CN114021952A

CN114021952A - Enterprise cooperation scoring method and device, electronic equipment and computer storage medium

Info

Publication number: CN114021952A
Application number: CN202111290473.6A
Authority: CN
Inventors: 刘天宇; 温嘉瑶; 梁森
Original assignee: Beijing Jindi Technology Co Ltd
Current assignee: Beijing Jindi Technology Co Ltd
Priority date: 2021-11-02
Filing date: 2021-11-02
Publication date: 2022-02-08

Abstract

The embodiment provides an enterprise cooperation scoring method, an enterprise cooperation scoring device, electronic equipment and a computer storage medium. Wherein the method comprises the following steps: acquiring enterprise data of an enterprise to be scored; determining enterprise characteristic data of the enterprise to be scored according to the enterprise data; according to the enterprise characteristic data, carrying out industry classification on the enterprise to be scored so as to obtain an industry classification result of the enterprise to be scored; determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored; and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored. The scheme can simply, conveniently and accurately acquire the enterprise cooperation score.

Description

Enterprise cooperation scoring method and device, electronic equipment and computer storage medium

Technical Field

The embodiment relates to the technical field of computers, in particular to an enterprise cooperation scoring method and device, electronic equipment and a computer storage medium.

Background

The supplier or the client plays a decisive role in the business activity of the enterprise. When a business seeks a supplier or a customer, the quality, cost, delivery, service, income, profit and the like are considered comprehensively. The enterprise cooperation scoring is a multi-dimensional comprehensive scoring for the target enterprise for the purpose of helping the enterprise to find suppliers or customers. The enterprise cooperation score is used for describing the safety of cooperation between enterprises, is different from the traditional credit score and tax score, concentrates on cooperation evaluation between the enterprises and at the industrial chain level, and pays more attention to the performance of the enterprise cooperation. The score of the business cooperation score reflects the horizontal ranking of the target business within the industry. When the scores of the two enterprises are similar, the method has considerable strength. On the contrary, the difference of the scores represents the difference of the comprehensive strength.

In the prior art, rule-based expert systems are mostly used for scoring. The method depends on expert experience, needs to have deep enough understanding on the business, repeatedly deduces the weight proportion, and carries out enough experiments and analysis, and is time-consuming and labor-consuming. Meanwhile, due to the complex configuration of the rules, when the rules need to be adjusted or migrated, the whole body is pulled one by one, and the maintenance is not easy. In addition, the system usually calculates the final weight of each dimension one by one, and cannot fully consider the cross combination between the dimensions, so that the enterprise cooperation score is not accurate enough.

Therefore, how to simply, conveniently and accurately acquire the enterprise cooperation score becomes a technical problem to be solved urgently at present.

Disclosure of Invention

In view of the above, one of the technical problems to be solved by the embodiments of the present invention is to provide an enterprise cooperation scoring method, apparatus, electronic device and computer storage medium, so as to solve the technical problem in the prior art how to simply, conveniently and accurately obtain an enterprise cooperation score.

According to a first aspect of the embodiments of the present invention, there is provided an enterprise cooperation scoring method, including: acquiring enterprise data of an enterprise to be scored; determining enterprise characteristic data of the enterprise to be scored according to the enterprise data; according to the enterprise characteristic data, carrying out industry classification on the enterprise to be scored so as to obtain an industry classification result of the enterprise to be scored; determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored; and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

According to a second aspect of the embodiments of the present invention, there is provided an enterprise cooperation scoring apparatus, including: the acquisition module is used for acquiring enterprise data of the enterprise to be evaluated; the first determination module is used for determining enterprise characteristic data of the enterprise to be scored according to the enterprise data; the industry classification module is used for performing industry classification on the enterprise to be scored according to the enterprise characteristic data so as to obtain an industry classification result of the enterprise to be scored; the second determination module is used for determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored; and the first scoring module is used for carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus, including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus; the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the enterprise cooperation scoring method in the first aspect.

According to a fourth aspect of embodiments of the present invention, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the enterprise collaboration scoring method as described in the first aspect.

The enterprise cooperation scoring scheme provided by the embodiment of the invention obtains enterprise data of an enterprise to be scored, determines enterprise characteristic data of the enterprise to be scored according to the enterprise data, classifies the enterprise to be scored according to the enterprise characteristic data to obtain an industry classification result of the enterprise to be scored, determines an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored, scores the enterprise to be scored according to the enterprise cooperation scoring model and the enterprise characteristic data to obtain the enterprise cooperation scoring result of the enterprise to be scored, on one hand, reduces expert workload required by modeling through a relation model of enterprise data and enterprise cooperation scoring established in a machine learning manner, the method has the advantages that the engineering period is shortened, the migration and maintenance cost is reduced, on the other hand, the enterprise feature crossing is automatically completed by accessing more enterprise features and with the help of a machine learning algorithm, the enterprise data are fully utilized, the accuracy of enterprise cooperation scoring is improved, the enterprise cooperation scoring can be simply, conveniently and accurately obtained, and then the safety of cooperation between enterprises is described.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present invention, and it is also possible for a person skilled in the art to obtain other drawings based on the drawings.

FIG. 1A is a flowchart illustrating steps of a business cooperation scoring method according to an embodiment of the present invention;

FIG. 1B is a schematic diagram illustrating an enterprise collaboration scoring method according to a first embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of an enterprise cooperation scoring device in the second embodiment;

fig. 3 is a schematic structural diagram of an electronic device in the third embodiment.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments of the present invention shall fall within the scope of the protection of the embodiments of the present invention.

The following further describes specific implementation of the embodiments of the present invention with reference to the drawings.

Referring to fig. 1A, a flowchart illustrating steps of an enterprise collaboration scoring method in accordance with a first embodiment is shown.

Specifically, the enterprise cooperation scoring method provided by this embodiment includes the following steps:

in step S101, enterprise data of an enterprise to be scored is acquired.

In this embodiment, the business data of the business to be scored may include at least one of the following: enterprise name data, enterprise business range data, enterprise industrial and commercial data, enterprise judicial dispute data, enterprise business range data, enterprise intellectual property data and enterprise business condition data. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In step S102, according to the enterprise data, enterprise characteristic data of the enterprise to be scored is determined.

