Material grading method, computer equipment and computer storage medium

Abstract

The embodiment of the invention discloses a material grading method, computer equipment and a computer storage medium. The computer equipment determines the importance degree of each material according to the material data and considers the material category to which the material belongs so as to determine the material grading rule corresponding to the material category to which the material belongs, factors for determining accurate grading of the material are considered, and the material grading rule describes the importance degree range corresponding to the grade of each material. Therefore, the material grade of the material can be determined based on the material grading rule corresponding to the category of the material and the importance degree of the material. Therefore, the material grade corresponding to each material can be quickly determined even for huge material data, the material grade calculation efficiency is greatly improved, the calculation cost is saved, the material grade is determined by considering the factor of the material category to which the material belongs, the material grading result is more accurate and accords with the actual condition of the material, and the material grading efficiency is improved. And the material management effectiveness can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of material management, and specifically to a material classification method, a computer device, and a computer storage medium. Background Art

[0002] Enterprise Resource Planning (ERP) system refers to a management platform that is built on the basis of information technology and provides decision-making and operation means for employees with systematic management ideas. It provides the function of integrating real-time information across regions, departments and even companies. The ERP system classifies inventory materials based on the ABC analysis method, that is, the ABC analysis method classifies inventory materials into three levels according to their importance: particularly important inventory (Class A materials), generally important materials (Class B materials) and unimportant materials (Class C materials). It can classify and control different types of materials.

[0003] At present, the classification of material data mainly relies on manual work based on pre-made fixed ABC grading logic to simply count and sort the material consumption data (such as amount, quantity, etc.), and grade the materials according to the sorting results. This requires a lot of manpower and time, with high calculation cost and low calculation efficiency. Summary of the invention

[0004] The embodiments of the present application provide a material grading method, a computer device, and a computer storage medium, which are used to improve the efficiency of material grade calculation, save calculation costs, determine the material grade by considering the material category to which the material belongs, and make the material grading result more accurate.

[0005] A first aspect of an embodiment of the present application provides a material classification method, the method comprising:

[0006] Get material data for each material;

[0007] For each material, determining the importance of the material according to the material data of the material;

[0008] Determine the material category corresponding to each of the materials, and determine the material grading rules corresponding to the material category; the material grading rules are used to describe the importance range of each material grade;

[0009] For each material corresponding to the material category, the material grade of the material is determined according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category.

[0010] A second aspect of an embodiment of the present application provides a computer device, the computer device comprising:

[0011] An acquisition unit, used for acquiring material data of each material;

[0012] A first determining unit is used to determine the importance of each material according to the material data of the material;

[0013] A second determination unit is used to determine the material category corresponding to each of the materials, and to determine the material classification rules corresponding to the material categories; the material classification rules are used to describe the importance range of each material grade;

[0014] The third determining unit is used to determine the material grade of each material corresponding to the material category according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category.

[0015] A third aspect of an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.

[0016] A fourth aspect of an embodiment of the present application provides a computer storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the method of the first aspect.

[0017] A fifth aspect of the embodiments of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device executes the method of the first aspect.

[0018] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0019] The importance of each material is determined based on the material data, and the material category to which the material belongs is taken into consideration to determine the material grading rules corresponding to the material category to which the material belongs. The factors that determine the accurate grading of materials are taken into consideration, and the material grading rules describe the range of importance corresponding to each material grade. Therefore, the material grade of the material can be determined based on the material grading rules corresponding to the material category to which the material belongs and the importance of the material. Therefore, even in the face of huge material data, the material grade corresponding to each material can be quickly determined, which greatly improves the efficiency of material grade calculation and saves calculation costs. In addition, the material grade is determined by considering the material category to which the material belongs, making the material grading results more accurate and in line with the actual situation of the material, which is conducive to improving the effectiveness of material management. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of the network framework in the embodiment of the present application;

[0021] Figure 2 This is a schematic diagram of a process of a material classification method in an embodiment of the present application;

[0022] Figure 3 This is a schematic diagram of the structure of a computer device in an embodiment of the present application;

[0023] Figure 4 This is another structural diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiments of the present application provide a material grading method, a computer device, and a computer storage medium, which are used to improve the efficiency of material grade calculation, save calculation costs, determine the material grade by considering the material category to which the material belongs, and make the material grading result more accurate.

