CN117541084B - Method and system for predicting yield of quinoa in grouting period - Google Patents
Method and system for predicting yield of quinoa in grouting period Download PDFInfo
- Publication number
- CN117541084B CN117541084B CN202410032042.7A CN202410032042A CN117541084B CN 117541084 B CN117541084 B CN 117541084B CN 202410032042 A CN202410032042 A CN 202410032042A CN 117541084 B CN117541084 B CN 117541084B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- condition
- yield prediction
- preset
- yield
- 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.)
- Active
Links
- 240000006162 Chenopodium quinoa Species 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 17
- 230000000007 visual effect Effects 0.000 claims abstract description 14
- 230000004720 fertilization Effects 0.000 claims description 15
- 238000012800 visualization Methods 0.000 claims description 8
- 241000607479 Yersinia pestis Species 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 241000196324 Embryophyta Species 0.000 claims 2
- 241000238631 Hexapoda Species 0.000 claims 2
- 238000003306 harvesting Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000003337 fertilizer Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Quality & Reliability (AREA)
- Marine Sciences & Fisheries (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for predicting the yield of quinoa in a grouting period, wherein the method comprises the following steps: when the planted quinoa enters a grouting period, obtaining a yield prediction basis of the planted quinoa; updating a preset yield prediction knowledge base; determining a yield prediction result based on the yield prediction basis and a yield prediction knowledge base; and visually outputting the yield prediction result based on a preset first visual template. According to the method and the system for predicting the output of the quinoa in the grouting period, the output prediction knowledge base is introduced, the output prediction of the quinoa in the grouting period is performed based on the output prediction basis and the output prediction knowledge base, the output prediction result is visually output, the prediction is not required by management personnel for quinoa planting, the labor cost is reduced, and the prediction efficiency is improved.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to a method and a system for predicting the yield of quinoa in a grouting period.
Background
The breeding stage of quinoa is divided into: emergence, seedling stage, branching stage, flowering stage, grouting stage, and harvesting stage. When quinoa enters a grouting period, yield prediction is needed, a harvesting and transporting plan is formulated in advance, and harvesting and transporting efficiency of quinoa is improved.
When the output of the quinoa in the grouting period is predicted, most of management personnel for quinoa planting are used, but the quinoa is planted in a large area, the workload of predicting the output of the quinoa in the grouting period is large, the predicted labor cost is large, and the prediction efficiency is low.
Therefore, an intelligent prediction method is needed to solve the above-mentioned drawbacks.
Disclosure of Invention
The invention aims to provide a method for predicting the yield of quinoa in the grouting period, which is characterized in that a yield prediction knowledge base is introduced, the yield prediction in the quinoa grouting period is performed based on a yield prediction basis and the yield prediction knowledge base, and a yield prediction result is visually output, so that management personnel for quinoa planting are not required to perform prediction, the labor cost is reduced, and the prediction efficiency is improved.
The invention provides a method for predicting the yield of quinoa in a grouting period, which comprises the following steps:
When the planted quinoa enters a grouting period, obtaining a yield prediction basis of the planted quinoa;
updating a preset yield prediction knowledge base;
determining a yield prediction result based on the yield prediction basis and a yield prediction knowledge base;
And visualizing output yield prediction results based on a preset first visualization template.
Preferably, updating the preset yield prediction knowledge base includes:
Extracting planting attribute information from the yield prediction basis;
generating a template based on a preset first condition, and generating a first knowledge application condition according to the planting attribute information;
Acquiring updated knowledge;
Determining updating knowledge meeting the first knowledge application condition and taking the updating knowledge as knowledge to be put in storage;
and storing the knowledge to be put in storage into a yield prediction knowledge base.
Preferably, acquiring the update knowledge includes:
Accessing a preset knowledge generation scene;
searching first knowledge meeting first triggering conditions from a knowledge generation scene;
acquiring knowledge attribute information of first knowledge from a knowledge generation scene;
Generating a template based on a preset second condition, and generating a second triggering condition according to knowledge attribute information;
searching for second knowledge meeting a second trigger condition from the knowledge generation scene;
Determining updated knowledge based on the first knowledge and the second knowledge;
The first trigger condition includes:
the content type of the first knowledge exists in a preset standard content type library;
the third knowledge does not exist in the knowledge generation scene; the similarity between the third knowledge and the second knowledge is larger than or equal to a preset similarity threshold value, and the third knowledge is generated later than the second knowledge in the knowledge generation scene.
Preferably, determining the yield prediction result based on the yield prediction basis and the yield prediction knowledge base includes:
generating a template based on a preset third condition, and generating a second knowledge application condition according to the yield prediction basis;
Attempting to determine fourth knowledge from the yield prediction knowledge base that meets the second knowledge applicable condition;
determining yield predictions based on fourth knowledge when the attempt is successful; otherwise, splitting the second knowledge application condition into a plurality of condition items;
based on the condition combination requirement, combining the condition items to obtain a third knowledge application condition;
attempting to determine fifth knowledge from the yield prediction knowledge base, wherein the fifth knowledge meets the third knowledge application condition;
determining yield predictions based on fifth knowledge when the attempt is successful; otherwise, based on a preset second visual template, visually outputting a yield prediction basis, a yield prediction knowledge base and a preset result input box;
Receiving a yield prediction result input by a user;
wherein the conditional combination requirement includes:
The difference value that the first total number of the condition items in the third knowledge application condition is smaller than the second total number of the condition items is smaller than or equal to a preset difference threshold value;
and the sum of the preset importance degrees corresponding to the condition types of the condition items in the third knowledge application condition is larger than or equal to the preset importance degrees and a threshold value.
Preferably, the method for predicting the yield of quinoa in the grouting period further comprises the following steps:
obtaining a first prediction time of a yield prediction result;
acquiring a historical yield prediction result and corresponding second prediction time of the planted quinoa;
setting a yield prediction result and a historical yield prediction result on a preset time axis based on the first prediction time and the second prediction time to be expressed as a plurality of result items;
determining a target result cluster from the time axis based on the result cluster condition;
acquiring a planting history and a future planting plan generated by planting quinoa in a target time interval; the left and right boundaries of the target time interval are the time points of the head and tail result items in the target result cluster on the time axis;
determining a yield prediction plan based on the planting history and the planting plan;
Based on a preset third visual template, visually outputting a yield prediction plan;
Executing a yield prediction plan;
Wherein the result cluster conditions include:
The difference degree between every two adjacent result items in the target result cluster is larger than or equal to a preset difference degree threshold value;
the time distance between every two adjacent result items in the target result cluster is smaller than or equal to a preset distance threshold.
The invention provides a quinoa grouting period yield prediction system, which comprises:
The output prediction basis acquisition module is used for acquiring output prediction basis of the planted quinoa when the planted quinoa enters a grouting period;
the yield prediction knowledge base updating module is used for updating a preset yield prediction knowledge base;
the yield prediction result determining module is used for determining a yield prediction result based on a yield prediction basis and a yield prediction knowledge base;
And the output module is used for outputting the output prediction result in a visualized manner based on a preset first visualization template.
Preferably, the yield prediction knowledge base updating module updates a preset yield prediction knowledge base, including:
Extracting planting attribute information from the yield prediction basis;
generating a template based on a preset first condition, and generating a first knowledge application condition according to the planting attribute information;
Acquiring updated knowledge;
Determining updating knowledge meeting the first knowledge application condition and taking the updating knowledge as knowledge to be put in storage;
and storing the knowledge to be put in storage into a yield prediction knowledge base.
Preferably, the yield prediction knowledge base updating module acquires the knowledge for updating, including:
Accessing a preset knowledge generation scene;
searching first knowledge meeting first triggering conditions from a knowledge generation scene;
acquiring knowledge attribute information of first knowledge from a knowledge generation scene;
Generating a template based on a preset second condition, and generating a second triggering condition according to knowledge attribute information;
searching for second knowledge meeting a second trigger condition from the knowledge generation scene;
Determining updated knowledge based on the first knowledge and the second knowledge;
The first trigger condition includes:
the content type of the first knowledge exists in a preset standard content type library;
the third knowledge does not exist in the knowledge generation scene; the similarity between the third knowledge and the second knowledge is larger than or equal to a preset similarity threshold value, and the third knowledge is generated later than the second knowledge in the knowledge generation scene.
Preferably, the yield prediction result determining module determines a yield prediction result based on a yield prediction basis and a yield prediction knowledge base, including:
generating a template based on a preset third condition, and generating a second knowledge application condition according to the yield prediction basis;
Attempting to determine fourth knowledge from the yield prediction knowledge base that meets the second knowledge applicable condition;
determining yield predictions based on fourth knowledge when the attempt is successful; otherwise, splitting the second knowledge application condition into a plurality of condition items;
based on the condition combination requirement, combining the condition items to obtain a third knowledge application condition;
attempting to determine fifth knowledge from the yield prediction knowledge base, wherein the fifth knowledge meets the third knowledge application condition;
determining yield predictions based on fifth knowledge when the attempt is successful; otherwise, based on a preset second visual template, visually outputting a yield prediction basis, a yield prediction knowledge base and a preset result input box;
Receiving a yield prediction result input by a user;
wherein the conditional combination requirement includes:
The difference value that the first total number of the condition items in the third knowledge application condition is smaller than the second total number of the condition items is smaller than or equal to a preset difference threshold value;
and the sum of the preset importance degrees corresponding to the condition types of the condition items in the third knowledge application condition is larger than or equal to the preset importance degrees and a threshold value.
Preferably, the quinoa grouting period yield prediction system further comprises:
a yield prediction plan execution module for comprising:
obtaining a first prediction time of a yield prediction result;
acquiring a historical yield prediction result and corresponding second prediction time of the planted quinoa;
setting a yield prediction result and a historical yield prediction result on a preset time axis based on the first prediction time and the second prediction time to be expressed as a plurality of result items;
determining a target result cluster from the time axis based on the result cluster condition;
acquiring a planting history and a future planting plan generated by planting quinoa in a target time interval; the left and right boundaries of the target time interval are the time points of the head and tail result items in the target result cluster on the time axis;
determining a yield prediction plan based on the planting history and the planting plan;
Based on a preset third visual template, visually outputting a yield prediction plan;
Executing a yield prediction plan;
Wherein the result cluster conditions include:
The difference degree between every two adjacent result items in the target result cluster is larger than or equal to a preset difference degree threshold value;
the time distance between every two adjacent result items in the target result cluster is smaller than or equal to a preset distance threshold.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a method for predicting the yield of quinoa during a grouting period according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a quinoa grouting period yield prediction system according to an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The embodiment of the invention provides a method for predicting the yield of quinoa in a grouting period, which is shown in a figure 1 and comprises the following steps:
step S1: when the planted quinoa enters a grouting period, obtaining a yield prediction basis of the planted quinoa;
step S2: updating a preset yield prediction knowledge base;
Step S3: determining a yield prediction result based on the yield prediction basis and a yield prediction knowledge base;
Step S4: and visualizing output yield prediction results based on a preset first visualization template.
In the above scheme, the yield prediction basis includes: quinoa varieties, planting areas, historical fertilization records (fertilization time, fertilization type, fertilization amount and the like) of different planting areas in quinoa planting fields, current growing images of quinoa, historical pest records (pest time, pest type and the like), historical growing environment records (growing temperature, humidity and the like), historical yield records (past quinoa yield) and the like; the yield prediction knowledge base has a large amount of yield prediction knowledge, and the yield prediction knowledge can be the yield prediction experience of the quinoa in the grouting period and can be docked with, acquired and collected by a person with the yield prediction experience of the quinoa in the grouting period in advance; the yield prediction knowledge in the yield prediction knowledge base is utilized to predict the yield of the quinoa in the grouting period according to the yield prediction basis, so that a yield prediction result is obtained; the yield prediction results include: the total yield of quinoa in different planting areas in the quinoa planting field; the first visualization template comprises: representing the output prediction result on a field map of the quinoa planting field, and outputting the field map; after visualizing the output yield prediction results, the user can see.
According to the application, the yield prediction knowledge base is introduced, the yield prediction in the quinoa grouting period is performed based on the yield prediction basis and the yield prediction knowledge base, and the yield prediction result is visually output, so that the prediction is not required by management personnel for quinoa planting, the labor cost is reduced, and the prediction efficiency is improved.
In one embodiment, updating the preset yield prediction knowledge base comprises:
extracting planting attribute information from the yield prediction basis; the planting attribute information includes: quinoa variety, planting area, historical fertilization type and the like;
Generating a template based on a preset first condition, and generating a first knowledge application condition according to the planting attribute information; the first condition generating template is a template for the system to compare with the first knowledge applicable condition generated according to the planting attribute information, specifically, for example: the planting attribute information is quinoa variety A, and the first knowledge application condition is that the knowledge is applicable to quinoa with quinoa variety A;
acquiring updated knowledge; updating knowledge to obtain a large amount of quinoa grouting period yield prediction experience;
determining updating knowledge meeting the first knowledge application condition and taking the updating knowledge as knowledge to be put in storage; when the updated knowledge accords with the first knowledge application condition, the updated knowledge is suitable for planting quinoa, and is used as the knowledge to be put in storage, and the updated knowledge is put in storage;
and storing the knowledge to be put in storage into a yield prediction knowledge base. And the first knowledge application condition is introduced, so that the knowledge base suitable for the current quinoa planting is updated in a targeted manner, and the applicability of the system is improved.
In one embodiment, obtaining updated knowledge includes:
Accessing a preset knowledge generation scene;
searching first knowledge meeting first triggering conditions from a knowledge generation scene;
acquiring knowledge attribute information of first knowledge from a knowledge generation scene;
Generating a template based on a preset second condition, and generating a second triggering condition according to knowledge attribute information;
searching for second knowledge meeting a second trigger condition from the knowledge generation scene;
Determining updated knowledge based on the first knowledge and the second knowledge;
The first trigger condition includes:
Condition 1: the content type of the first knowledge exists in a preset standard content type library;
Condition 2: the third knowledge does not exist in the knowledge generation scene; the similarity between the third knowledge and the second knowledge is larger than or equal to a preset similarity threshold value, and the third knowledge is generated later than the second knowledge in the knowledge generation scene.
In the above scheme, the knowledge generation scene includes: quinoa planting communication forum and the like; there are a plurality of standard content types in the standard content type library, the standard content types include: quinoa yield data and the like, so that a condition 1 is set, and the first knowledge screened out is quinoa yield data of a planting area shared by forum users in a quinoa planting communication forum; among them, forum users can be quinoa planting specialists, etc.; the similarity threshold may be, for example: 90%; setting the condition 2, wherein the first knowledge screened out can be ensured to be the quinoa yield data of the same planting area which is shared by the forum user for the last time (statistical errors possibly exist when the forum user actually shares the quinoa yield data, and the forum user shares again); the knowledge attribute information includes: a publishing party of the first knowledge, a planting area corresponding to quinoa yield data and the like; the second condition generating template is a template for the system to generate a second trigger condition according to knowledge attribute information, specifically, for example: the knowledge attribute information is a publishing party B of the first knowledge and a planting area C corresponding to the quinoa yield data, and the second triggering condition is that the knowledge is required to be a historical fertilization record, a historical pest and disease damage record, a historical growth environment record, a historical yield record and the like of quinoa planted in the planting area C published by the B; searching for second knowledge meeting a second trigger condition from the knowledge generation scene; thus, integrating the first knowledge and the second knowledge, the method obtains the characteristics of what quinoa variety, the growing environment, the yield of quinoa under the fertilization condition, and the like; generally, when collecting the updated knowledge, the system needs to be in butt joint with quinoa planting specialists, but the quinoa planting specialists can communicate, and the embodiment of the invention can adaptively extract the updated knowledge in the communication scene, so that the applicability of the system is improved.
In one embodiment, determining yield predictions based on yield prediction basis, yield prediction knowledge base, includes:
generating a template based on a preset third condition, and generating a second knowledge application condition according to the yield prediction basis;
Attempting to determine fourth knowledge from the yield prediction knowledge base that meets the second knowledge applicable condition;
determining yield predictions based on fourth knowledge when the attempt is successful; otherwise, splitting the second knowledge application condition into a plurality of condition items;
based on the condition combination requirement, combining the condition items to obtain a third knowledge application condition;
Attempting to determine fifth knowledge from the yield prediction knowledge base, wherein the fifth knowledge meets the third knowledge application condition; the fifth knowledge is required to accord with each condition item in the third knowledge applicable condition;
determining yield predictions based on fifth knowledge when the attempt is successful; otherwise, based on a preset second visual template, visually outputting a yield prediction basis, a yield prediction knowledge base and a preset result input box;
Receiving a yield prediction result input by a user;
wherein the conditional combination requirement includes:
condition C1: the difference value that the first total number of the condition items in the third knowledge application condition is smaller than the second total number of the condition items is smaller than or equal to a preset difference threshold value;
Condition C2: and the sum of the preset importance degrees corresponding to the condition types of the condition items in the third knowledge application condition is larger than or equal to the preset importance degrees and a threshold value.
In the above scheme, the third condition generating template is a template for the system to generate the second knowledge applicable condition according to the yield prediction basis, specifically, for example: the yield prediction basis is quinoa variety D, planting area E and historical fertilization record F, and the second knowledge application condition is that knowledge needs to be applied to the prediction of the quinoa grouting period yield of quinoa planted with the variety D, the planting area E and the historical fertilization record F; firstly, attempting to determine fourth knowledge meeting the second knowledge application condition from a yield prediction knowledge base, wherein the fourth knowledge meets the second knowledge application condition, which indicates that the fourth knowledge is completely suitable for the yield prediction of quinoa planted with quinoa in the grouting period, and determining a yield prediction result directly based on the fourth knowledge; otherwise, the fourth knowledge of the output prediction knowledge base which is not fully suitable for the output prediction of the quinoa in the quinoa grouting period for growing quinoa is described, and the applicable condition of the second knowledge is split into a plurality of condition items, specifically, the following conditions are: each condition item is that the variety is D, the planting area is E, and a historical fertilization record F is historically generated; the difference threshold may be, for example: 2; setting the condition C1 can ensure that the fifth knowledge screened out based on the third knowledge application condition accords with the condition item as much as possible; the importance represents the degree to which the yield prediction knowledge needs to satisfy the condition item, and can be set in advance by a technician according to actual requirements, for example: the yield prediction knowledge is necessarily suitable for quinoa varieties, otherwise, the yield prediction is meaningless based on the yield prediction knowledge, the condition type is quinoa model, and the corresponding importance is 10; the importance and threshold may be, for example: 80; the condition C2 is set, so that the fifth knowledge screened out based on the third knowledge application condition can be ensured to be suitable for the output prediction of the current grouting period of the quinoa; the essence of yield prediction is data prediction, and a certain error range exists, so that the matching of condition items is reasonable; attempting to determine fifth knowledge meeting the third knowledge application condition from the yield prediction knowledge base, and determining yield prediction results based on the fifth knowledge when the determination is completed; otherwise, visually outputting a yield prediction basis, a yield prediction knowledge base and a preset result input box for a user to make a decision and input a yield prediction result; the user can be quinoa planting management personnel; the second visualization template includes: and displaying the yield prediction basis, then displaying the yield prediction knowledge base, and finally displaying a result input box. Generally, in practical application, there may be a situation that the yield prediction knowledge base is not available, that is, the fourth knowledge is not searched, and the embodiment of the invention introduces a condition combination requirement for this special situation, reasonably determines the application condition of the third knowledge, screens out the fifth knowledge, and greatly improves the working capacity of the yield prediction knowledge base and the applicability of the system.
In one embodiment, the quinoa grouting period yield prediction method further comprises:
obtaining a first prediction time of a yield prediction result;
acquiring a historical yield prediction result and corresponding second prediction time of the planted quinoa;
Setting a yield prediction result and a historical yield prediction result on a preset time axis based on the first prediction time and the second prediction time to be expressed as a plurality of result items; when the method is used for setting, the yield prediction result and the historical yield prediction result are set at time points corresponding to the first prediction time and the second prediction time on a time axis, so that a result item is obtained;
determining a target result cluster from the time axis based on the result cluster condition;
Acquiring a planting history and a future planting plan generated by planting quinoa in a target time interval; the left and right boundaries of the target time interval are the time points of the head and tail result items in the target result cluster on the time axis; the planting history includes: historical fertilization types, fertilization amounts and the like; future planting plans include: future fertilization plans, etc.;
Determining a yield prediction plan based on the planting history and the planting plan; specifically, for example: the planting history generated by planting quinoa in a target time interval is G fertilizer H, the planting plan is that fertilizer H is applied in the future at time I, and the yield prediction plan is that yield prediction is performed again at time I; the planting history generated in the target time interval may represent the reason why the quinoa yield is affected, and thus, a yield prediction plan may be determined based on the planting history and the planting plan;
Based on a preset third visual template, visually outputting a yield prediction plan; the third visualization template includes: sequentially displaying yield prediction plans according to time sequences;
Executing a yield prediction plan;
Wherein the result cluster conditions include:
The difference degree between every two adjacent result items in the target result cluster is larger than or equal to a preset difference degree threshold value; the variance threshold may be, for example: 15%; when the result cluster condition is met, the result difference of the yield prediction results is larger, and the influence on the yield possibly occurs;
The time distance between every two adjacent result items in the target result cluster is smaller than or equal to a preset distance threshold. The distance threshold may be, for example: 3 days (distance unit on time axis is time unit); when the result cluster condition is met, the yield prediction interval time can be ensured not to be longer;
The embodiment of the invention reasonably determines and executes the yield prediction plan, can effectively help quinoa grower find out factors influencing quinoa yield and the like, and improves the prediction meaning.
The embodiment of the invention provides a quinoa grouting period yield prediction system, as shown in fig. 2, comprising:
The output prediction basis acquisition module 1 is used for acquiring output prediction basis of the planted quinoa when the planted quinoa enters a grouting period;
the yield prediction knowledge base updating module 2 is used for updating a preset yield prediction knowledge base;
the yield prediction result determining module 3 is used for determining a yield prediction result based on the yield prediction basis and a yield prediction knowledge base;
And the output module 4 is used for visually outputting the output prediction result based on a preset first visual template.
The yield prediction knowledge base updating module 2 updates a preset yield prediction knowledge base, including:
Extracting planting attribute information from the yield prediction basis;
generating a template based on a preset first condition, and generating a first knowledge application condition according to the planting attribute information;
Acquiring updated knowledge;
Determining updating knowledge meeting the first knowledge application condition and taking the updating knowledge as knowledge to be put in storage;
and storing the knowledge to be put in storage into a yield prediction knowledge base.
The yield prediction knowledge base updating module 2 acquires knowledge for updating, including:
Accessing a preset knowledge generation scene;
searching first knowledge meeting first triggering conditions from a knowledge generation scene;
acquiring knowledge attribute information of first knowledge from a knowledge generation scene;
Generating a template based on a preset second condition, and generating a second triggering condition according to knowledge attribute information;
searching for second knowledge meeting a second trigger condition from the knowledge generation scene;
Determining updated knowledge based on the first knowledge and the second knowledge;
The first trigger condition includes:
the content type of the first knowledge exists in a preset standard content type library;
the third knowledge does not exist in the knowledge generation scene; the similarity between the third knowledge and the second knowledge is larger than or equal to a preset similarity threshold value, and the third knowledge is generated later than the second knowledge in the knowledge generation scene.
The yield prediction result determining module 3 determines a yield prediction result based on the yield prediction basis and the yield prediction knowledge base, including:
generating a template based on a preset third condition, and generating a second knowledge application condition according to the yield prediction basis;
Attempting to determine fourth knowledge from the yield prediction knowledge base that meets the second knowledge applicable condition;
determining yield predictions based on fourth knowledge when the attempt is successful; otherwise, splitting the second knowledge application condition into a plurality of condition items;
based on the condition combination requirement, combining the condition items to obtain a third knowledge application condition;
attempting to determine fifth knowledge from the yield prediction knowledge base, wherein the fifth knowledge meets the third knowledge application condition;
determining yield predictions based on fifth knowledge when the attempt is successful; otherwise, based on a preset second visual template, visually outputting a yield prediction basis, a yield prediction knowledge base and a preset result input box;
Receiving a yield prediction result input by a user;
wherein the conditional combination requirement includes:
The difference value that the first total number of the condition items in the third knowledge application condition is smaller than the second total number of the condition items is smaller than or equal to a preset difference threshold value;
and the sum of the preset importance degrees corresponding to the condition types of the condition items in the third knowledge application condition is larger than or equal to the preset importance degrees and a threshold value.
Quinoa grouting period yield prediction system further comprises:
a yield prediction plan execution module for comprising:
obtaining a first prediction time of a yield prediction result;
acquiring a historical yield prediction result and corresponding second prediction time of the planted quinoa;
setting a yield prediction result and a historical yield prediction result on a preset time axis based on the first prediction time and the second prediction time to be expressed as a plurality of result items;
determining a target result cluster from the time axis based on the result cluster condition;
acquiring a planting history and a future planting plan generated by planting quinoa in a target time interval; the left and right boundaries of the target time interval are the time points of the head and tail result items in the target result cluster on the time axis;
determining a yield prediction plan based on the planting history and the planting plan;
Based on a preset third visual template, visually outputting a yield prediction plan;
Executing a yield prediction plan;
Wherein the result cluster conditions include:
The difference degree between every two adjacent result items in the target result cluster is larger than or equal to a preset difference degree threshold value;
the time distance between every two adjacent result items in the target result cluster is smaller than or equal to a preset distance threshold.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (2)
1. A method for predicting the yield of quinoa in a grouting period is characterized by comprising the following steps:
When the planted quinoa enters a grouting period, obtaining a yield prediction basis of the planted quinoa;
updating a preset yield prediction knowledge base;
Determining a yield prediction result based on the yield prediction basis and a yield prediction knowledge base;
Based on a preset first visual template, visually outputting the yield prediction result;
The updating of the preset yield prediction knowledge base comprises the following steps:
extracting planting attribute information from the yield prediction basis;
Generating a template based on a preset first condition, and generating a first knowledge application condition according to the planting attribute information;
Acquiring updated knowledge;
determining the updated knowledge meeting the first knowledge application conditions and taking the updated knowledge as the knowledge to be put in storage;
Storing the knowledge to be put in storage into the yield prediction knowledge base;
the acquiring update knowledge includes:
accessing a preset knowledge generation scene; the knowledge generation scenario includes: quinoa planting communication forum;
Searching first knowledge meeting a first triggering condition from the knowledge generation scene; the first knowledge includes: quinoa planting communicates quinoa yield data of a planting area shared by forum users in a forum;
Acquiring knowledge attribute information of the first knowledge from the knowledge generation scene; the knowledge attribute information includes: a publishing party of the first knowledge and a planting area corresponding to the quinoa yield data;
Generating a template based on a preset second condition, and generating a second triggering condition according to the knowledge attribute information; the second trigger condition includes: historical fertilization records, historical plant diseases and insect pests records, historical growth environment records and historical yield records of the planted quinoa in a planting area corresponding to quinoa yield data issued by a publisher of first knowledge are needed;
searching for second knowledge meeting the second trigger condition from the knowledge generation scene;
determining the update knowledge based on the first knowledge and the second knowledge;
the first trigger condition includes:
the content type of the first knowledge exists in a preset standard content type library;
the knowledge generation scene does not have third knowledge; the similarity between the third knowledge and the first knowledge is greater than or equal to a preset similarity threshold value, and the third knowledge is generated later than the first knowledge in the knowledge generation scene;
the determining a yield prediction result based on the yield prediction basis and the yield prediction knowledge base comprises the following steps:
generating a template based on a preset third condition, and generating a second knowledge application condition according to the yield prediction basis;
attempting to determine fourth knowledge from the yield prediction knowledge base that meets the second knowledge applicable condition;
determining the yield prediction result based on the fourth knowledge when the attempt is successful; otherwise, splitting the second knowledge application condition into a plurality of condition items;
combining the condition items based on the condition combination requirement to obtain a third knowledge application condition;
Attempting to determine fifth knowledge from the yield prediction knowledge base that meets the third knowledge applicable condition; the fifth knowledge is required to accord with each condition item in the third knowledge applicable condition;
Determining the yield prediction result based on the fifth knowledge when the attempt is successful; otherwise, based on a preset second visualization template, visually outputting the yield prediction basis, the yield prediction knowledge base and a preset result input box;
Receiving the output prediction result input by a user;
Wherein the condition combination requirement includes:
The first total number of the condition items in the third knowledge application condition is smaller than the second total number of the condition items in the second knowledge application condition, and the difference value between the first total number and the second total number is smaller than or equal to a preset difference value threshold; the difference threshold includes: 2;
The sum of the preset importance degrees corresponding to the condition types of the condition items in the third knowledge application condition is larger than or equal to a preset importance degree and a threshold value;
Further comprises:
Acquiring a first prediction time of the yield prediction result;
acquiring a historical yield prediction result and corresponding second prediction time of the planted quinoa;
Setting the yield prediction result and the historical yield prediction result on a preset time axis based on the first prediction time and the second prediction time to be expressed as a plurality of result items;
Determining a target result cluster from the timeline based on a result cluster condition;
Acquiring a planting history and a future planting plan generated by planting quinoa in a target time interval; the left and right boundaries of the target time interval are the time points of the end-to-end result items in the target result cluster on the time axis;
determining a yield prediction plan based on the planting history and the planting plan;
based on a preset third visual template, visually outputting the yield prediction plan;
Executing the yield prediction plan;
wherein the result cluster conditions include:
the difference degree between every two adjacent result items in the target result cluster is larger than or equal to a preset difference degree threshold value;
and the time distance between every two adjacent result items in the target result cluster is smaller than or equal to a preset distance threshold.
2. A quinoa grouting period yield prediction system, comprising:
The output prediction basis acquisition module is used for acquiring output prediction basis of the planted quinoa when the planted quinoa enters a grouting period;
the yield prediction knowledge base updating module is used for updating a preset yield prediction knowledge base;
The yield prediction result determining module is used for determining a yield prediction result based on the yield prediction basis and a yield prediction knowledge base;
The output prediction result output module is used for visually outputting the output prediction result based on a preset first visual template;
The yield prediction knowledge base updating module updates a preset yield prediction knowledge base, and comprises the following steps:
extracting planting attribute information from the yield prediction basis;
Generating a template based on a preset first condition, and generating a first knowledge application condition according to the planting attribute information;
Acquiring updated knowledge;
determining the updated knowledge meeting the first knowledge application conditions and taking the updated knowledge as the knowledge to be put in storage;
Storing the knowledge to be put in storage into the yield prediction knowledge base;
The yield prediction knowledge base updating module acquires knowledge for updating, and the method comprises the following steps:
accessing a preset knowledge generation scene; the knowledge generation scenario includes: quinoa planting communication forum;
Searching first knowledge meeting a first triggering condition from the knowledge generation scene; the first knowledge includes: quinoa planting communicates quinoa yield data of a planting area shared by forum users in a forum;
Acquiring knowledge attribute information of the first knowledge from the knowledge generation scene; the knowledge attribute information includes: a publishing party of the first knowledge and a planting area corresponding to the quinoa yield data;
Generating a template based on a preset second condition, and generating a second triggering condition according to the knowledge attribute information; the second trigger condition includes: historical fertilization records, historical plant diseases and insect pests records, historical growth environment records and historical yield records of the planted quinoa in a planting area corresponding to quinoa yield data issued by a publisher of first knowledge are needed;
searching for second knowledge meeting the second trigger condition from the knowledge generation scene;
determining the update knowledge based on the first knowledge and the second knowledge;
the first trigger condition includes:
the content type of the first knowledge exists in a preset standard content type library;
the knowledge generation scene does not have third knowledge; the similarity between the third knowledge and the first knowledge is greater than or equal to a preset similarity threshold value, and the third knowledge is generated later than the first knowledge in the knowledge generation scene;
the yield prediction result determining module determines a yield prediction result based on the yield prediction basis and a yield prediction knowledge base, and comprises the following steps:
generating a template based on a preset third condition, and generating a second knowledge application condition according to the yield prediction basis;
attempting to determine fourth knowledge from the yield prediction knowledge base that meets the second knowledge applicable condition;
determining the yield prediction result based on the fourth knowledge when the attempt is successful; otherwise, splitting the second knowledge application condition into a plurality of condition items;
combining the condition items based on the condition combination requirement to obtain a third knowledge application condition;
Attempting to determine fifth knowledge from the yield prediction knowledge base that meets the third knowledge applicable condition; the fifth knowledge is required to accord with each condition item in the third knowledge applicable condition;
Determining the yield prediction result based on the fifth knowledge when the attempt is successful; otherwise, based on a preset second visualization template, visually outputting the yield prediction basis, the yield prediction knowledge base and a preset result input box;
Receiving the output prediction result input by a user;
Wherein the condition combination requirement includes:
The first total number of the condition items in the third knowledge application condition is smaller than the second total number of the condition items in the second knowledge application condition, and the difference value between the first total number and the second total number is smaller than or equal to a preset difference value threshold; the difference threshold includes: 2;
The sum of the preset importance degrees corresponding to the condition types of the condition items in the third knowledge application condition is larger than or equal to a preset importance degree and a threshold value;
Further comprises:
a yield prediction plan execution module for comprising:
Acquiring a first prediction time of the yield prediction result;
acquiring a historical yield prediction result and corresponding second prediction time of the planted quinoa;
Setting the yield prediction result and the historical yield prediction result on a preset time axis based on the first prediction time and the second prediction time to be expressed as a plurality of result items;
Determining a target result cluster from the timeline based on a result cluster condition;
Acquiring a planting history and a future planting plan generated by planting quinoa in a target time interval; the left and right boundaries of the target time interval are the time points of the end-to-end result items in the target result cluster on the time axis;
determining a yield prediction plan based on the planting history and the planting plan;
based on a preset third visual template, visually outputting the yield prediction plan;
Executing the yield prediction plan;
wherein the result cluster conditions include:
the difference degree between every two adjacent result items in the target result cluster is larger than or equal to a preset difference degree threshold value;
and the time distance between every two adjacent result items in the target result cluster is smaller than or equal to a preset distance threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410032042.7A CN117541084B (en) | 2024-01-10 | 2024-01-10 | Method and system for predicting yield of quinoa in grouting period |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410032042.7A CN117541084B (en) | 2024-01-10 | 2024-01-10 | Method and system for predicting yield of quinoa in grouting period |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117541084A CN117541084A (en) | 2024-02-09 |
| CN117541084B true CN117541084B (en) | 2024-05-10 |
Family
ID=89790379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410032042.7A Active CN117541084B (en) | 2024-01-10 | 2024-01-10 | Method and system for predicting yield of quinoa in grouting period |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541084B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255999A (en) * | 2021-05-25 | 2021-08-13 | 中国农业科学院农业信息研究所 | Multi-model-based crop yield assessment method, device, equipment and medium |
| CN113408642A (en) * | 2021-06-30 | 2021-09-17 | 广州江南科友科技股份有限公司 | Fault triggering matching method, system and medium based on knowledge base expert rules |
| CN114742288A (en) * | 2022-03-29 | 2022-07-12 | 河北建筑工程学院 | Intelligent prediction method for chenopodium quinoa ear-sprouting yield |
| CN117194602A (en) * | 2023-09-06 | 2023-12-08 | 书音(上海)文化科技有限公司 | Local knowledge base updating method and system based on large language model and BERT model |
-
2024
- 2024-01-10 CN CN202410032042.7A patent/CN117541084B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255999A (en) * | 2021-05-25 | 2021-08-13 | 中国农业科学院农业信息研究所 | Multi-model-based crop yield assessment method, device, equipment and medium |
| CN113408642A (en) * | 2021-06-30 | 2021-09-17 | 广州江南科友科技股份有限公司 | Fault triggering matching method, system and medium based on knowledge base expert rules |
| CN114742288A (en) * | 2022-03-29 | 2022-07-12 | 河北建筑工程学院 | Intelligent prediction method for chenopodium quinoa ear-sprouting yield |
| CN117194602A (en) * | 2023-09-06 | 2023-12-08 | 书音(上海)文化科技有限公司 | Local knowledge base updating method and system based on large language model and BERT model |
Non-Patent Citations (4)
| Title |
|---|
| 杨长保,修远,马生忠,陈德利,范春光.面向对象技术在玉米产量预测专家系统开发中的应用研究.计算机与农业.2003,(第09期),第13-15页. * |
| 水环境评价决策支持系统知识库系统的设计;崔宝侠;姚晓颖;苏桂华;刘伟;;沈阳工业大学学报;20060228(第01期);第65-68页 * |
| 网络化水稻生产专家系统知识库的构建;任勃, 黄璜, 陈灿;作物研究;20040630(第02期);第75-80页 * |
| 面向对象技术在玉米产量预测专家系统开发中的应用研究;杨长保, 修远, 马生忠, 陈德利, 范春光;计算机与农业;20030926(第09期);第13-15页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117541084A (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583301B (en) | Method and device for predicting optimal external planting conditions in crop growth process | |
| EP3816880A1 (en) | A yield estimation method for arable crops and grasslands, coping with extreme weather conditions and with limited reference data requirements | |
| US20200250593A1 (en) | Yield estimation in the cultivation of crop plants | |
| EP3358518A1 (en) | Farmwork plan support system | |
| CN116012720B (en) | Crop growth condition monitoring method, device and medium based on high-resolution remote sensing image | |
| JP5671877B2 (en) | Farm work support device, farm work support method, and farm work support program | |
| Nevo et al. | An integrated expert system for optimal crop planning | |
| Cheema et al. | Information technology for sustainable agriculture | |
| US20220292429A1 (en) | Method and system for monitoring a cotton crop | |
| KR102381491B1 (en) | Information providing system for crop cultivation | |
| CN117541084B (en) | Method and system for predicting yield of quinoa in grouting period | |
| CN116579521B (en) | Yield prediction time window determining method, device, equipment and readable storage medium | |
| JP2001256289A (en) | Production managing system for agriculture and fisheries | |
| CN116127168B (en) | Crop growth real-time monitoring system and method based on Internet of things | |
| CN113010529A (en) | Crop management method and device based on knowledge graph | |
| Saxena et al. | FARMINGTON-A Machine Learning Approach in Agriculture | |
| Lal | Whole-Farm Simulation of Field Operations: An Object-Oriented Approach | |
| CN116720668B (en) | Big data agricultural management method, system and storage medium | |
| Kholiya et al. | Sustainable Development of Smart Farming and Agriculture Business using Data Mining | |
| Muraru et al. | Development of software for optimizing the fertilization of agricultural crop | |
| CN109191320A (en) | A kind of agricultural production management guidance method and system | |
| CN117933676B (en) | Agricultural planting management system | |
| Fairhurst et al. | A conceptual framework for precision agriculture in oil palm plantations | |
| CN118097659A (en) | Method and system for monitoring growth state of agaricus bisporus | |
| Namba et al. | Optimal pattern Discovery to Reveal the High Yield Inhibition Factor of Soybeans |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |