Dynamic matching scoring method and system, electronic equipment and storage medium

Abstract

The invention relates to the technical field of enterprise evaluation, in particular to a dynamic matching scoring method and system, electronic equipment and a storage medium. The method comprises the steps of obtaining operation data of a target enterprise and determining an industry type of the target enterprise, wherein the operation data comprises index data of a plurality of operation indexes; a multi-level rule tree corresponding to the industry type is called, a root node and each middle node in the multi-level rule tree correspond to an initial score and a preset score rule, and each leaf node of the multi-level rule tree corresponds to an operating index; matching the operation data with leaf nodes of the multi-level rule tree to obtain index data corresponding to each leaf node in the multi-level rule tree; and based on the index data corresponding to each leaf node and the initial scores and preset score rules corresponding to the root node and each intermediate node, performing iterative calculation from the leaf nodes to the root nodes of the multi-level rule tree to obtain a final score of the target enterprise. According to the invention, accurate and comprehensive evaluation of the target enterprise can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of enterprise evaluation, and in particular to a dynamic matching scoring method, system, electronic device and storage medium. Background Art

[0002] In the era of big data, the value of public data of enterprises has become increasingly prominent, especially in the fields of enterprise risk control and credit approval. Using these data for comprehensive evaluation has become a routine operation in the industry. The relevant data analysis and scoring system is mainly based on the financial statements, operating data and other information provided by the enterprise, and quantitative analysis is performed through preset algorithms and models to obtain the credit score or risk level of the enterprise.

[0003] However, relevant technologies generally adopt static rules, that is, pre-set analysis frameworks and weight distributions, which are difficult to adapt to the rapidly changing market environment and corporate conditions, resulting in low evaluation accuracy. Summary of the invention

[0004] In order to solve the problem of low enterprise evaluation accuracy in the prior art, the present application provides a dynamic matching scoring method, system, electronic device and storage medium.

[0005] In the first aspect, the present application provides a dynamic matching scoring method, which adopts the following technical solution: A dynamic matching scoring method, comprising: Acquire the operating data of the target enterprise and determine the industry type of the target enterprise, wherein the operating data includes a plurality of operating indicators and indicator data of each operating indicator; Retrieving a multi-level rule tree corresponding to the industry type, wherein a root node and each intermediate node in the multi-level rule tree correspond to an initial score and a preset scoring rule, and each leaf node of the multi-level rule tree corresponds to an operating indicator; Matching the business data with the leaf nodes of the multi-level rule tree to obtain the indicator data corresponding to each leaf node in the multi-level rule tree; Based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node, iterative calculations are performed from the leaf nodes to the root nodes of the multi-level rule tree to obtain the final score of the target enterprise.

[0006] By adopting the above technical solution, multiple operating indicators and their indicator data of the target enterprise can be obtained, so as to fully understand the operating status of the target enterprise. The design of the multi-level rule tree takes into account the characteristics and evaluation ratio standards of different lines, determines the industry type of the target enterprise and calls the corresponding multi-level rule tree to ensure customized evaluation of the target enterprise. The initial score and preset scoring rules in the multi-level rule tree can be adjusted according to actual conditions, so that the evaluation has higher flexibility and adaptability. The iterative calculation process from leaf node to root node is a process of comprehensive evaluation of various operating indicators of the target enterprise. This application realizes a comprehensive and accurate evaluation of the operating data of the target enterprise by constructing a multi-level rule tree.

[0007] In a preferred example, the present application can be further configured as follows: based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node, iterative calculation is performed from the leaf node to the root node of the multi-level rule tree to obtain the final score of the target enterprise, including: Based on the indicator data corresponding to each leaf node, comparing the indicator data of the child node of the first node with the preset scoring rule of the first node to obtain a first rule satisfaction result, where the first node is any intermediate node in the second to last level of the multi-level rule tree; adjusting the initial score of the first node based on the first rule satisfaction result to obtain the score of the first node; Based on the scores of each intermediate node in the second-to-last level of the multi-level rule tree, the scores of the child nodes of the second node are compared with the preset scoring rules of the second node to obtain the second rule satisfaction result, and the second node is any intermediate node in the third-to-last level of the multi-level rule tree; based on the second rule satisfaction result, the initial score of the second node is adjusted to obtain the score of the second node; and so on, based on the initial scores corresponding to the root node and each intermediate node and the preset scoring rules, iterative calculations are performed from the leaf nodes to the root nodes of the multi-level rule tree, and the score of the root node finally determined is used as the final score of the target enterprise.

[0008] By adopting the above technical solution, iterative calculations are performed from the leaf nodes to the root nodes of the multi-level rule tree. Based on the indicator data of each leaf node and the initial scores of the nodes at each level and the preset scoring rules, the scores of the nodes at each level are gradually adjusted and determined, and finally the final score of the target enterprise is obtained. This realizes dynamic adjustment and refined calculation of the evaluation process, ensuring the accuracy and comprehensiveness of the evaluation results.

[0009] In a preferred example, the present application can be further configured as follows: the method further includes: Constructing an initial multi-level rule tree, wherein a root node and each intermediate node in the initial multi-level rule tree correspond to a preset scoring rule, and each leaf node in the multi-level rule tree corresponds to a business indicator; Determine the importance of each intermediate node; Obtaining an initial score of the root node, assigning an initial score to each intermediate node based on the initial score of the root node and the importance of each intermediate node in the initial multi-level rule tree, and assigning an initial score to each leaf node based on the business data, to obtain a multi-level rule tree including initial scores and preset scoring rules; The sum of the initial scores of the child nodes of the target node is equal to the initial score of the target node, and the target node is the root node or any intermediate node.

[0010] By adopting the above technical solution, an initial multi-level rule tree including root nodes, intermediate nodes and leaf nodes is constructed, which provides a structural basis for subsequent evaluation. Each leaf node corresponds to an operating indicator, ensuring the comprehensiveness and pertinence of the evaluation. The preset scoring rules of the root node and each intermediate node are used as the basis for score calculation. By determining the importance of the intermediate nodes, a weight basis can be provided for score allocation to ensure the accuracy and rationality of the evaluation. Intermediate nodes with higher importance occupy a larger proportion in the evaluation process, which helps to highlight the focus of the evaluation. The initial score of the root node provides a starting point and benchmark for the evaluation process. By ensuring that the sum of the initial scores of the child nodes is equal to the initial score of the parent node, the conservation and consistency of the scores in the evaluation process are guaranteed.

[0011] In a preferred example, the present application may be further configured as follows: determining the importance of each intermediate node includes: Determine the influence degree of the business indicator corresponding to each leaf node on the target variable, and determine the importance degree of the business indicator corresponding to each leaf node based on the influence degree; Determine a child node of a target intermediate node based on the initial multi-level rule tree, wherein the target intermediate node is any node in the initial multi-level rule tree; The sum of the importance levels of the child nodes of the target intermediate node is calculated based on the importance level of each leaf node, and the sum of the importance levels is used as the importance level of the target intermediate node.

[0012] By adopting the above technical solution, the relationship between business indicators and target variables is quantified, and which indicators have a significant impact on the evaluation results are clarified, which helps to accurately identify key indicators in subsequent steps, thereby improving the accuracy and effectiveness of the evaluation. By clarifying the hierarchical relationship of each node in the multi-level rule tree, it is helpful to understand the internal logic and path of the evaluation model. By aggregating the importance of sub-nodes and calculating the importance of intermediate nodes, the hierarchical structure of the evaluation is strengthened, so that the evaluation results can reflect the relationship and weight distribution between indicators at different levels. The sum of the importance of sub-nodes is directly used as the importance of the intermediate nodes, avoiding complex weight distribution and calculation processes and improving evaluation efficiency.

[0013] In a preferred example, the present application may be further configured as follows: allocating an initial score to each leaf node based on the business data includes: Obtain similar operating data of similar enterprises in the same industry type as the target enterprise; Determine the relative position of the indicator data corresponding to each leaf node in the same type of business data; For a number of leaf nodes corresponding to the same parent node, initial scores corresponding to the leaf nodes are determined based on the initial score of the parent node and the relative positions of the leaf nodes.

[0014] By adopting the above technical solution, similar operating data of similar enterprises are obtained, which ensures that the benchmark and reference system of the evaluation are comparable in the industry, making the evaluation results more accurate and meaningful, and helping to have a more comprehensive understanding of the position and performance of the target enterprise in the industry. On the basis of the initial score of the parent node, weights are allocated according to the relative position of the leaf node, ensuring reasonable comparison and evaluation between different indicators at the same level. By aggregating the initial scores of the leaf nodes to the parent nodes, score calculation and evaluation from local to overall are realized, which helps to form a complete evaluation system.

[0015] In a preferred example, the present application can be further configured as follows: the method further includes: Receive a new rule input by a user, wherein the new rule is a preset scoring rule for a new intermediate node, or a new leaf node and the business data of the new leaf node; Determine the position of the newly added rule from the multi-level rule tree, and update the multi-level rule tree based on the position; The final score of the target enterprise is determined based on the updated multi-level rule tree.

[0016] By adopting the above technical solution, new rules input by users are received, including preset scoring rules for new intermediate nodes or new leaf nodes and their operating data, and the multi-level rule tree is updated accordingly, thereby achieving flexible adjustment and expansion of the evaluation model, ensuring the timeliness and accuracy of the evaluation results, and improving the applicability and practicality of the evaluation method.

[0017] In a second aspect, the present application provides a dynamic matching scoring system, which adopts the following technical solution: A dynamic matching scoring system, comprising: A data acquisition module, used to acquire the operating data of a target enterprise and determine the industry type of the target enterprise, wherein the operating data includes a plurality of operating indicators and indicator data of each operating indicator; A rule retrieval module, used to retrieve a multi-level rule tree corresponding to the industry type, wherein a root node and each intermediate node in the multi-level rule tree correspond to an initial score and a preset scoring rule, and each leaf node of the multi-level rule tree corresponds to an operating indicator; A rule matching module, used to match the business data with the leaf nodes of the multi-level rule tree to obtain the indicator data corresponding to each leaf node in the multi-level rule tree; The enterprise scoring module is used to iterate the calculation from the leaf node to the root node of the multi-level rule tree based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node to obtain the final score of the target enterprise.

[0018] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the dynamic matching scoring method as described in any one of the first aspects.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the dynamic matching scoring method as described in any one of the first aspects.

[0020] In summary, this application includes the following beneficial technical effects: This application can fully understand the operating status of the target enterprise by obtaining multiple operating indicators and indicator data of the target enterprise. The design of the multi-level rule tree takes into account the characteristics and evaluation ratio standards of different lines, determines the industry type of the target enterprise and calls the corresponding multi-level rule tree to ensure customized evaluation of the target enterprise. The initial score and preset scoring rules in the multi-level rule tree can be adjusted according to actual conditions, making the evaluation more flexible and adaptable. The iterative calculation process from leaf nodes to root nodes is a process of comprehensive evaluation of various operating indicators of the target enterprise. This application realizes a comprehensive and accurate evaluation of the target enterprise's operating data by constructing a multi-level rule tree. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flowchart of a dynamic matching scoring method provided in an embodiment of the present application; Figure 2 is a structural diagram of a dynamic matching scoring system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following is combined with Figure 1 -Attached Figure 3 This application is described in further detail.

[0023] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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.

[0025] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0026] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0027] This application embodiment provides a dynamic matching scoring method, such as Figure 1 As shown, the method provided in the embodiment of the present application is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S104, wherein: S101. Obtain operating data of a target enterprise and determine the industry type of the target enterprise, wherein the operating data includes a plurality of operating indicators and indicator data of each operating indicator.

[0028] Specifically, the target enterprise is any enterprise to be evaluated, and the enterprise data such as the enterprise registration information, main business and market positioning of the target enterprise are obtained, and the enterprise keywords are extracted from the obtained enterprise data. The preset corresponding relationship is retrieved, and the preset corresponding relationship includes various industry types and the keywords representing the industry type corresponding to each industry type. The preset corresponding relationship can be set by a technician and pre-stored in the database of the electronic device. The extracted enterprise keywords are matched with the keywords of each industry type in the preset corresponding relationship, and the one with the highest matching degree is determined from each industry type as the industry type of the target enterprise.

[0029] Furthermore, the target enterprise's operating data is obtained from internal or external public data sources (such as financial statements, market research reports, industry databases, etc.). The operating data includes multiple operating indicators, such as operating income, net profit, market share, R&D investment, and number of employees, etc. The value corresponding to each operating indicator is used as indicator data.

[0030] S102. Retrieve a multi-level rule tree corresponding to the industry type, wherein a root node and each intermediate node in the multi-level rule tree correspond to an initial score and a preset scoring rule, and each leaf node of the multi-level rule tree corresponds to an operating indicator.

[0031] Specifically, a multi-level rule tree is constructed for each industry type in advance, and the corresponding relationship between the industry type and the multi-level rule tree is stored in the database of the electronic device. The multi-level rule tree includes a root node, an intermediate node, and a leaf node. The root node and each intermediate node correspond to a preset scoring rule, and each leaf node corresponds to an operating indicator. The preset scoring rule and operating indicator are set by technical personnel and stored in the database in advance. Each node in the multi-level rule tree corresponds to an initial score. For the root node or any intermediate node, its initial score is equal to the sum of the initial scores of its child nodes.

[0032] S103, matching the business data with the leaf nodes of the multi-level rule tree to obtain the indicator data corresponding to each leaf node in the multi-level rule tree.

[0033] Specifically, a mapping table or dictionary dictionary can be created to match the field names of the operating indicators in the operating data of the target enterprise with the names of the operating indicators corresponding to the leaf nodes in the multi-level rule tree. This can be achieved through the data dictionary automatic mapping tool. The mapping table or dictionary can match the operating data with the leaf nodes of the multi-level rule tree. The similarity between the names of the operating indicators in the operating data and the names of the operating indicators of the leaf nodes can also be calculated through the text similarity algorithm, and a similarity threshold is set. If the similarity between a certain operating indicator name and the operating indicator name corresponding to the leaf node exceeds the similarity threshold, the match is considered successful.

[0034] In addition, if there are certain operating indicators in the target enterprise's operating data that do not find matching leaf nodes, these unmatched operating indicators will be sent to the user through the display interface of the electronic device, and the user can manually choose whether to add these operating indicators as new leaf nodes. If new leaf nodes need to be added, the multi-level rule tree will be updated accordingly.

[0035] S104: Based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node, iterative calculation is performed from the leaf node to the root node of the multi-level rule tree to obtain the final score of the target enterprise.

[0036] Specifically, any node in the second-to-last level of the multi-level rule tree is taken as the first node, and the child node of the first node is taken as the leaf node. It is determined whether the child node of the first node satisfies the preset scoring rule of the first node, and the initial score of the first node is adjusted according to the rule satisfaction to obtain the score of the first node. Any node in the third-to-last level of the multi-level rule tree is taken as the second node, and it is determined whether the child node of the second node satisfies the preset scoring rule of the second node, and the initial score of the second node is adjusted according to the rule satisfaction to obtain the score of the second node. Similarly, iterative calculations are performed from the leaf node to the root node of the multi-level rule tree to obtain the score of each intermediate node, and finally the score of the root node is determined according to the preset scoring rule of the root node, and the score of the root node is used as the final score of the target enterprise.

