CN116757707B - Crop fruit growth tracing method and system - Google Patents
Crop fruit growth tracing method and system Download PDFInfo
- Publication number
- CN116757707B CN116757707B CN202310725241.1A CN202310725241A CN116757707B CN 116757707 B CN116757707 B CN 116757707B CN 202310725241 A CN202310725241 A CN 202310725241A CN 116757707 B CN116757707 B CN 116757707B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- feature
- generate
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 133
- 230000012010 growth Effects 0.000 title claims abstract description 131
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 45
- 239000013598 vector Substances 0.000 claims abstract description 131
- 239000011159 matrix material Substances 0.000 claims abstract description 122
- 238000004458 analytical method Methods 0.000 claims abstract description 88
- 238000012545 processing Methods 0.000 claims abstract description 69
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims description 91
- 239000002689 soil Substances 0.000 claims description 49
- 230000007613 environmental effect Effects 0.000 claims description 37
- 238000012216 screening Methods 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 18
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004856 soil analysis Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 241000209094 Oryza Species 0.000 description 28
- 235000007164 Oryza sativa Nutrition 0.000 description 28
- 235000009566 rice Nutrition 0.000 description 28
- 230000004720 fertilization Effects 0.000 description 25
- 238000007726 management method Methods 0.000 description 22
- 238000003973 irrigation Methods 0.000 description 17
- 230000002262 irrigation Effects 0.000 description 17
- 239000000284 extract Substances 0.000 description 14
- 239000003337 fertilizer Substances 0.000 description 14
- 238000012544 monitoring process Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 238000005286 illumination Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000003306 harvesting Methods 0.000 description 7
- 235000013305 food Nutrition 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 240000008042 Zea mays Species 0.000 description 4
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 4
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 4
- 238000012271 agricultural production Methods 0.000 description 4
- 235000005822 corn Nutrition 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013138 pruning Methods 0.000 description 4
- 238000007637 random forest analysis Methods 0.000 description 4
- 241000209140 Triticum Species 0.000 description 3
- 235000021307 Triticum Nutrition 0.000 description 3
- 241000607479 Yersinia pestis Species 0.000 description 3
- 230000003698 anagen phase Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000003621 irrigation water Substances 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 239000000575 pesticide Substances 0.000 description 3
- 238000005507 spraying Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000013075 data extraction Methods 0.000 description 2
- 238000009313 farming Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 238000010899 nucleation Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 108091026890 Coding region Proteins 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000000540 analysis of variance Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method 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
- 238000005457 optimization Methods 0.000 description 1
- 239000003895 organic fertilizer Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000009331 sowing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000002277 temperature effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000009333 weeding Methods 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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Agronomy & Crop Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a method and a system for tracing the growth of crop fruits, which are used for improving the accuracy of tracing the growth of the crop fruits. Comprising the following steps: performing feature vector mapping on the environment parameter information to generate a first feature vector set, and performing feature matrix extraction on the manual operation information to generate a first feature matrix set; performing time stamp analysis on each first feature vector and each first feature matrix to generate a first time stamp set and a second time stamp set; performing time sequence matching to generate a target time sequence; performing data pairing on the first feature vector set and the first feature matrix set to generate target feature data, and performing identifier generation to obtain a target identifier; performing data encoding processing on the target identifier to generate target encoded data; and generating a target tracing report by tracing information of the target identifier through the target coding data.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method and a system for tracing the growth of crop fruits.
Background
The current global face diversified, safe and efficient agricultural production demands, and meanwhile, the attention of consumers to food safety problems is continuously improved, so that the crop growth process is required to be monitored, managed and traced in an omnibearing, efficient and reliable manner. Aiming at the demand, the intelligent monitoring, management and tracing of the crop growth process can be realized by utilizing the technology of the Internet of things, collecting and analyzing the crop growth environment parameters and the manual operation information and combining the data processing and encoding technology, so that the efficiency and the quality of agricultural production are improved, and the safety and the quality of foods are ensured.
However, there are several disadvantages to the prior art. The method and the precision for collecting and processing the environmental parameters and the manual operation information in the crop growth process are limited, and particularly, great challenges are presented in the aspects of mass data processing, feature extraction, model design and the like. Secondly, in terms of identifier generation and data coding processing, more excellent algorithms and technologies are lacking, so that the traceability and whole-course management of the crop growth process can be better realized. Thirdly, when the whole-course tracking and tracing of the crop growth process are realized, the problems and challenges in the aspects of data privacy protection, information security, standardization and the like are still faced.
Disclosure of Invention
The invention provides a method and a system for tracing the growth of crop fruits, which are used for improving the accuracy of tracing the growth of the crop fruits.
The first aspect of the invention provides a crop fruit growth tracing method, which comprises the following steps:
Collecting environmental parameter information of crops in the growth process, and collecting manual operation information of the crops in the growth process;
Performing feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, performing feature matrix extraction on the manual operation information to generate a first feature matrix set;
Performing time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set;
performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence;
Performing data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data;
Generating an identifier of the crop through the target characteristic data to obtain a target identifier;
performing data encoding processing on the target identifier to generate target encoded data;
and generating tracing information of the target identifier through the target coding data to generate a target tracing report.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the collecting environmental parameter information of the crops during the growth process, and at the same time, collecting manual operation information of the crops during the growth process, includes:
Acquiring temperature data of the crops in the growing process through a temperature sensor, and acquiring humidity data of the crops in the growing process through a humidity sensor;
collecting a soil picture set of the crops in the generation process through an image collecting device, inputting the soil picture set into a preset soil analysis model for soil parameter analysis, and generating soil parameter data;
taking the temperature data, the humidity data and the soil parameter data as the environment parameter information;
and collecting manual operation information of the crops in the production process.
With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect of the present invention, the collecting manual operation information of the crop in a generating process includes:
Acquiring a manual operation data table, and performing manual operation type traversal on the manual operation data table to generate a manual operation type set;
Performing operation data threshold analysis based on the manual operation type set to generate threshold data corresponding to each manual operation type;
extracting data from the manual operation data table to generate manual operation data;
Performing invalid data screening on the manual operation data based on threshold data corresponding to each manual operation type, and determining invalid data;
and performing invalid data elimination processing on the manual operation data to generate the manual operation information.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, performing timestamp analysis on each first feature vector in the first feature vector set to generate a first timestamp set, and simultaneously performing timestamp analysis on each first feature matrix in the first feature matrix set to generate a second timestamp set, where the generating includes:
classifying the environment types of the first feature vector set, and determining a corresponding environment type set;
performing record time matching on the first feature vector set through the environment type set, and determining a corresponding record time set;
Generating a first timestamp set through the record time set;
manually operating time extraction is carried out on the first feature matrix set, and time data corresponding to each first feature matrix is determined;
And carrying out time stamp analysis based on the time data corresponding to each first feature matrix to obtain time stamp data corresponding to each first feature matrix and generating a second time stamp set.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the performing time sequence matching on the first timestamp set and the second timestamp set to generate a corresponding target time sequence includes:
performing time sequence similarity analysis on the first time stamp set and the second time stamp set to generate a corresponding sequence similarity data set;
Performing threshold analysis on the sequence similarity data set to generate a plurality of similarity data meeting threshold requirements;
And performing time sequence matching on the first time stamp set and the second time stamp set through the plurality of similarity data to generate a corresponding target time sequence.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the performing, based on the target time sequence, a data pairing process on the first feature vector set and the first feature matrix set, to generate target feature data includes:
Performing first pairing relation analysis on the first feature vector set through the target time sequence to generate a first time pairing relation;
performing second pairing relation analysis on the first feature matrix set through the target time sequence to generate a second time pairing relation;
generating a corresponding data pairing conversion algorithm through the first time pairing relation and the second time pairing relation;
And carrying out data pairing processing on the first feature vector set and the first feature matrix set through the data pairing conversion algorithm to generate target feature data.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the generating an identifier for the crop by using the target feature data, to obtain a target identifier, includes:
calculating the feature importance degree of the target feature data to generate a corresponding feature importance degree set;
performing feature screening processing on the target feature data through the feature importance set to generate corresponding screened feature data;
and generating an identifier of the crop based on the screening characteristic data to obtain a target identifier.
The second aspect of the invention provides a crop fruit growth traceability system, comprising:
The acquisition module is used for acquiring environmental parameter information of crops in the growth process and acquiring manual operation information of the crops in the growth process;
the mapping module is used for carrying out feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, carrying out feature matrix extraction on the manual operation information to generate a first feature matrix set;
The analysis module is used for carrying out time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and simultaneously carrying out time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set;
The matching module is used for performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence;
The processing module is used for carrying out data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data;
The generation module is used for generating identifiers of the crops through the target characteristic data to obtain target identifiers;
the encoding module is used for carrying out data encoding processing on the target identifier to generate target encoded data;
and the tracing module is used for generating tracing information of the target identifier through the target coding data and generating a target tracing report.
A third aspect of the present invention provides a crop fruit growth traceability device comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the crop fruit growth traceability device to perform the crop fruit growth traceability method described above.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the above-described method of tracing crop fruit growth.
In the technical scheme provided by the invention, environmental parameter information of crops in the growth process is collected, and meanwhile, manual operation information of the crops in the growth process is collected; performing feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, performing feature matrix extraction on the manual operation information to generate a first feature matrix set; performing time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set; performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence; performing data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data; generating an identifier of the crop through the target characteristic data to obtain a target identifier; performing data encoding processing on the target identifier to generate target encoded data; and generating tracing information of the target identifier through the target coding data to generate a target tracing report. According to the intelligent crop growth monitoring system, intelligent monitoring and analysis are carried out on the crop growth process by adopting the Internet of things, big data and artificial intelligence technology, so that the problems in production are found and solved in time, and the production efficiency and quality are improved. By monitoring and analyzing the environmental parameter information, the crop growth environment such as temperature, humidity, soil pH value and the like can be better understood and controlled, so that the crop growth condition is optimized, and the crop yield and quality are improved. The progress condition of each production stage can be known by collecting and analyzing manual operation information, and the growth management strategy can be timely adjusted; meanwhile, the performance of operators can be evaluated and managed, and the scientificity and efficiency of management are improved. Through time sequence matching, data pairing processing and feature extraction, more comprehensive, accurate and reliable data information can be generated, references are provided for subsequent data analysis and decision making, and the scientificity and the accuracy of decision making are improved.
By carrying out identifier generation and data coding processing on crops, the whole-course tracking and management of the growth process of the crops can be realized, so that safer and more reliable products are provided for consumers, and the food safety and quality standard are promoted and improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for tracing the fruit growth of crops according to the present invention;
FIG. 2 is a flow chart of the method for collecting information of manual operation of crops during the process of generation according to the embodiment of the invention;
FIG. 3 is a flowchart of performing a timestamp analysis on each first feature vector in the first feature vector set according to an embodiment of the present invention;
FIG. 4 is a flowchart of performing time series matching on a first set of time stamps and a second set of time stamps according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of a system for tracing fruit growth of crops in accordance with an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a tracing apparatus for fruit growth of crops in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a system for tracing the growth of crop fruits, which are used for improving the accuracy of tracing the growth of the crop fruits. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, 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 described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation 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 or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and an embodiment of a method for tracing fruit growth of crops in an embodiment of the present invention includes:
s101, collecting environmental parameter information of crops in a growing process, and meanwhile, collecting manual operation information of the crops in the growing process;
It can be understood that the execution subject of the present invention may be a crop fruit growth traceability system, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, in order to collect environmental parameter information and manual operation information of crops during the growth process, a server uses a temperature sensor and a humidity sensor to acquire necessary data. Through temperature sensor, the server can real-time measurement crops's temperature data, knows its temperature change condition at different time points. The humidity sensor can help the server acquire humidity data around the crops so as to know the influence of the humidity on the crops. In addition, through image acquisition device, the soil picture collection of crops in the growth process is shot to the server. These pictures may include different areas and layers of soil. The server inputs the soil pictures into a preset soil analysis model for analysis. The model can extract soil parameter data such as soil texture, water content and the like through image processing and analysis technology. These soil parameter data are one of the important indicators of the crop growth environment. The temperature sensor is used for collecting temperature data, the humidity sensor is used for collecting humidity data, the image collecting device is used for collecting a soil picture set and analyzing soil parameters, and the server is used for obtaining environmental parameter information of crops in the growing process. Such information will help the server to understand the growing environment in which the crop is located and provide a basis for subsequent data processing and analysis. In addition, the server also needs to collect manual operation information of crops in the growing process. For example, the server records manual operations of farmers' fertilization times, irrigation frequency, pesticide use, etc. Such information may be obtained through manual recording or use of sensors and automation equipment. By collecting these manual operation information, the server knows the management and intervention of farmers on the crops and the influence of these operations on the growth of the crops. In summary, the server collects environmental parameter information and manual operation information of crops in the growth process through the temperature sensor, the humidity sensor and the image collecting device. These data are of great significance for the traceability and analysis of crop growth and can be used to generate targeted traceability reports and to make relevant decisions and optimizations. And aiming at the manual operation information of the crops in the generation process, the server acquires a data table containing the manual operation information of the crops in the generation process. This data table may contain information about date, operation type, operator, operation amount, etc. The server records these data either by manual recording or by automated equipment. The server traverses the manual operation types of the manual operation data table, identifies different manual operation types and generates a manual operation type set. For example, the server recognizes different types of manual operations such as fertilization, watering, spraying pesticides, etc. Based on the set of manual operation types, the server performs operation data threshold analysis, generating corresponding threshold data for each manual operation type. These threshold data may be derived based on agricultural expert advice, crop growth requirements or historical data, and the like. For example, for a fertilizer application operation, the server sets a suitable fertilizer application amount range as the threshold. The server performs data extraction on the manual operation data table to extract data related to operation types in the manual operation type set. This may involve screening out certain types of manual records for subsequent analysis and processing. After the operation data is acquired, the server performs invalid data screening on the operation data based on the threshold data of each manual operation type, and determines invalid data. The server determines whether each data point is within a reasonable range by comparing with the threshold data. If the data point is outside the threshold range, the server marks it as invalid data. For example, if the amount of fertilizer applied exceeds a preset threshold range, then this data point may be an outlier. And the server performs invalid data elimination processing on the manual operation data to generate cleaned manual operation information. By eliminating records determined to be invalid data, the server obtains a reliable manual information data set which can be used for subsequent analysis, tracing and decision-making.
S102, performing feature vector mapping on environment parameter information to generate a first feature vector set, and simultaneously, performing feature matrix extraction on manual operation information to generate a first feature matrix set;
Specifically, for environmental parameter information, the server collects various parameter data related to the crop growth process, such as temperature, humidity, illumination intensity, soil pH, etc. These parameter data may be collected in real time or recorded in a time series. The server performs feature vector mapping on these parameters. Feature vector mapping is the process of converting environmental parameter information into numeric feature vectors. For each parameter, the server selects some statistical features to represent, for example, average, maximum, minimum, standard deviation, etc. These statistical features may reflect the trend and extent of fluctuation of the parameter during crop growth. By combining these statistical features, the server obtains a feature vector representing a certain point in time or period of the environmental parameter information. For example, assume that a server collects temperature and humidity data for a crop over a week. The server calculates statistical characteristics of average temperature, average humidity, highest temperature, lowest humidity, etc. in the period of time. The feature values are combined into a feature vector representing the environmental parameter information for the time period. By doing similar calculations for each point in time or time period, the server generates a series of feature vectors, constituting a first set of feature vectors. For manual operation information, the server extracts the feature matrix therein. The manual operation information may include various manual intervention operations during the growth of the crop, such as fertilization, irrigation, spraying, etc. The server organizes the operation information into a data table in which each row represents an operation and each column represents a different attribute of the operation, such as operation type, operation time, operation amount, etc. Aiming at the feature matrix extraction of the manual operation information, the server selects the attribute of each operation as a feature and constructs the feature matrix. Each row represents an operation and each column represents an attribute. The server may obtain a series of feature matrices to form a first set of feature matrices. For example, assume that the server has a manual operation data table of a fertilizer application record, which includes attributes such as operation type (fertilizer application), operation time, and fertilizer application amount. The server takes the fertilizing amount of each row as one attribute of the characteristic matrix and forms a characteristic matrix. Each row represents one fertilization operation, and each column represents a fertilization amount attribute. For other operation types of data, the server may also extract the corresponding feature matrix. Through the steps, the server can map the feature vectors of the environment parameter information to generate a first feature vector set, and meanwhile, the feature matrix extraction is carried out on the manual operation information to generate the first feature matrix set. These feature vectors and feature matrices will provide the basis for subsequent analysis and processing. For example, assume that a server is monitoring the growth of a piece of paddy field. The server is provided with a temperature sensor and a humidity sensor to collect environmental parameter information. During a growing season, the server records temperature and humidity data once an hour. The data are processed to calculate the average temperature and humidity of each day, and finally a series of characteristic vectors are obtained to represent the environmental parameter information of different time periods. Meanwhile, the server also records manual operation information such as fertilization and irrigation. The server collates the operation information into a data table including operation type, operation time and operation amount. For the fertilization operation, the server extracts the operation amount as the attribute of the feature matrix to form a feature matrix. For irrigation operations and other types of operations, the server may also extract the corresponding attributes to form a feature matrix. By such processing, the server obtains a first feature vector set describing the trend of the change of the environmental parameter and a first feature matrix set describing the attribute information of the manual operation. These feature data will provide the basis for further analysis and decision making.
S103, performing time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set;
Specifically, for the first feature vector set, the server classifies the environment types, and determines a corresponding environment type set. This means that the server analyzes the feature vectors and identifies different environmental types, such as different growing seasons, climatic conditions or other environmental changes. By this step, the server is able to determine the different environment types present in the feature vector. And the server uses the environment type set to carry out record time matching on the first feature vector set, and determines a corresponding record time set. This means that the server associates each feature vector with the type of environment it belongs to and records the corresponding timestamp. By this step, the server knows the recording time corresponding to each feature vector. By sorting the set of recording times, the server generates a first set of timestamps. This set will contain the time stamp data for all the first feature vectors, arranged in time order. For the first feature matrix set, the server extracts temporal data related to the manual operation. This means that the server extracts time information related to manual operations, such as time recordings of fertilizer, irrigation or other manual operations, from each feature matrix. Based on the time data corresponding to each feature matrix, the server performs time stamp analysis to obtain time stamp data of each feature matrix, and generates a second time stamp set. This set will contain the timestamp data of all the second feature matrices, also arranged in time order. Through the steps, the server achieves time stamp analysis on the first feature vector set and the first feature matrix set, and generates a first time stamp set and a second time stamp set. These timestamp data will facilitate subsequent data pairing and traceability analysis. For example, assume that the server is researching the growth process of wheat. For the first set of feature vectors, the server analyzes the feature vectors to find that there are two environment types: spring and summer. The server classifies the feature vectors into the two environment types and records a corresponding timestamp for each feature vector. For the first set of feature matrices, the server extracts time data for the fertilization operation from each feature matrix. For example, the server finds that the first feature matrix corresponds to a fertilization time of 2023, 5, 1, and the second feature matrix corresponds to a fertilization time of 2023, 6, 15. The server performs a time stamp analysis on each feature matrix based on the time data, generating a second set of time stamps. It is assumed that the first set of time stamps record the spring and summer feature vector time stamps, and the second set of time stamps record the time stamps of the fertilization operation. By analyzing the two timestamp sets, the server obtains time information about the environment and manual operation in the wheat growing process. For example, by comparing the first set of time stamps to the second set of time stamps, the server may find that there are multiple time stamps for the fertilization operation within the time frame of the spring feature vector. This indicates that the farmer China Association for Promoting Democracy performed multiple fertilization operations during the spring. From these time stamp data, the server further analyzes the relationship between the environmental conditions and the manual operation. For example, the server studies whether there is a difference in the frequency and timing of fertilization by farmers under different environmental types. This helps the server to know the effect of fertilization on wheat growth and provides guidance for optimizing agricultural management.
S104, performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence;
Specifically, the server performs time sequence similarity analysis on the first time stamp set and the second time stamp set, and calculates the similarity between the first time stamp set and the second time stamp set. This can be achieved by various similarity measures such as euclidean distance, cosine similarity, or dynamic time warping. By calculating the similarity, the server obtains a sequence similarity dataset in which similarity values between the first set of time stamps and the second set of time stamps are recorded. The server performs a threshold analysis on the sequence similarity dataset to determine an appropriate threshold. The selection of the threshold value may be adjusted by experience or domain knowledge depending on the specific application scenario and requirements. The server filters out a plurality of similarity data satisfying a threshold requirement, the data representing pairs of sequences in the first set of time stamps and the second set of time stamps having sufficiently high similarity. And matching the time sequence by the server through the plurality of similarity data, and pairing the first time stamp set and the second time stamp set to generate a corresponding target time sequence. This means that the server finds pairs of timestamps in the first set of timestamps that have a high similarity with those in the second set of timestamps, establishing a correspondence between them. For example, assume that the server is researching the growth process of rice. For the first set of time stamps, the server records the growth stages of the rice, such as germination, growth, flowering and fruiting. For the second set of time stamps, the server records the irrigation time of the rice, i.e. the time stamp of each irrigation. Through time series similarity analysis, the server calculates the similarity between the first time stamp set and the second time stamp set. For example, there may be a higher degree of similarity between the growth phase and the irrigation time, while the degree of similarity is lower in other phases. The server performs a threshold analysis on the sequence similarity dataset, assuming that the server sets a similarity threshold, the server considers the two timestamp sequences to be matched only if the similarity exceeds the threshold. And screening out a plurality of similarity data meeting the condition by the server according to the threshold requirement. Through these similarity data, the server performs time series matching. For example, the server finds that there are multiple pairs of matched timestamps between the growth phase and the irrigation time, which means that multiple irrigations are performed at a particular phase of rice growth. Through time sequence matching, the server establishes a correspondence between the first set of time stamps and the second set of time stamps. The server generates a corresponding target time series comprising the growth phase and the corresponding irrigation time. By performing time series similarity analysis and matching on the first time stamp set and the second time stamp set, the server can find the correspondence between them and generate a target time series. The method can be applied to time data analysis in the growth process of many crops, and helps a server to understand the association between different environmental factors and manual operation, so that agricultural management and decision making are optimized.
S105, performing data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data;
Specifically, the server performs a first pairing relationship analysis on the first feature vector set by using the target time sequence. This means that the server compares the target time series with each feature vector in the first set of feature vectors, finding a feature vector that matches the target time series. By analyzing the relationship between them, the server generates a first time pairing relationship, i.e. the correspondence between the target time sequence and the first feature vector set is recorded. The server performs a second pairing relationship analysis on the first feature matrix set by using the target time sequence. Similar to the first pairing relationship analysis, the server compares the target time series with each feature matrix in the first feature matrix set to find a feature matrix that matches the target time series. By analyzing the relationship between them, the server generates a second time pairing relationship, i.e. the corresponding relationship between the target time sequence and the first feature matrix set is recorded. After the first and second time pairing relationships are generated, the server generates a data pairing transformation algorithm using the pairing relationships. The purpose of this algorithm is to match and transform the data in the first feature vector set and the first feature matrix set according to a pairing relationship to generate target feature data. The algorithm pairs the corresponding feature vector and the feature matrix according to the first time pairing relation and the second time pairing relation, and combines the data of the feature vector and the feature matrix to form target feature data. For example, assume that a server is researching the growth process of corn. The server has a first set of feature vectors that include daily environmental parameters such as illumination intensity, temperature, and humidity. The server also comprises a first characteristic matrix set which contains manual operation information such as daily fertilization amount, irrigation amount, pesticide usage amount and the like. The goal of the server is to pair these characteristic data with the growth stage of the corn in order to better understand the environmental parameters and the impact of manual operations on the corn growth. Through target time sequence analysis, the server finds the corresponding relation between the corn growth stage and time. For example, the server knows that 10 days are required from sowing to seedling stage, 20 days are required from seedling stage to growing stage, and 30 days are required from growing stage to harvesting stage. Using these pairing relationships, the server performs data pairing processing. According to the first time pairing relationship, the server matches a time period corresponding to the seeding to seedling stage in the target time sequence with the feature vector in the first feature vector set. The server obtains the target characteristic data of the seeding to seedling stage. According to the second time pairing relationship, the server matches the time period from the seedling stage to the growing stage in the target time sequence with the feature vector in the first feature vector set. The server obtains the target characteristic data from the seedling stage to the growing stage. The server matches a time period corresponding to the growing period to the harvesting period in the target time sequence with the feature vector in the first feature vector set according to the pairing relation, so that target feature data from the growing period to the harvesting period is obtained. After the data pairing processing of the feature vector set is completed, the server can also perform the data pairing processing on the first feature matrix set by using the first time pairing relationship and the second time pairing relationship. And matching the time period in the target time sequence with the feature matrix in the first feature matrix set, and obtaining target feature data in the corresponding time period by the server.
S106, carrying out identifier generation on crops through target characteristic data to obtain a target identifier;
Specifically, the server performs feature importance calculation on the target feature data. Feature importance is an indicator that measures the degree of contribution of each feature to the generation of the target identifier. Common feature importance calculation methods include information gain, base index, random forest, and the like. The server obtains the importance value of each feature by applying an appropriate feature importance calculation method to the target feature data, forming a feature importance set. And based on the feature importance set, the server performs feature screening processing on the target feature data. The purpose of feature screening is to select those features that most contribute to the generation of the target identifier to improve the accuracy and reliability of the identifier. According to the feature importance value, the server sets a threshold value, and selects the features with importance higher than the threshold value to form a screening feature data set. Based on the screening feature data set, the server performs identifier generation. The identifier is a symbol or code for uniquely identifying the crop. It may be a number, a string, or other form of identification. The server generates a target identifier associated with the crop by applying an appropriate algorithm or rule to the screening feature data set. For example, assume that a server studies a growth process of a rice variety and collects characteristic data related to the growth process, such as light intensity, soil humidity, air temperature, etc. And the server calculates the feature importance degree of the feature data to obtain the importance degree value of each feature. The server sets a threshold value and selects features with importance higher than the threshold value as screening feature data. For example, the server selects illumination intensity and soil moisture as screening features. The server generates a target identifier of the rice variety using the selected screening characteristic data, for example, giving each variety a unique number or name. By the method, the server generates the identifier of the crops according to the target characteristic data, so that the tracing and identification of the crops are realized. This helps agricultural managers to perform work in terms of variety management, origin tracing, quality control of agricultural products, and the like.
S107, performing data encoding processing on the target identifier to generate target encoded data;
Specifically, the server selects an appropriate encoding scheme for the target identifier. The coding mode can be selected according to specific requirements and application scenes, and common coding modes comprise binary coding, decimal coding, hexadecimal coding and the like. The coding mode is selected by considering the size, complexity and processing requirement of the data. And secondly, carrying out data coding processing on the target identifier according to the selected coding mode. The specific encoding process will vary from one encoding scheme to another. Taking binary encoding as an example, each element in the target identifier may be converted to a corresponding binary form and combined together to form a binary encoded sequence. For decimal encoding, each element in the target identifier is converted to a corresponding decimal number. Wherein, other coding modes also have corresponding conversion rules. In performing the encoding process, attention is paid to the accuracy and range of data. The encoded data is ensured to accurately represent the information of the original identifier, and the integrity and the accuracy of the data are maintained. And obtaining target coded data by the server through coding processing. These data may be used for subsequent storage, transmission and processing. By encoding, the server converts the target identifier into a data form which is easier to process and transmit, thereby improving the efficiency and security of the data. For example, assume that a server is to identify and encode a growing area of a batch of crops. The server represents the identifier of each growing place as a string, for example: "A001", "B002", etc. For the encoding process, the server selects a decimal encoding scheme. The server converts the characters in each identifier into corresponding decimal numbers. For example, "a001" is converted to 65, 48, 49, and "B002" is converted to 66, 48, 50. These decimal numbers are combined together to form a coding sequence, namely 65, 48, 49, 66, 48, 50. By such encoding processing, the server obtains target encoded data. These encoded data may be used for storage, transmission, and processing. When such data is needed, the server converts it back to the original identifier form by a reverse decoding process. In short, by performing data encoding processing on the target identifier, the server converts the identifier into a data form more suitable for processing and transmission, thereby improving the efficiency and security of the data. When selecting a proper data encoding process for the target identifier, the server selects a proper encoding mode and processes the target identifier according to the selected encoding mode.
S108, generating tracing information of the target identifier through the target coding data, and generating a target tracing report.
Specifically, the server decodes the target encoded data, converting it back to the original identifier form. This may convert the target encoded data into the target identifier using a corresponding decoding method. When the target identifier is decoded into its original form, the server obtains trace-source information associated with the target. This may be obtained by querying a database, record, or other reliable source. Such information may include planting sites, planting dates, farmland management measures, fertilizer application conditions, irrigation sources, picking times, etc. Based on the obtained traceability information, the server generates a target traceability report. This typically involves the process of sorting, organizing, and presenting information. Text processing tools, data visualization tools, or specialized report generation tools may be used to help generate clear, accurate, easily understood traceable reports. The content and format of the traceability report can be customized according to the requirements. It may include basic information of the target such as an identifier, date of planting, planting location, etc. Planting environment information may also be included describing the growth conditions of the target, such as soil type, climate, solar radiation, etc. Farmland management measures, fertilizer application conditions and irrigation water sources can also be recorded to demonstrate targeted planting processes and management quality. In addition, the picking time and the picking mode are also important parts, and can reflect the target harvesting time and the harvesting method. For example, assume that the server is tracking a batch of rice. The RICE identifier is decoded by the target encoded data, and the server obtains an original identifier "RICE001". Inquiring a related database and records, and acquiring the following traceability information by the server: the planting site of the rice is a farmland A, and the planting date is 2023 years, 4 months and 1 day. The rice planting environment comprises a soil type of swamp soil, a climate of subtropical climate and sufficient sunlight. Farmland has taken organic agricultural management measures, applied organic fertilizer, and used irrigation water from local water sources. The rice is subjected to proper field management and pest control during the mature period. The picking time is 2023, 9 and 15 days, and the picking mode is mechanized harvesting. Based on the tracing information, the server generates a detailed target tracing report which comprises basic information of rice, planting environment information, farmland management measures, fertilization conditions, irrigation water sources, field management and pest control measures, picking time, harvesting modes and the like. Such reports may provide a comprehensive description of the traceability history and related information of the rice, helping consumers to understand the rice planting process, quality and safety, and ensuring traceability and credibility of the product. The rice identifier is generated by tracing information through the target coding data, so that producers, supply chain participants and consumers can be helped to trace the planting, processing and circulation processes of the rice. This is critical to ensure food safety, quality control, sustainable agriculture, and consumer trust.
In the embodiment of the invention, the environmental parameter information of the crops in the growth process is collected, and meanwhile, the manual operation information of the crops in the growth process is collected; performing feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, performing feature matrix extraction on the manual operation information to generate a first feature matrix set; performing time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set; performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence; based on the target time sequence, carrying out data pairing processing on the first feature vector set and the first feature matrix set to generate target feature data; generating an identifier of the crop through the target characteristic data to obtain a target identifier; performing data encoding processing on the target identifier to generate target encoded data; and generating tracing information of the target identifier through the target coding data to generate a target tracing report. According to the intelligent crop growth monitoring system, intelligent monitoring and analysis are carried out on the crop growth process by adopting the Internet of things, big data and artificial intelligence technology, so that the problems in production are found and solved in time, and the production efficiency and quality are improved. By monitoring and analyzing the environmental parameter information, the crop growth environment such as temperature, humidity, soil pH value and the like can be better understood and controlled, so that the crop growth condition is optimized, and the crop yield and quality are improved. The progress condition of each production stage can be known by collecting and analyzing manual operation information, and the growth management strategy can be timely adjusted; meanwhile, the performance of operators can be evaluated and managed, and the scientificity and efficiency of management are improved. Through time sequence matching, data pairing processing and feature extraction, more comprehensive, accurate and reliable data information can be generated, references are provided for subsequent data analysis and decision making, and the scientificity and the accuracy of decision making are improved.
By carrying out identifier generation and data coding processing on crops, the whole-course tracking and management of the growth process of the crops can be realized, so that safer and more reliable products are provided for consumers, and the food safety and quality standard are promoted and improved.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Acquiring temperature data of crops in the growing process by a temperature sensor, and acquiring humidity data of the crops in the growing process by a humidity sensor;
(2) Collecting a soil picture set of crops in the generation process through an image collecting device, inputting the soil picture set into a preset soil analysis model for soil parameter analysis, and generating soil parameter data;
(3) Taking the temperature data, the humidity data and the soil parameter data as environment parameter information;
(4) And collecting manual operation information of crops in the production process.
Specifically, a temperature sensor may be used to monitor the temperature change of the crop in real time during the growth process. The temperature sensor may be installed in the vicinity of farmlands or crops, and periodically collects temperature data. These data may reflect the ambient temperature to which the crop is exposed, helping the farmer to understand the growth status of the crop and possible temperature effects. At the same time, humidity sensors are also indispensable tools for measuring the humidity level of crops during growth. Humidity sensors may be installed in the soil or around the crop, monitoring changes in humidity in the air. These data can reveal the effect of soil moisture conditions and atmospheric humidity on crops, helping farmers make corresponding irrigation and farming management decisions. In order to acquire soil parameter data, the image acquisition device can be utilized to shoot soil in the growth process of crops. The image capture device may be a camera, drone or other device that may be used for image capture. By taking a soil picture set, a large amount of soil image data can be collected. And inputting the soil picture sets into a preset soil analysis model for soil parameter analysis. The soil analysis model can process and analyze soil images by utilizing computer vision and machine learning technologies, and extract key parameters of soil, such as soil texture, color, water content and the like. The soil parameter data can provide important information about soil conditions, and helps farmers know soil fertility, drainage performance, and conditions suitable for planting crops and the like. And integrating the temperature data, the humidity data and the soil parameter data together to form complete environment parameter information. The information can provide comprehensive crop growth environment data, and helps farmers to carry out accurate farming management and decision-making, such as irrigation regulation and control, fertilization planning, pest control measure making and the like. Meanwhile, manual operation information of crops in the production process is required to be collected. This may be collected by a record of the farmer or by an automated system. The manual operation information comprises the activities of planting, fertilizing, spraying medicine, pruning and the like which manually interfere with the growth of crops. Such operational information is critical to analyzing and assessing the growth status and effect of crops. In order to collect manual operation information of crops in the process of generation, a record form or agricultural management software can be used for recording each manual operation. In the planting process, farmers can record the types, time and specific operation contents of various manual operations according to actual conditions. Such information may include the time and dosage of the fertilizer, the type and amount of the chemical to be sprayed, the time and manner of pruning, etc. The agricultural management software can also provide more intelligent data acquisition and management functions, and helps farmers to record and analyze manual operation information more conveniently. By collecting the manual operation information of the crops in the production process, the growth condition of the crops can be comprehensively analyzed and evaluated. By combining the environmental parameter information, the association relationship between the growth of crops, environmental factors and manual operation can be explored. For example, the effect of temperature and humidity changes on crop growth can be analyzed, the effect of different fertilization modes on crop yield can be evaluated, the effect of pruning on plant growth and fruiting can be evaluated, and the like.
In a specific embodiment, as shown in fig. 2, the process of collecting the manual operation information of the crops in the process of generation may specifically include the following steps:
S201, acquiring a manual operation data table, and performing manual operation type traversal on the manual operation data table to generate a manual operation type set;
s202, performing operation data threshold analysis based on a manual operation type set, and generating threshold data corresponding to each manual operation type;
S203, extracting data from the manual operation data table to generate manual operation data;
S204, performing invalid data screening on the manual operation data based on threshold data corresponding to each manual operation type, and determining invalid data;
s205, invalid data eliminating processing is carried out on the manual operation data, and manual operation information is generated.
The server acquires a manual operation data table, and the table records manual operation information in the crop generation process. This data table may be a file stored in the form of a spreadsheet, wherein each row represents a manual operation, including information about the type of operation, time of operation, operator, etc. The server performs manual operation type traversal on the manual operation data table, wherein the purpose of the traversal is to identify all different manual operation types and sort the manual operation types into a manual operation type set. For example, if the manual operation data table of the server includes three different operation types of fertilization, irrigation and pruning, the generated manual operation type set includes the three operation types. Based on the generated set of manual operation types, the server performs an operation data threshold analysis. The threshold is a criterion for measuring whether or not the operation data meets a predetermined condition. Different types of manual operations may have different thresholds, so the server generates corresponding threshold data for each type of manual operation. The threshold data may include minimum, maximum, average, etc. metrics that are used to measure a reasonable range of operational data. The server performs data extraction on the manual operation data table, and extracts data related to the manual operation from the manual operation data table. Such data may include information about the type of operation, time of operation, operator, etc. The result of the extraction will generate a set of manual operation data containing all manual operation data. Based on the threshold data corresponding to each manual operation type, the server performs invalid data screening on the manual operation data, namely marking the data which does not meet the threshold condition as invalid data. For example, for a fertilizer operation type, if the amount of fertilizer applied is less than a minimum threshold or greater than a maximum threshold, the server may flag these data as invalid data. And the server performs invalid data elimination processing on the manual operation data, and deletes the invalid data from the manual operation data set to obtain final manual operation information. This ensures the quality and accuracy of the manual operation data. For example, assume that the server has a manual operation data table of crops in which the amount of fertilizer applied by the fertilizer application operation is recorded. The server traverses the data table to find that the set of manual operation types includes fertilization. The server performs threshold analysis, and sets the minimum threshold value of the fertilizing amount to 10kg and the maximum threshold value to 50kg. Next, data of the fertilization operation, including the operation type and the fertilization amount, is extracted from the data table. According to the threshold data, the server screens out data with fertilizing amount smaller than 10kg or larger than 50kg and marks the data as invalid data. And removing invalid data to obtain effective manual operation information including the type and the fertilizing amount of fertilizing operation. Through the steps, the server successfully performs invalid data elimination processing on the manual operation data, and effective manual operation information is generated. This information can be used for subsequent analysis, decision making and report generation.
In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:
s301, classifying the environment types of the first feature vector set, and determining a corresponding environment type set;
s302, performing record time matching on a first feature vector set through an environment type set, and determining a corresponding record time set;
S303, generating a first timestamp set by recording the time set;
S304, manually operating time extraction is carried out on the first feature matrix set, and time data corresponding to each first feature matrix is determined;
S305, performing time stamp analysis based on the time data corresponding to each first feature matrix to obtain time stamp data corresponding to each first feature matrix and generate a second time stamp set.
It should be noted that, the classifying of the environmental types of the first feature vector set may be implemented by a machine learning or statistical method. The server uses the first feature vector set as input data, and applies a clustering algorithm or a classification model to train and classify. During training, the algorithm will analyze the similarity and differences between feature vectors and group them into different environment types. Finally, the server obtains a set of environment types, including different environment categories. For example, assume that the server uses a K-means clustering algorithm to classify the environment types for the first set of feature vectors. The algorithm will divide the feature vectors into different clusters based on their similarity between them. For example, for a rice growing environment, three clusters may be formed: high temperature and high humidity, low temperature and low humidity and suitable temperature and humidity. The server obtains a set of environmental types including high temperature and high humidity, low temperature and low humidity, and suitable temperature and humidity. And carrying out record time matching on the first feature vector set through the environment type set, and determining a corresponding record time set. This step is to find the recording time point for each environment type. And the server screens out corresponding first feature vector records according to each type in the environment type set, and extracts the recorded time information. These time information are combined together to form a recording time set. For example, for high temperature and high humidity in the environment type set, the server screens out all the first feature vector records belonging to the high temperature and high humidity environment, and extracts their time information. Assume that the server gets the following time information: 2022-05-01 08:00:00, 2022-05-01 12:00:00, 2022-05-01 16:00:00. These times constitute a collection of recording times. Based on the set of recording times, the server generates a first set of timestamps. The time stamp refers to a specific time point when a certain event occurs, and may be used to represent an absolute time of the recording time. The server converts each time in the recorded time set into a time stamp to obtain a first time stamp set. For example, for time "2022-05-01 08:00:00" in the set of recording times, the server converts it to a corresponding timestamp, such as "1650345600". The same conversion may be performed for other recording times. The server obtains a first set of time stamps. Meanwhile, the server extracts the manual operation time of the first feature matrix set and determines time data corresponding to each first feature matrix. The manual operation time refers to a time point or a time period when a specific operation is performed, and can be obtained through recording or monitoring. And the server extracts corresponding manual operation time information according to each matrix data in the first feature matrix set. This may be accomplished by recording a time stamp of the manual operation or marking a time period of the manual operation in the data. For example, manual operations during rice growth may include fertilization, irrigation, weeding, and the like. Each time a manual operation is performed, the server records the start time and the end time of the operation. For example, assume that the server has a first feature matrix corresponding to 2022-05-01 rice growth data. In this feature matrix, the server sees that there is one fertilization operation within the time period. The server records the start time of the operation as 2022-05-01 10:00:00 and the end time as 2022-05-01 10:30:00. The server obtains the manual operation time data corresponding to the feature matrix. Based on the time data corresponding to each first feature matrix, the server performs time stamp analysis to obtain time stamp data corresponding to each first feature matrix, and generates a second time stamp set. A timestamp is a number representing time, typically in the form of an integer or floating point number. It can be used to identify the order of occurrence of events in a time series. For example, for the manual operation time data described above, the server converts it into a corresponding time stamp. Assume that the server takes a certain fixed time point as a reference time, for example, a timestamp corresponding to 2022-01-01:00:00 is 0. Then, the server calculates a time stamp with respect to the reference time based on the operation time data. For a start time 2022-05-01 10:00:00, its corresponding timestamp may be an integer greater than 0 or a floating point number. Wherein the same conversion can be performed for other operation times as well. The server obtains the time stamp data corresponding to each first feature matrix and generates a second set of time stamps. Through the steps, the server successfully classifies the environment types of the first feature vector set, and determines a corresponding environment type set. Meanwhile, by recording time matching and time stamp analysis, the server obtains a first time stamp set and a second time stamp set. These sets of time stamps may be used in subsequent time series analysis, data comparison, or other related tasks.
In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:
s401, performing time sequence similarity analysis on the first time stamp set and the second time stamp set to generate a corresponding sequence similarity data set;
S402, carrying out threshold analysis on the sequence similarity data set to generate a plurality of similarity data meeting the threshold requirement;
S403, performing time sequence matching on the first time stamp set and the second time stamp set through a plurality of similarity data, and generating a corresponding target time sequence.
Specifically, for the first timestamp set and the second timestamp set, an appropriate similarity calculation method may be selected. For example, euclidean distance may be used to measure the degree of similarity between two time series. The euclidean distance is a method for measuring the similarity by calculating the difference of numerical values at corresponding positions of two time sequences and squaring the difference. In addition, other similarity measurement methods can be used, and a proper algorithm can be selected according to specific requirements. And inputting the first timestamp set and the second timestamp set into a similarity calculation method to obtain a corresponding sequence similarity data set. For each pair of time series, a similarity value can be obtained by calculating the similarity between them. These similarity values may form a similarity dataset for subsequent analysis and processing. And carrying out threshold analysis on the generated sequence similarity data set. The threshold is a threshold value for judging the similarity. By setting an appropriate threshold value, a plurality of similarity data satisfying the threshold value requirement can be screened out. The particular threshold setting may be determined based on the particular problem and need, for example, setting a similarity threshold, and selecting only data having a similarity above the threshold. And performing time sequence matching on the first time stamp set and the second time stamp set through a plurality of similarity data meeting the threshold requirement, and generating a corresponding target time sequence. This can be achieved by finding the time series pairs with the highest similarity and matching them to obtain the target time series. The matching manner may be determined according to a specific problem, for example, selecting a time sequence pair with highest similarity as a matching result, or adopting other matching strategies. For example, assume that there are two sets of time sequences, a first set of time stamps and a second set of time stamps, respectively. The server selects Euclidean distance as a similarity calculation method. And obtaining a sequence similarity data set by calculating Euclidean distance between each pair of time sequences. The server sets a similarity threshold and only selects data with similarity higher than the threshold. Assume that the server gets the following similarity dataset: the similarity of the first time stamp sequence 1 and the second time stamp sequence 1 is 0.85; the similarity of the first time stamp sequence 1 and the second time stamp sequence 2 is 0.92; the similarity of the first time stamp sequence 1 and the second time stamp sequence 3 is 0.76; the similarity of the first time stamp sequence 2 and the second time stamp sequence 1 is 0.88; the similarity of the first time stamp sequence 2 and the second time stamp sequence 2 is 0.95; the similarity of the first time stamp sequence 2 and the second time stamp sequence 3 is 0.82. The server sets the similarity threshold to 0.9. According to the threshold analysis, only the first time stamp sequence 2 and the second time stamp sequence 2 have a similarity higher than 0.9, so the server selects this time sequence as a matching result. By performing time series matching on the first time stamp sequence 2 and the second time stamp sequence 2, a corresponding target time series is generated. This means that the server pairs the first time stamp sequence 2 and the second time stamp sequence 2 to form a target time sequence. Through the above procedure, it is demonstrated how the matching of the first and second sets of time stamps and the generation of the target time sequence is achieved through the time sequence similarity analysis, the threshold analysis, and the time sequence matching.
In a specific embodiment, the process of executing step S105 may specifically include the following steps:
(1) Carrying out first pairing relation analysis on the first feature vector set through the target time sequence to generate a first time pairing relation;
(2) Performing second pairing relation analysis on the first feature matrix set through the target time sequence to generate a second time pairing relation;
(3) Generating a corresponding data pairing conversion algorithm through the first time pairing relation and the second time pairing relation;
(4) And the data pairing conversion algorithm performs data pairing processing on the first feature vector set and the first feature matrix set to generate target feature data.
Specifically, a first pairing relation analysis is performed on the first feature vector set through the target time sequence, and a first time pairing relation is generated. This may be matched by comparing the time stamps in the target time sequence with the time stamps in the first set of feature vectors. If a timestamp has a corresponding match in the target time series, then the feature vector is in a pairing relationship with the target time series. For example, assuming that the target time series includes a timestamp [2022-01-01, 2022-01-05, 2022-01-10], the first set of feature vectors includes a timestamp [2022-01-01, 2022-01-03, 2022-01-05], the first time pairing relationship is [2022-01-01, 2022-01-05]. And carrying out second pairing relation analysis on the first feature matrix set through the target time sequence, and generating a second time pairing relation. This may be matched by comparing the time stamps in the target time sequence with the time stamps in the first set of feature matrices. If there is a corresponding match in the target time series for a timestamp, then the feature matrix is in a pairing relationship with the target time series. For example, assuming that the target time series includes a timestamp [2022-01-01, 2022-01-05, 2022-01-10], the first set of feature matrices includes a timestamp [2022-01-01, 2022-01-03, 2022-01-05], the second time pairing relationship is [2022-01-01, 2022-01-05]. A data pairing conversion algorithm may be generated by the first time pairing relationship and the second time pairing relationship. The algorithm pairs the data in the first feature vector set and the first feature matrix set according to a pairing relationship. For example, assume that the first time pairing relationship is [2022-01-01, 2022-01-05], the second time pairing relationship is [2022-01-01, 2022-01-05], the server pairs a first feature vector of the first set of feature vectors with a first feature matrix of the first set of feature matrices, pairs a second feature vector of the first set of feature vectors with a second feature matrix of the first set of feature matrices, and so on. And carrying out data pairing processing on the first feature vector set and the first feature matrix set by the server through a data pairing conversion algorithm to generate target feature data. This means that the feature vectors and feature matrices of each pairing will be combined together to form the target feature data. These target feature data may be used for further analysis and application. For example, the target feature data may be input into a machine learning model for training to predict the growth status of the crop or make other relevant decisions. Furthermore, the target feature data may also be used to generate visual reports, conduct data mining and insight, and support crop management and optimize agricultural production.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Calculating the feature importance degree of the target feature data to generate a corresponding feature importance degree set;
(2) Performing feature screening processing on the target feature data through the feature importance set to generate corresponding screened feature data;
(3) And generating an identifier for the crop based on the screening characteristic data to obtain a target identifier.
Specifically, an appropriate feature importance calculating method is selected. Common methods include information gain, analysis of variance, decision trees, random forests, support vector machines, and the like. These methods may be selected based on the type of data and the nature of the problem. And secondly, calculating the feature importance degree of the target feature data according to the selected feature importance degree calculation method. This may be achieved through training and evaluation of algorithms or models. During the training process, a model may be constructed using the training dataset and the importance of each feature to the target variable is calculated. And generating a corresponding feature importance set according to the calculated feature importance. This set can be used for subsequent feature screening processes. And performing feature screening processing on the target feature data through the feature importance set. A threshold may be set to screen out features with higher importance or to select the first few features with highest importance. This can reduce the number of features and preserve features that have an important impact on the target variable. Based on the screening characteristic data, an identifier of the crop can be generated. The specific method can be dependent on the actual requirements and application scenario. For example, the screening signature data may be used as a signature of the crop, combined with other information (e.g., geographic location, growth stage, etc.), to generate a unique identifier. For example, assume that the server is to analyze and identify the growth of rice. The server collects a plurality of characteristics related to rice growth, such as illumination intensity, temperature, humidity, soil pH value and the like. The server selects a random forest algorithm as a feature importance calculation method. By training a random forest model, the server calculates the importance of each feature to the growth condition of the rice. The feature importance set is assumed to be as follows: illumination intensity (0.45), temperature (0.35), humidity (0.25), soil pH (0.15). And the server performs feature screening processing according to the importance level set. Assuming that the server sets an importance threshold to be 0.3, and screening out features with importance greater than or equal to 0.3. According to this threshold, the server retains the two characteristics of illumination intensity (0.45) and temperature (0.35). Based on the screening feature data, the server performs identifier generation of the rice based on the two features. Assume that the server combines the values of the two characteristics of illumination intensity and temperature to obtain a character string as an identifier of the rice. For example, assuming that the illumination intensity of a certain rice sample is 1000 Lux and the temperature is 28 degrees celsius, the corresponding identifier may be "1000_28". Through such feature importance calculation, feature screening and identifier generation processes, the server compresses the raw rice feature data into fewer key features and generates a unique identifier to represent the rice sample. The identifier can be used for tracing, tracking and managing rice, and facilitates agricultural production and research.
The method for tracing the growth of the crop fruit in the embodiment of the present invention is described above, and the system for tracing the growth of the crop fruit in the embodiment of the present invention is described below, referring to fig. 5, and one embodiment of the system for tracing the growth of the crop fruit in the embodiment of the present invention includes:
The acquisition module 501 is used for acquiring environmental parameter information of crops in the growth process and acquiring manual operation information of the crops in the growth process;
the mapping module 502 is configured to perform feature vector mapping on the environmental parameter information to generate a first feature vector set, and simultaneously perform feature matrix extraction on the manual operation information to generate a first feature matrix set;
An analysis module 503, configured to perform timestamp analysis on each first feature vector in the first feature vector set to generate a first timestamp set, and perform timestamp analysis on each first feature matrix in the first feature matrix set to generate a second timestamp set;
a matching module 504, configured to perform time sequence matching on the first timestamp set and the second timestamp set, and generate a corresponding target time sequence;
A processing module 505, configured to perform data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence, so as to generate target feature data;
A generating module 506, configured to generate an identifier for the crop according to the target feature data, so as to obtain a target identifier;
The encoding module 507 is configured to perform data encoding processing on the target identifier, and generate target encoded data;
And the tracing module 508 is configured to generate tracing information of the target identifier according to the target encoded data, and generate a target tracing report.
Through the cooperation of the components, the environmental parameter information of the crops in the growth process is collected, and meanwhile, the manual operation information of the crops in the growth process is collected; performing feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, performing feature matrix extraction on the manual operation information to generate a first feature matrix set; performing time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set; performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence; performing data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data; generating an identifier of the crop through the target characteristic data to obtain a target identifier; performing data encoding processing on the target identifier to generate target encoded data; and generating tracing information of the target identifier through the target coding data to generate a target tracing report. According to the intelligent crop growth monitoring system, intelligent monitoring and analysis are carried out on the crop growth process by adopting the Internet of things, big data and artificial intelligence technology, so that the problems in production are found and solved in time, and the production efficiency and quality are improved. By monitoring and analyzing the environmental parameter information, the crop growth environment such as temperature, humidity, soil pH value and the like can be better understood and controlled, so that the crop growth condition is optimized, and the crop yield and quality are improved. The progress condition of each production stage can be known by collecting and analyzing manual operation information, and the growth management strategy can be timely adjusted; meanwhile, the performance of operators can be evaluated and managed, and the scientificity and efficiency of management are improved. Through time sequence matching, data pairing processing and feature extraction, more comprehensive, accurate and reliable data information can be generated, references are provided for subsequent data analysis and decision making, and the scientificity and the accuracy of decision making are improved. By carrying out identifier generation and data coding processing on crops, the whole-course tracking and management of the growth process of the crops can be realized, so that safer and more reliable products are provided for consumers, and the food safety and quality standard are promoted and improved.
The detailed description of the crop fruit growth tracing system in the embodiment of the present invention is given above in fig. 5 from the point of view of the modularized functional entity, and the detailed description of the crop fruit growth tracing device in the embodiment of the present invention is given below from the point of view of hardware processing.
Fig. 6 is a schematic structural diagram of a crop fruit growth tracing device according to an embodiment of the present invention, where the crop fruit growth tracing device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (centralprocessingunits, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage mediums 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the crop fruit growth traceability device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the crop fruit growth traceability device 600.
Crop fruit growth traceability device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as WindowsServe, macOSX, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the structure of the crop fruit growth traceability device illustrated in fig. 6 does not constitute a limitation of the crop fruit growth traceability device, and may include more or fewer components than illustrated, or may combine certain components, or may be arranged in a different arrangement of components.
The invention also provides a crop fruit growth tracing device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the crop fruit growth tracing method in the embodiments.
The invention also provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium, and can also be a volatile computer readable storage medium, wherein instructions are stored in the computer readable storage medium, and when the instructions run on a computer, the instructions cause the computer to execute the steps of the crop fruit growth tracing method.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
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 invention 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 invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (randomacceSmemory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention 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 invention.
Claims (9)
1. The crop fruit growth tracing method is characterized by comprising the following steps of:
Collecting environmental parameter information of crops in the growth process, and collecting manual operation information of the crops in the growth process;
Performing feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, performing feature matrix extraction on the manual operation information to generate a first feature matrix set;
Performing time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set;
Performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence; the method specifically comprises the following steps: performing time sequence similarity analysis on the first time stamp set and the second time stamp set to generate a corresponding sequence similarity data set; performing threshold analysis on the sequence similarity data set to generate a plurality of similarity data meeting threshold requirements; performing time sequence matching on the first time stamp set and the second time stamp set through the plurality of similarity data to generate a corresponding target time sequence;
Performing data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data;
Generating an identifier of the crop through the target characteristic data to obtain a target identifier;
performing data encoding processing on the target identifier to generate target encoded data;
and generating tracing information of the target identifier through the target coding data to generate a target tracing report.
2. The method for tracing the growth of the fruits of the crops according to claim 1, wherein the step of collecting the environmental parameter information of the crops in the growth process and the step of collecting the manual operation information of the crops in the growth process comprises the following steps:
Acquiring temperature data of the crops in the growing process through a temperature sensor, and acquiring humidity data of the crops in the growing process through a humidity sensor;
collecting a soil picture set of the crops in the generation process through an image collecting device, inputting the soil picture set into a preset soil analysis model for soil parameter analysis, and generating soil parameter data;
taking the temperature data, the humidity data and the soil parameter data as the environment parameter information;
and collecting manual operation information of the crops in the production process.
3. The method for tracing the growth of fruits of crops according to claim 2, wherein said collecting information of manual operations of said crops during the process of production comprises:
Acquiring a manual operation data table, and performing manual operation type traversal on the manual operation data table to generate a manual operation type set;
Performing operation data threshold analysis based on the manual operation type set to generate threshold data corresponding to each manual operation type;
extracting data from the manual operation data table to generate manual operation data;
Performing invalid data screening on the manual operation data based on threshold data corresponding to each manual operation type, and determining invalid data;
and performing invalid data elimination processing on the manual operation data to generate the manual operation information.
4. The method of claim 1, wherein performing a time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and performing a time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set, includes:
classifying the environment types of the first feature vector set, and determining a corresponding environment type set;
performing record time matching on the first feature vector set through the environment type set, and determining a corresponding record time set;
Generating a first timestamp set through the record time set;
manually operating time extraction is carried out on the first feature matrix set, and time data corresponding to each first feature matrix is determined;
And carrying out time stamp analysis based on the time data corresponding to each first feature matrix to obtain time stamp data corresponding to each first feature matrix and generating a second time stamp set.
5. The method according to claim 1, wherein the performing data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data includes:
Performing first pairing relation analysis on the first feature vector set through the target time sequence to generate a first time pairing relation;
performing second pairing relation analysis on the first feature matrix set through the target time sequence to generate a second time pairing relation;
generating a corresponding data pairing conversion algorithm through the first time pairing relation and the second time pairing relation;
And carrying out data pairing processing on the first feature vector set and the first feature matrix set through the data pairing conversion algorithm to generate target feature data.
6. The method for tracing the growth of the fruit of the crop according to claim 1, wherein the generating the identifier of the crop by the target feature data to obtain the target identifier comprises:
calculating the feature importance degree of the target feature data to generate a corresponding feature importance degree set;
performing feature screening processing on the target feature data through the feature importance set to generate corresponding screened feature data;
and generating an identifier of the crop based on the screening characteristic data to obtain a target identifier.
7. The crop fruit growth traceability system is characterized by comprising:
The acquisition module is used for acquiring environmental parameter information of crops in the growth process and acquiring manual operation information of the crops in the growth process;
the mapping module is used for carrying out feature vector mapping on the environment parameter information to generate a first feature vector set, and simultaneously, carrying out feature matrix extraction on the manual operation information to generate a first feature matrix set;
The analysis module is used for carrying out time stamp analysis on each first feature vector in the first feature vector set to generate a first time stamp set, and simultaneously carrying out time stamp analysis on each first feature matrix in the first feature matrix set to generate a second time stamp set;
The matching module is used for performing time sequence matching on the first time stamp set and the second time stamp set to generate a corresponding target time sequence; the method specifically comprises the following steps: performing time sequence similarity analysis on the first time stamp set and the second time stamp set to generate a corresponding sequence similarity data set; performing threshold analysis on the sequence similarity data set to generate a plurality of similarity data meeting threshold requirements; performing time sequence matching on the first time stamp set and the second time stamp set through the plurality of similarity data to generate a corresponding target time sequence;
The processing module is used for carrying out data pairing processing on the first feature vector set and the first feature matrix set based on the target time sequence to generate target feature data;
The generation module is used for generating identifiers of the crops through the target characteristic data to obtain target identifiers;
the encoding module is used for carrying out data encoding processing on the target identifier to generate target encoded data;
and the tracing module is used for generating tracing information of the target identifier through the target coding data and generating a target tracing report.
8. Crop fruit growth traceability equipment, its characterized in that, crop fruit growth traceability equipment includes: a memory and at least one processor, the memory having instructions stored therein;
The at least one processor invokes the instructions in the memory to cause the crop fruit growth tracing apparatus to perform the crop fruit growth tracing method of any one of claims 1-6.
9. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the method of tracing fruit growth of crops as claimed in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310725241.1A CN116757707B (en) | 2023-06-19 | 2023-06-19 | Crop fruit growth tracing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310725241.1A CN116757707B (en) | 2023-06-19 | 2023-06-19 | Crop fruit growth tracing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116757707A CN116757707A (en) | 2023-09-15 |
| CN116757707B true CN116757707B (en) | 2024-05-24 |
Family
ID=87958439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310725241.1A Active CN116757707B (en) | 2023-06-19 | 2023-06-19 | Crop fruit growth tracing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116757707B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117629314A (en) * | 2024-01-26 | 2024-03-01 | 山东智云信息科技有限公司 | Environment intelligent monitoring system based on Internet of things |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008210024A (en) * | 2007-02-23 | 2008-09-11 | Nippon Telegr & Teleph Corp <Ntt> | Apparatus for analyzing set of documents, method for analyzing set of documents, program implementing this method, and recording medium storing this program |
| CN108615161A (en) * | 2018-04-20 | 2018-10-02 | 保定市中远邦泰电子科技有限公司 | Crops are traced to the source data system |
| CN113423018A (en) * | 2021-08-24 | 2021-09-21 | 腾讯科技（深圳）有限公司 | Game data processing method, device and storage medium |
| CN114066480A (en) * | 2021-11-08 | 2022-02-18 | 瀚云科技有限公司 | Method, device, system, equipment and storage medium for generating traceability information |
| CN114219512A (en) * | 2022-01-07 | 2022-03-22 | 瀚云科技有限公司 | Crop information pushing method and device, computer equipment and storage medium |
| CN115545678A (en) * | 2022-11-29 | 2022-12-30 | 浙江贵仁信息科技股份有限公司 | Water quality monitoring method based on water environment portrait and pollutant traceability |
| CN115630967A (en) * | 2022-10-12 | 2023-01-20 | 中国建设银行股份有限公司 | Intelligent tracing method and device for agricultural products, electronic equipment and storage medium |
| CN116011331A (en) * | 2022-12-30 | 2023-04-25 | 中国农业大学烟台研究院 | Irrigation decision method and device based on Internet of things |
-
2023
- 2023-06-19 CN CN202310725241.1A patent/CN116757707B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008210024A (en) * | 2007-02-23 | 2008-09-11 | Nippon Telegr & Teleph Corp <Ntt> | Apparatus for analyzing set of documents, method for analyzing set of documents, program implementing this method, and recording medium storing this program |
| CN108615161A (en) * | 2018-04-20 | 2018-10-02 | 保定市中远邦泰电子科技有限公司 | Crops are traced to the source data system |
| CN113423018A (en) * | 2021-08-24 | 2021-09-21 | 腾讯科技（深圳）有限公司 | Game data processing method, device and storage medium |
| CN114066480A (en) * | 2021-11-08 | 2022-02-18 | 瀚云科技有限公司 | Method, device, system, equipment and storage medium for generating traceability information |
| CN114219512A (en) * | 2022-01-07 | 2022-03-22 | 瀚云科技有限公司 | Crop information pushing method and device, computer equipment and storage medium |
| CN115630967A (en) * | 2022-10-12 | 2023-01-20 | 中国建设银行股份有限公司 | Intelligent tracing method and device for agricultural products, electronic equipment and storage medium |
| CN115545678A (en) * | 2022-11-29 | 2022-12-30 | 浙江贵仁信息科技股份有限公司 | Water quality monitoring method based on water environment portrait and pollutant traceability |
| CN116011331A (en) * | 2022-12-30 | 2023-04-25 | 中国农业大学烟台研究院 | Irrigation decision method and device based on Internet of things |
Non-Patent Citations (1)
| Title |
|---|
| 基于多视角聚类模型的微博文本数据挖掘算法研究;陈兰兰;胡细玲;;科技通报;20171130(11);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116757707A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170161560A1 (en) | System and method for harvest yield prediction | |
| CN110110595B (en) | Farmland image and medicine hypertrophy data analysis method based on satellite remote sensing image | |
| CA2663917C (en) | Variable zone crop-specific inputs prescription method and systems therefor | |
| CN111369093B (en) | Irrigation method and device based on machine learning | |
| CN111767802A (en) | Method and device for detecting abnormal state of object | |
| CN116757707B (en) | Crop fruit growth tracing method and system | |
| Ahmad et al. | A review of best management practices for potato crop using precision agricultural technologies | |
| CN112116206A (en) | Intelligent agricultural system based on big data | |
| CN113297925A (en) | Intelligent early warning method and system for quality of full chain of fruits and vegetables | |
| CN116300608A (en) | Intelligent agriculture remote monitoring system based on big data | |
| CN112215522A (en) | Crop growth monitoring system, method, computer equipment and storage medium | |
| Singla et al. | IoT based monitoring for the growth of basil using machine learning | |
| CN117033810B (en) | Agricultural data analysis management system and method based on big data | |
| CN117455062A (en) | Crop yield prediction algorithm based on multi-source heterogeneous agricultural data | |
| Jain et al. | Agriculture assistant for crop prediction and farming selection using machine learning model with real-time data using imaging through uav drone | |
| Sudhakar et al. | Computer Vision Based Machine Learning and Deep Learning Approaches for Identification of Nutrient Deficiency in Crops: A Survey. | |
| Prasad et al. | System model for smart precision farming for high crop yielding | |
| CN111008815A (en) | Real-time intelligent acquisition system and method for agricultural planting resource information | |
| CN116046687A (en) | Crop growth process monitoring method, device and medium | |
| CN114219512A (en) | Crop information pushing method and device, computer equipment and storage medium | |
| Sukojo et al. | Rice growth stages mapping with Normalized Difference Vegetation Index (NDVI) algorithm using sentinel-2 time series satellite imagery | |
| CN112235348A (en) | Multi-element big data acquisition and transmission platform based on 5G technology | |
| Sreethi et al. | Interplanetary file system protocol–based blockchain framework for routine data and security management in smart farming | |
| Rai et al. | Application of machine learning in agriculture with some examples | |
| Manfrini et al. | Development of precision apple fruit growing techniques: monitoring strategies for yield and high-quality fruit production |
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 |