Identity coding method and device, pet identity coding method and device

Abstract

The embodiments of this specification provide an identity coding method and apparatus, and a domestic animal identity coding method and apparatus. The domestic animal identity coding method includes: performing identity coding on a target object in a category dimension and a feature dimension, respectively, to obtain a first coding segment and a second coding segment; obtaining an identity identification sequence of a subject object to which the target object is subordinate, and extracting a position identification subsequence contained in the identity identification sequence; encoding the object attributes of the target object submitted in advance to obtain an attribute coding segment; obtaining geographic location information of the target object, and searching for a position code corresponding to the geographic location information based on a preset geographic location-code correspondence; determining whether the position code corresponding to the geographic location information is consistent with the position identification subsequence; if so, concatenating the position identification subsequence and the attribute coding segment to obtain a third coding segment; and concatenating the first coding segment, the second coding segment, and the third coding segment to obtain an identity coding sequence for the target object.

Description

[0001] This application is a divisional application of application number 201911168383.2, with an application date of November 25, 2019, and the invention name is “Identity coding method and device, domesticated animal identity coding method and device”. Technical Field

[0002] The embodiments of this specification relate to the field of coding technology, and more particularly to an identity coding method and device, and a pet identity coding method and device. Background Art

[0003] With the acceleration of the pace of social development, the work and life pressures faced by everyone as a participant in social development are also increasing. In order to enrich their lives without bringing too much burden to their lives, more and more people like to keep pets. While raising pets, they can make themselves feel fulfilled and it also helps their physical and mental health a lot. Especially for some elderly people living alone whose children are working hard in other places, the company of pets will make the elderly's life happier, and for some well-trained pets, when some accidents happen to the elderly, such as when they are sick, pets can also act as an alarm. Pets are equivalent to a member of the family for their owners and are very important. Therefore, many pet-oriented services have emerged, such as pet hospitals, pet bathing, pet insurance, etc.

[0004] In the process of providing services for pets, in order to facilitate the management of pets and provide better services to pets, it is necessary to provide personalized services to pets based on accurate identification of pets, so as to improve the satisfaction of pet services. Summary of the Invention

[0005] In view of this, embodiments of this specification provide an identity encoding method, an identity encoding device, a pet identity encoding method, a pet identity encoding device, two computing devices, and two computer-readable storage media.

[0006] The embodiment of this specification provides an identity coding method, including:

[0007] Performing feature recognition on the feature information of the target object according to the feature type of the feature information, and determining the attribute category of the target object based on the feature recognition result;

[0008] Encoding the attribute category of the target object to obtain a first encoding segment;

[0009] Performing vectorization processing on the object features extracted from the feature information to obtain a feature vector;

[0010] Encoding the feature vector to obtain a second encoding segment corresponding to the object feature;

[0011] The first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object are spliced ​​to obtain an identity coding sequence of the target object.

[0012] Optionally, performing feature recognition on the feature information of the target object according to a feature type of the feature information of the target object, and determining the attribute category of the target object according to the feature recognition result, includes:

[0013] performing sound feature recognition on the sound feature information according to the sound feature type of the sound feature information included in the feature information, and determining the primary attribute category of the target object based on the sound feature recognition result;

[0014] performing image feature recognition on the image feature information according to the image feature type of the image feature information included in the feature information, and determining the secondary attribute category of the target object under the primary attribute category based on the image recognition result;

[0015] The sound feature information and / or image feature information included in the feature information is input into a category detection model of the secondary attribute category to perform category detection, and the third-level attribute category of the target object under the secondary attribute category is output.

[0016] Optionally, encoding the attribute category of the target object to obtain a first encoding segment includes:

[0017] According to a pre-configured attribute category and code mapping relationship, searching for the first-level category code value of the first-level attribute category mapping in the attribute category and code mapping relationship, searching for the second-level category code value of the second-level attribute category mapping within the code range of the first-level attribute category mapping, and searching for the third-level category code value of the third-level attribute category mapping within the code range of the second-level attribute category mapping;

[0018] The first-level category code value with the highest attribute category level is used as the header, and the code values ​​of the attribute category mappings of each level are sequentially spliced ​​in descending order of the attribute category levels to obtain the first code segment.

[0019] Optionally, performing vectorization processing on the object features extracted from the feature information to obtain a feature vector includes:

[0020] Detecting and extracting identity identification features from the image feature information included in the feature information as the object features;

[0021] Performing vectorization processing on the identity identification feature to obtain the feature vector;

[0022] Accordingly, encoding the feature vector to obtain a second encoding segment corresponding to the object feature includes:

[0023] Quantizing and encoding the feature vector using a vector coding algorithm to obtain a vector code;

[0024] Perform code conversion on the vector code to obtain the second code segment, and establish a corresponding relationship between the second code segment and the object feature.

[0025] Optionally, the third encoding segment is encoded in the following manner:

[0026] Acquire a pre-submitted identity sequence of a subject object to which the target object belongs, and extract a position identification subsequence contained in the identity sequence;

[0027] Encoding the object attributes of the target object submitted in advance to obtain attribute encoding segments;

[0028] The position identifier subsequence and the attribute code segment are concatenated to obtain the third code segment.

[0029] Optionally, after the sub-step of obtaining the pre-submitted identity sequence of the subject object to which the target object belongs and extracting the position identifier subsequence contained in the identity sequence is executed, and before the step of concatenating the position identifier subsequence with the attribute code segment to obtain the third code segment is executed, the following steps are included:

[0030] Obtaining the geographic location information of the target object, and searching for a location code corresponding to the geographic location information based on a preset correspondence between geographic locations and codes;

[0031] Determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence;

[0032] If so, execute the sub-step of concatenating the position identifier subsequence with the attribute code segment to obtain the third code segment.

[0033] Optionally, if the result of the determination of whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence is no, perform the following operations:

[0034] Extracting the identity identification feature of the subject object to which the target object belongs from the image feature information included in the feature information;

[0035] Determining whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold;

[0036] If so, encoding the object attributes of the target object submitted in advance to obtain an attribute encoding segment;

[0037] The position code segment and the attribute code segment are concatenated to obtain the third code segment.

[0038] Optionally, the step of splicing the first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object to obtain the identity coding sequence of the target object includes:

[0039] According to the coding splicing order of the first coding segment, the second coding segment and the third coding segment, the first coding segment, the second coding segment and the third coding segment are spliced ​​in sequence, and the identity coding sequence is obtained after the splicing is completed.

[0040] Optionally, after executing the step of splicing the first coding segment, the second coding segment, and the third coding segment obtained by encoding the attribute information of the target object to obtain the identity coding sequence of the target object, the method includes:

[0041] Object identity information of the target object is created based on the identity coding sequence of the target object, the attribute information of the target object, and the image feature information included in the feature information.

[0042] This embodiment of the present invention provides an identity encoding device, comprising:

[0043] an attribute category determination module configured to perform feature recognition on the feature information of the target object according to the feature type of the feature information of the target object, and determine the attribute category of the target object according to the feature recognition result;

[0044] A first encoding module is configured to encode the attribute category of the target object to obtain a first encoding segment;

[0045] a vectorization processing module configured to perform vectorization processing on the object features extracted from the feature information to obtain a feature vector;

[0046] a second encoding module configured to encode the feature vector to obtain a second encoding segment corresponding to the object feature;

[0047] The coding splicing module is configured to splice the first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object to obtain an identity coding sequence of the target object.

[0048] This embodiment of the present invention provides a method for encoding the identity of a domesticated animal, comprising:

[0049] performing feature recognition on the biometric information of the pet according to the biometric type of the biometric information of the pet, and determining the attribute category of the pet according to the recognition result;

[0050] Encoding the attribute category of the feed to obtain a category code segment;

[0051] performing vectorization processing on the biometric features extracted from the biometric feature information to obtain a biometric feature vector;

[0052] Encoding the biometric feature vector to obtain a biometric feature encoding segment corresponding to the biometric feature;

[0053] The category coding segment, the biometric coding segment, and the attribute coding segment obtained by encoding the attribute information of the captive are spliced ​​to obtain the identity coding sequence of the captive.

[0054] Optionally, the performing feature recognition on the biometric information of the captive according to the biometric type of the biometric information of the captive, and determining the attribute category of the captive according to the recognition result, includes:

[0055] performing sound feature recognition on the sound feature information according to the sound feature type of the sound feature information included in the biometric feature information, and determining the type of the captive according to the sound feature recognition result;

[0056] performing image feature recognition on the image feature information according to the image feature type of the image feature information included in the biometric information, and determining the variety of the captive animal under the category based on the image recognition result;

[0057] The sound feature information and / or image feature information included in the biometric feature information is input into the gender detection model of the species to perform category detection, and the gender of the captive under the species is output.

[0058] Optionally, encoding the attribute category of the feed to obtain a category code segment includes:

[0059] According to a pre-configured attribute category and code mapping relationship, searching for the category code value of the category mapping in the attribute category and code mapping relationship, searching for the variety code value of the variety mapping within the code range of the category mapping, and searching for the gender code value of the gender mapping within the code range of the variety mapping;

[0060] The category code value of the highest attribute category level is used as the header, and the code values ​​of the attribute category mappings of each level are sequentially spliced ​​in descending order of the attribute category levels to obtain the category code segment.

[0061] Optionally, the vectorizing the biometric feature extracted from the biometric feature information to obtain a biometric feature vector includes:

[0062] Detecting and extracting identity identification features from the image feature information included in the biometric feature information as the biometric feature;

[0063] Performing vectorization processing on the identity identification feature to obtain the biometric feature vector;

[0064] Accordingly, encoding the biometric feature vector to obtain a biometric feature encoding segment corresponding to the biometric feature includes:

[0065] Quantizing and encoding the biometric feature vector using a vector encoding algorithm to obtain a vector code;

[0066] The vector code is converted to obtain the biometric characteristic code segment, and a corresponding relationship between the biometric characteristic code segment and the biometric characteristic is established.

[0067] Optionally, the attribute encoding segment is encoded in the following manner:

[0068] Obtaining a pre-submitted identity sequence of the breeder to which the feeder belongs, and extracting a position identification subsequence contained in the identity sequence;

[0069] Encoding the pre-submitted age attribute of the pet to obtain an age attribute coding segment;

[0070] The position identification subsequence is concatenated with the age attribute coding segment to obtain the attribute coding segment.

[0071] Optionally, after the steps of obtaining the pre-submitted identity sequence of the owner of the pet and extracting the position identifier subsequence contained in the identity sequence, and before the step of concatenating the position identifier subsequence with the attribute code segment to obtain the attribute code segment are performed, the following steps are included:

[0072] Obtaining geographic location information of the captive, and searching for a location code corresponding to the geographic location information based on a preset correspondence between geographic location and code;

[0073] Determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence;

[0074] If so, execute the step of concatenating the position identifier subsequence with the attribute code segment to obtain the attribute code segment.

[0075] Optionally, if the result of the determination of whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence is no, perform the following operations:

[0076] Extracting the identity identification feature of the breeder to which the pet belongs from the image feature information included in the feature information;

[0077] Determining whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold;

[0078] If yes, encode the pre-submitted age attribute of the pet to obtain an age attribute encoding segment;

[0079] The position code segment is concatenated with the age attribute code segment to obtain the attribute code segment.

[0080] Optionally, the step of splicing the category code segment, the biometric feature code segment, and the attribute code segment obtained by encoding the attribute information of the captive to obtain the identity code sequence of the captive includes:

[0081] According to the coding splicing order of the category coding segment, the biometric coding segment and the attribute coding segment, the category coding segment, the biometric coding segment and the attribute coding segment are spliced ​​in sequence, and the identity coding sequence is obtained after the splicing is completed.

[0082] Optionally, after the step of splicing the category code segment, the biometric feature code segment, and the attribute code segment obtained by encoding the attribute information of the pet to obtain the identity code sequence of the pet is performed, the method further includes:

[0083] The identity information of the pet is created based on the identity coding sequence of the pet, the attribute information of the pet, and the image feature information included in the biometric feature information.

[0084] The embodiment of this specification provides a pet identity encoding device, including:

[0085] an attribute category determination module configured to perform feature recognition on the biometric information of the pet according to the biometric type of the biometric information of the pet, and determine the attribute category of the pet based on the recognition result;

[0086] an attribute category encoding module configured to encode the attribute category of the feed to obtain a category code segment;

[0087] a vectorization processing module configured to perform vectorization processing on the biometric features extracted from the biometric feature information to obtain a biometric feature vector;

[0088] a biometric encoding module configured to encode the biometric vector to obtain a biometric encoding segment corresponding to the biometric;

[0089] The coding splicing module is configured to splice the category coding segment, the biometric coding segment and the attribute coding segment obtained by encoding the attribute information of the pet to obtain the identity coding sequence of the pet.

[0090] An embodiment of this specification provides a computing device, including:

[0091] memory and processor;

[0092] The memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions:

[0093] Performing feature recognition on the feature information of the target object according to the feature type of the feature information, and determining the attribute category of the target object based on the feature recognition result;

[0094] Encoding the attribute category of the target object to obtain a first encoding segment;

[0095] Performing vectorization processing on the object features extracted from the feature information to obtain a feature vector;

[0096] Encoding the feature vector to obtain a second encoding segment corresponding to the object feature;

[0097] The first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object are spliced ​​to obtain an identity coding sequence of the target object.

[0098] An embodiment of this specification provides a computing device, including:

[0099] memory and processor;

[0100] The memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions:

[0101] performing feature recognition on the biometric information of the pet according to the biometric type of the biometric information of the pet, and determining the attribute category of the pet according to the recognition result;

[0102] Encoding the attribute category of the feed to obtain a category code segment;

[0103] performing vectorization processing on the biometric features extracted from the biometric feature information to obtain a biometric feature vector;

[0104] Encoding the biometric feature vector to obtain a biometric feature encoding segment corresponding to the biometric feature;

[0105] The category coding segment, the biometric coding segment, and the attribute coding segment obtained by encoding the attribute information of the captive are spliced ​​to obtain the identity coding sequence of the captive.

[0106] The embodiments of this specification provide a computer-readable storage medium storing computer instructions, which implement the steps of the identity encoding method when executed by a processor.

[0107] The embodiments of this specification provide a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the method for encoding the identity of a domesticated animal.

[0108] The identity coding method provided in an embodiment of the present specification realizes the identity coding of the target object in the category dimension by encoding the attribute category of the target object, realizes the identity coding of the target object in the feature dimension by encoding the features after vectorization processing, and realizes the identity coding of the target object in the attribute dimension by encoding the attribute information of the target object. Finally, the coding segments obtained by encoding each dimension are spliced ​​to obtain the identity coding sequence of the target object, thereby improving the accuracy and effectiveness of the identity coding of the target object, thereby being more conducive to the promotion and application of the identity coding system of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0109] Figure 1 This is a flowchart of an identity coding method provided in an embodiment of this specification;

[0110] Figure 2 This is a schematic diagram of an identity coding device provided in an embodiment of this specification;

[0111] Figure 3 This is a flowchart of a method for encoding the identity of a domesticated animal provided in an embodiment of this specification;

[0112] Figure 4 Schematic diagram of a pet identity coding device provided in an embodiment of this specification;

[0113] Figure 5 This is a structural block diagram of a computing device provided in an embodiment of this specification;

[0114] Figure 6 This is a structural block diagram of another computing device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0115] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0116] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0117] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0118] One embodiment of this specification provides an identity encoding method. One or more embodiments of this specification also provide an identity encoding device, a pet identity encoding method, a pet identity encoding device, two computing devices, and two computer-readable storage media. The following details each of the embodiments provided herein, along with the accompanying figures, and illustrates each step of the method.

[0119] An embodiment of an identity coding method provided in this specification is as follows:

[0120] Refer to the attached Figure 1 , which shows a processing flow chart of an identity encoding method provided in an embodiment of this specification.

[0121] Step S102 : performing feature recognition on the feature information of the target object according to the feature type of the feature information of the target object, and determining the attribute category of the target object according to the feature recognition result.

[0122] The target object in this embodiment refers to an object that requires identity coding. This embodiment uses pets as an example to illustrate the target object. In addition, the target object can also be a living organism such as an animal or plant. Pets in this embodiment include pets that enhance the user's emotional pleasure (such as canines, cats, and amphibians), animals raised by users for economic purposes (such as poultry and livestock), and animals raised for social welfare or environmental protection purposes (such as protected animals raised in animal sanctuaries and stray animals raised by social welfare organizations for social welfare purposes).

[0123] This embodiment uses pets as an example to illustrate the target object and specifically describes the pet identity encoding process. The identity encoding process for two types of pets, namely, animals raised for economic purposes and animals raised for social welfare or environmental protection purposes, can be found in the specific implementation of the pet identity encoding process provided in this embodiment, and will not be further described in detail in this embodiment.

[0124] In this embodiment, in the process of identity encoding of the target object, the identity encoding of the target object is performed based on the three encoding dimensions of category dimension, feature dimension and attribute dimension. Specifically, the identity encoding of the target object is performed in the category dimension, feature dimension and attribute dimension respectively, and finally the encoding segments of these three encoding dimensions are integrated into an identity encoding sequence in a splicing manner, so as to realize the identity encoding of the target object.

[0125] In a specific implementation, the target object is first identified in the category dimension. Specifically, the feature information of the target object is identified according to its feature type, and the attribute category of the target object is further determined based on the feature identification result. In order to enhance the accuracy of feature identification and thereby improve the effectiveness of the attribute category of the target object determined based on the feature identification result, an optional implementation provided in this embodiment combines characteristic information of different feature types for feature identification and attribute category determination, specifically implemented as follows:

[0126] 1) performing sound feature recognition on the sound feature information according to the sound feature type of the sound feature information included in the feature information, and determining the primary attribute category of the target object based on the sound feature recognition result;

[0127] 2) performing image feature recognition on the image feature information according to the image feature type of the image feature information included in the feature information, and determining the secondary attribute category of the target object under the primary attribute category based on the image recognition result;

[0128] 3) Inputting the sound feature information and / or image feature information included in the feature information into a category detection model of the secondary attribute category to perform category detection, and outputting the third-level attribute category of the target object under the secondary attribute category.

[0129] For example, in the process of encoding the identity of a pet, the pre-collected characteristic information of the pet includes the pet's voiceprint information and the pet's full-body photo, frontal photo, and nose print photo. The voiceprint information is the characteristic information of the sound type, and the full-body photo, frontal photo, and nose print photo are the characteristic information of the image type.

[0130] First, according to the characteristic information of the sound type (calling voiceprint information) contained in the characteristic information, the pet's calling voiceprint information is subjected to voiceprint feature recognition. If the voiceprint feature recognition result shows that the calling voiceprint is the call of a dog pet, the type of the pet is determined to be a dog based on the voiceprint feature recognition result.

[0131] Then, according to the feature information of the image type (full body photo) included in the feature information, image feature recognition is performed on the full body photo of the pet. If the image feature recognition result shows that the shape and color of the spots on the pet's body are most similar to the shape and color of the spots on the body of a shepherd dog, then the breed of the pet is determined to be a shepherd dog under the dog category based on the image feature recognition result.

[0132] Finally, the pet's voiceprint information, as well as the pet's full-body photo, frontal face photo, and nose print photo are input into a pre-trained gender detection model for gender detection. The gender detection model is used to detect the pet's gender based on the input feature information. After detection by the gender detection model, the output of the pet's gender is female.

[0133] Step S104: Encode the attribute category of the target object to obtain a first encoding segment.

[0134] After determining the attribute category of the target object in step S102, the attribute category of the target object is encoded to obtain a first encoding segment. In an optional implementation provided by this embodiment, the attribute categories of the target object at various levels are combined during the encoding process to improve the effectiveness of identity encoding in the category dimension. Specifically, the attribute categories of the target object are encoded in the following manner:

[0135] According to a pre-configured attribute category and code mapping relationship, searching for the first-level category code value of the first-level attribute category mapping in the attribute category and code mapping relationship, searching for the second-level category code value of the second-level attribute category mapping within the code range of the first-level attribute category mapping, and searching for the third-level category code value of the third-level attribute category mapping within the code range of the second-level attribute category mapping;

[0136] The first-level category code value with the highest attribute category level is used as the header, and the code values ​​of the attribute category mappings of each level are sequentially spliced ​​in descending order of the attribute category levels to obtain the first code segment.

[0137] Continuing with the above example, according to the pre-configured pet attribute category and code mapping relationship table, the code value mapped to the dog pet (first-level attribute category) is searched in the pet attribute category and code mapping relationship table. The search result shows that the code value mapped to the dog pet is "02";

[0138] Furthermore, in the code range of the dog pet mapping in the pet attribute category and code mapping relationship table, the code value mapped for the shepherd dog (secondary attribute category) is searched, and the search result shows that the code value mapped for the shepherd dog is "334";

[0139] Furthermore, in the code range of the shepherd dog mapping in the pet attribute category and code mapping relationship table, the code value mapped when the pet's gender is female is searched, and the search result shows that the code value mapped when the pet's gender is female is "2";

[0140] After finding the code value mapped for a female shepherd dog, use the code value "02" mapped for the dog pet as the head, and then sequentially concatenate the code value "334" mapped for the shepherd dog and the code value "2" mapped for the female with the head. After the concatenation is completed, the category code segment of the female shepherd dog is "023342."

[0141] Step S106: performing vectorization processing on the object features extracted from the feature information to obtain a feature vector.

[0142] As described above, this embodiment performs identity encoding on the target object based on the three coding dimensions of category dimension, feature dimension and attribute dimension. Specifically, the target object is identity encoded in the category dimension, feature dimension and attribute dimension respectively, and finally the coding segments of these three coding dimensions are integrated into an identity coding sequence in a splicing manner, so as to realize the identity encoding of the target object.

[0143] In specific implementations, in the process of encoding the identity of the target object in the feature dimension, due to the complexity of the characteristics of the target object, the feature extraction and processing process is often relatively complicated. Here, the efficiency of feature extraction and processing is improved by vectorizing the object features extracted from the feature information, and finally the identity of the target object is encoded in the feature dimension using the obtained feature vector. In an optional implementation provided by this embodiment, the object features extracted from the feature information are vectorized, and the specific implementation is as follows:

[0144] Detecting and extracting identity identification features from the image feature information included in the feature information as the object features;

[0145] Vectorization is performed on the identity identification feature to obtain the feature vector.

[0146] For example, in the process of encoding the identity of a pet, the pre-collected characteristic information of the pet includes the pet's voiceprint information, as well as the pet's full-body photo, frontal photo, and nose print photo. Among them, the nose print photo that represents the pet's biological characteristics is first detected, and the detected nose print features are extracted. Then, the extracted nose print features are vectorized to obtain the nose print feature vector Vector.

[0147] Step S108: Encode the feature vector to obtain a second encoding segment corresponding to the object feature.

[0148] In step S106, the object features extracted from the feature information are vectorized to obtain the feature vector. In this step, the feature vector is encoded to implement identity encoding of the target object using the feature dimension. The specific encoding process is as follows:

[0149] Quantizing and encoding the feature vector using a vector coding algorithm to obtain a vector code;

[0150] Perform code conversion on the vector code to obtain the second code segment, and establish a corresponding relationship between the second code segment and the object feature.

[0151] In the above example, the nose print feature vector obtained after vectorization processing of the nose print features extracted from the pet's nose print photo is Vector. On this basis, the nose print feature vector Vector is quantized and encoded using a vector encoding algorithm. The encoding result is a 32-bit vector code. The vector code is then encoded and converted using encoding compression or sampling to obtain a 6-bit biometric coding segment "100008". The biometric coding segment "100008" is the coding segment that characterizes the pet's nose print features. By establishing a corresponding relationship between the biometric coding segment "100008" and the pet's nose print features, the 6-bit biometric coding segment "100008" is used to represent the pet's biometric features.

