Disclosure of Invention
In view of the above problems, the present application provides an agricultural machinery operation mode recognition model training method, an agricultural machinery operation mode recognition model training device, and a terminal device.
The application provides an agricultural machinery operation mode recognition model training method, which comprises the following steps:
the method comprises the steps of obtaining a first sampling data set and a second sampling data set, wherein the first sampling data set is a data set formed by a plurality of pieces of driving data collected by an agricultural machine in the driving process of a road area, the second sampling data set is a data set formed by a plurality of pieces of driving data collected by the agricultural machine in the driving process of an operation area, and each piece of driving data in the first sampling data set or the second sampling data set comprises sampling time, driving speed, position coordinates, linear acceleration, angular acceleration and course angle;
sequentially traversing the driving speed, the position coordinate, the linear acceleration, the angular acceleration and the course angle in each driving data in the first sampling data set and the second sampling data set according to the sampling time to filter and remove interference data in the first sampling data set and the second sampling data set;
and training an agricultural machinery operation mode recognition model by using the first sampling data set and the second sampling data set after the interference data is removed.
According to the agricultural machinery operation mode recognition model training method, the interference data comprise stop data and drift data, the stop data are data collected when the agricultural machinery stops, and the drift data are sampling abnormal data.
The application discloses agricultural machinery running mode identification model training method, according to the sampling time traverse travel speed, position coordinate, linear acceleration, angular acceleration and course angle in each piece of the data of going in the first sampling data set with the second sampling data set in proper order and remove with the filtration first sampling data set with the interference data in the second sampling data set, include:
sequentially arranging the running data in the first sampling data set and the second sampling data set according to the sampling time corresponding to each piece of running data;
sequentially traversing each piece of driving data in the first sampling data set and the second sampling data set;
if the running speed in N continuous running data in the first sampling data set or the second sampling data set is zero, removing N-1 running data from the N continuous running data, wherein N is more than or equal to 2;
and marking the running data reserved in the continuous N running data in the first sampling data set or the second sampling data set to obtain marked data.
The application discloses agricultural machinery running mode identification model training method, will get rid of stop data first sampling data set is recorded as first standard data set, will get rid of stop data the second sampling data set is recorded as the second standard data set, according to sampling time traversals in proper order travel speed, position coordinate, linear acceleration, angular acceleration and course angle in the first sampling data set with each data of traveling in the second sampling data set get rid of with the filtration first sampling data set with the interference data in the second sampling data set, still include:
segmenting the first normative dataset according to the label data in the first normative dataset to determine a plurality of first normative dataset subsets;
segmenting the second normative dataset according to the label data in the second normative dataset to determine a plurality of second normative datasets;
and traversing the travel speed, the position coordinates, the linear acceleration, the angular acceleration and the heading angle in each travel data in each first standard data subset and each second standard data subset to filter and remove drift data in each first standard data subset and each second standard data subset.
The agricultural machinery operation mode recognition model training method provided by the application is used for traversing the driving speed, the position coordinates, the linear acceleration, the angular acceleration and the course angle in each driving data in each first standard data subset and each second standard data subset so as to filter and remove drift data in each first standard data subset and each second standard data subset, and comprises the following steps:
when determining the ith piece of driving data in the jth first standard data subset or the second standard data subset:
estimating an estimated distance between an agricultural machine position corresponding to the i-1 th driving data and an agricultural machine position corresponding to the i-1 th driving data by using a sampling time interval and the driving speed and the linear acceleration in the i-1 th driving data in the jth first standard data subset or the second standard data subset;
estimating an estimated angular displacement between a course angle corresponding to the i-1 th running data and a course angle corresponding to the i-1 th running data by using a sampling time interval and the angular acceleration in the i-1 th running data;
determining an actual distance between an agricultural machine position corresponding to the i-2 th driving data and an agricultural machine position corresponding to the i-1 th driving data by using a position coordinate in the i-2 th driving data in the jth first standard data subset or the second standard data subset and a position coordinate in the i-1 th driving data;
determining a distance mean value according to the difference of position coordinates in all adjacent data before the i-1 th driving data in the jth first standard data subset or the second standard data subset;
determining a maximum distance and a minimum distance from the estimated distance, the actual distance, and the distance mean;
and determining the ith driving data according to the maximum distance, the minimum distance and the estimated angular displacement.
