Supplier performance scoring method, training method, device and equipment

Abstract

The invention relates to the technical field of performance evaluation, and provides a performance scoring method, training method, device and equipment for a supplier, and the method comprises the steps: obtaining the supply information corresponding to the supplier; performing feature extraction processing on the supply information based on a feature extraction sub-model of the performance scoring model to obtain feature information corresponding to the supplier; based on a performance prediction sub-model of the performance scoring model, determining the performance probability of the supplier according to the feature information; and determining a performance scoring result of the supplier according to the feature information and the performance probability based on an evaluation sub-model of the performance scoring model, so as to improve the performance evaluation convenience of the supplier and improve the performance evaluation effect of the supplier.

Description

Technical Field

[0001] The present application relates to the technical field of contract performance evaluation, and in particular to a supplier contract performance scoring method, training method, device and equipment. Background Art

[0002] In the related art, when conducting performance evaluation on suppliers, staff are generally required to fill in the corresponding supplier performance evaluation form at the end of each year or after the project acceptance of the supplier's performance to evaluate the supplier's performance.

[0003] However, when the performance of suppliers is evaluated manually by staff, it is easy for the performance evaluation to be delayed due to untimely performance evaluation, or for the performance evaluation to be distorted due to subjective judgment bias, thereby resulting in poor convenience and poor performance evaluation effect for suppliers. Summary of the invention

[0004] The main purpose of this application is to provide a supplier performance scoring method, training method, device and equipment, aiming to improve the convenience of supplier performance evaluation and improve the effectiveness of supplier performance evaluation.

[0005] In a first aspect, the present application provides a method for evaluating the performance of a supplier, comprising the following steps:

[0006] Get the supply information corresponding to the supplier;

[0007] Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier;

[0008] The fulfillment prediction sub-model based on the fulfillment scoring model determines the fulfillment probability of the supplier according to the characteristic information;

[0009] Based on the scoring sub-model of the performance scoring model, the performance scoring result of the supplier is determined according to the feature information and the performance probability.

[0010] In a second aspect, the present application also provides a training method for a performance scoring model, the training method comprising:

[0011] Obtaining a training sample set, wherein the training sample set includes supply information corresponding to each of a plurality of suppliers and a performance score result label corresponding to each of the suppliers;

[0012] Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier;

[0013] The fulfillment prediction sub-model based on the fulfillment scoring model determines the fulfillment probability of the supplier according to the characteristic information;

[0014] Based on the scoring sub-model of the performance scoring model, determining the performance scoring result of the supplier according to the characteristic information and the performance probability;

[0015] Determining model optimization parameters of the performance scoring model according to the performance scoring and the performance scoring result label;

[0016] According to the model optimization parameters, the model parameters of the performance scoring model are adjusted.

[0017] In a third aspect, the present application further provides a supplier's performance scoring device, the performance scoring device comprising:

[0018] The acquisition module is used to obtain the supply information corresponding to the supplier;

[0019] A feature extraction module, used to perform feature extraction processing on the supply information based on the feature extraction sub-model of the performance scoring model to obtain feature information corresponding to the supplier;

[0020] A contract performance prediction module, configured to determine the contract performance probability of the supplier based on the contract performance prediction sub-model of the contract performance scoring model and according to the characteristic information;

[0021] The performance scoring module is used to determine the performance scoring result of the supplier based on the scoring sub-model of the performance scoring model according to the characteristic information and the performance probability.

[0022] In a fourth aspect, the present application further provides a computer device, the computer device comprising a memory and a processor;

[0023] The memory is used to store computer programs;

[0024] The processor is used to execute the computer program and implement the supplier performance scoring method as described above, or implement the performance scoring model training method as described above when executing the computer program.

[0025] In a fifth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the supplier performance scoring method as described above are implemented, or the steps of the performance scoring model training method as described above are implemented.

[0026] The present application provides a supplier performance scoring method, training method, device and equipment. The supplier performance scoring method includes: obtaining supply information corresponding to the supplier; based on the feature extraction sub-model of the performance scoring model, performing feature extraction processing on the supply information to obtain feature information corresponding to the supplier; based on the performance prediction sub-model of the performance scoring model, determining the supplier's performance probability according to the feature information; based on the scoring sub-model of the performance scoring model, determining the supplier's performance scoring result according to the feature information and the performance probability, so as to improve the convenience of supplier performance evaluation and improve the effect of supplier performance evaluation.