[0152] In this step, the target object is firstly identity-encoded in the category dimension through steps S102 and S104, and then the target object is identity-encoded in the feature dimension through steps S106 and S108. It should be noted that the encoding order of the target object is not limited to this. The target object can also be identity-encoded in the feature dimension first, and then in the category dimension; or, the target object can be identity-encoded in the category dimension and the feature dimension by using a parallel processing method. The specific implementation can refer to the above steps S102 and S108, which will not be repeated here.

[0153] Step S110 , concatenating the first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object to obtain an identity coding sequence of the target object.

[0154] In addition to implementing identity coding of the target object in the category dimension and feature dimension in steps S102 to S108, identity coding of the target object is also required in the attribute dimension, which is specifically implemented in the following manner:

[0155] Acquire a pre-submitted identity sequence of a subject object to which the target object belongs, and extract a position identification subsequence contained in the identity sequence;

[0156] Encoding the object attributes of the target object submitted in advance to obtain attribute encoding segments;

[0157] The position identifier subsequence and the attribute code segment are concatenated to obtain the third code segment.

[0158] As described above, the identity encoding of the target object in the attribute dimension depends on the identity identification sequence of the subject object to which the target object belongs. Accordingly, the accuracy of the identity encoding of the target object in the attribute dimension also depends on whether the identity identification sequence of the subject object is accurate or valid. In an optional implementation provided by this embodiment, in order to improve the accuracy and validity of the identity identification sequence of the subject object, in the process of identity encoding the target object in the attribute dimension, the validity of the identity identification sequence of the subject object is verified. Specifically, the validity verification is performed in the following manner:

[0159] 1) Obtaining the geographic location information of the target object, and searching for the location code corresponding to the geographic location information based on a preset correspondence between geographic location and code;

[0160] 2) determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence;

[0161] If so, it indicates that the validity verification of the identity identification sequence of the subject object has passed, and the sub-step of splicing the position identification sub-sequence with the attribute code segment to obtain the third code segment is executed;

[0162] If not, further verify the validity of the identity sequence of the subject object, which is specifically implemented as follows:

[0163] (a) extracting an identity identification feature of a subject object to which the target object belongs from image feature information included in the feature information;

[0164] (b) determining whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold;

[0165] If so, it indicates that the identity sequence of the subject object matches the subject object, and the object attributes of the target object submitted in advance are encoded to obtain an attribute encoding segment;

[0166] splicing the position code segment with the attribute code segment to obtain the third code segment;

[0167] If not, it indicates that the validity verification of the identity sequence of the subject object has failed, and a reminder to re-enter the identity sequence is issued.

[0168] For example, in the process of encoding the identity of a pet, the ID number of the pet owner that was previously submitted is first obtained, and the location identifier subsequence contained in the ID number is extracted (i.e., the first 6 digits of the ID number used to identify the pet owner's address, "340827");

[0169] Then, the pet's geographic location information is obtained, and the location code corresponding to the pet's geographic location information is determined, and whether the location code is consistent with the location identification subsequence contained in the pet owner's ID number is determined;

[0170] If there is any inconsistency, the head portrait features of the pet owner are extracted from the human-pet photo contained in the pet's feature information, and the identity validity of the pet owner is verified by judging whether the ID number of the pet owner submitted in advance is consistent with the ID number corresponding to the head portrait features of the pet owner. If they are consistent, the pre-submitted pet's date of birth "January 19, 2010" is encoded to obtain the date of birth code segment "20100119", and the position identifier subsequence "340827" is spliced ​​with the date of birth code segment "20100119". After the splicing is completed, the pet's attribute code segment "34082720100119" is obtained.

[0171] After encoding the identity of the target object in the three coding dimensions of category dimension, feature dimension and attribute dimension, the first coding segment obtained by encoding the category dimension, the second coding segment obtained by encoding the feature dimension and the third coding segment obtained by encoding the attribute dimension are spliced ​​to obtain the identity coding sequence of the target object.

[0172] In order to improve the splicing efficiency of the identity coding sequence, this embodiment provides an optional implementation method, in which the first coding segment, the second coding segment and the third coding segment are spliced ​​in sequence according to the coding splicing order of the first coding segment, the second coding segment and the third coding segment, and the identity coding sequence is obtained after the splicing is completed.

[0173] Continuing with the above example, the category coding segment obtained by encoding the pet in the category dimension is "023342", the biometric coding segment obtained by encoding the pet in the feature dimension is "100008", and the attribute coding segment obtained by encoding the pet in the attribute dimension is "34082720100119". The attribute coding segment, category coding segment, and biometric coding segment are spliced ​​in the coding splicing order of "attribute dimension->category dimension->feature dimension". The identity coding sequence obtained after splicing is "34082720100119023342100008".

[0174] In actual applications, after the target object is identity-encoded to obtain the identity coding sequence of the target object, the object identity information of the target object can be created based on the identity coding sequence of the target object, the attribute information of the target object, and the image feature information contained in the feature information. For example, a pet ID card of a pet can be created based on the identity coding sequence of the pet, thereby applying the identity coding sequence of the target object to a specific scenario, which is conducive to the application and promotion of the identity coding of the target object.

[0175] To sum up, the identity coding method realizes the identity coding of the target object in the category dimension by encoding the attribute category of the target object, realizes the identity coding of the target object in the feature dimension by encoding the features after vectorization processing, and realizes the identity coding of the target object in the attribute dimension by encoding the attribute information of the target object. Finally, the coding segments obtained by encoding each dimension are spliced ​​to obtain the identity coding sequence of the target object, which improves the accuracy and effectiveness of the identity coding of the target object, and is more conducive to the promotion and application of the identity coding system of the target object.

[0176] An embodiment of an identity encoding device provided in this specification is as follows:

[0177] In the above embodiment, an identity coding method is provided, and correspondingly, an identity coding device is also provided, which will be described below with reference to the accompanying drawings.

[0178] Refer to the attached Figure 2 , which shows a schematic diagram of an identity encoding device provided by this embodiment.

[0179] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0180] This specification provides an identity encoding device, including:

[0181] The attribute category determination module 202 is configured to perform feature recognition on the feature information of the target object according to the feature type of the feature information, and determine the attribute category of the target object according to the feature recognition result;

[0182] A first encoding module 204 is configured to encode the attribute category of the target object to obtain a first encoding segment;

[0183] A vectorization processing module 206 is configured to perform vectorization processing on the object features extracted from the feature information to obtain a feature vector;

[0184] A second encoding module 208 is configured to encode the feature vector to obtain a second encoding segment corresponding to the object feature;

[0185] The coding splicing module 210 is configured to splice the first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object to obtain an identity coding sequence of the target object.

[0186] Optionally, the attribute category determination module 202 includes:

[0187] a primary attribute category determination submodule configured to perform sound feature recognition on the sound feature information according to the sound feature type of the sound feature information included in the feature information, and determine the primary attribute category of the target object based on the sound feature recognition result;

[0188] a secondary attribute category determination submodule configured to perform image feature recognition on the image feature information according to the image feature type of the image feature information included in the feature information, and determine the secondary attribute category of the target object under the primary attribute category based on the image recognition result;

[0189] The tertiary attribute category determination submodule is configured to perform category detection by inputting the sound feature information and / or image feature information contained in the feature information into the category detection model of the secondary attribute category, and output the tertiary attribute category of the target object under the secondary attribute category.

[0190] Optionally, the first encoding module 204 includes:

[0191] a code value determination submodule configured to search, based on a pre-configured attribute category and code mapping relationship, for the first-level category code value of the first-level attribute category mapping in the attribute category and code mapping relationship, search for the second-level category code value of the second-level attribute category mapping within the code range of the first-level attribute category mapping, and search for the third-level category code value of the third-level attribute category mapping within the code range of the second-level attribute category mapping;

[0192] The splicing submodule is configured to use the first-level category code value with the highest attribute category level as the header, and splice the code values ​​mapped by the attribute categories of each level in descending order to obtain the first code segment.