[0025] See also Figure 1 In the embodiment of the present application, the network framework includes:

[0026] The service server 100 and the terminal cluster; the terminal cluster may include: terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n and other terminal devices.

[0027] The business server 100 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud database, cloud service, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform. The terminal device (including terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n) may be a smart phone, tablet computer, laptop computer, desktop computer, PDA, mobile internet device (MID), wearable device (such as smart watch, smart bracelet, etc.), smart computer, smart car and other smart terminals.

[0028] Among them, the business server 100 can establish a communication connection with each terminal device in the terminal cluster, and a communication connection can also be established between each terminal device in the terminal cluster. In other words, the business server 100 can establish a communication connection with each terminal device in the terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n. For example, a communication connection can be established between the terminal device 200a and the business server 100. A communication connection can be established between the terminal device 200a and the terminal device 200b, and a communication connection can also be established between the terminal device 200a and the terminal device 200c. Among them, the above-mentioned communication connection does not limit the connection method, and can be directly or indirectly connected through a wired communication method, or can be directly or indirectly connected through a wireless communication method, etc., which can be determined according to the actual application scenario, and this application is not limited here.

[0029] It should be understood that Figure 1 Each terminal device in the terminal cluster shown can be installed with an application client. When the application client runs in each terminal device, it can interact with the business server 100 respectively, so that the business server 100 can receive business data from each terminal device (such as financial management data uploaded by the user through the terminal device). Among them, the application client can be an application client with the function of displaying text, images, audio and video, such as a financial management application, an enterprise affairs management application, a browser application, a social application, an instant messaging application, a live broadcast application, a game application, a short video application, a video application, a music application, a shopping application, a novel application, a payment application, etc., which can be determined according to the actual application scenario requirements and is not limited here. Among them, the application client can be an independent client or an embedded sub-client integrated in a client (such as a financial management client, an enterprise affairs management client, etc.), which can be determined according to the actual application scenario and is not limited here.

[0030] In the material grading calculation, the relevant scheme relies on manual calculation of material data based on the prefabricated fixed ABC grading logic to determine the corresponding material grade. This method requires a lot of manpower and material resources, especially when the amount of material data is huge, the method of relying on manual calculation of grading is costly and inefficient. Moreover, the manual calculation of material data and material grading does not consider the actual situation of the material to divide the material grade, because the grade classification standards corresponding to different types of materials are not the same. If all materials are graded only according to the fixed material ABC grading logic, the material grading results will be inaccurate, resulting in the material grading results not being consistent with the actual situation of the material, affecting material management.

[0031] In order to solve the above technical problems, a material classification method of the embodiment of the present application is proposed. Figure 1The material classification method in the embodiment of the present application is described in the network framework of:

[0032] See also Figure 2 In the embodiment of the present application, one embodiment of the material classification method includes:

[0033] 201. Get material data for each material;

[0034] The method of this embodiment can be applied to a computer device, which can be Figure 1 The business server 100 or each terminal device in the network framework shown. The computer device can obtain the material data of each material, and the material data can be data of any information about the material, such as the purchase data of the material, the consumption data of the material, etc. The material data can specifically include field information of multiple fields of the material, such as the name, code, specification, remarks, quantity, unit price, historical consumption data, business organization, etc. of the material.

[0035] 202. For each material, determine the importance of the material according to the material data of the material;

[0036] For each material, the computer equipment can determine the importance of the material based on the material data of the material. This importance can be used to guide management personnel to adopt corresponding management strategies for the material.

[0037] 203. Determine a material category corresponding to each of the materials, and determine a material grading rule corresponding to the material category; the material grading rule is used to describe the importance range of each material grade;

[0038] The computer device can determine the material category corresponding to each material, and determine the material grading rules corresponding to the material category. The material grading rules can be used to describe the importance range corresponding to each material grade.

[0039] 204. For each material corresponding to the material category, determine the material grade of the material according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category;

[0040] Since the material classification rule indicates the importance range corresponding to each material grade, when the importance of each material is determined, the importance range of each material can be determined, and then the material grade corresponding to the importance range of the material's importance can be determined as the material grade of the material. For example, the material classification rule defines the importance range corresponding to the three grades of grade A, grade B, and grade C. Assuming that the calculated importance of a certain material falls into the importance range corresponding to grade B, the material grade of the material is determined to be grade B.

[0041] In this embodiment, the importance of each material is determined based on the material data, and the material category to which the material belongs is taken into consideration to determine the material grading rules corresponding to the material category to which the material belongs. The factors that determine the accurate grading of the material are taken into consideration, and the material grading rules describe the range of importance corresponding to each material grade. Therefore, the material grade of the material can be determined based on the material grading rules corresponding to the material category to which the material belongs and the importance of the material. Therefore, even in the face of huge material data, the material grade corresponding to each material can be quickly determined, which greatly improves the efficiency of material grade calculation and saves calculation costs. In addition, the material grade is determined by considering the material category to which the material belongs, so that the material grading results are more accurate, in line with the actual situation of the material, and are conducive to improving the effectiveness of material management.

[0042] based on Figure 2 In the illustrated embodiment, in an optional implementation, a preset index of a material can be calculated and the material grade can be determined based on the preset index. Specifically, the importance range corresponding to each material grade may include an index value range of a preset index, and the preset index corresponds to the importance of the material. The index value of the preset index can be used to characterize the importance corresponding to the material. Therefore, when determining the importance of a material based on material data, the index value of the preset index of the material can be calculated based on the material data of the material. For example, for any preset index, an algorithm for calculating the index value of the preset index can be obtained. The algorithm of the preset index is a method for processing material data, including but not limited to statistical analysis, subtraction, accumulation, and proportion calculation of material data. Therefore, the material data can be processed based on the algorithm corresponding to the preset index to obtain the index value of the material data at the preset index.

[0043] Furthermore, when determining the material grade, the material grade corresponding to the index value range into which the index value of the material falls can be determined as the material grade of the material among the multiple index value ranges of the multiple material grades of the material grading rules corresponding to the material category to which the material belongs.

[0044] The preset indicator may be any indicator of the material, as long as it can be used to describe the importance of the material. In some optional ways, the preset indicator may include the cumulative ratio of the target attribute of each material corresponding to the material category to which the material belongs, and the target attribute may be any attribute of the material, such as the consumption of the material, the amount of the material, and the like, and the indicator value range of the preset indicator includes the cumulative ratio range corresponding to the cumulative ratio.

[0045] When determining the material grade based on the target attribute, the target cumulative proportion range within which the cumulative proportion of the target attribute of the material falls can be determined within the multiple cumulative proportion ranges of the multiple material grades of the material grading rules corresponding to the material category to which the material belongs, and the material grade corresponding to the target cumulative proportion range can be determined as the material grade of the material.

[0046] For example, if the material grade of a material is calculated according to the amount of the material, the cumulative proportion of the amount consumed by a certain material can be calculated first, and then in the multiple cumulative proportion ranges of the multiple material grades of the material grading rules corresponding to the material category to which the material belongs, such as the multiple material grades of the material grading rules corresponding to the material category to which the material belongs include Grade A, Grade B and Grade C, and each grade corresponds to a cumulative proportion range. If it is determined that the cumulative proportion of the amount consumed by the material falls within the cumulative proportion range corresponding to Grade B, then the material grade of the material can be determined to be Grade B.

[0047] The cumulative proportion of the target attribute of each material corresponding to the material category to which the material belongs can be determined by sorting the material data of the target attribute of multiple materials corresponding to the material category to which the material belongs in a preset order to obtain a sorting result; and calculating the proportion of the material data of each material in the target attribute to the material data of all materials corresponding to the material category. Furthermore, for the first material corresponding to the material category to which the material belongs in the sorting result, the proportion of the first material is taken as the cumulative proportion of the first material; and for each material after the first material corresponding to the material category to which the material belongs in the sorting result, the proportion of the material and the cumulative proportion of the previous material in the sorting result are added to obtain the cumulative proportion of the material in the target attribute.

[0048] For example, materials are classified into material grades according to the amount of material consumption. Suppose that material 1, material 2, and material 3 all belong to the material category of "mechanical parts", and the amount of their respective consumption is 5,000, 12,000, and 8,000 respectively. Then the materials are sorted in order of the amount from large to small, and the sorting result is material 2-material 3-material 1. The proportion of the amount consumed by each material in the amount consumed by all materials in the material category is calculated separately. For example, the proportion of the amount consumed by material 1 in the amount consumed by all materials is 20%, the corresponding proportion of material 2 is 48%, and the corresponding proportion of material 3 is 32%. According to the above sorting results, the cumulative proportion of material 2 is 48%, the cumulative proportion of material 3 is 80%, and the cumulative proportion of material 1 is 100%.

[0049] Moreover, according to the material grading rules corresponding to the material category of "mechanical parts", the cumulative proportion range of the amount corresponding to Grade A is within 80%, the cumulative proportion range of the amount corresponding to Grade B is 80% to 95%, and the cumulative proportion range of the amount corresponding to Grade C is 95 to 100%. It can be determined that Material 2 falls into the cumulative proportion range of the amount corresponding to Grade A, and the material grade of Material 2 is determined to be Grade A; by analogy, it can be determined that the material grade of Material 1 is Grade C, and the material grade of Material 3 is Grade B.

[0050] Of course, the material grade of the material may also be determined directly according to the ratio of the target attribute of the material, without calculating the cumulative ratio of the target attribute of the material to determine the material grade of the material, which is not limited here.

[0051] Therefore, the material grade of the material is determined according to the material data of the target attribute of the material, wherein the target attribute may include a variety of arbitrary attributes of the material. Therefore, the index value of the preset index of the material can be calculated considering various factors of the material, and the material grade of the material can be determined based on the index value, so that the determination of the material grade is more in line with the actual situation of the material, which can ensure that the material grade classification is more accurate, and provide an accurate and effective data basis for material management.

[0052] In an optional manner, a grading model may be used to grade materials. The grading model may integrate one or more material grading rules, and material data may be input into the grading model. The grading model determines the corresponding material category based on the material data, and further determines the available material grading rules based on the determined material category. In addition, the grading model may calculate the index value of the preset index corresponding to each material (such as the cumulative proportion mentioned above), determine the material grade corresponding to each material based on the material grading rule and the calculated index value, and output the grading results to the user for viewing.

[0053] The user can confirm the grading results output by the model. If the confirmation is correct, the grading results output by the model can be adopted. If there are erroneous grading results in the grading results, the user can confirm whether there are abnormalities in the material data, such as confirming whether there are significant deviations between the current material data and the historical material data. If there are abnormalities in the material data, the abnormal material data can be corrected and the corrected material data can be input into the grading model so that the grading model can re-grade the materials based on the corrected material data. Alternatively, when the user confirms that there are abnormalities in the grading results output by the model and confirms that there are no abnormal data in the material data, the index value range corresponding to each material grade in the material grading rules can be adjusted, such as adjusting the cumulative proportion range corresponding to each material grade. The grading model then re-grades the materials based on the adjusted grading rules and outputs the re-graded grading results.

[0054] based on Figure 2In the illustrated embodiment, in an optional implementation manner, the material data used for grading processing may be the original data of various materials in the ERP system, or may be the material data obtained by preprocessing the original data. Therefore, when obtaining material data, one preprocessing method may be to obtain the material data of each material in the historical period, and for each material, calculate the target reference range of the reference index of the material based on the material data of the material in the historical period. Afterwards, the original material data of each material in the current period may be obtained, and for each material, the target material data may be extracted from the material data of the material in the current period based on the target reference range of the material, and the material data of each material used for material grading processing may be obtained.

[0055] For example, the data preprocessing model can be used to preprocess the material data. The material consumption data of a certain historical period of each business organization in the ERP system can be introduced into the data preprocessing model, or the material data of the historical period can be imported through a table for data preprocessing and model training. In the data preprocessing model, the model can calculate the index values ​​of benchmark indicators such as the average consumption quantity, maximum and minimum consumption quantity of each material based on a combination of algorithms such as the moving average algorithm and the weighted average algorithm, or calculate the index values ​​of benchmark indicators such as the average consumption cycle, the shortest consumption cycle, and the longest consumption cycle of the material.

[0056] After obtaining the indicator values ​​of the above-mentioned benchmark indicators, the corresponding target benchmark range can be determined based on the indicator values ​​of the above-mentioned benchmark indicators. For example, the target benchmark range of material consumption of a certain material can be determined according to the indicator values ​​of benchmark indicators such as average consumption quantity, maximum and minimum consumption quantity. Therefore, when the original material data of the material in the current period is input into the data preprocessing model, the model can confirm the original material data of the material in the current period based on the target benchmark range. For example, the material data that meets the target benchmark range can be labeled with a label indicating that the data is accurate, such as the words "compliant business data", indicating that the material data can be used for subsequent calculations; the material data that does not meet the target benchmark range can be labeled with a label indicating that the data is abnormal, such as the words "false data for supplementary orders", indicating that the material data needs to be eliminated and cannot be used for subsequent material grading processing.

[0057] The model can output the labeling results of each material data to the user for confirmation. When the user confirms that the labeling results of the model are correct, the model can automatically extract the target material data from the original material data of the material in the current period based on the labeling results, for example, retain the material data in the original material data of the material in the current period that meets the target benchmark range, and remove the material data in the original material data of the material in the current period that exceeds the target benchmark range. If the user confirms that some of the labeling results are incorrect, the labeling results of the model can be corrected. For example, if the model determines that a certain material data is abnormal, the user can correct it to normal material data, and trigger the model to recalculate the target benchmark range of the material in each benchmark indicator based on the corrected labeling results, and re-extract new target material data from the original material data according to the updated target benchmark range.

[0058] Therefore, preprocessing the material data used for material grading can improve the reliability and accuracy of the material data, ensure more accurate material grading processing, and help improve the accuracy of material grading.

[0059] based on Figure 2 In an optional implementation of the illustrated embodiment, the material category to which a material belongs may be determined based on a variety of methods. One method is that for each material, the material category identifier that matches the material identifier of the material is determined based on a text similarity algorithm, and the material category corresponding to the material category identifier is the material category corresponding to the material. Another method may be that for each material, the material category identifier that matches the group identifier to which the material belongs is determined based on a text similarity algorithm, and the material category corresponding to the material category identifier is the material category corresponding to the material.

[0060] Among them, based on the text similarity algorithm, the material category identifier that matches the material identification of the material is determined, or the material category identifier that matches the group identifier to which the material belongs is determined. An optional implementation method is to perform word segmentation processing on the description information of the material to obtain the material identification of the material, and determine the matching words with the highest similarity to the material identification of the material in a preset word library based on the text similarity algorithm; based on the correspondence between the words preset in the word library and the material category identifier, the material category identifier corresponding to the matching words is determined as the material category identifier matched by the material identification of the material.

[0061] Similarly, the material category corresponding to a material can also be determined by the material group identifier to which the material belongs. For example, an optional method is to perform word segmentation processing on the description information of each material to obtain the group identifier to which the material belongs, and determine the matching words with the highest similarity to the group identifier to which the material belongs in the word library, and based on the correspondence between the words preset in the word library and the material category identifier, determine the material category identifier corresponding to the matching word as the material category identifier matched by the material identifier of the material, thereby determining the material category corresponding to the material.

[0062] For example, the master data text, material group and other descriptive information of the preprocessed materials can be collected, and the descriptive information about the materials can be input into the search program. The search program can have a built-in plug-in with a search function, such as a built-in Elasticsearch (search server), so that the search plug-in can be used to segment the description information of the materials, and the material identification of the materials can be obtained. The key words that match the material identification of the materials can be searched in the pre-configured word library, that is, the similarity between each word and the material identification is calculated in the word library according to the text similarity algorithm, and the word with the highest similarity is determined to be the word that matches the material identification. In addition, the word library also records the correspondence between each word and the material category identification, so the material category identification corresponding to the word that matches the material identification can be determined based on the correspondence, and then the material category corresponding to the material category identification is the material category to which the material belongs.

[0063] The text similarity algorithm can calculate the semantic similarity between texts. The specific similarity algorithm can be a cosine distance, Euclidean distance, inner product, or other similarity algorithms, which are not limited here.

[0064] Therefore, the similarity algorithm can be used to efficiently and accurately determine the material category corresponding to the material, ensuring accurate classification of the material category, which in turn helps to accurately determine the material grading rules corresponding to the material category.

[0065] Based on the aforementioned embodiments and their various optional implementations, after determining the material grades corresponding to various materials, the grading results can be output and synchronized with various ERP systems and platforms. The grading results of various materials can be sent to various ERP systems and platforms. Users of various ERP systems and platforms can independently view the detailed data of ABC grading of materials through system functions. The ERP system can synchronously update the main data of the materials according to the grading results of the materials. By automatically integrating the material grading results through the ERP system, the workload of manually updating material information one by one can be reduced.

[0066] The material classification method in the embodiment of the present application is described above. The computer device in the embodiment of the present application is described below. Figure 3 In the embodiment of the present application, one embodiment of the computer device includes:

[0067] An acquisition unit, used for acquiring material data of each material;

[0068] A first determining unit is used to determine the importance of each material according to the material data of the material;

[0069] A second determination unit is used to determine the material category corresponding to each of the materials, and to determine the material classification rules corresponding to the material categories; the material classification rules are used to describe the importance range of each material grade;

[0070] The third determining unit is used to determine the material grade of each material corresponding to the material category according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category.

[0071] In a preferred implementation of this embodiment, the importance range includes an indicator value range of a preset indicator;

[0072] The first determination unit is specifically used to calculate the index value of the preset index of the material according to the material data of the material, and the index value of the preset index is used to represent the importance corresponding to the material;

[0073] The third determination unit is specifically used to determine, among the multiple index value ranges of the multiple material grades of the material grading rule corresponding to the material category, the material grade corresponding to the index value range into which the index value of the material falls as the material grade of the material.

[0074] In a preferred implementation of this embodiment, the preset indicator includes the cumulative ratio of the target attribute of each material corresponding to the material category; the indicator value range of the preset indicator includes the cumulative ratio range corresponding to the cumulative ratio;

[0075] The third determining unit is specifically configured to:

[0076] Determine, among the multiple cumulative proportion ranges of the multiple material grades of the material grading rule corresponding to the material category, a target cumulative proportion range within which the cumulative proportion of the target attribute of the material falls;

[0077] The material grade corresponding to the target cumulative proportion range is determined as the material grade of the material.

[0078] In a preferred implementation manner of this embodiment, the third determining unit is specifically configured to:

[0079] The step of determining the cumulative proportion of the target attribute of each material corresponding to the material category is performed, and the determining step includes:

[0080] Sorting the material data of the target attribute of the multiple materials corresponding to the material category in a preset order to obtain a sorting result;

[0081] Calculate the ratio of the material data of each material in the target attribute to the material data of all materials corresponding to the material category in the target attribute;

[0082] For the first material corresponding to the material category in the sorting result, the proportion of the first material is used as the cumulative proportion of the first material;

[0083] For each material after the first material corresponding to the material category in the sorting result, the proportion of the material and the cumulative proportion of the previous material in the sorting result are accumulated to obtain the cumulative proportion of the material in the target attribute.

[0084] In a preferred implementation manner of this embodiment, the acquisition unit is specifically used for:

[0085] Get material data for each material during the historical period;

[0086] A data preprocessing model is obtained, and material data of each material during the historical period is input into the data preprocessing model, so that the data preprocessing model performs the following steps:

[0087] For each material, a target benchmark range of the benchmark indicator of the material is calculated based on the material data of the material during the historical period;

[0088] Get the original material data of each material in the current period;

[0089] For each material, target material data is extracted from the original material data of the material in the current period according to the target reference range of the material, so as to obtain material data of the material for material classification.

[0090] In a preferred implementation manner of this embodiment, the second determining unit is specifically configured to:

[0091] For each material, the description information of the material is segmented to obtain the material identification of the material, and the matching words with the highest similarity to the material identification of the material are determined in the preset word library. Based on the correspondence between the words preset in the word library and the material category identification, the material category identification corresponding to the matching words is determined as the material category identification matched by the material identification of the material, so as to determine the material category corresponding to the material;

[0092] or,

[0093] For each material, the description information of the material is segmented to obtain the group identifier to which the material belongs, and the matching word with the highest similarity to the group identifier to which the material belongs is determined in the vocabulary library. Based on the correspondence between the words preset in the vocabulary library and the material category identifier, the material category identifier corresponding to the matching word is determined as the material category identifier matched by the material identifier of the material, so as to determine the material category corresponding to the material.

[0094] In a preferred implementation manner of this embodiment, the acquisition unit is further used for:

[0095] Obtaining a preset material classification model, wherein the material classification model integrates a plurality of material classification rules;

[0096] Inputting the material data of each material into the material classification model, so that the material classification model executes the material classification method on the material data of each material based on the material classification rule, and outputs the material classification result of each material;

[0097] When an adjustment operation on the material data is received, the adjusted material data is input into the material classification model, so that the material classification model executes the material classification method on the adjusted material data based on the material classification rule, and outputs a result of material reclassification.

[0098] In this embodiment, the operations performed by each unit in the computer device are the same as those described above. Figure 2 The description in the illustrated embodiment is similar and will not be repeated here.

[0099] The computer device in the embodiment of the present application is described below. Figure 4 In the embodiment of the present application, one embodiment of the computer device includes:

[0100] The computer device 400 may include one or more central processing units (CPU) 401 and a memory 405 , wherein the memory 405 stores one or more application programs or data.

[0101] The memory 405 may be a volatile storage or a persistent storage. The program stored in the memory 405 may include one or more modules, each of which may include a series of instruction operations in the computer device. Furthermore, the central processor 401 may be configured to communicate with the memory 405 and execute a series of instruction operations in the memory 405 on the computer device 400.

[0102] The computer device 400 may also include one or more power supplies 402, one or more wired or wireless network interfaces 403, one or more input and output interfaces 404, and / or one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0103] The CPU 401 can execute the aforementioned Figure 2 The operations performed by the computer device in the illustrated embodiment will not be described in detail here.

[0104] The present application also provides a computer storage medium, wherein one embodiment includes: the computer storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the aforementioned Figure 2 The operations performed by the computer device in the illustrated embodiment.

[0105] The present application also provides a computer program product, wherein one embodiment includes: when the computer program product is run on a computer device, the computer device executes the aforementioned Figure 2 The operations performed by the computer device in the illustrated embodiment.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0107] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A material classification method, characterized in that: The method comprises: Get material data for each material; For each material, determining the importance of the material according to the material data of the material; Determine the material category corresponding to each of the materials, and determine the material grading rules corresponding to the material category; the material grading rules are used to describe the importance range of each material grade; For each material corresponding to the material category, the material grade of the material is determined according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category.

