Semantic identifier generation method, semantic identifier generation apparatuses and storage medium

Abstract

The embodiments of the present disclosure provide a semantic identifier generation method, semantic identifier generation apparatuses and a storage medium. The method comprises: a semantic identifier generation apparatus acquiring an identifier; determining an identifier framework code of the identifier; performing analysis processing on the identifier on the basis of the identifier framework code, so as to obtain an ontology prefix code; and determining a semantic identifier on the basis of the ontology prefix code, the identifier framework code and the identifier. The present disclosure involves no human participation during the whole process of semantic identifier generation, and can automatically generate semantic identifiers, thus improving the intelligence of Internet of Things systems.

Description

Semantic identifier generation method, semantic identifier generation device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 202311810679.6 and application date of December 26, 2023, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0003] The present disclosure relates to the field of Internet of Things, and in particular to a method for generating a semantic identifier, a device for generating a semantic identifier, and a storage medium. Background Art

[0004] In the Internet of Things (IoT), every object requires a unique identifier as its digital identity to help users obtain detailed information about the object. Thousands of IoT identifiers coexist in the IoT ecosystem, such as the European Article Number (EAN), Digital Object Unique Identifier (DOI), and Global Standard 1 (GS1). These identifier schemes vary in length, value range, and structure, making it difficult for IoT objects to independently identify the identification framework of other objects and obtain their detailed information.

[0005] Currently, the industry has designed a series of compatible identifiers to accommodate heterogeneous identifiers and perform unified resolution, such as object identifiers (OIDs) and digital object identifiers (Handles). Through compatible identifiers, unified resolution of heterogeneous identifiers in different forms can be achieved; however, existing compatible identifiers are not automatically generated. Instead, users of the original identifiers are required to manually register their identifiers to a compatible identification system in advance according to the standard rules defined by the compatible identifiers, thereby reducing the intelligence of the IoT system. In addition, these compatible identifiers lack semantic information that can be understood by machines and cannot support intelligent interoperability between different objects. Summary of the Invention

[0006] The embodiments of the present disclosure provide a semantic identifier generation method, a semantic identifier generation device, and a storage medium, which can automatically generate semantic identifiers, thereby improving the intelligence of the Internet of Things system while supporting intelligent interaction between different objects.

[0007] The technical solution of the embodiment of the present disclosure is implemented as follows:

[0008] In a first aspect, an embodiment of the present disclosure provides a method for generating a semantic identifier, the method comprising:

[0009] Get the identifier;

[0010] determining an identification framework code of the identifier;

[0011] Parsing the identifier based on the identification framework code to obtain an ontology prefix code;

[0012] A semantic identifier is determined based on the ontology prefix code, the identification framework code, and the identifier.

[0013] In a second aspect, an embodiment of the present disclosure provides a semantic identifier generation device, the semantic identifier generation device comprising: an acquisition unit, a determination unit, and a parsing unit;

[0014] The acquiring unit is configured to acquire an identifier;

[0015] The determining unit is configured to determine an identification framework code of the identifier;

[0016] The parsing unit is configured to parse the identifier based on the identification framework code to obtain an entity prefix code;

[0017] The determining unit is further configured to determine a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier.

[0018] In a third aspect, an embodiment of the present disclosure provides a semantic identifier generation device, the semantic identifier generation device comprising: a processor and a memory; wherein,

[0019] The memory is used to store a computer program that can be run on the processor;

[0020] The processor is configured to execute the semantic identifier generation method described above when running the computer program.

[0021] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, characterized in that computer program code is stored on the storage medium, and when the computer program code is executed by a computer, the semantic identifier generation method as described above is implemented.

[0022] The embodiment of the present disclosure provides a semantic identifier generation method, a semantic identifier generation device and a storage medium, the method comprising: the semantic identifier generation device obtains an identifier; determines an identification framework code of the identifier; parses and processes the identifier based on the identification framework code to obtain an ontology prefix code; and determines the semantic identifier based on the ontology prefix code, the identification framework code and the identifier. In other words, the semantic identifier generation device can automatically obtain the identification framework code corresponding to the identifier, and then parse and process the identifier based on the identification framework code to obtain an ontology prefix code, and then determine the semantic identifier based on the ontology prefix code, the identification framework code and the identifier. The entire process of generating semantic identifiers disclosed in the present disclosure does not require human participation, and can automatically generate semantic identifiers, thereby improving the intelligence of the Internet of Things system. The ontology prefix code proposed in the present disclosure can provide corresponding semantic information to support intelligent interaction between different objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG1 is a schematic diagram of a method for generating a semantic identifier according to an embodiment of the present disclosure;

[0024] FIG2 is a schematic diagram of character mapping proposed in an embodiment of the present disclosure;

[0025] FIG3 is a schematic diagram of acquiring a first image according to an embodiment of the present disclosure;

[0026] FIG4 is a schematic diagram of the main body structure according to an embodiment of the present disclosure;

[0027] FIG5 is a second schematic diagram of the main body structure proposed in an embodiment of the present disclosure;

[0028] FIG6 is a schematic diagram of a semantic identifier structure proposed in an embodiment of the present disclosure;

[0029] FIG7 is a second schematic diagram of a method for generating a semantic identifier according to an embodiment of the present disclosure;

[0030] FIG8 is a schematic diagram of a strategy for converting a logo into a color image proposed in an embodiment of the present disclosure;

[0031] FIG9 is a first schematic diagram of the structure of the apparatus for generating a semantic identifier according to an embodiment of the present disclosure;

[0032] FIG10 is a second schematic diagram of the composition structure of the semantic identifier generation device proposed in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. It should be understood that the specific embodiments described herein are only used to explain the relevant applications and are not intended to limit such applications. It should also be noted that for ease of description, only the portions relevant to the relevant applications are shown in the drawings.

[0034] In the Internet of Things (IoT), every object requires a unique identifier as a digital identity, helping users access detailed information about it. However, thousands of IoT identifiers coexist within the IoT ecosystem, such as the European Article Number (EAN), Digital Object Unique Identifier (DOI), and Global Standard 1 (GS1). These identifier schemes vary in length, value range, and structure. This makes it difficult for IoT objects to independently identify the identification frameworks of other objects and obtain their detailed information.

[0035] To address this issue, the industry has designed a series of compatible identifiers, such as OIDs and Handles, through standardized definitions to accommodate heterogeneous identifiers and enable unified resolution. These compatible identifiers enable unified resolution of heterogeneous identifiers in different formats. However, existing compatible identifiers are not automatically generated. Instead, users of legacy identifiers are required to manually register their identifiers with a compatible identification system in advance according to the standard rules defined by the compatible identifiers, as only they know the identification schemes to which the legacy identifiers belong. However, in IoT scenarios, with the increasing number of IoT objects, manually identifying and resolving these identifiers is unrealistic, a drawback that severely limits the intelligent capabilities of the compatible identifier system. Furthermore, these compatible identifiers lack machine-understandable semantic information, making them incapable of supporting intelligent interoperability between different objects.