The method for training the agricultural machinery operation mode recognition model, which determines the ith driving data according to the maximum distance, the minimum distance and the estimated angular displacement, comprises the following steps:
judging whether the difference between the position coordinate in the next driving data adjacent to the i-1 th driving data and the position coordinate in the i-1 th driving data is less than or equal to the maximum distance and greater than or equal to the minimum distance or not;
if the difference between the position coordinates is less than or equal to the maximum distance and greater than or equal to the minimum distance, judging whether the difference between the course angle in the next piece of driving data and the course angle in the i-1 th piece of driving data is less than or equal to the estimated angular displacement;
if the difference of the course angles is less than or equal to the estimated angular displacement, taking the next piece of driving data as the ith piece of driving data;
and if the difference of the position coordinates is greater than the maximum distance or the difference of the position coordinates is less than the minimum distance or the difference of the course angle is greater than the estimated angular displacement, deleting the next piece of driving data.
The application provides an agricultural machinery operation mode recognition model training device, the device includes:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring a first sampling data set and a second sampling data set, the first sampling data set is a data set formed by a plurality of pieces of driving data acquired by an agricultural machine in the driving process of a road area, the second sampling data set is a data set formed by a plurality of pieces of driving data acquired by the agricultural machine in the driving process of an operation area, and each piece of driving data in the first sampling data set or the second sampling data set comprises sampling time, driving speed, position coordinates, linear acceleration, angular acceleration and course angle;
the filtering module is used for sequentially traversing the driving speed, the position coordinate, the linear acceleration, the angular acceleration and the course angle in each driving data in the first sampling data set and the second sampling data set according to the sampling time so as to filter and remove the interference data in the first sampling data set and the second sampling data set;
and the training module is used for training the agricultural machinery operation mode recognition model by utilizing the first sampling data set and the second sampling data set after the interference data is removed.
Agricultural machinery operation mode identification model training device, interference data is including stopping data and drift data, the data that stop data do when agricultural machinery stops are gathered, the drift data are sampling abnormal data.
The application provides a terminal device, which comprises a memory and a processor, wherein the memory stores a computer program, and the computer program executes the agricultural machinery operation mode recognition model training method when running on the processor.
The application provides a readable storage medium, which stores a computer program, and the computer program executes the agricultural machinery operation mode recognition model training method when running on a processor.
According to the method, the sampling time sequentially traverses the running speed, the position coordinate, the linear acceleration, the angular acceleration and the course angle in each running data in the first sampling data set and the second sampling data set so as to filter and remove interference data in the first sampling data set and the second sampling data set, and the first sampling data set and the second sampling data set after the interference data are removed are utilized to train an agricultural machinery operation mode recognition model. On one hand, the agricultural machine operation mode can be automatically identified through the agricultural machine operation mode identification model obtained through training, so that the waste of human resources is avoided, and the working efficiency of the agricultural machine is improved; on the other hand, the first sampling data set and the second sampling data set after the interference data are removed are used for training the agricultural machinery operation mode recognition model, so that the training process of the agricultural machinery operation mode recognition model can be prevented from being interfered by the interference data, and the accuracy of agricultural machinery operation mode recognition is effectively improved.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Hereinafter, the terms "including", "having", and their derivatives, which may be used in various embodiments of the present invention, are only intended to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be construed as first excluding the existence of, or adding to, one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.
Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as those defined in commonly used dictionaries) should be interpreted as having a meaning that is consistent with their contextual meaning in the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in various embodiments of the present invention.
The application provides a method for judging whether an agricultural machine runs in a road area or a working area according to the running speed, position coordinates, linear acceleration, angular acceleration and course angle of the agricultural machine.
According to the technical scheme, a first sampling data set and a second sampling data set are obtained, the first sampling data set is a data set consisting of a plurality of pieces of driving data collected by an agricultural machine in the driving process of a road area, the second sampling data set is a data set consisting of a plurality of pieces of driving data collected by the agricultural machine in the driving process of an operation area, and each piece of driving data in the first sampling data set or the second sampling data set comprises sampling time, driving speed, position coordinates, linear acceleration, angular acceleration and course angle; sequentially traversing the driving speed, the position coordinate, the linear acceleration, the angular acceleration and the course angle in each driving data in the first sampling data set and the second sampling data set according to the sampling time to filter and remove interference data in the first sampling data set and the second sampling data set; the running speed, position coordinates, linear acceleration, angular acceleration and course angle of the agricultural machine in the first sampling data set and the second sampling data set after the interference data is removed can be used as data bases, the model base of the agricultural machine running mode identification model can be trained by the one-dimensional neural network, a two-classification model with the agricultural machine running mode (road mode and operation mode) identification function is obtained, and finally the agricultural machine running mode identification model is used for predicting the running speed, position coordinates, linear acceleration, angular acceleration and course angle of the agricultural machine.
Example 1
One embodiment of the present application, as shown in fig. 1, provides an agricultural machinery operation mode recognition model training method, which includes the following steps:
s100: a first sampled data set and a second sampled data set are acquired.
The first sampling data set is a data set formed by a plurality of pieces of driving data collected by the agricultural machinery in the driving process of a road area, the second sampling data set is a data set formed by a plurality of pieces of driving data collected by the agricultural machinery in the driving process of an operation area, and each piece of driving data in the first sampling data set or the second sampling data set comprises sampling time, driving speed, position coordinates, linear acceleration, angular acceleration and course angle.
Exemplarily, the first sampling data set and the second sampling data set may be pre-stored in a predetermined database, and when the agricultural machinery operation mode identification model is trained, the first sampling data set and the second sampling data set are obtained from the predetermined database, it can be understood that each piece of data in the first sampling data set has a first label, and the first label is used for labeling each piece of data in the first sampling data set as a plurality of pieces of driving data collected by the agricultural machinery in the driving process of the road area; each piece of data in the second sampling data set is provided with a second label, and the first label is used for labeling the second sampling data set as a plurality of pieces of driving data collected in the driving process of the agricultural machinery in the operation area.
For example, the first sampled data set and the second sampled data set may be pre-stored in corresponding files, for example, the first sampled data set is placed in a folder of "road mode", the second sampled data set is placed in a folder of "farm work mode", and when the agricultural machine operation mode recognition model is trained, the agricultural machine operation mode recognition model is trained by using data in the folder of "road mode" and the folder of "farm work mode".
S200: and sequentially traversing the driving speed, the position coordinate, the linear acceleration, the angular acceleration and the course angle in each driving data in the first sampling data set and the second sampling data set according to the sampling time so as to filter and remove the interference data in the first sampling data set and the second sampling data set.
The interference data comprises stop data and drift data, and the stop data is data collected when the agricultural machinery stops. The drift data is data acquired under the condition of sampling abnormality, the sampling abnormality is related to a sensor for acquiring the driving data, for example, the reason for generating the drift data includes that the sensor for acquiring the driving data is not well calibrated when being shipped, so that a fixed-size offset always exists between the acquired driving data and the actual driving data; due to the processing speed of the CPU or the GPS algorithm being not good enough, the sensors (GPS devices) used to collect travel data detect a "drift" in the GPS signal while in motion compared to the data when stopped.
Further, methods for filtering drift data include kalman filtering, bayesian filtering, and the like.
S300: and training an agricultural machinery operation mode recognition model by using the first sampling data set and the second sampling data set after the interference data is removed.
If the collection frequency of the sensor for collecting the driving data is Fhz, considering that the actual running speed of the agricultural machinery is 0-20 km/h, in the actual situation, the running road lengths of the agricultural machinery are different, and one section of data containing obvious features meets the requirement that the road length L is more than 10m, so that the total number of the data collected within 10m is N-10/v-F. According to actual experience, the total number of the data collected within the length of 10 meters is 60-120 data. And then the input layer of the agricultural machinery operation mode recognition model acquires 60-120 pieces of data for training at a time, and preferably, the input layer of the agricultural machinery operation mode recognition model acquires 90 pieces of data for training at a time.
According to the embodiment, the running speed, the position coordinate, the linear acceleration, the angular acceleration and the course angle in each piece of running data in the first sampling data set and the second sampling data set are sequentially traversed according to the sampling time so as to filter and remove interference data in the first sampling data set and the second sampling data set, and the first sampling data set and the second sampling data set after the interference data are removed are utilized to train the agricultural machinery operation mode identification model. On one hand, the agricultural machine operation mode can be automatically recognized through the agricultural machine operation mode recognition model obtained through training, so that the waste of human resources is avoided, and the working efficiency of the agricultural machine is improved; on the other hand, the first sampling data set and the second sampling data set after the interference data are removed are used for training the agricultural machinery operation mode recognition model, so that the training process of the agricultural machinery operation mode recognition model can be prevented from being interfered by the interference data (stop data and drift data), and the accuracy of agricultural machinery operation mode recognition is effectively improved.
Example 2
One embodiment of the present application, as shown in fig. 2, proposes a method of filtering stop data, the method comprising the steps of:
s210: and sequentially arranging the running data in the first sampling data set and the second sampling data set according to the sampling time corresponding to each piece of running data.
S220: sequentially traversing each of the travel data in the first and second sampled data sets.
S230: and if the running speed in the N continuous running data in the first sampling data set or the second sampling data set is zero, removing N-1 running data from the N continuous running data, wherein N is more than or equal to 2.
S240: and marking the running data reserved in the continuous N running data in the first sampling data set or the second sampling data set to obtain marked data.
Further, the first sampled data set from which the stop data is removed is denoted as a first standard data set, and the second sampled data set from which the stop data is removed is denoted as a second standard data set, as shown in fig. 3, a method for filtering drift data is proposed, which includes the following steps:
s250: the first normative dataset is partitioned according to the label data in the first normative dataset to determine a plurality of first normative subsets of data and the second normative dataset is partitioned according to the label data in the second normative dataset to determine a plurality of second normative subsets of data.
Drift data in each of the first and second subsets of standard data may be filtered out by traversing the speed, position coordinates, linear acceleration, angular acceleration, and heading angle in each of the travel data in each of the first and second subsets of standard data.
S260: and estimating an estimated distance between the position of the agricultural machine corresponding to the i-1 th driving data and the position of the agricultural machine corresponding to the i-1 th driving data by using the sampling time interval and the driving speed and the linear acceleration in the i-1 th driving data in the jth first standard data subset or the second standard data subset.
J is more than or equal to 1 and less than or equal to J, and J is the total number of the first standard data subset or the second standard data subset. It will be appreciated that the total number of first subsets of standard data and the total number of second subsets of standard data may not be the same. I is more than or equal to 1 and less than or equal to I, and I is the total number of the driving data in the jth first standard data subset or the second standard data subset.
The sampling time interval is known in advance and can be denoted as t, i.e., the inverse of the sampling frequency of the sensor used to acquire the driving data.
The traveling speed in the i-1 th traveling data can be denoted as vi-1And linear acceleration can be recorded as ai-1And the estimated distance delta S1 between the position of the agricultural machine corresponding to the i-1 th driving data and the position of the agricultural machine corresponding to the i-th driving data is 1/2 ai-1*t2+vi-1。
S270: and estimating the estimated angular displacement between the course angle corresponding to the i-1 th running data and the course angle corresponding to the i-1 th running data by using the sampling time interval and the angular acceleration in the i-1 th running data.
The angular acceleration in the i-1 th running data can be recorded as wi-1If the estimated angular displacement delta w between the heading angle corresponding to the i-1 th driving data and the heading angle corresponding to the i-th driving data is wi-1*t。
S280: and determining the actual distance between the agricultural machinery position corresponding to the i-2 th driving data and the agricultural machinery position corresponding to the i-1 th driving data by using the position coordinate in the i-2 th driving data in the jth first standard data subset or the second standard data subset and the position coordinate in the i-1 th driving data.
The actual distance delta S2 between the position of the agricultural machine corresponding to the i-2 th driving data and the position of the agricultural machine corresponding to the i-1 th driving data is delta Si-1~i-2=Si-1-Si-2,Si-1Representing the position of the agricultural machine corresponding to the i-1 th driving data, Si-2Representing the position of the agricultural machine corresponding to the i-2 th driving data. It can be understood that the actual distance Δ S2 between the position of the agricultural machine corresponding to the i-2 th driving data and the position of the agricultural machine corresponding to the i-1 th driving data does not differ much from the actual distance between the position of the agricultural machine corresponding to the i-1 th driving data and the position of the agricultural machine corresponding to the i-1 th driving data.
S290: and determining a distance mean value according to the difference of position coordinates in all adjacent data before the i-1 th driving data in the jth first standard data subset or the second standard data subset.
The difference between the position coordinates in all the neighboring data before the i-1 th travel data item determines the distance average Δ S3 (Δ S)i-1~i-2+ΔSi-2~i-3+……+ΔS1~2)/(i-2)。
S291: determining a maximum distance and a minimum distance from the estimated distance, the actual distance, and the distance mean.
The maximum distance and the minimum distance are determined from Δ S1, Δ S2, and Δ S3.
S292: and determining the ith driving data according to the maximum distance, the minimum distance and the estimated angular displacement.
It may be determined whether a difference between the position coordinate in the next travel data adjacent to the i-1 th travel data and the position coordinate in the i-1 th travel data is equal to or less than the maximum distance and equal to or greater than the minimum distance.
And if the difference between the position coordinates is less than or equal to the maximum distance and greater than or equal to the minimum distance, judging whether the difference between the course angle in the next piece of driving data and the course angle in the i-1 th piece of driving data is less than or equal to the estimated angular displacement.
If the difference of the course angles is less than or equal to the estimated angular displacement, taking the next piece of driving data as the ith piece of driving data; and if the difference of the position coordinates is greater than the maximum distance or the difference of the position coordinates is less than the minimum distance or the difference of the course angle is greater than the estimated angular displacement, deleting the next piece of driving data.
Exemplarily, as shown in fig. 4, the maximum distance may be represented as a boundary where the maximum circle in fig. 4 is located, and the minimum distance may be represented as a boundary where the minimum circle in fig. 4 is located, it is understood that the next driving data adjacent to the i-1 th driving data should be located in an area formed by the maximum circle boundary and the minimum circle boundary, and further, according to the estimated angular displacement, it may be determined that the i-th driving data is located in an area formed by the maximum distance, the minimum distance, and the estimated angular displacement, such as a shaded area shown in fig. 4, and then the driving data corresponding to the position coordinates located in the shaded area may be used as the i-th driving data, i.e., point a in fig. 4.
Example 3
In one embodiment of the present application, as shown in fig. 5, an agricultural machinery operation mode recognition model training device 10 includes an obtaining module 11, a filtering module 12, and a training module 13.
The system comprises an acquisition module 11, a first sampling data set and a second sampling data set, wherein the first sampling data set is a data set consisting of a plurality of pieces of driving data acquired by an agricultural machine in the driving process of a road area, the second sampling data set is a data set consisting of a plurality of pieces of driving data acquired by the agricultural machine in the driving process of an operation area, and each piece of driving data in the first sampling data set or the second sampling data set comprises sampling time, driving speed, position coordinates, linear acceleration, angular acceleration and course angle; the filtering module 12 is configured to sequentially traverse the driving speed, the position coordinate, the linear acceleration, the angular acceleration, and the heading angle in each driving data in the first sampling data set and the second sampling data set according to the sampling time to filter and remove interference data in the first sampling data set and the second sampling data set; and the training module 13 is used for training the agricultural machinery operation mode recognition model by using the first sampling data set and the second sampling data set after the interference data is removed.
Further, the interference data comprises stop data and drift data, the stop data is data collected when the agricultural machinery stops, the drift data is data collected under the abnormal sampling condition, and the abnormal sampling condition is related to a sensor used for collecting driving data.
