as they only consider data of a single machinery or only the experience of a single expert. Accordingly, setting up an efficient recommendation system is time consuming as sufficient data needs to be collected first. In addition, building a recommendation system based on data coming from other users of the same type of agricultural machinery presents a risk for system integrity due to potentially corrupted data from other users (competitors). Summary of the Invention

It is thus an object of the present invention to increase the efficiency of operating an agricultural machinery while staying within the applicable law regulations (e.g., with respect to sustainability). It is a further object of the invention to increase the integrity of data used for generating instructions for usage. Higher data integrity results in higher data quality allowing for even further increased operation efficiency. Additionally, the collected and verified user profile data coming from a plurality of users should ideally allow for improvements along the entire supply chain (e.g., improvement of the design or configuration of the machinery, optimizing chemical agents used in the operations, removal of suboptimal designs or chemicals (mixtures) etc.).

One or more of these objects are achieved by the subject-matter of the independent claims. Preferred embodiments are subject of the dependent claims.

A 1 ^st embodiment of the invention is a method for supporting usage of an agricultural machinery, the method comprising: collecting, by an agricultural machinery controller (AMC) user profile data of the agricultural machinery; transmitting, by the AMC, the collected user profile data to a server; receiving, by the server, the collected user profile data from the AMC; generating, by the server, an instruction for usage of the agricultural machinery based at least in part on the collected user profile data; transmitting, by the server, the instruction for usage of the agricultural machinery to the AMC; receiving, by the AMC, the instruction for usage of the agricultural machinery; applying, by the AMC, an operation control instruction for usage of the agricultural machinery; wherein the operation control instruction for usage applied by the AMC is at least in part based on the instruction for usage received by the AMC; and wherein the server has access to a set of historical user profile data, and generating the instruction for usage of the agricultural machinery comprises: comparing the collected user profile data to at least a subset of the set of historical user profile data; and determining the instruction for usage of the agricultural machinery based on the comparison of the collected user profile data to at least the subset of the set of historical user profile data. A 2 ^nd embodiment of the invention is a method for supporting optimal usage of an agricultural machinery, the method comprising: receiving, by a server, collected user profile data from an agricultural machinery controller (AMC); generating, by the server, an instruction for usage of the agricultural machinery based at least in part on the collected user profile data; transmitting, by the server, the instruction for usage of the agricultural machinery to the AMC; and wherein the server has access to a set of historical user profile data, and generating the instruction for usage of the agricultural machinery comprises: comparing the collected user profile data to at least a subset of the set of historical user profile data; and determining the instruction for usage of the agricultural machinery based on the comparison of the collected user profile data to at least the subset of the set of historical user profile data.

Generating the instruction for usage of the agricultural machinery based on collected user profile data of the agricultural machinery allows for an optimized assessment of the current circumstances the agricultural machinery is operating. Thus, a customized instruction can be generated which allows for a more efficient way of operating the agricultural machinery. The comparison of the user profile data to other user profile data (e.g., of other users) may relate to searching for a user profile which is most similar to the collected user profile with respect to for example the operating circumstances. Generating the instruction based on the comparison allows for a higher significance of the instruction as it becomes more reliable. Thus, the efficiency of operating the agricultural machinery is further increased.

According to a 3 ^rd embodiment, in any one of the preceding embodiments, the collected user profile data comprises one or more of the following: location data of the agricultural machinery, machine configuration data of the agricultural machinery, crop type data, weather data, production data and resources used by the agricultural machinery.

By specifying the collected user profile data, a current operating state of the agricultural machinery can be described in more detail, allowing for a higher precision when assessing the circumstances under which the machinery is operating. Thus, an even more suitable instruction can be generated, resulting in an increase of operation efficiency of the machinery. Using this additional information may for example allow to determine where (location via GPS) and under which weather conditions the machinery is operating, which may affect the given instruction for usage. Furthermore, the location data may allow to determine under which legal factors (e.g., environmental regulations with respect to sustainability) have to be considered when creating an instruction for usage. For example, the usage of a specific type of chemical may be limited to a certain amount in a certain country or the spraying height may be limited to a certain height. Accordingly, this regulation may be considered when generating the instruction for usage.

According to a 4 ^th embodiment, in the preceding embodiment, the set of historical user profile data comprises a plurality of collected machinery usage data samples, each machinery usage data sample being associated with a score, preferably comprising at least one of an environmental impact score or a production score.

When comparing the collected user profile data to the historical user profile data for generating the instruction for usage, a score (e.g., a production score or an environmental impact score) can be considered. For example, if a user of the agricultural machinery tries to operate as sustainable as possible, samples of the plurality of collected machinery usage data with an associated low environmental impact score will not be considered for generating an instruction. In another example, where a user aims at maximizing the production, a suitable sample of the plurality of collected machinery usage data samples can be associated with a high production score. Thus, an instruction for usage can be customized to specific operation goals using a corresponding score associated with each sample, resulting in an overall increase of operation efficiency.

According to a 5 ^th embodiment, in the preceding embodiment, the plurality of collected machinery usage data samples includes collected machinery usage data samples from at least another agricultural machinery of the same machinery type.

By incorporating data collected from other agricultural machineries operated by for example other users, a more equally distributed plurality of collected machinery usage data samples can be achieved. Thereby, potentially one-sided operating mistakes by the user of the agricultural machinery can be compensated. Thus, the generated instruction will likely be an instruction resulting in higher efficiency. According to a 6 ^th embodiment, in any one of the 3 ^th to 5 ^th and 1 ^st embodiments, the method further comprises transmitting, by the AMC, the operation control instruction to the server; receiving, by the server, the operation control instruction from the AMC; determining, by the server, based on at least the operation control instruction, a score, the score preferably comprising at least an environmental impact score or a production score; generating, by the server, a machinery usage data sample by adding the score to the collected user profile data; and adding the machinery usage data sample to the set of historical user profile data.

According to a 7 ^th embodiment, in any one of the 3 ^th to 5 ^th and 2 ^nd embodiments, the method further comprises: receiving, by the server, the operation control instruction from the AMC; determining, by the server, based on at least the operation control instruction, a score, the score preferably comprising at least an environmental impact score or a production score; generating, by the server, a machinery usage data sample by adding the score to the collected user profile data; and adding the machinery usage data sample to the set of historical user profile data.

A feedback loop is generated where the server determines a score based on at least the received operation control instruction. Determining the score may be based on comparing the transmitted instruction for usage with the received operation control instruction. For example, if the applied operation control instruction would be identical with the instruction for usage, the corresponding score would be high. The more the applied operation control instruction deviates from the instruction for usage, the lower the score may be. A new sample of the historical user profile data may be created on the server. As a result, the amount of collected machinery usage data samples can be increased, allowing for a better data baseline for future instructions. Furthermore, the server is able to determine whether the generated instruction was effective based on for example the actual production output of the agricultural machinery (e.g., product! on/ha). Accordingly, the server could adapt the method of generating the instruction for usage if the instruction in question previously achieved a low production output. Thus, data and prediction quality of the instruction generation can be improved, resulting in an increased operation efficiency.

According to an additional embodiment in any one of the 6 ^th or 7 ^th embodiment, a feedback message may be transmitted from the server to the AMC. This feedback message may include the score as well as information on how to improve the score (e.g., by a machinery/equipment upgrade, different (amount and/or mixture of) chemicals, smarter use of the machinery like adaption of spray height etc.). The feedback message may additionally or alternatively include a warning if the operation control instruction violates corresponding law regulations (e.g., local environmental emission laws etc.). The server may store and continuously update the corresponding regulations. This may further increase the efficiency of operation, especially with respect to the sustainability goals set by the local law regulations.

According to an 8 ^th embodiment, in any one of the preceding embodiments, the method further comprises verifying, by the server, the received operation control instruction.

Verifying the received operation control instruction improves the data quality. Furthermore, system integrity is increased, as no invalid data is added to the set of historical user profile data. This can be crucial, as an instruction for usage generated on corrupted data could cause the agricultural machinery to behave in an unforeseen manner, potentially with risks for the user.

According to a 9 ^th embodiment, in the preceding embodiment, verification of the received operation control instruction comprises determining whether the operation control instruction is consistent with transaction data exchanged between the user of the agricultural machinery and a set of providers, wherein the set of providers comprises one or more chemicals suppliers and/or one or more machine manufacturers; wherein the received operation control instruction is consistent if it is traceable from the transaction data. The transaction data may also include transaction regarding productivity (e.g., sales of potato harvest to factories).

Determining whether the (allegedly) applied operation control instruction is consistent with the transaction data exchanged between the user of the agricultural machinery and a set of providers presents an efficient way of verifying the operation control instruction. Thus, adding invalid data can be avoided, resulting in higher system integrity and higher data quality. It is to be understood that the term “user” as used in the context of the present invention does not only relate to the person operating the agricultural machinery at a certain point in time but can also relate to the actual owner of the agricultural machinery, an administrator of the agricultural machinery or any other similar role of a person having direct control of the machinery or directly benefitting from the use of the machinery.

In one example, an operation control instruction may be considered traceable from transaction data if the resources (e.g., chemicals) used by the agricultural machinery indicated by the operation control instruction match the chemicals sold to the user of the agricultural machinery. In addition, the already used amount of the chemicals can be considered when assessing the traceability of the operation control instruction. For example, if the operation control instruction indicates the usage of 10 entities of a specific chemical and 20 entities of the specific chemical have been sold to the user of the agricultural machinery, but 15 entities of the specific chemical have already been used according to the transaction data, then usage of 10 more entities is not traceable. In another example, an operation control instruction may be considered traceable from the transaction data if an agricultural machinery has actually been sold to the user of the agricultural machinery and if the indicated machine configuration of the agricultural machinery is part of a set of possible machine configurations of the agricultural machinery. These are non-limiting examples, and it is to be understood that any combination of verifying the consistence between operation control instruction(s) and the transaction data is covered by the present invention.

According to a 10 ^th embodiment, in the preceding embodiment, the transaction data comprises one or more of: data on a first chemicals stock provided by at least one chemicals supplier to the user of the agricultural machinery; data on a second chemicals stock consumed by the user of the agricultural machinery; identity data of the agricultural machinery, preferably including a machine manufacturer id and/or a proof of a transfer of ownership of the agricultural machinery; a production output (e.g., a produced crop harvest stock, a crop harvest stock sold to customers etc.) and/or a set of possible machine configurations of the agricultural machinery. By specifying the transaction data, the verification of the operation control instruction can be improved. Based on the transaction data, the traceability of the operation control instruction can be determined. The more detailed the transaction data is specified, the harder it is to work around the verification of a corrupted operation control instruction. Thus, the system integrity is increased.

According to an 11 ^th embodiment, in any one of the 9 ^th to 10 ^th embodiments, the transaction data is stored on a blockchain; wherein the verification is successful if the operation control instruction is consistent with the transaction data stored on the blockchain and if the operation control instruction is valid, the blockchain storing the transaction data is updated according to the operation control instruction.

Storing the transaction data on a blockchain and verifying the operation control instruction by each of the providers further minimizes the risk of corrupted data being mistakenly added. Furthermore, the blockchain allows for a decentralized and trustless system design, which for example can reduce the risk of data loss due to the distributed data storage. By updating the transaction data stored on the blockchain, the traceability for future validations is secured. For example, if the operation control instruction indicates a usage of 10 liters of a specific type of chemical and according to the transaction data 100 liters have been sold, and 90 liters have already been used, the remaining stock of 10 liter will be updated (i.e., in this example set to 0 liters remaining). As a result, should a future operation control instruction indicate the usage of yet again 10 liters, this future operation control instruction could be verified as invalid as it is not traceable anymore. However, should a transaction of that chemical have been completed in the meantime (e.g., the user of the agricultural machinery has bought 100 liters of that chemical to refill his stock again) this future operation control instruction may be verified as valid.

According to another embodiment, the set of historical user profile data is used at least by a subset of the set of providers to technically improve a product provided.

Due to the collection of a plurality of usage data samples, providers (e.g., the machine manufacturer) can use this data for improving the products they provide. For example, the machine manufacturer could recognize from the historical user profile data that a certain machine configuration possibility is missing which would allow for improved operation efficiency under certain circumstances. The manufacturer could fill this gap and hence directly contribute to a further increase of operation efficiency. In a further example for a product improvement, a provider (e.g. the manufacturer of the agricultural machinery) can use the set of historical user profile data to improve the construction of the agricultural machinery, or could improve a default configuration of the agricultural machinery with respect to e.g. a weather situation and a desired goal like high productivity (e.g. based on a productivity score) and/or high sustainability (e.g., based on an environmental impact score). In a second example, a chemicals supplier could gain insights about potential improvements of mixtures of the provided chemicals based on the historical usage data. As a result, the given instructions for usage may result in the converging towards a certain machinery configuration allowing the manufacturer to remove non-optimal configurations. The same applies for chemical supplies which for example respect to the optimal chemical mixture.

