Data classification method and device, equipment, medium and product

By adjusting the confidence and similarity of data classification methods and updating data categories, the problem of high manual labeling error rate is solved, and the accuracy of data classification is improved. Especially when data classification is incorrect, ensuring that the data characteristics are similar to the correct category. The degree is less than the error category, which improves the accuracy of subsequent classifications.

CN119066522APending Publication Date: 2024-12-03CHINA MOBILE INFORMATION TECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411296099.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

With the development of computer technology, the amount of data to be processed increases and the error rate of manual labeling increases, resulting in a decrease in the accuracy of data classification.

Method used

By adjusting the confidence and similarity of data classification methods, update the data category until the similarity is less than a certain threshold, improving the accuracy of data classification.

Benefits of technology

Reduce the data classification error rate and improve the accuracy of data classification. Especially when data classification is incorrect, by adjusting the confidence and similarity, ensure that the similarity between the data characteristics and the correct category is less than that of the wrong category, improving the accuracy of subsequent classifications. sex.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066522A_ABST
    Figure CN119066522A_ABST
Patent Text Reader

Abstract

The invention discloses a data classification method and device, equipment, a medium and a product, and relates to the technical field of data processing. The data classification method comprises the following steps: classifying first data by utilizing a first data classification mode to obtain a first category to which the first data belongs; under the condition that first indication information is received, the first confidence coefficient is reduced and / or the second confidence coefficient is improved, the classification of the first data is updated to be a second category, the first indication information is used for indicating that the category to which the first data belongs is the second category, and the second indication information is used for indicating the category to which the first data belongs. The first confidence coefficient is the confidence coefficient that the first data classification corresponding to the first data classification mode is a first category, and the second confidence coefficient is the confidence coefficient that the first data classification corresponding to the first data classification mode is a second category; and classifying the second data by using the first data classification mode after confidence adjustment. According to the scheme disclosed by the invention, the accuracy of data classification can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a data classification method, device, equipment, medium and product. Background Art

[0002] Data classification is to group data with some common attributes or characteristics together and distinguish the data by the attributes or characteristics of their categories. In other words, information with the same content and nature and information that requires unified management is grouped together, while information that is different and needs to be managed separately is distinguished, and then the relationship between each set is determined to form an organized classification system.

[0003] Before data classification, it is necessary to manually label the category to which the sample data belongs. However, with the development of computer technology, the amount of data to be processed is increasing, and the amount of manual labeling tasks is also increasing, resulting in an increasing error rate in data category labeling. This will cause data classification errors when classifying data, affecting the accuracy of data classification. Summary of the invention

[0004] The embodiments of the present application provide a data classification method, apparatus, device, medium and product, which can improve the accuracy of data classification.

[0005] In a first aspect, an embodiment of the present application provides a data classification method, including:

[0006] Classify the first data using a first data classification method to obtain a first category to which the first data belongs;

[0007] In case of receiving the first indication information, lowering the first confidence and / or increasing the second confidence until the first similarity is less than the second similarity, and updating the classification of the first data to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified into the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified into the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category;

[0008] The second data is classified using the first data classification method after the confidence is adjusted.

[0009] In a second aspect, an embodiment of the present application provides a data classification device, including:

[0010] A first classification module, used to classify the first data using a first data classification method to obtain a first category to which the first data belongs;

[0011] an adjustment module, configured to, upon receiving first indication information, reduce the first confidence and / or increase the second confidence until the first similarity is less than the second similarity, and update the classification of the first data to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified into the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified into the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category;

[0012] The second classification module is used to classify the second data using the first data classification method after the confidence is adjusted.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the data classification method provided in the embodiment of the present application are implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the steps of the data classification method provided in the embodiment of the present application are implemented.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions, and when the computer program instructions are executed by a processor, the steps of the data classification method provided in the embodiment of the present application are implemented.

[0016] In an embodiment of the present application, the first data is classified by using a first data classification method to obtain a first category to which the first data belongs; when the first indication information is received, the first confidence is lowered and / or the second confidence is increased until the first similarity is less than the second similarity, and the classification of the first data is updated to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified as the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified as the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category; the second data classification method after the confidence adjustment is used to classify the second data. In this way, when the first data belonging to the second category is classified into the first category (i.e., the first data is classified incorrectly), by reducing the confidence that the first data is classified into the first category corresponding to the first data classification method and / or increasing the confidence that the first data is classified into the second category corresponding to the first data classification method, the similarity between the data features of the first data and the data features of the first category can be made smaller than the similarity between the data features of the first data and the data features of the second category, thereby improving the accuracy of subsequent data classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 It is a flowchart of a data classification method provided in an embodiment of the present application;

[0019] Figure 2 is a structural schematic diagram of a data classification device provided in an embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0022] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0023] The data classification method, device, equipment, medium and product provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0024] Figure 1 Schematic diagram of the data classification method provided in the embodiment of the present application. Figure 1 As shown, data classification methods may include:

[0025] Step 101: Classify first data using a first data classification method to obtain a first category to which the first data belongs;

[0026] The embodiment of the present application does not limit the first data classification method used to classify the first data in step 101, and any available method can be applied to the embodiment of the present application.

[0027] Step 102: upon receiving the first indication information, lowering the first confidence and / or increasing the second confidence until the first similarity is less than the second similarity, and updating the classification of the first data to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified into the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified into the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category;

[0028] Exemplarily, assuming that the confidence level of data classified as category a is Za, the similarity between the data features of the data and the data features of category a is Sa; the confidence level of data classified as category b is Zb, the similarity between the data features of the data and the data features of category b is Sb.

[0029] The data is classified as Class A data using the first data classification method, but after user verification it is found that the data is actually classified as Class B, that is, Sa is greater than Sb at this time, so Za is reduced and / or Zb is increased to make Sa less than Sb, and the classification of the data is updated to Class B.

[0030] Step 103: Classify the second data using the first data classification method after the confidence is adjusted.

[0031] Exemplarily, assuming that the confidence level of data classified as category a is Za, the similarity between the data features of the data and the data features of category a is Sa; the confidence level of data classified as category b is Zb, the similarity between the data features of the data and the data features of category b is Sb.

[0032] The data is classified as Class A data using the first data classification method, but after user verification it is found that the data is actually classified as Class B, that is, Sa is greater than Sb at this time, so Za is reduced and / or Zb is increased to make Sa less than Sb, and the classification of the data is updated to Class B.

[0033] After Za is reduced and / or Zb is increased, the unclassified data is continuously classified using the first data classification method after the confidence is adjusted.

[0034] It should be noted that when the confidence level of a certain data being classified into a certain category is adjusted, the similarity between the data features of the data and the data features of the category will change accordingly.

[0035] In an embodiment of the present application, the first data is classified by using a first data classification method to obtain a first category to which the first data belongs; when the first indication information is received, the first confidence is lowered and / or the second confidence is increased until the first similarity is less than the second similarity, and the classification of the first data is updated to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified as the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified as the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category; the second data classification method after the confidence adjustment is used to classify the second data. In this way, when the first data belonging to the second category is classified into the first category (i.e., the first data is classified incorrectly), by reducing the confidence that the first data is classified into the first category corresponding to the first data classification method and / or increasing the confidence that the first data is classified into the second category corresponding to the first data classification method, the similarity between the data features of the first data and the data features of the first category can be made smaller than the similarity between the data features of the first data and the data features of the second category, thereby improving the accuracy of subsequent data classification.

[0036] In some possible implementations of the embodiments of the present application, lowering the first confidence level may include: calculating a first absolute value of a first difference between a first similarity and a second similarity; calculating a first ratio of the first absolute value to a first hit rate to obtain a first adjustment coefficient, wherein the first hit rate is a probability that the first data hits a data feature of a first category; when the first adjustment coefficient is greater than or equal to 0 and less than 1, keeping the first adjustment coefficient unchanged, and when the first adjustment coefficient is greater than or equal to 1, assigning the first adjustment coefficient to the difference between the first adjustment coefficient and 1; calculating a third confidence level based on the first adjustment coefficient, the second similarity and the first hit rate; when the third confidence level is greater than or equal to a first threshold, assigning the first confidence level to a third confidence level; when the third confidence level is less than the first threshold, assigning the first confidence level to the first threshold.

[0037] In some possible implementations of the embodiments of the present application, the data characteristics of the data hitting the category in the embodiments of the present application refer to the data characteristics of the data matching the data characteristics of the category. That is, the first data hitting the data characteristics of the first category refers to the data characteristics of the first data matching the data characteristics of the first category, and the first data hitting the data characteristics of the second category refers to the data characteristics of the first data matching the data characteristics of the second category.

[0038] In some possible implementations of the embodiments of the present application, the various adjustment coefficients in the embodiments of the present application (including the first adjustment coefficient mentioned above and the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient described below) are coefficients used to adjust the confidence.

[0039] In some possible implementations of the embodiments of the present application, the various thresholds in the embodiments of the present application (including the first threshold mentioned above and the second threshold and the third threshold described below) can be set according to actual needs.

[0040] In some possible implementations of the embodiments of the present application, the first threshold in the embodiments of the present application may be the minimum value that the first confidence level can reach, which may be set according to actual needs, for example, 1%.

[0041] Exemplarily, assuming that the confidence level of data being classified as category a is Za, and the probability that the data hits the data features of category a is Ha, then the similarity between the data features of the data and the data features of category a is Sa=Ha*Za; assuming that the confidence level of data being classified as category b is Zb, and the probability that the data hits the data features of category b is Hb, then the similarity between the data features of the data and the data features of category b is Sb=Hb*Zb.

[0042] In order to make Sa smaller than Sb, Za needs to be <Sb / Ha。

[0043] In some possible implementations of the embodiments of the present application, the first adjustment coefficient may be calculated according to the following formula (1).

[0044]

[0045] In formula (1), Δa is the first adjustment coefficient, Sa is the first similarity, Sb is the second similarity, and Ha is the first hit rate.

[0046] When 0≤Δa<1, Δa remains unchanged; when Δa is greater than 1, Δa=Δa-1.

[0047] For example, assuming that Δa calculated according to the above formula (1) is 0.6, then Δa is kept unchanged, and Δa is still 0.6; assuming that Δa calculated according to the above formula (1) is 1.5, then Δa=1.5-1=0.5, and at this time, Δa is 0.5.

[0048] In some possible implementations of the embodiments of the present application, when calculating the third confidence based on the first adjustment coefficient, the second similarity and the first hit rate, the first product of the first adjustment coefficient and the second similarity can be calculated, and then the sixth ratio of the first product to the first hit rate can be calculated to obtain the third confidence.

[0049] In some possible implementations of the embodiments of the present application, the third confidence level may be calculated according to the following formula (2).

[0050] Za′=Δa*Sb / Ha (2)

[0051] In formula (2), Za′ is the third confidence, Δa is the first adjustment coefficient, Sb is the second similarity, and Ha is the first hit rate.

[0052] When Za′≥1%, the confidence level of classifying the data into category a is reduced from Za to Za′; when Za′<1%, the confidence level of classifying the data into category a is reduced from Za to 1%.

[0053] In some possible implementations of the embodiments of the present application, improving the second confidence level may include: calculating a second absolute value of a second difference between the first similarity and the second similarity; calculating a second ratio of the second absolute value to the second hit rate to obtain a second adjustment coefficient, wherein the second hit rate is the probability that the first data hits the data feature of the second category; when the second adjustment coefficient is greater than or equal to 1, keeping the first adjustment coefficient unchanged, and when the second adjustment coefficient is greater than or equal to 0 and less than 1, assigning the second adjustment coefficient to the sum of the second adjustment coefficient and 1; calculating a fourth confidence level based on the second adjustment coefficient, the first similarity and the second hit rate; when the fourth confidence level is greater than or equal to the second threshold, assigning the second confidence level to the second threshold; when the third confidence level is less than the second threshold, assigning the second confidence level to the fourth confidence level.

[0054] In some possible implementations of the embodiments of the present application, the second threshold in the embodiments of the present application is the maximum value that the second confidence level can reach, which can be set according to actual needs, for example, 100%.

[0055] Exemplarily, assuming that the confidence level of data being classified as category a is Za, and the probability that the data hits the data features of category a is Ha, then the similarity between the data features of the data and the data features of category a is Sa=Ha*Za; assuming that the confidence level of data being classified as category b is Zb, and the probability that the data hits the data features of category b is Hb, then the similarity between the data features of the data and the data features of category b is Sb=Hb*Zb.

[0056] In order to make Sa smaller than Sb, it is necessary to make Sa / Hb <Zb。

[0057] In some possible implementations of the embodiments of the present application, the second adjustment coefficient may be calculated according to the following formula (3).

[0058]

[0059] In formula (1), Δb is the first adjustment coefficient, Sa is the first similarity, Sb is the second similarity, and Hb is the second hit rate.