Further, the sequentially traversing the driving speed, the position coordinate, the linear acceleration, the angular acceleration and the heading angle in each driving data in the first sampling data set and the second sampling data set according to the sampling time to filter and remove the interference data in the first sampling data set and the second sampling data set includes: sequentially arranging the running data in the first sampling data set and the second sampling data set according to the sampling time corresponding to each piece of running data; sequentially traversing each piece of driving data in the first sampling data set and the second sampling data set; if the running speed in N continuous running data in the first sampling data set or the second sampling data set is zero, removing N-1 running data from the N continuous running data, wherein N is more than or equal to 2; and marking the running data reserved in the continuous N running data in the first sampling data set or the second sampling data set to obtain marked data.
Further, the step of sequentially traversing the travel speed, the position coordinate, the linear acceleration, the angular acceleration, and the heading angle in each piece of the travel data in the first sample data set and the second sample data set according to the sampling time to filter and remove the interference data in the first sample data set and the second sample data set further includes: segmenting the first normative dataset according to the label data in the first normative dataset to determine a plurality of first normative dataset subsets; segmenting the second normative dataset according to the label data in the second normative dataset to determine a plurality of second normative datasets; and traversing the travel speed, the position coordinates, the linear acceleration, the angular acceleration and the heading angle in each travel data in each first standard data subset and each second standard data subset to filter and remove drift data in each first standard data subset and each second standard data subset.
Further, the traversing of the travel speed, the position coordinate, the linear acceleration, the angular acceleration, and the heading angle in each of the travel data in each of the first and second subsets of standard data to filter drift data in each of the first and second subsets of standard data includes: when determining the ith piece of driving data in the jth first standard data subset or the second standard data subset: estimating an estimated distance between an agricultural machine position corresponding to the i-1 th driving data and an agricultural machine position corresponding to the i-1 th driving data by using a sampling time interval and the driving speed and the linear acceleration in the i-1 th driving data in the jth first standard data subset or the second standard data subset; estimating an estimated angular displacement between a course angle corresponding to the i-1 th running data and a course angle corresponding to the i-1 th running data by using a sampling time interval and the angular acceleration in the i-1 th running data; determining an actual distance between an agricultural machine position corresponding to the i-2 th driving data and an agricultural machine position corresponding to the i-1 th driving data by using a position coordinate in the i-2 th driving data in the jth first standard data subset or the second standard data subset and a position coordinate in the i-1 th driving data; determining a distance mean value according to the difference of position coordinates in all adjacent data before the i-1 th driving data in the jth first standard data subset or the second standard data subset; determining a maximum distance and a minimum distance from the estimated distance, the actual distance, and the distance mean; and determining the ith driving data according to the maximum distance, the minimum distance and the estimated angular displacement.
Further, the determining the ith driving data according to the maximum distance, the minimum distance and the estimated angular displacement includes: judging whether the difference between the position coordinate in the next driving data adjacent to the i-1 th driving data and the position coordinate in the i-1 th driving data is less than or equal to the maximum distance and greater than or equal to the minimum distance or not; if the difference between the position coordinates is less than or equal to the maximum distance and greater than or equal to the minimum distance, judging whether the difference between the course angle in the next piece of driving data and the course angle in the i-1 th piece of driving data is less than or equal to the estimated angular displacement; if the difference of the course angles is less than or equal to the estimated angular displacement, taking the next piece of driving data as the ith piece of driving data; and if the difference of the position coordinates is greater than the maximum distance or the difference of the position coordinates is less than the minimum distance or the difference of the course angle is greater than the estimated angular displacement, deleting the next piece of driving data.
The agricultural machinery operation mode recognition model training device 10 disclosed in this embodiment is used for executing the agricultural machinery operation mode recognition model training method described in the above embodiment by matching the acquisition module 11, the filtering module 12, and the training module 13, and the implementation scheme and the beneficial effects related to the above embodiment are also applicable in this embodiment, and are not described again here.
The application also relates to a terminal device, which comprises a memory and a processor, wherein the memory stores a computer program, and the computer program executes the agricultural machinery operation mode recognition model training method when running on the processor.
The present application also relates to a readable storage medium storing a computer program which, when executed on a processor, performs the agricultural operation mode recognition model training method described herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, each functional module or unit in each embodiment of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solution of the present invention or a part of the technical solution that contributes to the prior art in essence can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention.