Animal and plant data classification method and device, electronic equipment and storage medium

Abstract

The invention discloses an animal and plant data classification method and device, electronic equipment and a storage medium, and the method comprises the steps: after obtaining a plurality of pieces of animal and plant data to be classified, extracting feature data from each piece of animal and plant data, the feature data comprising real object feature data, environment feature data and gene feature data; the animal and plant data are classified according to the physical feature data and the environment feature data, a plurality of entity classification categories are obtained, and each entity classification category comprises a plurality of animal and plant data; and classifying the animal and plant data of each entity classification category according to the gene feature data to obtain a plurality of gene classification categories, and classifying the animal and plant data according to the gene classification categories. According to the method, comprehensive classification is carried out through the object features, the environment features and the gene features, so that classification deviation is avoided, and the classification accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data classification processing, and in particular to a classification method, device, electronic equipment and storage medium for animal and plant data. Background Art

[0002] Plant taxonomy is an ancient and comprehensive branch of botany, serving as a foundational discipline for the identification and utilization of plants. Classical plant classifications are primarily based on external morphology and internal anatomical features. One of the primary methods of classification involves a stepwise classification based on traits using a key table. This method employs plant morphological comparison, using criteria and distinguishing features for grouping (family, genus, species, etc.) to distinguish unknown plants from previously documented ones, ultimately identifying the species to which they belong.

[0003] With the development of artificial intelligence and big data in recent years, traditional plant classification has been transformed into online applications. Specifically, the morphological family and other physical characteristics of animals and plants are manually classified, and then the data of each category is classified, stored and managed according to the classification results.

[0004] However, the currently commonly used methods have the following technical problems: manual identification of plant species by physical characteristics is not only cumbersome but also has low accuracy; and with the development of genetic modification and hybridization, more plants and animals may have similar physical characteristics but large genetic differences, or similar genes but large differences in physical characteristics. Therefore, the error of distinguishing by physical characteristics alone is large, and the accuracy of classification is further reduced. Summary of the Invention

[0005] The present invention provides a classification method, device, electronic device and storage medium for plant and animal data, which can solve one or more of the above-mentioned technical problems.

[0006] A first aspect of an embodiment of the present invention provides a method for classifying animal and plant data, the method comprising: after acquiring a plurality of animal and plant data to be classified, extracting feature data from each of the animal and plant data, the feature data comprising physical feature data, environmental feature data, and genetic feature data;

[0007] Classifying the plurality of animal and plant data according to the physical object feature data and the environmental feature data to obtain a plurality of entity classification categories, wherein each entity classification category includes a plurality of animal and plant data;

[0008] The plant and animal data of each entity classification category is classified according to the gene feature data to obtain a plurality of gene classification categories, and the plurality of plant and animal data are classified according to the gene classification categories.

[0009] In a possible implementation of the first aspect, the plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including:

[0010] Convert each of the physical object feature data and each of the environmental feature data into text to obtain a physical object feature text and an environmental feature text;

[0011] Performing a first text classification on the plurality of physical object feature texts using a word matching method to obtain a plurality of physical object text categories;

[0012] A word matching method is used to perform a second text classification on the environmental feature text contained in each of the physical object text categories to obtain a plurality of entity classification categories.

[0013] In a possible implementation of the first aspect, the plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including:

[0014] Performing numerical extraction on each of the physical object characteristic data and each of the environmental characteristic data to obtain a physical object characteristic value and an environmental characteristic value, respectively;

[0015] Dividing the physical object into several physical object value categories according to the magnitude of the physical object characteristic value;

[0016] The plurality of plant and animal data contained in each of the physical object numerical categories are classified according to the magnitude of the environmental characteristic values to obtain a plurality of entity classification categories.

[0017] In a possible implementation of the first aspect, classifying the plant and animal data of each entity classification category according to the genetic feature data to obtain a plurality of genetic classification categories includes:

[0018] If the family and genus of each animal and plant data included in the entity classification category are the same, extracting the corresponding base sequence from each of the gene feature data;

[0019] Calculating the similarity between base sequences of the plant and animal data included in each entity classification category to obtain multiple base similarities;

[0020] Several gene classification categories are obtained by classifying according to the numerical values of the multiple base similarities.

[0021] In a possible implementation of the first aspect, classifying the plant and animal data of each entity classification category according to the genetic feature data to obtain a plurality of genetic classification categories includes:

[0022] If any of the families and genera of each of the animal and plant data included in the entity classification category is different, extracting the corresponding base pair arrangement sequence from each of the gene feature data;

[0023] Calculating the similarity of the arrangement order of base pairs of the plant and animal data included in each entity classification category to obtain multiple arrangement similarities;

[0024] Several gene classification categories are obtained by classifying according to the numerical values of the plurality of arrangement similarities.

[0025] In a possible implementation of the first aspect, after the step of classifying the plurality of animal and plant data according to the gene classification category, the method further includes:

[0026] Obtaining upload timestamps of the plurality of animal and plant data included in the gene classification category, and generating an encryption key using the upload timestamps;

[0027] The encryption key is used to encrypt and store the plurality of plant and animal data contained in the gene classification category.

[0028] In a possible implementation of the first aspect, generating an encryption key by using the upload timestamp includes:

[0029] Extracting a plurality of time values from the upload timestamp according to a preset byte length;

[0030] The plurality of time values are concatenated to generate an encryption key.

[0031] A second aspect of an embodiment of the present invention provides a device for classifying animal and plant data, the device comprising:

[0032] A feature data extraction module is used to extract feature data from each of the plurality of animal and plant data to be classified after obtaining the plurality of animal and plant data to be classified, wherein the feature data includes physical feature data, environmental feature data and gene feature data;

[0033] An entity and environment classification module, configured to classify the plurality of animal and plant data according to the physical object feature data and the environmental feature data to obtain a plurality of entity classification categories, wherein each entity classification category includes a plurality of animal and plant data;

[0034] The gene classification module is used to classify the animal and plant data of each entity classification category according to the gene feature data to obtain a plurality of gene classification categories, and classify the plurality of animal and plant data according to the gene classification categories.

[0035] In a possible implementation of the second aspect, the plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including:

[0036] Convert each of the physical object feature data and each of the environmental feature data into text to obtain a physical object feature text and an environmental feature text;

[0037] Performing a first text classification on the plurality of physical object feature texts using a word matching method to obtain a plurality of physical object text categories;

[0038] A word matching method is used to perform a second text classification on the environmental feature text contained in each of the physical object text categories to obtain a plurality of entity classification categories.

[0039] In a possible implementation of the second aspect, the plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including:

[0040] Performing numerical extraction on each of the physical object characteristic data and each of the environmental characteristic data to obtain a physical object characteristic value and an environmental characteristic value, respectively;

[0041] Dividing the physical object into several physical object value categories according to the magnitude of the physical object characteristic value;

[0042] The plurality of plant and animal data contained in each of the physical object numerical categories are classified according to the magnitude of the environmental characteristic values to obtain a plurality of entity classification categories.

[0043] In a possible implementation of the second aspect, classifying the plant and animal data of each entity classification category according to the genetic feature data to obtain a plurality of genetic classification categories includes:

[0044] If the family and genus of each animal and plant data included in the entity classification category are the same, extracting the corresponding base sequence from each of the gene feature data;

[0045] Calculating the similarity between base sequences of the plant and animal data included in each entity classification category to obtain multiple base similarities;

[0046] Several gene classification categories are obtained by classifying according to the numerical values of the multiple base similarities.

[0047] In a possible implementation of the second aspect, classifying the plant and animal data of each entity classification category according to the genetic feature data to obtain a plurality of genetic classification categories includes:

[0048] If any of the families and genera of each of the animal and plant data included in the entity classification category is different, extracting the corresponding base pair arrangement sequence from each of the gene feature data;

[0049] Calculating the similarity of the arrangement order of base pairs of the plant and animal data included in each entity classification category to obtain multiple arrangement similarities;

[0050] Several gene classification categories are obtained by classifying according to the numerical values of the plurality of arrangement similarities.

[0051] In a possible implementation of the second aspect, the apparatus further includes:

[0052] a key generation module, configured to obtain upload timestamps of the plurality of plant and animal data included in the gene classification category, and generate an encryption key using the upload timestamps;

[0053] The encryption and storage module is used to encrypt and store the plurality of animal and plant data contained in the gene classification category using the encryption key.

[0054] In a possible implementation of the second aspect, generating an encryption key by using the upload timestamp includes:

[0055] Extracting a plurality of time values from the upload timestamp according to a preset byte length;

[0056] The plurality of time values are concatenated to generate an encryption key.

[0057] Compared to existing technologies, the methods, devices, electronic devices, and storage media for classifying plant and animal data provided by embodiments of the present invention offer the following advantages: after obtaining multiple plant and animal data to be classified, the present invention can extract feature data from each piece of data; classify the multiple plant and animal data based on the physical feature data and environmental feature data to obtain several entity classification categories; classify the plant and animal data in each entity classification category based on the genetic feature data to obtain several genetic classification categories, and then classify the multiple plant and animal data according to the genetic classification categories. Comprehensive classification based on physical, environmental, and genetic features avoids classification bias and improves classification accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a method for classifying animal and plant data provided by one embodiment of the present invention;

[0059] Figure 2 It is a structural diagram of a classification device for animal and plant data provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] In order to solve the above problems, the following specific embodiments will be used to introduce and explain in detail a classification method, device, electronic device and computer-readable storage medium for animal and plant data provided in the embodiments of the present application.

[0062] The classification device for the animal and plant data may be integrated into an electronic device, which may be a server, a terminal or other device.

[0063] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. Terminals include but are not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, aircraft, etc., but are not limited to these. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this. The embodiments of the present invention can be applied to various scenarios, including but not limited to cloud technology, cloud security, artificial intelligence, smart transportation, assisted driving, etc.

[0064] For example, taking the example of a classification device for animal and plant data integrated into an electronic device, after the electronic device receives multiple animal and plant data to be classified, feature data can be extracted from each animal and plant data; the multiple animal and plant data can be classified according to the physical feature data and the environmental feature data to obtain several entity classification categories; the animal and plant data of each entity classification category can be classified according to the genetic feature data to obtain several genetic classification categories, and the multiple animal and plant data can be classified according to the genetic classification categories to improve the accuracy of data classification.

[0065] It can be understood that in the specific implementation of this application, data feature extraction, determination of classification categories, and classification processing are involved. When the following embodiments of this application are applied to specific products or technologies, permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0066] It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0067] Reference Figure 1 , which shows a flow chart of a classification method for animal and plant data provided by an embodiment of the present invention.

[0068] As an example, the classification method of the animal and plant data may include:

[0069] S11. After obtaining a plurality of animal and plant data to be classified, extract feature data from each of the animal and plant data, wherein the feature data includes physical feature data, environmental feature data, and gene feature data.

[0070] In one embodiment, animal and plant data that needs to be classified can be obtained, which can specifically be the animal and plant data input by a user.

[0071] For example, data on various hybrid rice varieties grown over a 10-year period include: the origin of the rice, the planting area of the rice, the rice yield, the planting time of the rice, the harvesting time of the rice, the genetic sequence of the rice, the size of the rice grains, the shape of the rice, the color of the rice, etc.

[0072] For example, the data on peanuts planted this year include: the origin of peanuts, the planting area of peanuts, the yield of peanuts, the planting time of peanuts, the harvest time of peanuts, the genetic sequence of peanuts, the size of peanut fruits, the size of peanut shells, the shape of peanuts, the color of peanuts, etc.

[0073] For example, butterfly data includes: the butterfly's birthplace, the ambient temperature of the butterfly's birthplace, the size of the butterfly's wings, the humidity of the butterfly's living environment, the sunshine hours of the butterfly's living environment, the butterfly's feeding time, the butterfly's genetic sequence, the butterfly's color, etc.

[0074] After obtaining the animal and plant data, the required feature data can be extracted from the animal and plant data. The feature data may include: physical feature data (for example, the size of peanuts, the color of butterflies, etc.), environmental feature data (for example, the pH value of the soil where peanuts are grown, the temperature and humidity of the butterfly's living environment, etc.) and genetic feature data (for example, the genetic sequence of peanuts, the genetic sequence of butterflies, etc.).

[0075] In one embodiment, the user can add various data to a table on his smart terminal or electronic device; when extracting feature data, the smart terminal or electronic device can read the various category names in the table, thereby extracting the required feature data based on the category names.

[0076] S12. Classify the plurality of animal and plant data according to the physical object feature data and the environmental feature data to obtain a plurality of entity classification categories, wherein each entity classification category contains a plurality of animal and plant data.

[0077] In one embodiment, since the feature data includes: physical feature data and environmental feature data, a first classification can be performed based on the physical feature data and the environmental feature data to obtain several different entity classification categories. After completing the first classification, a second classification is performed based on its genotype to improve the classification accuracy.

[0078] Since there are multiple animal and plant data, after completing a classification, each entity classification category can contain several animal and plant data.

[0079] For example, a user uploads 100 pieces of animal and plant data. After classification, three entity classification categories can be obtained. The first entity classification category can contain 50 pieces of animal and plant data, the second entity classification category can contain 30 pieces of animal and plant data, and the third entity classification category can contain 20 pieces of animal and plant data.

[0080] In an optional embodiment, the plant and animal data uploaded by the user is a text described by the user. In order to classify the text content uploaded by the user, as an example, the classification of the plurality of plant and animal data according to the physical feature data and the environmental feature data may include the following sub-steps:

[0081] S21. Convert each of the physical object feature data and each of the environmental feature data into text to obtain a physical object feature text and an environmental feature text.

[0082] S22. Perform a first text classification on the plurality of physical feature texts using a word matching method to obtain a plurality of physical text categories.

[0083] S23. Perform a second text classification on the environmental feature text contained in each of the physical text categories using a word matching method to obtain a plurality of entity classification categories.

[0084] Specifically, each physical object feature data and each environmental feature data may be converted into text first, to obtain a physical object feature text and an environmental feature text respectively.

[0085] Then, the word matching method can be used to perform the first text classification on thousands of physical feature texts to obtain several physical text categories.

[0086] For example, consider multiple plant and animal data items, each representing different butterfly species, whose entity characteristic is color. This data can be categorized based on color text, resulting in several object text categories. Each category corresponds to a specific color text, and each object text category contains at least one piece of plant and animal data. For example, consider receiving 12 plant and animal data items and categorizing them into three object text categories. The first object text category can contain three pieces of plant and animal data, the second can contain four pieces of plant and animal data, and the third can contain five pieces of plant and animal data.

[0087] For example, multiple pieces of plant and animal data may be related to different grape varieties, and their entity characteristics may be color. Alternatively, the multiple pieces of plant and animal data related to grapes can be categorized by color text to obtain several entity text categories. Each category can correspond to a specific color text, and each entity text category contains at least one piece of plant and animal data.

[0088] Then, the word matching method can be used to perform a second text classification on the environmental feature text contained in each physical text category to obtain several entity classification categories.

[0089] Specifically, the environmental characteristic text of the animal and plant data contained in each physical text category is read, and then the animal and plant data contained in each physical text category is classified for the second time according to the environmental characteristic text. Each category is an entity classification category, which can be divided into several entity classification categories.

[0090] In an actual operation mode, the classification operation according to the conventional word matching method can be as follows: perform word feature fusion and character feature fusion on each text to obtain word fusion features and character fusion features respectively; merge the word fusion features and character fusion features to obtain deep fusion features; and then determine the category matching results of each text based on the deep fusion features to obtain the classification category.

[0091] Among them, the fusion method of word feature fusion can be specifically as follows: the word vector corresponding to each text can be obtained; the vector product of each word vector is calculated; then activation output is performed based on the vector product calculation result, and the maximum value of the first preset number of the activation output result is extracted as the word fusion feature.

[0092] Among them, the fusion method of word feature fusion can be specifically as follows: the word vectors of each text can be obtained; the vector product of each word vector is calculated; and then activation output is performed based on the vector product calculation results of each word vector, and the maximum value of the first second preset number of the activation output results is extracted as the word fusion feature.

[0093] The method of merging the word fusion feature and the character fusion feature to obtain the deep fusion feature can be specifically as follows: merging the word fusion feature and the character fusion feature to obtain a merged feature; using a preset multi-layer perceptron to extract features from the merged feature to obtain a deep fusion feature of the first text and the second text, wherein the mathematical representation of the multi-layer perceptron is:

[0094] Zl=relu(W(l-1)Z(l-1)+B(l-1)).

[0095] In the above formula, l represents the number of layers of the multilayer perceptron, W(l-1) and B(l-1) represent the weight parameter matrix and bias vector of the lth layer of the multilayer perceptron respectively, Zl represents the output of the lth layer of the multilayer perceptron, Z(l-1) represents the input of the lth layer of the multilayer perceptron, and relu represents the activation function.

[0096] Finally, the category matching results of the text can be determined based on the deep fusion features.

[0097] In an embodiment of the present invention, the obtained deep fusion features include key matching features at the character level and key matching features at the word level of the text to be classified. Based on the deep fusion features, the category matching results of the text can be determined more accurately.

[0098] From the above, it can be seen that the present invention performs word feature fusion and character feature fusion through text to obtain word-level fusion features and character-level fusion features respectively; then the two are merged to obtain the deep fusion features of the text, and the deep fusion features are used for classification. The deep fusion features combine the character-level features and word-level features of the two texts, so the feature information contained is more comprehensive, and the matching results of the two determined thereby can be more accurate.

[0099] In addition, classification can also be performed according to conventional word matching methods, which can be adjusted according to actual needs.

[0100] In one embodiment, the plant and animal data uploaded by the user is related numerical parameters. In order to classify the numerical parameters uploaded by the user, for example, the classification of the plurality of plant and animal data according to the physical feature data and the environmental feature data may include the following sub-steps:

[0101] S31 . Perform numerical extraction on each of the physical object characteristic data and each of the environmental characteristic data to obtain a physical object characteristic value and an environmental characteristic value, respectively.

[0102] S32. Divide the physical object into several physical object value categories according to the magnitude of the physical object characteristic values.

[0103] S33. Classify the plurality of plant and animal data contained in each of the physical object numerical categories according to the magnitude of the environmental characteristic values to obtain a plurality of entity classification categories.

[0104] In one implementation, the numerical value corresponding to each physical feature data may be extracted to obtain the physical feature numerical value, and the numerical value corresponding to each environmental feature data may be extracted to obtain the environmental feature numerical value.

[0105] For example, a user uploads data about 10 peanuts. After extracting the physical, environmental, and genetic characteristics of each peanut from its plant and animal data, the user can read the corresponding values of the physical characteristics to obtain the physical characteristic values, or read the corresponding values of the environmental characteristics to obtain the environmental characteristic values. Physical characteristic values may include: the number of peanuts, the number of kernels, and the size of the peanuts; environmental characteristic values may include: the pH of the soil in which the peanuts were grown, the planting time, and the planting temperature.

[0106] After extraction, the object characteristic data can be divided into several object numerical categories according to the numerical value of the object characteristic data. In one implementation, the user can pre-set several numerical intervals, and objects in the same numerical interval belong to the same object numerical category.

[0107] For example, the physical characteristic value is the number of peanut seeds. One seed is one numerical interval, two seeds are one numerical interval, and three seeds are one numerical interval.

[0108] Suppose, after reading 10 physical characteristic values of peanuts, we determine the numerical intervals for each physical characteristic value. After partitioning, the first numerical interval for one seed has two animal and plant data points; the second numerical interval for two seeds has three animal and plant data points; and the third numerical interval for three seeds has five animal and plant data points.

[0109] After completing the first division to determine several physical object numerical categories, the several plant and animal data contained in each physical object numerical category can be classified according to the size of the environmental characteristic value to obtain several entity classification categories.

[0110] In one embodiment, the user may also pre-set several numerical ranges. Data in the same numerical range belong to one category, and several animal and plant data within the physical numerical category may be classified.

[0111] For example, the environmental characteristic value is the planting temperature, 10-15 degrees is a numerical interval, 15-20 degrees is a numerical interval, and 20-25 degrees is a numerical interval.

[0112] For example, a seed's numerical interval contains two pieces of plant and animal data. The first piece of plant and animal data corresponds to a planting temperature of 18 degrees Celsius, while the second piece of plant and animal data corresponds to a planting temperature of 23 degrees Celsius. The two pieces of plant and animal data corresponding to the seed's numerical interval can be divided into two categories, resulting in two entity classification categories. Similarly, the three pieces of plant and animal data corresponding to the two seed's numerical interval can be divided using the same method. Finally, the five pieces of plant and animal data corresponding to the three seed's numerical interval can be divided using the same method, resulting in multiple entity classification categories.

[0113] S13. Classify the animal and plant data of each entity classification category according to the gene feature data to obtain a plurality of gene classification categories, and classify the plurality of animal and plant data according to the gene classification categories.

[0114] After categorizing the entity based on physical and environmental characteristics, each entity category contains at least one plant or animal data item. Each entity category can be further categorized based on genetic data to improve classification accuracy.

[0115] In one implementation, classification can be performed based on the genotype of the gene feature data or the value of the gene pair, etc., and the specific method can be adjusted according to actual needs.

[0116] In one embodiment, the plant and animal data included in the entity classification category is data with similar physical and environmental characteristics, and may belong to the same family or genus. Data of the same family or genus generally have the same genotype. In order to classify data of the same genus, as an example, the plant and animal data of each entity classification category is classified according to the genetic feature data to obtain a plurality of genetic classification categories, which may include the following sub-steps:

[0117] S41. If the family and genus of each animal and plant data included in the entity classification category are the same, extract the corresponding base sequence from each gene feature data.

[0118] S42. Calculate the similarity between base sequences of the plant and animal data included in each entity classification category to obtain multiple base similarities.

[0119] S43. Classify the genes according to the numerical values of the base similarities to obtain a plurality of gene classification categories.

[0120] Specifically, we can determine whether the family and genus of each plant and animal data item included in each entity classification category are the same. If the family and genus of each plant and animal data item included in each entity classification category are the same, it means that they belong to the same species, and the corresponding base sequence can be extracted from each gene feature data item. For example, accttcggggtccc…att.

[0121] Next, the base sequence similarities between the plant and animal data within the same entity classification category can be calculated to obtain multiple base similarities. In one calculation method, a base sequence can be arbitrarily selected as a reference sequence. The total number of bases in the reference sequence is then counted, and the number of identical bases between the reference sequence and the base sequence to be calculated is then counted. The ratio of the number of identical bases to the total number of identical bases is then calculated to obtain the base similarity.

[0122] For example, the reference sequence and the base sequence to be calculated are ACCTTCGGTT and AACTTTGGTT, respectively. After calculation, the total number of bases is 10, and the number of identical bases is 8. Therefore, the similarity of the two base sequences is 8 / 10 = 0.8.

[0123] Finally, several gene classification categories can be obtained according to the numerical values of multiple base similarities.

[0124] In one embodiment, the user may also pre-set several numerical ranges, and the values in the same numerical range belong to the same gene classification category.

[0125] For example, 0.8-1 is a gene classification category, 0.6-0.8 is a gene classification category, and so on. The interval can be determined based on the value of the base similarity, and then the corresponding classification category can be determined based on the interval, so that several gene classification categories can be obtained.

[0126] In one embodiment, when animals and plants undergo genetic mutations during growth or development, species with different genes exhibit the same physical state under the same environmental temperature. To categorize data of different genes or species, for example, categorizing the animal and plant data of each entity classification category based on the genetic feature data to obtain a plurality of genetic classification categories may include the following sub-steps:

[0127] S51. If any of the families and genera of each of the animal and plant data included in the entity classification category is different, extract the corresponding base pair arrangement sequence from each of the gene feature data.

[0128] S52: Calculate the similarity of the arrangement order of base pairs of the plant and animal data included in each entity classification category to obtain multiple arrangement similarities.

[0129] S53, classifying according to the numerical values of the plurality of arrangement similarities to obtain a plurality of gene classification categories.

[0130] Specifically, we can determine whether the animal and plant data contained in each entity classification category are of the same family or genus. If at least one family or genus differs within each entity classification category, this indicates a possible genetic mutation and the animals are not of the same species. We can then extract the corresponding base pair sequence from each gene signature data. For example, if the base sequence is accttcggggtccc…att, the sequence would be ACCTTC….

[0131] Next, the similarities between the base sequences of the animal and plant data included in the same entity classification category may be calculated to obtain multiple base similarities.

[0132] In one calculation method, the total number of bases in the two base sequences is first counted, and then the number of identical bases at the same position in the two base sequences is counted. The ratio of the number of identical bases at the same position to the total number is calculated to obtain the base similarity.

[0133] For example, the two base sequences are ACCTTCGGTT and AACTTTGGTT. After calculation, the total number of bases in the two base sequences is 20, and the number of identical bases at the same position is 16. Therefore, the similarity of the two base sequences is 16 / 20 = 0.8.

[0134] Finally, several gene classification categories can be obtained according to the numerical values of multiple base similarities.

[0135] In one embodiment, the user may also pre-set several numerical ranges, and the values in the same numerical range belong to the same gene classification category.

[0136] For example, 0.5-1 is a gene classification category, 1-1.5 is a gene classification category, and so on. The interval can be determined based on the value of the base similarity, and then the corresponding classification category can be determined based on the interval, so that several gene classification categories can be obtained.

[0137] After completing the above classification, the plurality of animal and plant data may be classified and stored according to the above gene classification categories.

[0138] S14. Obtain upload timestamps of the plurality of animal and plant data included in the gene classification category, and generate an encryption key using the upload timestamps.

[0139] S15. Use the encryption key to encrypt and save the plurality of animal and plant data included in the gene classification category.

[0140] In one embodiment, to ensure data security during categorized storage, the upload timestamp of the multiple plant and animal data included in each genetic classification category can be obtained and then used to generate an encryption key. Finally, the encryption key is used to encrypt the multiple plant and animal data included in the entire genetic classification category to generate encrypted data, which is then stored.

[0141] It should be noted that each gene classification category may contain multiple plant and animal data, and the upload time of each data may be the same or different. If the upload time is different, you can arbitrarily select an upload timestamp and use it to generate the encryption key.

[0142] In one embodiment, generating an encryption key using the upload timestamp may include the following sub-steps:

[0143] S141. Extract several time values from the upload timestamp according to a preset byte length.

[0144] S142: Concatenate the multiple time values to generate an encryption key.

[0145] For example, if the upload timestamp is 202401011201 and the default byte length is 8 bits, you can extract 20240101 to obtain several time values. Add the "20240101" values together and use the added value as the encryption key. The encryption key is then used to encrypt the data.

[0146] In this embodiment, an embodiment of the present invention provides a method for classifying plant and animal data. The method has the following beneficial effects: after obtaining multiple plant and animal data to be classified, the method can extract feature data from each piece of plant and animal data; classify the multiple plant and animal data according to the physical feature data and environmental feature data to obtain multiple entity classification categories; classify the plant and animal data in each entity classification category according to the genetic feature data to obtain multiple genetic classification categories, and classify the multiple plant and animal data according to the genetic classification categories. Comprehensive classification based on physical, environmental, and genetic features can avoid classification bias and improve classification accuracy.

[0147] The present invention also provides a classification device for plant and animal data, see Figure 2 , which shows a structural diagram of a classification device for animal and plant data provided by an embodiment of the present invention.

[0148] As an example, the classification device for the animal and plant data may include:

[0149] The feature data extraction module 201 is used to extract feature data from each of the animal and plant data after obtaining the data of the plurality of animals and plants to be classified, wherein the feature data includes physical feature data, environmental feature data and gene feature data;

[0150] The entity and environment classification module 202 is configured to classify the plurality of animal and plant data according to the physical object feature data and the environmental feature data to obtain a plurality of entity classification categories, wherein each entity classification category includes a plurality of animal and plant data;

[0151] The gene classification module 203 is used to classify the animal and plant data of each entity classification category according to the gene feature data to obtain a plurality of gene classification categories, and classify the plurality of animal and plant data according to the gene classification categories.

[0152] Optionally, the plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including:

[0153] Convert each of the physical object feature data and each of the environmental feature data into text to obtain a physical object feature text and an environmental feature text;

[0154] Performing a first text classification on the plurality of physical object feature texts using a word matching method to obtain a plurality of physical object text categories;

[0155] A word matching method is used to perform a second text classification on the environmental feature text contained in each of the physical object text categories to obtain a plurality of entity classification categories.

[0156] Optionally, the plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including:

[0157] Performing numerical extraction on each of the physical object characteristic data and each of the environmental characteristic data to obtain a physical object characteristic value and an environmental characteristic value, respectively;

[0158] Dividing the physical object into several physical object value categories according to the magnitude of the physical object characteristic value;

[0159] The plurality of plant and animal data contained in each of the physical object numerical categories are classified according to the magnitude of the environmental characteristic values to obtain a plurality of entity classification categories.

[0160] Optionally, the animal and plant data of each entity classification category is classified according to the gene feature data to obtain several gene classification categories, including:

[0161] If the family and genus of each animal and plant data included in the entity classification category are the same, extracting the corresponding base sequence from each of the gene feature data;

[0162] Calculating the similarity between base sequences of the plant and animal data included in each entity classification category to obtain multiple base similarities;

[0163] Several gene classification categories are obtained by classifying according to the numerical values of the multiple base similarities.

[0164] Optionally, the animal and plant data of each entity classification category is classified according to the gene feature data to obtain several gene classification categories, including:

[0165] If any of the families and genera of each of the animal and plant data included in the entity classification category is different, extracting the corresponding base pair arrangement sequence from each of the gene feature data;

[0166] Calculating the similarity of the arrangement order of base pairs of the plant and animal data included in each entity classification category to obtain multiple arrangement similarities;

[0167] Several gene classification categories are obtained by classifying according to the numerical values of the plurality of arrangement similarities.

[0168] Optionally, the device further comprises:

[0169] a key generation module, configured to obtain upload timestamps of the plurality of plant and animal data included in the gene classification category, and generate an encryption key using the upload timestamps;

[0170] The encryption and storage module is used to encrypt and store the plurality of animal and plant data contained in the gene classification category using the encryption key.

[0171] Optionally, generating an encryption key using the upload timestamp includes:

[0172] Extracting a plurality of time values from the upload timestamp according to a preset byte length;

[0173] The plurality of time values are concatenated to generate an encryption key.

[0174] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0175] Furthermore, an embodiment of the present application also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the classification method for plant and animal data as described in the above embodiment is implemented.

[0176] Furthermore, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer-executable program, and the computer-executable program is used to enable a computer to execute the classification method of animal and plant data as described in the above embodiment.

[0177] Those skilled in the art will appreciate that the embodiments of the present application may also provide computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0178] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), apparatuses and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0179] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0181] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A classification method for plant and animal data, characterized in that: The method comprises: After obtaining a plurality of animal and plant data to be classified, extracting feature data from each of the animal and plant data, the feature data including physical feature data, environmental feature data, and gene feature data; Classifying the plurality of animal and plant data according to the physical object feature data and the environmental feature data to obtain a plurality of entity classification categories, wherein each entity classification category includes a plurality of animal and plant data; The plant and animal data of each entity classification category is classified according to the gene feature data to obtain a plurality of gene classification categories, and the plurality of plant and animal data are classified according to the gene classification categories.

2. The classification method of animal and plant data according to claim 1, characterized in that: The plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including: Convert each of the physical object feature data and each of the environmental feature data into text to obtain a physical object feature text and an environmental feature text; Performing a first text classification on the plurality of physical object feature texts using a word matching method to obtain a plurality of physical object text categories; A word matching method is used to perform a second text classification on the environmental feature text contained in each of the physical object text categories to obtain a plurality of entity classification categories.

3. The classification method of animal and plant data according to claim 1, characterized in that: The plurality of animal and plant data are classified according to the physical object feature data and the environmental feature data to obtain several entity classification categories, including: Performing numerical extraction on each of the physical object characteristic data and each of the environmental characteristic data to obtain a physical object characteristic value and an environmental characteristic value, respectively; Dividing the physical object into several physical object value categories according to the magnitude of the physical object characteristic value; The plurality of plant and animal data contained in each of the physical object numerical categories are classified according to the magnitude of the environmental characteristic values to obtain a plurality of entity classification categories.

4. The method for classifying animal and plant data according to any one of claims 2 or 3, characterized in that: The animal and plant data of each entity classification category is classified according to the gene feature data to obtain several gene classification categories, including: If the family and genus of each animal and plant data included in the entity classification category are the same, extracting the corresponding base sequence from each of the gene feature data; Calculating the similarity between base sequences of the plant and animal data included in each entity classification category to obtain multiple base similarities; Several gene classification categories are obtained by classifying according to the numerical values of the multiple base similarities.

5. The method for classifying animal and plant data according to any one of claims 2 or 3, characterized in that: The animal and plant data of each entity classification category is classified according to the gene feature data to obtain several gene classification categories, including: If any of the families and genera of each of the animal and plant data included in the entity classification category is different, extracting the corresponding base pair arrangement sequence from each of the gene feature data; Calculating the similarity of the arrangement order of base pairs of the plant and animal data included in each entity classification category to obtain multiple arrangement similarities; Several gene classification categories are obtained by classifying according to the numerical values of the plurality of arrangement similarities.

6. The method for classifying animal and plant data according to claim 1, wherein: After the step of classifying the plurality of animal and plant data according to the gene classification categories, the method further includes: Obtaining upload timestamps of the plurality of animal and plant data included in the gene classification category, and generating an encryption key using the upload timestamps; The encryption key is used to encrypt and store the plurality of plant and animal data contained in the gene classification category.

7. The method for classifying animal and plant data according to claim 6, characterized in that: The generating of an encryption key by using the upload timestamp includes: Extracting a plurality of time values from the upload timestamp according to a preset byte length; The plurality of time values are concatenated to generate an encryption key.

8. A classification device for plant and animal data, characterized in that: The device comprises: A feature data extraction module is used to extract feature data from each of the plurality of animal and plant data to be classified after obtaining the plurality of animal and plant data to be classified, wherein the feature data includes physical feature data, environmental feature data and gene feature data; An entity and environment classification module, configured to classify the plurality of animal and plant data according to the physical object feature data and the environmental feature data to obtain a plurality of entity classification categories, wherein each entity classification category includes a plurality of animal and plant data; The gene classification module is used to classify the animal and plant data of each entity classification category according to the gene feature data to obtain a plurality of gene classification categories, and classify the plurality of animal and plant data according to the gene classification categories.

9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for classifying animal and plant data according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to enable a computer to execute the classification method for animal and plant data according to any one of claims 1 to 7.

Images