[0037] This embodiment can fully understand the operating status of the target enterprise by acquiring multiple operating indicators and indicator data of the target enterprise. The design of the multi-level rule tree takes into account the characteristics and evaluation ratio standards of different lines, determines the industry type of the target enterprise and calls the corresponding multi-level rule tree to ensure customized evaluation of the target enterprise. The initial score and preset scoring rules in the multi-level rule tree can be adjusted according to actual conditions, making the evaluation more flexible and adaptable. The iterative calculation process from leaf nodes to root nodes is a process of comprehensive evaluation of various operating indicators of the target enterprise. This application realizes a comprehensive and accurate evaluation of the target enterprise's operating data by constructing a multi-level rule tree.

[0038] In a possible implementation manner of the embodiment of the present application, the method further includes: Construct an initial multi-level rule tree, in which the root node and each intermediate node correspond to a preset scoring rule, and each leaf node in the multi-level rule tree corresponds to a business indicator; Determine the importance of each intermediate node; Obtaining the initial score of the root node, assigning an initial score to each intermediate node based on the initial score of the root node and the importance of each intermediate node in the initial multi-level rule tree, and assigning an initial score to each leaf node based on the business data, to obtain a multi-level rule tree including initial scores and preset scoring rules; The sum of the initial scores of the child nodes of the target node is equal to the initial score of the target node, and the target node is the root node or any intermediate node.

[0039] In this embodiment, the data structure of the initial multi-level rule tree can be set and input by a technician based on experience or business needs. The root node and each intermediate node contain a preset scoring rule, which defines how to calculate the score of the node through the scores of the child nodes.

[0040] The initial score of the root node is the basis for assigning initial scores to each intermediate node. The initial score of the root node is set and input by a technician. Optionally, the initial score of the root node is set to 100. The sum of the initial scores of the child nodes of the root node is equal to the initial score of the root node. The initial score of any intermediate node in the initial multi-level rule tree is equal to the sum of the initial scores of its child nodes.

[0041] Take the root node or any intermediate node as the target node, and distribute the initial score of the target node to each child node in proportion to the importance of its child nodes. For example, the initial score of the target node is 80, and it has three child nodes with importance levels of 0.4, 0.5, and 0.3, respectively. The sum of the importance levels of these three child nodes is calculated to be 1.2, and the initial scores of these three child nodes are: 80×0.4 / 1.2, 80×0.5 / 1.2, and 80×0.3 / 1.2, respectively. Starting from the root node of the initial multi-level rule tree, assign scores to each intermediate node in the above manner until the initial scores of each intermediate node in the second to last level are determined.

[0042] For leaf nodes that do not have child nodes, the business data corresponding to the leaf nodes can be compared with similar business data, and scores can be assigned to each leaf node based on the performance of the business data in similar business data. For several leaf nodes corresponding to the same parent node, the sum of the initial scores of the several leaf nodes is also equal to the initial score of their parent node. Finally, a multi-level rule tree with determined initial scores and preset scoring rules is obtained.

[0043] This embodiment constructs an initial multi-level rule tree including a root node, intermediate nodes and leaf nodes, which provides a structural basis for subsequent evaluation. Each leaf node corresponds to an operating indicator, ensuring the comprehensiveness and pertinence of the evaluation. The preset scoring rules of the root node and each intermediate node are used as the basis for score calculation. By determining the importance of the intermediate nodes, a weight basis can be provided for score allocation to ensure the accuracy and rationality of the evaluation. Intermediate nodes with higher importance occupy a larger proportion in the evaluation process, which helps to highlight the focus of the evaluation. The initial score of the root node provides a starting point and benchmark for the evaluation process. By ensuring that the sum of the initial scores of the child nodes is equal to the initial score of the parent node, the conservation and consistency of the scores in the evaluation process are guaranteed.

[0044] A possible implementation of the embodiment of the present application is to determine the importance of each intermediate node, including: Determine the influence of the operating indicator corresponding to each leaf node on the target variable, and determine the importance of the operating indicator corresponding to each leaf node based on the influence; Determine the child nodes of the target intermediate node based on the initial multi-level rule tree, where the target intermediate node is any node in the initial multi-level rule tree; The sum of the importance of the child nodes of the target intermediate node is calculated based on the importance of each leaf node, and the sum of the importance is used as the importance of the target intermediate node.

