CN117910228A - Method and related device for generating agronomic scheme based on agronomic scheme model - Google Patents
Method and related device for generating agronomic scheme based on agronomic scheme model Download PDFInfo
- Publication number
- CN117910228A CN117910228A CN202311786177.4A CN202311786177A CN117910228A CN 117910228 A CN117910228 A CN 117910228A CN 202311786177 A CN202311786177 A CN 202311786177A CN 117910228 A CN117910228 A CN 117910228A
- Authority
- CN
- China
- Prior art keywords
- agricultural
- model
- crop growth
- agronomic
- scheme
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000009418 agronomic effect Effects 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 70
- 238000000605 extraction Methods 0.000 claims abstract description 35
- 208000024891 symptom Diseases 0.000 claims description 75
- 238000012549 training Methods 0.000 claims description 24
- 239000002689 soil Substances 0.000 claims description 17
- 238000010276 construction Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000012271 agricultural production Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
Abstract
The invention discloses a method for generating an agronomic scheme based on an agronomic scheme model, which comprises the following steps: acquiring agricultural data information to construct an agricultural expert knowledge base, and constructing an agricultural scheme model based on the agricultural expert knowledge base; constructing a condition constraint sub-model to constrain the agronomic scheme model; inputting current crop growth condition data information, and performing feature extraction processing; judging the crop growth condition based on the characteristic extraction result of the agronomic scheme model; the agronomic scheme model calls an agronomic expert knowledge base to judge the growth condition of crops and process the result to generate an agronomic scheme; the method realizes that the agronomic scheme model is built based on the agronomic expert knowledge base, and the agronomic scheme model generates the agronomic scheme based on the input of the current crop growth condition data information, thereby being beneficial to the quality and the yield of agricultural production.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to a method and a related device for generating an agricultural scheme based on an agricultural scheme model.
Background
With the continuous development of digital agriculture, the agricultural experience is developed from manual to digital, and the traditional agricultural experience is summarized and implemented by farmers according to experience, so that the crop yield and quality are lower. The experienced agricultural expert has better agricultural knowledge and experience, and can conduct agricultural guidance on farmers. However, the number of agricultural specialists is limited, and the popularization of agricultural technology cannot be well performed.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method and a related device for generating an agronomic scheme based on an agronomic scheme model, which are used for generating the agronomic scheme based on the input of the current crop growth condition data information by constructing the agronomic scheme model based on an agronomic expert knowledge base.
In order to achieve the above object, the present invention adopts the following technical scheme:
the first aspect of the application provides a method for generating an agronomic proposal based on an agronomic proposal model, comprising the following steps:
S101, acquiring agricultural data information to construct an agricultural expert knowledge base, and constructing an agricultural scheme model based on the agricultural expert knowledge base;
s102, constructing a condition constraint sub-model to constrain the agronomic scheme model;
s103, inputting current crop growth condition data information, and performing feature extraction processing;
S104, judging the growth condition of crops based on the feature extraction result of the agronomic proposal model;
s105, the agronomic scheme model calls an agronomic expert knowledge base to generate an agronomic scheme for the crop growth condition judging and processing result.
Further, the step of obtaining the agricultural data information to construct an agricultural expert knowledge base comprises the following steps:
acquiring agricultural data information and performing feature extraction processing;
And constructing an agricultural expert knowledge base based on the feature extraction processing result.
Further, constructing an agricultural scheme model based on the agricultural expert knowledge base comprises the following steps:
constructing a data set of a large language model based on an agricultural expert knowledge base;
Constructing batched data sets based on an agricultural expert knowledge base, and carrying out batch training on a large language model based on a predefined template for each batch of data sets;
If the model obtained by the current batch training is higher than the preset training loss, fine-tuning a template of the template (the template can contain context information so that the model can understand and generate content related to the template, and the context can be previous dialogue history, background knowledge or constraint in a specific field) and a data set are retrained;
If the model obtained by the training of the current batch is not higher than the preset training loss, continuing to train the data set of the next batch, and training the next batch based on the model obtained by the training of the previous batch until the training of the data sets of all batches is completed, so as to obtain the farm scheme model.