[0036] The current method of generating compatible identifiers still has the following shortcomings: (1) Traditional identifiers are heterogeneous and cannot be uniformly parsed, thus failing to support mutual recognition and interoperability between devices; (2) A small number of compatible identifiers can be compatible with some heterogeneous identifiers, but their generation process is manual, requiring users to manually map the original identifiers to compatible identifiers based on the defined standards. This is because only they know which identification scheme the legacy identifiers belong to, and there is a lack of automatic recognition capabilities for heterogeneous identifiers. As the number of IoT objects continues to increase, manually identifying and parsing these identifiers is unrealistic, wasting manpower and resources, and having a low degree of automation. Moreover, these compatible identifiers lack semantic information and cannot support intelligent interaction of the identified objects; (3) There are certain defects in the semantic identifier used in the related technology to be compatible with heterogeneous identifiers. First, there is a problem of information confusion and indistinguishability in the semantic prefix part of the identifier structure. For example, it is impossible to accurately distinguish whether the identifier 1101 represents 101 entities in the first layer or 01 entities in the 11th layer; secondly, this method requires manual identification of the identification scheme of the legacy identifier, because only the user who registered the identifier knows what identification scheme the legacy identifier belongs to; and this scheme requires manual acquisition of the semantic prefix, and does not involve a method for automatically acquiring the semantic prefix. Therefore, this method cannot automatically generate semantic identifiers, and can only be generated manually by users. However, in the Internet of Things scenario, with the continuous increase in the number of Internet of Things objects, it is unrealistic to manually generate compatible identifiers. This defect seriously limits the intelligent capabilities of the compatible identifier system.

[0037] In order to solve the problem that the current Internet of Things system has poor intelligence and cannot support intelligent interactive operability between different objects, the embodiment of the present disclosure provides a semantic identifier generation method, a semantic identifier generation device and a storage medium. The method includes: the semantic identifier generation device obtains an identifier; determines the identification framework code of the identifier; parses the identifier based on the identification framework code to obtain the ontology prefix code; and determines the semantic identifier based on the ontology prefix code, the identification framework code and the identifier. In other words, the semantic identifier generation device can automatically obtain the identification framework code corresponding to the identifier, and then parse the identifier based on the identification framework code to obtain the ontology prefix code, and then determine the semantic identifier based on the ontology prefix code, the identification framework code and the identifier. The entire process of generating semantic identifiers disclosed in the present disclosure does not require human participation, and can automatically generate semantic identifiers, thereby improving the intelligence of the Internet of Things system. The ontology prefix code proposed in the present disclosure can provide corresponding semantic information to support intelligent interaction between different objects.

[0038] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present disclosure.

[0039] Example 1

[0040] The present disclosure provides a method for generating a semantic identifier. FIG1 is a schematic diagram of a method for generating a semantic identifier according to an embodiment of the present disclosure. As shown in FIG1 , the method for generating a semantic identifier may include the following steps:

[0041] Step 101: Obtain an identifier.

[0042] In an embodiment of the present disclosure, the semantic identifier generating device may obtain an identifier.

[0043] It should be noted that in the embodiments of the present disclosure, the identifier obtained by the semantic identifier generation device can be the original identifier of the Internet of Things object. The original identifier can also be called a legacy identifier. For example, the legacy identifier can be an identifier sequence represented by a QR code label on the surface of a product. The present disclosure does not specifically limit the category of the obtained identifier.

[0044] Step 102: Determine the identification framework code of the identifier.

[0045] In an embodiment of the present disclosure, after obtaining the identifier, the semantic identifier generating device may determine the identification framework code of the identifier.

[0046] It should be noted that, in an embodiment of the present disclosure, when determining the identification frame code of an identifier, the semantic identifier generation device can determine the first image corresponding to the identifier; wherein the first image is a colored polygonal image; and then the first image can be input into a convolutional neural network to obtain the identification frame code.

[0047] Furthermore, in an embodiment of the present disclosure, when determining the first image corresponding to the identifier, the semantic identifier generating device can determine the character array of the identifier; then it can determine the encoding value of each character in the character array; and further, it can determine the first image based on the first encoding value of the i-th character and the second encoding value of the i+1-th character; wherein i is a positive integer.

[0048] It should be noted that, in the embodiments of the present disclosure, the encoding value may be the American Standard Code for Information Interchange (ASCII), and the present disclosure does not specifically limit the encoding value type.

[0049] Exemplarily, in an embodiment of the present disclosure, assuming that the identifier obtained by the semantic identifier generating device is 6254687914710, then the character array of the identifier [6, 2, 5, 4, 6, 8, 7, 9, 1, 4, 7, 1, 0] can be determined, and then the ASCII code of each character in the character array [54, 50, 53, 52, 54, 56, 49, 57, 49, 52, 55, 49, 48] can be determined, so that the first image can be determined based on the ASCII code of the i-th character and the ASCII code of the i+1-th character.

[0050] It should be noted that, in an embodiment of the present disclosure, Figure 2 is a schematic diagram of the character mapping proposed in the embodiment of the present disclosure. As shown in Figure 2, before determining the first image based on the ASCII code of the i-th character and the ASCII code of the i+1-th character, the semantic identifier generating device can divide the circle into N equal parts with a radius of 128 (the ASCII code value range is 0 to 127), where N is the number of characters in the character array. Then, each character in the character array of the identifier can be mapped to a point on the dividing line in a counterclockwise order, and the distance between the position of the point and the center of the circle is the value of the ASCII code of the mapped character.

[0051] Furthermore, in an embodiment of the present disclosure, when the semantic identifier generating device determines the first image based on the first coding value of the i-th character and the second coding value of the i+1-th character, it can determine the corresponding first color value and second color value based on the first coding value and the second coding value respectively; then it can determine the RGB color value of the triangular area based on the first color value, the second color value and the third color value; wherein the triangular area is composed of the positions corresponding to the i-th character, the i+1-th character and the third color value; and then the RGB color value can be colored to obtain the first image.

[0052] It should be noted that, in the embodiments of the present disclosure, R in RGB stands for Red, G stands for Green, and B stands for Blue. The color information corresponding to the first color value is green (G), the color information corresponding to the second color value is blue (B), and the color information corresponding to the third color information is red (R).

[0053] It should be noted that, in the embodiment of the present disclosure, the position corresponding to the third color value may be the origin of the circle.