[0193] Optionally, the vectorized processing module 206 includes:

[0194] a detection and extraction submodule, configured to detect and extract identity identification features from the image feature information contained in the feature information as the object features;

[0195] A vectorization processing submodule is configured to perform vectorization processing on the identity identification feature to obtain the feature vector;

[0196] Accordingly, the second encoding module 208 includes:

[0197] a quantization coding submodule, configured to perform quantization coding on the feature vector using a vector coding algorithm to obtain a vector code;

[0198] The encoding conversion submodule is configured to perform encoding conversion on the vector encoding to obtain the second encoding segment and establish a corresponding relationship between the second encoding segment and the object feature.

[0199] Optionally, the third encoding segment is encoded by running the following submodules:

[0200] a position identifier subsequence extraction submodule configured to obtain a pre-submitted identity identifier sequence of a subject object to which the target object belongs, and extract a position identifier subsequence contained in the identity identifier sequence;

[0201] An object attribute encoding submodule is configured to encode the object attributes of the target object submitted in advance to obtain an attribute encoding segment;

[0202] The attribute coding segment splicing submodule is configured to splice the position identifier subsequence with the attribute coding segment to obtain the third coding segment.

[0203] Optionally, the third encoding segment is further encoded by running the following submodules:

[0204] a location code search submodule configured to obtain the location information of the target object and search for the location code corresponding to the location information based on a preset correspondence between the location and the code;

[0205] a position code determination submodule, configured to determine whether the position code corresponding to the geographic location information is consistent with the position identification subsequence;

[0206] If so, run the attribute coding segment splicing submodule.

[0207] Optionally, if the position code judgment submodule outputs a judgment result of no after running, the following submodules are run:

[0208] an extraction submodule configured to extract an identity identification feature of a subject object to which the target object belongs from the image feature information included in the feature information;

[0209] An identity identification feature judgment submodule is configured to judge whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold;

[0210] If so, run the encoding submodule and the splicing submodule;

[0211] The encoding submodule is configured to encode the object attributes of the target object submitted in advance to obtain attribute encoding segments;

[0212] The splicing submodule is configured to splice the position code segment and the attribute code segment to obtain the third code segment.

[0213] Optionally, the coding splicing module 210 is specifically configured to splice the first coding segment, the second coding segment and the third coding segment in sequence according to the coding splicing order of the first coding segment, the second coding segment and the third coding segment, and obtain the identity coding sequence after splicing is completed.

[0214] Optionally, the identity encoding device includes:

[0215] The object identity information creation module is configured to create the object identity information of the target object based on the identity coding sequence of the target object, the attribute information of the target object, and the image feature information included in the feature information.

[0216] An embodiment of a method for encoding the identity of a domesticated animal provided in this specification is as follows:

[0217] Refer to the attached Figure 3 , which shows a processing flow chart of a pet identity coding method provided in an embodiment of this specification, wherein the pet identity coding method includes steps S302 to S310.

[0218] Step S302: performing feature recognition on the biometric information of the pet according to its biometric type, and determining the attribute category of the pet according to the recognition result.

[0219] The pets described in this embodiment include pets that enhance the user's sense of pleasure on an emotional level (dog pets, cat pets, amphibian pets, etc.), and also include animals raised by users for economic purposes (such as poultry, livestock, etc.). In addition, they also include animals raised for social welfare or environmental protection purposes (such as protected animals raised in animal sanctuaries, stray animals raised by social welfare organizations for social welfare purposes, etc.).

[0220] This embodiment uses pets as an example to illustrate the pet identity encoding process. The identity encoding process for two types of pets, namely, animals raised for economic purposes and animals raised for social welfare or environmental protection purposes, can be found in the specific implementation of the pet identity encoding process provided in this embodiment, and will not be further described in detail in this embodiment.

[0221] In this embodiment, during the identity coding of the pet, the identity coding of the pet is performed based on three coding dimensions: category dimension, feature dimension, and attribute dimension. Specifically, the identity coding of the pet is performed based on the category dimension, feature dimension, and attribute dimension respectively, and finally the coding segments of the three coding dimensions are spliced ​​together to form an identity coding sequence, thereby realizing the identity coding of the pet.

[0222] In a specific implementation, the animal is first coded for identity based on the category dimension. Specifically, the biometric information is identified based on its biometric type, and the animal's attribute category is further determined based on the identification results. To enhance the accuracy of feature identification and thereby improve the effectiveness of the attribute category of the animal determined based on the feature identification results, this embodiment provides an optional implementation that combines characteristic information of different feature types for feature identification and attribute category determination. This is specifically achieved in the following manner:

[0223] 1) performing sound feature recognition on the sound feature information according to the sound feature type of the sound feature information included in the biometric feature information, and determining the type of the animal based on the sound feature recognition result;

[0224] 2) performing image feature recognition on the image feature information according to the image feature type of the image feature information included in the biometric information, and determining the variety of the captive animal under the category based on the image recognition result;

[0225] 3) Inputting the sound feature information and / or image feature information included in the biometric information into a gender detection model of the species to perform category detection, and outputting the gender of the pet under the species.

[0226] For example, in the process of encoding the identity of a pet, the pre-collected characteristic information of the pet includes the pet's voiceprint information and the pet's full-body photo, frontal photo, and nose print photo. The voiceprint information is the characteristic information of the sound type, and the full-body photo, frontal photo, and nose print photo are the characteristic information of the image type.

[0227] First, according to the characteristic information of the sound type (calling voiceprint information) contained in the characteristic information, the pet's calling voiceprint information is subjected to voiceprint feature recognition. If the voiceprint feature recognition result shows that the calling voiceprint is the call of a dog pet, the type of the pet is determined to be a dog based on the voiceprint feature recognition result.

[0228] Then, according to the feature information of the image type (full body photo) included in the feature information, image feature recognition is performed on the full body photo of the pet. If the image feature recognition result shows that the shape and color of the spots on the pet's body are most similar to the shape and color of the spots on the body of a shepherd dog, then the breed of the pet is determined to be a shepherd dog under the dog category based on the image feature recognition result.

[0229] Finally, the pet's voiceprint information, as well as the pet's full-body photo, frontal face photo, and nose print photo are input into a pre-trained gender detection model for gender detection. The gender detection model is used to detect the pet's gender based on the input feature information. After detection by the gender detection model, the output of the pet's gender is female.

[0230] Step S304: Encode the attribute category of the feed to obtain a category code segment.

[0231] After determining the attribute category of the pet in step S302, the attribute category of the pet is encoded to obtain a category code segment. In an optional implementation provided by this embodiment, the encoding process combines the attribute categories of the pet at various levels to improve the effectiveness of identity coding in the category dimension. Specifically, the attribute category of the pet is encoded in the following manner:

[0232] According to a pre-configured attribute category and code mapping relationship, searching for the category code value of the category mapping in the attribute category and code mapping relationship, searching for the variety code value of the variety mapping within the code range of the category mapping, and searching for the gender code value of the gender mapping within the code range of the variety mapping;

[0233] The category code value of the highest attribute category level is used as the header, and the code values ​​of the attribute category mappings of each level are sequentially spliced ​​in descending order of the attribute category levels to obtain the category code segment.

[0234] Continuing with the above example, according to the pre-configured pet attribute category and code mapping relationship table, the code value mapped to the dog pet (first-level attribute category) is searched in the pet attribute category and code mapping relationship table. The search result shows that the code value mapped to the dog pet is "02";

[0235] Furthermore, in the code range of the dog pet mapping in the pet attribute category and code mapping relationship table, the code value mapped for the shepherd dog (secondary attribute category) is searched, and the search result shows that the code value mapped for the shepherd dog is "334";

[0236] Furthermore, in the code range of the shepherd dog mapping in the pet attribute category and code mapping relationship table, the code value mapped when the pet's gender is female is searched, and the search result shows that the code value mapped when the pet's gender is female is "2";

[0237] After finding the code value mapped for a female shepherd dog, use the code value "02" mapped for the dog pet as the head, and then sequentially concatenate the code value "334" mapped for the shepherd dog and the code value "2" mapped for the female with the head. After the concatenation is completed, the category code segment of the female shepherd dog is "023342."

[0238] Step S306: performing vectorization processing on the biometric features extracted from the biometric feature information to obtain a biometric feature vector.