[0027] Based on the setting of the performance scoring model, the computer device can determine the characteristic information and performance probability corresponding to the supplier through the performance scoring model, and determine the performance scoring result of the supplier by comprehensively considering the characteristic information and performance probability corresponding to the supplier. In the process of determining the performance scoring result of the supplier, there is no need for the staff to manually score the supplier, which is conducive to saving manpower, thereby facilitating the convenience of the performance evaluation of the supplier. Accordingly, when the performance score of the supplier is determined by comprehensively considering the characteristic information and performance probability corresponding to the supplier, it is conducive to improving the performance evaluation effect of the supplier. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 It is a flow chart of a supplier performance scoring method provided in an embodiment of the present application;

[0030] Figure 2 It is a flowchart of a training method for a performance scoring model provided in an embodiment of the present application;

[0031] Figure 3 is a schematic block diagram of a supplier's performance scoring device provided in an embodiment of the present application;

[0032] Figure 4 It is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0035] The embodiments of the present application provide a method, device and equipment for scoring the performance of a supplier. The method for scoring the performance of the supplier can be applied to a computer device, which can be a mobile phone, a tablet computer, a laptop computer, a desktop computer and the like. It can also be applied to a server, which can be a separate server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0036] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0037] See also Figure 1 , Figure 1 It is a flow chart of a supplier performance scoring method provided in an embodiment of the present application. It should be noted that the supplier performance scoring method provided in an embodiment of the present application can be used in a computer device, and of course can also be used in a server. For example, the server can obtain the supply information corresponding to the supplier from the computer device, and process the supply information according to the supplier's performance scoring method to determine the supplier's performance scoring result. Exemplarily, the server can, for example, send the supplier's performance scoring result to the computer device; of course, it is not limited to this, and no limitation is made here.

[0038] In specific implementation, computer devices include but are not limited to: any one of mobile phones, tablet computers, laptop computers, and desktop computers; the server can be a single server or a server cluster, or a cloud server that provides cloud computing services.

[0039] like Figure 1As shown, the supplier's performance scoring method includes steps S101 to S104.

[0040] Step S101: Obtain supply information corresponding to a supplier.

[0041] When it is necessary to conduct a performance evaluation on a supplier, the computer device can obtain the corresponding supply information of the supplier.

[0042] Exemplarily, supply information includes supplier's contract information, performance data, and operating information.

[0043] For example, a computer device can determine the supplier's contract information based on the supplier's contract text. Contract information can be used to indicate performance requirements for suppliers. For example, a computer device can use an optical character recognition (OCR) algorithm to perform text recognition on the contract text to obtain contract text information. For contract text information, a computer device can use a natural language processing algorithm to perform lexical analysis, syntactic analysis, and semantic analysis on the contract text information to extract key information from the contract text information, thereby determining the supplier's contract information based on the key information, such as supply task requirements, contract cycle, delivery results, acceptance criteria, etc., without limitation here. Since the supplier's contract information can directly affect the supplier's performance score results, the computer device can integrate the supplier's contract information to conduct a performance evaluation on the supplier.

[0044] For example, performance data can be used to indicate the performance of suppliers. Performance conditions include, for example, supply quality, delivery cycle, price, service, acceptance, etc., which are not limited here. Since the performance data of suppliers can directly affect the performance score of suppliers, the computer device can integrate the performance data of suppliers to evaluate the performance of suppliers.

[0045] For example, business information can be used to indicate the supplier's business conditions and business risks. Since the supplier's business information will affect the supplier's supply stability, and thus the supplier's business information will indirectly affect the supplier's performance score, the computer device can integrate the supplier's business information to evaluate the supplier's performance. The computer device can determine the supplier's business information through a preset enterprise query system. For example, the computer device can determine the supplier's business information based on the supplier's financial statements, judicial litigation information, public opinion information, etc., without limitation here.

[0046] When the corresponding supply information of the supplier is obtained, the supply information can be used by the subsequent performance scoring model to determine the performance scoring result of the supplier. Accordingly, the computer equipment can subsequently comprehensively consider the supplier's contract information, performance data and operating information to evaluate the supplier's performance, which is conducive to improving the accuracy of the supplier's performance evaluation in the future, thereby improving the performance evaluation effect of the supplier.

[0047] In some implementations, data preprocessing is performed on the supply information based on a data preprocessing sub-model of the fulfillment scoring model to obtain processed supply information.

[0048] When the supply information corresponding to the supplier is obtained, the computer device can input the supply information into the data preprocessing sub-model of the performance scoring model, and the data preprocessing sub-model can perform data preprocessing on the supply information to obtain the processed supply information. For example, the data preprocessing sub-model can perform data cleaning, missing value processing, outlier processing, etc. on the supply information to determine the processed supply information.

