Ear tag number identification method and device, computer equipment and storage medium

Abstract

The invention provides an ear tag number identification method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining insured historical ear tag insurance data, and constructing a historical ear tag library according to the historical ear tag insurance data; grouping the plurality of historical ear tag features to obtain a plurality of ear tag groups and identification information corresponding to each ear tag group; generating a hash bucket corresponding to each ear tag group, adding a historical ear tag number corresponding to each historical ear tag feature in the ear tag group into the hash bucket corresponding to the ear tag group, and generating a Bloom filter according to the plurality of hash buckets after addition is completed; obtaining a to-be-identified ear tag number and ear tag features corresponding to the ear tag number, matching the ear tag features with the identification information corresponding to each hash bucket, and determining a target hash bucket corresponding to the ear tag number; and inputting the ear tag number into a Bloom filter, and performing streaming calculation on the ear tag number and each historical ear tag number in the target hash bucket by the Bloom filter to obtain a calculation result corresponding to the ear tag number, thereby completing identification of the ear tag number.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, which is applied to the financial field, and in particular to an ear tag number recognition method, device, computer equipment and storage medium. Background Art

[0002] In the field of financial insurance, for agricultural insurance objects with ear tags such as pigs, cattle, and sheep, when salesmen are carrying out underwriting operations, the usual practice in the industry is to collect the ear tag numbers of farmers' objects and upload them to the underwriting operation system. However, due to the disorder of ear tags in various places, it has always been a difficult problem in the field of agricultural insurance to identify objects with ear tags such as pigs, cattle, and sheep by ear tags. As a result, the ear tag method of biometric identification has gradually become a dead end. For insurance companies, how to identify the object through the existing physical identification of ear tags is of great significance for cost savings in the underwriting process and underwriting risk management.

[0003] Therefore, there is an urgent need for an ear tag number recognition method that can quickly and accurately identify whether the current ear tag number has been insured based on the insured ear tags. Summary of the invention

[0004] The present application provides an ear tag identification method, apparatus, computer equipment and storage medium, aiming to solve the problem of identifying objects with ear tags, such as pigs, cattle and sheep, by ear tags, which has always been a difficult problem in the field of agricultural insurance due to the disorder of ear tags in various places.

[0005] In a first aspect, the present application provides an ear tag number recognition method, comprising:

[0006] Acquire the historical ear tag insurance data of the insured, and construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes the historical ear tag number and the historical ear tag feature corresponding to the historical ear tag number;

[0007] Grouping the plurality of historical ear tag features to obtain a plurality of ear tag groups and identification information corresponding to each of the ear tag groups;

[0008] Generate a hash bucket corresponding to each ear tag group, wherein identification information of the hash bucket is identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter according to the multiple hash buckets that have been added;

[0009] Acquire the ear tag number to be identified and the ear tag feature corresponding to the ear tag number, match the ear tag feature with the identification information corresponding to each hash bucket, and determine the target hash bucket corresponding to the ear tag number;

[0010] The ear tag number is input into the Bloom filter, and the Bloom filter performs streaming calculation on the ear tag number and each of the historical ear tag numbers in the target hash bucket to obtain a calculation result corresponding to the ear tag number, and completes the identification of the ear tag number according to the calculation result.

[0011] In some embodiments, the obtaining of the ear tag number to be identified and the ear tag feature corresponding to the ear tag number includes: obtaining the insured ear tag number segment to be identified; obtaining multiple insured identifiers in a preset agricultural insurance database; matching each of the insured identifiers with the insured ear tag number segment to generate multiple insured marks in the insured ear tag number segment according to the successfully matched insured identifiers; splitting the insured ear tag number segment according to the insured marks to obtain multiple ear tag numbers; and generating the ear tag feature corresponding to the ear tag number according to the insured mark corresponding to the ear tag number.

[0012] In some embodiments, after completing the identification of the ear tag number according to the calculation result, it also includes: parsing the calculation result, obtaining the historical ear tag number corresponding to the ear tag number; obtaining multiple first associated ear tag numbers corresponding to the historical ear tag number; obtaining multiple second associated ear tag numbers corresponding to the ear tag number, matching the first associated ear tag number with the second associated ear tag number; if the first associated ear tag number fails to match the second associated ear tag number, generating a warning message.

[0013] Exemplarily, the matching of the first associated ear tag number with the second associated ear tag number includes: generating the distribution rule according to the order corresponding to the multiple first associated ear tag numbers and the first associated ear tag numbers; matching the multiple second associated ear tag numbers according to the distribution rule to determine that the matching of the first associated ear tag number with the second associated ear tag number fails when the second associated ear tag number does not conform to the distribution rule.

[0014] In some embodiments, the grouping of the multiple historical ear tag features to obtain multiple ear tag groups and identification information corresponding to each ear tag group includes: obtaining multiple insurance dimensions from a preset agricultural insurance database; generating an initial ear tag group corresponding to each insurance dimension; performing feature matching with each historical ear tag feature according to each insurance dimension; adding the successfully matched historical ear tag features to the initial ear tag group corresponding to the insurance dimension to obtain multiple ear tag groups; and using the insurance dimension corresponding to the ear tag group as the identification information.

[0015] In some embodiments, generating a Bloom filter based on the multiple hash buckets that have been added includes: obtaining an initial Bloom filter based on the multiple hash buckets; initializing the bit array of the initial Bloom filter to set all bits of the Bloom filter to 0; obtaining a hash value of each of the historical ear tag numbers in each of the hash buckets; and setting each of the hash values ​​in the initial Bloom filter to 1 in the bit array corresponding to the bit array to obtain the Bloom filter.

[0016] In some embodiments, constructing a historical ear tag library based on the historical ear tag insurance data includes: performing spark data cleaning on the historical ear tag data; wherein the spark data cleaning includes data deduplication, missing value processing, data conversion, outlier detection and data formatting; and constructing the historical ear tag library based on the cleaned historical ear tag data.

[0017] In a second aspect, the present application provides an ear tag number recognition device, comprising:

[0018] A data acquisition unit, used to acquire the historical ear tag insurance data of the insured, and to construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes the historical ear tag number and the historical ear tag feature corresponding to the historical ear tag number;

[0019] A feature grouping unit, used to group the plurality of historical ear tag features, and obtain a plurality of ear tag groups and identification information corresponding to each of the ear tag groups;

[0020] a Bloom generation unit, configured to generate a hash bucket corresponding to each ear tag group, wherein identification information of the hash bucket is identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter according to the multiple hash buckets that have been added;

[0021] a target determination unit, configured to obtain an ear tag number to be identified and an ear tag feature corresponding to the ear tag number, and determine a target hash bucket corresponding to the ear tag number by matching the ear tag feature with identification information corresponding to each hash bucket;

[0022] The identification completion unit is used to input the ear tag number into the Bloom filter, and the Bloom filter performs streaming calculations on the ear tag number and each of the historical ear tag numbers in the target hash bucket to obtain a calculation result corresponding to the ear tag number, and completes the identification of the ear tag number based on the calculation result.

[0023] In a third aspect, the present application further provides a computer device, including:

[0024] Memory and processor;

[0025] The memory is used to store computer programs;

[0026] The processor is used to execute the computer program and implement the steps of the ear tag number recognition method described in the first aspect when executing the computer program.

[0027] In a fourth aspect, the present application 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, the processor implements the steps of the ear tag number recognition method as described in the first aspect above.

[0028] The present application discloses an ear tag number recognition method, device, computer equipment and storage medium. By obtaining the insured historical ear tag insurance data, a historical ear tag library containing historical ear tag numbers and their corresponding features is constructed based on these data. The historical ear tag features are grouped to generate multiple ear tag groups, and corresponding identification information is assigned to each ear tag group. A hash bucket is generated for each ear tag group, and the identification information of the hash bucket is consistent with the identification information of the ear tag group. The ear tag number corresponding to each historical ear tag feature in the ear tag group is added to the corresponding hash bucket. A Bloom filter is generated based on these hash buckets. The ear tag number to be identified and its corresponding ear tag feature are obtained. The ear tag feature is matched with the identification information of each hash bucket to determine the target hash bucket corresponding to the ear tag number to be identified. The ear tag number to be identified is input into the Bloom filter, and each historical ear tag number in the target hash bucket is stream-calculated by the Bloom filter, and the ear tag number to be identified is identified based on the calculation result.

[0029] By utilizing the high efficiency of Bloom filters, streaming computing is used to speed up the ear tag number recognition process. At the same time, by grouping ear tag features and generating hash buckets, the accuracy of feature matching is improved and the possibility of mismatching is reduced. Then, the existing historical ear tag insurance data is fully utilized to build a historical ear tag library containing rich information to provide data support for the recognition process. Ear tag number data is managed by grouping and hash buckets, making ear tag number management more orderly and convenient. This method is suitable for the recognition of objects with ear tags, such as pigs, cattle, and sheep, and is especially suitable for the field of agricultural insurance.

[0030] In summary, the ear tag number recognition method provided by the researchers constructs a historical ear tag library, manages historical ear tag features in groups, and uses hash buckets and Bloom filters to achieve efficient and accurate ear tag number recognition. It provides a reliable technical means for the agricultural insurance field and solves the recognition problem caused by disordered ear tag numbers.

[0031] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 is a schematic flow chart of the steps of an ear tag number recognition method provided by an embodiment of the present application;

[0034] Figure 2 is a schematic flow chart of the steps of a Bloom filter generation method provided in an embodiment of the present application;

[0035] Figure 3 This is a schematic flow chart of the steps of a method for generating early warning information provided by an embodiment of the present application;

[0036] Figure 4 It is a schematic diagram of the structure of an ear tag number recognition device provided by an embodiment of the present application;

[0037] Figure 5 It is a schematic block diagram of the structure of a computer device provided in one embodiment of the present application.

[0038] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0040] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0041] It should be understood that, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the difference.

[0042] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0043] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0044] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0045] In the field of financial insurance, for agricultural insurance objects with ear tags such as pigs, cattle, and sheep, when salesmen are carrying out underwriting operations, the usual practice in the industry is to collect the ear tag numbers of farmers' objects and upload them to the underwriting operation system. However, due to the disorder of ear tags in various places, it has always been a difficult problem in the field of agricultural insurance to identify objects with ear tags such as pigs, cattle, and sheep by ear tags. As a result, the ear tag method of biometric identification has gradually become a dead end. For insurance companies, how to identify the object through the existing physical identification of ear tags is of great significance for cost savings in the underwriting process and underwriting risk management.

[0046] Therefore, there is an urgent need for an ear tag number recognition method that can quickly and accurately identify whether the current ear tag number has been insured based on the insured ear tags.

[0047] To solve the above problems, please refer to Figure 1 , Figure 1 1 is a schematic flow chart of an ear tag number recognition method provided by an embodiment of the present application. The ear tag number recognition method can be implemented by a computer device, and the computer device can be deployed on a single server or a server cluster. It can also be deployed on a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0048] To solve the above problems, please refer to Figure 1 Specifically, Figure 1 As shown, the provided ear tag number recognition method includes steps S101 to S105. The details are as follows:

[0049] Step S101. Obtain historical ear tag insurance data of insured persons, and construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes historical ear tag numbers and historical ear tag features corresponding to the historical ear tag numbers.

[0050] Specifically, by collecting and building a database containing historical ear tag numbers and their corresponding features, i.e., a historical ear tag library. These historical data may include ear tag numbers, associated animal features, insurance details, and other information. By establishing a basic database, data support is provided for subsequent identification and matching processes. The rules between ear tag numbers and features can be discovered through historical data analysis to improve identification accuracy.

[0051] In some embodiments, a historical ear tag library is constructed based on historical ear tag insurance data, including: performing spark data cleaning on the historical ear tag data; wherein spark data cleaning includes data deduplication, missing value processing, data conversion, outlier detection and data formatting; and constructing a historical ear tag library based on the cleaned historical ear tag data.

[0052] Use Spark technology to deduplicate historical ear tag data and remove duplicate ear tag number records to ensure that each ear tag number is unique in the historical data set. The content of each step corresponding to Spark technology is as follows:

[0053] Missing value processing: Identify and process missing values ​​in data by filling in default values, estimating missing values, or deleting missing data records to ensure data integrity.

[0054] Data conversion: Convert historical ear tag data to a unified format and standard to ensure consistency in subsequent processing and analysis. For example, unify the date format or convert values ​​in different units to a unified unit.

[0055] Outlier detection: Identify outliers in the data, such as data errors or values ​​outside a reasonable range, and make necessary corrections or deletions to maintain the credibility and accuracy of the data.

[0056] Data formatting: Format the cleaned data into a predefined structure for easy subsequent storage and retrieval. For example, format the ear tag number and the corresponding insurance information into a standardized format such as JSON or CSV.

[0057] Based on the cleaned historical ear tag data, a structured historical ear tag library is constructed. The historical ear tag library can be stored in relational databases (such as MySQL), non-relational databases (such as MongoDB), or distributed storage systems (such as Hadoop HDFS). The cleaned data is systematically stored in the historical ear tag library to ensure orderly storage and fast retrieval of data.

[0058] In summary, through data deduplication, missing value processing and outlier detection, the accuracy and reliability of the data are effectively improved, ensuring that the data in the historical ear tag library is of high quality. The data conversion and formatting steps make all data conform to unified standards and formats, ensuring the consistency and standardization of the data, and facilitating subsequent processing and analysis. Using Spark for data cleaning, making full use of its distributed computing capabilities, improving the processing efficiency and speed of large-scale historical ear tag data, and suitable for processing massive data. Building a historical ear tag library will systematically store the cleaned high-quality data, which is convenient for rapid query and analysis, and supports subsequent business needs. By establishing a historical ear tag library, a reliable data foundation is provided for subsequent ear tag number matching, Bloom filter generation and other related operations, ensuring the stable operation of the entire system process.

[0059] The above embodiment describes in detail the process of cleaning historical ear tag data and building a historical ear tag library, and uses Spark technology to perform efficient data cleaning to ensure high data quality and consistency. At the same time, the cleaned data is systematically stored in the historical ear tag library, providing a solid data foundation for subsequent operations.

[0060] Step S102: Group multiple historical ear tag features to obtain multiple ear tag groups and identification information corresponding to each ear tag group.

[0061] Specifically, ear tag numbers are grouped according to historical ear tag features (such as shape, color, position, etc.) to generate multiple ear tag groups. Each ear tag group is bound with unique identification information. Preliminary classification and grouping of data helps to match ear tag features more quickly and accurately in subsequent steps. In order to reduce complexity, complex data sets are simplified into several easy-to-handle subsets.

[0062] Step S103. Generate a hash bucket corresponding to each ear tag group, where the identification information of the hash bucket is the identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter based on the multiple hash buckets that have been added.

[0063] Specifically, by creating a corresponding hash bucket for each ear tag group, the identification information of the hash bucket is consistent with the identification information of the ear tag group. The ear tag number corresponding to each historical ear tag feature is added to the corresponding hash bucket. A Bloom filter is built based on the hash bucket for fast query and filtering of data. The efficient search and matching capabilities of hash and Bloom filters are used to improve the speed and accuracy of subsequent matching and identification. It also reduces memory usage and query time to meet the needs of large-scale data processing.

[0064] In some embodiments, multiple historical ear tag features are grouped to obtain multiple ear tag groups and identification information corresponding to each ear tag group, including: obtaining multiple insurance dimensions from a preset agricultural insurance database; generating an initial ear tag group corresponding to each insurance dimension; performing feature matching with each historical ear tag feature according to each insurance dimension; adding the successfully matched historical ear tag features to the initial ear tag group corresponding to the insurance dimension to obtain multiple ear tag groups; and using the insurance dimension corresponding to the ear tag group as identification information.

[0065] First, multiple insurance dimensions are extracted from the preset agricultural insurance database. Insurance dimensions can be different standards or attributes used to classify and organize ear tag data, such as region, animal breed, insurance date, etc. Insurance dimensions provide a structured and orderly classification standard, making ear tag feature grouping more systematic and organized. This improves the flexibility and accuracy of subsequent matching and processing.

[0066] Then, based on the obtained insurance dimensions, generate the initial ear tag groups corresponding to each insurance dimension. These initial ear tag groups are empty and await subsequent grouping. For example, if the insurance dimension is species, the corresponding "pig ear tag group", "cattle ear tag group", etc. are generated (it can also be a combination of region and species, or it can only include species, which can be set arbitrarily according to needs). Establish a basic data framework to provide structural support for the subsequent classification and addition of ear tag numbers based on features. Improving the scalability and adaptability of the system is helpful for data management and query efficiency.

[0067] Then, feature matching is performed between each insurance dimension and each historical ear tag feature, and the successfully matched historical ear tag features are added to the initial ear tag group corresponding to the corresponding insurance dimension according to the matching result.

[0068] Accurately classify ear tag features into ear tag groups corresponding to each insurance dimension to ensure the accuracy and rationality of data distribution. The grouped data is easier to manage and query, reducing data confusion and improving the accuracy of subsequent data processing.

[0069] Finally, the insurance dimension of each ear tag group is used as its identification information for the subsequent hash bucket generation and data matching. The clear identification information provides a clear reference for the subsequent hash bucket generation and Bloom filter construction, which helps to quickly find and identify. It provides a basis for efficient access to hash buckets, making data grouping and subsequent matching processes more efficient.

[0070] In summary, by using the insurance dimension for grouping, the grouping of historical ear tag features is more scientific and reasonable, and the accuracy and efficiency of grouping are improved. By providing a more systematic and structured data management method, the data processing of ear tag numbers is more orderly, providing a good foundation for subsequent operations. The matching efficiency of ear tag features after grouping is higher. With the use of identification information, specific data can be quickly located and found, improving the efficiency of query and matching. By using the insurance dimension for grouping and identification, the system is more flexible and convenient when expanding and adapting to new data and features, and has stronger scalability. Effectively manage and match ear tag features to prevent data confusion and tampering, and improve the security and reliability of the system. Grouping through specific insurance dimensions and feature matching, systematically classify and identify ear tag features, making the entire ear tag number recognition system more efficient and reliable.

[0071] In some embodiments, Figure 2 The method of generating a Bloom filter according to the multiple hash buckets that have been added includes steps S103a to S103c.

[0072] Step S103a. Obtain an initial Bloom filter according to multiple hash buckets; initialize the bit array of the initial Bloom filter to set all bits of the Bloom filter to 0.

[0073] Get an initial Bloom filter from multiple hash buckets. This involves creating an initial Bloom filter object and allocating the required bit array space for it. Initialize the initial Bloom filter's bit array, setting all bits to 0.

[0074] In summary, by initializing the Bloom filter, we ensure that all bits are in their initial state. This prevents any raw or random data from affecting the accuracy of the filter. Setting all bits to 0 provides a clean starting point, ensuring that the Bloom filter can correctly reflect the distribution of hash values ​​in subsequent steps.

[0075] Step S103b: Obtain the hash value of each historical ear tag number in each hash bucket.

[0076] By traversing each hash bucket, each historical ear tag number in each bucket is obtained. A hash function is used to calculate the hash value of each historical ear tag number. Depending on specific needs, multiple hash functions may be used to increase the accuracy of the filter. By calculating the hash value of each historical ear tag number, key input data is provided to the Bloom filter. These hash values ​​will be used to update the bit array of the Bloom filter. Using multiple hash functions (if used) can reduce the false positive rate of the Bloom filter and improve the accuracy of the match.

[0077] Step S103c. In the initial Bloom filter, set the bit corresponding to each hash value in the bit array to 1 to obtain a Bloom filter.

[0078] In the initial Bloom filter, the corresponding bit of the bit array is set to 1 according to the obtained hash value. Each hash value corresponds to one or more bits in the Bloom filter, and the hash value is used to change the state of a specific bit in the bit array. By gradually updating the Bloom filter, it reflects the hash value information of all historical ear tag numbers. By setting these bits, the existence of multiple ear tag numbers can be effectively represented. The Bloom filter is established in a more efficient way, occupies less storage space, and can quickly determine whether a certain ear tag number may exist in a known hash bucket.

[0079] In summary, the overall beneficial effects of generating a Bloom filter provided include:

[0080] 1. Efficient data query: Bloom filter uses hash function and bit array to quickly determine whether an element exists, which greatly improves query efficiency.

[0081] 2. Save storage space: Using a bit array instead of storing all historical ear tag numbers reduces memory usage.

[0082] 3. Reduce computational complexity: The computational complexity of initializing and updating Bloom filters is low, which is suitable for large-scale data processing.

[0083] 4. Improve system security: Bloom filters can reduce the system's query requests for non-existent ear tag numbers, reduce misoperations, and improve the overall security of the system.

[0084] 5. Reduce the false positive rate: The use of multiple hash functions can reduce the false positive results of the Bloom filter to a certain extent and improve the reliability of the filtering effect.

[0085] Through steps S103a to S103c, the Bloom filter can effectively cooperate with the ear tag number recognition system, provide efficient query and matching support, and ensure the high performance and reliability of the method.

[0086] Step S104: Obtain the ear tag number to be identified and the ear tag feature corresponding to the ear tag number, match the ear tag feature with the identification information corresponding to each hash bucket, and determine the target hash bucket corresponding to the ear tag number.

[0087] Specifically, by obtaining the ear tag number to be identified and its corresponding ear tag feature, the target hash bucket to which the ear tag number belongs is determined by matching the ear tag feature to be identified with the identification information of each hash bucket. This provides a method for quickly screening and locating the ear tag features to be identified, narrowing the matching range and improving the matching efficiency. This ensures that subsequent steps perform streaming calculations and matching within a more precise range.

[0088] Step S105: Input the ear tag number into the Bloom filter. The Bloom filter performs streaming calculation on the ear tag number and each historical ear tag number in the target hash bucket to obtain the calculation result corresponding to the ear tag number, and completes the identification of the ear tag number according to the calculation result.

[0089] Specifically, the ear tag number to be identified is input into the Bloom filter. The Bloom filter performs streaming calculations on the ear tag number and compares it with each historical ear tag number in the target hash bucket. The identification result of the ear tag number is confirmed based on the calculation result. Streaming calculations (such as flip calculations) are used to ensure efficient processing of matching tasks with large amounts of data, and ear tag number identification is completed quickly and accurately. The Bloom filter itself has efficient query characteristics, which further improves the recognition speed and accuracy and reduces misidentification.

[0090] In summary, the provided method combines historical data acquisition, feature grouping, hash allocation to final streaming calculation and recognition to form an efficient and accurate ear tag number recognition method. This method can effectively solve the problem of disordered ear tags in the field of agricultural insurance and provide a stable and reliable recognition mechanism.

[0091] In some embodiments, obtaining an ear tag number to be identified and an ear tag feature corresponding to the ear tag number includes: obtaining an insured ear tag number segment to be identified; obtaining multiple insured identifiers in a preset agricultural insurance database; matching each insured identifier with the insured ear tag number segment to generate multiple insured marks in the insured ear tag number segment according to the successfully matched insured identifiers; splitting the insured ear tag number segment according to the insured marks to obtain multiple ear tag numbers; and generating ear tag features corresponding to the ear tag numbers according to the insured marks corresponding to the ear tag numbers.

[0092] In some embodiments, Figure 3 As shown, after the ear tag number is identified according to the calculation result, step S106 to step S108 are further included.

[0093] Step S106: Analyze the calculation result, obtain the historical ear tag number corresponding to the ear tag number; obtain multiple first associated ear tag numbers corresponding to the historical ear tag number.

[0094] By analyzing the recognition calculation results, the historical ear tag number corresponding to the ear tag number to be identified is obtained. Multiple first associated ear tag numbers corresponding to the historical ear tag number are retrieved from the historical ear tag library. These associated ear tag numbers may come from other animals insured in the same batch, or may be associated ear tag numbers determined based on certain specific association rules. By obtaining a set of associated ear tag numbers, further batch verification can be performed based on the identification. This provides necessary data support for subsequent difference comparison and anomaly detection, ensuring the consistency and integrity of batch data.

[0095] Step S107: Acquire multiple second associated ear tag numbers corresponding to the ear tag number, and match the first associated ear tag number with the second associated ear tag number.

[0096] By obtaining multiple second associated ear tag numbers corresponding to the ear tag number to be identified from real-time or pre-stored data. These ear tag numbers are similar to the first associated ear tag number and may come from field records or dynamic data collection. The first associated ear tag number is matched with the second associated ear tag number to compare their consistency and validity. By matching the two sets of associated ear tag numbers, the legitimacy and consistency of the ear tag number to be identified are further verified to prevent part or a single ear tag number from being transferred or tampered with. A redundant verification mechanism is then provided to increase the reliability and anti-fraud capability of the identification process.

[0097] Step S108: If the first associated ear tag number fails to match the second associated ear tag number, a warning message is generated.

[0098] Determine the matching result of the first associated ear tag number and the second associated ear tag number. If the match fails, generate an early warning message to indicate possible abnormalities or potential risks. Through the early warning mechanism, abnormalities can be discovered and handled early to prevent fraud, and corresponding measures can be taken in time to protect the interests of insurance companies and the legitimate rights and interests of farmers. Provide an automated monitoring and early warning method to reduce labor costs and improve management efficiency.

[0099] Steps S106 to S108 add a layer of security and verification mechanism to ear tag identification by matching and comparing the associated ear tag numbers. This mechanism helps prevent farmers from transferring a single or partial ear tag number to others, thereby ensuring the integrity and consistency of the insured animal data for each batch. In the field of agricultural insurance, this batch verification method effectively reduces risks and improves the reliability and trust of the system.

[0100] Exemplarily, matching a first associated ear tag number with a second associated ear tag number includes: generating a distribution rule based on a plurality of first associated ear tag numbers and the order corresponding to the first associated ear tag numbers; matching a plurality of second associated ear tag numbers based on the distribution rule to determine that a match between the first associated ear tag number and the second associated ear tag number fails when the second associated ear tag number does not conform to the distribution rule.

[0101] First, analyze multiple first-associated ear tag numbers obtained from historical data to study and determine their obvious distribution patterns. This pattern can be based on the arrangement order, numbering rules, adjacent relationships, etc. of the ear tag numbers. For example, if the ear tag numbers are numbered according to a certain pattern, such as continuous numbering, specific regular intervals, or other specific arrangement rules, this pattern will be extracted and recorded. By studying and capturing the distribution pattern of the first-associated ear tag numbers, a unique feature model specific to the batch of ear tag numbers is constructed, so that subsequent matching has a clear reference standard. Increase the recognition system's understanding of the relationship and overall structure of the ear tag numbers, and improve the accuracy of matching and verification.

[0102] Then, the ear tag number to be identified and its associated second associated ear tag number are obtained, and these ear tag numbers to be identified are matched and verified based on the distribution law extracted in the first step. The second associated ear tag numbers are analyzed and arranged in the same order or rule to check whether they conform to the previously determined distribution law.

[0103] By matching with known distribution rules, we can ensure that the newly acquired ear tag numbers are arranged and distributed in the expected way. If they do not conform to the rules, we can quickly point out the abnormal points. Through strict rule matching, we can consolidate the consistency and authenticity of the data and reduce the recognition errors caused by circumventing the rules.

[0104] Finally, the second associated ear tag number is evaluated to see whether it conforms to the distribution pattern of the first associated ear tag number. If any deviation or abnormality is found, the match is immediately determined to have failed. Based on the matching result, corresponding operations are performed, such as generating warning information.

[0105] Through the regular matching mechanism, the legitimacy and consistency of the ear tag number can be determined quickly and accurately. When the matching fails, early warning information is generated in time, providing an early error capture and correction mechanism to prevent potential errors from flowing into the subsequent process.

[0106] Furthermore, by capturing and applying the distribution law of ear tag numbers, it is ensured that the expected arrangement and distribution pattern is strictly followed during the matching process, thereby improving data consistency and integrity. By mapping the second associated ear tag number to a known distribution law, anomalies can be quickly discovered and matching failures can be determined, thereby improving the system's efficiency in finding and handling potential problems. It further prevents single or partial ear tag numbers from being transferred or tampered with, ensuring the integrity of the ear tag numbers of each batch of insured animals and the reliability of the corresponding relationship. When a match fails, an early warning message is automatically generated to promptly notify relevant personnel to take corresponding measures, thereby improving management efficiency and reducing human intervention. Furthermore, in combination with the above-mentioned embodiments, the provided ear tag number recognition method introduces a more detailed and rigorous mechanism in the matching and verification process, thereby enhancing the reliability and security of the overall recognition system.

[0107] See also Figure 4 As shown, Figure 4 1 is a schematic diagram of the structure of the ear tag number recognition device 200 provided in an embodiment of the present application. The ear tag number recognition device 200 is used to perform the steps of the ear tag number recognition method shown in the above embodiments. The ear tag number recognition device 200 can be a single server or a server cluster, or the ear tag number recognition device 200 can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0108] like Figure 4 As shown, the ear tag number recognition device 200 includes:

[0109] The data acquisition unit 201 is used to acquire the historical ear tag insurance data of the insured, and to construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes the historical ear tag number and the historical ear tag feature corresponding to the historical ear tag number;

[0110] A feature grouping unit 202, configured to group the plurality of historical ear tag features, and obtain a plurality of ear tag groups and identification information corresponding to each of the ear tag groups;

[0111] A Bloom generation unit 203 is used to generate a hash bucket corresponding to each ear tag group, wherein the identification information of the hash bucket is the identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter according to the multiple hash buckets that have been added;

[0112] The target determination unit 204 is used to obtain the ear tag number to be identified and the ear tag feature corresponding to the ear tag number, and match the ear tag feature with the identification information corresponding to each hash bucket to determine the target hash bucket corresponding to the ear tag number;

[0113] The identification completion unit 205 is used to input the ear tag number into the Bloom filter, and the Bloom filter performs streaming calculations on the ear tag number and each of the historical ear tag numbers in the target hash bucket to obtain a calculation result corresponding to the ear tag number, and completes the identification of the ear tag number based on the calculation result.

[0114] It should be noted that, those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the ear tag number recognition device and each module described above can refer to the corresponding processes in the ear tag number recognition method embodiments described in the above embodiments, and will not be repeated here.

[0115] The ear tag number recognition method described above can be implemented in the form of a computer program. The computer program can be used in Figure 4 Run on the device shown.

[0116] See also Figure 5 , Figure 5 1 is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0117] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any ear tag number recognition method.

[0118] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0119] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any ear tag number recognition method.

[0120] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the terminal to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0122] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0123] Acquire the historical ear tag insurance data of the insured, and construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes the historical ear tag number and the historical ear tag feature corresponding to the historical ear tag number;

[0124] Grouping the plurality of historical ear tag features to obtain a plurality of ear tag groups and identification information corresponding to each of the ear tag groups;

[0125] Generate a hash bucket corresponding to each ear tag group, wherein identification information of the hash bucket is identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter according to the multiple hash buckets that have been added;

[0126] Acquire the ear tag number to be identified and the ear tag feature corresponding to the ear tag number, match the ear tag feature with the identification information corresponding to each hash bucket, and determine the target hash bucket corresponding to the ear tag number;

[0127] The ear tag number is input into the Bloom filter, and the Bloom filter performs streaming calculation on the ear tag number and each of the historical ear tag numbers in the target hash bucket to obtain a calculation result corresponding to the ear tag number, and completes the identification of the ear tag number according to the calculation result.

[0128] In some embodiments, the obtaining of the ear tag number to be identified and the ear tag feature corresponding to the ear tag number includes: obtaining the insured ear tag number segment to be identified; obtaining multiple insured identifiers in a preset agricultural insurance database; matching each of the insured identifiers with the insured ear tag number segment to generate multiple insured marks in the insured ear tag number segment according to the successfully matched insured identifiers; splitting the insured ear tag number segment according to the insured marks to obtain multiple ear tag numbers; and generating the ear tag feature corresponding to the ear tag number according to the insured mark corresponding to the ear tag number.

[0129] In some embodiments, after completing the identification of the ear tag number according to the calculation result, it also includes: parsing the calculation result, obtaining the historical ear tag number corresponding to the ear tag number; obtaining multiple first associated ear tag numbers corresponding to the historical ear tag number; obtaining multiple second associated ear tag numbers corresponding to the ear tag number, matching the first associated ear tag number with the second associated ear tag number; if the first associated ear tag number fails to match the second associated ear tag number, generating a warning message.

[0130] Exemplarily, the matching of the first associated ear tag number with the second associated ear tag number includes: generating the distribution rule according to the order corresponding to the multiple first associated ear tag numbers and the first associated ear tag numbers; matching the multiple second associated ear tag numbers according to the distribution rule to determine that the matching of the first associated ear tag number with the second associated ear tag number fails when the second associated ear tag number does not conform to the distribution rule.

[0131] In some embodiments, the grouping of the multiple historical ear tag features to obtain multiple ear tag groups and identification information corresponding to each ear tag group includes: obtaining multiple insurance dimensions from a preset agricultural insurance database; generating an initial ear tag group corresponding to each insurance dimension; performing feature matching with each historical ear tag feature according to each insurance dimension; adding the successfully matched historical ear tag features to the initial ear tag group corresponding to the insurance dimension to obtain multiple ear tag groups; and using the insurance dimension corresponding to the ear tag group as the identification information.

[0132] In some embodiments, generating a Bloom filter based on the multiple hash buckets that have been added includes: obtaining an initial Bloom filter based on the multiple hash buckets; initializing the bit array of the initial Bloom filter to set all bits of the Bloom filter to 0; obtaining a hash value of each of the historical ear tag numbers in each of the hash buckets; and setting each of the hash values ​​in the initial Bloom filter to 1 in the bit array corresponding to the bit array to obtain the Bloom filter.

[0133] In some embodiments, constructing a historical ear tag library based on the historical ear tag insurance data includes: performing spark data cleaning on the historical ear tag data; wherein the spark data cleaning includes data deduplication, missing value processing, data conversion, outlier detection and data formatting; and constructing the historical ear tag library based on the cleaned historical ear tag data.

[0134] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program. The computer program includes program instructions. The processor executes the program instructions to implement the steps of the ear tag number recognition method provided in the above embodiments of the present application.

[0135] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0136] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for identifying ear tags, characterized in that: include: Acquire the historical ear tag insurance data of the insured, and construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes the historical ear tag number and the historical ear tag feature corresponding to the historical ear tag number; Grouping the plurality of historical ear tag features to obtain a plurality of ear tag groups and identification information corresponding to each of the ear tag groups; Generate a hash bucket corresponding to each ear tag group, wherein identification information of the hash bucket is identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter according to the multiple hash buckets that have been added; Acquire the ear tag number to be identified and the ear tag feature corresponding to the ear tag number, match the ear tag feature with the identification information corresponding to each hash bucket, and determine the target hash bucket corresponding to the ear tag number; The ear tag number is input into the Bloom filter, and the Bloom filter performs streaming calculation on the ear tag number and each of the historical ear tag numbers in the target hash bucket to obtain a calculation result corresponding to the ear tag number, and completes the identification of the ear tag number according to the calculation result.

2. The method according to claim 1, characterized in that The obtaining the ear tag number to be identified and the ear tag feature corresponding to the ear tag number includes: Obtain the insured ear tag number segment to be identified; Obtain multiple underwriting identifiers in a preset agricultural insurance database; Matching each of the insurance identifications with the insurance ear label number segment to generate a plurality of insurance marks in the insurance ear label number segment according to the successfully matched insurance identifications; Splitting the insurance ear tag number segment according to the insurance mark to obtain a plurality of ear tag numbers; The ear tag feature corresponding to the ear tag number is generated according to the insurance mark corresponding to the ear tag number.

3. The method according to claim 1, characterized in that After the ear tag number is identified according to the calculation result, the method further includes: Analyze the calculation result to obtain the historical ear tag number corresponding to the ear tag number; Acquire multiple first associated ear tag numbers corresponding to the historical ear tag numbers; Acquire multiple second associated ear tag numbers corresponding to the ear tag number, and match the first associated ear tag number with the second associated ear tag number; If the first associated ear tag number fails to match the second associated ear tag number, a warning message is generated.

4. The method according to claim 3, characterized in that The matching the first associated ear tag number with the second associated ear tag number comprises: generating the distribution rule according to a plurality of the first associated ear tag numbers and a corresponding order of the first associated ear tag number; The plurality of second associated ear tag numbers are matched according to the distribution rule, so as to determine that the first associated ear tag number fails to match the second associated ear tag number when the second associated ear tag number does not conform to the distribution rule.

5. The method according to claim 1, characterized in that The step of grouping the plurality of historical ear tag features to obtain a plurality of ear tag groups and identification information corresponding to each ear tag group includes: Obtain multiple insurance dimensions in the preset agricultural insurance database; Generate an initial ear tag group corresponding to each of the insurance dimensions; Perform feature matching with each of the historical ear tag features according to each of the insurance dimensions; The successfully matched historical ear tag features are added to the initial ear tag group corresponding to the insurance dimension to obtain multiple ear tag groups; the insurance dimension corresponding to the ear tag group is used as the identification information.

6. The method according to claim 1, characterized in that The step of generating a Bloom filter according to the added plurality of hash buckets includes: Acquire an initial Bloom filter according to the plurality of hash buckets; Initializing a bit array of the initial Bloom filter to set all bits of the Bloom filter to 0; Obtaining a hash value of each of the historical ear tags in each of the hash buckets; In the initial Bloom filter, each of the hash values ​​in the bit array corresponding to the bit array is set to 1 to obtain the Bloom filter.

7. The method according to claim 1, characterized in that The step of constructing a historical ear tag library according to the historical ear tag insurance data includes: Performing spark data cleaning on the historical ear tag data; wherein the spark data cleaning includes data deduplication, missing value processing, data conversion, outlier detection and data formatting; The historical ear tag library is constructed according to the cleaned historical ear tag data.

8. An ear tag identification device, characterized in that: include: A data acquisition unit, used to acquire the historical ear tag insurance data of the insured, and to construct a historical ear tag library according to the historical ear tag insurance data; wherein the historical insurance data includes the historical ear tag number and the historical ear tag feature corresponding to the historical ear tag number; A feature grouping unit, used to group the plurality of historical ear tag features, and obtain a plurality of ear tag groups and identification information corresponding to each of the ear tag groups; a Bloom generation unit, configured to generate a hash bucket corresponding to each ear tag group, wherein identification information of the hash bucket is identification information of the ear tag group, add the historical ear tag number corresponding to each historical ear tag feature in the ear tag group to the hash bucket corresponding to the ear tag group, and generate a Bloom filter according to the multiple hash buckets that have been added; a target determination unit, configured to obtain an ear tag number to be identified and an ear tag feature corresponding to the ear tag number, and determine a target hash bucket corresponding to the ear tag number by matching the ear tag feature with identification information corresponding to each hash bucket; The identification completion unit is used to input the ear tag number into the Bloom filter, and the Bloom filter performs streaming calculations on the ear tag number and each of the historical ear tag numbers in the target hash bucket to obtain a calculation result corresponding to the ear tag number, and completes the identification of the ear tag number based on the calculation result.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 7.

Images