According to a 12 ^th embodiment, in any one of the 8 ^th to 11 ^th embodiments, the steps of determining the score, transmitting the score, receiving the score, generating the machinery usage data sample and/or adding the machinery usage data sample are only carried out if the verification has been successful.

Accordingly, if verification of the collected usage data fails, no score is generated by the server. In addition, the corrupted data (i.e., the operation control instruction) is not added and the transaction data not updated. Thus, system integrity is maintained.

A 13 ^th embodiment of the invention is a system for supporting usage of an agricultural machinery comprising at least one agricultural machinery controller (AMC); and a server; wherein the system is configured to perform the method according to any one of the preceding embodiments.

A 14 ^th embodiment of the invention is a server for supporting usage of an agricultural machinery, the server comprising means to perform the method according to any one of the 2 ^nd or 7 ^th , or any one of the 3 ^rd to 5 ^th or 8 ^th to 12 ^th , and 2 ^nd embodiments. io

A 15 ^th embodiment of the invention is a computer program, which when executed causes a computer to carry out the steps according to the method of any one of the 1 ^st to 12 ^th embodiments.

Brief Description of the Drawings

Various embodiments of the present invention are described in more detail in the following by reference to the accompanying figures, without the present invention being limited to the embodiments of these figures.

Fig. 1 illustrates a system for supporting usage of an agricultural machinery according to an embodiment of the invention.

Fig. 2 illustrates a method for supporting usage of an agricultural machinery according to an embodiment of the invention.

Fig. 3 illustrates a server for supporting usage of an agricultural machinery according to an embodiment of the invention.

Fig. 4 illustrates a method for supporting usage of an agricultural machinery according to an embodiment of the invention.

Fig. 5 illustrates a method for verifying an operation control instruction of an agricultural machinery according to an embodiment of the invention.

Throughout the present drawings and specification, the same reference numerals refer to the same elements. In the drawings, reference signs are illustrated exemplarily without limiting the embodiments of the drawings to merely comprising the illustrated reference signs.

Detailed Description

In the following, exemplary embodiments of the present invention are described in more detail. Fig. 1 shows a system 100 for supporting usage of an agricultural machinery according to an embodiment of the invention. The system 100 comprises at least one agricultural machinery controller (AMC) 110. An AMC 110 may be any hardware and/or software component suitable for collecting data of an agricultural machinery and transmitting and receiving data via any suitable type of interface (e.g., wireless or wired communication) to perform a method for supporting usage of an agricultural machinery according to the present invention. An AMC 110 may be attached to the agricultural machinery or may be at a remote location (e.g., a server or a Cloud). The system 100 also comprises a server 120. The server 120 may be located on the agricultural machinery. The server 120 may also or alternatively be located at a remote location (e.g., on-prem or Cloud). The server 120 may comprise any suitable means for supporting a method for supporting usage of an agricultural machinery according to the present invention. The server 120 may comprise means for storing historical user profile data. The at least one AMC 110 may be operably connected to the server 120 (e.g., via an HTTP, WIFI or any other suitable interface). The system 100 may also comprise a set of providers 130 with which the user of the agricultural machinery has made transactions (e.g., for buying the agricultural machinery or buying chemicals for the usage of operating the agricultural machinery). The system 100 may further comprise transaction data 140 representing transactions made between a user of an agricultural machinery and any one of the set of providers. While the transaction data 140 has been depicted as a separate entity in Fig. 1 it is to be understood that the transaction data 140 can be stored in any suitable way (e.g., at a central database located for example at the server or via a decentralized database like a blockchain distributed across all or certain entities of the system 100) according to embodiments of the present invention.

Fig. 2 shows a method 200 for supporting usage of an agricultural machinery. The method 200 may for example be performed by the system 100 explained with reference to Fig. 1. In step 210, user profile data of an agricultural machinery is collected by an AMC 110. In step 220, the collected user profile data is transmitted to a server 120 by the AMC 110. In step 230, the server 120 receives the collected user profile data from the AMC 110. In step 240, the server 120 generates an instruction for usage of the agricultural machinery based at least in part on the collected user profile data. In step 250, the server 120 transmits the instruction for usage of the agricultural machinery to the AMC 110. In step 260, the AMC 110 receives the instruction for usage of the agricultural machinery. In step 270, the AMC 110 applies an operation instruction for usage of the agricultural machinery, wherein the operation instruction for usage applied by the AMC 110 is at least in part based on the instruction for usage received by the AMC 110.

In a non-illustrated embodiment, the AMC 110 may transmit the operation control instruction to the server 120. The server 120 may receive the operation control instruction and determine based on at least the operation control instruction a score. In a further nonillustrated embodiment, the server 120 may verify the operation control instruction received from the AMC 110. A method for verifying an operation control instruction may for example be the method 500 described with respect to Fig. 5.

It is to be understood that the specific order or hierarchy of steps in the method 200 are an illustration of an exemplary process. Based upon design or implementation preferences, it is understood that the specific order or hierarchy of steps in the method 200 may be rearranged.

Fig. 3 shows an example of a system 300 for supporting the usage of an agricultural machinery (e-g., a sprayer). The AMC 110 collects user profile data of the agricultural sprayer like location data, weather data; resources used by the agricultural sprayer like the chemical mixture sprayed; the corresponding crop type data; and a machine configuration like a certain spraying pattern (e.g., spot spraying, variable dosage, height of spraying and/or control spraying for each individual nozzle). The collected user profile data may then be transmitted by the AMC 110 to the server 120, which upon receiving the collected user profile data may generate an instruction for usage of the agricultural sprayer based at least in part on the collected user profile data. For example, based on the weather data, the server may identify windy conditions. Accordingly, the sprayed chemicals may tend to drift due to the wind, resulting in a less precise spraying result. E.g., in case of spot spraying, the actual spots to be sprayed may not be hit properly due to the chemicals being diverted by the wind. The instruction for usage of the agricultural sprayer may thus comprise adjustments of the sprayer system to avoid/reduce the drift of chemicals (e.g., by adapting a height setting of the spraying above crops, adapting the driving speed of the sprayer, adapting the number of nozzles and/or adapting the type of the nozzle). The server 120 may transmit this instruction to the AMC 110, which again will apply an operation control instruction at least in part based on the received instruction for usage. Accordingly, the AMC 110 may for example cause the agricultural sprayer to reduce the driving speed to improve the precision of the sprayer and reduce the drift of chemicals.

Additionally, the server 120 when generating the instruction for usage may compare the received collected user profile data to a set of historical user profile data. The historical user profile data may come from the agricultural sprayer seeking advice and/or additionally from other agricultural sprayers of other users. Each sample of the historical user profile data may be associated with a corresponding score (e.g., production score, environmental impact score etc.). When comparing the collected user profile data to the historical user profile data, the server 120 may search for data samples of the historical user profile data which are as similar as possible to the collected user profile data. A data sample is considered similar if the circumstances described by the data sample are approximately to the same as those circumstances described by the received collected user profile data. In the example of the sprayer, a similar data sample would for example be a sprayer carrying out the same spraying pattern under the same weather conditions for the same type of crop. Once the server 120 has identified the similar sample(s), the server checks which instructions have been given in the past, how it was applied in operation, and which score the corresponding instructions have achieved. Accordingly, the instructions (and/or the associated operations) with the best result/score would be used or would serve as a basis for determining the instruction for usage for the agricultural sprayer seeking the instruction.

Additionally, the AMC 110 of the agricultural sprayer, after receiving the instruction for usage and applying a corresponding operation control instruction (e.g., reduce the driving speed and the spraying height) may transmit the operation control instruction to the server 120. The server 120 may determine a score based on at least the operation control instruction. For example, the server 120 may determine how well the user of the agricultural machinery has followed the instruction for usage (e.g., by comparing the instruction for usage with the received operation control instruction). For example, should the operation control instruction indicate that the reduction of driving speed and spraying height equals to the values indicated by the instruction for usage, this would result in a high score. However, should the operation control instruction indicate that neither the driving speed nor the spraying height was reduced the score would be rated low. The server 120 may generate a new machinery usage sample by adding the score to the corresponding collected user profile data and by adding the machinery usage sample to the set of historical user profile data. Therefore, the set of historical user profile data can be increased and serve for determining future instructions based on a broader dataset.

The system 300 may also comprise a verification step of the operation control instruction received by the server 120 from the AMC 110 of the agricultural machinery, in this example the agricultural sprayer. The verification method could be the one described in Fig. 5. Verification of the operation control instruction may be necessary if for example a plurality of users of agricultural sprayers are participating in the system 300. In such a case, intentionally or unintentionally corrupted data input by one user could result in sub-optimal instructions given to the other users. Such a manipulation could result in one of the users achieving a competitive advantage over the other users. This may be of particular interest if the users are competitors. In order to avoid manipulation of the operation between users, a verification step is conducted where the server 120 verifies the received operation control instruction before generating the machinery usage data sample. If the verification is not successful, the corresponding operation control instruction will not be added into the set of historical user profile data.

The verification may be based on a consistency check between the operation control instruction and transaction data. The transaction data may for example be a log or a documentation of each transaction between the user of the agricultural sprayer and a set of providers 130. A first provider may be the chemicals supplier 130. Accordingly, each chemical sold to the user is documented inside the transaction data. A second provider may be the machine manufacturer 130b. Accordingly, transactions (e.g., sold sprayer type and/or sold sprayer upgrade parts) between the user and machine manufacturer 130b are documented inside the transaction data as well. In case an operation control instruction is received from an AMC 110 for a corresponding sprayer, the server initiates the verification process and checks whether the information provided by the operation control instruction is traceable from the transaction data. If for example the operation control instruction indicates that the sprayer has allegedly sprayed a chemical of type A, but no chemical of type A has been sold by the chemicals supplier 130a to the user according to the transaction data, then the operation control instruction is not traceable from the transaction data and the operation control instruction can be considered as corrupted. However, if the operation control instruction is traceable from the transaction data (for example, the indicated type and amount of sprayed chemicals has been sold to the user by the chemicals supplier 130a), it is ensured that the user of the agricultural sprayer is not trying to manipulate the system with corrupted data.

In the example illustrated in Fig. 3 the transaction data is stored on a blockchain 140 to further increase the system integrity. In this case, when initiating the verification of the operation control instruction by the server 120, the server 120 may verify whether the operation control instruction can be verified (i.e., is traceable) based on the transaction data stored on the blockchain. The transaction data at least contains each transaction made between the user of the agricultural machinery and each provider (e.g., chemicals supplier 130a and machine manufacturer 130b). In general, one can consider the verification to be successful if the data (i.e., the operation control instruction) is consistent with (i.e., traceable from) the data stored on the blockchain. In the example of Fig. 3 with only 2 providers this would be the case if the operation control instruction is traceable from the transaction data stored on the blockchain, wherein the transaction data at least includes the chemicals, the machine and the machine upgrades sold to the user. In case of a successful verification, the blockchain storing the transaction data 140 will be updated accordingly, and the server 120 is notified about the validity of the operation control instruction. The server 120 may then proceed with generating the machinery usage data sample.

Fig. 4 shows a method 400 for supporting usage of an agricultural machinery. The method 400 may for example be performed by the server 120 of system 100. The steps described in the following (i.e., 410, 420, 430) may correspond to the corresponding steps performed by the server 120 with respect to the method 200. In step 410, the server 120 receives the collected user profile data from an AMC 110. In step 420, the server generates an instruction for usage of the agricultural machinery based at least in part on the collected user profile data In step 430, the server 120 transmits the instruction for usage of the agricultural machinery to the AMC 110.

In a non-illustrated embodiment, the server 120 may receive an operation control instruction from the AMC 110 and determine based on at least the operation control instruction a score. In a further non-illustrated embodiment, the server 120 may verify the operation control instruction received from the AMC 110. A method for verifying an operation control instruction may for example be the method 500 described with respect to Fig. 5.

It is to be understood that the specific order or hierarchy of steps in the method 400 are an illustration of an exemplary process. Based upon design or implementation preferences, it is understood that the specific order or hierarchy of steps in the method 400 may be rearranged.

Fig. 5 shows a method 500 for verifying an operation control instruction. In step 510, it is determined whether the operation control instruction is consistent with transaction data 140 exchanged between a user of the agricultural machinery and a set of providers 130. In step 520, the server 120 determines a validity of the operation control instruction based on the consistency check of step 510. In step 530, if the operation control instruction is determined as valid in step 520, a blockchain storing the transaction data is updated according to the operation control instruction.

It is to be understood that the specific order or hierarchy of steps in the method 500 are an illustration of an exemplary process. Based upon design or implementation preferences, it is understood that the specific order or hierarchy of steps in the method 500 may be rearranged.