[0049] In this way, by preprocessing the supply information corresponding to the supplier, the data quality of the processed supply information can be improved. When the subsequent performance scoring model determines the supplier's performance scoring result based on the processed supply information, it is beneficial to improve the accuracy of the performance scoring result.

[0050] Step S102: Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier.

[0051] For example, when the performance scoring model obtains the supply information corresponding to the supplier, it can perform feature extraction processing on the supply information through the feature extraction sub-model to obtain the feature information corresponding to the supplier. The feature information can be used to indicate the score of the feature corresponding to the supply information. Accordingly, when the feature information is determined, the feature information can be used by the subsequent performance scoring model to determine the performance scoring result for the supplier.

[0052] Exemplarily, the supply information corresponding to the supplier may include the supplier's contract information, performance data and operating information. When the performance evaluation model obtains the supply information corresponding to the supplier, it may input the supplier's contract information, performance data and operating information into the feature extraction sub-model.

[0053] In some embodiments, the supplier's contract information, performance data, and operating information are input into a feature extraction sub-model to obtain at least one of the supplier's corresponding delivery punctuality characteristics, supply quality characteristics, service quality characteristics, supply cycle characteristics, litigation risk characteristics, and operating conditions characteristics.

[0054] For example, when the supplier's contract information, performance data, and operating information are input into the feature extraction sub-model, the feature extraction sub-model can determine the corresponding characteristics of the supplier based on at least one of the supplier's contract information, performance data, and operating information. For example, the feature extraction sub-model can determine the supplier's corresponding on-time delivery rate characteristics, supply quality characteristics, service quality characteristics, and supply cycle characteristics based on the contract information and performance data. For another example, the feature extraction sub-model can determine the supplier's corresponding operating situation characteristics based on the operating information. Of course, the feature extraction sub-model's determination process of the supplier's corresponding characteristic information is not limited to this and is not limited here.

[0055] In an exemplary embodiment, when the feature extraction submodel determines the supplier's corresponding delivery punctuality characteristics, supply quality characteristics, service quality characteristics, supply cycle characteristics, litigation risk characteristics, and operating conditions characteristics, the feature extraction submodel can output the supplier's corresponding feature information in the form of a score.

[0056] For example, suppliers include supplier A and supplier B. The feature extraction submodel determines the feature information corresponding to supplier A based on the supply information corresponding to supplier A, and determines the feature information corresponding to supplier B based on the supply information corresponding to supplier B, as shown in Table 1.

[0057] Feature information Supplier A Supplier B On-time delivery characteristics 80 60 Supply quality characteristics 75 60 Quality of Service Features 70 60 Supply cycle characteristics 70 60 Litigation risk characteristics 80 50 Operating characteristics 85 70

[0058] Table 1

[0059] When the characteristic information of supplier A and supplier B is determined, the performance scoring model can subsequently determine the performance scoring results of supplier A and supplier B based on the characteristic information of supplier A and supplier B. Of course, it is not limited to supplier A and supplier B, and is not limited here.

[0060] In this way, when the characteristic information corresponding to the supplier is determined through the feature extraction sub-model of the performance scoring model, the characteristic information corresponding to the supplier can be used to subsequently determine the performance scoring result corresponding to the supplier, which is conducive to subsequently improving the convenience of performance evaluation of the supplier.

[0061] Step S103: Based on the fulfillment prediction sub-model of the fulfillment scoring model, the supplier's fulfillment probability is determined according to the characteristic information.

[0062] For example, when the performance scoring model obtains the corresponding characteristic information of the supplier, it can predict the supplier's performance probability through the performance prediction sub-model. The performance probability can be used to indicate the probability of the supplier's performance type being good performance or poor performance. When the performance type is good performance, the supplier's performance quality is good. When the performance type is poor performance, the supplier's performance quality is poor. Since the supplier's performance quality will affect the supplier's performance scoring results, the performance scoring model can determine the supplier's performance probability through the performance prediction sub-model.

[0063] In some embodiments, characteristic information is input into a performance prediction sub-model to obtain the supplier's performance type and the probability corresponding to the performance type; the performance type includes good performance or poor performance; based on the performance type and the probability corresponding to the performance type, the supplier's performance probability is determined.

[0064] For example, when the fulfillment prediction sub-model obtains characteristic information, it can determine the supplier's fulfillment type and the probability corresponding to the fulfillment type based on the characteristic information.

[0065] In the case where different suppliers have different performance qualities, the performance probabilities of different suppliers may also be different. Since the feature information can be used to indicate the score of the feature corresponding to the supply information, the performance prediction sub-model can predict the supplier's performance quality based on the feature information, thereby determining whether the supplier's performance type is good performance or poor performance. Accordingly, in the case where the performance prediction sub-model determines the supplier's performance type, the performance prediction sub-model can further determine the probability corresponding to the performance type. Based on this, the performance prediction sub-model can determine the performance probability by comprehensively considering the supplier's performance type and the probability corresponding to the performance type.

[0066] Take the example of suppliers including supplier A and supplier B. The performance prediction sub-model determines that the performance type corresponding to supplier A is good performance based on the characteristic information corresponding to supplier A, and the probability corresponding to this performance type is 80%. Since the probability that supplier A has good performance is greater than or equal to the preset probability threshold, the performance prediction sub-model can determine that the performance probability of supplier A is 80%. The performance prediction sub-model determines that the performance type corresponding to supplier B is poor performance based on the characteristic information corresponding to supplier B, and the probability corresponding to this performance type is 60%. Since the probability that supplier B has poor performance is greater than or equal to the preset probability threshold, the performance prediction sub-model can determine that the performance probability of supplier B is 60%. Among them, the preset probability threshold can be pre-set or set by the user, which is not limited here.

[0067] In this way, when the performance scoring model determines the supplier's performance probability based on the characteristic information through the performance prediction sub-model, the performance probability can be used by the performance scoring model to subsequently determine the supplier's performance scoring result, which is conducive to improving the convenience of supplier performance evaluation. Accordingly, the performance scoring model can subsequently determine the supplier's performance scoring result based on the probability of the supplier's good performance or poor performance, which is conducive to improving the accuracy of the supplier's performance evaluation, thereby improving the performance evaluation effect of the supplier.

[0068] Step S104: Based on the scoring sub-model of the performance scoring model, determine the performance scoring result of the supplier according to the feature information and the performance probability.

[0069] When the feature extraction sub-model determines the characteristic information corresponding to the supplier and the performance prediction sub-model determines the performance probability of the supplier, the performance scoring model can determine the performance scoring result of the supplier by comprehensively considering the characteristic information corresponding to the supplier and the performance probability of the supplier.

[0070] For example, the performance scoring model can input feature information and performance probability into the scoring sub-model, and the scoring sub-model can then combine the feature information and performance probability to calculate the supplier's performance scoring results, thereby outputting the supplier's performance scoring results.

[0071] In some embodiments, a first score of the supplier is determined based on the feature information and a weight coefficient corresponding to the feature information; and a performance rating result of the supplier is determined based on the first score and the performance probability.

[0072] For example, the characteristic information may include at least one of the characteristics of on-time delivery rate, supply quality, service quality, supply cycle, litigation risk, and business situation of the supplier. Different characteristic information may have different weight coefficients. Based on this, the scoring sub-model may determine the first score of the supplier by comprehensively considering the characteristic information and the weight coefficient corresponding to the characteristic information in the process of determining the performance score result of the supplier.

[0073] For example, the scoring sub-model may multiply the feature information by the weight coefficient corresponding to the feature information to obtain a first score for the supplier.

[0074] For example, the weight coefficient corresponding to the on-time delivery rate feature is 0.2, the weight coefficient corresponding to the supply quality feature is 0.3, the weight coefficient corresponding to the service quality feature is 0.2, the weight coefficient corresponding to the delivery cycle feature is 0.1, the weight coefficient corresponding to the litigation risk feature is 0.1, and the weight coefficient corresponding to the operating situation feature is 0.1. Combined with the characteristic information corresponding to supplier A and the characteristic information corresponding to supplier B mentioned in Table 1, the scoring sub-model can determine that the first score of supplier A is 76 and the first score of supplier B is 60.

[0075] Of course, it is not limited to this. For example, the scoring sub-model can set corresponding scoring weights for feature information based on a percentage scoring mechanism.

[0076] The scoring sub-model can multiply the feature information by the weight coefficient corresponding to the feature information and the scoring weight corresponding to the feature information to obtain the first score of the supplier.

[0077] For example, the weight coefficient corresponding to the on-time delivery rate feature is 0.2, the weight coefficient corresponding to the supply quality feature is 0.3, the weight coefficient corresponding to the service quality feature is 0.2, the weight coefficient corresponding to the delivery cycle feature is 0.1, the weight coefficient corresponding to the litigation risk feature is 0.1, the weight coefficient corresponding to the operating situation feature is 0.1, and the scoring weight corresponding to the feature information is 0.4. The scoring sub-model combines Table 1, the weight coefficients of each feature information, and the scoring weights of each feature information to determine that the first score of supplier A is 30.4 and the first score of supplier B is 24.