Further, the condition constraint sub-model comprises a user limiting module, an industry limiting module and an output limiting module.
Further, constructing a condition constraint sub-model to constrain the agronomic scheme model includes the following steps:
Constructing a condition constraint sub-model, wherein the condition constraint sub-model comprises a user limiting module, an industry limiting module and an output limiting module;
The user limiting module is used for carrying out operation processing of corresponding authority levels according to users with different authority levels;
an industry restriction module based on the condition constraint sub-model, which is used for outputting only agriculture related answer data content based on the inputted question data;
And the output limiting module is used for limiting the file format of the output content data based on the condition constraint submodel.
Further, inputting current crop growth condition data information and performing feature extraction processing comprises the following steps:
Inputting crop growth environment data information and crop growth stage data information:
Carrying out data preprocessing on crop growth environment data information and crop growth stage data information;
Extracting characteristic keywords from the data preprocessing result to obtain weather characteristic keywords, soil characteristic keywords, crop growth characteristic keywords and crop growth symptom characteristic keywords, constructing a knowledge graph based on the extraction result of the characteristic keywords, wherein the knowledge graph comprises different crop types and growth symptom characteristics of different crops under different weather characteristics, soil characteristics and crop growth characteristics, and storing the obtained knowledge graph in a graph database in a distributed manner.
Further, the crop growth condition judgment processing for the feature extraction result based on the agronomic program model includes the following steps:
If the knowledge graph is not searched, inputting meteorological features, soil features and crop growth features into an agronomic scheme model to judge and treat crop growth symptoms, so as to obtain a crop growth symptom judging and treating result;
if the crop growth symptom judging treatment result is dissimilar to the crop growth symptom characteristic, marking the crop growth symptom judging treatment result;
if the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, selecting the crop growth symptom judging and processing result similar to the crop growth symptom characteristic;
And calculating a cosine similarity formula by using the similarity between the crop growth symptom judging and processing result and the crop growth symptom characteristic:
Wherein similarity is the result of the crop growth symptom judging treatment and the characteristic of the crop growth symptom
The degree of similarity between the two,Representing the predicted crop growth symptom feature vector,/>Representing the characteristic vector of the known existing crop growth symptoms.
Further, the agricultural scheme model calls an agricultural expert knowledge base to judge the crop growth condition and generate an agricultural scheme according to the result of the processing, and the agricultural scheme comprises the following steps:
If the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, invoking an agricultural expert knowledge base based on an agricultural scheme model, and generating an agricultural scheme based on the crop growth symptom judging and processing result similar to the crop growth symptom characteristic;
If the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, marking the crop growth symptom judging and processing result by the agronomic scheme model and outputting the result.
A second aspect of the present application provides a system for generating an agricultural solution based on an agricultural solution model, comprising:
The data acquisition unit is used for acquiring agricultural data information;
a first construction unit for constructing an agricultural expert knowledge base based on the agricultural data information;
the second construction unit is used for constructing an agronomic scheme model based on an agronomic expert knowledge base;
The third construction unit is used for constructing a condition constraint sub-model which is used for constraining the agronomic scheme model;
the first processing unit is used for inputting current crop growth condition data information and carrying out characteristic extraction processing;
the second processing unit is used for judging and processing the crop growth condition on the basis of the characteristic extraction result of the agronomic scheme model;
The third processing unit is used for calling an agricultural expert knowledge base to judge the growth condition of the crops by the agricultural scheme model to generate an agricultural scheme;
the user interaction unit is used for inquiring, formulating and managing the agricultural scheme by a user;
And the agriculture management unit is used for carrying out agriculture recording, growth environment monitoring and agriculture scheme management.
A third aspect of the present application provides an apparatus for generating an agricultural solution based on an agricultural solution model, comprising a processor and a memory:
The memory is used for storing the program codes and transmitting the program codes to the processor;
The processor is configured to generate a agronomic solution method based on an agronomic solution model for performing the above method according to instructions in the program code.
A fourth aspect of the present application provides a computer readable storage medium storing program code for performing the method of generating an agricultural solution based on the agricultural solution model of the first aspect.
The application has the beneficial effects that: the method realizes that the agronomic scheme model is built based on the agronomic expert knowledge base, and the agronomic scheme model generates the agronomic scheme based on the input of the current crop growth condition data information.
The method has the advantages that the large-scale language model technology and the agricultural expert knowledge base are utilized to construct an agricultural scheme model, the agricultural scheme is intelligently recommended to farmers, the problem that the traditional agricultural scheme is roughly managed and even does not exist is solved, the agricultural production level is further improved, namely agricultural scheme generation of agricultural producers is facilitated, agricultural activities are formulated aiming at the intelligent agricultural scheme, and the quality and the yield of agricultural production can be facilitated.
The problem of lack of farmer experience is solved by the agriculture scheme model, and the problem of agricultural technology is solved by changing the past experience to be less and no experience into the popularization guidance of the expert knowledge base.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the steps of a method of generating an agronomic program based on an agronomic program model according to the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
a method of generating an agronomic proposal based on an agronomic proposal model, comprising the steps of:
S101, acquiring agricultural data information to construct an agricultural expert knowledge base, and constructing an agricultural scheme model based on the agricultural expert knowledge base;
and constructing an agricultural expert knowledge base by acquiring agricultural data information, and constructing an agricultural scheme model based on the agricultural expert knowledge base. The method for acquiring the agricultural data information may be that the agricultural data information is acquired by accessing a connection paper database, the agricultural data information is acquired by accessing a connection hundred-degree database, or the agricultural data information … … is acquired by accessing a connection server database, and the specific setting of the acquisition method for acquiring the agricultural data information is not made in the invention.
The method for obtaining the agricultural data information and constructing the agricultural expert knowledge base comprises the following steps:
acquiring agricultural data information and performing feature extraction processing;
And constructing an agricultural expert knowledge base based on the feature extraction processing result.
The construction of the agriculture scheme model based on the agriculture expert knowledge base comprises the following steps:
constructing a data set of a large language model based on an agricultural expert knowledge base;
Constructing batched data sets based on an agricultural expert knowledge base, and carrying out batch training on a large language model based on a predefined template for each batch of data sets;
If the model obtained by the current batch training is higher than the preset training loss, fine-tuning a template of the template (the template can contain context information so that the model can understand and generate content related to the template, and the context can be previous dialogue history, background knowledge or constraint in a specific field) and a data set are retrained;
If the model obtained by the training of the current batch is not higher than the preset training loss, continuing to train the data set of the next batch, and training the next batch based on the model obtained by the training of the previous batch until the training of the data sets of all batches is completed, so as to obtain the farm scheme model.
S102, constructing a condition constraint sub-model to constrain the agronomic scheme model;
And constructing an agricultural expert knowledge base by acquiring agricultural data information, and constructing an agricultural scheme model based on the agricultural expert knowledge base to complete the construction of the agricultural scheme model so as to obtain the agricultural scheme model. And constraining the agronomic scheme model by constructing a condition constraint sub-model, wherein the condition constraint sub-model comprises a user limiting module, an industry limiting module and an output limiting module. It should be noted that, the user restriction module is used for defining the authority level of the agricultural expert role for the user, and restricting the user authority based on the authority level of the agricultural expert role, that is, the user restriction module is used for performing the operation processing of the corresponding authority level according to the users with different authority levels. The industry restriction module is used for carrying out industry restriction on the output data content, namely the industry restriction module is used for only outputting agriculture related answer data content based on the input question data. The output limiting module is used for limiting the file format of the output content data.
The construction of the condition constraint sub-model to constrain the agronomic scheme model comprises the following steps:
Constructing a condition constraint sub-model, wherein the condition constraint sub-model comprises a user limiting module, an industry limiting module and an output limiting module;
The user limiting module is used for carrying out operation processing of corresponding authority levels according to users with different authority levels;
an industry restriction module based on the condition constraint sub-model, which is used for outputting only agriculture related answer data content based on the inputted question data;
And the output limiting module is used for limiting the file format of the output content data based on the condition constraint submodel.
S103, inputting current crop growth condition data information, and performing feature extraction processing;
The agricultural expert knowledge base is constructed by acquiring the agricultural data information, the agricultural scheme model is constructed based on the agricultural expert knowledge base, the construction of the agricultural scheme model is completed, the agricultural scheme model is obtained, and the agricultural scheme model is constrained by the construction condition constraint sub-model. Inputting current crop growth condition data information, and performing feature extraction processing. The current crop growth condition data information includes crop growth environment data information and crop growth stage data information, the crop growth environment data information includes meteorological data information and soil data information, and the crop growth stage data information includes crop growth symptom data information and crop growth data information.
Inputting current crop growth condition data information and performing feature extraction processing comprises the following steps:
Inputting crop growth environment data information and crop growth stage data information:
Carrying out data preprocessing on crop growth environment data information and crop growth stage data information;
Extracting characteristic keywords from the data preprocessing result to obtain weather characteristic keywords, soil characteristic keywords, crop growth characteristic keywords and crop growth symptom characteristic keywords, constructing a knowledge graph based on the extraction result of the characteristic keywords, wherein the knowledge graph comprises different crop types and growth symptom characteristics of different crops under different weather characteristics, soil characteristics and crop growth characteristics, and storing the obtained knowledge graph in a graph database in a distributed manner.
The crop growth environment data information includes meteorological data information and soil data information, the meteorological data information refers to the temperature, humidity, wind power, illumination intensity and rainfall … … of the current location of crops, the soil data information includes the current soil humidity, soil temperature, soil acid-base number and soil NPK … … crop growth symptom data information refers to the softening of branches and leaves, early leaf sunset and small leaf shrinkage … … of crops, and the crop growth data information refers to the germination period, seedling period, growth development period, flowering period and fruit period … … of crops
S104, judging the growth condition of crops based on the feature extraction result of the agronomic proposal model;
Inputting current crop growth condition data information, carrying out feature extraction processing to obtain feature extraction processing results, and carrying out crop growth condition judgment processing on the feature extraction results based on a farming scheme model, wherein the feature extraction results comprise meteorological features, soil features, crop growth features and crop growth symptom features.
The crop growth condition judging processing for the feature extraction result based on the agronomic proposal model comprises the following steps:
If the knowledge graph is not searched, inputting meteorological features, soil features and crop growth features into an agronomic scheme model to judge and treat crop growth symptoms, so as to obtain a crop growth symptom judging and treating result;
if the crop growth symptom judging treatment result is dissimilar to the crop growth symptom characteristic, marking the crop growth symptom judging treatment result;
if the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, selecting the crop growth symptom judging and processing result similar to the crop growth symptom characteristic;
And calculating a cosine similarity formula by using the similarity between the crop growth symptom judging and processing result and the crop growth symptom characteristic:
wherein similarity is the similarity between the result of the crop growth symptom judging treatment and the characteristic of the crop growth symptom, Representing the predicted crop growth symptom feature vector,/>Representing the characteristic vector of the known existing crop growth symptoms. The vector information can be obtained by inputting the characteristic text data into the bert model, and the obtained vector information is actually the sum of token embeddings (vector representation of words), segment embeddings (vector representation of two sentences in the auxiliary bert distinguishing sentence pair), position embeddings (vector representation of the input sequence attribute is learned by bert).
S105, the agronomic scheme model calls an agronomic expert knowledge base to generate an agronomic scheme for the crop growth condition judging and processing result;
Crop growth condition judgment processing is carried out on the feature extraction result based on the agronomic scheme model to obtain a crop growth condition judgment processing result, the agronomic scheme model calls an agronomic expert knowledge base to generate an agronomic scheme for the crop growth condition judgment processing result, and the crop growth condition judgment processing result comprises dissimilar crop growth condition judgment and similar crop growth condition judgment.
The agricultural scheme model calls an agricultural expert knowledge base to judge the growth condition of crops to generate an agricultural scheme, and the agricultural scheme comprises the following steps:
If the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, the agronomic scheme model calls an agronomic expert knowledge base, and an agronomic scheme is generated based on the crop growth symptom judging and processing result similar to the crop growth symptom characteristic;
If the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, marking the crop growth symptom judging and processing result by the agronomic scheme model and outputting the result.
The method for generating the agronomic scheme based on the agronomic scheme model is provided in the embodiment of the application, and the system for generating the agronomic scheme based on the agronomic scheme model is provided in the embodiment of the application.
A system for generating an agronomic proposal based on an agronomic proposal model, comprising:
The data acquisition unit is used for acquiring agricultural data information;
a first construction unit for constructing an agricultural expert knowledge base based on the agricultural data information;
the second construction unit is used for constructing an agronomic scheme model based on an agronomic expert knowledge base;
The third construction unit is used for constructing a condition constraint sub-model which is used for constraining the agronomic scheme model;
the first processing unit is used for inputting current crop growth condition data information and carrying out characteristic extraction processing;
the second processing unit is used for judging and processing the crop growth condition on the basis of the characteristic extraction result of the agronomic scheme model;
The third processing unit is used for calling an agricultural expert knowledge base to judge the growth condition of the crops by the agricultural scheme model to generate an agricultural scheme;
the user interaction unit is used for inquiring, formulating and managing the agricultural scheme by a user;
And the agriculture management unit is used for carrying out agriculture recording, growth environment monitoring and agriculture scheme management.
Further, in an embodiment of the present application, there is also provided an apparatus for generating an agronomic solution based on an agronomic solution model, the apparatus including a processor and a memory:
The memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute the agronomic solution method based on the agronomic solution model of the method embodiment described above according to instructions in the program code.
Further, in an embodiment of the present application, there is also provided a computer readable storage medium, where the computer readable storage medium is used to store program code, where the program code is used to execute the method for generating an agronomic solution based on an agronomic solution model according to the embodiment of the method described above.
It will be clear to those skilled in the art that, for convenience and brevity of description, the specific working procedures of the above-described system and unit may refer to the corresponding procedures in the foregoing method embodiments, which are not repeated here.
The terms "first," "second," and "third" in the description of the application and in the above-described figures, etc. are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: u disk, mobile hard disk, read-only memory (ROM), random access memory (RandomAccess Memory, RAM), magnetic disk or optical disk, etc.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A method for generating an agricultural regimen based on an agricultural regimen model, comprising the steps of:
S101, acquiring agricultural data information to construct an agricultural expert knowledge base, and constructing an agricultural scheme model based on the agricultural expert knowledge base;
s102, constructing a condition constraint sub-model to constrain the agronomic scheme model;
s103, inputting current crop growth condition data information, and performing feature extraction processing;
S104, judging the growth condition of crops based on the feature extraction result of the agronomic proposal model;
s105, the agronomic scheme model calls an agronomic expert knowledge base to generate an agronomic scheme for the crop growth condition judging and processing result.
2. The method for generating an agricultural solution based on an agricultural solution model according to claim 1, wherein the step of obtaining agricultural data information to construct an agricultural expert knowledge base includes the steps of:
acquiring agricultural data information and performing feature extraction processing;
And constructing an agricultural expert knowledge base based on the feature extraction processing result.
3. The method for generating an agricultural solution based on an agricultural solution model according to claim 1, wherein the constructing an agricultural solution model based on an agricultural expert knowledge base includes the steps of:
constructing a data set of a large language model based on an agricultural expert knowledge base;
Constructing batched data sets based on an agricultural expert knowledge base, and carrying out batch training on a large language model based on a predefined template for each batch of data sets;
If the model obtained by the current batch of training is higher than the preset training loss, fine-tuning the template and the data set for retraining;
If the model obtained by the training of the current batch is not higher than the preset training loss, continuing to train the data set of the next batch, and training the next batch based on the model obtained by the training of the previous batch until the training of the data sets of all batches is completed, so as to obtain the farm scheme model.
4. The method for generating an agricultural solution based on an agricultural solution model according to claim 1, wherein the construction condition constraint sub-model constrains the agricultural solution model comprising the steps of:
Constructing a condition constraint sub-model, wherein the condition constraint sub-model comprises a user limiting module, an industry limiting module and an output limiting module;
The user limiting module is used for carrying out operation processing of corresponding authority levels according to users with different authority levels;
an industry restriction module based on the condition constraint sub-model, which is used for outputting only agriculture related answer data content based on the inputted question data;
And the output limiting module is used for limiting the file format of the output content data based on the condition constraint submodel.
5. The method for generating an agricultural scheme based on an agricultural scheme model according to claim 1, wherein the inputting current crop growth data information and performing feature extraction processing comprises the steps of:
Inputting crop growth environment data information and crop growth stage data information:
Carrying out data preprocessing on crop growth environment data information and crop growth stage data information;
Extracting characteristic keywords from the data preprocessing result to obtain weather characteristic keywords, soil characteristic keywords, crop growth characteristic keywords and crop growth symptom characteristic keywords, constructing a knowledge graph based on the extraction result of the characteristic keywords, wherein the knowledge graph comprises different crop types and growth symptom characteristics of different crops under different weather characteristics, soil characteristics and crop growth characteristics, and storing the obtained knowledge graph in a graph database in a distributed manner.
6. The agronomic scheme generating method based on the agronomic scheme model according to claim 1, wherein the agronomic scheme model based on the agronomic scheme model performs the crop growth condition judging processing on the feature extraction result, comprising the steps of:
If the knowledge graph is not searched, inputting meteorological features, soil features and crop growth features into an agronomic scheme model to judge and treat crop growth symptoms, so as to obtain a crop growth symptom judging and treating result;
if the crop growth symptom judging treatment result is dissimilar to the crop growth symptom characteristic, marking the crop growth symptom judging treatment result;
if the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, selecting the crop growth symptom judging and processing result similar to the crop growth symptom characteristic;
And calculating a cosine similarity formula by using the similarity between the crop growth symptom judging and processing result and the crop growth symptom characteristic:
wherein similarity is the similarity between the result of the crop growth symptom judging treatment and the characteristic of the crop growth symptom, Representing the predicted crop growth symptom feature vector,/>Representing the characteristic vector of the known existing crop growth symptoms.
7. The method for generating an agricultural scheme based on an agricultural scheme model according to claim 1, wherein the agricultural scheme model calls an agricultural expert knowledge base to generate an agricultural scheme for a crop growth condition determination processing result, comprising the steps of:
If the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, invoking an agricultural expert knowledge base based on an agricultural scheme model, and generating an agricultural scheme based on the crop growth symptom judging and processing result similar to the crop growth symptom characteristic;
If the crop growth symptom judging and processing result is similar to the crop growth symptom characteristic, marking the crop growth symptom judging and processing result by the agronomic scheme model and outputting the result.
8. A system for generating an agricultural solution based on an agricultural solution model for implementing the method for generating an agricultural solution based on an agricultural solution model according to claims 1-7, comprising:
The data acquisition unit is used for acquiring agricultural data information;
a first construction unit for constructing an agricultural expert knowledge base based on the agricultural data information;
the second construction unit is used for constructing an agronomic scheme model based on an agronomic expert knowledge base;
The third construction unit is used for constructing a condition constraint sub-model which is used for constraining the agronomic scheme model;
the first processing unit is used for inputting current crop growth condition data information and carrying out characteristic extraction processing;
the second processing unit is used for judging and processing the crop growth condition on the basis of the characteristic extraction result of the agronomic scheme model;
The third processing unit is used for calling an agricultural expert knowledge base to judge the growth condition of the crops by the agricultural scheme model to generate an agricultural scheme;
the user interaction unit is used for inquiring, formulating and managing the agricultural scheme by a user;
And the agriculture management unit is used for carrying out agriculture recording, growth environment monitoring and agriculture scheme management.
9. An apparatus for generating an agricultural regimen based on an agricultural regimen model, comprising a processor and a memory:
The memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute the agronomic solution method based on the agronomic solution model of any of claims 1 to 7 according to instructions in program code.
10. A computer readable storage medium for storing program code for performing the method of generating an agricultural solution based on an agricultural solution model of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311786177.4A CN117910228A (en) | 2023-12-22 | 2023-12-22 | Method and related device for generating agronomic scheme based on agronomic scheme model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311786177.4A CN117910228A (en) | 2023-12-22 | 2023-12-22 | Method and related device for generating agronomic scheme based on agronomic scheme model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117910228A true CN117910228A (en) | 2024-04-19 |
Family
ID=90688177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311786177.4A Pending CN117910228A (en) | 2023-12-22 | 2023-12-22 | Method and related device for generating agronomic scheme based on agronomic scheme model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117910228A (en) |
-
2023
- 2023-12-22 CN CN202311786177.4A patent/CN117910228A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110209839A (en) | Agricultural knowledge map construction device, method and computer readable storage medium | |
| CN113849655B (en) | Patent text multi-label classification method | |
| CN115618021A (en) | Method and device for recommending suitable planting area of crop variety | |
| Ranjani et al. | Crop yield prediction using machine learning algorithm | |
| WO2016121432A1 (en) | Skill transfer facilitating system, method for facilitating skill transfer, and computer-readable recording medium | |
| WO2022262586A1 (en) | Method for plant identification, computer system and computer-readable storage medium | |
| Jie | RETRACTED ARTICLE: Precision and intelligent agricultural decision support system based on big data analysis | |
| CN117173400B (en) | Low-carbon treatment scheme recommendation method and system for litchi insect pest | |
| Deepa et al. | An effective automated ontology construction based on the agriculture domain | |
| Vargas-Canales et al. | Trends in science, technology, and innovation in the agri-food sector | |
| CN113220827A (en) | Construction method and device of agricultural corpus | |
| Deepthi et al. | Application of expert systems for agricultural crop disease diagnoses—A review | |
| CN114860917B (en) | Agricultural knowledge question-answering method, device, electronic equipment and storage medium | |
| CN117193772A (en) | Deep learning code-free application layout optimization method and system based on user feedback | |
| Usip et al. | A machine learning-based mobile Chatbot for crop farmers | |
| CN117910228A (en) | Method and related device for generating agronomic scheme based on agronomic scheme model | |
| CN113434644B (en) | Agricultural technology knowledge service method and system | |
| CN113743790B (en) | Method and system for improving rice quality of saline-alkali soil and storage medium | |
| Parmar et al. | Crop Yield Prediction based on Feature Selection and Machine Learners: A Review | |
| US11810645B1 (en) | System and method of making predictions of mature cannabis plants from seedling information | |
| James | A Machine Learning-Based Mobile Chatbot for Crop Farmers | |
| Jindal et al. | Analysis and Application of Regularized Neural Networks in Smart Agriculture | |
| CN116306794B (en) | Crop water demand prediction method and device, electronic equipment and storage medium | |
| CN118014761A (en) | Intelligent agricultural greenhouse management method, system and storage medium based on AI | |
| CN115660236B (en) | Crop weather period prediction method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |