A radiation scanning method, system and medium for data information label

Abstract

The embodiments of the present application provide a radiation scanning method, system and medium for a data information label, the method comprising: acquiring a scanned image of the data information label, analyzing and processing the scanned image to obtain a scanned image that satisfies set conditional information; extracting data features of the scanned image, performing attribute analysis on the data features based on an extraction model to obtain data attribute values; clustering the data attribute values ​​based on a clustering algorithm to obtain clustering results, and generating multiple categories of data features based on the clustering results; extracting the center point of the data feature of each category as a label to obtain a data information label; performing semantic extraction on the data features through an extraction model to accurately analyze the data attributes, classify and process the data attributes, establish data information labels, and improve the analysis accuracy of the data information.

Description

Technical Field

[0001] The present application relates to the field of radiation scanning technology, and in particular to a radiation scanning method, system and medium for a data information label. Background Art

[0002] Data labels, as the name suggests, are marks and descriptions added to data. They are a kind of annotation, annotation and understanding of data by humans or systems. Data information labels include the attributes of the data. The existing radiation scanning methods are unable to classify and process the data, resulting in large errors in data labels. In addition, no extraction model is established to extract the meaning of the data, which affects the classification results when classifying data attributes. Effective technical solutions are urgently needed for the above problems. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a radiation scanning method, system and medium for data information labels, which semantically extracts data features through an extraction model, thereby accurately analyzing data attributes, classifying data attributes, establishing data information labels, and improving the analysis accuracy of data information.

[0004] The embodiment of the present application also provides a radiation scanning method for a data information label, including:

[0005] Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information;

[0006] Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values;

[0007] Clustering the data attribute values ​​based on the clustering algorithm to obtain clustering results, and generating data features of multiple categories based on the clustering results;

[0008] The center point of the data feature of each category is extracted as the label to obtain the data information label.

[0009] Optionally, in the radiation scanning method of the data information label described in the embodiment of the present application, obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that satisfies the set condition information specifically includes:

[0010] Obtain a scanned image of the data information label and analyze the pixel values ​​of the image pixels;

[0011] Analyzing whether the clarity of the scanned image meets a set clarity threshold based on the pixel value and the set pixel interval;

[0012] If the set definition threshold is not met, the scanned image that does not meet the set definition threshold is subjected to noise reduction processing to remove noise features;

[0013] If the set definition threshold is met, data features are extracted from the scanned image to obtain a scanned image that meets the set condition information.

[0014] Optionally, in the radiation scanning method of the data information label described in the embodiment of the present application, extracting data features of the scanned image, performing attribute analysis on the data features based on the extraction model, and obtaining data attribute values ​​specifically include:

[0015] Obtain the data features of the scanned image, build an extraction model based on the knowledge graph, input the data features into the extraction model, and obtain the attribute information of the data features;

[0016] The attribute information of the data features includes semantic information, voice information, association information between different data features and form information of the data features, and the form information includes nouns, verbs and adjectives;

[0017] Analyze the similarity between different data features based on the attribute information of data features;

[0018] Classify synonyms, near-synonyms and irrelevant words between different data features based on similarity analysis;

[0019] The attribute information of the data features is assigned based on the weight coefficients between the data features of different categories to obtain the data attribute values.

[0020] Optionally, in the radiation scanning method of the data information tag described in the embodiment of the present application, the synonyms, near synonyms and irrelevant words between different data features are classified based on similarity analysis, specifically including:

[0021] Obtain different data features, compare different data features, and calculate similarity;

[0022] Comparing the similarity with a set similarity threshold, where the similarity threshold includes a first similarity threshold and a second similarity threshold, and the first similarity threshold is less than the second similarity threshold;

[0023] If the similarity is less than the first similarity threshold, the data feature is determined to be an irrelevant word;

[0024] If the similarity is greater than or equal to the first similarity threshold and less than the second similarity threshold, the two data features are determined to be synonyms;

[0025] If the similarity is greater than or equal to a second similarity threshold, the two data features are determined to be synonyms;

[0026] Separately classify synonyms, near-synonyms, and unrelated words.

[0027] Optionally, in the radiation scanning method of the data information tag described in the embodiment of the present application, the data attribute values ​​are clustered based on a clustering algorithm to obtain clustering results, and multiple categories of data features are generated based on the clustering results, specifically including:

[0028] Obtain data attribute values, and set clustering intervals based on clustering algorithms. The clustering intervals include attribute upper and lower limits.

[0029] Compare the data attribute value with the attribute upper limit value and the attribute lower limit value;

[0030] Determine whether the data attribute value is greater than or equal to the attribute lower limit value and less than or equal to the attribute upper limit value;

[0031] If it is greater than or equal to the lower limit of the attribute and less than or equal to the upper limit of the attribute, the data attribute value is determined to be in the cluster interval, and all data features in the same cluster interval are divided into the same category;

[0032] If it is less than the attribute lower limit, a lower limit threshold is established, and based on the lower limit threshold, the data features within the interval between the lower limit threshold and the attribute lower limit are classified into the same category, wherein the lower limit threshold is less than the attribute lower limit;

[0033] If it is greater than the attribute upper limit value, an upper limit threshold is established, and the data features within the interval between the attribute upper limit value and the upper limit threshold are divided into the same category based on the upper limit threshold, wherein the upper limit threshold is greater than the attribute upper limit value.

[0034] Optionally, in the radiation scanning method of the data information label described in the embodiment of the present application, extracting the center point of the data feature of each category as a label to obtain the data information label specifically includes:

[0035] Set the category range area and analyze the data features of the same category in the category range area;

[0036] Get the center point of the category range area, and extract keywords from the data features closest to the center point;

[0037] Use keywords as labels to generate data information labels for this category.

[0038] In a second aspect, an embodiment of the present application provides a radiation scanning system for a data information tag, the system comprising: a memory and a processor, the memory comprising a program of a radiation scanning method for a data information tag, and when the program of the radiation scanning method for a data information tag is executed by the processor, the following steps are implemented:

[0039] Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information;

[0040] Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values;

[0041] Clustering the data attribute values ​​based on the clustering algorithm to obtain clustering results, and generating data features of multiple categories based on the clustering results;

[0042] The center point of the data feature of each category is extracted as the label to obtain the data information label.

[0043] Optionally, in the radiation scanning system of the data information label described in the embodiment of the present application, acquiring a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that satisfies the set condition information specifically includes:

[0044] Obtain a scanned image of the data information label and analyze the pixel values ​​of the image pixels;

[0045] Analyzing whether the clarity of the scanned image meets a set clarity threshold based on the pixel value and the set pixel interval;

[0046] If the set definition threshold is not met, the scanned image that does not meet the set definition threshold is subjected to noise reduction processing to remove noise features;

[0047] If the set definition threshold is met, data features are extracted from the scanned image to obtain a scanned image that meets the set condition information.

[0048] Optionally, in the radiation scanning system of the data information tag described in the embodiment of the present application, extracting data features of the scanned image, performing attribute analysis on the data features based on the extraction model, and obtaining data attribute values ​​specifically include:

[0049] Obtain the data features of the scanned image, build an extraction model based on the knowledge graph, input the data features into the extraction model, and obtain the attribute information of the data features;

[0050] The attribute information of the data features includes semantic information, voice information, association information between different data features and form information of the data features, and the form information includes nouns, verbs and adjectives;

[0051] Analyze the similarity between different data features based on the attribute information of data features;

[0052] Classify synonyms, near-synonyms and irrelevant words between different data features based on similarity analysis;

[0053] The attribute information of the data features is assigned based on the weight coefficients between the data features of different categories to obtain the data attribute values.

[0054] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a radiation scanning method program for a data information label. When the radiation scanning method program for a data information label is executed by a processor, the steps of the radiation scanning method for a data information label as described in any one of the above items are implemented.

[0055] As can be seen from the above, the embodiments of the present application provide a radiation scanning method, system and medium for a data information label, which obtains a scanned image of the data information label, analyzes and processes the scanned image, and obtains a scanned image that meets the set condition information; extracts data features of the scanned image, and performs attribute analysis on the data features based on an extraction model to obtain data attribute values; clusters the data attribute values ​​based on a clustering algorithm to obtain clustering results, and generates multiple categories of data features based on the clustering results; extracts the center point of the data feature of each category as a label to obtain a data information label; performs semantic extraction on the data features through the extraction model, thereby accurately analyzing the data attributes, classifying and processing the data attributes, establishing data information labels, and improving the analysis accuracy of the data information. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A flow chart of a radiation scanning method for a data information tag provided in an embodiment of the present application;

[0058] Figure 2 A flow chart of a scanning image analysis and processing method of a radiation scanning method for a data information label provided in an embodiment of the present application;

[0059] Figure 3 A flow chart of a data attribute value analysis method for a radiation scanning method of a data information tag provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0061] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0062] Please refer to Figure 1 , Figure 1 The present invention is a flowchart of a method for scanning a data information tag by radiation in some embodiments of the present invention. The method for scanning a data information tag by radiation is used in a terminal device, and the method for scanning a data information tag by radiation includes the following steps:

[0063] S101, obtaining a scanned image of a data information label, analyzing and processing the scanned image, and obtaining a scanned image that satisfies set condition information;

[0064] S102, extracting data features of the scanned image, performing attribute analysis on the data features based on the extraction model, and obtaining data attribute values;

[0065] S103, clustering the data attribute values ​​based on a clustering algorithm to obtain a clustering result, and generating data features of multiple categories based on the clustering result;

[0066] S104, extracting the center point of the data feature of each category as a label to obtain a data information label.

[0067] It should be noted that by scanning the image of the data information label, the attributes of the data features are extracted, and the data features are classified according to the data attributes, thereby improving the analysis accuracy of the data information label.

[0068] Please refer to Figure 2 , Figure 2The present invention is a flowchart of a scanning image analysis and processing method of a radiation scanning method for a data information label in some embodiments of the present invention. According to an embodiment of the present invention, a scanning image of a data information label is obtained, and the scanning image is analyzed and processed to obtain a scanning image that meets the set condition information, specifically including:

[0069] S201, obtaining a scanned image of a data information label and analyzing pixel values ​​of image pixels;

[0070] S202, analyzing whether the definition of the scanned image meets a set definition threshold based on the pixel value and the set pixel interval;

[0071] S203, if the set definition threshold is not met, the scanned image that does not meet the set definition threshold is subjected to noise reduction processing to remove noise features;

[0072] S204: If the set definition threshold is met, data features are extracted from the scanned image to obtain a scanned image that meets the set condition information.

[0073] It should be noted that by performing noise reduction processing on the scanned image, noise features in the image are removed and the resolution of the scanned image is improved.

[0074] Please refer to Figure 3 , Figure 3 This is a flow chart of a data attribute value analysis method of a radiation scanning method for a data information tag in some embodiments of the present application. According to an embodiment of the present invention, data features of a scanned image are extracted, and attribute analysis of the data features is performed based on an extraction model to obtain data attribute values, specifically including:

[0075] S301, obtaining data features of the scanned image, building an extraction model based on the knowledge graph, inputting the data features into the extraction model, and obtaining attribute information of the data features;

[0076] The attribute information of data features includes semantic information, voice information, association information between different data features and form information of data features. The form information includes nouns, verbs and adjectives.

[0077] S302, analyzing similarities between different data features based on attribute information of the data features;

[0078] S303, classifying synonyms, near-synonyms and irrelevant words between different data features based on similarity analysis;

[0079] S304, assigning values ​​to the attribute information of the data features based on the weight coefficients between the data features of different categories to obtain data attribute values.

[0080] It should be noted that by analyzing the similarities between different data features, different data features are divided into synonyms, near-synonyms and irrelevant words, so as to accurately classify different data features and improve the analysis accuracy of data attributes.

[0081] According to an embodiment of the present invention, the synonyms, near synonyms and irrelevant words between different data features are classified based on similarity analysis, specifically including:

[0082] Obtain different data features, compare different data features, and calculate similarity;

[0083] Comparing the similarity with a set similarity threshold, where the similarity threshold includes a first similarity threshold and a second similarity threshold, and the first similarity threshold is less than the second similarity threshold;

[0084] If the similarity is less than the first similarity threshold, the data feature is determined to be an irrelevant word;

[0085] If the similarity is greater than or equal to the first similarity threshold and less than the second similarity threshold, the two data features are determined to be synonyms;

[0086] If the similarity is greater than or equal to a second similarity threshold, the two data features are determined to be synonyms;

[0087] Separately classify synonyms, near-synonyms, and unrelated words.

[0088] It should be noted that different similarities divide the data features into different categories, thereby improving the accuracy of data feature category division.

[0089] According to an embodiment of the present invention, data attribute values ​​are clustered based on a clustering algorithm to obtain a clustering result, and data features of multiple categories are generated based on the clustering result, specifically including:

[0090] Obtain data attribute values, and set clustering intervals based on clustering algorithms. The clustering intervals include attribute upper and lower limits.

[0091] Compare the data attribute value with the attribute upper limit value and the attribute lower limit value;

[0092] Determine whether the data attribute value is greater than or equal to the attribute lower limit value and less than or equal to the attribute upper limit value;

[0093] If it is greater than or equal to the lower limit of the attribute and less than or equal to the upper limit of the attribute, the data attribute value is determined to be in the cluster interval, and all data features in the same cluster interval are divided into the same category;

[0094] If it is less than the attribute lower limit, a lower limit threshold is established, and based on the lower limit threshold, the data features within the interval between the lower limit threshold and the attribute lower limit are classified into the same category, wherein the lower limit threshold is less than the attribute lower limit;

[0095] If it is greater than the attribute upper limit value, an upper limit threshold is established, and the data features within the interval between the attribute upper limit value and the upper limit threshold are divided into the same category based on the upper limit threshold, wherein the upper limit threshold is greater than the attribute upper limit value.

[0096] It should be noted that by analyzing the data attribute values, the data features are accurately divided into categories, thereby ensuring that the data information label can more accurately reflect the data attributes within the category.

[0097] According to an embodiment of the present invention, the center point of the data feature of each category is extracted as a label to obtain a data information label, which specifically includes:

[0098] Set the category range area and analyze the data features of the same category in the category range area;

[0099] Get the center point of the category range area, and extract keywords from the data features closest to the center point;

[0100] Use keywords as labels to generate data information labels for this category.

[0101] It should be noted that by analyzing the location of data features in the category range area, the data features corresponding to the center point of the category range area are screened out, and data information labels are established based on the data features corresponding to the center point to improve the accuracy of the data information labels.

[0102] According to an embodiment of the present invention, the center point position of the category range area is obtained, and keywords are extracted from the data features closest to the center point position, specifically including:

[0103] Get the category range area, calculate the center point of the category range area, and set multiple Euclidean distances with the center point as the center of the circle;

[0104] The category range area is divided into multiple sub-areas based on multiple Euclidean distances;

[0105] Determine whether the Euclidean distance between the edge line of the sub-region and the center point is less than the set distance threshold;

[0106] If it is less than, then extract the keywords of the data features in the sub-area;

[0107] If it is greater than, it is determined to be an edge sub-region and is removed.

[0108] It should be noted that the sub-regions satisfying the distance threshold are calculated according to the Euclidean distance, and the keywords of the data features are extracted, and the data information labels are established by analyzing the keywords in the sub-regions satisfying the distance threshold.

[0109] In a second aspect, an embodiment of the present application provides a radiation scanning system for a data information tag, the system comprising: a memory and a processor, the memory comprising a program of a radiation scanning method for a data information tag, and when the program of the radiation scanning method for a data information tag is executed by the processor, the following steps are implemented:

[0110] Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information;

[0111] Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values;

[0112] Clustering the data attribute values ​​based on the clustering algorithm to obtain clustering results, and generating data features of multiple categories based on the clustering results;

[0113] The center point of the data feature of each category is extracted as the label to obtain the data information label.

[0114] It should be noted that by scanning the image of the data information label, the attributes of the data features are extracted, and the data features are classified according to the data attributes, thereby improving the analysis accuracy of the data information label.

[0115] According to an embodiment of the present invention, obtaining a scanned image of a data information label, analyzing and processing the scanned image, and obtaining a scanned image that satisfies set condition information specifically includes:

[0116] Obtain a scanned image of the data information label and analyze the pixel values ​​of the image pixels;

[0117] Analyzing whether the clarity of the scanned image meets a set clarity threshold based on the pixel value and the set pixel interval;

[0118] If the set definition threshold is not met, the scanned image that does not meet the set definition threshold is subjected to noise reduction processing to remove noise features;

[0119] If the set definition threshold is met, data features are extracted from the scanned image to obtain a scanned image that meets the set condition information.

[0120] It should be noted that by performing noise reduction processing on the scanned image, noise features in the image are removed and the resolution of the scanned image is improved.

[0121] According to an embodiment of the present invention, data features of a scanned image are extracted, and attribute analysis is performed on the data features based on an extraction model to obtain data attribute values, specifically including:

[0122] Obtain the data features of the scanned image, build an extraction model based on the knowledge graph, input the data features into the extraction model, and obtain the attribute information of the data features;

[0123] The attribute information of data features includes semantic information, voice information, association information between different data features and form information of data features. The form information includes nouns, verbs and adjectives.

[0124] Analyze the similarity between different data features based on the attribute information of data features;

[0125] Classify synonyms, near-synonyms and irrelevant words between different data features based on similarity analysis;

[0126] The attribute information of the data features is assigned based on the weight coefficients between the data features of different categories to obtain the data attribute values.

[0127] It should be noted that by analyzing the similarities between different data features, different data features are divided into synonyms, near-synonyms and irrelevant words, so as to accurately classify different data features and improve the analysis accuracy of data attributes.

[0128] According to an embodiment of the present invention, the synonyms, near synonyms and irrelevant words between different data features are classified based on similarity analysis, specifically including:

[0129] Obtain different data features, compare different data features, and calculate similarity;

[0130] Comparing the similarity with a set similarity threshold, where the similarity threshold includes a first similarity threshold and a second similarity threshold, and the first similarity threshold is less than the second similarity threshold;

[0131] If the similarity is less than the first similarity threshold, the data feature is determined to be an irrelevant word;

[0132] If the similarity is greater than or equal to the first similarity threshold and less than the second similarity threshold, the two data features are determined to be synonyms;

[0133] If the similarity is greater than or equal to a second similarity threshold, the two data features are determined to be synonyms;

[0134] Separately classify synonyms, near-synonyms, and unrelated words.

[0135] It should be noted that different similarities divide the data features into different categories, thereby improving the accuracy of data feature category division.

[0136] According to an embodiment of the present invention, data attribute values ​​are clustered based on a clustering algorithm to obtain a clustering result, and data features of multiple categories are generated based on the clustering result, specifically including:

[0137] Obtain data attribute values, and set clustering intervals based on clustering algorithms. The clustering intervals include attribute upper and lower limits.

[0138] Compare the data attribute value with the attribute upper limit value and the attribute lower limit value;

[0139] Determine whether the data attribute value is greater than or equal to the attribute lower limit value and less than or equal to the attribute upper limit value;

[0140] If it is greater than or equal to the lower limit of the attribute and less than or equal to the upper limit of the attribute, the data attribute value is determined to be in the cluster interval, and all data features in the same cluster interval are divided into the same category;

[0141] If it is less than the attribute lower limit, a lower limit threshold is established, and based on the lower limit threshold, the data features within the interval between the lower limit threshold and the attribute lower limit are classified into the same category, wherein the lower limit threshold is less than the attribute lower limit;

[0142] If it is greater than the attribute upper limit value, an upper limit threshold is established, and the data features within the interval between the attribute upper limit value and the upper limit threshold are divided into the same category based on the upper limit threshold, wherein the upper limit threshold is greater than the attribute upper limit value.

[0143] It should be noted that by analyzing the data attribute values, the data features are accurately divided into categories, thereby ensuring that the data information label can more accurately reflect the data attributes within the category.

[0144] According to an embodiment of the present invention, the center point of the data feature of each category is extracted as a label to obtain a data information label, which specifically includes:

[0145] Set the category range area and analyze the data features of the same category in the category range area;

[0146] Get the center point of the category range area, and extract keywords from the data features closest to the center point;

[0147] Use keywords as labels to generate data information labels for this category.

[0148] It should be noted that by analyzing the location of data features in the category range area, the data features corresponding to the center point of the category range area are screened out, and data information labels are established based on the data features corresponding to the center point to improve the accuracy of the data information labels.

[0149] According to an embodiment of the present invention, the center point position of the category range area is obtained, and keywords are extracted from the data features closest to the center point position, specifically including:

[0150] Get the category range area, calculate the center point of the category range area, and set multiple Euclidean distances with the center point as the center of the circle;

[0151] The category range area is divided into multiple sub-areas based on multiple Euclidean distances;

[0152] Determine whether the Euclidean distance between the edge line of the sub-region and the center point is less than the set distance threshold;

[0153] If it is less than, then extract the keywords of the data features in the sub-area;

[0154] If it is greater than, it is determined to be an edge sub-region and is removed.

[0155] It should be noted that the sub-regions satisfying the distance threshold are calculated according to the Euclidean distance, and the keywords of the data features are extracted, and the data information labels are established by analyzing the keywords in the sub-regions satisfying the distance threshold.

[0156] A third aspect of the present invention provides a computer-readable storage medium, which includes a radiation scanning method program for a data information label. When the radiation scanning method program for a data information label is executed by a processor, the steps of the radiation scanning method for a data information label as described above are implemented.

[0157] The present invention discloses a radiation scanning method, system and medium for a data information label. The method obtains a scanned image of the data information label, analyzes and processes the scanned image, and obtains a scanned image that meets set condition information; extracts data features of the scanned image, and performs attribute analysis on the data features based on an extraction model to obtain data attribute values; clusters the data attribute values ​​based on a clustering algorithm to obtain clustering results, and generates data features of multiple categories based on the clustering results; extracts the center point of the data feature of each category as a label to obtain a data information label; semantically extracts the data features through an extraction model, thereby accurately analyzing the data attributes, classifying and processing the data attributes, establishing data information labels, and improving the analysis accuracy of the data information.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0159] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0160] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0161] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0162] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A radiation scanning method for a data information label, characterized in that: include: Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information; Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values; Clustering the data attribute values ​​based on the clustering algorithm to obtain clustering results, and generating data features of multiple categories based on the clustering results; Extract the center point of each category of data features as a label to obtain the data information label; Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information, specifically including: Obtain a scanned image of the data information label and analyze the pixel values ​​of the image pixels; Analyzing whether the clarity of the scanned image meets a set clarity threshold based on the pixel value and the set pixel interval; If the set definition threshold is not met, the scanned image that does not meet the set definition threshold is subjected to noise reduction processing to remove noise features; If the set definition threshold is met, data features are extracted from the scanned image to obtain a scanned image that meets the set condition information; Extract the center point of each category of data features as a label to obtain data information labels, including: Set the category range area and analyze the data features of the same category in the category range area; Get the center point of the category range area, and extract keywords from the data features closest to the center point; Use keywords as labels to generate data information labels for this category; Get the center point of the category range area, and extract keywords from the data features closest to the center point, including: Get the category range area, calculate the center point of the category range area, and set multiple Euclidean distances with the center point as the center of the circle; The category range area is divided into multiple sub-areas based on multiple Euclidean distances; Determine whether the Euclidean distance between the edge line of the sub-region and the center point is less than the set distance threshold; If it is less than, then extract the keywords of the data features in the sub-area; If it is greater than, it is determined to be an edge sub-region and is removed.

2. The radiation scanning method of the data information label according to claim 1, characterized in that: Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values, including: Obtain the data features of the scanned image, build an extraction model based on the knowledge graph, input the data features into the extraction model, and obtain the attribute information of the data features; The attribute information of the data features includes semantic information, voice information, association information between different data features and form information of the data features, and the form information includes nouns, verbs and adjectives; Analyze the similarity between different data features based on the attribute information of data features; Classify synonyms, near-synonyms and irrelevant words between different data features based on similarity analysis; The attribute information of the data features is assigned based on the weight coefficients between the data features of different categories to obtain the data attribute values.