[0054] Exemplarily, in an embodiment of the present disclosure, assuming that i is 1, based on the first encoding value corresponding to the first character, that is, the ASCII code value is 54, and the ASCII code value corresponding to the i+1th character, that is, the second character, is 50, then the ASCII code value of the first character and the ASCII code value corresponding to the second character can be mapped to the RGB color space respectively, so that the corresponding first color value and second color value can be determined. The first color value can be expressed by formula (1), the second color value can be expressed by formula (2), and the third color value is the color value corresponding to the origin. The third color value can be set to a constant value of 255, so that the RGB color value (255, 2*a1-1, 2*a2-1) of the triangle area can be determined based on the first color value, the second color value, and the third color value. First color value = 2*a1-1 (1)

[0055] Where a1 represents the ASCII code value corresponding to the i-th character. Second color value = 2*a2-1 (2)

[0056] Where a2 represents the ASCII code value corresponding to the i+1th character.

[0057] It should be noted that, in an embodiment of the present disclosure, Figure 3 is a schematic diagram of obtaining the first image proposed in an embodiment of the present disclosure. As shown in Figure 3, the semantic identifier generating device can traverse all adjacent vertices in the circle, that is, determine the RGB color value of each triangular area based on the ASCII code value of the i-th character, the ASCII code value of the i+1-th character and the third color value, and then all the mapped points can be connected, and each triangular area in the connected polygon can be colored (filled) with its corresponding RGB color, so that the first image can be obtained.

[0058] Furthermore, in an embodiment of the present disclosure, the semantic identifier generating device may input the generated first image into a convolutional neural network (CNN), thereby obtaining an identification framework code.

[0059] That is to say, in an embodiment of the present disclosure, the semantic identifier generation device can automatically convert the identifier into a colored polygonal image, and then use the CNN network to process the colored image to obtain the identifier frame code of the identifier. The present disclosure can utilize the advantages of the CNN network in processing colored images to improve the recognition accuracy of the identifier.

[0060] Step 103: parse the identifier based on the identification framework code to obtain the entity prefix code.

[0061] In an embodiment of the present disclosure, after determining the identification framework code of the identifier, the semantic identifier generating device may parse the identifier based on the identification framework code to obtain the ontology prefix code.

[0062] It should be noted that in the embodiment of the present disclosure, when the semantic identifier generation device parses the identifier based on the identification framework code to obtain the ontology prefix code, it can parse out the object category represented by the identifier based on the identification framework code; then the object category can be mapped to the class in the ontology to obtain the ontology prefix code.

[0063] It should be noted that, in the embodiments of the present disclosure, the ontology may be a set of terms used to describe a field, and its organizational structure may be hierarchical. The present disclosure does not specifically limit the number and types of classes included in the ontology.

[0064] Illustratively, in an embodiment of the present disclosure, FIG4 is a schematic diagram of the ontology structure proposed in an embodiment of the present disclosure. As shown in FIG4 , the ontology may include objects, and the classes of objects include people, supermarkets, payment methods, commodities, etc., and different classes may also include different subclasses. For example, commodities include the following subclasses: food, vegetables, fruits, drinks, etc. The present disclosure does not specifically limit the number and types of classes included in the ontology.

[0065] It should be noted that, in an embodiment of the present disclosure, the semantic identifier generation device can determine the descriptive information represented by the identifier based on the identification framework code; wherein the descriptive information includes at least one pair of key-value pairs, and the key includes at least the object category, object name, retail price, and object specifications; and furthermore, the class of the object category in the ontology can be determined based on the object category.

[0066] Illustratively, in an embodiment of the present disclosure, as shown in Table 1 below, the description information includes at least one key-value pair, where the key may include Code, item name (object name), item category (object category), specification (object specification), company name, retail price, ..., and the values ​​corresponding to the keys are 8938515483013, Nestlé Coffee, Coffee, 268 ml, Nestlé (China) Co., Ltd., 10 yuan, ..., and the present disclosure does not specifically limit the number and type of parameters included in the description information.

[0067] Table 1

[0068] Furthermore, in an embodiment of the present disclosure, when the semantic identifier generating device determines the class of the object category in the ontology based on the object category, it can first determine the semantic similarity between the object category and each class in the ontology; and then it can determine the class of the object category in the ontology based on the semantic similarity.

[0069] Exemplarily, in an embodiment of the present disclosure, when determining the semantic similarity between the object category and each class in the ontology, the semantic identifier generating device can determine the semantic similarity between the value of the object category and each class in the ontology. For example, as shown in Table 1 above, the semantic similarity between the object category and the words in the first column key in Table 1 can be calculated based on the semantic similarity. The value corresponding to the key with the largest semantic similarity value is "coffee". Then, the semantic similarity between "coffee" and each class in the ontology can be calculated based on the semantic similarity. The class with the largest semantic similarity in the ontology is the class to be mapped.

[0070] It should be noted that in an embodiment of the present disclosure, after mapping the object category to the class in the ontology, the semantic identifier generation device can determine the path information from the root node in the ontology to the class based on the class in the ontology; wherein the path information includes a set of index numbers, and the index numbers are positive integers; and then the ontology prefix code can be determined based on the first preset symbol and the path information.

[0071] For example, in an embodiment of the present disclosure, Figure 5 is a second schematic diagram of the ontology structure proposed in an embodiment of the present disclosure. As shown in Figure 5, the objects include categories of people, supermarkets, payment methods, commodities, ..., and the corresponding index numbers are 1, 2, 3, and 4 respectively; commodities include the following subcategories: food, vegetables, fruits, beverages, ..., and the corresponding index numbers are 1, 2, 3, and 4 respectively; beverages include subcategories of carbonated beverages, coffee, juice, mineral water, milk, ..., and the corresponding index numbers are 1, 2, 3, 4, and 5 respectively.

[0072] It should be noted that, in the embodiment of the present disclosure, assuming that the semantic identifier generating device calculates the semantic similarity between "coffee" and each class in the ontology based on semantic similarity, and the class with the greatest semantic similarity in the ontology is coffee, then the path information from the root node (object) in the ontology to the class (coffee) can be determined based on the class (coffee) in the ontology. The path information from the object in the ontology to coffee can be represented by a set of index numbers. As shown in Figure 5 above, index number 1442 is the path information from the object in the ontology to coffee.

[0073] Furthermore, in an embodiment of the present disclosure, when determining the ontology prefix code based on the first preset symbol and the path information, the semantic identifier generating device may separate the index number using the first preset symbol to obtain the ontology prefix code.

[0074] It should be noted that in an embodiment of the present disclosure, the first preset symbol may be “.”. For example, the index number 1442 may be separated by the first preset symbol to obtain the entity prefix code 1.4.4.2. The present disclosure does not specifically limit the type of the first preset symbol.

[0075] It should be noted that in the embodiments of the present disclosure, the object category can be automatically mapped to the class in the ontology through the semantic similarity technology, so that the ontology prefix code can be automatically obtained. This process does not require human participation, thereby improving the intelligence of the Internet of Things system.

[0076] It should be noted that, in the embodiments of the present disclosure, the semantic identifier generation device can also convert the obtained descriptive information (key-value pairs) into data attributes in the Internet of Things ontology, such as updating the descriptive information such as Nestlé Coffee <Retail Price, 10 Yuan><Specifications, 268ML> into the ontology. In this way, more details about the object can be obtained from the ontology without having to frequently access the legacy identifier management system. At the same time, this information can be used as common knowledge to assist in intelligent interaction between physical objects.

[0077] Step 104: Determine a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier.

[0078] In an embodiment of the present disclosure, after parsing the identifier based on the identification framework code to obtain the ontology prefix code, the semantic identifier generating device may determine the semantic identifier based on the ontology prefix code, the identification framework code and the identifier.

[0079] It should be noted that in the embodiment of the present disclosure, when the semantic identifier generating device determines the semantic identifier based on the ontology prefix code, identification framework code and identifier, it can determine the semantic identifier based on the second preset symbol, ontology prefix code, identification framework code and identifier.

[0080] Exemplarily, in an embodiment of the present disclosure, the semantic identifier generating device may combine the ontology prefix code, the identification framework code and the identifier, and each part may be divided by a second preset symbol, the second preset symbol may be " / ", for example, 1.4.4.2 represents the ontology prefix code, 4 represents the identification framework code, 8938515483013 represents the identifier, and the semantic identifier may be represented by 1.4.4.2 / 4 / 8938515483013. The present disclosure does not specifically limit the type of the second preset symbol.

[0081] In summary, the semantic identifier generation device can automatically convert the identifier into a color polygon image, and then use the CNN network to process the color image to obtain the identifier framework code of the identifier. The present disclosure can utilize the advantages of the CNN network in color image processing to improve the recognition accuracy of the identifier. Then, the identifier can be parsed based on the identification framework code to obtain the ontology prefix code, that is, the object category can be automatically mapped to the class in the ontology through semantic similarity technology, so that the ontology prefix code can be automatically obtained. This process does not require human participation, thereby improving the intelligence of the Internet of Things system. The semantic identifier can be determined based on the second preset symbol, the ontology prefix code, the identification framework code and the identifier. The semantic identifier generation device can also convert the obtained description information (key-value pair) into data attributes in the Internet of Things ontology, such as updating the description information of Nestle Coffee <retail price, 10 yuan><specifications, 268ML> into the ontology. In this way, more details about the object can be obtained from the ontology without having to frequently access the legacy identifier management system, and this information can be used as common knowledge to assist in intelligent interaction between objects.

[0082] The embodiment of the present disclosure provides a method for generating a semantic identifier, which includes: a semantic identifier generating device obtains an identifier; determines an identification framework code of the identifier; parses and processes the identifier based on the identification framework code to obtain an ontology prefix code; and determines a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier. In other words, the semantic identifier generating device can automatically obtain the identification framework code corresponding to the identifier, and then parses and processes the identifier based on the identification framework code to obtain an ontology prefix code, and then determines a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier. The entire process of generating a semantic identifier in the present disclosure does not require human intervention, and can automatically generate a semantic identifier, thereby improving the intelligence of the Internet of Things system. The ontology prefix code proposed in the present disclosure can provide corresponding semantic information to support intelligent interaction between different objects.

[0083] Example 2

[0084] Based on the above embodiments, another embodiment of the present disclosure provides a semantic identifier generation method and a novel semantic compatible identification framework, which includes three parts: an ontology prefix (ontology prefix code), an original identification framework code (identification framework code), and an original identifier (identifier). The framework can accurately and uniquely identify IoT objects with compatible legacy identifiers, and can provide semantic information based on the ontology to support interoperability between identified objects; then, a heterogeneous identification framework automatic recognition method based on color images can be used to obtain the identification framework code; secondly, based on semantic similarity technology, a method for automatically obtaining an ontology prefix is ​​proposed, which automatically obtains the ontology prefix based on the object content (object category) resolved by the identifier and the class mapping in the ontology; finally, the ontology prefix (ontology prefix code), the original identification framework code (identification framework code), and the original identifier (identifier) ​​are combined to automatically obtain a semantic compatible identifier (semantic identifier). The entire process does not require human participation. Based on the automatically generated semantic compatible identifier (semantic identifier) ​​and the public knowledge provided by the IoT ontology, it can support intelligent interaction between IoT objects in IoT scenarios such as smart homes and unmanned supermarkets.

[0085] It should be noted that, in the embodiment of the present disclosure, Figure 6 is a schematic diagram of the semantic identifier structure proposed in the embodiment of the present disclosure. As shown in Figure 6, the semantic compatibility identifier (semantic identifier) ​​mainly includes three parts: the ontology prefix (ontology prefix code), the original identifier framework code (identification framework code), and the original identifier (identifier). These three parts are connected by the symbol " / ". In order to construct a semantic compatibility identifier, the present disclosure designs an Internet of Things ontology (ontology) and encodes the classes of each layer in the ontology from left to right, which is called the class label code (index number). The Internet of Things ontology is shown in Figure 5, which only shows part of the ontology related to the unmanned supermarket.

[0086] It should be noted that in the embodiments of the present disclosure, the identifier obtained by the semantic identifier generation device can be the original identifier of the Internet of Things object. The original identifier can also be called a legacy identifier. For example, the legacy identifier can be an identifier sequence represented by a QR code label on the surface of a product. The present disclosure does not specifically limit the category of the obtained identifier.

[0087] It should be noted that, in the embodiment of the present disclosure, the ontology prefix (ontology prefix code) is composed of a group of integers separated by ".", which represent the path from the root node of the ontology to the node that identifies the object class. In the ontology prefix, the parent node represents the parent class, and each integer segment represents a subclass label code (subclass index number) of the parent class from left to right; for example, the prefix "1.4" represents the class "commodity", and the prefix "1.4.4" represents the class "beverage", which is the fourth subclass of the "commodity" class. Through the ontology prefix (ontology prefix code), the specific class to which the object belongs can be obtained, so that the object can know what it is and what other objects are. Each object is mapped to an instance of a specific class in the ontology through the ontology prefix, and the relationship between the object and other objects is established. By designing the ontology prefix as a path from the root node of the ontology to the node that identifies the object class, the hierarchical information of the object can be more clearly identified, and it can uniquely correspond to a class in the Internet of Things ontology, avoiding the problem of information confusion in the semantic prefix part in the related technology.

[0088] It should be noted that in the embodiments of the present disclosure, the original identification framework code (identification framework code) is an identification framework index number formulated by experts, as shown in Table 2 below, indicating what framework the original identifier (identifier) ​​is, and is used to be compatible with heterogeneous identifiers, so that the corresponding identification resolution system can be selected according to the framework code of the original identifier (identifier) ​​for unified resolution. When an identifier is obtained, it is necessary to first identify the framework code of the identifier before subsequent unified resolution can be performed. Therefore, the present disclosure proposes an identification framework recognition method based on color images.

[0089] Table 2

[0090] It should be noted that in the embodiments of the present disclosure, through semantic compatibility identification (semantic identifier), it is possible to be compatible with heterogeneous identifications in the Internet of Things, and all objects with heterogeneous identifications in the Internet of Things system can be mapped to an instance of the corresponding class in the Internet of Things ontology according to the ontology prefix in the semantic compatibility identification. The name of the instance is the semantic compatibility identification. Therefore, the Internet of Things objects can use the public knowledge provided by the Internet of Things ontology to perform intelligent collaborative tasks such as semantic retrieval and semantic reasoning. As shown in Figure 5, the four types of objects in the IoT ontology (people, supermarkets, commodities, and payment methods) have different identifiers. Commodities (coffee) are identified by European Article Numbers (EAN), people are identified by passport numbers, supermarkets are identified by Global Location Numbers (GLN), and payment methods are identified by credit card numbers. Semantic-compatible identifiers (semantic identifiers) add different ontology prefixes (ontology prefix codes) and identification framework codes to the original identifiers. The ontology prefixes can be used to find the corresponding category of the identified object in the ontology, and the identification framework code can be used to determine the framework to which the original identifier belongs. For example, "1.1 / 1 / E501129487" indicates that the object is a person, and its original identification framework is Passport No. The semantic knowledge provided by the IoT ontology (unmanned supermarket section) shown in Figure 5 can support intelligent scenarios such as automatic shopping and automatic returns in unmanned supermarkets.

[0091] Furthermore, in the embodiments of the present disclosure, the automatic generation process of semantically compatible identifiers (semantic identifiers) mainly includes three parts: automatic identification of identifier frameworks (identifier framework codes), automatic acquisition of ontology prefixes (ontology prefix codes), and automatic combination of identifiers. Through the automatic generation method of semantically compatible identifiers (semantic identifiers), the original identifiers can be intelligently and efficiently mapped to semantically compatible identifiers without human intervention, thereby being compatible with heterogeneous identifiers, and the original identifiers are endowed with semantic information that can be understood by IoT objects. Based on the semantic information in the ontology, intelligent interaction between IoT objects is supported.

[0092] It should be noted that, in the embodiment of the present disclosure, Figure 7 is a second schematic diagram of the semantic identifier generation method proposed in the embodiment of the present disclosure. As shown in Figure 7, the semantic identifier generation device can first obtain the original identification (identifier), and then automatically identify the original identification frame based on the identification frame recognition method of the color image to obtain the original identification frame code (identification frame code), and then based on the identification frame code, it can be parsed in the corresponding parsing system, and the ontology prefix (ontology prefix code) can be automatically obtained based on the semantic similarity technology. Finally, the ontology prefix (ontology prefix code), identification frame code, and original identification (identifier) ​​can be combined to obtain a semantically compatible identification (semantic identifier).

[0093] It should be noted that in the embodiments of the present disclosure, a method for automatically identifying heterogeneous identification frames based on color images is proposed to obtain identification frame codes. Deep learning technology has achieved remarkable success in fields such as computer vision. In particular, the representative deep learning algorithm, Convolutional Neural Networks (CNN), has outperformed humans in various image recognition tasks such as object detection, face recognition, image segmentation, and human pose estimation. CNNs are good at representing two-dimensional signals. With sufficient image samples and corresponding class labels, CNNs can automatically and adaptively extract hierarchical spatial features and color features and learn classifiers. However, CNN models generally require images as input and work better with color images. Therefore, to meet the input data requirements of CNNs, the present disclosure designs a strategy for converting identification to color images. The specific strategy process is shown below. Compared with other image conversion strategies, this strategy can express more information, such as identification length, character size, and identifier symbol differential information. At the same time, it can more fully utilize the advantages of CNN for color image learning, resulting in high identification recognition accuracy. In addition, compared with current comprehensive identification methods, this solution is simpler, more practical, and more scalable.

[0094] It should be noted that, in the embodiment of the present disclosure, FIG8 is a schematic diagram of the conversion strategy from the identification to the color image proposed in the embodiment of the present disclosure. As shown in FIG8 , the conversion strategy may include the following steps: (1) obtaining the identification string and converting it into a character sequence (character array) with a length of n; (2) converting each character of the identification character sequence (character array) into an ASCII code to obtain an integer sequence of length n [54, 50, 53, 52, 54, 56, 49, 57, 49, 52, 55, 49, 48]; (3) making a circle with a radius of 128 (the ASCII code range is 0 to 127), and dividing the circle into n equal parts; (4) mapping each character in the identification to a point on the equal dividing line of the circle in step (3) in sequence, The distance between the position of the point and the center of the circle is equal to the value of the ASCII code of the mapped identifier (mapped character); the first character is mapped to the 0° bisector, and the subsequent characters are mapped to the corresponding bisectors in counterclockwise order; (5) In addition, according to the ASCII code values ​​of the adjacent vertices i (the i-th character) and i+1 (the i+1-th character), the triangular area formed by the adjacent vertices i and i+1 and the center of the circle is painted in RGB color. If the ASCII code values ​​of the adjacent vertices i and i+1 are a1 and a2, the RGB color is (255, 2*a1-1, 2*a2-1); (6) All mapped points are connected and colored according to the RGB color of the corresponding triangular area to obtain a colored polygon image, and the colored image is saved.

[0095] Exemplarily, in an embodiment of the present disclosure, assuming that the identifier obtained by the semantic identifier generating device is 6254687914710, the character array of the identifier [6, 2, 5, 4, 6, 8, 7, 9, 1, 4, 7, 1, 0] can be determined, and then the ASCII code of each character in the character array [54, 50, 53, 52, 54, 56, 49, 57, 49, 52, 55, 49, 48] can be determined, so that the first image (color polygon image) can be determined based on the ASCII code corresponding to the i-th character and the ASCII code corresponding to the i+1-th character.

[0096] Exemplarily, in an embodiment of the present disclosure, assuming that i is 1, based on the first encoding value corresponding to the first character, that is, the ASCII code value is 54, the ASCII code value corresponding to the i+1th character, that is, the second character, is 50, and then the corresponding first color value and second color value can be determined based on the ASCII code value of the first character and the ASCII code value corresponding to the second character, respectively. The first color value can be expressed by the above formula (1), the second color value can be expressed by the above formula (2), the third color value is the color value corresponding to the origin, and the third color value can be set to a constant value of 255, so that the RGB color value (255, 2*a1-1, 2*a2-1) of the triangle area can be determined based on the first color value, the second color value and the third color value.