[0078] Of course, it is not limited to this. The weight coefficient of the feature information and the scoring weight of the feature information can be preset or set by the user, and there is no limitation here.

[0079] When the first score of the supplier is determined, the scoring sub-model can combine the first score and the supplier's performance probability to determine the supplier's performance scoring result.

[0080] In some implementations, the first score is multiplied by the fulfillment probability to obtain a second score for the supplier; the second score is added to the corresponding preset score of the supplier to obtain the supplier's fulfillment score result.

[0081] For example, when the performance scoring model can determine the performance scoring results of different suppliers, the performance scoring model can combine the historical performance scoring results of all suppliers to determine the preset score of the supplier. The preset score can be used to indicate the reference score result of the supplier. For example, the preset score of the supplier can be determined based on any one of the average, median, and mode of the historical performance scoring results of all suppliers, without limitation. The setting of the preset score corresponding to the supplier can avoid the poor accuracy of the performance evaluation of the supplier due to the large difference between the second scores of the supplier.

[0082] For example, if the first score of supplier A is 30.4, the first score of supplier B is 24, the fulfillment probability of supplier A is 80%, and the fulfillment probability of supplier B is 60%. The scoring sub-model can multiply the first score of supplier A by the fulfillment probability of supplier A to obtain the second score of supplier A as 24.32. Correspondingly, the scoring sub-model can multiply the first score of supplier B by the fulfillment probability of supplier B to obtain the second score of supplier B as 14.4.

[0083] When the supplier's second score is determined, the scoring sub-model can add the second score to the supplier's corresponding preset score to obtain the supplier's performance score result.

[0084] For example, if the preset score of the supplier is 60, the second score of supplier A is 24.32, and the second score of supplier B is 14.4, the scoring sub-model can determine that the performance score of supplier A is 84.32 based on the second score of supplier A combined with the preset score. Correspondingly, the scoring sub-model can determine that the performance score of supplier B is 74.4 based on the second score of supplier B combined with the preset score.

[0085] When the performance scoring model determines the performance scoring result of the supplier, the business personnel can refer to the performance scoring result to consider measures such as supplier selection, maintenance, and change, without any restriction here.

[0086] The supplier performance scoring method provided in the above embodiment obtains the supply information corresponding to the supplier; based on the feature extraction sub-model of the performance scoring model, performs feature extraction processing on the supply information to obtain the feature information corresponding to the supplier; based on the performance prediction sub-model of the performance scoring model, determines the supplier's performance probability according to the feature information; based on the scoring sub-model of the performance scoring model, determines the supplier's performance scoring result according to the feature information and the performance probability, so as to improve the convenience of supplier performance evaluation and improve the effect of supplier performance evaluation.

[0087] Based on the setting of the performance scoring model, the computer device can determine the characteristic information and performance probability corresponding to the supplier through the performance scoring model, and determine the performance scoring result of the supplier by comprehensively considering the characteristic information and performance probability corresponding to the supplier. In the process of determining the performance scoring result of the supplier, there is no need for staff to manually score the supplier, which is conducive to saving manpower, thereby improving the convenience of performance evaluation of the supplier. Accordingly, when the performance scoring result of the supplier is determined by comprehensively considering the characteristic information and performance probability corresponding to the supplier, it is conducive to improving the performance evaluation effect of the supplier.

[0088] See also Figure 2 , Figure 2 It is a flow chart of a training method for a performance scoring model provided by an embodiment of the present application. It should be noted that the training method for the performance scoring model provided by the embodiment of the present application can be used for computer devices, and of course can also be used for servers. For example, the server can obtain a training sample set from a computer device, process the training sample set according to the training method of the performance scoring model, and obtain the model optimization parameters of the performance scoring model. And according to the model optimization parameters, adjust the model parameters of the performance scoring model to obtain an optimized business response model. Exemplarily, the server can, for example, send the optimized performance scoring model to the computer device, so that when the computer device obtains the supply information corresponding to the supplier, it can determine the performance scoring result of the supplier through the optimized performance scoring model; of course, it is not limited to this, and no limitation is made here.

[0089] In specific implementation, computer devices include but are not limited to: any one of mobile phones, tablet computers, laptop computers, and desktop computers; the server can be a single server or a server cluster, or a cloud server that provides cloud computing services.

[0090] like Figure 2 As shown, the training method of the performance scoring model includes steps S201 to S206.

[0091] Step S201: Obtain a training sample set, where the training sample set includes supply information corresponding to multiple suppliers and a performance score result label corresponding to each supplier.

[0092] For example, when training a performance scoring model, a training sample set may be obtained. The training sample set may include supply information corresponding to multiple suppliers. The supply information corresponding to each supplier in the training sample set may be provided with a corresponding performance scoring result label. The training sample set may be used for subsequent training of the performance scoring model.

[0093] In some embodiments, when the supply information corresponding to the supplier is obtained, the performance scoring model can perform data preprocessing on the supply information through the data preprocessing sub-model to obtain the processed supply information. Accordingly, the training sample set can include the processed supply information corresponding to each of the multiple suppliers and the performance scoring result label corresponding to each supplier, so as to facilitate the subsequent training of the performance scoring model.

[0094] In some implementations, when the supply information corresponding to the supplier is obtained, the performance score result label corresponding to the supplier can be determined by a preset marking method, which is not limited here.

[0095] In this way, when the supply information corresponding to the supplier and the performance score result label corresponding to the supplier are determined, the performance score model can be trained subsequently.

[0096] Step S202: Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier.

[0097] For example, when training the fulfillment scoring model, it is necessary to learn how to determine the characteristic information corresponding to the supplier. Based on this, the characteristic information can be input into the feature extraction sub-model of the fulfillment scoring model, so that the feature extraction sub-model can extract the supply information and obtain the characteristic information corresponding to the supplier.

[0098] In some embodiments, the supply information may include the supplier's contract information, performance data, and business information. When the supply information is input into the feature extraction sub-model, the feature extraction sub-model may learn how to determine the characteristic information corresponding to the supplier based on at least one of the contract information, performance data, and business information. Accordingly, the characteristic information corresponding to the supplier may include at least one of the supplier's corresponding delivery on-time rate characteristics, supply quality characteristics, service quality characteristics, supply cycle characteristics, litigation risk characteristics, and business situation characteristics.

[0099] In this way, when the characteristic information corresponding to the supplier is determined, the performance scoring model can optimize the model parameters of the performance scoring model based on the characteristic information to improve the training effect of the performance scoring model.

[0100] Step S203: Based on the performance prediction sub-model of the performance scoring model, the performance probability of the supplier is determined according to the characteristic information.

[0101] For example, when training the fulfillment scoring model, it is necessary to learn how to determine the supply probability corresponding to the supplier. Based on this, the feature information can be input into the fulfillment prediction sub-model of the fulfillment scoring model, so that the fulfillment prediction sub-model can predict the supplier's fulfillment probability based on the feature information and obtain the supplier's fulfillment probability.

[0102] In some embodiments, the performance prediction sub-model can determine the performance type of the supplier, such as good performance or poor performance. In the process of training the performance prediction sub-model, the performance prediction sub-model can be trained according to a binary classification machine learning algorithm of logistic regression.

[0103] In this way, when the supplier's performance probability is determined, the performance scoring model can comprehensively consider the supplier's performance probability and optimize the model parameters of the performance scoring model to improve the training effect of the performance scoring model.

[0104] Step S204: Based on the scoring sub-model of the performance scoring model, determine the performance scoring result of the supplier according to the feature information and the performance probability.

[0105] For example, when training the performance scoring model, it is necessary to learn how to determine the performance scoring results of suppliers. Based on this, the feature information and the performance probability can be input into the scoring sub-model to determine the performance scoring results of suppliers based on the scoring sub-model, the feature information and the performance probability.

[0106] In this way, when the supplier's performance scoring results are determined, the performance scoring model can integrate the supplier's performance scoring results and optimize the model parameters of the performance scoring model to improve the training effect of the performance scoring model.

[0107] Step S205: Determine the model optimization parameters of the performance scoring model according to the performance scoring result and the performance scoring result label.

[0108] For example, the performance scoring result determined by the performance scoring model is equivalent to the predicted result of the performance scoring model on the supplier's performance scoring result. The performance scoring result label corresponding to the supplier is equivalent to the actual result of the performance scoring model on the supplier's performance scoring result. According to the performance scoring result and the performance scoring result label, the loss value between the actual result and the predicted result of the performance scoring model when determining the supplier's performance scoring result can be determined.

[0109] The performance scoring model can determine the model optimization parameters of the performance scoring model according to the loss value. The model optimization parameters can be used to subsequently adjust the model parameters of the performance scoring model so that the performance scoring model can more accurately move the predicted results of the performance scoring model for the supplier's performance scoring results closer to the actual results, thereby achieving the purpose of training.

[0110] Step S206: Adjust the model parameters of the performance scoring model according to the model optimization parameters.

[0111] For example, the performance scoring model can adjust the model parameters of the performance scoring model according to the model optimization parameters. For example, the performance scoring model can adjust the model parameters of at least one of the feature extraction sub-model, the performance prediction sub-model, and the scoring sub-model according to the model optimization parameters, which is not limited here.

[0112] By adjusting the model parameters of the performance scoring model, the performance scoring model can more accurately bring the predicted results of the supplier's performance scoring results closer to the actual results, so as to achieve the purpose of training, which is conducive to improving the accuracy of the performance scoring model in determining the supplier's performance scoring results.

[0113] The training method of the performance scoring model provided in the above embodiment obtains a training sample set, and the training sample set includes the supply information corresponding to each of the multiple suppliers and the performance scoring result label corresponding to each supplier; based on the feature extraction sub-model of the performance scoring model, the supply information is subjected to feature extraction processing to obtain the feature information corresponding to the supplier; based on the performance prediction sub-model of the performance scoring model, the performance probability of the supplier is determined according to the feature information; based on the scoring sub-model of the performance scoring model, the performance scoring result of the supplier is determined according to the feature information and the performance probability, so as to improve the accuracy of determining the performance scoring result, thereby improving the training effect of the performance scoring model. The performance scoring model can be subsequently applied to financial services related to the performance evaluation of suppliers, which is conducive to improving the convenience of performance evaluation of suppliers and improving the performance evaluation effect of suppliers. For example, when processing related financial services, if it is necessary to perform performance evaluation on suppliers, the performance scoring result of the supplier can be obtained by processing the corresponding supply information of the supplier through the performance scoring model, so as to improve the convenience of performance evaluation of suppliers and improve the performance evaluation effect of suppliers. Accordingly, in the process of determining the supplier's performance score results, there is no need to spend a lot of manpower and time, which is conducive to improving the efficiency of handling financial business.

[0114] See also Figure 3 , Figure 3The present invention provides a schematic block diagram of a supplier's performance scoring device provided in an embodiment of the present invention. The performance scoring device can be configured in a server or an electronic device to execute the supplier's performance scoring method described above.

[0115] like Figure 3 As shown, the contract performance scoring device includes: an acquisition module 110, a feature extraction module 120, a contract performance prediction module 130 and a contract performance scoring module 140.

[0116] The acquisition module 110 is used to acquire the supply information corresponding to the supplier.

[0117] The feature extraction module 120 is used to perform feature extraction processing on the supply information based on the feature extraction sub-model of the performance scoring model to obtain feature information corresponding to the supplier.

[0118] The fulfillment prediction module 130 is used to determine the fulfillment probability of the supplier based on the fulfillment prediction sub-model of the fulfillment scoring model and according to the characteristic information.

[0119] The performance scoring module 140 is used to determine the performance scoring result of the supplier based on the scoring sub-model of the performance scoring model, according to the characteristic information and the performance probability.

[0120] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] The method of the present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0122] Exemplarily, the above method and apparatus may be implemented in the form of a computer program, which may be run on a computer device.

[0123] See also Figure 4 , Figure 4 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server or an electronic device.

[0124] like Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0125] The storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can cause the processor to execute any supplier performance scoring method, or cause the processor to execute any performance scoring model training method.

[0126] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0127] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any supplier's performance scoring method, or execute any performance scoring model training method.

[0128] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 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.

[0129] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0130] In one embodiment, the processor is used to execute a computer program and implement the following steps when executing the computer program:

[0131] Get the supply information corresponding to the supplier;

[0132] Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier;

[0133] The fulfillment prediction sub-model based on the fulfillment scoring model determines the fulfillment probability of the supplier according to the characteristic information;

[0134] Based on the scoring sub-model of the performance scoring model, the performance scoring result of the supplier is determined according to the feature information and the performance probability.

[0135] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and brevity of description, the specific working process of the above description of the supplier's performance scoring can refer to the corresponding process in the aforementioned supplier's performance scoring method embodiment, and will not be repeated here.

[0136] In another embodiment, the processor is used to execute a computer program and implement the following steps when executing the computer program:

[0137] Obtaining a training sample set, wherein the training sample set includes supply information corresponding to each of a plurality of suppliers and a performance score result label corresponding to each of the suppliers;

[0138] Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier;

[0139] The fulfillment prediction sub-model based on the fulfillment scoring model determines the fulfillment probability of the supplier according to the characteristic information;

[0140] Based on the scoring sub-model of the performance scoring model, determining the performance scoring result of the supplier according to the characteristic information and the performance probability;

[0141] Determining model optimization parameters of the performance scoring model according to the performance scoring and the performance scoring result label;

[0142] According to the model optimization parameters, the model parameters of the performance scoring model are adjusted.

[0143] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the training of the performance scoring model described above can refer to the corresponding process in the aforementioned embodiment of the training method of the performance scoring model, and will not be repeated here.

[0144] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The method implemented when the computer program is executed by a processor can refer to the various embodiments of the supplier performance scoring method of the present application, or refer to the various embodiments of the training method of the performance scoring model of the present application.

[0145] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0146] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0147] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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 system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0148] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A supplier performance scoring method, characterized in that: include: Get the supply information corresponding to the supplier; Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier; The fulfillment prediction sub-model based on the fulfillment scoring model determines the fulfillment probability of the supplier according to the characteristic information; Based on the scoring sub-model of the performance scoring model, the performance scoring result of the supplier is determined according to the feature information and the performance probability.

2. The performance scoring method according to claim 1, characterized in that: The supply information includes the supplier's contract information, performance data and operating information; The feature extraction sub-model based on the performance scoring model performs feature extraction processing on the supply information to obtain feature information corresponding to the supplier, including: The supplier's contract information, performance data and operating information are input into the feature extraction sub-model to obtain at least one of the supplier's corresponding delivery punctuality characteristics, supply quality characteristics, service quality characteristics, supply cycle characteristics, litigation risk characteristics and operating conditions characteristics.

3. The performance scoring method according to claim 1, characterized in that: The contract performance prediction sub-model based on the contract performance scoring model determines the contract performance probability of the supplier according to the characteristic information, including: Inputting the characteristic information into the performance prediction sub-model to obtain the performance type of the supplier and the probability corresponding to the performance type; the performance type includes good performance or bad performance; The fulfillment probability of the supplier is determined according to the fulfillment type and the probability corresponding to the fulfillment type.

4. The performance scoring method according to claim 1, characterized in that: The scoring sub-model based on the performance scoring model determines the performance scoring result of the supplier according to the feature information and the performance probability, including: Determining a first score of the supplier according to the feature information and a weight coefficient corresponding to the feature information; A performance score result of the supplier is determined based on the first score and the performance probability.

5. The performance scoring method according to claim 4, characterized in that: The step of determining the supplier's contract performance score result according to the first score and the contract performance probability includes: Multiplying the first score by the fulfillment probability to obtain a second score for the supplier; The second score is added to the preset score corresponding to the supplier to obtain the performance score result of the supplier.

6. The performance scoring method according to any one of claims 1 to 5, characterized in that: After obtaining the supply information corresponding to the supplier, the method further includes: Based on the data preprocessing sub-model of the performance scoring model, data preprocessing is performed on the supply information to obtain processed supply information.

7. A training method for a performance scoring model, characterized in that: The training method comprises: Obtaining a training sample set, wherein the training sample set includes supply information corresponding to each of a plurality of suppliers and a performance score result label corresponding to each of the suppliers; Based on the feature extraction sub-model of the performance scoring model, feature extraction processing is performed on the supply information to obtain feature information corresponding to the supplier; The fulfillment prediction sub-model based on the fulfillment scoring model determines the fulfillment probability of the supplier according to the characteristic information; Based on the scoring sub-model of the performance scoring model, determining the performance scoring result of the supplier according to the characteristic information and the performance probability; Determining model optimization parameters of the performance scoring model according to the performance scoring and the performance scoring result label; According to the model optimization parameters, the model parameters of the performance scoring model are adjusted.

8. A supplier performance scoring device, characterized in that: The performance scoring device comprises: The acquisition module is used to obtain the supply information corresponding to the supplier; A feature extraction module, configured to perform feature extraction processing on the supply information based on a feature extraction sub-model of a performance scoring model, to obtain feature information corresponding to the supplier; A contract performance prediction module, configured to determine the contract performance probability of the supplier based on the contract performance prediction sub-model of the contract performance scoring model and according to the characteristic information; The performance scoring module is used to determine the performance scoring result of the supplier based on the scoring sub-model of the performance scoring model according to the characteristic information and the performance probability.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the supplier performance scoring method as described in any one of claims 1 to 6 when executing the computer program, or implement the training method of the performance scoring model as described in claim 7.

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 supplier performance scoring method as described in any one of claims 1 to 6 are implemented, or the training method of the performance scoring model as described in claim 7 is implemented.

Images