Digitalized tracing method and system for agricultural product supply chain information

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a digital traceability method and system for agricultural product supply chain information, and the method comprises the steps: carrying out the abnormality recognition based on authenticity and rationality of picking and processing registration data according to weather change information data, obtaining a first abnormality recognition result, and obtaining a second abnormality recognition result according to a regional picking and processing data set; performing anomaly analysis based on a clustering algorithm on the picking processing registration data to obtain a second anomaly recognition result; performing weighted calculation on the first anomaly identification result and the second anomaly identification result to obtain an anomaly risk tag; performing growth state prediction based on the target agricultural product on the crop growth environment data to obtain a growth state label; and chaining the target agricultural product, the target agricultural area, the picking processing registration data, the abnormal risk tag and the growth state tag to obtain an agricultural product supply chain information flow chart. The source tracing depth of source data in agricultural product supply chain information can be increased, and the reliability of an agricultural product supply chain is further improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a digital traceability method and system for agricultural product supply chain information. Background Art

[0002] As people's living standards continue to improve, the public's requirements for the quality of agricultural products are gradually increasing. The quality of agricultural products has become the primary consideration for consumers, but consumers and buyers cannot truly and effectively monitor the entire process of agricultural products. It just so happens that at this time, digitalization, intelligence, big data and other technologies are also developing rapidly. In order to respond to the needs of consumers, more and more agricultural products have begun to integrate digital technology into their own industries, and agricultural product supply chain information has been generated.

[0003] Today's agricultural product supply chain information is protected by science and technology, and can meet the transparency and immutability of agricultural product data. However, due to the low level of scientific and technological acceptance of agricultural product growers, too many scientific and technological processes will increase the burden on growers, making the initial production data in the agricultural product supply chain the crop's origin mark plus some certification marks, and unable to more clearly understand the growth, picking, drying and processing of crops. Once the source of agricultural products is wrong, even if the subsequent reprocessing, transportation and sales are strictly and clearly controlled, consumers will still buy unqualified or defective products, thereby damaging the reputation of an agricultural product brand or regional characteristics. Summary of the invention

[0004] The present invention provides a digital traceability method for agricultural product supply chain information, the main purpose of which is to increase the traceability depth of source data in the agricultural product supply chain information and further improve the reliability of the agricultural product supply chain.

[0005] To achieve the above-mentioned purpose, the present invention provides a digital traceability method for agricultural product supply chain information, comprising: Receiving the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and performing an origin authentication operation on the picking and processing registration data to obtain an origin authentication result; When the origin authentication result is authentication passed, the target agricultural area is obtained, and the picking and processing registration data is stored in a pre-built data verification database, and the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data are obtained; Acquire the crop growth environment data of the target agricultural area within the growth stage date, and acquire the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence from a pre-constructed agricultural environment monitoring database; Using the data verification database, all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area are obtained to obtain a regional picking and processing data set; Using the pre-trained abnormal data authentication model, according to the weather change information data, the picking and processing registration data is subjected to abnormality identification based on authenticity and rationality to obtain a first abnormal identification result; according to the regional picking and processing data set, the picking and processing registration data is subjected to abnormality analysis based on a clustering algorithm to obtain a second abnormal identification result; Performing weighted calculation on the first anomaly recognition result and the second anomaly recognition result to obtain an anomaly risk label; Predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label; The target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels are used to construct supply chain source data, and the supply chain source data is uploaded to a pre-built agricultural product supply chain system to obtain an agricultural product supply chain information flow chart.

[0006] Optionally, the performing of an origin-based authentication operation on the picking and processing registration data includes: Obtaining the sender information of the picking and processing registration data, and using a pre-built registration database to verify the sender information to obtain an information authentication result; When the information authentication result is passed, obtaining the registered planting area corresponding to the sender information; According to the registered planting area, the picking and processing registration data is subjected to a quantity- and region-based origin authentication operation to obtain an origin authentication result.

[0007] Optionally, the abnormality identification of the harvesting and processing registration data based on authenticity and rationality is performed according to the weather change information data to obtain a first abnormality identification result, including: Performing a weather feature extraction operation on the weather change information data to obtain a real weather feature sequence set; Performing a weather feature extraction operation on the harvesting and processing registration data to obtain a set of registered weather feature sequences; According to the real weather feature sequence set, the registered weather feature sequence set is authenticated to obtain a weather anomaly percentage; Performing a feature extraction operation based on the execution action on the picking and processing registration data to obtain an execution action feature sequence set; According to the pre-built crop production management guide and the real weather feature sequence set, the rationality of the execution action feature sequence set is judged to obtain the action abnormality percentage; The action abnormality percentage and the weather abnormality percentage are weightedly calculated to obtain a first abnormality recognition result.

[0008] Optionally, performing an abnormality analysis based on a clustering algorithm on the picking and processing registration data according to the regional picking and processing data set to obtain a second abnormality identification result includes: Use pre-built indicator sets to build a multi-dimensional indicator space; Performing a mapping operation based on the multidimensional index space on the regional picking and processing data set to obtain a regional picking and processing cluster; Identify the cluster center coordinate points of each preset indicator in the indicator set in the picking and processing cluster in the area to obtain an indicator center point set; The deviations of each preset indicator between the indicator center point set and the picking and processing registration data are calculated to obtain a second abnormality recognition result.

[0009] Optionally, performing weighted calculation on the first abnormality recognition result and the second abnormality recognition result to obtain an abnormality risk label includes: Calculating the mean of the deviations of the preset indicators in the second abnormality identification result to obtain an indicator abnormality score; Performing weighted calculation on the indicator abnormality score and the first abnormality identification result to obtain an abnormality risk score; The pre-constructed risk classification interval is used to query the abnormal risk level corresponding to the abnormal risk score, and the abnormal risk level is used to construct an abnormal risk label.

[0010] Optionally, the predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label includes: Acquiring crop physiological knowledge data of the target agricultural product, and performing a text feature recognition operation on the crop physiological knowledge data to obtain a text segmentation vector set; Performing a semantic recognition operation on the text word segmentation vector set to obtain a semantic recognition result; Performing an environmental feature extraction operation on the crop growth environment data to obtain an environmental indicator set and an environmental numerical feature set, wherein the environmental numerical feature set includes numerical change features corresponding to each environmental indicator in the environmental indicator set; Performing a correlation analysis on the semantic recognition result based on the environmental indicator set to obtain growth correlation features of each environmental indicator in the environmental indicator set for the target agricultural product, and summarizing each growth correlation feature to obtain a growth correlation feature set; According to the environmental numerical feature set, weight configuration is performed on the growth-related feature set to obtain a growth-influencing feature set, and a full-connection recognition operation based on the growth state of the crop is performed on the growth-influencing feature set to obtain a growth state recognition result; The growth status identification result is configured as a growth status label.

[0011] Optionally, the step of uploading the supply chain source data to a pre-built agricultural product supply chain system includes: Performing a sensitive word recognition operation on the supply chain source data to obtain sensitive data, and encrypting the sensitive data in the supply chain source data using a pre-built first key to obtain partially encrypted source data; Using a pre-built hash algorithm, generating a unique hash value for the locally encrypted source data; Generate a digital signature for the unique hash value using a pre-built private key; Obtain a timestamp, and package the unique hash value, digital signature, and timestamp to obtain a data packet; The data packet is chained using a pre-built public chain, and the first key is chained using a pre-built consortium chain.

[0012] Optionally, before uploading the supply chain source data to a pre-built agricultural product supply chain system, the method further includes: Determining whether the abnormal risk label is higher than or equal to a preset unqualified level; When the abnormal risk tag is higher than or equal to the unqualified level, sending the supply chain source data to a pre-built agricultural product quality supervision database; When the abnormal risk label is less than the unqualified level, the step of uploading the supply chain source data to the pre-built agricultural product supply chain system is performed.

[0013] Optionally, the receiving of the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal includes: Perform data cleaning operations based on duplication, missing values ​​and abnormal values ​​on the initialized picking and processing registration data to obtain cleaned data; The cleaning data is formatted based on unit, text format and field standardization to obtain standardized picking and processing registration data.

[0014] To achieve the above-mentioned purpose, the present invention also provides a digital traceability system for agricultural product supply chain information, comprising: The agricultural product data acquisition module is used to receive the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and perform an origin authentication operation on the picking and processing registration data to obtain an origin authentication result, and when the origin authentication result is authentication passed, obtain the target agricultural area, and store the picking and processing registration data in a pre-built data verification database, and obtain the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data; The authentication data acquisition module is used to obtain the crop growth environment data of the target agricultural area within the growth stage date from the pre-constructed agricultural environment monitoring database, and obtain the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence, and use the data verification database to obtain all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area to obtain a regional picking and processing data set; An abnormality identification module is used to use a pre-trained abnormality data authentication model to perform abnormality identification based on authenticity and rationality on the picking and processing registration data according to the weather change information data to obtain a first abnormality identification result, perform abnormality analysis based on a clustering algorithm on the picking and processing registration data according to the regional picking and processing data set to obtain a second abnormality identification result, perform weighted calculation on the first abnormality identification result and the second abnormality identification result to obtain an abnormal risk label, and perform a growth state prediction on the crop growth environment data based on the growth state of the target agricultural product to obtain a growth state label; The source data chain module is used to construct the supply chain source data using the target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels, and chain the supply chain source data to the pre-built agricultural product supply chain system to obtain the agricultural product supply chain information flow chart.

[0015] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: A memory storing at least one instruction; The processor executes the instructions stored in the memory to implement the digital traceability method of agricultural product supply chain information described above.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned digital traceability method for agricultural product supply chain information.

[0017] The present invention is to solve the problem described in the background technology. The present invention analyzes the source data of the agricultural product supply chain for abnormality, and ensures that the supply chain improves reliability from the source. First, the picking and processing registration data of the target agricultural product sent by the agricultural product user end is obtained, wherein the agricultural product user end can be a farmer's mobile phone app. The farmer automatically obtains the timestamp by clicking a few buttons, and automatically edits the picking and processing registration data, so as to maximize the acquisition of agricultural product production processes such as harvesting, processing, and drying of crops without increasing the burden on farmers; further, the data itself is compared with the real environment through the pre-trained abnormal data authentication model, and the data is compared with the collective data to perform abnormality analysis, and abnormal risk labels are obtained to ensure the accuracy of the picking and processing registration data; in addition, the overall growth state of the target agricultural product in the target agricultural area can be identified according to the real environment data of the crop growth environment data, and the growth state label is obtained, so as to analyze the quality of the target agricultural product from the two aspects of the overall region and the individual farmers, so as to store it on the chain. Therefore, the present invention can increase the traceability depth of the source data in the agricultural product supply chain information, and further improve the reliability of the agricultural product supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of a digital traceability method for agricultural product supply chain information provided by an embodiment of the present invention; Figure 2 A functional module diagram of a digital traceability system for agricultural product supply chain information provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the digital traceability method for agricultural product supply chain information provided by an embodiment of the present invention.

[0019] Description of figure markings: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides a digital traceability method for agricultural product supply chain information. The execution subject of the digital traceability method for agricultural product supply chain information includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the digital traceability method for agricultural product supply chain information can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1 FIG. 1 is a flow chart of a digital traceability method for agricultural product supply chain information provided by an embodiment of the present invention. In this embodiment, the digital traceability method for agricultural product supply chain information includes: S1. Receive the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and perform an origin authentication operation on the picking and processing registration data to obtain an origin authentication result.

[0024] In an embodiment of the present invention, the agricultural product user terminal can be a farmer's mobile phone app, or an intelligent customer service. Farmers register agricultural product production nodes such as harvesting, processing, and drying by clicking or voice, so that the mobile phone app automatically obtains relevant information such as timestamps for editing to obtain picking and processing registration data.

[0025] In addition, in an embodiment of the present invention, a management platform of the digital traceability system of the agricultural product supply chain information will establish a connection with the agricultural product user terminal, and will be responsible for supervising and managing the farmers' picking and processing registration data and uploading it to the chain.

[0026] Among them, the target agricultural products can be various agricultural products such as tea, tangerine peel, and fruit.

[0027] Specifically, in the embodiment of the present invention, a geographical indication product in the south, such as tangerine peel, is used as an example to illustrate the target agricultural product. The picking and processing registration data may include [A batch of tangerine peel: "22 years: tangerine picking: 11.20~12.10 (may be continuous or discontinuous data), tangerine peel processing: 11.23~12.13, dried peel drying: 11.24~12.20"; "23 years: 3.1 and 9.1 drying"; "24 years: 3.1 and 9.1 drying"].

[0028] In detail, in the embodiment of the present invention, the receiving of the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal includes: Perform data cleaning operations based on duplication, missing values ​​and abnormal values ​​on the initialized picking and processing registration data to obtain cleaned data; The cleaning data is formatted based on unit, text format and field standardization to obtain standardized picking and processing registration data.

[0029] Specifically, in an embodiment of the present invention, the data cleaning refers to the operation of removing duplicate data, empty values, invalid fields (such as extra characters, missing fields, etc.) and abnormal values ​​in the picking and processing registration data, for example, the "harvest time" cannot be later than the "processing time", such as whether the yield matches the land area.

[0030] The data formatting process refers to unifying the format of the data, for example, the temperature unit is unified as ℃, and the date is unified as "ABC (year.month.day)".

[0031] Specifically, in the embodiment of the present invention, data cleaning and data formatting can be performed according to tools such as Excel, Pandas library, ETL tools and BI tools to obtain usable picking and processing registration data.

[0032] In detail, in the embodiment of the present invention, the operation of performing origin authentication on the picking and processing registration data includes: Obtaining the sender information of the picking and processing registration data, and using a pre-built registration database to verify the sender information to obtain an information authentication result; When the information authentication result is passed, obtaining the registered planting area corresponding to the sender information; According to the registered planting area, the picking and processing registration data is subjected to a quantity- and region-based origin authentication operation to obtain an origin authentication result.

[0033] The sender information may include a specific farmer, a village collective or a cooperative.

[0034] The registration database is a database used to manage information on farmer objects, which may include sensitive information such as name, gender, address, mobile phone number, registered planting area, etc.

[0035] In the embodiment of the present invention, when the management platform receives the picking and processing registration data, it will confirm the source of the picking and processing registration data to ensure that the picking and processing registration data is sent by the farmers registered in the management platform.

[0036] Specifically, in the embodiment of the present invention, information authentication is performed through a database query operation. If it can be queried that the user is a farmer, the authentication is passed. Otherwise, if the user identity information is only the transporter of agricultural products, the authentication fails. Then a secondary authentication is performed to check whether the planting area in the picking and processing registration data is the registered planting area. If the secondary authentication is passed, the authentication result of the origin of the target agricultural product is configured as passed.

[0037] S2. When the origin authentication result is passed, the target agricultural area is obtained, and the picking and processing registration data is stored in a pre-constructed data verification database, and the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data are obtained.

[0038] The target agricultural area may be a land area contracted by a farmer, village or cooperative, and the area may be in units of mu or hectare.

[0039] When the target agricultural area is registered in the management platform, the management platform can obtain weather information from the regional government and other organizations to monitor the climate level of the target agricultural area. In addition, sensors can be distributed to the target agricultural area according to the size of the target agricultural area to monitor the temperature, humidity, soil nutrients, etc. of the target agricultural area in real time.

[0040] Among them, the data verification database refers to the location where the picking and processing registration data is stored before it is uploaded to the chain, which is used to analyze the abnormality of the picking and processing registration data, so as to avoid false and erroneous picking and processing registration data from being uploaded to the chain, resulting in false information in the entire agricultural product supply chain.

[0041] Specifically, in an embodiment of the present invention, the weather conditions of [22: 11.20~12.10, 11.23~12.13, 11.24~12.20; 23: 3.1 and 9.1; 24: 3.1 and 9.1] are obtained from government agencies through a pre-built data interface to obtain the growing stage dates [22.3.1~22.11.20], the picking date sequence [22.11.20~22.12.10] and the processing date sequence [22.11.23~22.12.13, 22.11.24~22.12.20, 23.3.1, 23.9.1, ...]

[0042] S3. Obtain the crop growth environment data of the target agricultural area within the growth stage dates, and obtain the weather change information data of the target agricultural area within the picking date sequence and processing date sequence from a pre-constructed agricultural environment monitoring database.

[0043] Among them, the agricultural environment monitoring database is used to receive data collected by various sensors in the target agricultural area, such as temperature, humidity, soil nutrients, etc., as well as weather data provided by relevant government departments, such as temperature, wind speed, light intensity and precipitation, etc.

[0044] Specifically, in an embodiment of the present invention, the crop growth environment data of the target agricultural area within the growth stage date is obtained, and the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence is obtained. Among them, the crop growth environment data is data provided by both the government and the sensor, and more detailed data is conducive to understanding the specific growth status of crops in the target agricultural area. The weather change information data within the picking date sequence and the processing date sequence can be obtained through the weather information data provided by the government because it no longer relies on field data.

[0045] S4. Utilize the data verification database to obtain all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area, and obtain a regional picking and processing data set.

[0046] In the embodiment of the present invention, each agricultural area will store the picking and processing registration data in the data verification database. In order to compare the differences between the picking and processing registration data of the target agricultural area and other agricultural areas, the present invention obtains all the picking and processing registration data sent by each agricultural product user end to obtain a regional picking and processing data set.

[0047] S5. Using the pre-trained abnormality data authentication model, according to the weather change information data, perform abnormality identification on the picking and processing registration data based on authenticity and rationality to obtain a first abnormality identification result; according to the regional picking and processing data set, perform abnormality analysis on the picking and processing registration data based on a clustering algorithm to obtain a second abnormality identification result.

[0048] The abnormal data authentication model is a multi-task model based on neural networks, which is used to identify abnormalities in the harvesting and processing registration data from two aspects: "the authenticity of the data itself" and "the difference between the data itself and the group", and then summarize the output. The training process is completed by machine learning of a large number of manually labeled training samples using the cross entropy loss algorithm and the gradient descent algorithm.

[0049] In detail, in the embodiment of the present invention, the abnormality identification based on authenticity and rationality of the picking and processing registration data is performed according to the weather change information data to obtain a first abnormality identification result, including: Performing a weather feature extraction operation on the weather change information data to obtain a real weather feature sequence set; Performing a weather feature extraction operation on the harvesting and processing registration data to obtain a set of registered weather feature sequences; According to the real weather feature sequence set, the registered weather feature sequence set is authenticated to obtain a weather anomaly percentage; Performing a feature extraction operation based on the execution action on the picking and processing registration data to obtain an execution action feature sequence set; According to the pre-built crop production management guide and the real weather feature sequence set, the rationality of the execution action feature sequence set is judged to obtain the action abnormality percentage; The action abnormality percentage and the weather abnormality percentage are weightedly calculated to obtain a first abnormality recognition result.

[0050] The weather feature extraction operation refers to the operation of extracting only the temperature, wind speed, light, weather type and other information in the text using a pre-built convolution kernel layer.

[0051] The feature extraction operation based on the execution action refers to an operation that only extracts features related to the execution action in the text and ignores other features. In the embodiment of the present invention, the execution actions include picking, peeling, washing, and drying.

[0052] Among them, the crop production management guide is a manual for regional governments or agricultural institutions to conduct quality control on certain agricultural products. It is used to guide farmers to plant and manage crops through standardized guidance to improve crop quality, thereby driving regional development or influence.

[0053] Specifically, in the embodiment of the present invention, the authenticity of the registered weather feature sequence set is authenticated according to the real weather feature sequence set to obtain the weather anomaly percentage. For example, when the harvesting and processing registration data records a certain day as sunny, but the weather change information data of the target planting area provided by the government is rainy, this group of data can be marked as abnormal data, and the weather anomaly percentage can be obtained by sorting out the proportion of abnormal data in the harvesting and processing registration data.

[0054] Specifically, in the embodiment of the present invention, the rationality judgment refers to whether some actions in the picking and processing registration data meet many management requirements indicated in the crop production management guide. For example, the first long-term drying of tangerine peel can be done on sunny or cloudy days, and the subsequent drying needs to be done twice a year, both on sunny days. If the picking and processing registration data shows that tangerine peel is dried in the rain, or has not been dried for many years, it can be judged to be unreasonable.

[0055] After the action abnormality percentage and the weather abnormality percentage are obtained, a weighted calculation may be performed, for example, the action abnormality percentage weight is 0.7, and the weather abnormality percentage is 0.3, to obtain a first abnormality recognition result.

[0056] Furthermore, the abnormal data authentication model can be used to perform a second abnormality identification.

[0057] In detail, in the embodiment of the present invention, the abnormality analysis of the picking and processing registration data based on the regional picking and processing data set is performed based on a clustering algorithm to obtain a second abnormality identification result, including: Use pre-built indicator sets to build a multi-dimensional indicator space; Performing a mapping operation based on the multidimensional index space on the regional picking and processing data set to obtain a regional picking and processing cluster; Identify the cluster center coordinate points of each preset indicator in the indicator set in the picking and processing cluster in the area to obtain an indicator center point set; The deviations of each preset indicator between the indicator center point set and the picking and processing registration data are calculated to obtain a second abnormality recognition result.

[0058] The indicator set includes various preset indicators such as picking, processing, and drying.

[0059] The multidimensional indicator space includes various preset indicators such as picking, processing, and drying, as well as a time indicator.

[0060] Specifically, in the embodiment of the present invention, when the picking date sequences corresponding to all persons, such as [22.11.20~22.12.10] and the processing date sequences, such as [22.11.23~22.12.13, 22.11.24~22.12.20, 23.3.1, 23.9.1, ...] are mapped to the multidimensional indicator space, the regional picking and processing clusters are obtained.

[0061] It should be known that even with a crop production management guide, the overall production process will deviate from the crop production management guide due to various factors such as weather conditions, labor allocation, and the degree of advancement of production machinery, and it is more for reference.

[0062] In the embodiment of the present invention, the index center point set is obtained by clustering the center coordinate points, and then the deviation of each preset index between the index center point set and the picking and processing registration data is calculated to obtain the second abnormality identification result. For example, if the drying dates in the index center point set are all [11.14~11.16, 11.18~12.10], it can be indicated that [11.17] may have windy and rainy weather that is not conducive to drying. If the picking and processing registration data of a farmer shows that [11.14~12.10] are all drying, then the farmer may have a problem of lax drying management, and the score of the second abnormality identification result is higher.

[0063] S6. Perform weighted calculation on the first abnormality recognition result and the second abnormality recognition result to obtain an abnormality risk label.

[0064] In detail, in the embodiment of the present invention, the weighted calculation of the first abnormality recognition result and the second abnormality recognition result to obtain the abnormality risk label includes: Calculating the mean of the deviations of the preset indicators in the second abnormality identification result to obtain an indicator abnormality score; Performing weighted calculation on the indicator abnormality score and the first abnormality identification result to obtain an abnormality risk score; The pre-constructed risk classification interval is used to query the abnormal risk level corresponding to the abnormal risk score, and the abnormal risk level is used to construct an abnormal risk label.

[0065] Among them, the risk classification interval refers to the interval divided by the management platform based on calculations and actual inspections, for example, 0~3 is a safe interval, 3~5 is a slight risk interval, and greater than 5 is a high risk interval.

[0066] Specifically, in the embodiment of the present invention, the second abnormality recognition result has abnormality recognition scores of multiple indicators. By summing and averaging the abnormality recognition scores, the overall indicator abnormality score can be obtained. Then, a weighted calculation is performed with the first abnormality recognition result, for example, the weight of the first abnormality recognition result is 0.4, and the weight of the second abnormality recognition result is 0.6, to obtain the abnormality risk score.

[0067] The abnormal risk score is then compared with the risk classification interval to obtain the abnormal risk level, and then the abnormal risk label is constructed. Among them, the slight risk interval of the present invention may be problems such as early or late harvesting, short or long drying time, etc., while the high-risk interval may have problems such as improper management and data falsification.

[0068] S7. Predicting the growth status of the target agricultural product based on the crop growth environment data to obtain a growth status label.

[0069] In detail, in the embodiment of the present invention, the step of predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label includes: Acquiring crop physiological knowledge data of the target agricultural product, and performing a text feature recognition operation on the crop physiological knowledge data to obtain a text segmentation vector set; Performing a semantic recognition operation on the text word segmentation vector set to obtain a semantic recognition result; Performing an environmental feature extraction operation on the crop growth environment data to obtain an environmental indicator set and an environmental numerical feature set, wherein the environmental numerical feature set includes numerical change features corresponding to each environmental indicator in the environmental indicator set; Performing a correlation analysis on the semantic recognition result based on the environmental indicator set to obtain growth correlation features of each environmental indicator in the environmental indicator set for the target agricultural product, and summarizing each growth correlation feature to obtain a growth correlation feature set; According to the environmental numerical feature set, weight configuration is performed on the growth-related feature set to obtain a growth-influencing feature set, and a full-connection recognition operation based on the growth state of the crop is performed on the growth-influencing feature set to obtain a growth state recognition result; The growth status identification result is configured as a growth status label.

[0070] The crop physiological knowledge data can be obtained from online information, surveys and research, or agricultural platform databases.

[0071] The semantic recognition operation refers to converting text characters into data that can be understood by a machine model, which can be achieved through a neural network speech model such as Bert.

[0072] Since different varieties of target agricultural products may lead to different growth habits of crops, it is necessary to obtain crop physiological knowledge data before predicting the growth status of crops. In the embodiment of the present invention, the crop physiological knowledge data is mostly text data, so it is necessary to perform text segmentation quantization on the crop physiological knowledge data to obtain a text segmentation vector set, and then perform semantic analysis to obtain a semantic recognition result.

[0073] In addition, since different environmental factors have different degrees of influence on crops, the crop growth environment data in the embodiment of the present invention only monitors some environmental factors. Therefore, only the environmental indicator set in the crop growth environment data is considered.

[0074] Specifically, in the embodiment of the present invention, through correlation analysis, the growth correlation characteristics of each environmental indicator in the environmental indicator set for the target agricultural product are obtained, and the various growth correlation characteristics are summarized to obtain a growth correlation characteristic set.

[0075] For example, a certain citrus variety requires a warm and humid climate. Temperature, light and precipitation are closely related to citrus growth, and soil organic matter requires a slightly acidic state. Therefore, by identifying whether each value in the growth-affecting feature set has a gap with the expected index in terms of temperature, light, precipitation, and soil acidity and alkalinity, the larger the gap, the worse the growth state.

[0076] Finally, a growth state label is constructed based on the growth state recognition results obtained. Among them, the neural network for predicting the growth state can learn the knowledge of the impact of the difference of various indicators on crop growth through machine learning.

[0077] S8. Use the target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels to construct supply chain source data, and upload the supply chain source data to a pre-built agricultural product supply chain system to obtain an agricultural product supply chain information flow chart.

[0078] In detail, in an embodiment of the present invention, the process of uploading the supply chain source data to a pre-built agricultural product supply chain system includes: Performing a sensitive word recognition operation on the supply chain source data to obtain sensitive data, and encrypting the sensitive data in the supply chain source data using a pre-built first key to obtain partially encrypted source data; Using a pre-built hash algorithm, generating a unique hash value for the locally encrypted source data; Generate a digital signature for the unique hash value using a pre-built private key; Obtain a timestamp, and package the unique hash value, digital signature, and timestamp to obtain a data packet; The data packet is chained using a pre-built public chain, and the first key is chained using a pre-built consortium chain.

[0079] Among them, the sensitive word identification refers to the identification of data that infringes on the privacy of farmers, such as address, telephone number, etc.

[0080] The hash algorithm refers to a cryptographic algorithm whose basic function is to perform mathematical operations on input data (which can be of any length) to generate an output value of a fixed length (usually a short number or string). This output value is called a hash value.

[0081] The private key is a cryptographic tool used to sign the hash value of a message or data to ensure that only the person holding the private key can generate the corresponding digital signature.

[0082] The digital signature is an electronic authentication method based on cryptography technology, which is mainly used to verify the authenticity, integrity and identity of the sender of digital information.

[0083] The timestamp refers to a data mark used to record the precise time information of a specific event when it occurs. The timestamp is usually expressed in the form of date and time, including year, month, day, hour, minute, and second.

[0084] The public chain refers to a blockchain network that anyone can participate in, which is completely open and decentralized. It allows all users to freely read, send transactions and participate in the consensus process.

[0085] The consortium chain is a blockchain network jointly maintained by a specific alliance of organizations. Participants need to be authorized, and only authorized nodes can join the network and participate in data writing and consensus processes.

[0086] Specifically, in the embodiment of the present invention, the sensitive data is encrypted by a first key, and then packaged according to the unique hash value, digital signature and timestamp described above to obtain a data packet. Then consumers or other users can decrypt and view the non-sensitive data in the supply chain source data by scanning a QR code, and other farmers or docking companies participating in the alliance chain can view the information in the sensitive data to facilitate contact.

[0087] In detail, in an embodiment of the present invention, before uploading the supply chain source data to a pre-built agricultural product supply chain system, the method further includes: Determining whether the abnormal risk label is higher than or equal to a preset unqualified level; When the abnormal risk tag is higher than or equal to the unqualified level, sending the supply chain source data to a pre-built agricultural product quality supervision database; When the abnormal risk label is less than the unqualified level, the step of uploading the supply chain source data to the pre-built agricultural product supply chain system is performed.

[0088] The unqualified level may be set as a high risk level.

[0089] Among them, the agricultural product quality supervision database is a kind of data used to store relevant data of target agricultural areas with unclear quality. Professional assessors can conduct on-site product inspections on the target agricultural areas based on the agricultural product quality supervision database. If qualified, they can be added to the chain. If unqualified, the problem may be solved by not granting brand marks for sale, or introducing insurance compensation, etc.

[0090] In an embodiment of the present invention, when the abnormal risk label is higher than or equal to a preset unqualified level, there may be product quality problems, which may cause damage to the product brand. Therefore, the supply chain source data can be first saved in the agricultural product quality supervision database and wait for subsequent processing.

[0091] Furthermore, in the embodiment of the present invention, the management platform is responsible for managing the data supervision chain part of the agricultural product end, and other agricultural product supply chain information will be aggregated to the pre-built agricultural product supply chain through other channels. The agricultural product supply chain system in the blockchain has high automation and transparency. When the supply chain source data of the present invention is uploaded to the agricultural product supply chain system, the agricultural product supply chain system will expand the original agricultural product supply chain information, thereby obtaining an agricultural product supply chain information flow chart with deeper traceability.

[0092] The present invention is to solve the problem described in the background technology. The present invention analyzes the source data of the agricultural product supply chain for abnormality, and ensures that the supply chain improves reliability from the source. First, the picking and processing registration data of the target agricultural product sent by the agricultural product user end is obtained, wherein the agricultural product user end can be a farmer's mobile phone app. The farmer automatically obtains the timestamp by clicking a few buttons, and automatically edits the picking and processing registration data, so as to maximize the acquisition of agricultural product production processes such as harvesting, processing, and drying of crops without increasing the burden on farmers; further, the data itself is compared with the real environment through the pre-trained abnormal data authentication model, and the data is compared with the collective data to perform abnormality analysis, and abnormal risk labels are obtained to ensure the accuracy of the picking and processing registration data; in addition, the overall growth state of the target agricultural product in the target agricultural area can be identified according to the real environment data of the crop growth environment data, and the growth state label is obtained, so as to analyze the quality of the target agricultural product from the two aspects of the overall region and the individual farmers, so as to store it on the chain. Therefore, the present invention can increase the traceability depth of the source data in the agricultural product supply chain information, and further improve the reliability of the agricultural product supply chain.

[0093] like Figure 2 , which is a functional module diagram of a digital traceability system for agricultural product supply chain information provided by an embodiment of the present invention.

[0094] The digital traceability system 100 for agricultural product supply chain information of the present invention can be installed in an electronic device. According to the functions implemented, the digital traceability system 100 for agricultural product supply chain information can include an agricultural product data acquisition module 101, an authentication data acquisition module 102, an abnormality identification module 103 and a source data uplink module 104. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0095] The agricultural product data acquisition module 101 is used to receive the picking and processing registration data of the target agricultural product sent by the pre-constructed agricultural product user terminal, and perform an origin authentication operation on the picking and processing registration data to obtain an origin authentication result, and when the origin authentication result is authentication passed, obtain the target agricultural area, and store the picking and processing registration data in a pre-constructed data verification database, and obtain the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data; The authentication data acquisition module 102 is used to obtain the crop growth environment data of the target agricultural area within the growth stage date from the pre-constructed agricultural environment monitoring database, and obtain the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence, and use the data verification database to obtain all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area to obtain a regional picking and processing data set; The abnormality identification module 103 is used to use the pre-trained abnormality data authentication model to perform abnormality identification on the picking and processing registration data based on authenticity and rationality according to the weather change information data to obtain a first abnormality identification result, perform abnormality analysis on the picking and processing registration data based on a clustering algorithm according to the regional picking and processing data set to obtain a second abnormality identification result, perform weighted calculation on the first abnormality identification result and the second abnormality identification result to obtain an abnormal risk label, and perform growth status prediction on the crop growth environment data based on the target agricultural product to obtain a growth status label; The source data uploading module 104 is used to construct supply chain source data using the target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels, and to upload the supply chain source data to a pre-built agricultural product supply chain system to obtain an agricultural product supply chain information flow chart.

[0096] In detail, each module in the digital traceability system 100 for agricultural product supply chain information in the embodiment of the present invention is used in the same manner as described above. Figure 1The digital traceability method of agricultural product supply chain information described in the present invention is the same technical means and can produce the same technical effects, so I will not go into details here.

[0097] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a digital traceability method for agricultural product supply chain information provided by an embodiment of the present invention.

[0098] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a digital traceability method program for agricultural product supply chain information.

[0099] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the digital traceability method program of the agricultural product supply chain information, but also can be used to temporarily store data that has been output or is to be output.

[0100] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a digital traceability method program for agricultural product supply chain information, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0101] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0102] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0103] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0104] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0105] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0106] The digital traceability method program of agricultural product supply chain information stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Receiving the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and performing an origin authentication operation on the picking and processing registration data to obtain an origin authentication result; When the origin authentication result is authentication passed, the target agricultural area is obtained, and the picking and processing registration data is stored in a pre-built data verification database, and the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data are obtained; Acquire the crop growth environment data of the target agricultural area within the growth stage date, and acquire the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence from a pre-constructed agricultural environment monitoring database; Using the data verification database, all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area are obtained to obtain a regional picking and processing data set; Using the pre-trained abnormal data authentication model, according to the weather change information data, the picking and processing registration data is subjected to abnormality identification based on authenticity and rationality to obtain a first abnormal identification result; according to the regional picking and processing data set, the picking and processing registration data is subjected to abnormality analysis based on a clustering algorithm to obtain a second abnormal identification result; Performing weighted calculation on the first anomaly recognition result and the second anomaly recognition result to obtain an anomaly risk label; Predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label; The target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels are used to construct supply chain source data, and the supply chain source data is uploaded to a pre-built agricultural product supply chain system to obtain an agricultural product supply chain information flow chart.

[0107] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0108] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0109] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement: Receiving the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and performing an origin authentication operation on the picking and processing registration data to obtain an origin authentication result; When the origin authentication result is authentication passed, the target agricultural area is obtained, and the picking and processing registration data is stored in a pre-built data verification database, and the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data are obtained; Acquire the crop growth environment data of the target agricultural area within the growth stage date, and acquire the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence from a pre-constructed agricultural environment monitoring database; Using the data verification database, all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area are obtained to obtain a regional picking and processing data set; Using the pre-trained abnormal data authentication model, according to the weather change information data, the picking and processing registration data is subjected to abnormality identification based on authenticity and rationality to obtain a first abnormal identification result; according to the regional picking and processing data set, the picking and processing registration data is subjected to abnormality analysis based on a clustering algorithm to obtain a second abnormal identification result; Performing weighted calculation on the first anomaly recognition result and the second anomaly recognition result to obtain an anomaly risk label; Predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label; The target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels are used to construct supply chain source data, and the supply chain source data is uploaded to a pre-built agricultural product supply chain system to obtain an agricultural product supply chain information flow chart.

[0110] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0111] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0113] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A digital traceability method for agricultural product supply chain information, characterized in that: The method comprises: Receiving the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and performing an origin authentication operation on the picking and processing registration data to obtain an origin authentication result; When the origin authentication result is authentication passed, the target agricultural area is obtained, and the picking and processing registration data is stored in a pre-built data verification database, and the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data are obtained; Acquire the crop growth environment data of the target agricultural area within the growth stage date, and acquire the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence from a pre-constructed agricultural environment monitoring database; Using the data verification database, all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area are obtained to obtain a regional picking and processing data set; Using the pre-trained abnormal data authentication model, according to the weather change information data, the picking and processing registration data is subjected to abnormality identification based on authenticity and rationality to obtain a first abnormal identification result; according to the regional picking and processing data set, the picking and processing registration data is subjected to abnormality analysis based on a clustering algorithm to obtain a second abnormal identification result; Performing weighted calculation on the first anomaly recognition result and the second anomaly recognition result to obtain an anomaly risk label; Predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label; The target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels are used to construct supply chain source data, and the supply chain source data is uploaded to a pre-built agricultural product supply chain system to obtain an agricultural product supply chain information flow chart.

2. The digital traceability method for agricultural product supply chain information according to claim 1, characterized in that: The performing of origin-based authentication operation on the picking and processing registration data includes: Obtaining the sender information of the picking and processing registration data, and using a pre-built registration database to verify the sender information to obtain an information authentication result; When the information authentication result is passed, obtaining the registered planting area corresponding to the sender information; According to the registered planting area, the picking and processing registration data is subjected to a quantity- and region-based origin authentication operation to obtain an origin authentication result.

3. The digital traceability method for agricultural product supply chain information according to claim 2, characterized in that: According to the weather change information data, the harvesting and processing registration data is subjected to abnormality identification based on authenticity and rationality to obtain a first abnormality identification result, including: Performing a weather feature extraction operation on the weather change information data to obtain a real weather feature sequence set; Performing a weather feature extraction operation on the harvesting and processing registration data to obtain a set of registered weather feature sequences; According to the real weather feature sequence set, the registered weather feature sequence set is authenticated to obtain a weather anomaly percentage; Performing a feature extraction operation based on the execution action on the picking and processing registration data to obtain an execution action feature sequence set; According to the pre-built crop production management guide and the real weather feature sequence set, the rationality of the execution action feature sequence set is judged to obtain the action abnormality percentage; The action abnormality percentage and the weather abnormality percentage are weightedly calculated to obtain a first abnormality recognition result.

4. The digital traceability method for agricultural product supply chain information according to claim 3, characterized in that: According to the regional picking and processing data set, performing abnormality analysis on the picking and processing registration data based on a clustering algorithm to obtain a second abnormality identification result includes: Use pre-built indicator sets to build a multi-dimensional indicator space; Performing a mapping operation based on the multidimensional index space on the regional picking and processing data set to obtain a regional picking and processing cluster; Identify the cluster center coordinate points of each preset indicator in the indicator set in the picking and processing cluster in the area to obtain an indicator center point set; The deviations of each preset indicator between the indicator center point set and the picking and processing registration data are calculated to obtain a second abnormality recognition result.

5. The digital traceability method for agricultural product supply chain information according to claim 4, characterized in that: The step of performing weighted calculation on the first abnormality recognition result and the second abnormality recognition result to obtain an abnormality risk label includes: Calculating the mean of the deviations of the preset indicators in the second abnormality identification result to obtain an indicator abnormality score; Performing weighted calculation on the indicator abnormality score and the first abnormality identification result to obtain an abnormality risk score; The pre-constructed risk classification interval is used to query the abnormal risk level corresponding to the abnormal risk score, and the abnormal risk level is used to construct an abnormal risk label.

6. The digital traceability method for agricultural product supply chain information according to claim 5, characterized in that: The step of predicting the growth state of the target agricultural product based on the crop growth environment data to obtain a growth state label includes: Acquiring crop physiological knowledge data of the target agricultural product, and performing a text feature recognition operation on the crop physiological knowledge data to obtain a text segmentation vector set; Performing a semantic recognition operation on the text word segmentation vector set to obtain a semantic recognition result; Performing an environmental feature extraction operation on the crop growth environment data to obtain an environmental indicator set and an environmental numerical feature set, wherein the environmental numerical feature set includes numerical change features corresponding to each environmental indicator in the environmental indicator set; Performing a correlation analysis on the semantic recognition result based on the environmental indicator set to obtain growth correlation features of each environmental indicator in the environmental indicator set for the target agricultural product, and summarizing each growth correlation feature to obtain a growth correlation feature set; According to the environmental numerical feature set, weight configuration is performed on the growth-related feature set to obtain a growth-influencing feature set, and a full-connection recognition operation based on the crop growth state is performed on the growth-influencing feature set to obtain a growth state recognition result; The growth status identification result is configured as a growth status label.

7. The digital traceability method for agricultural product supply chain information according to claim 6, characterized in that: The step of uploading the supply chain source data to a pre-built agricultural product supply chain system includes: Performing a sensitive word recognition operation on the supply chain source data to obtain sensitive data, and encrypting the sensitive data in the supply chain source data using a pre-built first key to obtain partially encrypted source data; Using a pre-built hash algorithm, generating a unique hash value for the locally encrypted source data; Generate a digital signature for the unique hash value using a pre-built private key; Obtain a timestamp, and package the unique hash value, digital signature, and timestamp to obtain a data packet; The data packet is chained using a pre-built public chain, and the first key is chained using a pre-built consortium chain.

8. The digital traceability method for agricultural product supply chain information according to claim 7, characterized in that: Before uploading the supply chain source data to the pre-built agricultural product supply chain system, the method further includes: Determining whether the abnormal risk label is higher than or equal to a preset unqualified level; When the abnormal risk tag is higher than or equal to the unqualified level, sending the supply chain source data to a pre-built agricultural product quality supervision database; When the abnormal risk label is less than the unqualified level, the step of uploading the supply chain source data to the pre-built agricultural product supply chain system is performed.

9. The digital traceability method for agricultural product supply chain information according to claim 8, characterized in that: The receiving of the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal includes: Perform data cleaning operations based on duplication, missing values ​​and abnormal values ​​on the initialized picking and processing registration data to obtain cleaned data; The cleaning data is formatted based on unit, text format and field standardization to obtain standardized picking and processing registration data.

10. A digital traceability system for agricultural product supply chain information, characterized in that: The system comprises: The agricultural product data acquisition module is used to receive the picking and processing registration data of the target agricultural product sent by the pre-built agricultural product user terminal, and perform an origin authentication operation on the picking and processing registration data to obtain an origin authentication result, and when the origin authentication result is authentication passed, obtain the target agricultural area, and store the picking and processing registration data in a pre-built data verification database, and obtain the growth stage date, picking date sequence and processing date sequence in the picking and processing registration data; The authentication data acquisition module is used to obtain the crop growth environment data of the target agricultural area within the growth stage date from the pre-constructed agricultural environment monitoring database, and obtain the weather change information data of the target agricultural area within the picking date sequence and the processing date sequence, and use the data verification database to obtain all the picking and processing registration data sent by each agricultural product user terminal in the target agricultural area to obtain a regional picking and processing data set; An abnormality identification module is used to use a pre-trained abnormality data authentication model to perform abnormality identification based on authenticity and rationality on the picking and processing registration data according to the weather change information data to obtain a first abnormality identification result, perform abnormality analysis based on a clustering algorithm on the picking and processing registration data according to the regional picking and processing data set to obtain a second abnormality identification result, perform weighted calculation on the first abnormality identification result and the second abnormality identification result to obtain an abnormal risk label, and perform a growth state prediction on the crop growth environment data based on the growth state of the target agricultural product to obtain a growth state label; The source data chain module is used to construct the supply chain source data using the target agricultural products, target agricultural areas, picking and processing registration data, abnormal risk labels and growth status labels, and chain the supply chain source data to the pre-built agricultural product supply chain system to obtain the agricultural product supply chain information flow chart.

Images