Industrial chain quality evaluation method, apparatus and device, and readable storage medium
By obtaining the indicator data of the target industrial chain and the time of event occurrence, and using the dual-differential method model to evaluate the quality of the industrial chain, the problem of poor evaluation flexibility in traditional methods is solved, and higher flexibility and accuracy are achieved.
Patent Information
- Application Number
- CN202411034561.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-12-03
AI Technical Summary
The traditional industrial chain quality evaluation method has the problem of poor evaluation flexibility, especially the gray correlation analysis method requires subjective preset weights, and the multi-dimensional pyramid model needs to be updated frequently, resulting in low evaluation accuracy and high cost.
By obtaining the indicator data of the target industrial chain and the preset time period and the time of the target event, using the dual-differential method model to extract feature data, calculate the impact of the target event on the industrial chain quantitative data, and then evaluate the quality of the industrial chain, avoiding subjective weights Analysis and model updates.
It improves the flexibility and accuracy of industrial chain quality assessment, simplifies the analysis process, reduces waste of computing resources, and enhances sensitivity to overall changes.
Smart Images

Figure CN119067485A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of industrial chain, and in particular to an industrial chain quality assessment method, device, equipment, and readable storage medium. Background Art
[0002] The industrial chain usually refers to the entire industrial chain from raw materials to consumers. The quality of the industrial chain can reflect the impact resistance of the industrial chain. Therefore, it is necessary to evaluate the quality of the industrial chain.
[0003] Traditional evaluation methods usually analyze relevant indicator information of the industrial chain (such as business income, total taxes and fees, number of property rights, etc.) based on the grey correlation analysis method or the multidimensional pyramid model to obtain the evaluation results of the quality of the industrial chain.
[0004] However, the above-mentioned industrial chain quality assessment method has the problem of poor assessment flexibility. Summary of the invention
[0005] Based on this, it is necessary to provide an industrial chain quality assessment method, device, equipment, and readable storage medium that can improve assessment flexibility in response to the above-mentioned technical problems.
[0006] In a first aspect, the present application provides an industrial chain quality assessment method, including:
[0007] Obtain the indicator data corresponding to the target industrial chain and the preset time period, and obtain the occurrence time of the target event corresponding to the target industrial chain, which is within the preset time period;
[0008] Obtain quantitative data on the impact of the target event on the target industrial chain based on the occurrence time and indicator data;
[0009] Based on the quantitative data of target impact, the quality of the target industrial chain is evaluated.
[0010] In the above embodiment, by calculating the quantitative data of the target impact of the target event occurring within the preset time period corresponding to the indicator data on the target industrial chain, the quality of the target industrial chain is evaluated according to the quantitative data of the target impact. There is no need to analyze the relevant indicator information based on subjective preset weights as when evaluating the quality of the industrial chain through the grey correlation analysis method, and there is no need to continuously train and update the multidimensional pyramid model as when evaluating the quality of the industrial chain through the multidimensional pyramid model. The technical solution provided by the present application is more flexible in evaluating the quality of the industrial chain.
[0011] In one embodiment, according to the occurrence time and indicator data, quantitative data of the target impact of the target event on the target industrial chain is obtained, including:
[0012] Extract features from the indicator data according to the occurrence time to obtain first feature data and second feature data, where the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time;
[0013] Target impact quantified data is determined based on the first feature data and the second feature data.
[0014] In the above embodiment, feature extraction is performed on the indicator data according to the occurrence time to obtain first feature data before the occurrence time and second feature data after the occurrence time, and the target impact quantification data is determined based on the first feature data and the second feature data. The determination method is simple and more flexible.
[0015] In one embodiment, there are multiple indicator data, and the target impact quantitative data is determined according to the first feature data and the second feature data, including:
[0016] For each indicator data, determining candidate impact quantification data corresponding to the indicator data according to the first feature data and the second feature data corresponding to the indicator data;
[0017] The target impact quantification data is determined according to each candidate impact quantification data.
[0018] In the above embodiment, candidate impact quantification data is first determined for each indicator data, and then target impact quantification data is determined based on each candidate quantification data. The determination process is more detailed, so that the target impact quantification data finally determined is more accurate.
[0019] In one embodiment, determining candidate impact quantification data corresponding to the indicator data according to first feature data and second feature data corresponding to the indicator data includes:
[0020] Substituting the first characteristic data and the second characteristic data into the double difference method model respectively, to obtain first influence quantification data corresponding to the first characteristic data and second influence quantification data corresponding to the second characteristic data;
[0021] Acquire first significance quantitative data corresponding to the first influence quantitative data according to the first influence quantitative data, and acquire second significance quantitative data corresponding to the second influence quantitative data according to the second influence quantitative data;
[0022] The candidate impact quantification data is obtained according to the difference between the first saliency quantification data and the second saliency quantification data.
[0023] In the above embodiment, the first feature data and the second feature data are analyzed by using a double difference model, and the analysis process is simpler.
[0024] In one embodiment, determining the target impact quantification data according to each candidate impact quantification data includes:
[0025] The largest candidate influence quantization data among the candidate influence quantization data is determined as the target influence quantization data.
[0026] In the above embodiment, by focusing on the indicator data that has the greatest impact on the quantitative data of the target, the analysis process can be simplified while maintaining sensitivity to overall changes.
[0027] In one embodiment, the quality of the target industrial chain is evaluated based on the target impact quantitative data, including:
[0028] The quality assessment result of the target industrial chain is determined based on the size of the target impact quantitative data. The target impact quantitative data is negatively correlated with the quality of the target industrial chain.
[0029] In the above embodiment, the quality assessment result of the target industrial chain is determined by the size of the target impact quantification data, the assessment process is simple, and the waste of computing resources is reduced.
[0030] In one embodiment, there are multiple indicator data, and obtaining the indicator data corresponding to the target industrial chain and the preset time period includes:
[0031] Obtain multiple initial indicator data;
[0032] The initial indicator data are preprocessed to obtain the indicator data. The preprocessing at least includes consistency processing. The consistency processing is used to adjust the indicator directionality of the initial indicator data to be consistent.
[0033] In the above embodiment, by performing consistency processing on the unprocessed initial indicator data, the uniformity of the indicator directionality of the indicator data is ensured, and the data quality of the indicator data is improved.
[0034] In a second aspect, the present application also provides an industrial chain quality assessment device, including:
[0035] An acquisition module is used to acquire the indicator data corresponding to the target industrial chain and the preset time period, and acquire the occurrence time of the target event corresponding to the target industrial chain, which is within the preset time period;
[0036] The impact module is used to obtain the quantitative data of the target impact of the target event on the target industrial chain based on the occurrence time and indicator data;
[0037] The evaluation module is used to evaluate the quality of the target industrial chain based on the quantitative data of target impact.
[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.
[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.
[0040] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.
[0041] The above-mentioned industrial chain quality assessment method, device, equipment, and readable storage medium can obtain the target impact quantitative data of the target event on the target industrial chain according to the occurrence time and the indicator data by obtaining the indicator data corresponding to the target industrial chain and the preset time period, and obtain the occurrence time of the target event corresponding to the target industrial chain. And according to the target impact quantitative data, the quality of the target industrial chain is evaluated, wherein the occurrence time is within the preset time period. In this way, by calculating the target impact quantitative data of the target event occurring within the preset time period corresponding to the indicator data on the target industrial chain, the quality of the target industrial chain is evaluated according to the target impact quantitative data, without the need to analyze the relevant indicator information based on the subjective preset weights when evaluating the quality of the industrial chain through the gray correlation analysis method, and without the need to continuously train and update the multidimensional pyramid model when evaluating the quality of the industrial chain through the multidimensional pyramid model. The technical solution provided by the present application is more flexible when evaluating the quality of the industrial chain. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0043] FIG1 is a diagram of an application environment of an industrial chain quality assessment method in one embodiment;
[0044] Figure 2 A schematic diagram of a process flow of an industrial chain quality assessment method in one embodiment;
[0045] Figure 3 is a flow chart of step 202 in another embodiment;
[0046] Figure 4 is a flow chart of step 302 in another embodiment;
[0047] Figure 5 is a flow chart of an exemplary industrial chain quality assessment method in another embodiment;
[0048] Figure 6 is a structural block diagram of an industrial chain quality assessment device in one embodiment;
[0049] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0051] The industrial chain usually refers to the entire industrial chain from raw materials to the hands of consumers. In recent years, the market environment has strongly supported the high-quality development of the industrial chain by filling in the gaps in the industrial chain, upgrading the traditional industrial chain, and establishing emerging industrial chains to enhance the stability and competitiveness of the industrial chain development.
[0052] The quality of the industrial chain can reflect its ability to resist shocks, so it is necessary to evaluate the quality of the industrial chain.
[0053] Traditional evaluation methods usually analyze relevant indicator information of the industrial chain (such as business income, total taxes and fees, number of property rights, etc.) based on the grey correlation analysis method or the multidimensional pyramid model to obtain the evaluation results of the quality of the industrial chain.
[0054] When evaluating the quality of an industrial chain through the grey correlation analysis method, it is necessary to first screen the relevant indicator information of the industrial chain in order to select the important indicator information. However, the screening process relies on subjectively set weights, which results in low evaluation accuracy.
[0055] When evaluating the quality of the industrial chain through a multidimensional pyramid model, a multidimensional pyramid model is trained in advance, and then the trained multidimensional pyramid model is used to analyze the relevant indicator information. However, the input and output dimensions of the trained multidimensional pyramid model are fixed, but the relevant indicator information of the industrial chain is constantly changing with the passage of time. If the multidimensional pyramid model is used to evaluate the quality of the industrial chain, the multidimensional pyramid model needs to be continuously trained and updated, resulting in excessively high evaluation costs.
[0056] Therefore, the above-mentioned real estate industry chain quality assessment methods all have the problem of poor assessment flexibility.
[0057] In view of this, the present application provides an industrial chain quality assessment method, device, equipment, and readable storage medium. By obtaining the index data corresponding to the target industrial chain and the preset time period, and obtaining the occurrence time of the target event corresponding to the target industrial chain, the target impact quantitative data of the target event on the target industrial chain can be obtained according to the occurrence time and the index data, and the quality of the target industrial chain can be assessed according to the target impact quantitative data, wherein the occurrence time is within the preset time period. In this way, by calculating the target impact quantitative data of the target event on the target industrial chain that occurs within the preset time period corresponding to the index data, the quality of the target industrial chain is assessed according to the target impact quantitative data, without the need to analyze the relevant index information based on the subjective preset weights when evaluating the quality of the industrial chain through the gray correlation analysis method, and without the need to continuously train and update the multidimensional pyramid model when evaluating the quality of the industrial chain through the multidimensional pyramid model, the technical solution provided by the present application is more flexible when evaluating the quality of the industrial chain.
[0058] The industrial chain quality assessment method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the data storage system can store the data that the server 101 needs to process, and the data storage system can be integrated on the server 101, or placed on the cloud or other network servers. The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.
[0059] In an exemplary embodiment, Figure 2 As shown, a method for evaluating the quality of an industrial chain is provided. The method is applied to the server 101 in FIG. 1 as an example for explanation. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The method includes the following steps 201 to 203. Among them:
[0060] Step 201 : obtaining indicator data corresponding to a target industrial chain and a preset time period, and obtaining the occurrence time of a target event corresponding to the target industrial chain.
[0061] The occurrence time is within a preset time period.
[0062] The target industrial chain can be the industrial chain to be evaluated, and the indicator can be information closely related to the development of the target industrial chain. In the embodiment of the present application, the indicator can be set according to actual application needs. For example, according to the content of the talent, innovation and industrial chain quality report, five dimensions of indicators can be divided, including talent capital, enterprise vitality, manufacturing performance, overall industry situation, and innovation resources. Among them, enterprise vitality can be broken down into three indicators, including main business income, total actual tax payment, and number of employees at the end of the period. The dimension of innovation resources can include three indicators: R&D expenses, the proportion of R&D expenses to main business income, and the proportion of research and development personnel to employees. The dimension of manufacturing performance can include two indicators: the number of intellectual property rights and energy consumption indicators. The overall industry situation can include the growth rate of main business income. Talent capital includes the proportion of technical talents and the growth rate of technical talents.
[0063] The indicator data corresponds to the preset indicators. Optionally, the server can collect global information of the target industrial chain. The global information may include enterprise data, enterprise recognition data, industry distribution data, and main product production data, etc. Then, the required indicator data is filtered out from the global information according to the preset indicators; optionally, the server can collect the required indicator data according to the preset indicators.
[0064] In a possible implementation, there are multiple indicator data, and the process of obtaining the indicator data corresponding to the target industrial chain and the preset time period may include: the server obtains multiple initial indicator data, and then preprocesses each initial indicator data to obtain each indicator data.
[0065] In an embodiment of the present application, the server can collect multiple initial indicator data according to preset indicators. Regarding the collection method, optionally, the server can directly obtain multiple initial indicator data from a database; optionally, the server can obtain multiple initial indicator data input externally through an external interface.
[0066] Since these initial indicator data are all unprocessed data and the data quality is not high, in order to improve the data quality and thus improve the accuracy of the quality assessment of the industrial chain, in an embodiment of the present application, the server can also perform data preprocessing on the initial indicator data, wherein the preprocessing at least includes consistency processing, and the consistency processing is used to adjust the indicator directionality of each initial indicator data to be consistent. For example, the indicator directionality of the A indicator data is positive, that is, the larger the value, the better the indicator, and the indicator directionality of the B indicator data is negative, that is, the smaller the value, the better the indicator. If the two indicators are not processed consistently, the result obtained by analyzing the two indicators comprehensively will be erroneous. Therefore, the server can perform consistency processing on each indicator data to ensure the uniformity of the indicator directionality of each data.
[0067] Optionally, data preprocessing also includes data cleaning, verification, conversion, standardization, etc. For example, standardization can make the values of each indicator data fall within a specific numerical range, such as 0-1, or -1-1, thereby eliminating the differences in characteristic attributes such as dimension, order of magnitude, and nature of each indicator data, and converting each indicator data into a unified standard.
[0068] After obtaining the indicator data corresponding to the preset time period, the server can evaluate the quality of the target industrial chain by analyzing the impact of a certain target event occurring within the preset time period on the target industrial chain.
[0069] In an embodiment of the present application, the target event may be a policy targeted at a target industrial chain. These events will have an impact on the target industrial chain, and the impact can be reflected through the indicator data of the target industrial chain. For example, the preset time period is from 2014 to 2018, and a trade protection policy is promulgated in 2017. Tariff barriers are raised, resulting in increased costs. The main business income in the indicator data may decline after 2016. However, when the quality of the industrial chain is high, its risk resistance is strong, and the main business income may recover in the subsequent period. For industrial chains with poorer quality, due to their weaker risk resistance, the main business income may decline all the way. Therefore, by analyzing the impact of the target event on the target industrial chain, the quality of the target industrial chain can be evaluated.
[0070] Step 202, obtaining quantitative data of the target impact of the target event on the target industrial chain according to the occurrence time and indicator data.
[0071] In an embodiment of the present application, quantitative data of the target impact of the target event on the target industrial chain can be obtained based on the occurrence time of the target event and the indicator data. The quantitative data of the target impact can characterize the degree of impact of the target event on the target industrial chain.
[0072] In an embodiment of the present application, the server can divide the indicator data into indicator data before the occurrence time and indicator data after the occurrence time according to the occurrence time. Then, in a possible implementation manner, the server can determine the quantitative data of the target impact of the target event on the target industrial chain by calculating the degree of difference between the indicator data before the occurrence time and the indicator data after the occurrence time.
[0073] In another possible implementation, the server may calculate the change rate of individual indicator data after the target event occurs based on the indicator data before the occurrence time and the indicator data after the occurrence time, and determine the quantitative data of the target impact of the target event on the target industrial chain based on the change rate.
[0074] Step 203: Evaluate the quality of the target industrial chain based on the target impact quantification data.
[0075] After the server obtains the target impact quantification data, it can evaluate the quality of the target industrial chain based on the target impact quantification data.
[0076] In one possible implementation, the server can detect whether the target impact quantification data exceeds a preset threshold. If so, it indicates that the target industrial chain is deeply affected by the target event and its risk resistance is relatively poor. The server can determine that the quality assessment result of the target industrial chain is poor. On the contrary, if the target impact quantification data does not exceed the preset threshold, it indicates that the target industrial chain is less affected by the target event and has a stronger risk resistance. The server can determine that the quality assessment result of the target industrial chain is good.
[0077] In another possible implementation, the server may directly determine the quality assessment result of the target industry chain according to the size of the target impact quantification data, wherein the target impact quantification data is negatively correlated with the quality of the target industry chain.
[0078] In the above embodiment, by calculating the quantitative data of the target impact of the target event occurring within the preset time period corresponding to the indicator data on the target industrial chain, the quality of the target industrial chain is evaluated according to the quantitative data of the target impact. There is no need to analyze the relevant indicator information based on subjective preset weights as when evaluating the quality of the industrial chain through the grey correlation analysis method, and there is no need to continuously train and update the multidimensional pyramid model as when evaluating the quality of the industrial chain through the multidimensional pyramid model. The technical solution provided by the present application is more flexible in evaluating the quality of the industrial chain.
[0079] In one embodiment, based on Figure 2 The embodiment shown, see Figure 3 This embodiment involves a process of obtaining quantitative data of the target impact of a target event on a target industrial chain based on the occurrence time and indicator data. Figure 3 As shown, in this embodiment, step 202 includes Figure 3 Step 301 and step 302 are shown.
[0080] Step 301 , extracting features from indicator data according to occurrence time to obtain first feature data and second feature data.
[0081] In an embodiment of the present application, feature extraction can be performed on indicator data according to the occurrence time to obtain first feature data and second feature data corresponding to each indicator data, wherein the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time.
[0082] In the embodiment of the present application, the first characteristic data corresponds to the second characteristic data, but the corresponding times are different. The number can be multiple. For an indicator data, its characteristic data can be the occurrence time, region, innovation resources, talent capital, enterprise vitality, etc. In a possible implementation mode, the characteristic data can also include whether it is an experimental group. Regarding whether it is the characteristic data of the experimental group, the server can judge according to whether the time corresponding to the characteristic data is after the occurrence time. If the time is after the occurrence time, the characteristic data is the experimental group, otherwise it is not the experimental group, that is, the first characteristic data is not the experimental group, and the second characteristic data is the experimental group.
[0083] Step 302: Determine target impact quantification data based on the first feature data and the second feature data.
[0084] After obtaining the first characteristic data and the second characteristic data corresponding to each first indicator data, the server may determine the target impact quantification data according to each first characteristic data and the second characteristic item data.
[0085] Optionally, the server can determine the target impact quantitative data by calculating the quantitative difference value between each first feature data and the second feature data; optionally, the server can determine the change of each indicator data after the target event occurs based on the first feature data and the second feature data, thereby determining the target impact quantitative data.
[0086] In the above embodiment, feature extraction is performed on the indicator data according to the occurrence time to obtain first feature data before the occurrence time and second feature data after the occurrence time, and the target impact quantification data is determined based on the first feature data and the second feature data. The determination method is simple and more flexible.
[0087] In one embodiment, based on Figure 3 The embodiment shown, see Figure 4 This embodiment relates to a process of determining target impact quantified data based on first feature data and second feature data. Figure 4 As shown, in this embodiment, step 302 includes Figure 4 Step 401 and step 402 are shown.
[0088] Step 401 : for each indicator data, determine candidate impact quantification data corresponding to the indicator data according to first feature data and second feature data corresponding to the indicator data.
[0089] In the embodiment of the present application, the candidate impact quantification data corresponds to each indicator data and is used to characterize the impact degree of the target event on each indicator data.
[0090] Regarding the calculation method of the candidate quantitative data, in a possible implementation, the server may determine the candidate impact quantitative data corresponding to the indicator data according to the difference between the second feature data and the first feature data.
[0091] In another possible implementation, the server may substitute the first feature data and the second feature data into the double difference model respectively to obtain first influence quantification data corresponding to the first feature data and second influence quantification data corresponding to the second feature data, and then obtain first significance quantification data corresponding to the first influence quantification data based on the first influence quantification data, and obtain second significance quantification data corresponding to the second influence quantification data based on the second influence quantification data, and finally obtain candidate influence quantification data based on the difference between the first significance quantification data and the second significance quantification data.
[0092] Among them, the double difference model can estimate the net impact of the target event on the target industrial chain by comparing the changes in data affected by the target event (second characteristic data) and data not affected or less affected by the target event (second characteristic data) before and after the target event.
[0093] In the embodiment of the present application, the formula corresponding to the double difference model can refer to formula (1):
[0094] Y it =α+δD i +λT t +β(D i ×T t )+εi t (1)
[0095] Among them, Y it is the degree of influence, Di can be the first characteristic data or the second characteristic data, T t To characterize D i Whether the corresponding time is after the event occurs, if so, it is 1, if not, it is 0, δ, λ and β are the coefficients before each term, ε it is a random error term.
[0096] Substituting the first characteristic data and the second characteristic data into formula (1) respectively, the first influence quantization data corresponding to the first characteristic data and the second influence quantization data corresponding to the second characteristic data can be obtained.
[0097] After obtaining the first influence quantification data and the second influence quantification data corresponding to each indicator data, the server can obtain the first significance quantification data corresponding to the first influence quantification data and the second significance quantification data corresponding to the second influence quantification data according to a conventional significance statistical method.
[0098] After obtaining the first significance quantification data and the second significance quantification data corresponding to the indicator data, the server can subtract the first significance quantification data from the second significance quantification data, and obtain the absolute value of the difference, and determine the absolute value, that is, the candidate influence quantification data corresponding to the indicator data. It can be understood that the larger the candidate influence quantification data, the greater the influence received by the indicator data.
[0099] In this way, the first characteristic data and the second characteristic data are analyzed by the double difference model, and the analysis process is simple.
[0100] Step 402: determining target impact quantification data according to each candidate impact quantification data.
[0101] Through the above embodiment, the server obtains the candidate impact quantification data corresponding to each indicator data. In a possible implementation, the server may calculate the average value of each candidate impact quantification data and use the average value as the target impact quantification data.
[0102] In another possible implementation, the server may determine the largest candidate impact quantification data among the candidate impact quantification data as the target impact quantification data. In this way, by focusing on the indicator data with the largest target impact quantification data, the analysis process can be simplified while maintaining sensitivity to overall changes.
[0103] In the above embodiment, candidate impact quantification data is first determined for each indicator data, and then target impact quantification data is determined based on each candidate quantification data. The determination process is more detailed, so that the target impact quantification data finally determined is more accurate.
[0104] In one embodiment, a method for evaluating the quality of an industrial chain is provided, for use in a server, such as Figure 5 As shown, the method comprises the following steps:
[0105] Step 501, obtaining a plurality of initial indicator data.
[0106] Step 502: pre-process each initial indicator data to obtain each indicator data.
[0107] The preprocessing includes at least a consistency processing, and the consistency processing is used to adjust the indicator directionality of each initial indicator data to be consistent.
[0108] Step 503: Obtain the occurrence time of the target event corresponding to the target industrial chain.
[0109] The occurrence time is within a preset time period.
[0110] Step 504 , extracting features from the indicator data according to the occurrence time to obtain first feature data and second feature data.
[0111] The time corresponding to the first characteristic data is before the occurrence time, and the time corresponding to the second characteristic data is after the occurrence time.
[0112] Step 505 , for each indicator data, the first characteristic data and the second characteristic data are respectively substituted into the double difference method model to obtain the first influence quantification data corresponding to the first characteristic data and the second influence quantification data corresponding to the second characteristic data.
[0113] Step 506: acquiring first significance quantification data corresponding to the first influence quantification data according to the first influence quantification data, and acquiring second significance quantification data corresponding to the second influence quantification data according to the second influence quantification data.
[0114] Step 507: Obtain candidate impact quantification data according to the difference between the first significance quantification data and the second significance quantification data.
[0115] Step 508: Determine the largest candidate influence quantization data among the candidate influence quantization data as the target influence quantization data.
[0116] Among them, the number of indicator data is multiple.
[0117] Step 509, determining the quality assessment result of the target industrial chain according to the size of the target impact quantification data.
[0118] Among them, the quantitative data of target impact is negatively correlated with the quality of the target industrial chain.
[0119] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0120] Based on the same inventive concept, the embodiment of the present application also provides an industrial chain quality assessment device for implementing the industrial chain quality assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more industrial chain quality assessment device embodiments provided below can refer to the limitations of the industrial chain quality assessment method above, and will not be repeated here.
[0121] In an exemplary embodiment, Figure 6 As shown, an industrial chain quality assessment device is provided, including: an acquisition module 601, an impact module 602 and an assessment module 603, wherein:
[0122] The acquisition module 601 is used to acquire the indicator data corresponding to the target industrial chain and the preset time period, and acquire the occurrence time of the target event corresponding to the target industrial chain, and the occurrence time is within the preset time period;
[0123] Impact module 602, used to obtain quantitative data of the target impact of the target event on the target industrial chain according to the occurrence time and indicator data;
[0124] The evaluation module 603 is used to evaluate the quality of the target industrial chain according to the target impact quantitative data.
[0125] In one embodiment, the impact module 602 includes:
[0126] A feature extraction unit is used to extract features from the indicator data according to the occurrence time to obtain first feature data and second feature data, wherein the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time;
[0127] The target impact determination unit is used to determine the target impact quantitative data according to the first feature data and the second feature data.
[0128] In one of the embodiments, there are multiple indicator data, and the target impact determination unit is specifically used to determine, for each indicator data, candidate impact quantification data corresponding to the indicator data according to first feature data and second feature data corresponding to the indicator data; and determine the target impact quantification data according to each candidate impact quantification data.
[0129] In one of the embodiments, the target impact determination unit is also used to substitute the first feature data and the second feature data into the double difference method model respectively to obtain first impact quantification data corresponding to the first feature data and second impact quantification data corresponding to the second feature data; obtain first significance quantification data corresponding to the first impact quantification data according to the first impact quantification data, and obtain second significance quantification data corresponding to the second impact quantification data according to the second impact quantification data; obtain candidate impact quantification data according to the difference between the first significance quantification data and the second significance quantification data.
[0130] In one of the embodiments, the target impact determination unit is further configured to determine the largest candidate impact quantization data among the candidate impact quantization data as the target impact quantization data.
[0131] In one embodiment, the evaluation module 603 includes:
[0132] The quality assessment unit is used to determine the quality assessment result of the target industrial chain according to the size of the target impact quantitative data. The target impact quantitative data is negatively correlated with the quality of the target industrial chain.
[0133] In one embodiment, the acquisition module 601 includes:
[0134] An initial acquisition unit, used to acquire multiple initial indicator data;
[0135] The preprocessing unit is used to preprocess each initial indicator data to obtain each indicator data, and the preprocessing at least includes consistency processing, and the consistency processing is used to adjust the indicator directionality of each initial indicator data to be consistent.
[0136] Each module in the above industrial chain quality assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0137] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store industrial chain quality assessment data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for assessing the quality of an industrial chain is implemented.
[0138] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0139] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0140] Obtaining indicator data corresponding to a target industrial chain and a preset time period, and obtaining an occurrence time of a target event corresponding to the target industrial chain, wherein the occurrence time is within the preset time period;
[0141] According to the occurrence time and the indicator data, obtaining quantitative data of the target impact of the target event on the target industrial chain;
[0142] Based on the target impact quantitative data, the quality of the target industrial chain is evaluated.
[0143] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0144] Extracting features from the indicator data according to the occurrence time to obtain first feature data and second feature data, wherein the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time;
[0145] The target impact quantification data is determined according to the first feature data and the second feature data.
[0146] In one embodiment, the number of the indicator data is multiple, and the processor further implements the following steps when executing the computer program:
[0147] For each indicator data, determining candidate impact quantification data corresponding to the indicator data according to the first feature data and the second feature data corresponding to the indicator data;
[0148] The target impact quantification data is determined according to each of the candidate impact quantification data.
[0149] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0150] Substituting the first feature data and the second feature data into a double difference method model respectively, to obtain first influence quantification data corresponding to the first feature data and second influence quantification data corresponding to the second feature data;
[0151] Acquire first significance quantitative data corresponding to the first influence quantification data according to the first influence quantification data, and acquire second significance quantitative data corresponding to the second influence quantification data according to the second influence quantification data;
[0152] The candidate impact quantification data is obtained according to a difference between the first significance quantification data and the second significance quantification data.
[0153] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0154] The largest candidate influence quantization data among the candidate influence quantization data is determined as the target influence quantization data.
[0155] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0156] The quality assessment result of the target industrial chain is determined according to the size of the target impact quantification data, and the target impact quantification data is negatively correlated with the quality of the target industrial chain.
[0157] In one embodiment, the number of the indicator data is multiple, and the processor further implements the following steps when executing the computer program:
[0158] Obtain multiple initial indicator data;
[0159] Preprocessing is performed on each of the initial indicator data to obtain each of the indicator data, wherein the preprocessing at least includes a consistency process, and the consistency process is used to adjust the indicator directionality of each of the initial indicator data to be consistent.
[0160] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0161] Obtaining indicator data corresponding to a target industrial chain and a preset time period, and obtaining an occurrence time of a target event corresponding to the target industrial chain, wherein the occurrence time is within the preset time period;
[0162] According to the occurrence time and the indicator data, obtaining quantitative data of the target impact of the target event on the target industrial chain;
[0163] Based on the target impact quantitative data, the quality of the target industrial chain is evaluated.
[0164] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0165] Extracting features from the indicator data according to the occurrence time to obtain first feature data and second feature data, wherein the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time;
[0166] The target impact quantification data is determined according to the first feature data and the second feature data.
[0167] In one embodiment, the number of the indicator data is multiple, and when the computer program is executed by the processor, the following steps are also implemented:
[0168] For each indicator data, determining candidate impact quantification data corresponding to the indicator data according to the first feature data and the second feature data corresponding to the indicator data;
[0169] The target impact quantification data is determined according to each of the candidate impact quantification data.
[0170] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0171] Substituting the first feature data and the second feature data into a double difference method model respectively, to obtain first influence quantification data corresponding to the first feature data and second influence quantification data corresponding to the second feature data;
[0172] Acquire first significance quantitative data corresponding to the first influence quantification data according to the first influence quantification data, and acquire second significance quantitative data corresponding to the second influence quantification data according to the second influence quantification data;
[0173] The candidate impact quantification data is obtained according to a difference between the first significance quantification data and the second significance quantification data.
[0174] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0175] The largest candidate influence quantization data among the candidate influence quantization data is determined as the target influence quantization data.
[0176] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0177] The quality assessment result of the target industrial chain is determined according to the size of the target impact quantification data, and the target impact quantification data is negatively correlated with the quality of the target industrial chain.
[0178] In one embodiment, the number of the indicator data is multiple, and when the computer program is executed by the processor, the following steps are also implemented:
[0179] Obtain multiple initial indicator data;
[0180] Preprocessing is performed on each of the initial indicator data to obtain each of the indicator data, wherein the preprocessing at least includes a consistency process, and the consistency process is used to adjust the indicator directionality of each of the initial indicator data to be consistent.
[0181] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0182] Obtaining indicator data corresponding to a target industrial chain and a preset time period, and obtaining an occurrence time of a target event corresponding to the target industrial chain, wherein the occurrence time is within the preset time period;
[0183] According to the occurrence time and the indicator data, obtaining quantitative data of the target impact of the target event on the target industrial chain;
[0184] Based on the target impact quantitative data, the quality of the target industrial chain is evaluated.
[0185] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0186] Extracting features from the indicator data according to the occurrence time to obtain first feature data and second feature data, wherein the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time;
[0187] The target impact quantification data is determined according to the first feature data and the second feature data.
[0188] In one embodiment, the number of the indicator data is multiple, and when the computer program is executed by the processor, the following steps are also implemented:
[0189] For each indicator data, determining candidate impact quantification data corresponding to the indicator data according to the first feature data and the second feature data corresponding to the indicator data;
[0190] The target impact quantification data is determined according to each of the candidate impact quantification data.
[0191] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0192] Substituting the first feature data and the second feature data into a double difference method model respectively, to obtain first influence quantification data corresponding to the first feature data and second influence quantification data corresponding to the second feature data;
[0193] Acquire first significance quantitative data corresponding to the first influence quantification data according to the first influence quantification data, and acquire second significance quantitative data corresponding to the second influence quantification data according to the second influence quantification data;
[0194] The candidate impact quantification data is obtained according to a difference between the first significance quantification data and the second significance quantification data.
[0195] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0196] The largest candidate influence quantization data among the candidate influence quantization data is determined as the target influence quantization data.
[0197] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0198] The quality assessment result of the target industrial chain is determined according to the size of the target impact quantification data, and the target impact quantification data is negatively correlated with the quality of the target industrial chain.
[0199] In one embodiment, the number of the indicator data is multiple, and when the computer program is executed by the processor, the following steps are also implemented:
[0200] Obtain multiple initial indicator data;
[0201] Preprocessing is performed on each of the initial indicator data to obtain each of the indicator data, wherein the preprocessing at least includes a consistency process, and the consistency process is used to adjust the indicator directionality of each of the initial indicator data to be consistent.
[0202] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0203] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0204] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0205] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for evaluating the quality of an industrial chain, characterized in that: The method comprises: Obtaining indicator data corresponding to a target industrial chain and a preset time period, and obtaining an occurrence time of a target event corresponding to the target industrial chain, wherein the occurrence time is within the preset time period; According to the occurrence time and the indicator data, obtaining quantitative data of the target impact of the target event on the target industrial chain; Based on the target impact quantitative data, the quality of the target industrial chain is evaluated.
2. The method according to claim 1, characterized in that The step of obtaining quantitative data of the target impact of the target event on the target industrial chain according to the occurrence time and the indicator data includes: Extracting features from the indicator data according to the occurrence time to obtain first feature data and second feature data, wherein the time corresponding to the first feature data is before the occurrence time, and the time corresponding to the second feature data is after the occurrence time; The target impact quantification data is determined according to the first feature data and the second feature data.
3. The method according to claim 2, characterized in that The number of the indicator data is multiple, and the determining the target impact quantitative data according to the first feature data and the second feature data includes: For each indicator data, determining candidate impact quantification data corresponding to the indicator data according to the first feature data and the second feature data corresponding to the indicator data; The target impact quantification data is determined according to each of the candidate impact quantification data.
4. The method according to claim 3, characterized in that: The determining, according to the first feature data and the second feature data corresponding to the indicator data, candidate impact quantification data corresponding to the indicator data includes: Substituting the first feature data and the second feature data into a double difference method model respectively, to obtain first influence quantification data corresponding to the first feature data and second influence quantification data corresponding to the second feature data; Acquire first significance quantitative data corresponding to the first influence quantification data according to the first influence quantification data, and acquire second significance quantitative data corresponding to the second influence quantification data according to the second influence quantification data; The candidate impact quantification data is obtained according to a difference between the first significance quantification data and the second significance quantification data.
5. The method according to claim 3, characterized in that: The step of determining the target impact quantified data according to each of the candidate impact quantified data comprises: The largest candidate influence quantization data among the candidate influence quantization data is determined as the target influence quantization data.
6. The method according to claim 1, characterized in that The quality of the target industrial chain is evaluated based on the target impact quantitative data, including: The quality assessment result of the target industrial chain is determined according to the size of the target impact quantification data, and the target impact quantification data is negatively correlated with the quality of the target industrial chain.
7. The method according to claim 1, characterized in that The number of the indicator data is multiple, and the obtaining of the indicator data corresponding to the target industrial chain and the preset time period includes: Obtain multiple initial indicator data; Preprocessing is performed on each of the initial indicator data to obtain each of the indicator data, wherein the preprocessing at least includes a consistency process, and the consistency process is used to adjust the indicator directionality of each of the initial indicator data to be consistent.
8. An industrial chain quality assessment device, characterized in that: The device comprises: An acquisition module, used to acquire the indicator data corresponding to the target industrial chain and the preset time period, and acquire the occurrence time of the target event corresponding to the target industrial chain, wherein the occurrence time is within the preset time period; An impact module, used to obtain quantitative data of the target impact of the target event on the target industrial chain according to the occurrence time and the indicator data; An evaluation module is used to evaluate the quality of the target industrial chain based on the target impact quantification data.
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 steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