2. The method according to claim 1, characterized in that The importance range includes the indicator value range of the preset indicator; Determining the importance of the material according to the material data of the material includes: Calculating an index value of the preset index of the material according to the material data of the material, wherein the index value of the preset index is used to represent the importance of the material; Determining the material grade of the material according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category includes: Among the multiple index value ranges of the multiple material grades of the material grading rule corresponding to the material category, the material grade corresponding to the index value range into which the index value of the material falls is determined as the material grade of the material.

3. The method according to claim 2, characterized in that The preset indicator includes the cumulative proportion of the target attribute of each material corresponding to the material category; the indicator value range of the preset indicator includes the cumulative proportion range corresponding to the cumulative proportion; The step of determining, among the multiple index value ranges of the multiple material grades of the material grading rule corresponding to the material category, the material grade corresponding to the index value range into which the index value of the material falls as the material grade of the material comprises: Determine, among the plurality of the cumulative proportion ranges of the plurality of material grades of the material grading rule corresponding to the material category, a target cumulative proportion range into which the cumulative proportion of the material at the target attribute falls; The material grade corresponding to the target cumulative proportion range is determined as the material grade of the material.

4. The method according to claim 3, characterized in that The cumulative proportion of the target attribute of each material corresponding to the material category, wherein the steps of determining the cumulative proportion of the target attribute of each material corresponding to the material category include: Sorting the material data of the target attribute of the multiple materials corresponding to the material category in a preset order to obtain a sorting result; Calculate the ratio of the material data of each material in the target attribute to the material data of all materials corresponding to the material category in the target attribute; For the first material corresponding to the material category in the sorting result, the proportion of the first material is used as the cumulative proportion of the first material; For each material after the first material corresponding to the material category in the sorting result, the proportion of the material and the cumulative proportion of the previous material in the sorting result are accumulated to obtain the cumulative proportion of the material in the target attribute.

5. The method according to claim 1, characterized in that The obtaining of material data of each material includes: Get material data for each material during the historical period; A data preprocessing model is obtained, and material data of each material during the historical period is input into the data preprocessing model, so that the data preprocessing model performs the following steps: For each material, a target benchmark range of the benchmark indicator of the material is calculated based on the material data of the material during the historical period; Get the original material data of each material in the current period; For each material, target material data is extracted from the original material data of the material in the current period according to the target reference range of the material, so as to obtain material data of the material for material classification.

6. The method according to claim 1, characterized in that The determining of the material category corresponding to each of the materials includes: For each material, the description information of the material is segmented to obtain the material identification of the material, and the matching words with the highest similarity to the material identification of the material are determined in the preset word library. Based on the correspondence between the words preset in the word library and the material category identification, the material category identification corresponding to the matching words is determined as the material category identification matched by the material identification of the material, so as to determine the material category corresponding to the material; or, For each material, the description information of the material is segmented to obtain the group identifier to which the material belongs, and the matching word with the highest similarity to the group identifier to which the material belongs is determined in the vocabulary library. Based on the correspondence between the words preset in the vocabulary library and the material category identifier, the material category identifier corresponding to the matching word is determined as the material category identifier matched by the material identifier of the material, so as to determine the material category corresponding to the material.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Obtaining a preset material classification model, wherein the material classification model integrates a plurality of material classification rules; Inputting the material data of each material into the material classification model, so that the material classification model executes the material classification method on the material data of each material based on the material classification rule, and outputs the material classification result of each material; When an adjustment operation on the material data is received, the adjusted material data is input into the material classification model, so that the material classification model executes the material classification method on the adjusted material data based on the material classification rule, and outputs a result of material reclassification.

8. A computer device, characterized in that: The computer device comprises: An acquisition unit, used for acquiring material data of each material; A first determining unit is used to determine the importance of each material according to the material data of the material; A second determination unit is used to determine the material category corresponding to each of the materials, and to determine the material classification rules corresponding to the material categories; the material classification rules are used to describe the importance range of each material grade; The third determination unit is used to determine the material grade of each material corresponding to the material category according to the importance of the material and the importance range of each material grade in the material grading rule corresponding to the material category.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 7.

Images