[0060] When 0≤Δb<1, Δb=Δb+1; when Δb is greater than 1, Δb remains unchanged.

[0061] For example, assuming that Δb calculated according to the above formula (3) is 0.6, then Δb=0.6+1=1.6, and in this case, Δb is 1.6; assuming that Δb calculated according to the above formula (3) is 1.5, then Δb is kept unchanged, and in this case, Δb is 1.5.

[0062] In some possible implementations of the embodiments of the present application, when calculating the fourth confidence based on the second adjustment coefficient, the first similarity and the second hit rate, the second product of the second adjustment coefficient and the first similarity can be calculated, and then the seventh ratio of the second product to the second hit rate can be calculated to obtain the fourth confidence.

[0063] In some possible implementations of the embodiments of the present application, the fourth confidence level may be calculated according to the following formula (4).

[0064] Zb′=Δb*Sa / Hb (4)

[0065] In formula (4), Zb′ is the fourth confidence, Δb is the second adjustment coefficient, Sa is the first similarity, and Hb is the second hit rate.

[0066] When Zb′≥100%, the confidence level of classifying the data into category b is increased from Zb to 100%; when Zb′<100%, the confidence level of classifying the data into category a is increased from Zb to Zb′.

[0067] In some possible implementations of the embodiments of the present application, it is possible that after the confidence of classifying the first data into the first category is reduced and adjusted multiple times and reduced to the first threshold, the similarity between the data feature of the first data and the data feature of the first category is still greater than the similarity between the data feature of the first data and the data feature of the second category. At this time, it is necessary to continue to improve the confidence of classifying the first data into the second category. Based on this, reducing the first confidence and improving the second confidence may include: calculating a third absolute value of a third difference between the first similarity and the second similarity; calculating a third ratio of the third absolute value to the third hit rate to obtain a third adjustment coefficient, wherein the third hit rate is the probability that the first data hits the data feature of the first category; when the third adjustment coefficient is greater than or equal to 0 and less than 1, keeping the third adjustment coefficient unchanged; when the third adjustment coefficient is greater than or equal to 1, increasing the third adjustment coefficient. The adjustment coefficient is assigned a value equal to the difference between the third adjustment coefficient and 1; the fifth confidence is calculated according to the third adjustment coefficient, the second similarity and the third hit rate; when the fifth confidence is greater than or equal to the third threshold, the first confidence is assigned to the fifth confidence; when the fifth confidence is less than the third threshold, the first confidence is assigned to the third threshold; when the first confidence is not equal to the third threshold and the first similarity is greater than the second similarity, the step of calculating the third absolute value of the third difference between the first similarity and the second similarity is returned to; when the first confidence is equal to the third threshold and the first similarity is greater than the second similarity, the average value of the third adjustment coefficients obtained by each calculation is calculated; according to the average value and the second confidence, the fourth adjustment coefficient is determined, wherein the fourth adjustment coefficient is greater than 1; the second confidence is determined according to the fourth adjustment coefficient, the first similarity and the third hit rate.

[0068] In some possible implementations of the embodiments of the present application, the fifth confidence Za' can be calculated according to the above formulas (1) and (2). When Za'≥1%, the confidence of classifying the data into category a is reduced from Za to Za'; when Za'<1%, the confidence of classifying the data into category a is reduced from Za to 1%. When the confidence of classifying the data into category a is greater than 1% and the similarity between the data features of the data and the data features of category a is still greater than the similarity between the data features of the data and the data features of category b, it is necessary to continue to reduce the confidence of classifying the data into category a. At this time, the fifth confidence is calculated according to the above formulas (1) and (2) until the confidence of classifying the data into category a is equal to 1%. When the confidence of classifying the data into category a is equal to 1% but the similarity between the data features of the data and the data features of category a is still greater than the similarity between the data features of the data and the data features of category b, the confidence of classifying the data into category b is increased.

[0069] In some possible implementations of the embodiments of the present application, determining the fourth adjustment coefficient based on the average value and the second confidence level may include: calculating a fourth ratio of the fourth difference to the third threshold; calculating a fifth ratio of the average value to the fourth ratio to obtain a fourth adjustment coefficient; wherein the fourth difference is the difference between 1 and the second confidence level.

[0070] In some possible implementations of the embodiments of the present application, the fourth adjustment coefficient may be calculated according to the following formula (5).

[0071]

[0072] In formula (5), Δb is the fourth adjustment coefficient, is the average value of Δa calculated each time in the process of reducing the first confidence level to the third threshold, Zb is the second confidence level, and Δo is the third threshold.

[0073] In some possible implementations of the embodiments of the present application, the third threshold in the embodiments of the present application can be set according to actual needs.

[0074] After the fourth adjustment coefficient Δb is calculated according to the above formula (5), the confidence level that the data is classified as category b can be calculated according to the above formula (4).

[0075] The present application also provides a data classification device, such as Figure 2 shown. Figure 2 200 is a schematic diagram of the structure of a data classification device provided in an embodiment of the present application. The data classification device 200 may include:

[0076] A first classification module 201 is used to classify the first data using a first data classification method to obtain a first category to which the first data belongs;

[0077] An adjustment module 202 is used to, upon receiving the first indication information, reduce the first confidence and / or increase the second confidence until the first similarity is less than the second similarity, and update the classification of the first data to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified into the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified into the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category;

[0078] The second classification module 203 is used to classify the second data using the first data classification method after the confidence is adjusted.

[0079] In an embodiment of the present application, the first data is classified by using a first data classification method to obtain a first category to which the first data belongs; when the first indication information is received, the first confidence is lowered and / or the second confidence is increased until the first similarity is less than the second similarity, and the classification of the first data is updated to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified as the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified as the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category; the second data classification method after the confidence adjustment is used to classify the second data. In this way, when the first data belonging to the second category is classified into the first category (i.e., the first data is classified incorrectly), by reducing the confidence that the first data is classified into the first category corresponding to the first data classification method and / or increasing the confidence that the first data is classified into the second category corresponding to the first data classification method, the similarity between the data features of the first data and the data features of the first category can be made smaller than the similarity between the data features of the first data and the data features of the second category, thereby improving the accuracy of subsequent data classification.

[0080] In some possible implementations of the embodiments of the present application, the adjustment module 202 is specifically used to:

[0081] Calculate a first absolute value of a first difference between the first similarity and the second similarity;

[0082] Calculate a first ratio of the first absolute value to the first hit rate to obtain a first adjustment coefficient, wherein the first hit rate is a probability that the first data hits a data feature of the first category;

[0083] When the first adjustment coefficient is greater than or equal to 0 and less than 1, the first adjustment coefficient is kept unchanged; when the first adjustment coefficient is greater than or equal to 1, the first adjustment coefficient is assigned a value equal to the difference between the first adjustment coefficient and 1;

[0084] Calculating a third confidence level according to the first adjustment coefficient, the second similarity, and the first hit rate;

[0085] When the third confidence level is greater than or equal to the first threshold, assigning the first confidence level to the third confidence level;

[0086] When the third confidence level is smaller than the first threshold, the first confidence level is assigned the first threshold.

[0087] In some possible implementations of the embodiments of the present application, the adjustment module 202 is specifically used to:

[0088] Calculating a second absolute value of a second difference between the first similarity and the second similarity;

[0089] Calculate a second ratio of the second absolute value to the second hit rate to obtain a second adjustment coefficient, wherein the second hit rate is a probability that the first data hits a data feature of the second category;

[0090] When the second adjustment coefficient is greater than or equal to 1, the first adjustment coefficient is kept unchanged; when the second adjustment coefficient is greater than or equal to 0 and less than 1, the second adjustment coefficient is assigned a value equal to the sum of the second adjustment coefficient and 1;

[0091] Calculating a fourth confidence level according to the second adjustment coefficient, the first similarity, and the second hit rate;

[0092] When the fourth confidence level is greater than or equal to the second threshold, assigning the second confidence level to the second threshold;

[0093] When the third confidence level is less than the second threshold, the second confidence level is assigned as a fourth confidence level.