In some optional embodiments, when determining the enterprise characteristic data of the enterprise to be scored according to the enterprise data, performing data type conversion on the enterprise data to obtain the enterprise data after data type conversion; and splicing the enterprise data after the data type conversion to obtain enterprise characteristic data of the enterprise to be scored. Specifically, enterprise data disclosed by an enterprise to be scored is crawled from a network, data type conversion is carried out on the enterprise data, and then the converted enterprise data are spliced to obtain enterprise characteristic data of the enterprise to be scored. Therefore, the enterprise characteristic data of the enterprise to be scored can be effectively obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, the enterprise data of the enterprise bulletin to be scored can be crawled from the network through a web crawler program. The web crawler program may be understood as a program that automatically captures web information according to a certain rule, and the web crawler program may be implemented by using Python language, Java language, or Javascript language. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when performing data type conversion on the enterprise data, performing data type conversion on the data of the character string type and the data of the numerical value type in the enterprise data to obtain the data of the numerical value type. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when the enterprise data after data type conversion is spliced, the data of the numerical type is spliced to obtain the enterprise feature vector of the enterprise to be scored. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In step S103, performing industry classification on the enterprise to be scored according to the enterprise feature data to obtain an industry classification result of the enterprise to be scored.

In some alternative embodiments, the enterprise characterization data may include enterprise name characterization data and enterprise business scope characterization data. And when the enterprises to be scored are subjected to industry classification according to the enterprise characteristic data, performing industry classification on the enterprises to be scored according to the enterprise name characterization data and the enterprise operation range characterization data through an enterprise belonging industry classification model so as to obtain an industry classification result of the enterprises to be scored. Therefore, the enterprises to be scored are classified in industry according to the enterprise name characterization data and the enterprise operation range characterization data through the enterprise belonging industry classification model, and the industry classification results of the enterprises to be scored can be accurately obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, the business classification model of the enterprise may be any suitable neural network model that can implement feature extraction or target object detection, including but not limited to a convolutional neural network model, an reinforcement learning neural network model, a generative network model in an antagonistic neural network model, and so on. The specific structure of the neural network model can be set by those skilled in the art according to actual requirements, such as the number of convolutional layers, the size of convolutional core, the number of channels, and so on. For example, the business-to-business classification model may be a long-and-short memory network model for the business-to-business classification. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In step S104, according to the industry classification result of the enterprise to be scored, an enterprise cooperation scoring model corresponding to the enterprise to be scored is determined in enterprise cooperation scoring models of a plurality of industry classifications.

In this embodiment, each industry category has a corresponding business cooperation scoring model. After the industry classification result of the enterprise to be scored is obtained, the enterprise cooperation scoring model corresponding to the enterprise to be scored can be determined according to the industry classification result of the enterprise to be scored. The enterprise cooperation scoring model can be a LightGBM model, and can also be a classical machine learning model such as XGboost and a regression tree, or a deep learning neural network such as CNN, RNN and Transformer. The light GBM (light Gradient Boosting machine) is a framework for realizing a GBDT (Gradient Boosting Decision Tree) algorithm, the GBDT has the main idea that a weak classifier (Decision tree) is used for iterative training to obtain an optimal model, and the model has the advantages of good training effect, difficulty in overfitting and the like. LightGBM is a distributed gradient boosting framework based on a decision tree algorithm. The design idea of LightGBM is mainly two points: the use of data to a memory is reduced, and more data can be used as much as possible by a single machine under the condition of not sacrificing the speed; the communication cost is reduced, the efficiency of multi-machine parallel is improved, and the linear acceleration on calculation is realized. It can be seen that the LightGBM was originally designed to provide a fast, efficient, low-memory, high-accuracy data science tool that supports parallel and large-scale data processing. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, before determining, according to the industry classification result of the enterprise to be scored, an enterprise cooperation scoring model corresponding to the enterprise to be scored in an enterprise cooperation scoring model of several industry classifications, the method further includes: determining enterprise characteristic data of the sample enterprise according to the acquired enterprise data of the sample enterprise; carrying out industry classification on the sample enterprise according to the enterprise characteristic data of the sample enterprise to obtain an industry classification result of the sample enterprise; determining the enterprise characteristic data of the sample enterprise in the same industry classification as a training sample of an enterprise cooperation scoring model of the same industry classification; and training the enterprise cooperation scoring model of the same industry classification according to the training sample of the enterprise cooperation scoring model of the same industry classification. Therefore, the training samples of the enterprise cooperation scoring model of the same industry classification can be accurately determined, and the enterprise cooperation scoring model of the same industry classification can be effectively trained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In one specific example, the sample business may be understood as a business that is a training sample, and the business characteristics data may include business name characterization data and business scope characterization data. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, the method further comprises: carrying out descriptive statistics on enterprise characteristic data of the sample enterprises in the same industry classification to obtain various enterprise indexes of the same industry classification; determining the mean value and the standard deviation of each enterprise index of the same industry classification according to each enterprise index data in the enterprise feature data of the sample enterprise in the same industry classification; normalizing each enterprise index data in the enterprise feature data of the sample enterprises in the same industry classification according to the mean value and the standard deviation of each enterprise index in the same industry classification to obtain normalized enterprise feature data of the sample enterprises in the same industry classification; when the enterprise characteristic data of the sample enterprise in the same industry classification is determined to be a training sample of the enterprise cooperation scoring model of the same industry classification, the normalized enterprise characteristic data of the sample enterprise in the same industry classification is determined to be a training sample of the enterprise cooperation scoring model of the same industry classification. Therefore, the mean value and the standard deviation of each enterprise index of the same industry classification can be accurately determined through each enterprise index data in the enterprise feature data of the sample enterprise in the same industry classification, in addition, the normalized enterprise feature data of the sample enterprise in the same industry classification can be effectively obtained, and the training sample of the enterprise cooperation scoring model of the same industry classification can also be accurately determined. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when the enterprise cooperation scoring model of the same industry class is trained according to the training samples of the enterprise cooperation scoring model of the same industry class, the training samples of the enterprise cooperation scoring model of the same industry class are sampled in a layered sampling mode to obtain the training data of the enterprise cooperation scoring model of the same industry class; and training the enterprise cooperation scoring model of the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification. Therefore, the enterprise cooperation scoring model of the same industry classification can be effectively trained through the training data of the enterprise cooperation scoring model of the same industry classification. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when the enterprise cooperation rating model of the same industry class is trained according to the training data of the enterprise cooperation rating model of the same industry class, marking the training data according to the enterprise index data, used for marking the training data, of the sample enterprise in the same industry class so as to obtain enterprise cooperation rating marking data corresponding to the training data; performing associated storage on the training data and enterprise cooperation grade marking data corresponding to the training data to obtain a training set of enterprise cooperation grade models of the same industry classification; and training the enterprise cooperation scoring model of the same industry classification according to the training set of the enterprise cooperation scoring model of the same industry classification. The enterprise index data used for marking the training data can be the number of the social security paid carelessly in the annual report of the enterprise. Therefore, the training data are labeled through the enterprise index data used for labeling the training data of the sample enterprises in the same industry classification, the enterprise cooperation scoring labeling data corresponding to the training data can be accurately obtained, in addition, the training data and the enterprise cooperation scoring labeling data corresponding to the training data are stored in a correlation mode, the training set of the enterprise cooperation scoring model in the same industry classification can be accurately obtained, and the enterprise cooperation scoring model in the same industry classification can be effectively trained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, when the training data is labeled according to enterprise index data used for labeling the training data of sample enterprises in the same industry classification, logarithm is taken of the enterprise index data used for labeling the training data of the sample enterprises in the same industry classification to obtain a logarithm result, and the training data is labeled according to the logarithm result to obtain enterprise cooperation grade labeling data corresponding to the training data. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In one particular example, enterprise data is collected for a sample enterprise bulletin. The enterprise data of the exposure may include business data, judicial data, intellectual property data, and the like. The collection mode is mainly crawled from the network. Then, the data of the character strings, the numerical values and the like are uniformly converted into data of the numerical value type and spliced into vector representation. And then classifying the enterprises according to the industry, and carrying out descriptive statistics one by one to obtain various enterprise indexes in the industry. Specifically, all enterprises are classified into 20 categories such as financial industry, manufacturing industry and the like according to the classification system of national economy industry. And counting the mean value and the standard deviation of each enterprise index according to the industry, and normalizing by using the mean value and the standard deviation. Finally, the training samples are labeled. Specifically, training data of various industries are obtained by using hierarchical sampling, and then a machine is used for labeling. Compared with pure manual labeling, the method reduces the workload, and can obtain better labeling quality than pure machine labeling. The specific marking method is characterized in that a regression model is trained by taking the number of social security payments disclosed in the annual report of the enterprise as a standard. Commonly used regression models include: linear regression, cable regression, tree regression, and the like. In this embodiment, a tree regression model is employed. And correcting the model prediction result, including the processes of taking the upper limit of the logarithm compression value and manually checking. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when the enterprise cooperation scoring model of the same industry class is trained according to the training set of the enterprise cooperation scoring model of the same industry class, performing enterprise cooperation scoring on sample enterprises in the same industry class according to training data of the enterprise cooperation scoring model of the same industry class in the training set through the enterprise cooperation scoring model of the same industry class to be trained so as to obtain enterprise cooperation scoring prediction data corresponding to the training data; and training the enterprise cooperation scoring model of the same industry classification according to the enterprise cooperation scoring marking data and the enterprise cooperation scoring prediction data corresponding to the training data. The enterprise cooperation score prediction data can be prediction scores of enterprise cooperation scores, and the enterprise cooperation score annotation data can be annotation scores of the enterprise cooperation scores. Therefore, the enterprise cooperation scoring model of the same industry classification can be effectively trained through the enterprise cooperation scoring marking data and the enterprise cooperation scoring prediction data corresponding to the training data. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, when an enterprise cooperation scoring model of the same industry classification is trained according to enterprise cooperation scoring annotation data and enterprise cooperation scoring prediction data corresponding to the training data, a difference value between the enterprise cooperation scoring annotation data and the enterprise cooperation scoring prediction data is determined through a target loss function; and adjusting the model parameters of the enterprise cooperation scoring model of the same industry classification based on the difference value. The target loss function can be any loss function such as a cross entropy loss function, a softmax loss function, an L1 loss function, and an L2 loss function. When the model parameters of the enterprise cooperation scoring model of the same industry class are adjusted, a back propagation algorithm or a random gradient descent algorithm can be adopted to adjust the model parameters of the enterprise cooperation scoring model of the same industry class. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, the currently obtained enterprise cooperation grade prediction data is evaluated by determining a difference value between the enterprise cooperation grade marking data and the enterprise cooperation grade prediction data, so as to serve as a basis for subsequently training an enterprise cooperation grade model of the same industry classification. Specifically, the difference value may be transmitted back to the enterprise cooperation scoring model of the same industry class, so as to iteratively train the enterprise cooperation scoring model of the same industry class. The training of the enterprise cooperation scoring model of the same industry class is an iterative process, and this embodiment describes only one training process, but it should be understood by those skilled in the art that this training mode may be adopted for each training of the enterprise cooperation scoring model of the same industry class until the training of the enterprise cooperation scoring model of the same industry class is completed. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, the method further comprises: and evaluating the training effect of the enterprise cooperation scoring model of the same industry classification according to the enterprise characteristic data of the winning bid enterprises of the same industry classification. Therefore, the training effect of the enterprise cooperation scoring model of the same industry classification can be effectively evaluated through the enterprise characteristic data of the winning-bid enterprises of the same industry classification. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In one particular example, the bid information of the post is collected to verify the effectiveness of the enterprise collaborative scoring model. The bidding information discloses the list of candidate businesses which are successfully bid, and the list is derived by technical experts and economic experts together. The enterprises selected by the experts should have similar strength levels, that is, similar enterprise cooperation score scores, so that the effect of the enterprise cooperation score model can be effectively evaluated through the normalized enterprise characteristic data of the candidate enterprises. And analyzing the sample with poor performance, and continuously iterating by adjusting the training data and the model parameters until the model meets the engineering requirement level. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In step S105, performing enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model, so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

In some optional embodiments, before performing enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model, the method further includes: and when the enterprise to be scored is subjected to enterprise cooperation scoring through the enterprise cooperation scoring model and the normalized enterprise characteristic data, the enterprise to be scored is subjected to enterprise cooperation scoring through the enterprise cooperation scoring model according to the normalized enterprise characteristic data so as to obtain an enterprise cooperation scoring result of the enterprise to be scored. The industry classification result of the enterprise to be scored can be service industry, food industry, tobacco and wine industry and the like. Therefore, the enterprise characteristic data of the enterprise to be scored is normalized according to the industry classification result of the enterprise to be scored, the normalized enterprise characteristic data can be effectively obtained, in addition, the enterprise cooperation scoring is carried out on the enterprise to be scored according to the normalized enterprise characteristic data, and the enterprise cooperation scoring result of the enterprise to be scored can be effectively obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when the enterprise characteristic data of the enterprise to be evaluated is normalized according to the industry classification result of the enterprise to be evaluated, the mean value and the standard deviation corresponding to each item of enterprise index data in the enterprise characteristic data of the enterprise to be evaluated are determined according to the industry classification result of the enterprise to be evaluated; and normalizing the enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the mean value and the standard deviation corresponding to the enterprise index data in the enterprise characteristic data of the enterprise to be scored. Therefore, various enterprise index data in the enterprise characteristic data of the enterprise to be scored are normalized through the mean value and the standard deviation corresponding to the various enterprise index data in the enterprise characteristic data of the enterprise to be scored, and the normalized enterprise characteristic data can be effectively obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, when the enterprise characteristic data of the enterprise to be evaluated is normalized according to the industry classification result of the enterprise to be evaluated, the mean value and the standard deviation corresponding to each item of enterprise index data in the enterprise characteristic data of the enterprise to be evaluated are determined according to the industry classification result of the enterprise to be evaluated; and normalizing the enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the mean value and the standard deviation corresponding to the enterprise index data in the enterprise characteristic data of the enterprise to be scored so as to obtain the normalized enterprise characteristic data. Therefore, the enterprise index data in the enterprise characteristic data of the enterprise to be scored can be accurately normalized through the mean value and the standard deviation corresponding to the enterprise index data in the enterprise characteristic data of the enterprise to be scored, and the normalized enterprise characteristic data can be accurately obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, the enterprise index data in the enterprise characteristic data of the enterprise to be scored may be enterprise name characterization data, enterprise operation range characterization data, enterprise industry and commerce characterization data, enterprise judicial dispute characterization data, enterprise operation range characterization data, enterprise intellectual property characterization data, and enterprise operation condition characterization data. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, when a mean value and a standard deviation corresponding to each item of enterprise index data in the enterprise feature data of the enterprise to be scored are determined according to the industry classification result of the enterprise to be scored, the mean value and the standard deviation of each item of enterprise index corresponding to the industry classification result of the enterprise to be scored are determined; and determining the mean value and the standard deviation corresponding to each item of enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the mean value and the standard deviation corresponding to each item of enterprise index corresponding to the industry classification result of the enterprise to be scored. The enterprise index can be an enterprise name, an enterprise operation range, an enterprise industry and commerce, an enterprise judicial dispute, an enterprise operation range, an enterprise intellectual property right and an enterprise operation condition. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, after performing enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model, the method further includes: according to a preset enterprise cooperation score correction rule, correcting the enterprise cooperation score result of the enterprise to be scored so as to obtain a corrected enterprise cooperation score result of the enterprise to be scored; and determining the corrected enterprise cooperation scoring result of the enterprise to be scored as the final enterprise cooperation scoring result of the enterprise to be scored. Therefore, the enterprise cooperation scoring result of the enterprise to be scored is revised through the preset enterprise cooperation scoring revision rule, and the final enterprise cooperation scoring result of the enterprise to be scored can be accurately obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, the preset enterprise cooperation score correction rules include a strong enterprise cooperation score correction rule and a weak enterprise cooperation score correction rule. The strong enterprise cooperation score correction rules comprise financial blacklists, distrusted executives, serious violations, bankruptcy cases and the like, and the weak enterprise cooperation score correction rules comprise debt notices and the like. And when the preset enterprise cooperation score correction rule is an enterprise cooperation score correction strong rule, determining a final enterprise cooperation score result of the enterprise to be scored according to the enterprise cooperation score correction strong rule directly. For example, if the enterprise to be scored is on a financial blacklist, the final enterprise cooperation scoring result of the enterprise to be scored is 59 points. And when the preset enterprise cooperation grade correction rule is an enterprise cooperation grade correction weak rule, determining a final enterprise cooperation grade result of the enterprise to be graded according to the score and the weight of the enterprise cooperation grade correction weak rule and the enterprise cooperation grade result and the weight of the enterprise to be graded. Since the enterprise may choose not to disclose part of the data when disclosing the annual newspaper, the part of the data is very sparse, and the machine model cannot effectively learn the relevance of the part of the data and the enterprise cooperation score. In order to make up for the deficiency, enterprise cooperation score correction rules are introduced to the part of the characteristics for correction. Compared with a rule system completely depending on experts, the method for modeling the dimension with sufficient information quantity by using machine learning only needs to introduce the enterprise cooperation score correction rule into the sparse part of the dimension. And then, the model score is corrected through an enterprise cooperation score correction rule, so that the score precision is improved, and a final score result is obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In some optional embodiments, the enterprise data of the enterprise to be scored selects public enterprise data for the enterprise to be scored; the method further comprises the following steps: forecasting enterprise data which are selected by the enterprise to be scored and are not disclosed through an enterprise data estimation model; and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise data which is selected not to be disclosed by the enterprise to be scored and the enterprise data which is selected to be disclosed by the enterprise to be scored by the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored. Therefore, the enterprise data which are selected and not disclosed by the enterprise to be scored are estimated through the enterprise data estimation model, and the enterprise data which are selected and not disclosed by the enterprise to be scored can be accurately obtained. In addition, enterprise cooperation scoring is carried out on the enterprise to be scored according to the enterprise data which are selected and not disclosed by the enterprise to be scored and the enterprise data which are selected and disclosed by the enterprise to be scored through the enterprise cooperation scoring model, and an enterprise cooperation scoring result of the enterprise to be scored can be further accurately obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a particular example, the enterprise data estimation model may be any suitable neural network model that may enable feature extraction or target object detection, including but not limited to convolutional neural network models, reinforcement learning neural network models, generative network models in antagonistic neural network models, and so forth. The specific structure of the neural network model can be set by those skilled in the art according to actual requirements, such as the number of convolutional layers, the size of convolutional core, the number of channels, and so on. When enterprise data which are selected and not disclosed by the enterprise to be scored are estimated through an enterprise data estimation model, the enterprise data which are selected and not disclosed by the enterprise to be scored are estimated through the enterprise data estimation model according to the enterprise data which are selected and disclosed by the enterprise to be scored, and the enterprise data which are selected and not disclosed by the enterprise to be scored can be accurately obtained. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, in order to further reduce the number of the enterprise cooperation score correction rules, the model may be used to estimate the enterprise data that is not disclosed by the enterprise, such as the number of social security payments, business situation, and the like. On one hand, the data which are not disclosed by the enterprise are filled through machine learning, on the other hand, the data are utilized to model the enterprise cooperation score, the process is continuously iterated to improve the model estimation precision, and the number of the enterprise cooperation score correction rules is gradually reduced. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

In a specific example, as shown in fig. 1B, the enterprise cooperation scoring process provided by this embodiment is as follows: the method comprises the steps of firstly collecting enterprise data of sample enterprise selective publicity, then processing the enterprise data of the sample enterprise selective publicity to obtain normalized enterprise characteristic data of the sample enterprise, then classifying the industries to which the sample enterprises belong according to the normalized enterprise characteristic data of the sample enterprise, then labeling the normalized enterprise characteristic data of the sample enterprise according to the industries to obtain labeled data, then training a model according to the labeled data to obtain model files of each industry, and then performing model effect verification according to the model files of each industry to obtain a final model. And (3) scoring the model of the enterprise to be scored through the model, correcting the model score by utilizing an enterprise cooperation score correction rule (expert rule), and comprehensively obtaining a scoring result. The enterprise cooperation scoring model can be applied to similar enterprise retrieval and other scenes in the industry. In addition, during modeling, a relation model is established for enterprise selection public data and enterprise cooperation scores mainly in a mode of statistics and machine learning, and the method is different from a traditional rule-based expert system, and can remarkably reduce the number and complexity of enterprise cooperation score correction rules. It should be understood that the above description is only exemplary, and the present embodiment is not limited thereto.

By the enterprise cooperation scoring method provided by the embodiment, enterprise data of an enterprise to be scored is obtained, enterprise characteristic data of the enterprise to be scored is determined according to the enterprise data, the enterprise to be scored is subjected to industry classification according to the enterprise characteristic data to obtain an industry classification result of the enterprise to be scored, an enterprise cooperation scoring model corresponding to the enterprise to be scored is determined in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored, enterprise cooperation scoring is performed on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model to obtain an enterprise cooperation scoring result of the enterprise to be scored, on one hand, a relation model of public enterprise data and enterprise cooperation scoring is established in a machine learning mode, and the expert workload required by modeling is reduced, the engineering period is shortened, the migration and maintenance cost is reduced, on the other hand, the enterprise feature crossing is automatically completed by accessing more enterprise features and with the help of a machine learning algorithm, the accuracy of enterprise cooperation scoring is improved by fully utilizing the public enterprise data, the enterprise cooperation scoring can be simply, conveniently and accurately obtained, and then the safety of cooperation between enterprises is described.

The enterprise collaboration scoring method provided by the present embodiment may be performed by any suitable device having data processing capabilities, including but not limited to: a camera, a terminal, a mobile terminal, a PC, a server, an in-vehicle device, an entertainment device, an advertising device, a Personal Digital Assistant (PDA), a tablet computer, a notebook computer, a handheld game console, smart glasses, a smart watch, a wearable device, a virtual display device, a display enhancement device, or the like.

Referring to fig. 2, a schematic structural diagram of an enterprise cooperation scoring device in the second embodiment is shown.

The enterprise cooperation scoring device provided by the embodiment comprises: an obtaining module 201, configured to obtain enterprise data of an enterprise to be scored; a first determining module 202, configured to determine, according to the enterprise data, enterprise feature data of the enterprise to be scored; the industry classification module 203 is used for performing industry classification on the enterprise to be scored according to the enterprise characteristic data so as to obtain an industry classification result of the enterprise to be scored; a second determining module 204, configured to determine, according to the industry classification result of the enterprise to be scored, an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications; the first scoring module 205 is configured to perform enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model, so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

Optionally, the first determining module 202 is specifically configured to: performing data type conversion on the enterprise data to obtain the enterprise data after data type conversion; and splicing the enterprise data after the data type conversion to obtain enterprise characteristic data of the enterprise to be scored.

Optionally, before the first scoring module 205, the apparatus further includes: a normalization module, configured to normalize the enterprise feature data of the enterprise to be scored according to the industry classification result of the enterprise to be scored, to obtain normalized enterprise feature data, where the first scoring module 205 is specifically configured to: and carrying out enterprise cooperation scoring on the enterprise to be scored according to the normalized enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

Optionally, the enterprise characteristic data includes enterprise name characterization data and enterprise operation range characterization data; the industry classification module 203 is specifically configured to: and carrying out industry classification on the enterprise to be scored according to the enterprise name characterization data and the enterprise operation range characterization data through an industry classification model to which the enterprise belongs so as to obtain an industry classification result of the enterprise to be scored.

Optionally, the normalization module is specifically configured to: determining a mean value and a standard deviation corresponding to each item of enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the industry classification result of the enterprise to be scored; and normalizing the enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the mean value and the standard deviation corresponding to the enterprise index data in the enterprise characteristic data of the enterprise to be scored.

Optionally, before the second determining module 204, the apparatus further includes: the third determining module is used for determining enterprise characteristic data of the sample enterprise according to the acquired enterprise data of the sample enterprise; the classification module is used for carrying out industry classification on the sample enterprise according to the enterprise characteristic data of the sample enterprise so as to obtain an industry classification result of the sample enterprise; the fourth determination module is used for determining that the enterprise characteristic data of the sample enterprise in the same industry classification is a training sample of an enterprise cooperation scoring model of the same industry classification; and the training module is used for training the enterprise cooperation scoring model of the same industry classification according to the training sample of the enterprise cooperation scoring model of the same industry classification.

Optionally, the apparatus further comprises: the statistical module is used for carrying out descriptive statistics on the enterprise characteristic data of the sample enterprises in the same industry classification so as to obtain each enterprise index of the same industry classification; a fifth determining module, configured to determine a mean value and a standard deviation of each enterprise index of the same industry class according to each enterprise index data in the enterprise feature data of the sample enterprise in the same industry class; the normalization module is used for normalizing the enterprise index data in the enterprise feature data of the sample enterprises in the same industry classification according to the mean value and the standard deviation of the enterprise indexes in the same industry classification so as to obtain the normalized enterprise feature data of the sample enterprises in the same industry classification; the fourth determining module is specifically configured to: and determining the normalized enterprise feature data of the sample enterprise in the same industry classification as a training sample of the enterprise cooperation scoring model of the same industry classification.

Optionally, the training module comprises: the sampling sub-module is used for sampling the training samples of the enterprise cooperation scoring model of the same industry class in a layered sampling mode to obtain the training data of the enterprise cooperation scoring model of the same industry class; and the training submodule is used for training the enterprise cooperation scoring model of the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification.

Optionally, the training submodule includes: the marking unit is used for marking the training data according to enterprise index data, used for marking the training data, of the sample enterprises in the same industry classification so as to obtain enterprise cooperation grade marking data corresponding to the training data; the storage unit is used for performing associated storage on the training data and enterprise cooperation grade marking data corresponding to the training data so as to obtain a training set of enterprise cooperation grade models of the same industry classification; and the training unit is used for training the enterprise cooperation scoring model of the same industry classification according to the training set of the enterprise cooperation scoring model of the same industry classification.

Optionally, the training unit is specifically configured to: carrying out enterprise cooperation scoring on sample enterprises in the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification in the training set through the enterprise cooperation scoring model of the same industry classification to be trained so as to obtain enterprise cooperation scoring prediction data corresponding to the training data; and training the enterprise cooperation scoring model of the same industry classification according to the enterprise cooperation scoring marking data and the enterprise cooperation scoring prediction data corresponding to the training data.

Optionally, the apparatus further comprises: and the evaluation module is used for evaluating the training effect of the enterprise cooperation scoring model of the same industry classification according to the enterprise characteristic data of the winning-bid enterprises of the same industry classification.

Optionally, after the first scoring module 205, the apparatus further comprises: the correction module is used for correcting the enterprise cooperation scoring result of the enterprise to be scored according to a preset enterprise cooperation scoring correction rule so as to obtain a corrected enterprise cooperation scoring result of the enterprise to be scored; and the sixth determining module is used for determining that the corrected enterprise cooperation scoring result of the enterprise to be scored is the final enterprise cooperation scoring result of the enterprise to be scored.

Optionally, the enterprise data of the enterprise to be scored selects public enterprise data for the enterprise to be scored; the device further comprises: the estimation module is used for predicting the enterprise data which is selected by the enterprise to be scored and is not disclosed through an enterprise data estimation model; and the second scoring module is used for carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise data which is selected by the enterprise to be scored and not disclosed and the enterprise data which is selected by the enterprise to be scored and disclosed by the enterprise to be scored through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

The enterprise cooperation scoring device provided in this embodiment is used to implement the corresponding enterprise cooperation scoring method in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.

Referring to fig. 3, a schematic structural diagram of an electronic device according to a third embodiment of the present invention is shown, and the specific embodiment of the present invention does not limit the specific implementation of the electronic device.

As shown in fig. 3, the electronic device may include: a processor (processor)302, a communication Interface 304, a memory 306, and a communication bus 308.

Wherein:

the processor 302, communication interface 304, and memory 306 communicate with each other via a communication bus 308.

A communication interface 304 for communicating with other electronic devices or servers.

The processor 302 is configured to execute the program 310, and may specifically execute the relevant steps in the above-described embodiment of the enterprise cooperation scoring method.

In particular, program 310 may include program code comprising computer operating instructions.

The processor 302 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The intelligent device comprises one or more processors which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

And a memory 306 for storing a program 310. Memory 306 may comprise high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 310 may specifically be configured to cause the processor 302 to perform the following operations: acquiring enterprise data of an enterprise to be scored; determining enterprise characteristic data of the enterprise to be scored according to the enterprise data; according to the enterprise characteristic data, carrying out industry classification on the enterprise to be scored so as to obtain an industry classification result of the enterprise to be scored; determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored; and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

In an alternative embodiment, the program 310 is further configured to enable the processor 302, when determining the enterprise characteristic data of the enterprise to be scored according to the enterprise data, to perform data type conversion on the enterprise data to obtain the enterprise data after data type conversion; and splicing the enterprise data after the data type conversion to obtain enterprise characteristic data of the enterprise to be scored.

In an optional implementation manner, the program 310 is further configured to enable the processor 302, before performing enterprise cooperation scoring on the enterprise to be scored according to the enterprise feature data through the enterprise cooperation scoring model, normalize the enterprise feature data of the enterprise to be scored according to the industry classification result of the enterprise to be scored to obtain normalized enterprise feature data, and when performing enterprise cooperation scoring on the enterprise to be scored according to the enterprise feature data through the enterprise cooperation scoring model, perform enterprise cooperation scoring on the enterprise to be scored according to the normalized enterprise feature data through the enterprise cooperation scoring model to obtain an enterprise cooperation scoring result of the enterprise to be scored.

In an alternative embodiment, the enterprise characteristic data comprises enterprise name characterization data and enterprise business scope characterization data; the program 310 is further configured to enable the processor 302 to perform industry classification on the to-be-scored enterprise according to the enterprise name characterization data and the enterprise operation range characterization data through an industry classification model to which the enterprise belongs when performing industry classification on the to-be-scored enterprise according to the enterprise feature data, so as to obtain an industry classification result of the to-be-scored enterprise.

In an optional implementation manner, the program 310 is further configured to enable the processor 302 to determine, according to the industry classification result of the to-be-evaluated enterprise, a mean value and a standard deviation corresponding to each item of enterprise index data in the enterprise feature data of the to-be-evaluated enterprise when the enterprise feature data of the to-be-evaluated enterprise is normalized according to the industry classification result of the to-be-evaluated enterprise; and normalizing the enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the mean value and the standard deviation corresponding to the enterprise index data in the enterprise characteristic data of the enterprise to be scored.

In an optional implementation manner, the program 310 is further configured to enable the processor 302 to determine enterprise feature data of the sample enterprise according to the acquired enterprise data of the sample enterprise before determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored; carrying out industry classification on the sample enterprise according to the enterprise characteristic data of the sample enterprise to obtain an industry classification result of the sample enterprise; determining the enterprise characteristic data of the sample enterprise in the same industry classification as a training sample of an enterprise cooperation scoring model of the same industry classification; and training the enterprise cooperation scoring model of the same industry classification according to the training sample of the enterprise cooperation scoring model of the same industry classification.

In an alternative embodiment, the program 310 is further configured to enable the processor 302 to perform descriptive statistics on the enterprise characteristic data of the sample enterprise in the same industry class to obtain enterprise indexes of the same industry class; determining the mean value and the standard deviation of each enterprise index of the same industry classification according to each enterprise index data in the enterprise feature data of the sample enterprise in the same industry classification; normalizing each enterprise index data in the enterprise feature data of the sample enterprises in the same industry classification according to the mean value and the standard deviation of each enterprise index in the same industry classification to obtain normalized enterprise feature data of the sample enterprises in the same industry classification; when the enterprise characteristic data of the sample enterprise in the same industry classification is determined to be a training sample of the enterprise cooperation scoring model of the same industry classification, the normalized enterprise characteristic data of the sample enterprise in the same industry classification is determined to be a training sample of the enterprise cooperation scoring model of the same industry classification.

In an alternative embodiment, the program 310 is further configured to cause the processor 302 to sample the training samples of the enterprise cooperation scoring model of the same industry class in a hierarchical sampling manner when training the enterprise cooperation scoring model of the same industry class according to the training samples of the enterprise cooperation scoring model of the same industry class to obtain training data of the enterprise cooperation scoring model of the same industry class; and training the enterprise cooperation scoring model of the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification.

In an alternative embodiment, the program 310 is further configured to enable the processor 302, when training the enterprise cooperation scoring model of the same industry class according to the training data of the enterprise cooperation scoring model of the same industry class, label the training data according to the enterprise index data, used for labeling the training data, of the sample enterprise in the same industry class, so as to obtain enterprise cooperation scoring labeling data corresponding to the training data; performing associated storage on the training data and enterprise cooperation grade marking data corresponding to the training data to obtain a training set of enterprise cooperation grade models of the same industry classification; and training the enterprise cooperation scoring model of the same industry classification according to the training set of the enterprise cooperation scoring model of the same industry classification.

In an alternative embodiment, the program 310 is further configured to enable the processor 302, when training the enterprise cooperation scoring model of the same industry class according to the training set of the enterprise cooperation scoring model of the same industry class, perform enterprise cooperation scoring on sample enterprises in the same industry class according to training data of the enterprise cooperation scoring model of the same industry class in the training set through the enterprise cooperation scoring model of the same industry class to be trained, so as to obtain enterprise cooperation scoring prediction data corresponding to the training data; and training the enterprise cooperation scoring model of the same industry classification according to the enterprise cooperation scoring marking data and the enterprise cooperation scoring prediction data corresponding to the training data.

In an alternative embodiment, program 310 is further configured to cause processor 302 to evaluate a training effect of the business cooperation scoring model for the same industry class based on the business feature data of the winning business for the same industry class.

In an optional implementation manner, the program 310 is further configured to enable the processor 302 to modify the enterprise cooperation scoring result of the enterprise to be scored according to a preset enterprise cooperation scoring modification rule after performing enterprise cooperation scoring on the enterprise to be scored according to the enterprise feature data through the enterprise cooperation scoring model, so as to obtain a modified enterprise cooperation scoring result of the enterprise to be scored; and determining the corrected enterprise cooperation scoring result of the enterprise to be scored as the final enterprise cooperation scoring result of the enterprise to be scored.

In an alternative embodiment, the enterprise data of the enterprise to be scored selects the enterprise data disclosed for the enterprise to be scored, and the program 310 is further configured to cause the processor 302 to predict, through an enterprise data estimation model, that the enterprise to be scored selects the enterprise data not disclosed; and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise data which is selected not to be disclosed by the enterprise to be scored and the enterprise data which is selected to be disclosed by the enterprise to be scored by the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

For specific implementation of each step in the program 310, reference may be made to corresponding steps and corresponding descriptions in units in the above embodiments of the enterprise cooperation scoring method, which are not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.

Through the electronic equipment of the embodiment, enterprise data of an enterprise to be scored is obtained, enterprise characteristic data of the enterprise to be scored is determined according to the enterprise data, the enterprise to be scored is subjected to industry classification according to the enterprise characteristic data so as to obtain an industry classification result of the enterprise to be scored, an enterprise cooperation scoring model corresponding to the enterprise to be scored is determined in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored, enterprise cooperation scoring is performed on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain the enterprise cooperation scoring result of the enterprise to be scored, on one hand, a relation model of public enterprise data and enterprise cooperation scoring is established in a machine learning mode, and the expert workload required by modeling is reduced, the engineering period is shortened, the migration and maintenance cost is reduced, on the other hand, the enterprise feature crossing is automatically completed by accessing more enterprise features and with the help of a machine learning algorithm, the accuracy of enterprise cooperation scoring is improved by fully utilizing the public enterprise data, the enterprise cooperation scoring can be simply, conveniently and accurately obtained, and then the safety of cooperation between enterprises is described.

It should be noted that, according to the implementation requirement, each component/step described in the embodiment of the present invention may be divided into more components/steps, and two or more components/steps or partial operations of the components/steps may also be combined into a new component/step to achieve the purpose of the embodiment of the present invention.

The above-described method according to an embodiment of the present invention may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, a RAM, a floppy disk, a hard disk, or a magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein may be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware such as an ASIC or FPGA. It will be appreciated that the computer, processor, microprocessor controller, or programmable hardware includes memory components (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the enterprise collaboration scoring methods described herein. Further, when a general-purpose computer accesses code for implementing the enterprise collaboration scoring method illustrated herein, execution of the code transforms the general-purpose computer into a special-purpose computer for performing the enterprise collaboration scoring method illustrated herein.

Those of ordinary skill in the art will appreciate that the various illustrative elements and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

The above embodiments are only for illustrating the embodiments of the present invention and not for limiting the embodiments of the present invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present invention, so that all equivalent technical solutions also belong to the scope of the embodiments of the present invention, and the scope of patent protection of the embodiments of the present invention should be defined by the claims.

Claims

1. An enterprise collaboration scoring method, the method comprising:

acquiring enterprise data of an enterprise to be scored;

determining enterprise characteristic data of the enterprise to be scored according to the enterprise data;

according to the enterprise characteristic data, carrying out industry classification on the enterprise to be scored so as to obtain an industry classification result of the enterprise to be scored;

determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored;

and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

2. The method according to claim 1, wherein the determining the enterprise characteristic data of the enterprise to be scored according to the enterprise data comprises:

performing data type conversion on the enterprise data to obtain the enterprise data after data type conversion;

and splicing the enterprise data after the data type conversion to obtain enterprise characteristic data of the enterprise to be scored.

3. The method according to claim 1, wherein before scoring the business to be scored according to the business feature data by the business cooperation scoring model, the method further comprises:

normalizing the enterprise characteristic data of the enterprise to be evaluated according to the industry classification result of the enterprise to be evaluated to obtain normalized enterprise characteristic data;

the enterprise cooperation scoring of the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model comprises the following steps:

and carrying out enterprise cooperation scoring on the enterprise to be scored according to the normalized enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

4. The enterprise collaboration scoring method of claim 1, wherein the enterprise trait data comprises enterprise name characterization data and enterprise business range characterization data;

and the industry classification of the enterprises to be scored according to the enterprise characteristic data comprises the following steps:

and carrying out industry classification on the enterprise to be scored according to the enterprise name characterization data and the enterprise operation range characterization data through an industry classification model to which the enterprise belongs so as to obtain an industry classification result of the enterprise to be scored.

5. The enterprise cooperation scoring method according to claim 3, wherein the normalizing the enterprise feature data of the enterprise to be scored according to the industry classification result of the enterprise to be scored comprises:

determining a mean value and a standard deviation corresponding to each item of enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the industry classification result of the enterprise to be scored;

and normalizing the enterprise index data in the enterprise characteristic data of the enterprise to be scored according to the mean value and the standard deviation corresponding to the enterprise index data in the enterprise characteristic data of the enterprise to be scored.

6. The enterprise cooperation scoring method according to claim 1, wherein before determining the enterprise cooperation scoring model corresponding to the enterprise to be scored in the enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored, the method further comprises:

determining enterprise characteristic data of the sample enterprise according to the acquired enterprise data of the sample enterprise;

carrying out industry classification on the sample enterprise according to the enterprise characteristic data of the sample enterprise to obtain an industry classification result of the sample enterprise;

determining the enterprise characteristic data of the sample enterprise in the same industry classification as a training sample of an enterprise cooperation scoring model of the same industry classification;

and training the enterprise cooperation scoring model of the same industry classification according to the training sample of the enterprise cooperation scoring model of the same industry classification.

7. The enterprise collaboration scoring method of claim 6, further comprising:

carrying out descriptive statistics on enterprise characteristic data of the sample enterprises in the same industry classification to obtain various enterprise indexes of the same industry classification;

determining the mean value and the standard deviation of each enterprise index of the same industry classification according to each enterprise index data in the enterprise feature data of the sample enterprise in the same industry classification;

normalizing each enterprise index data in the enterprise feature data of the sample enterprises in the same industry classification according to the mean value and the standard deviation of each enterprise index in the same industry classification to obtain normalized enterprise feature data of the sample enterprises in the same industry classification;

the determining that the enterprise characteristic data of the sample enterprise in the same industry classification is a training sample of an enterprise cooperation scoring model of the same industry classification comprises:

and determining the normalized enterprise feature data of the sample enterprise in the same industry classification as a training sample of the enterprise cooperation scoring model of the same industry classification.

8. The enterprise collaboration scoring method of claim 6,

the training of the enterprise cooperation scoring model of the same industry classification according to the training sample of the enterprise cooperation scoring model of the same industry classification comprises the following steps:

sampling training samples of the enterprise cooperation scoring model of the same industry class in a layered sampling mode to obtain training data of the enterprise cooperation scoring model of the same industry class;

and training the enterprise cooperation scoring model of the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification.

9. The enterprise collaboration scoring method of claim 8,

the training of the enterprise cooperation scoring model of the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification comprises the following steps:

marking the training data according to enterprise index data, used for marking the training data, of sample enterprises in the same industry classification to obtain enterprise cooperation grade marking data corresponding to the training data;

performing associated storage on the training data and enterprise cooperation grade marking data corresponding to the training data to obtain a training set of enterprise cooperation grade models of the same industry classification;

and training the enterprise cooperation scoring model of the same industry classification according to the training set of the enterprise cooperation scoring model of the same industry classification.

10. The enterprise collaboration scoring method of claim 9,

the training of the enterprise cooperation scoring model of the same industry classification according to the training set of the enterprise cooperation scoring model of the same industry classification comprises the following steps:

carrying out enterprise cooperation scoring on sample enterprises in the same industry classification according to the training data of the enterprise cooperation scoring model of the same industry classification in the training set through the enterprise cooperation scoring model of the same industry classification to be trained so as to obtain enterprise cooperation scoring prediction data corresponding to the training data;

and training the enterprise cooperation scoring model of the same industry classification according to the enterprise cooperation scoring marking data and the enterprise cooperation scoring prediction data corresponding to the training data.

11. The enterprise collaboration scoring method of claim 10, further comprising:

and evaluating the training effect of the enterprise cooperation scoring model of the same industry classification according to the enterprise characteristic data of the winning bid enterprises of the same industry classification.

12. The method of claim 1, wherein after the enterprise cooperation scoring is performed on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model, the method further comprises:

according to a preset enterprise cooperation score correction rule, correcting the enterprise cooperation score result of the enterprise to be scored so as to obtain a corrected enterprise cooperation score result of the enterprise to be scored;

and determining the corrected enterprise cooperation scoring result of the enterprise to be scored as the final enterprise cooperation scoring result of the enterprise to be scored.

13. The enterprise collaboration scoring method according to claim 1, wherein the enterprise data of the enterprise to be scored selects public enterprise data for the enterprise to be scored;

the method further comprises the following steps:

forecasting enterprise data which are selected by the enterprise to be scored and are not disclosed through an enterprise data estimation model;

and carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise data which is selected not to be disclosed by the enterprise to be scored and the enterprise data which is selected to be disclosed by the enterprise to be scored by the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

14. An enterprise collaboration scoring apparatus, the apparatus comprising:

the acquisition module is used for acquiring enterprise data of the enterprise to be evaluated;

the first determination module is used for determining enterprise characteristic data of the enterprise to be scored according to the enterprise data;

the industry classification module is used for performing industry classification on the enterprise to be scored according to the enterprise characteristic data so as to obtain an industry classification result of the enterprise to be scored;

the second determination module is used for determining an enterprise cooperation scoring model corresponding to the enterprise to be scored in enterprise cooperation scoring models of a plurality of industry classifications according to the industry classification result of the enterprise to be scored;

and the first scoring module is used for carrying out enterprise cooperation scoring on the enterprise to be scored according to the enterprise characteristic data through the enterprise cooperation scoring model so as to obtain an enterprise cooperation scoring result of the enterprise to be scored.

15. An electronic device, characterized in that the device comprises:

the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is configured to store at least one executable instruction, which causes the processor to perform operations corresponding to the enterprise cooperation scoring method according to any one of claims 1-13.

16. A computer storage medium, having stored thereon a computer program which, when executed by a processor, implements an enterprise collaboration scoring method as recited in any one of claims 1-13.