Supply chain maturity evaluation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a supply chain maturity evaluation method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a transport capacity resource data set corresponding to a target supply chain; performing feature extraction on the transport capacity resource data set, and analyzing the transport capacity resource data set to obtain transport information key items with a nonlinear relationship; obtaining a reference value corresponding to each transport information key item based on the transport capacity resource data set; inputting the reference value of each transportation information key item into a preset evaluation model to obtain an evaluation result corresponding to each transportation information key item; and obtaining a maturity evaluation result of the target supply chain based on the evaluation result corresponding to each transportation information key item. By adopting the method, the accuracy of evaluating the maturity of the supply chain can be improved.

Description

Technical Field

[0001] The present application relates to the field of supply chain transportation technology, and in particular to a supply chain maturity assessment method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of logistics technology, the supply chain may become more complex, and the competitiveness between enterprises is gradually increasing. In order to improve the management of transportation resources in the supply chain, enterprises can analyze the transportation resources in the supply chain to understand the advantages and disadvantages of transportation resources in the supply chain. However, the current data volume of transportation resources in the supply chain is large, and the analysis of transportation resources often relies on subjective judgment and qualitative analysis, which will lead to low reliability and inaccuracy in the analysis of transportation resources in the supply chain. Summary of the invention

[0003] Based on this, it is necessary to provide a supply chain maturity assessment method, apparatus, computer equipment, computer-readable storage medium and computer program product that can efficiently and accurately assess the maturity of the supply chain in response to the above technical problems.

[0004] In a first aspect, the present application provides a supply chain maturity assessment method, comprising:

[0005] Obtain the transportation resource dataset corresponding to the target supply chain;

[0006] Extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information having nonlinear relationships;

[0007] Obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set;

[0008] Input the scores of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information;

[0009] Based on the evaluation results corresponding to the key items of the transportation information, a maturity evaluation result of the target supply chain is obtained.

[0010] In one embodiment, the step of extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information having nonlinear relationships includes:

[0011] Performing feature extraction on the transport resource data set to obtain a feature value corresponding to the transport resource data set and a feature vector corresponding to the feature value;

[0012] The key item of the transportation information is obtained based on the feature vector corresponding to the feature value that meets the first preset condition.

[0013] In one embodiment, the step of extracting features from the transport resource dataset includes:

[0014] Converting the transport resource data set into a transport resource matrix;

[0015] Obtaining a covariance matrix corresponding to the transport resource matrix;

[0016] Perform eigendecomposition on the covariance matrix to obtain eigenvalues ​​corresponding to the transportation resource data set and eigenvectors corresponding to the eigenvalues.

[0017] In one embodiment, the step of obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set includes:

[0018] Based on each data group in the transport resource data set and the key item of transport information, obtaining a value of each data group corresponding to the key item of transport information;

[0019] Based on the value of each data group corresponding to the key item of transportation information, a reference value of the key item of transportation information is obtained.

[0020] In one embodiment, the step of obtaining the maturity evaluation result of the target supply chain based on the evaluation results corresponding to each of the key items of the transportation information includes:

[0021] Obtaining a target evaluation result greater than a preset threshold from the evaluation results corresponding to the key items of the transportation information;

[0022] Obtaining the quantitative ratio of the target evaluation results to the evaluation results corresponding to the key items of the transportation information;

[0023] If the quantity ratio meets the second preset condition, the maturity assessment result is determined to be mature.

[0024] In one embodiment, the method further comprises:

[0025] Obtain model training data set;

[0026] The model training data set is divided into a training set and a test set, and the parameters of the random forest model are initialized;

[0027] Optimizing the parameters of the random forest model based on the training set training to obtain a random forest model to be confirmed;

[0028] Evaluate the performance of the random forest model to be confirmed based on the test set;

[0029] When the performance of the random forest model to be confirmed meets the preset standard, the random forest model to be confirmed is confirmed as the preset evaluation model.

[0030] In a second aspect, the present application also provides a supply chain maturity assessment device, comprising:

[0031] An acquisition module is used to obtain a transportation resource dataset corresponding to a target supply chain;

[0032] An analysis module, used to extract features from the transport resource data set, analyze the transport resource data set, and obtain key items of transport information with nonlinear relationships;

[0033] A quantitative module, used for obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set;

[0034] An evaluation module, used to input the reference values ​​of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information;

[0035] The confirmation module is used to obtain the maturity evaluation result of the target supply chain based on the evaluation results corresponding to each key item of the transportation information.

[0036] 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 following steps are implemented:

[0037] Obtain the transportation resource dataset corresponding to the target supply chain;

[0038] Extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information having nonlinear relationships;

[0039] Obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set;

[0040] Inputting the reference values ​​of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information;

[0041] Based on the evaluation results corresponding to each of the key items of the transportation information, a maturity evaluation result of the target supply chain is obtained.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtain the transportation resource dataset corresponding to the target supply chain;

[0044] Extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information having nonlinear relationships;

[0045] Obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set;

[0046] Inputting the reference values ​​of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information;

[0047] Based on the evaluation results corresponding to each of the key items of the transportation information, a maturity evaluation result of the target supply chain is obtained.

[0048] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0049] Obtain the transportation resource dataset corresponding to the target supply chain;

[0050] Extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information having nonlinear relationships;

[0051] Obtaining reference values ​​corresponding to each key item of the transportation information based on the transportation resource data set;

[0052] Inputting the reference values ​​of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information;

[0053] Based on the evaluation results corresponding to each of the key items of the transportation information, a maturity evaluation result of the target supply chain is obtained.

[0054] The above-mentioned supply chain maturity assessment method, device, computer equipment, computer-readable storage medium and computer program product obtain the capacity resource data set corresponding to the target supply chain, extract features from the capacity resource data set, analyze the capacity resource data set, and obtain key items of transportation information with nonlinear relationships. In this way, the capacity resource data set can be represented based on a small amount of data to reduce the amount of calculation for assessment. Then, reference values ​​corresponding to each key item of transportation information are obtained based on the capacity resource data set, and the reference values ​​of each key item of transportation information are respectively input into a preset assessment model to obtain assessment results corresponding to each key item of transportation information. In this way, the effect of each key item of transportation information on the maturity of the target supply chain can be quantified, so that the maturity assessment result of the target supply chain can be obtained based on the assessment results corresponding to each key item of transportation information, and then the maturity of the target supply chain can be accurately and efficiently assessed. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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.

[0056] FIG1 is a schematic diagram of a flow chart of a method for evaluating the maturity of a supply chain in one embodiment;

[0057] FIG2 is a schematic flow chart of steps for obtaining key items of transportation information in one embodiment;

[0058] FIG3 is a schematic diagram of a flow chart of a feature extraction step in one embodiment;

[0059] FIG4 is a schematic diagram of the overall situation of transport resource analysis in one embodiment;

[0060] FIG5 is a schematic diagram of internal transport capacity for transport resource analysis in one embodiment;

[0061] FIG6 is a schematic diagram of external transport capacity for transport resource analysis in one embodiment;

[0062] FIG7 is a structural block diagram of a supply chain maturity assessment device in one embodiment;

[0063] FIG8 is a diagram showing the internal structure of a computer device in one embodiment;

[0064] FIG. 9 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0065] 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.

[0066] The maturity assessment method of the supply chain provided in the embodiment of the present application can be applied to a terminal or a server. If applied to a server, the data storage system can store the data that the server needs to process. The data storage system can be integrated on the server, or it can be placed on the cloud or other network servers. The server can obtain the capacity resource data set corresponding to the target supply chain, perform feature extraction on the capacity resource data set, analyze the capacity resource data set, and obtain key items of transportation information with nonlinear relationships; obtain reference values ​​corresponding to each key item of transportation information based on the capacity resource data set; input the reference values ​​of each key item of transportation information into the preset assessment model to obtain the assessment results corresponding to each key item of transportation information; based on the assessment results corresponding to each key item of transportation information, obtain the maturity assessment result of the target supply chain. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0067] In an exemplary embodiment, as shown in FIG1 , a supply chain maturity assessment method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, 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. In this embodiment, the method includes the following steps:

[0068] Step 102: Acquire a transportation resource dataset corresponding to the target supply chain.

[0069] Among them, the transportation resource data set refers to the collection of relevant transportation data for transportation in the target supply chain. The transportation resource data set includes multiple data items. Each data item can represent a type of data related to transportation data. The transportation resource data set may include at least the following data: transportation cost data, transportation time data, punctuality data, cargo damage rate data, and loading rate data. Among them, the transportation cost data is used to record the cost information under different transportation modes or routes. The transportation time data is used to record the time required to transport goods from the starting point to the end point. The punctuality rate data is used to record the frequency of on-time arrival during the transportation of goods. The cargo damage rate data is used to record the proportion of cargo damage during transportation. The loading rate data is used to record the efficiency of the transportation tool in loading goods.

[0070] Optionally / exemplarily, the transportation resource dataset corresponding to the target supply chain may be obtained from an organization associated with the target supply chain, for example, from an internal enterprise system, a third-party logistics company, or a public data source.

[0071] Step 104 , extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information with nonlinear relationships.

[0072] Among them, the key items of transportation information are used to characterize the important features of the capacity resource data set. Optionally, the number of key items of transportation information is less than the number of types of data items in the capacity resource data set. When the number of key items of transportation information obtained based on the capacity resource data set is more than one, there is a nonlinear relationship between the key items of transportation information. In this way, the capacity resource data set can be simplified, while retaining the original information of the capacity resource data set, reducing the possibility of inaccurate evaluation due to lost data. Key items of transportation information may include, for example, transportation cost and transportation time.

[0073] Exemplarily, in order to obtain the key items of transportation information corresponding to the capacity resource data set, the principal component analysis method can be used to extract features from the data in the capacity resource data set to analyze the capacity resource data set. Using the principal component analysis method, the possibly related data items in the capacity resource data set can be converted into a set of linearly unrelated key items of transportation information through orthogonal transformation. Specifically, the capacity resource data set is processed using the principal component analysis method to obtain the principal components that can characterize the capacity resource data set. The principal component corresponds to the key item of transportation information. And each principal component is a linear combination of the original data items. In this way, the data dimension can be simplified and the important features of the capacity resource data set can be extracted. Moreover, since the principal components are linear combinations of the original data items, these principal components are able to retain the data information of the capacity resource data set.

[0074] Optionally, in order to obtain the key items of transportation information corresponding to the transportation resource data set, methods such as isometric mapping method, kernel principal component analysis method, and local linear embedding method can also be used.

[0075] Step 106: Obtain reference values ​​corresponding to each key item of transportation information based on the transportation resource data set.

[0076] In addition to obtaining key items of transportation information, it is also necessary to obtain reference values ​​corresponding to the key items of transportation information so that the maturity of the target supply chain can be evaluated based on quantitative indicators.

[0077] Exemplarily, the principal component analysis method is used to determine the reference value corresponding to the key item of transportation information based on the score of the principal component. The score of the principal component represents the projection of the original data on the principal component. The score of each principal component is a coordinate value of the original data point (a data group corresponding to a set of data items) in the new coordinate system. That is, the score of the principal component is the score of the linear combination of the original data in the direction of a specific principal component. Therefore, each key item of transportation information can be a linear combination of the original data items.

[0078] Optionally, if local linear embedding (LLE) is used to obtain the key items of transportation information, the reference values ​​of the key items of transportation information may be LLE embeddings or LLE coordinates.

[0079] That is to say, the capacity resource data set can be composed of multiple data groups, each of which records the values ​​corresponding to each data item. The projection value corresponding to the key item of transportation information of each data group is obtained. The projection values ​​corresponding to all data groups constitute the reference values ​​corresponding to the key item of transportation information.

[0080] Step 108: inputting the reference values ​​corresponding to the key items of transportation information into the preset evaluation model to obtain the evaluation results corresponding to the key items of transportation information.

[0081] Among them, the evaluation result corresponding to the key item of transportation information may refer to the ability level of the key item of transportation information in meeting the transportation demand for the target supply chain. For example, if the evaluation result corresponding to the transportation time is 80%, it can be said that the target supply chain has an advantage in the evaluation indicator of transportation time, which has a positive effect on the maturity of the target supply chain. The preset evaluation model analyzes the reference value corresponding to the key item of transportation information to obtain the maturity of the key item of transportation information, so as to facilitate the maturity of the target supply chain based on the maturity of each key item of transportation information. The evaluation result can be a level or a numerical value.

[0082] Exemplarily, the preset evaluation model may be a random forest model. After obtaining the reference values ​​corresponding to the key items of transportation information, each reference value may be input into the random forest model to obtain the evaluation results corresponding to the key items of transportation information. The random forest model may analyze the reference values ​​corresponding to the key items of transportation information to predict the evaluation results corresponding to the key items of transportation information.

[0083] Optionally, the preset evaluation model may also be other machine learning models, which learn the relationship between the input reference value and the predicted evaluation result during training, so as to be able to predict the corresponding evaluation result based on the reference value in the future.

[0084] Step 110, based on the evaluation results corresponding to each key item of transportation information, obtain the maturity evaluation result of the target supply chain.

[0085] Since the key items of transportation information are important features that can characterize the transportation resource data set, the maturity evaluation results of the target supply chain can be obtained based on the evaluation results corresponding to the important features. For example, the maturity evaluation results of the target supply chain can be obtained based on the evaluation results of transportation time and transportation cost.

[0086] Exemplarily, obtaining the maturity evaluation result of the target supply chain based on the evaluation results corresponding to each key item of transportation information may include: determining whether the evaluation results corresponding to each key item of transportation information meet the preset conditions. If the evaluation results corresponding to each key item of transportation information meet the preset conditions, the maturity evaluation result of the target supply chain may be determined to be mature.

[0087] Optionally, obtaining the maturity evaluation result of the target supply chain based on the evaluation results corresponding to each key item of transportation information may further include: sorting the evaluation results corresponding to each key item of transportation information, and determining whether the first k evaluation results in the sorted results meet a preset condition (for example, greater than a preset threshold). If the first k evaluation results meet the preset condition, the maturity evaluation result of the target supply chain is determined to be mature.

[0088] Optionally, the obtained maturity assessment result can be a numerical value or a grade (such as high grade, medium grade, low grade). If the numerical value is greater than a preset threshold, or the grade is high, the maturity assessment result of the target supply chain can be determined to be mature.

[0089] In the above-mentioned supply chain maturity assessment method, by obtaining the capacity resource data set corresponding to the target supply chain, feature extraction is performed on the capacity resource data set, and the capacity resource data set is analyzed to obtain key items of transportation information with nonlinear relationships. In this way, the capacity resource data set can be represented based on a small amount of data to reduce the amount of calculation for assessment. Then, reference values ​​corresponding to each key item of transportation information are obtained based on the capacity resource data set, and the reference values ​​of each key item of transportation information are respectively input into the preset assessment model to obtain assessment results corresponding to each key item of transportation information. In this way, the effect of each key item of transportation information on the maturity of the target supply chain can be quantified, so that the maturity assessment result of the target supply chain can be obtained based on the assessment results corresponding to each key item of transportation information, and then the maturity of the target supply chain can be accurately and efficiently assessed.

[0090] The purpose of extracting features from the transport resource dataset is to extract important features that can characterize the original data of the transport resource dataset. In some embodiments, some machine learning models can be used to extract features from the transport resource dataset. In other embodiments, since the transport resource dataset is composed of some data groups, statistical methods can be used to process the transport resource dataset to obtain important features. As shown in FIG2 , extracting features from the transport resource dataset, analyzing the transport resource dataset, and obtaining key items of transportation information with nonlinear relationships include steps 202 to 204. Among them:

[0091] Step 202: extract features from the transport resource data set to obtain feature values ​​corresponding to the transport resource data set and feature vectors corresponding to the feature values.

[0092] Step 204 , obtaining key items of transportation information based on feature vectors corresponding to feature values ​​that meet the first preset condition.

[0093] Exemplarily, by extracting features from the transport resource data set based on a statistical method, a feature value corresponding to the transport resource data set and a feature vector corresponding to the feature value can be obtained. The number of feature values ​​can be multiple. When the feature value satisfies a first preset condition (for example, greater than a preset threshold), the key item of transportation information can be determined based on the feature vector corresponding to the feature value. For example, the feature vector is determined as the key item of transportation information.

[0094] Optionally, if the statistical method is principal component analysis, obtaining the key items of transportation information based on the eigenvectors corresponding to the eigenvalues ​​that meet the first preset condition includes: arranging a group of eigenvalues ​​from large to small, selecting the eigenvectors corresponding to the first k largest eigenvalues ​​as principal components (i.e., key items of transportation information), and obtaining a group of principal components. Wherein, k is a preset constant.

[0095] In this embodiment, by performing feature extraction on the capacity resource data set, the eigenvalue corresponding to the capacity resource data set and the eigenvector corresponding to the eigenvalue are obtained. In this way, the key items of transportation information can be obtained based on statistical methods, reducing the complexity of obtaining the key items of transportation information. The key items of transportation information are then screened out based on the eigenvalues ​​that meet the first preset conditions, which can reduce the complexity of evaluating the maturity of the model. By evaluating the maturity of the model through the key items of transportation information that are highly correlated with the capacity resource data set, the accuracy of the evaluation can be guaranteed while improving the efficiency of the evaluation.

[0096] In some embodiments, as shown in FIG3 , the step of extracting features from the transport resource data set includes steps 302 to 306.

[0097] Step 302: Convert the transport capacity resource data set into a transport capacity resource matrix.

[0098] Step 304: Obtain the covariance matrix corresponding to the transport resource matrix.

[0099] Step 306: perform eigendecomposition on the covariance matrix to obtain eigenvalues ​​corresponding to the transport resource data set and eigenvectors corresponding to the eigenvalues.

[0100] The capacity resource matrix is ​​obtained by converting the data representation of the capacity resource data set into a matrix. That is, the capacity resources in the matrix and the capacity resource data set are the same, but the representation is different.

[0101] Exemplarily, after obtaining the capacity resource matrix, the covariance matrix corresponding to the capacity resource matrix is ​​obtained. After eigendecomposition is performed on the covariance matrix, the eigenvalues ​​corresponding to the covariance matrix and the eigenvectors corresponding to each eigenvalue are obtained, and the eigenvalues ​​that meet the preset conditions (for example, the first k are selected in order from large to small) are screened out, so that the eigenvectors corresponding to the capacity resource data set can be obtained based on the eigenvectors corresponding to the screened eigenvalues, and then the key items of transportation information are obtained.

[0102] In this embodiment, the covariance matrix of the transportation resource data set is obtained, the covariance matrix is ​​eigendecomposed, the obtained eigenvalues ​​are screened, and the key items of transportation information are obtained based on the eigenvectors corresponding to the screened eigenvalues. This can simplify the process of obtaining the key items of transportation information and ensure the accuracy of the key items of transportation information.

[0103] In some embodiments, in order to obtain the reference values ​​corresponding to each key item of transportation information based on the capacity resource data, first, based on each data group and key item of transportation information in the capacity resource data set, the value of each data group corresponding to the key item of transportation information can be obtained, and then based on the value of each data group corresponding to the key item of transportation information, the reference value of the key item of transportation information can be obtained.

[0104] As mentioned above, it is necessary to obtain the reference values ​​corresponding to the key items of transportation information so as to be able to evaluate the maturity of the target supply chain based on quantitative indicators. After obtaining the key items of transportation information, it is necessary to obtain the projection values ​​of the key items of transportation information based on the transportation resource data set to obtain the reference values ​​corresponding to the key items of transportation information.

[0105] Exemplarily, each data group in the transport resource data set is weighted with the key item of transport information to obtain a value corresponding to each data group, and then the values ​​corresponding to each data group are combined to obtain a reference value corresponding to the key item of transport information. That is, the reference value includes multiple values ​​and is composed of multiple values. The reference value can be a vector or array composed of multiple values.

[0106] In this embodiment, based on each data group and key items of transportation information in the capacity resource data set, a reference value of each data group corresponding to the key items of transportation information is obtained, and then based on the numerical value of each data group corresponding to the key items of transportation information, the reference value of the key items of transportation information is obtained. In this way, the projection value of the entire capacity resource data set corresponding to the key items of transportation information can be obtained. In this way, the reference value of the key items of transportation information can retain the information of the entire capacity resource data set, thereby improving the reliability of the maturity assessment results of the target supply chain obtained based on the reference value.

[0107] In some embodiments, a maturity assessment result of the target supply chain is obtained based on the assessment results corresponding to each key item of transportation information, including: obtaining a target assessment result that meets preset conditions from the assessment results corresponding to the key items of transportation information; obtaining the quantitative ratio of the target assessment result relative to the assessment results corresponding to the key items of transportation information; if the quantitative ratio is greater than a preset threshold, the maturity assessment result is determined to be mature.

[0108] Exemplarily, the evaluation result corresponding to the key item of transportation information can be a numerical value or a grade. The preset condition can be greater than or equal to a certain numerical value, or belong to a high grade, or belong to a high grade or a low grade. The preset condition is used to screen out the key items of transportation information with qualified maturity. Therefore, the target evaluation result that meets the preset condition is obtained from the evaluation results corresponding to the key items of transportation information, and the key items of transportation information with qualified maturity of the target supply chain can be screened out. If the proportion of key items of transportation information with qualified maturity is relatively large, it can be determined that the maturity evaluation result of the target supply chain is mature. Optionally, the maturity evaluation result can also be a numerical value. When the numerical value is greater than a preset target threshold, the target supply chain is mature. To determine the proportion of key items of transportation information with qualified maturity, the ratio between the number of target evaluation results and the number of key items of transportation information can be calculated, and the quantitative proportion of the target evaluation results relative to the evaluation results corresponding to the key items of transportation information can be obtained. When the quantitative proportion is greater than the preset threshold, the maturity evaluation result is mature.

[0109] In this embodiment, the target evaluation result that meets the second preset condition is obtained from the evaluation results corresponding to the key items of transportation information; the quantitative ratio of the target evaluation result to the evaluation results corresponding to the key items of transportation information is obtained; if the quantitative ratio is greater than the preset threshold, the maturity evaluation result is determined to be mature. In this way, the maturity evaluation results of the target supply chain can be characterized by quantitative data, which is convenient for the subsequent management of each supply chain. In addition, the maturity of the target supply chain can be improved by the evaluation results corresponding to the key items of transportation information, which is conducive to improving the robustness of the supply chain.

[0110] In some embodiments, the step of obtaining a preset evaluation model may include: obtaining a model training data set; dividing the model training data set into a training set and a test set, and initializing the parameters of the random forest model; optimizing the parameters of the random forest model based on the training set training to obtain a random forest model to be confirmed; evaluating the performance of the random forest model to be confirmed based on the test set; when the performance of the random forest model to be confirmed meets the preset criteria, confirming the random forest model to be confirmed as the preset evaluation model.

[0111] In this embodiment, a training capacity resource dataset is obtained, that is, a dataset for model training is selected from the cleaned and converted capacity resource dataset; the training capacity resource dataset is divided into a training set and a test set. Specifically, stratified sampling or other sampling methods can be used to divide the dataset into two parts: a training set (usually accounting for 70%-80%) and a test set (the remaining 30%-20%).

[0112] Initialize the parameters of the random forest model. Specifically, select the initial parameters of the random forest model, such as the number of decision trees, the depth of the tree, the minimum number of samples of leaf nodes, etc.; use the training set to train and optimize the parameters of the random forest model, that is, use the training set data to train the random forest model.

[0113] Optionally, perform cross-validation to optimize model parameters, using methods such as grid search (GridSearchCV) or random search (RandomizedSearchCV).

[0114] Use the test set to evaluate the performance of the random forest model to be confirmed; use the test set data to evaluate the performance of the model, and specific calculation evaluation indicators may include: accuracy, precision, recall rate, F1 score, etc.; based on the above calculation evaluation indicators, it can be judged whether the check model meets the preset performance standards; if the performance of the random forest model to be confirmed on the test set meets the preset standards, it will be confirmed as the trained random forest model.

[0115] In this embodiment, by using a random forest model that meets preset standards to predict the evaluation results corresponding to key items of transportation information, the key items of transportation information can be processed based on machine learning, thereby improving the reliability and stability of subsequent maturity evaluations.

[0116] In some embodiments, after obtaining the capacity resource data set corresponding to the target supply chain, the capacity resource data set may be preprocessed before the feature extraction is performed on the capacity resource data set. Exemplarily, a data cleaning operation is performed on the initial capacity resource data set to obtain a cleaned capacity resource data set. The data cleaning operation includes: deleting missing values, abnormal values ​​and duplicate values ​​in the initial capacity resource data set. A data conversion operation is performed on the cleaned capacity resource data set to obtain a capacity resource data set. The data conversion operation includes: performing standardization and normalization operations on the cleaned capacity resource data set. In this embodiment, the initial capacity resource data set of the target supply chain is obtained, and the data sources of the initial capacity resource data set may include internal databases and external data; the internal database includes the company's internal transportation records, logistics management system, etc.; the external data includes public industry reports, data from third-party logistics service providers, market research data, etc. Optionally, the specific method of obtaining the initial capacity resource data set can be directly extracted from the database, or collected from public websites using web crawler technology, or negotiated with partners or suppliers to obtain data. After obtaining the initial capacity resource data set, it is necessary to integrate the initial capacity resource data set, that is, integrate the data from different sources into an initial data set to ensure the consistency and integrity of the data. Perform a data cleaning operation on the initial capacity resource data set to obtain a cleaned capacity resource data set, wherein the data cleaning operation includes: deleting missing values, outliers and duplicate values ​​in the initial capacity resource data set; deleting missing values ​​in the initial capacity resource data set includes deleting completely missing records, and for partially missing data, you can choose to fill (such as using the mean, median, mode or using model prediction to fill) or delete; deleting outliers in the initial capacity resource data set includes using statistical methods to identify outliers, delete or correct outliers, depending on the nature and cause of the outliers; deleting duplicate values ​​in the initial capacity resource data set includes using the inspection function of the data set to find and delete identical duplicate records. In this embodiment, a data conversion operation is performed on the cleaned capacity resource data set to obtain a capacity resource data set, wherein the data conversion operation includes: performing standardization and normalization operations on the cleaned capacity resource data set. The standardization operation includes: using the Z-score standardization formula to perform a standardization operation on the cleaned capacity resource data set, and the standardized data has a zero mean and unit variance. The normalization operation includes: using the minimum-maximum standardization formula to perform a normalization operation on the cleaned capacity resource data set, and the normalized data will fall within the interval [0,1].

[0117] In this embodiment, by preprocessing the initial capacity resource data set, the accuracy of the data can be improved, thereby improving the accuracy and stability of subsequent maturity assessment results.

[0118] In an exemplary embodiment, in order to evaluate the maturity of the target supply chain, a transportation resource dataset corresponding to the target supply chain may be obtained. Optionally, the transportation resource dataset of the target supply chain may be obtained from an internal enterprise system, a third-party logistics company, or a public data source.

[0119] After obtaining the capacity resource data set, feature extraction can be performed on the capacity resource data set to obtain key items of transportation information with nonlinear relationships. Then, reference values ​​corresponding to each key item of transportation information are obtained based on the capacity resource data set. Exemplarily, after obtaining the capacity resource data set, the principal component analysis method can be used to process the capacity resource data set to obtain a set of principal component scores, wherein the principal component corresponding to each principal component score in a set of principal component scores corresponds to a capacity resource evaluation indicator, and the capacity resource evaluation indicators include at least: transportation cost and transportation time. The capacity resource evaluation indicators are also key items of transportation information.

[0120] When the reference values ​​corresponding to each key item of transportation information are obtained based on the capacity resource data set, the capacity resource data set can be converted into a capacity resource matrix. Obtain the covariance matrix corresponding to the capacity resource matrix; perform eigendecomposition on the covariance matrix to obtain the eigenvalues ​​corresponding to the capacity resource data set and the eigenvectors corresponding to the eigenvalues. Based on the eigenvectors corresponding to the eigenvalues ​​that meet the first preset condition, obtain the key items of transportation information; based on each data group and the key items of transportation information in the capacity resource data set, obtain the numerical value of each data group corresponding to the key items of transportation information; based on the numerical value of each data group corresponding to the key items of transportation information, obtain the reference value of the key items of transportation information. Exemplarily, calculate the covariance matrix of the capacity resource data set; perform eigendecomposition on the covariance matrix to obtain a set of eigenvalues, wherein each eigenvalue in a set of eigenvalues ​​corresponds to an eigenvector; arrange a set of eigenvalues ​​from large to small, select the eigenvectors corresponding to the first k largest eigenvalues ​​as principal components, and obtain a set of principal components, wherein k is a preset constant; multiply the capacity resource data set by each principal component in a set of principal components to obtain a set of principal component scores. The principal component score is the reference value of the key item of transportation information.

[0121] By using principal component analysis to process the transport resource dataset, high-dimensional data can be converted into low-dimensional data without losing too much information, which helps to simplify the data structure and facilitate analysis and visualization. At the same time, by reducing the dimension of the dataset, the consumption of computing resources can be reduced and the operation speed of the model can be improved.

[0122] After obtaining the reference values ​​of each key item of transportation information, the reference values ​​of each key item of transportation information are respectively input into the preset evaluation model to obtain the evaluation results corresponding to each key item of transportation information. For example, a set of principal component scores are input into the trained random forest model (i.e., the preset evaluation model) to obtain a set of principal component prediction results output by the trained random forest model, and the maturity of the transportation capacity resources of the target supply chain is evaluated based on a set of principal component prediction results. Maturity generally refers to the ability level of transportation capacity resources to meet transportation needs. The evaluation results can be quantitative scores or qualitative grades (such as high, medium, and low maturity).

[0123] After obtaining the evaluation results corresponding to each key item of transportation information, obtain the target evaluation results that meet the second preset condition from the evaluation results corresponding to the key items of transportation information; obtain the quantitative proportion of the target evaluation results relative to the evaluation results corresponding to the key items of transportation information; if the quantitative proportion is greater than the preset threshold, the maturity evaluation result is determined to be mature. For example, calculate the quantitative proportion of the principal component prediction scores greater than the preset score threshold in a group of principal component prediction scores; evaluate the maturity of the capacity resources of the target supply chain based on the quantitative proportion to obtain the capacity resource maturity score, wherein the quantitative proportion is positively correlated with the capacity resource maturity score. In this embodiment, it is necessary to determine the preset score threshold, that is, set a score threshold, which is used to determine whether the principal component prediction score meets the standard of capacity resource maturity; calculate the quantitative proportion, count the number of scores greater than the preset score threshold in all principal component prediction scores, calculate the proportion of these scores to the total number of principal component prediction scores, and convert the calculated quantitative proportion into the capacity resource maturity score; since the quantitative proportion is positively correlated with the capacity resource maturity score, a simple linear conversion can be used or a more complex conversion function can be designed according to business needs. The quantified capacity resource maturity score obtained in this embodiment can be used to evaluate the capacity resource maturity of the target supply chain. The higher the score, the higher the capacity resource maturity of the supply chain, and vice versa.

[0124] Through the above embodiments, the target supply chain's transportation resource maturity evaluation result can be determined based on a set of principal component prediction results, thereby improving the accuracy of the supply chain's transportation resource maturity evaluation. By analyzing the principal component prediction results, an improvement plan for improving the maturity of the supply chain's transportation resource can also be obtained, further improving the maturity and robustness of the supply chain.

[0125] In one embodiment, as shown in Figures 4 to 6, by analyzing the transport capacity contribution of logistics and integrating internal and external transport capacity resources, the allocation and supply of power grid materials are enabled, providing auxiliary decision-making for further improving the capacity and focus of power grid infrastructure material transportation.

[0126] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0127] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0128] 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.

[0129] Based on the same inventive concept, the embodiment of the present application also provides a supply chain maturity assessment device for implementing the supply chain maturity 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 the embodiments of one or more supply chain maturity assessment devices provided below can refer to the limitations of the supply chain maturity assessment method above, and will not be repeated here.

[0130] In an exemplary embodiment, as shown in FIG. 7 , a supply chain maturity assessment device 700 is provided, comprising: an acquisition module 701 , an analysis module 702 , a quantification module 703 , an assessment module 707 and a confirmation module 705 , wherein:

[0131] The acquisition module 701 is used to acquire the transportation resource data set corresponding to the target supply chain.

[0132] The analysis module 702 is used to extract features from the transport resource data set, analyze the transport resource data set, and obtain key items of transportation information with nonlinear relationships.

[0133] The quantitative module 703 is used to obtain reference values ​​corresponding to each key item of transportation information based on the transportation resource data set.

[0134] The evaluation module 707 is used to input the reference values ​​of each key item of transportation information into a preset evaluation model to obtain evaluation results corresponding to each key item of transportation information.

[0135] The confirmation module 705 is used to obtain the maturity evaluation result of the target supply chain based on the evaluation results corresponding to each key item of the transportation information.

[0136] In some embodiments, the analysis module 702 is also used to extract features from the capacity resource data set to obtain feature values ​​corresponding to the capacity resource data set and feature vectors corresponding to the feature values; based on the feature vectors corresponding to the feature values ​​that meet the first preset conditions, key items of transportation information are obtained.