[0097] It should be noted that in an embodiment of the present disclosure, the semantic identifier generating device can traverse all adjacent vertices in the circle, that is, determine the RGB color value of each triangular area based on the ASCII code value of the i-th character, the ASCII code value of the i+1-th character and the third color value, and then all the mapped points can be connected and the RGB color values ​​can be colored to obtain the first image.

[0098] It should be noted that in the embodiment of the present disclosure, the identification framework identified by the above method is corresponded to the identification framework index table established by experts (such as Table 2) to obtain the identification framework code; for example, the identification E501129487 is identified as Passport No (passport number) through the identification recognition algorithm, and based on the identification framework index table established by experts, it can be known that the identification framework code is 1.

[0099] That is to say, in an embodiment of the present disclosure, the semantic identifier generation device can automatically convert the identifier into a colored polygonal image, and then use the CNN network to process the colored image to obtain the identifier frame code of the identifier. The present disclosure can utilize the advantages of the CNN network in processing colored images to improve the recognition accuracy of the identifier.

[0100] Furthermore, in the embodiments of the present disclosure, after an enterprise or user produces a product, it will register the code and fill in the description information on the identification resolution platform such as Handle, Ecode, and OID. For example, when registering the item "Nestle Coffee", its description information will be filled in, as shown in Table 1 above. The information in the table appears in the form of key-value pairs, the first column is the key, and the second column is the value corresponding to the key, such as <item type, coffee>.

[0101] Exemplarily, in an embodiment of the present disclosure, as shown in Table 1 above, the description information includes at least one key-value pair, the key may include Code, item name (object name), item category (object category), specification (object specification), company name, retail price, ..., the values ​​corresponding to the keys are 8938515483013, Nestlé Coffee, Coffee, 268 ml, Nestlé (China) Co., Ltd., 10 yuan, ..., the present disclosure does not specifically limit the number and type of parameters included in the description information.

[0102] It should be noted that in the embodiments of the present disclosure, due to different understandings and experiences of different enterprises or users, they may use different descriptions to describe IoT entities when registering them. Different identification systems may also use different description templates for IoT entities. Furthermore, the terms used in the IoT ontology may differ from those used in the identification resolution system, and synonyms may exist. For example, User 1 may describe an object using "item type, coffee," while User 2 may use "item category, coffee." Therefore, it is difficult to directly map the legacy identifier to the ontology to obtain the ontology prefix. It is necessary to design a method to automatically obtain the ontology prefix. The present disclosure proposes an automatic acquisition method for the ontology prefix (ontology prefix code) based on semantic similarity technology. The specific process is as follows: (1) First, the semantic identifier generation device can obtain the identification framework and parse it. Based on the identification framework obtained in the first step, the parsing request is sent to the parsing system related to the identification framework to obtain the description information table of the identification object filled in by the user, as shown in Table 1; (2) The semantic identifier generation device can obtain the type of the object based on the semantic similarity technology, train the Word2vec model based on large corpora such as Wikipedia, and then calculate the semantic similarity between the words in the first column key in the identification description information table and the word item type (object category) based on the semantic similarity technology, and obtain the value corresponding to the key with the largest semantic similarity value, which is the class of the IoT item. As shown in Table 1, the key "item category" in the second row has the greatest semantic similarity with the item type, and its corresponding value is "coffee"; (3) Based on the obtained object type (object category), it is mapped to the ontology to obtain the ontology category (the class of the object category in the ontology), and the semantic similarity between the value corresponding to the item type in the identification description information and the various classes in the IoT ontology is calculated again based on the semantic similarity technology. The class with the greatest semantic similarity in the IoT ontology is the class to be mapped; (4) The semantic prefix (ontology prefix code) is obtained according to the ontology category, and then the path (path information) from the root node to the class is obtained according to the position of the mapped class in the IoT ontology, and each layer of the path is divided by "." to obtain the ontology prefix (ontology prefix code); for example, "coffee" has the greatest semantic similarity with "coffee" in the IoT ontology, so the identification object is mapped to the IoT ontology "coffee", so the semantic prefix (ontology prefix code) is 1.4.4.2.

[0103] Exemplarily, in an embodiment of the present disclosure, when determining the semantic similarity between the object category and each class in the ontology, the semantic identifier generating device can determine the semantic similarity between the value of the object category and each class in the ontology. For example, as shown in Table 1 above, the semantic similarity between the object category and the words in the first column key in Table 1 can be calculated based on the semantic similarity. The value corresponding to the key with the largest semantic similarity value is "coffee". Then, the semantic similarity between "coffee" and each class in the ontology can be calculated based on the semantic similarity. The class with the largest semantic similarity in the ontology is the class to be mapped.

[0104] It should be noted that in an embodiment of the present disclosure, after mapping the object category to the class in the ontology, the semantic identifier generation device can determine the path information from the root node in the ontology to the class based on the class in the ontology; wherein the path information includes a set of index numbers, and the index numbers are positive integers; and then the ontology prefix code can be determined based on the first preset symbol and the path information.

[0105] For example, in an embodiment of the present disclosure, as shown in FIG5 , the classes of objects include people, supermarkets, payment methods, commodities, …, and the corresponding index numbers are 1, 2, 3, and 4 respectively; commodities include the following subclasses: food, vegetables, fruits, beverages, …, and the corresponding index numbers are 1, 2, 3, and 4 respectively; beverages include the following subclasses: carbonated beverages, coffee, juice, mineral water, milk, …, and the corresponding index numbers are 1, 2, 3, 4, and 5 respectively.

[0106] It should be noted that, in the embodiment of the present disclosure, assuming that the semantic identifier generating device calculates the semantic similarity between "coffee" and each class in the ontology based on semantic similarity, and the class with the greatest semantic similarity in the ontology is coffee, then the path information from the root node (object) in the ontology to the class (coffee) can be determined based on the class (coffee) in the ontology. The path information from the object in the ontology to coffee can be represented by a set of index numbers. As shown in Figure 5 above, index number 1442 is the path information from the object in the ontology to coffee.

[0107] Exemplarily, in an embodiment of the present disclosure, the first preset symbol may be “.”. For example, the index number 1442 may be separated by the first preset symbol to obtain the entity prefix code 1.4.4.2. The present disclosure does not specifically limit the type of the first preset symbol.

[0108] It should be noted that in the embodiments of the present disclosure, the object category can be automatically mapped to the class in the ontology through the semantic similarity technology, so that the ontology prefix code can be automatically obtained. This process does not require human participation, thereby improving the intelligence of the Internet of Things system.

[0109] It should be noted that, in the embodiments of the present disclosure, the semantic identifier generation device can also convert the obtained descriptive information (key-value pairs) into data attributes in the Internet of Things ontology, such as updating the descriptive information such as Nestlé Coffee <Retail Price, 10 Yuan><Specifications, 268ML> into the ontology. In this way, more details about the object can be obtained from the ontology without having to frequently access the legacy identifier management system. At the same time, this information can be used as common knowledge to assist in intelligent interaction between physical objects.

[0110] Furthermore, in an embodiment of the present disclosure, the semantic identifier generation device can combine the ontology prefix (ontology prefix code), the semantic identification framework code (identification framework code) and the original identification (identifier), and separate each part with " / " (a second preset symbol) to finally obtain a semantic identification (semantic identifier), such as "1.1 / 1 / E501129487" indicates that the object is a person, such as "1.4.4.2 / 4 / 8938515483013" identifies a commodity coffee.

[0111] It should be noted that in the embodiments of the present disclosure, based on the above automatic generation process of semantically compatible identifiers (semantic identifiers), it is possible to be compatible with a variety of heterogeneous identifiers. At the same time, the semantically compatible identifiers (semantic identifiers) embed semantic information into character sequences, making each identified object an instance of the semantic ontology. In the Internet of Things ontology, a set of commonly used classes and attributes are defined, and each instance belonging to a class is named with a semantic identifier. In this way, the ontology, as a knowledge base, can provide public knowledge for objects identified by semantically compatible identifiers and realize autonomous collaborative decision-making.

[0112] In summary, the semantic identifier generation device can automatically convert the identifier into a color polygon image, and then use the CNN network to process the color image to obtain the identifier framework code of the identifier. The present disclosure can utilize the advantages of the CNN network in color image processing to improve the recognition accuracy of the identifier. Then, the identifier can be parsed based on the identification framework code to obtain the ontology prefix code, that is, the object category can be automatically mapped to the class in the ontology through semantic similarity technology, so that the ontology prefix code can be automatically obtained. This process does not require human participation, thereby improving the intelligence of the Internet of Things system. The semantic identifier can be determined based on the second preset symbol, the ontology prefix code, the identification framework code and the identifier. The semantic identifier generation device can also convert the obtained description information (key-value pair) into data attributes in the Internet of Things ontology, such as updating the description information of Nestle Coffee <retail price, 10 yuan><specifications, 268ML> into the ontology. In this way, more details about the object can be obtained from the ontology without having to frequently access the legacy identifier management system, and this information can be used as common knowledge to assist in intelligent interaction between objects.

[0113] The embodiment of the present disclosure provides a method for generating a semantic identifier, which includes: a semantic identifier generating device obtains an identifier; determines an identification framework code of the identifier; parses and processes the identifier based on the identification framework code to obtain an ontology prefix code; and determines a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier. In other words, the semantic identifier generating device can automatically obtain the identification framework code corresponding to the identifier, and then parses and processes the identifier based on the identification framework code to obtain an ontology prefix code, and then determines a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier. The entire process of generating a semantic identifier in the present disclosure does not require human intervention, and can automatically generate a semantic identifier, thereby improving the intelligence of the Internet of Things system. The ontology prefix code proposed in the present disclosure can provide corresponding semantic information to support intelligent interaction between different objects.

[0114] Example 3

[0115] Based on the above embodiments, the present disclosure provides a semantic identifier generation device. FIG9 is a schematic diagram of the composition structure of the semantic identifier generation device. As shown in FIG9 , the semantic identifier generation device 10 includes: an acquisition unit 11, a determination unit 12, and a parsing unit 13;

[0116] The acquiring unit 11 is used to acquire an identifier;

[0117] The determining unit 12 is configured to determine an identification framework code of the identifier;

[0118] The parsing unit 13 is used to parse the identifier based on the identification framework code to obtain the entity prefix code;

[0119] The determining unit 12 is further configured to determine a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier.

[0120] In an embodiment of the present disclosure, further, Figure 10 is a second schematic diagram of the composition structure of the semantic identifier generation device. As shown in Figure 10, the semantic identifier generation device 10 proposed in the embodiment of the present disclosure may also include a processor 14, a memory 15 storing executable instructions of the processor 14, and further, the semantic identifier generation device 10 may also include a communication interface 16, and a bus 17 for connecting the processor 14, the memory 15 and the communication interface 16.

[0121] In the embodiment of the present disclosure, the above-mentioned processor 14 can be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It can be understood that for different devices, the electronic device used to implement the above-mentioned processor function can also be other, and the embodiment of the present disclosure does not specifically limit it. The semantic identifier generation device 10 can also include a memory 15, which can be connected to the processor 14, wherein the memory 15 is used to store executable program code, which program code includes computer operating instructions. The memory 15 may include a high-speed RAM memory, and may also include a non-volatile memory, for example, at least two disk memories.

[0122] In the embodiment of the present disclosure, the bus 17 is used to connect the communication interface 16, the processor 14, and the memory 15, as well as to facilitate mutual communication between these devices.

[0123] In the embodiment of the present disclosure, the memory 15 is used to store instructions and data.

[0124] Furthermore, in an embodiment of the present disclosure, the above-mentioned processor 14 is used to obtain an identifier; determine the identification framework code of the identifier; parse the identifier based on the identification framework code to obtain the ontology prefix code; and determine the semantic identifier based on the ontology prefix code, the identification framework code and the identifier.

[0125] In practical applications, the memory 15 may be a volatile memory, such as a random-access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 14.

[0126] The embodiment of the present disclosure provides a semantic identifier generation device, which obtains an identifier; determines an identification framework code of the identifier; parses the identifier based on the identification framework code to obtain an ontology prefix code; and determines a semantic identifier based on the ontology prefix code, the identification framework code, and the identifier. In other words, the semantic identifier generation device can automatically obtain the identification framework code corresponding to the identifier, and then parse the identifier based on the identification framework code to obtain an ontology prefix code, and then determine the semantic identifier based on the ontology prefix code, the identification framework code, and the identifier. The entire process of generating semantic identifiers in the present disclosure does not require human participation, and can automatically generate semantic identifiers, thereby improving the intelligence of the Internet of Things system. The ontology prefix code proposed in the present disclosure can provide corresponding semantic information to support intelligent interaction between different objects.

[0127] An embodiment of the present disclosure provides a computer-readable storage medium having a program stored thereon, which implements the semantic identifier generation method described above when the program is executed by a processor.

[0128] Specifically, the program instructions corresponding to the semantic identifier generation method in this embodiment can be stored on a storage medium such as an optical disk, a hard disk, or a USB flash drive. When the program instructions corresponding to the semantic identifier generation method in the storage medium are read or executed by an electronic device, the following steps are included:

[0129] Get the identifier;

[0130] determining an identification framework code of the identifier;

[0131] Parsing the identifier based on the identification framework code to obtain an ontology prefix code;

[0132] A semantic identifier is determined based on the ontology prefix code, the identification framework code, and the identifier.