[0239] In specific implementations, the process of encoding the identity of the captive in the feature dimension is often complex due to the complexity of the captive's features. Therefore, the efficiency of feature extraction and processing is improved by vectorizing the biometric features extracted from the feature information. Ultimately, the obtained feature vector is used to encode the captive's identity in the feature dimension. In an optional implementation provided by this embodiment, vectorizing the biometric features extracted from the feature information is specifically implemented as follows:

[0240] Detecting and extracting identity identification features from the image feature information included in the biometric feature information as the biometric feature;

[0241] Vectorization is performed on the identity identification feature to obtain the biometric feature vector.

[0242] For example, in the process of encoding the identity of a pet, the pre-collected characteristic information of the pet includes the pet's voiceprint information, as well as the pet's full-body photo, frontal photo, and nose print photo. Among them, the nose print photo that represents the pet's biological characteristics is first detected, and the detected nose print features are extracted. Then, the extracted nose print features are vectorized to obtain the nose print feature vector Vector.

[0243] Step S308: Encode the biometric feature vector to obtain a biometric feature encoding segment corresponding to the biometric feature.

[0244] After the above step S306 performs vectorization processing on the biometric features extracted from the feature information to obtain the biometric feature vector, in this step, the biometric feature vector is encoded to achieve identity encoding of the animal based on the feature dimension. The specific encoding process is as follows:

[0245] Quantizing and encoding the biometric feature vector using a vector encoding algorithm to obtain a vector code;

[0246] The vector code is converted to obtain the biometric characteristic code segment, and a corresponding relationship between the biometric characteristic code segment and the biometric characteristic is established.

[0247] In the above example, the nose print feature vector obtained after vectorization processing of the nose print features extracted from the pet's nose print photo is Vector. On this basis, the nose print feature vector Vector is quantized and encoded using a vector encoding algorithm. The encoding result is a 32-bit vector code. The vector code is then encoded and converted using encoding compression or sampling to obtain a 6-bit biometric coding segment "100008". The biometric coding segment "100008" is the coding segment that characterizes the pet's nose print features. By establishing a corresponding relationship between the biometric coding segment "100008" and the pet's nose print features, the 6-bit biometric coding segment "100008" is used to represent the pet's biometric features.

[0248] In this step, the identity of the pet is firstly coded in the category dimension through steps S302 and S304, and then the identity of the pet is coded in the feature dimension through steps S306 and S308. It should be noted that the coding order of the pet is not limited to this. The identity of the pet can also be coded in the feature dimension first, and then in the category dimension; or the identity of the pet can be coded in the category dimension and the feature dimension in parallel processing. The specific implementation refers to the above steps S302 and S308, which will not be repeated here.

[0249] Step S310: splicing the category code segment, the biometric feature code segment, and the attribute code segment obtained by encoding the attribute information of the pet to obtain an identity code sequence of the pet.

[0250] In addition to implementing identity coding of the pet in the category dimension and feature dimension in steps S302 to S308, identity coding of the pet in the attribute dimension is also required, which is specifically implemented in the following manner:

[0251] Obtaining a pre-submitted identity sequence of the breeder to which the feeder belongs, and extracting a position identification subsequence contained in the identity sequence;

[0252] Encoding the pre-submitted age attribute of the pet to obtain an age attribute coding segment;

[0253] The position identification subsequence is concatenated with the age attribute coding segment to obtain the attribute coding segment.

[0254] As described above, the identity coding of the pet in the attribute dimension depends on the identity identification sequence of the keeper to which the pet belongs. Accordingly, the accuracy of the identity coding of the pet in the attribute dimension also depends on whether the identity identification sequence of the keeper is accurate or valid. In an optional implementation provided by this embodiment, to improve the accuracy and validity of the keeper's identity identification sequence, the validity of the keeper's identity identification sequence is verified during the identity coding of the pet in the attribute dimension. Specifically, the validity verification is performed in the following manner:

[0255] 1) obtaining the geographical location information of the pet, and searching for the location code corresponding to the geographical location information based on a preset correspondence between the geographical location and the code;

[0256] 2) determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence;

[0257] If so, it indicates that the validity verification of the identity sequence of the owner of the animal has passed, and the step of concatenating the position identifier subsequence with the attribute code segment to obtain the attribute code segment is executed;

[0258] If not, further verify the validity of the identity sequence of the owner of the animal, which is specifically implemented as follows:

[0259] (a) extracting an identity identification feature of the breeder to which the animal belongs from image feature information included in the feature information;

[0260] (b) determining whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold;

[0261] If yes, it indicates that the identity sequence of the breeder matches the breeder, and the age attribute of the breeder submitted in advance is encoded to obtain an age attribute encoding segment;

[0262] splicing the position code and the age attribute code segment to obtain the attribute code segment;

[0263] If not, it indicates that the validity verification of the identity sequence of the breeder to which the pet belongs has failed, and a reminder to re-enter the identity sequence is issued.

[0264] For example, in the process of encoding the identity of a pet, the ID number of the pet owner that was previously submitted is first obtained, and the location identifier subsequence contained in the ID number is extracted (i.e., the first 6 digits of the ID number used to identify the pet owner's address, "340827");

[0265] Then, the pet's geographic location information is obtained, and the location code corresponding to the pet's geographic location information is determined, and whether the location code is consistent with the location identification subsequence contained in the pet owner's ID number is determined;

[0266] If there is any inconsistency, the head portrait features of the pet owner are extracted from the human-pet photo contained in the pet's feature information, and the identity validity of the pet owner is verified by judging whether the ID number of the pet owner submitted in advance is consistent with the ID number corresponding to the head portrait features of the pet owner. If they are consistent, the pre-submitted pet's date of birth "January 19, 2010" is encoded to obtain the date of birth code segment "20100119", and the position identifier subsequence "340827" is spliced ​​with the date of birth code segment "20100119". After the splicing is completed, the pet's attribute code segment "34082720100119" is obtained.

[0267] After encoding the identity of the captive in the three dimensions of category dimension, feature dimension and attribute dimension, the category coding segment obtained by encoding the category dimension, the biometric coding segment obtained by encoding the feature dimension and the attribute coding segment obtained by encoding the attribute dimension are spliced ​​to obtain the identity coding sequence of the captive.

[0268] In order to improve the splicing efficiency of the identity coding sequence, this embodiment provides an optional implementation method, in which the category coding segment, the biometric coding segment and the attribute coding segment are spliced ​​in sequence according to the coding splicing order of the category coding segment, the biometric coding segment and the attribute coding segment, and the identity coding sequence is obtained after the splicing is completed.

[0269] Continuing with the above example, the category coding segment obtained by encoding the pet in the category dimension is "023342", the biometric coding segment obtained by encoding the pet in the feature dimension is "100008", and the attribute coding segment obtained by encoding the pet in the attribute dimension is "34082720100119". The attribute coding segment, category coding segment, and biometric coding segment are spliced ​​in the coding splicing order of "attribute dimension->category dimension->feature dimension". The identity coding sequence obtained after splicing is "34082720100119023342100008".

[0270] In practical applications, after the pet is identity-coded to obtain its identity coding sequence, the pet's identity information can be created based on the pet's identity coding sequence, its attribute information, and the image feature information included in the feature information. For example, a pet ID card can be created based on the pet's identity coding sequence, thereby applying the pet's identity coding sequence to specific scenarios, which is beneficial to the application of the pet's identity coding method.

[0271] In summary, the method for encoding the identity of domestic animals realizes the identity encoding of domestic animals in the category dimension by encoding the attribute categories of domestic animals, realizes the identity encoding of domestic animals in the feature dimension by encoding the features after vectorization processing, and realizes the identity encoding of domestic animals in the attribute dimension by encoding the attribute information of domestic animals. Finally, the coding segments obtained by encoding each dimension are spliced ​​to obtain the identity coding sequence of the domestic animal, which improves the accuracy and effectiveness of the identity coding of domestic animals, thereby being more conducive to the promotion and application of the identity coding system of domestic animals.

[0272] An embodiment of a pet identity coding device provided in this specification is as follows:

[0273] In the above embodiment, a pet identity coding method is provided. Correspondingly, a pet identity coding device is also provided, which will be described below with reference to the accompanying drawings.

