Target classification method and device

Abstract

The present invention discloses a method and device for target classification, and relates to the field of computer technology. A specific implementation of the method includes: clustering the targets to be classified using the feature data of at least one dimension of multiple targets to be classified to form multiple categories; obtaining the average value of the feature data of the targets to be classified in each dimension in each category, and determining the average value as the attribute data of the category in the dimension; using the attribute data of each dimension of each category to determine the initial score and skewness of the category; correcting the initial score according to the skewness to obtain the final score of the category; and determining the level of each category according to the final score. This implementation can achieve reasonable and accurate target classification, and since no human participation is required in the classification process, the classification results can be dynamically adjusted in real time according to data changes.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a target classification method and device. Background Art

[0002] In production and life, there is a need to divide multiple targets such as products and physical places into multiple levels of different importance or priority. There are two existing classification methods. The first method requires the calculation of a single index value for each target based on the characteristic data of multiple dimensions, and the classification is performed based on the size of the index value. This method has low classification accuracy. The second method first requires determining multiple central targets among the above targets and manually setting a level for each central target. After that, the spatial distance between the remaining targets and the central target is calculated to determine the levels of the remaining targets. This method cannot dynamically adjust the central target according to data changes and thus cannot guarantee the timeliness of the classification. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a target classification method and device, which can achieve reasonable and accurate target classification. At the same time, since no human participation is required in the classification process, the classification results can be dynamically adjusted in real time according to data changes.

[0004] To achieve the above objective, according to one aspect of the present invention, a target classification method is provided.

[0005] The target classification method of the embodiment of the present invention includes: clustering the targets to be classified using the feature data of at least one dimension of multiple targets to be classified to form multiple categories; obtaining the average value of the feature data of the targets to be classified in each dimension in each category, and determining the average value as the attribute data of the category in the dimension; using the attribute data of each dimension of each category to determine the initial score and skewness of the category; correcting the initial score according to the skewness to obtain the final score of the category; and determining the level of each category based on the final score.

[0006] Optionally, the method further comprises: after acquiring the attribute data: performing normalization processing on the attribute data of the multiple categories in the same dimension to obtain normalized data of each category in the dimension.

[0007] Optionally, using the attribute data of each dimension of each category to determine the initial score of the category includes: determining the weighted sum of the normalized data of each dimension in each category as the initial score of the category.

[0008] Optionally, the skewness of each category is determined using the attribute data of each dimension of each category, including: determining the mean, median and standard deviation of the normalized data of each dimension in each category; dividing the difference between the mean and the median by the standard deviation to obtain the skewness of the category.

[0009] Optionally, the skewness of each category is determined using the attribute data of each dimension of each category, including: dividing the third-order central moment of the normalized data of each dimension in each category by the cube of the standard deviation to obtain the skewness of the category.

[0010] Optionally, the initial score is corrected according to the skewness, including: determining the product of the skewness of each category and a preset adjustment coefficient, and determining the difference between 1 and the product as the correction coefficient of the category; and multiplying the correction coefficient by the initial score of the category to obtain the final score of the category.

[0011] To achieve the above objective, according to another aspect of the present invention, a target classification device is provided.

[0012] The target grading device of the embodiment of the present invention may include: a clustering unit, used to cluster the targets to be graded using the feature data of at least one dimension of multiple targets to be graded to form multiple categories; an attribute data acquisition unit, used to obtain the average value of the feature data of the targets to be graded in each dimension in each category, and determine the average value as the attribute data of the category in the dimension; a final score determination unit, used to determine the initial score and skewness of the category using the attribute data of each dimension of each category; correct the initial score according to the skewness to obtain the final score of the category; and a grading unit, used to determine the level of each category based on the final score.

[0013] Optionally, the attribute data acquisition unit can also be used to: after acquiring the attribute data: perform normalization processing on the attribute data of the multiple categories in the same dimension to obtain normalized data of each category in the dimension; the final score determination unit can also be used to: determine the weighted sum of the normalized data of each dimension in each category as the initial score of the category; determine the mean, median and standard deviation of the normalized data of each dimension in each category, divide the difference between the mean and the median by the standard deviation to obtain the skewness of the category; determine the product of the skewness of each category and a preset adjustment coefficient, determine the difference between 1 and the product as the correction coefficient of the category, and multiply the correction coefficient by the initial score of the category to obtain the final score of the category.

[0014] To achieve the above objective, according to another aspect of the present invention, an electronic device is provided.

[0015] An electronic device of the present invention comprises: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the target classification method provided by the present invention.

[0016] To achieve the above objective, according to yet another aspect of the present invention, a computer-readable storage medium is provided.

[0017] A computer-readable storage medium of the present invention stores a computer program, which implements the target classification method provided by the present invention when executed by a processor.

[0018] According to the technical solution of the present invention, one embodiment of the above invention has the following advantages or beneficial effects: the present invention first clusters the target to be classified according to the characteristic data of each dimension to form multiple categories, and then calculates the attribute data, normalized data, initial score and final score of each category in turn and uses the final score to perform category classification to achieve the classification of each target to be classified. Since the above clustering process takes into account the characteristic data of all dimensions of the target to be classified, the accuracy is high, thereby ensuring the accuracy of subsequent classification. At the same time, the present invention calculates the skewness of each category to adjust the initial score to obtain the final score for classification, thereby correcting the deviation of the initial score caused by the maximum or minimum value in the normalized data, thereby further ensuring the objectivity and rationality of the classification result. In addition, since the above classification process does not require human participation, when the characteristic data of the target to be classified changes, the classification result can be adjusted dynamically and in real time.

[0019] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0021] Figure 1 Schematic diagram of the main steps of the target classification method in an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of specific execution steps of the target classification method in an embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of components of a target classification device in an embodiment of the present invention;

[0024] Figure 4 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

[0025] Figure 5 It is a schematic diagram of the structure of an electronic device used to implement the target classification method in the embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0027] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0028] Figure 1 Schematic diagram of main steps of the target classification method according to an embodiment of the present invention.

[0029] like Figure 1 As shown, the target classification method of the embodiment of the present invention can be specifically performed according to the following steps:

[0030] Step S101: clustering the targets to be classified using feature data of at least one dimension of the targets to be classified to form multiple categories.

[0031] In an embodiment of the present invention, the target to be classified can be any entity or data object that needs to be classified. The following will mainly take the target to be classified as a variety of products as an example for explanation. It can be understood that the target to be classified can be divided into multiple levels through the above classification, and these multiple levels generally have different levels, importance or priorities. In this step, multiple targets to be classified have feature data of at least one dimension, so these feature data can be used to cluster the targets to be classified, thereby forming multiple categories. The above clustering can be implemented using existing clustering algorithms such as K-Means (K means). Since the above clustering process takes into account the feature data of multiple dimensions of the target to be classified, the accuracy is high, and the accuracy of subsequent classification can be guaranteed. The following table shows the feature data of multiple products in the first dimension, the second dimension, the third dimension, and the fourth dimension. The first dimension, the second dimension, the third dimension, and the fourth dimension can be various dimensions related to classification such as manufacturing time, manufacturing cost, service life, and qualified rate in specific scenarios.

[0032]

[0033]

[0034] Using clustering algorithms to cluster the 12 products based on the feature data of the four dimensions can form the three categories shown in the table below. It can be understood that the following is only an example and does not correspond to the actual calculation results.

[0035] Product Identification category 1 1 2 1 3 1 4 3 5 3 6 2 7 2 8 2 9 3 10 3 11 2 12 1

[0036] Step S102: Obtain the average value of the feature data of the to-be-classified objects in each category in each dimension, and determine the average value as the attribute data of the category in the dimension.

[0037] In this step, each category formed by clustering can be graded to obtain the level to which each target to be graded belongs. Specifically, for each category, the average value of the feature data of each target to be graded in each dimension can be obtained, and the average value can be determined as the attribute data of the category in this dimension. Exemplarily, the above average value can be an arithmetic mean. Taking category 1 and the first dimension in the above table as an example, the feature data 2, 5, 5, 4 of the targets to be graded in category 1, i.e., products 1, 2, 3, and 12 in the first dimension are obtained, and the average value 4 of the four feature data is used as the attribute data of category 1 in the first dimension. The attribute data of the three categories in the above table in each dimension are shown in the following table.

[0038] category First Dimension The Second Dimension The Third Dimension The Fourth Dimension 1 4 8 10 200000 2 5 9 4 300000 3 1 3 5 100000

[0039] Step S103: using the attribute data of each dimension of each category, determining the initial score and skewness of the category; correcting the initial score according to the skewness to obtain the final score of the category.

[0040] In this step, the initial score is a grading indicator determined based on the attribute data, which can roughly determine the level to which each category belongs. In practical applications, the weighted sum of the attribute data of each dimension in each category can be directly calculated as the initial score of the category. It can be understood that the above weighted sum can be calculated based on the weight value preset for each dimension. More preferably, the initial score of each category can be determined by the following method: First, for the same dimension, the attribute data of each category in the dimension is normalized to obtain the normalized data of each category in the dimension. The above normalization process can adopt various existing normalization methods such as the minimum-maximum normalization method, the Z-score normalization method, etc. The following will mainly use the minimum-maximum normalization method as an example for explanation. The minimum-maximum normalization method uses the following formula:

[0041]

[0042] Among them, x' is the target data after normalization, x is the target data before normalization, Min and Max are the minimum and maximum values ​​of each data respectively.

[0043] The Z-score normalization method uses the following formula:

[0044]

[0045] Among them, μ is the mean value of each data, and σ is the standard deviation of each data.

[0046] After obtaining the normalized data of each category in each dimension, the weighted sum of the normalized data of each dimension in each category can be determined as the initial score of the category. The following table shows the normalized data and initial scores of the three categories in each dimension in the above example. For ease of presentation, the weight values ​​of each dimension in this example are equal.

[0047] category First Dimension The Second Dimension The Third Dimension The Fourth Dimension Initial score 1 0.75 0.83 1.00 0.50 3.08 2 1.00 1.00 0.00 1.00 3.00 3 0.00 0.00 0.17 0.00 0.17

[0048] It can be seen from the above table that the initial score of category 1 is higher than that of category 2. If the initial score is used as a grading indicator, the level of category 1 is higher than that of category 2. However, by observing the specific conditions of each dimension, it can be found that the normalized data of category 1 in the first dimension, the second dimension and the fourth dimension are all smaller than those of category 2. Therefore, a more reasonable grading result should be that the level of category 2 is higher than that of category 1. The reason for the above phenomenon is that the normalized data of different categories have different degrees of skewness, which will affect the initial score and make the initial score have a certain deviation. In order to correct the above deviation, the concept of skewness can be introduced. Skewness is a statistical term, also known as skewness or skewness coefficient, which is used to characterize the skewness direction and degree of skewness of the distribution of statistical data. In an embodiment of the present invention, the skewness of multiple data can be calculated using the following formula:

[0049]

[0050] Among them, γ is the skewness, k3 is the third-order central moment, σ is the standard deviation, E represents the expectation, and X is the random variable corresponding to the above multiple data.

[0051] In practical applications, when the skewness is a negative number, the probability density curve of the random variable is left-skewed (i.e., the long tail of the curve is on the left); when the skewness is a positive number, the probability density curve of the random variable is right-skewed (i.e., the long tail of the curve is on the right). In particular, the inventors of the present invention observed that when the probability density curve of the random variable is unimodal and continuous, if the skewness is a negative number, the average value of the multiple data is less than the median; if the skewness is a positive number, the average value of the multiple data is greater than the median, so the following simpler skewness calculation formula is proposed. It can be understood that the median is the median. When the number of data is an odd number, the median is a data in the middle position of the data after sorting by size; when the number of data is an even number, the median is the average of two data in the middle position of the data after sorting by size.

[0052]

[0053] Wherein, M is the median. In the embodiment of the present invention, the skewness can be calculated using normalized data of each category, or can be directly calculated using attribute data. The following is an example of calculating the skewness using normalized data.

[0054] In a specific scenario, if the skewness of a category (i.e., the skewness of the normalized data of each dimension of the category) is negative, the initial score is affected by the minimum value in the normalized data and is smaller than the objective standard. The smaller the skewness, the greater the deviation. If the skewness of a category is positive, the initial score is affected by the maximum value in the normalized data and is larger than the objective standard. The larger the skewness, the greater the deviation. Therefore, the initial score can be corrected by the skewness. The specific formula used is as follows:

[0055] α=1-γ*θ

[0056] Among them, α is the correction coefficient, θ is the preset adjustment coefficient, and θ can be taken as 0.5 for example. The above correction coefficient decreases as the skewness increases, so it can correct the deviation of the initial score. In specific applications, the initial score of a category can be multiplied by the correction coefficient of the category to obtain the final score of the category for the final category classification. The skewness, correction coefficient, and final score of each category in the above table are shown in the following table. The skewness in the table is calculated using the aforementioned second skewness calculation formula and takes one significant digit.

[0057]

[0058]

[0059] Step S104: Determine the level of each category according to the final score.

[0060] In this step, the level of each category can be determined according to the size of the final score. For example, categories 1, 2, and 3 in the above table are determined as level b, level a, and level c, respectively, where the level a is greater than level b, and the level b is greater than level c. In this way, the level of each target to be classified can be obtained as shown in the following table.

[0061] Product Identification category level 1 1 b 2 1 b 3 1 b 4 3 c 5 3 c 6 2 a 7 2 a 8 2 a 9 3 c 10 3 c 11 2 a 12 1 b

[0062] Figure 2 FIG. 1 is a schematic diagram of specific execution steps of the target classification method in an embodiment of the present invention. Figure 2As shown, when grading multiple targets to be graded, clustering algorithms such as K-Means can be used to cluster the targets to be graded into multiple categories, and then the average value of the characteristic data of each target to be graded in each category in each dimension is counted, and the average value is used as the attribute data of the category in the dimension. After that, the attribute data of different categories in the same dimension can be normalized, that is, normalization is performed within each dimension to obtain normalized data of each dimension of each category. After that, the weighted sum of the normalized data of each category can be calculated as the initial score, and the skewness of each category can be calculated to obtain the correction coefficient to correct the initial score to obtain the final score. Finally, the final score is used to grade each category to obtain the level to which each target to be graded belongs.

[0063] In the technical solution of the embodiment of the present invention, the objects to be classified are first clustered according to the characteristic data of each dimension to form multiple categories, and then the attribute data, normalized data, initial score and final score of each category can be calculated in turn and the category classification can be performed using the final score to achieve the classification of each object to be classified. Since the above clustering process takes into account the characteristic data of all dimensions of the objects to be classified, the accuracy is high, thereby ensuring the accuracy of subsequent classification. At the same time, the present invention calculates the skewness of each category to adjust the initial score to obtain the final score for classification, thereby correcting the deviation of the initial score caused by the maximum or minimum value in the normalized data, thereby further ensuring the objectivity and rationality of the classification result. In addition, since the above classification process does not require human participation, when the characteristic data of the object to be classified changes, the classification result can be adjusted dynamically and in real time.

[0064] It should be noted that, for the convenience of description, the aforementioned method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, and some steps can actually be performed in other sequences or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the present invention.

[0065] In order to better implement the above-mentioned solution of the embodiment of the present invention, relevant devices for implementing the above-mentioned solution are also provided below.

[0066] See also Figure 3 As shown, the target grading device 300 provided by the embodiment of the present invention may include: a clustering unit 301 , an attribute data acquiring unit 302 , a final score determining unit 303 and a grading unit 304 .

[0067] Among them, the clustering unit 301 can be used to cluster the targets to be classified using the feature data of at least one dimension of multiple targets to be classified to form multiple categories; the attribute data acquisition unit 302 can be used to obtain the average value of the feature data of the targets to be classified in each dimension in each category, and determine the average value as the attribute data of the category in the dimension; the final score determination unit 303 can be used to use the attribute data of each dimension of each category to determine the initial score and skewness of the category; correct the initial score according to the skewness to obtain the final score of the category; the grading unit 304 can be used to determine the level of each category based on the final score.

[0068] In an embodiment of the present invention, the attribute data acquisition unit 302 can also be used to: after acquiring the attribute data: perform normalization processing on the attribute data of the multiple categories in the same dimension to obtain the normalized data of each category in the dimension; the final score determination unit 303 can also be used to: determine the weighted sum of the normalized data of each dimension in each category as the initial score of the category; determine the mean, median and standard deviation of the normalized data of each dimension in each category, divide the difference between the mean and the median by the standard deviation to obtain the skewness of the category; determine the product of the skewness of each category and a preset adjustment coefficient, determine the difference between 1 and the product as the correction coefficient of the category, and multiply the correction coefficient by the initial score of the category to obtain the final score of the category.

[0069] As a preferred solution, the final score determination unit 303 may also be used to: divide the third-order central moment of the normalized data of each dimension in each category by the cube of the standard deviation to obtain the skewness of the category.

[0070] In the technical solution of the embodiment of the present invention, the objects to be classified are first clustered according to the characteristic data of each dimension to form multiple categories, and then the attribute data, normalized data, initial score and final score of each category can be calculated in turn and the category classification can be performed using the final score to achieve the classification of each object to be classified. Since the above clustering process takes into account the characteristic data of all dimensions of the objects to be classified, the accuracy is high, thereby ensuring the accuracy of subsequent classification. At the same time, the present invention calculates the skewness of each category to adjust the initial score to obtain the final score for classification, thereby correcting the deviation of the initial score caused by the maximum or minimum value in the normalized data, thereby further ensuring the objectivity and rationality of the classification result. In addition, since the above classification process does not require human participation, when the characteristic data of the object to be classified changes, the classification result can be adjusted dynamically and in real time.

[0071] Figure 4 An exemplary system architecture 400 to which the target classification method or target classification apparatus according to the embodiment of the present invention can be applied is shown.

[0072] like Figure 4 As shown, the system architecture 400 may include terminal devices 401, 402, 403, a network 404 and a server 405 (this architecture is only an example, and the components included in the specific architecture may be adjusted according to the specific application). The network 404 is used to provide a medium for a communication link between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0073] Users can use terminal devices 401, 402, 403 to interact with server 405 via network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, 403, such as target classification applications (only as an example).

[0074] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0075] The server 405 may be a server that provides various services, such as a background server (only an example) that supports the target classification application operated by the user using the terminal devices 401, 402, 403. The server 405 may process the received target classification request, etc., and feed back the processing result (such as the classification result - only an example) to the terminal devices 401, 402, 403.

[0076] It should be noted that the target classification method provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the target classification device is generally disposed in the server 405 .

[0077] It should be understood that Figure 4 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0078] The present invention also provides an electronic device. The electronic device of an embodiment of the present invention comprises: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the target classification method provided by the present invention.

[0079] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of an electronic device suitable for implementing an embodiment of the present invention. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0080] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0081] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0082] In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the main step diagram. In the above embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, the above functions defined in the system of the present invention are executed.

[0083] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0084] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0085] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a clustering unit, an attribute data acquisition unit, a final score determination unit, and a grading unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the clustering unit may also be described as "a unit that provides multiple categories to the attribute data acquisition unit".

[0086] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the steps executed by the device include: clustering the multiple objects to be classified using the feature data of at least one dimension of the multiple objects to be classified to form multiple categories; obtaining the average value of the feature data of the objects to be classified in each dimension in each category, and determining the average value as the attribute data of the category in the dimension; using the attribute data of each dimension of each category to determine the initial score and skewness of the category; correcting the initial score according to the skewness to obtain the final score of the category; determining the level of each category according to the final score.

[0087] In the technical solution of the embodiment of the present invention, the objects to be classified are first clustered according to the characteristic data of each dimension to form multiple categories, and then the attribute data, normalized data, initial score and final score of each category can be calculated in turn and the category classification can be performed using the final score to achieve the classification of each object to be classified. Since the above clustering process takes into account the characteristic data of all dimensions of the objects to be classified, the accuracy is high, thereby ensuring the accuracy of subsequent classification. At the same time, the present invention calculates the skewness of each category to adjust the initial score to obtain the final score for classification, thereby correcting the deviation of the initial score caused by the maximum or minimum value in the normalized data, thereby further ensuring the objectivity and rationality of the classification result. In addition, since the above classification process does not require human participation, when the characteristic data of the object to be classified changes, the classification result can be adjusted dynamically and in real time.

[0088] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A target classification method, characterized in that: include: Clustering the objects to be classified using feature data of at least one dimension of the objects to be classified to form multiple categories; the dimension includes at least one of the following: manufacturing time, manufacturing cost, service life, and qualified rate; Obtain the average value of the characteristic data of the target to be classified in each category in each dimension, and determine the average value as the attribute data of the category in the dimension; Using the attribute data of each dimension of each category, determine the initial score and skewness of the category; modify the initial score according to the skewness to obtain the final score of the category; Determine the level of each category based on said final score; The initial score of each category is determined using the attribute data of each dimension of each category, including: determining the weighted sum of the normalized data of each dimension in each category as the initial score of the category.

2. The method according to claim 1, characterized in that The method further comprises: After acquiring the attribute data: performing normalization processing on the attribute data of the multiple categories in the same dimension to obtain normalized data of each category in the dimension.

3. The method according to claim 2, characterized in that The skewness of each category is determined using the attribute data of each dimension of the category, including: Determine the mean, median, and standard deviation of the normalized data for each dimension in each category; Divide the difference between the mean and the median by the standard deviation to get the skewness for that category.

4. The method according to claim 2, characterized in that: The skewness of each category is determined using the attribute data of each dimension of the category, including: The skewness of each category is obtained by dividing the third-order central moment of the normalized data in each dimension in each category by the cube of the standard deviation.

5. The method according to any one of claims 1 to 4, characterized in that: The initial score is corrected according to the skewness, including: Determine the product of the skewness of each category and the preset adjustment coefficient, and determine the difference between 1 and the product as the correction coefficient for the category; Multiply the correction factor by the initial score for the category to get the final score for the category.

6. A target classification device, characterized in that: include: A clustering unit, used to cluster the objects to be classified using feature data of at least one dimension of the objects to be classified to form multiple categories; the dimension includes at least one of the following: manufacturing time, manufacturing cost, service life, and qualified rate; An attribute data acquisition unit, used to acquire an average value of feature data of the target to be classified in each category in each dimension, and determine the average value as the attribute data of the category in the dimension; A final score determination unit is used to determine the initial score and skewness of each category using the attribute data of each dimension of each category; and to correct the initial score according to the skewness to obtain the final score of the category; a grading unit, for determining the grade of each category according to the final score; The final score determination unit is further used to determine the weighted sum of the normalized data of each dimension in each category as the initial score of the category.

7. The device according to claim 6, characterized in that The attribute data acquisition unit is further used to: after acquiring the attribute data: perform normalization processing on the attribute data of the multiple categories in the same dimension to obtain normalized data of each category in the dimension; The final score determination unit is further used to: determine the mean, median and standard deviation of the normalized data of each dimension in each category, and divide the difference between the mean and the median by the standard deviation to obtain the skewness of the category; Determine the product of the skewness of each category and the preset adjustment coefficient, determine the difference between 1 and the product as the correction coefficient of the category, and multiply the correction coefficient by the initial score of the category to obtain the final score of the category.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images