3. The radiation scanning method of the data information label according to claim 2, characterized in that: Based on similarity analysis, synonyms, near synonyms and irrelevant words between different data features are classified, including: Obtain different data features, compare different data features, and calculate similarity; Comparing the similarity with a set similarity threshold, where the similarity threshold includes a first similarity threshold and a second similarity threshold, and the first similarity threshold is less than the second similarity threshold; If the similarity is less than the first similarity threshold, the data feature is determined to be an irrelevant word; If the similarity is greater than or equal to the first similarity threshold and less than the second similarity threshold, the two data features are determined to be synonyms; If the similarity is greater than or equal to a second similarity threshold, the two data features are determined to be synonyms; Separately classify synonyms, near-synonyms, and unrelated words.

4. The radiation scanning method of the data information label according to claim 3, characterized in that: Based on the clustering algorithm, the data attribute values ​​are clustered to obtain clustering results, and multiple categories of data features are generated based on the clustering results, including: Obtain data attribute values, and set clustering intervals based on clustering algorithms. The clustering intervals include attribute upper and lower limits. Compare the data attribute value with the attribute upper limit value and the attribute lower limit value; Determine whether the data attribute value is greater than or equal to the attribute lower limit value and less than or equal to the attribute upper limit value; If it is greater than or equal to the lower limit of the attribute and less than or equal to the upper limit of the attribute, the data attribute value is determined to be in the cluster interval, and all data features in the same cluster interval are divided into the same category; If it is less than the attribute lower limit, a lower limit threshold is established, and based on the lower limit threshold, the data features within the interval between the lower limit threshold and the attribute lower limit are classified into the same category, wherein the lower limit threshold is less than the attribute lower limit; If it is greater than the attribute upper limit value, an upper limit threshold is established, and the data features within the interval between the attribute upper limit value and the upper limit threshold are divided into the same category based on the upper limit threshold, wherein the upper limit threshold is greater than the attribute upper limit value.

5. A radiation scanning system for a data information label, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a radiation scanning method for a data information tag, and when the program of the radiation scanning method for a data information tag is executed by the processor, the following steps are implemented: Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information; Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values; Clustering the data attribute values ​​based on the clustering algorithm to obtain clustering results, and generating data features of multiple categories based on the clustering results; Extract the center point of each category of data features as a label to obtain the data information label; Obtaining a scanned image of the data information label, analyzing and processing the scanned image, and obtaining a scanned image that meets the set condition information, specifically including: Obtain a scanned image of the data information label and analyze the pixel values ​​of the image pixels; Analyzing whether the clarity of the scanned image meets a set clarity threshold based on the pixel value and the set pixel interval; If the set definition threshold is not met, the scanned image that does not meet the set definition threshold is subjected to noise reduction processing to remove noise features; If the set definition threshold is met, data features are extracted from the scanned image to obtain a scanned image that meets the set condition information; Extract the center point of each category of data features as a label to obtain data information labels, including: Set the category range area and analyze the data features of the same category in the category range area; Get the center point of the category range area, and extract keywords from the data features closest to the center point; Use keywords as labels to generate data information labels for this category; Get the center point of the category range area, and extract keywords from the data features closest to the center point, including: Get the category range area, calculate the center point of the category range area, and set multiple Euclidean distances with the center point as the center of the circle; The category range area is divided into multiple sub-areas based on multiple Euclidean distances; Determine whether the Euclidean distance between the edge line of the sub-region and the center point is less than the set distance threshold; If it is less than, then extract the keywords of the data features in the sub-area; If it is greater than, it is determined to be an edge sub-region and is removed.

6. The radiation scanning system for data information labels according to claim 5, characterized in that: Extract the data features of the scanned image, perform attribute analysis on the data features based on the extraction model, and obtain the data attribute values, including: Obtain the data features of the scanned image, build an extraction model based on the knowledge graph, input the data features into the extraction model, and obtain the attribute information of the data features; The attribute information of the data features includes semantic information, voice information, association information between different data features and form information of the data features, and the form information includes nouns, verbs and adjectives; Analyze the similarity between different data features based on the attribute information of data features; Classify synonyms, near-synonyms and irrelevant words between different data features based on similarity analysis; The attribute information of the data features is assigned based on the weight coefficients between the data features of different categories to obtain the data attribute values.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a radiation scanning method program for a data information tag. When the radiation scanning method program for a data information tag is executed by a processor, the steps of the radiation scanning method for a data information tag as described in any one of claims 1 to 4 are implemented.

Images