[0274] Refer to the attached Figure 4 , which shows a schematic diagram of a domesticated animal identity coding device provided by this embodiment.

[0275] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0276] This specification provides a pet identity coding device, including:

[0277] The attribute category determination module 402 is configured to perform feature recognition on the biometric information of the pet according to the biometric type of the biometric information of the pet, and determine the attribute category of the pet based on the recognition result;

[0278] The attribute category encoding module 404 is configured to encode the attribute category of the feed to obtain a category code segment;

[0279] a vectorization processing module 406 configured to perform vectorization processing on the biometric features extracted from the biometric feature information to obtain a biometric feature vector;

[0280] A biometric encoding module 408 is configured to encode the biometric feature vector to obtain a biometric encoding segment corresponding to the biometric feature;

[0281] The code splicing module 410 is configured to splice the category code segment, the biometric feature code segment, and the attribute code segment obtained by encoding the attribute information of the pet to obtain the identity code sequence of the pet.

[0282] Optionally, the attribute category determination module 402 includes:

[0283] a type determination submodule configured to perform sound feature recognition on the sound feature information according to the sound feature type of the sound feature information included in the biometric information, and determine the type of the captive according to the sound feature recognition result;

[0284] a variety determination submodule configured to perform image feature recognition on the image feature information according to the image feature type of the image feature information included in the biometric information, and determine the variety of the captive animal under the category based on the image recognition result;

[0285] The gender determination submodule is configured to input the sound feature information and / or image feature information included in the biometric information into the gender detection model of the species to perform category detection and output the gender of the captive under the species.

[0286] Optionally, the attribute category encoding module 404 includes:

[0287] a search submodule configured to search, according to a preconfigured attribute category and code mapping relationship, for the category code value of the category mapping in the attribute category and code mapping relationship, search for the variety code value of the variety mapping within the code range of the category mapping, and search for the gender code value of the gender mapping within the code range of the variety mapping;

[0288] The category code splicing submodule is configured to use the category code value of the highest attribute category level as the header, and splice the code values ​​of the attribute category mappings of each level in descending order to obtain the category code segment.

[0289] Optionally, the vectorized processing module 406 includes:

[0290] a detection and extraction submodule, configured to detect and extract identity identification features from the image feature information included in the biometric feature information as the biometric feature;

[0291] a vectorization processing submodule, configured to perform vectorization processing on the identity identification feature to obtain the biometric feature vector;

[0292] Accordingly, the biometric encoding module 408 includes:

[0293] a quantization coding submodule, configured to perform quantization coding on the biometric feature vector using a vector coding algorithm to obtain a vector code;

[0294] The encoding conversion submodule is configured to perform encoding conversion on the vector encoding to obtain the biometric characteristic encoding segment and establish a corresponding relationship between the biometric characteristic encoding segment and the biometric characteristic.

[0295] Optionally, the attribute encoding segment is encoded by running the following submodules:

[0296] a position identification subsequence extraction submodule configured to obtain a pre-submitted identity identification sequence of the breeder to which the feeder belongs, and extract a position identification subsequence contained in the identity identification sequence;

[0297] an age attribute encoding submodule configured to encode the pre-submitted age attribute of the pet to obtain an attribute encoding segment;

[0298] The attribute coding segment splicing submodule is configured to splice the position identification subsequence with the attribute coding segment to obtain the attribute coding segment.

[0299] Optionally, the attribute encoding segment is further encoded by running the following submodules:

[0300] a position code search submodule configured to obtain the geographical location information of the pet and search for the position code corresponding to the geographical location information based on a preset correspondence between the geographical location and the code;

[0301] a position code determination submodule, configured to determine whether the position code corresponding to the geographic location information is consistent with the position identification subsequence;

[0302] If so, run the attribute coding segment splicing submodule.

[0303] Optionally, if the position code judgment submodule outputs a judgment result of no after running, the following submodules are run:

[0304] an extraction submodule configured to extract an identity identification feature of the breeder to which the pet belongs from the image feature information included in the feature information;

[0305] An identity identification feature judgment submodule is configured to judge whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold;

[0306] If so, run the encoding submodule and the splicing submodule;

[0307] The encoding submodule is configured to encode the pre-submitted age attribute of the pet to obtain an age attribute encoding segment;

[0308] The splicing submodule is configured to splice the position code and the age attribute code segment to obtain the attribute code segment.

[0309] Optionally, the animal identity encoding device includes:

[0310] According to the coding splicing order of the category coding segment, the biometric coding segment and the attribute coding segment, the category coding segment, the biometric coding segment and the attribute coding segment are spliced ​​in sequence, and the identity coding sequence is obtained after the splicing is completed.

[0311] Optionally, the animal identity encoding device includes:

[0312] The identity information creation module is configured to create the identity information of the pet based on the identity coding sequence of the pet, the attribute information of the pet, and the image feature information included in the biometric feature information.

[0313] An embodiment of a computing device provided in this specification is as follows:

[0314] Figure 5 5 is a block diagram illustrating a computing device 500 according to one embodiment of the present disclosure. Components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0315] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)), whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0316] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 5 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0317] Computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 500 can also be a mobile or stationary server.

[0318] This specification provides a computing device, including a memory 510, a processor 520, and computer instructions stored in the memory and executable on the processor. The processor 520 is configured to execute the following computer-executable instructions:

[0319] Performing feature recognition on the feature information of the target object according to the feature type of the feature information, and determining the attribute category of the target object based on the feature recognition result;

[0320] Encoding the attribute category of the target object to obtain a first encoding segment;

[0321] Performing vectorization processing on the object features extracted from the feature information to obtain a feature vector;

[0322] Encoding the feature vector to obtain a second encoding segment corresponding to the object feature;

[0323] The first coding segment, the second coding segment, and a third coding segment obtained by encoding the attribute information of the target object are spliced ​​to obtain an identity coding sequence of the target object.

[0324] Another computing device embodiment provided in this specification is as follows:

[0325] Figure 6 6 is a block diagram illustrating a computing device 600 according to an embodiment of the present disclosure. Components of the computing device 600 include, but are not limited to, a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and a database 650 is used to store data.

[0326] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0327] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 6 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0328] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 600 may also be a mobile or stationary server.

[0329] This specification provides a computing device, including a memory 610, a processor 620, and computer instructions stored in the memory and executable on the processor. The processor 620 is configured to execute the following computer-executable instructions:

[0330] performing feature recognition on the biometric information of the pet according to the biometric type of the biometric information of the pet, and determining the attribute category of the pet according to the recognition result;

[0331] Encoding the attribute category of the feed to obtain a category code segment;

[0332] performing vectorization processing on the biometric features extracted from the biometric feature information to obtain a biometric feature vector;

[0333] Encoding the biometric feature vector to obtain a biometric feature encoding segment corresponding to the biometric feature;

[0334] The category coding segment, the biometric coding segment, and the attribute coding segment obtained by encoding the attribute information of the captive are spliced ​​to obtain the identity coding sequence of the captive.

[0335] An embodiment of a computer-readable storage medium provided in this specification is as follows:

[0336] One embodiment of the present specification provides a computer-readable storage medium storing computer instructions, which implement the steps of the identity encoding method when executed by a processor.

[0337] The above is a schematic solution of a computer-readable storage medium of this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the above-mentioned identity encoding method are based on the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the above-mentioned identity encoding method.

[0338] Another embodiment of a computer-readable storage medium provided in this specification is as follows:

[0339] One embodiment of the present specification provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the method for encoding the identity of a domesticated animal.

[0340] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium is based on the same concept as the technical solution of the aforementioned method for encoding the identity of a domestic animal. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the aforementioned method for encoding the identity of a domestic animal.