[0133] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0134] The present disclosure is described with reference to the implementation flow diagrams and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flow diagram and / or block diagram can be implemented by computer program instructions, as well as the combination of the processes and / or boxes in the flow diagram and / or block diagram. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flow diagram and / or one or more boxes in the block diagram.

[0135] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in implementing one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0137] The above description is merely a preferred embodiment of the present disclosure and is not intended to limit the scope of protection of the present disclosure.

Claims

1. A method for generating semantic identifiers, characterized in that, The method includes: Obtain an identifier; Determine the identification framework code of the identifier; Based on the identification framework code, perform parsing processing on the identifier to obtain an ontology prefix code; Based on the ontology prefix code, the identification framework code, and the identifier, determine a semantic identifier.

2. The method according to claim 1, characterized in that The determining the identification framework code of the identifier includes: Determine a first image corresponding to the identifier; wherein, the first image is a color polygon image; Input the first image into a convolutional neural network to obtain the identification framework code.

3. The method according to claim 2, characterized in that, The determining the first image corresponding to the identifier includes: Determine a character array of the identifier; Determine the encoding value of each character in the character array; Based on the first encoding value of the i-th character and the second encoding value of the (i + 1)-th character, determine the first image; wherein, i is a positive integer.

4. The method according to claim 3, characterized in that, The based on the first encoding value of the i-th character and the second encoding value of the (i + 1)-th character to determine the first image includes: Based on the first encoding value and the second encoding value, respectively determine corresponding first color value and second color value; Based on the first color value, the second color value, and a third color value, determine the RGB color value of a triangular region; wherein, the triangular region is composed of positions corresponding to the i-th character, the (i + 1)-th character, and the third color value; Perform coloring processing on the RGB color value to obtain the first image.

5. The method according to any one of claims 1-4, characterized in that, The based on the identification framework code to perform parsing processing on the identifier to obtain an ontology prefix code includes: Based on the identification framework code, parse out the object category represented by the identifier; Map the object category to a class in the ontology to obtain the ontology prefix code.

6. The method according to claim 5, wherein The method further includes: Based on the identification framework code, determine the description information represented by the identifier; wherein, the description information includes at least one pair of key-value pairs, and the keys at least include object category, object name, retail price, object specification; Based on the object category, determine the class of the object category in the ontology.

7. The method according to claim 6, wherein The based on the object category to determine the class of the object category in the ontology includes: Determine the semantic similarity between the object category and each class in the ontology; Based on the semantic similarity, determine the class of the object category in the ontology.

8. The method according to any one of claims 5 to 7, characterized in that, After the mapping the object category to a class in the ontology, the method further includes: Based on the class in the ontology, determine the path information from the root node in the ontology to the class; wherein, the path information includes a set of index numbers, and the index numbers are positive integers; Based on a first preset symbol and the path information, determine the ontology prefix code.

9. The method according to claim 8, wherein The based on the first preset symbol and the path information to determine the ontology prefix code includes: Separate the index numbers through the first preset symbol to obtain the ontology prefix code.

10. The method according to any one of claims 1-9, characterized in that, The based on the ontology prefix code, the identification framework code, and the identifier to determine a semantic identifier includes: Based on a second preset symbol, the ontology prefix code, the identification framework code, and the identifier, determine the semantic identifier.

11. A semantic identifier generation device, characterized in that, The generating device includes: an obtaining unit, a determining unit, and a parsing unit; The obtaining unit is configured to obtain an identifier; The determining unit is configured to determine an identification frame code of the identifier; The parsing unit is configured to perform a parsing process on the identifier based on the identification frame code to obtain an ontology prefix code; The determining unit is further configured to determine a semantic identifier based on the ontology prefix code, the identification frame code, and the identifier.

12. The device according to claim 11, wherein, The determining unit includes: The first determining subunit is configured to determine a first image corresponding to the identifier; wherein, the first image is a color polygon image; The first obtaining subunit is configured to input the first image into a convolutional neural network to obtain the identification frame code.

13. The device according to claim 12, characterized in that, The determining unit includes: The second determining subunit is configured to determine a character array of the identifier; The third determining subunit is configured to determine an encoding value of each character in the character array; The fourth determining subunit is configured to determine the first image based on a first encoding value of the i-th character and a second encoding value of the (i + 1)-th character; wherein, i is a positive integer.

14. The device according to claim 13, characterized in that, The fourth determining subunit is configured to: Determine a corresponding first color value and a second color value based on the first encoding value and the second encoding value respectively; Determine an RGB color value of a triangular region based on the first color value, the second color value, and a third color value; wherein, the triangular region is composed of positions corresponding to the i-th character, the (i + 1)-th character, and the third color value; Perform a coloring process on the RGB color value to obtain the first image.

15. The device according to any one of claims 11 - 14, characterized in that, The parsing unit is configured to: The parsing subunit is configured to parse an object category represented by the identifier based on the identification frame code; The second obtaining subunit is configured to map the object category to a class in the ontology to obtain the ontology prefix code.

16. The device according to claim 15, characterized in that, The determining unit is further configured to: Determine description information represented by the identifier based on the identification frame code; wherein, the description information includes at least one pair of key-value pairs, and the key includes at least an object category, an object name, a retail price, and an object specification; Determine a class of the object category in the ontology based on the object category.

17. The device according to claim 16, characterized in that, The determining unit includes: The fifth determining subunit is configured to determine a semantic similarity between the object category and each class in the ontology; The sixth determining subunit is configured to determine a class of the object category in the ontology based on the semantic similarity.

18. The device according to any one of claims 15-17, characterized in that The determining unit is further configured to: After mapping the object category to a class in the ontology, Determine path information from a root node in the ontology to the class based on the class in the ontology; wherein, the path information includes a set of index numbers, and the index number is a positive integer; Determine the ontology prefix code based on a first preset symbol and the path information.

19. The device according to claim 18, wherein The determining unit includes: The third obtaining subunit is configured to separate the index number through the first preset symbol to obtain the ontology prefix code.

20. The device according to any one of claims 11-19, characterized in that, The determining module includes: The seventh determining submodule is configured to determine the semantic identifier based on a second preset symbol, the ontology prefix code, the identification frame code, and the identifier.

21. A semantic identifier generation device, characterized in that The generating device includes: a processor and a memory; wherein, The memory is used for storing a computer program capable of running on the processor; The processor is used for executing the method according to any one of claims 1-10 when running the computer program.

22. A computer-readable storage medium, characterized in that, Computer program code is stored on the storage medium, and when the computer program code is executed by a computer, the method according to any one of claims 1-10 is executed.

Images