[0137] In some embodiments, the analysis module 702 is also used to convert the capacity resource data set into a capacity resource matrix; obtain the covariance matrix corresponding to the capacity resource matrix; and perform eigendecomposition on the covariance matrix to obtain the eigenvalues ​​corresponding to the capacity resource data set and the eigenvectors corresponding to the eigenvalues.

[0138] In some embodiments, the quantification module 703 is also used to obtain a reference value of each data group corresponding to the key item of transportation information based on each data group and key item of transportation information in the capacity resource data set; and obtain a reference value of the key item of transportation information based on the numerical value of each data group corresponding to the key item of transportation information.

[0139] In some embodiments, the confirmation module 705 is also used to obtain a target evaluation result that meets a second preset condition from the evaluation results corresponding to the key items of transportation information; obtain the quantitative proportion of the target evaluation results corresponding to the evaluation results corresponding to the key items of transportation information; if the quantitative proportion is greater than a preset threshold, the maturity evaluation result is determined to be mature.

[0140] In some embodiments, the supply chain maturity assessment device 700 further includes a training device. The training device is used to obtain a model training data set; divide the model training data set into a training set and a test set, and initialize the parameters of the random forest model; optimize the parameters of the random forest model based on the training set training to obtain a random forest model to be confirmed; evaluate the performance of the random forest model to be confirmed based on the test set; when the performance of the random forest model to be confirmed meets the preset standard, confirm the random forest model to be confirmed as a preset assessment model.

[0141] Each module in the supply chain maturity 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.

[0142] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG8. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. 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 data such as a preset evaluation model, a first preset condition, a second preset condition, and a preset threshold. 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 maturity assessment method for a supply chain is implemented.

[0143] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. 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 in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a supply chain maturity assessment method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0144] Those skilled in the art will understand that the structure shown in FIG. 8 or FIG. 9 is merely a block diagram of a partial 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 shown in the figure, or combine certain components, or have a different arrangement of components.

[0145] 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 the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0146] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 supply chain maturity assessment method, characterized in that: The method comprises: Obtain the transportation resource dataset corresponding to the target supply chain; Extracting features from the transport resource data set, analyzing the transport resource data set, and obtaining key items of transport information having nonlinear relationships; Obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set; Inputting the reference values ​​of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information; Based on the evaluation results corresponding to each of the key items of the transportation information, a maturity evaluation result of the target supply chain is obtained.

2. The method according to claim 1, characterized in that The feature extraction of the transport resource data set and the analysis of the transport resource data set to obtain key items of transport information with nonlinear relationships include: Performing feature extraction on the transport resource data set to obtain a feature value corresponding to the transport resource data set and a feature vector corresponding to the feature value; The key item of the transportation information is obtained based on the feature vector corresponding to the feature value that meets the first preset condition.

3. The method according to claim 2, characterized in that The extracting features from the transport resource data set includes: Converting the transport resource data set into a transport resource matrix; Obtaining a covariance matrix corresponding to the transport resource matrix; Perform eigendecomposition on the covariance matrix to obtain eigenvalues ​​corresponding to the transportation resource data set and eigenvectors corresponding to the eigenvalues.

4. The method according to claim 2, characterized in that: The obtaining of reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set includes: Based on each data group in the transport resource data set and the key item of transport information, obtaining a value of each data group corresponding to the key item of transport information; Based on the value of each data group corresponding to the key item of transportation information, a reference value of the key item of transportation information is obtained.

5. The method according to claim 1, characterized in that The maturity evaluation result of the target supply chain is obtained based on the evaluation results corresponding to the key items of the transportation information, including: Obtaining a target evaluation result that meets a second preset condition from the evaluation results corresponding to the key items of the transportation information; Obtaining the quantitative ratio of the target evaluation results to the evaluation results corresponding to the key items of the transportation information; If the quantity ratio is greater than a preset threshold, the maturity assessment result is determined to be mature.

6. The method according to claim 1, characterized in that The method also includes: Obtain model training data set; The model training data set is divided into a training set and a test set, and the parameters of the random forest model are initialized; Optimizing the parameters of the random forest model based on the training set training to obtain a random forest model to be confirmed; Evaluate the performance of the random forest model to be confirmed based on the test set; When the performance of the random forest model to be confirmed meets the preset standard, the random forest model to be confirmed is confirmed as the preset evaluation model.

7. A supply chain maturity assessment device, characterized in that: The device comprises: An acquisition module is used to obtain a transportation resource dataset corresponding to a target supply chain; An analysis module, used to extract features from the transport resource data set, analyze the transport resource data set, and obtain key items of transport information with nonlinear relationships; A quantitative module, used for obtaining reference values ​​corresponding to each of the key items of the transportation information based on the transportation resource data set; An evaluation module, used to input the reference values ​​of each of the key items of the transportation information into a preset evaluation model to obtain evaluation results corresponding to each of the key items of the transportation information; The confirmation module is used to obtain the maturity evaluation result of the target supply chain based on the evaluation results corresponding to each key item of the transportation information.

8. 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 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images