[0341] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0342] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0343] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0344] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0345] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. An identity encoding method, comprising: According to the recognition results of the sound feature information and / or image feature information of the target object, the identity of the target object is encoded in the category dimension and the feature dimension respectively to obtain a first encoding segment and a second encoding segment, wherein the category dimension includes the attribute category of the target object; Obtaining a pre-submitted identity sequence of a subject object to which the target object belongs, and extracting a position identification subsequence contained in the identity sequence; Encoding the pre-submitted object attributes of the target object to obtain attribute code segments, wherein the attribute code segments include a birth date code segment of the target object; Obtaining the geographic location information of the target object, and searching for a location code corresponding to the geographic location information based on a preset correspondence between geographic locations and codes; Determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence; If so, concatenate the position identifier subsequence with the attribute code segment to obtain a third code segment; The first coding segment, the second coding segment, and the third coding segment are spliced ​​together to obtain an identity coding sequence of the target object.

2. The identity coding method according to claim 1, if the determination result of the sub-step of determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence is no, performing the following operations: Extracting the identity identification feature of the subject object to which the target object belongs from the image feature information included in the feature information; Determining whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold; If so, encoding the object attributes of the target object submitted in advance to obtain an attribute encoding segment; The position code segment and the attribute code segment are concatenated to obtain the third code segment.

3. The identity coding method according to claim 1, wherein the step of concatenating the first coding segment, the second coding segment, and the third coding segment to obtain the identity coding sequence of the target object comprises: According to the coding splicing order of the first coding segment, the second coding segment and the third coding segment, the first coding segment, the second coding segment and the third coding segment are spliced ​​in sequence, and the identity coding sequence is obtained after the splicing is completed.

4. The identity coding method according to any one of claims 1 to 3, further comprising: after the step of concatenating the first coding segment, the second coding segment, and the third coding segment to obtain the identity coding sequence of the target object: Object identity information of the target object is created based on the identity coding sequence of the target object, the attribute information of the target object, and the image feature information included in the feature information.

5. An identity encoding device comprising: an encoding module configured to perform identity encoding on the target object in a category dimension and a feature dimension based on recognition results of the sound feature information and / or image feature information of the target object, respectively, to obtain a first encoding segment and a second encoding segment, wherein the category dimension includes an attribute category of the target object; A position identifier subsequence extraction submodule is configured to obtain a pre-submitted identity identifier sequence of a subject object to which a target object belongs, and extract a position identifier subsequence contained in the identity identifier sequence; An object attribute encoding submodule is configured to encode the object attributes of the target object submitted in advance to obtain attribute encoding segments, wherein the attribute encoding segments include a birth date encoding segment of the target object; a location code search submodule configured to obtain the location information of the target object and search for the location code corresponding to the location information based on a preset correspondence between the location and the code; a position code determination submodule, configured to determine whether the position code corresponding to the geographic location information is consistent with the position identification subsequence; If yes, run the attribute code segment splicing submodule; the attribute code segment splicing submodule is configured to splice the position identifier subsequence with the attribute code segment to obtain a third code segment; The coding splicing module is configured to splice the first coding segment, the second coding segment and the third coding segment to obtain the identity coding sequence of the target object.

6. A method for encoding the identity of a domesticated animal, comprising: According to the recognition results of the sound feature information and / or image feature information of the pet, the pet is respectively encoded in the category dimension and the feature dimension to obtain a category code segment and a biometric feature code segment, wherein the category dimension includes the attribute category of the pet; Obtaining a pre-submitted identity sequence of the breeder to which the feeder belongs, and extracting a position identification subsequence contained in the identity sequence; Encoding the pre-submitted age attribute of the pet to obtain an age attribute coding segment; Obtaining geographic location information of the captive, and searching for a location code corresponding to the geographic location information based on a preset correspondence between geographic location and code; Determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence; If so, concatenate the position identifier subsequence with the age attribute code segment to obtain the attribute code segment; The category coding segment, the biometric coding segment and the attribute coding segment are spliced ​​together to obtain the identity coding sequence of the captive.

7. The pet identity coding method according to claim 6, if the result of the determination of whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence is negative, performing the following operations: Extracting the identity identification feature of the breeder to which the pet belongs from the image feature information included in the feature information; Determining whether the similarity between the identity identification feature and the identity identification image recorded in the identity information corresponding to the identity identification sequence is greater than a preset similarity threshold; If yes, encode the pre-submitted age attribute of the pet to obtain an age attribute encoding segment; The position code segment is concatenated with the age attribute code segment to obtain the attribute code segment.

8. The method for encoding the identity of a domesticated animal according to claim 6, wherein the step of concatenating the category encoding segment, the biometric encoding segment, and the attribute encoding segment to obtain the identity encoding sequence of the domesticated animal comprises: According to the coding splicing order of the category coding segment, the biometric coding segment and the attribute coding segment, the category coding segment, the biometric coding segment and the attribute coding segment are spliced ​​in sequence, and the identity coding sequence is obtained after the splicing is completed.

9. The method for encoding the identity of a domesticated animal according to any one of claims 6 to 8, further comprising: after the step of concatenating the category code segment, the biometric feature code segment, and the attribute code segment to obtain the identity code sequence of the domesticated animal; The identity information of the pet is created based on the identity coding sequence of the pet, the attribute information of the pet, and the image feature information included in the biometric feature information.

10. A pet identity coding device comprising: an encoding module configured to perform identity encoding on the pet in a category dimension and a feature dimension based on recognition results of the sound feature information and / or image feature information of the pet, respectively, to obtain a category encoding segment and a biometric feature encoding segment, wherein the category dimension includes an attribute category of the pet; The position identification subsequence extraction submodule is configured to obtain a pre-submitted identity identification sequence of the breeder to which the feeder belongs, and extract the position identification subsequence contained in the identity identification sequence; an age attribute encoding submodule configured to encode the pre-submitted age attribute of the pet to obtain an age attribute encoding segment; a position code search submodule configured to obtain the geographical location information of the pet and search for the position code corresponding to the geographical location information based on a preset correspondence between the geographical location and the code; a position code determination submodule, configured to determine whether the position code corresponding to the geographic location information is consistent with the position identification subsequence; If so, running the attribute code segment splicing submodule; the attribute code segment splicing submodule is configured to splice the position identifier subsequence with the age attribute code segment to obtain the attribute code segment; The coding splicing module is configured to splice the category coding segment, the biometric coding segment and the attribute coding segment to obtain the identity coding sequence of the captive.

11. A computing device comprising: memory and processor; The memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions: According to the recognition results of the sound feature information and / or image feature information of the target object, the identity of the target object is encoded in the category dimension and the feature dimension respectively to obtain a first encoding segment and a second encoding segment, wherein the category dimension includes the attribute category of the target object; Obtaining a pre-submitted identity sequence of a subject object to which the target object belongs, and extracting a position identification subsequence contained in the identity sequence; Encoding the pre-submitted object attributes of the target object to obtain attribute code segments, wherein the attribute code segments include a birth date code segment of the target object; Obtaining the geographic location information of the target object, and searching for a location code corresponding to the geographic location information based on a preset correspondence between geographic locations and codes; Determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence; If so, concatenate the position identifier subsequence with the attribute code segment to obtain a third code segment; The first coding segment, the second coding segment, and the third coding segment are spliced ​​together to obtain an identity coding sequence of the target object.

12. A computing device comprising: memory and processor; The memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions: According to the recognition results of the sound feature information and / or image feature information of the pet, the pet is respectively encoded in the category dimension and the feature dimension to obtain a category code segment and a biometric feature code segment, wherein the category dimension includes the attribute category of the pet; Obtaining a pre-submitted identity sequence of the breeder to which the feeder belongs, and extracting a position identification subsequence contained in the identity sequence; Encoding the pre-submitted age attribute of the pet to obtain an age attribute coding segment; Obtaining geographic location information of the captive, and searching for a location code corresponding to the geographic location information based on a preset correspondence between geographic location and code; Determining whether the location code corresponding to the geographic location information is consistent with the location identifier subsequence; If so, concatenate the position identifier subsequence with the age attribute code segment to obtain the attribute code segment; The category coding segment, the biometric coding segment and the attribute coding segment are spliced ​​together to obtain the identity coding sequence of the captive.

13. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the identity encoding method according to any one of claims 1 to 4.

14. A computer-readable storage medium storing computer instructions, wherein when the instructions are executed by a processor, the steps of the method for encoding the identity of a domesticated animal according to any one of claims 6 to 9 are implemented.

Images