[0094] In some possible implementations of the embodiments of the present application, the adjustment module 202 is specifically used to:

[0095] Calculating a third absolute value of a third difference between the first similarity and the second similarity;

[0096] Calculate the ratio of the third absolute value to the third hit rate to obtain a third adjustment coefficient, wherein the third hit rate is the probability that the first data hits the data feature of the first category;

[0097] When the third adjustment coefficient is greater than or equal to 0 and less than 1, the third adjustment coefficient is kept unchanged; when the third adjustment coefficient is greater than or equal to 1, the third adjustment coefficient is assigned a value equal to the difference between the third adjustment coefficient and 1;

[0098] Calculating a fifth confidence level according to the third adjustment coefficient, the second similarity, and the third hit rate;

[0099] When the fifth confidence level is greater than or equal to the third threshold, the first confidence level is assigned to the fifth confidence level; when the fifth confidence level is less than the third threshold, the first confidence level is assigned to the third threshold;

[0100] When the first confidence is not equal to the third threshold and the first similarity is greater than the second similarity, returning to the step of calculating a third absolute value of a third difference between the first similarity and the second similarity;

[0101] When the first confidence level is equal to the third threshold and the first similarity level is greater than the second similarity level, calculating an average value of the third adjustment coefficients obtained from each calculation;

[0102] Determine a fourth adjustment coefficient according to the average value and the second confidence level, wherein the fourth adjustment coefficient is greater than 1;

[0103] A second confidence level is determined according to the fourth adjustment coefficient, the first similarity level, and the third hit rate.

[0104] In some possible implementations of the embodiments of the present application, the adjustment module 202 is specifically used to:

[0105] Calculating a fourth ratio of the fourth difference to the third threshold, wherein the fourth difference is a difference between 1 and the second confidence level;

[0106] A fifth ratio of the average value to the fourth ratio is calculated to obtain a fourth adjustment coefficient.

[0107] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0108] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0109] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0110] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 302 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 302 may be inside or outside the electronic device. In some specific embodiments, the memory 302 is a non-volatile solid-state memory.

[0111] In some specific embodiments, the memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the data classification method according to the present application.

[0112] The processor 301 implements the steps of the data classification method provided in the embodiment of the present application by reading and executing the computer program instructions stored in the memory 302.

[0113] In one example, the electronic device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0114] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0115] The bus 310 includes hardware, software or both, coupling the components of the electronic device to each other. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro channel architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus or other suitable buses or a combination of two or more of these. Where appropriate, the bus 310 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0116] The electronic device can execute the steps of the data classification method provided in the embodiment of the present application, thereby achieving the corresponding technical effects of the data classification method provided in the embodiment of the present application.

[0117] In addition, in combination with the data classification method in the above embodiment, the embodiment of the present application also provides a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the steps of the data classification method provided in the embodiment of the present application are implemented. Examples of computer-readable storage media include non-transitory computer-readable media, such as ROM, RAM, magnetic disk or optical disk, etc.

[0118] An embodiment of the present application provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the steps of the data classification method provided in the embodiment of the present application are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0119] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0120] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable read-only memory (Erasable Read Only Memory, EROM), floppy disks, compact discs (Compact Disc Read-Only Memory, CD-ROM), optical disks, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0121] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0122] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0123] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A data classification method, characterized in that: The method comprises: Classifying the first data using a first data classification method to obtain a first category to which the first data belongs; In case of receiving the first indication information, lowering the first confidence and / or increasing the second confidence until the first similarity is less than the second similarity, and updating the classification of the first data to the second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified into the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified into the second category corresponding to the first data classification method, the first similarity is the similarity between the data feature of the first data and the data feature of the first category, and the second similarity is the similarity between the data feature of the first data and the data feature of the second category; The second data is classified using the first data classification method after the confidence is adjusted.

2. The method according to claim 1, characterized in that The lowering of the first confidence level comprises: Calculating a first absolute value of a first difference between the first similarity and the second similarity; Calculating a first ratio of the first absolute value to a first hit rate to obtain a first adjustment coefficient, wherein the first hit rate is a probability that the first data hits a data feature of the first category; When the first adjustment coefficient is greater than or equal to 0 and less than 1, the first adjustment coefficient is kept unchanged; when the first adjustment coefficient is greater than or equal to 1, the first adjustment coefficient is assigned a value equal to the difference between the first adjustment coefficient and 1; Calculating a third confidence level according to the first adjustment coefficient, the second similarity, and the first hit rate; When the third confidence level is greater than or equal to the first threshold, assigning the first confidence level to the third confidence level; When the third confidence level is smaller than the first threshold, the first confidence level is assigned to the first threshold.

3. The method according to claim 1, characterized in that Improving the second confidence level comprises: Calculating a second absolute value of a second difference between the first similarity and the second similarity; Calculate a second ratio of the second absolute value to a second hit rate to obtain a second adjustment coefficient, wherein the second hit rate is a probability that the first data hits the data feature of the second category; When the second adjustment coefficient is greater than or equal to 1, the second adjustment coefficient is kept unchanged; when the second adjustment coefficient is greater than or equal to 0 and less than 1, the second adjustment coefficient is assigned a value equal to the sum of the second adjustment coefficient and 1; Calculating a fourth confidence level according to the second adjustment coefficient, the first similarity, and the second hit rate; When the fourth confidence level is greater than or equal to the second threshold, assigning the second confidence level to the second threshold; When the fourth confidence level is smaller than the second threshold, the second confidence level is assigned as the fourth confidence level.

4. The method according to claim 1, characterized in that: Lowering the first confidence level and increasing the second confidence level, including: Calculating a third absolute value of a third difference between the first similarity and the second similarity; Calculating a third ratio of the third absolute value to a third hit rate to obtain a third adjustment coefficient, wherein the third hit rate is a probability that the first data hits the data feature of the first category; When the third adjustment coefficient is greater than or equal to 0 and less than 1, the third adjustment coefficient is kept unchanged; when the third adjustment coefficient is greater than or equal to 1, the third adjustment coefficient is assigned a value equal to the difference between the third adjustment coefficient and 1; Calculating a fifth confidence level according to the third adjustment coefficient, the second similarity and the third hit rate; When the fifth confidence level is greater than or equal to the third threshold, assigning the first confidence level to the fifth confidence level; when the fifth confidence level is less than the third threshold, assigning the first confidence level to the third threshold; When the first confidence level is not equal to the third threshold and the first similarity level is greater than the second similarity level, returning to the step of calculating a third absolute value of a third difference between the first similarity level and the second similarity level; When the first confidence level is equal to the third threshold and the first similarity level is greater than the second similarity level, calculating an average value of the third adjustment coefficients obtained through various calculations; Determine a fourth adjustment coefficient according to the average value and the second confidence level, wherein the fourth adjustment coefficient is greater than 1; The second confidence level is determined according to the fourth adjustment coefficient, the first similarity and the third hit rate.

5. The method according to claim 4, characterized in that Determining a fourth adjustment coefficient according to the average value and the second confidence level includes: Calculating a fourth ratio of a fourth difference value to the third threshold value, wherein the fourth difference value is a difference between 1 and the second confidence level; A fifth ratio of the average value to the fourth ratio is calculated to obtain the fourth adjustment coefficient.

6. A data classification device, characterized in that: The device comprises: A first classification module, used to classify the first data using a first data classification method to obtain a first category to which the first data belongs; an adjustment module, configured to, upon receiving first indication information, reduce a first confidence and / or increase a second confidence until the first similarity is less than the second similarity, and update the classification of the first data to a second category, wherein the first indication information is used to indicate that the category to which the first data belongs is the second category, the first confidence is the confidence that the first data is classified into the first category corresponding to the first data classification method, the second confidence is the confidence that the first data is classified into the second category corresponding to the first data classification method, the first similarity is the similarity between a data feature of the first data and a data feature of the first category, and the second similarity is the similarity between a data feature of the first data and a data feature of the second category; The second classification module is used to classify the second data by using the first data classification method after the confidence is adjusted.

7. The device according to claim 6, characterized in that The adjustment module is specifically used for: Calculating a first absolute value of a first difference between the first similarity and the second similarity; Calculating a first ratio of the first absolute value to a first hit rate to obtain a first adjustment coefficient, wherein the first hit rate is a probability that the first data hits a data feature of the first category; When the first adjustment coefficient is greater than or equal to 0 and less than 1, the first adjustment coefficient is kept unchanged; when the first adjustment coefficient is greater than or equal to 1, the first adjustment coefficient is assigned a value equal to the difference between the first adjustment coefficient and 1; Calculating a third confidence level according to the first adjustment coefficient, the second similarity, and the first hit rate; When the third confidence level is greater than or equal to the first threshold, assigning the first confidence level to the third confidence level; When the third confidence level is smaller than the first threshold, the first confidence level is assigned to the first threshold.

8. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the steps of the data classification method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steps of the data classification method according to any one of claims 1 to 5 are implemented.

10. A computer program product, characterized in that The computer program product comprises computer program instructions, and when the computer program instructions are executed by a processor, the steps of the data classification method according to any one of claims 1 to 5 are implemented.