[0045] In this embodiment, the target variable is an operating indicator that can characterize the enterprise's capabilities, such as market share, and the importance of the target variable is set to 1. The SHAP (SHapley Additive exPlanations) value method can be used, which is a method for explaining the prediction results of the model, and can evaluate the contribution of each operating indicator to the target variable. A SHAP value can be generated for each operating indicator to indicate the degree of influence of the operating indicator on the prediction result of the target variable. The SFAP value is set in the range of 0-1, thereby obtaining the importance of each leaf node in the multi-level rule tree.

[0046] After determining the importance of each leaf node in the multi-level rule tree, iterate and calculate the importance of the intermediate nodes from the leaf node to the root node. Take any intermediate node in the second-to-last level of the multi-level rule tree as the first node, and take the sum of the importance of the child nodes of the first node as the importance of the first node. Take any intermediate node in the third-to-last level of the multi-level rule tree as the second node, and take the sum of the importance of the child nodes of the second node as the importance of the second node, and so on, to calculate the importance of each intermediate node.

[0047] This embodiment quantifies the relationship between operating indicators and target variables, clarifies which indicators have a significant impact on the evaluation results, and helps to accurately identify key indicators in subsequent steps, thereby improving the accuracy and effectiveness of the evaluation. By clarifying the hierarchical relationship between nodes in the multi-level rule tree, it helps to understand the internal logic and path of the evaluation model. By aggregating the importance of sub-nodes and calculating the importance of intermediate nodes, the hierarchical structure of the evaluation is strengthened, so that the evaluation results can reflect the relationship and weight distribution between indicators at different levels. The sum of the importance of sub-nodes is directly used as the importance of intermediate nodes, avoiding complex weight distribution and calculation processes and improving evaluation efficiency.

[0048] A possible implementation of the embodiment of the present application is to assign an initial score to each leaf node based on the business data, including: Obtain similar operating data of similar enterprises in the same industry type as the target enterprise; Determine the relative position of the indicator data corresponding to each leaf node in the same type of business data; For a number of leaf nodes corresponding to the same parent node, initial scores corresponding to the leaf nodes are determined based on the initial score of the parent node and the relative positions of the leaf nodes.

[0049] In this embodiment, the similar business data includes business data of multiple similar enterprises, and the similar business data includes indicator data corresponding to the business indicator. The business data is compared with the indicator data corresponding to the same indicator in the similar business data to determine the relative position of the indicator data of the target enterprise in the indicator data corresponding to the business indicator in the similar business data, where the relative position can be a ranking or a percentage.

[0050] Determine the relative position of the indicator data corresponding to each leaf node in the same type of business data, including: from the business data of the target enterprise and the same type of business data of similar enterprises, corresponding to a plurality of indicator data of the target indicator, one indicator data corresponding to the target indicator represents the target enterprise or any similar enterprise, and the target indicator is the business indicator corresponding to any leaf node; arrange the plurality of indicator data based on the positive and negative directions of the indicators to obtain an indicator data list; determine the position sequence of the indicator data of the target indicator in the business data in the indicator data list and the number of indicator data in the indicator data list; calculate the ratio of the position sequence and the number of indicator data as the relative position of the node corresponding to the target indicator in the same type of business data.

[0051] Specifically, if the target indicator is included in 99 similar enterprises, the number of indicator data corresponding to the target indicator in the target enterprise's operating data and the target indicator in the similar operating data is 100, and the number of data in the obtained indicator data list is 100. A positive indicator is an indicator whose value is larger, which is more favorable to the development of the enterprise, and a negative indicator is an indicator whose value is larger, which is more unfavorable to the development of the enterprise. For example, positive indicators include: market size, number of employees, and negative indicators include: number of overdue debts, number of defaults. The positive and negative indicators can be set by technicians and entered into electronic devices. For positive indicators, the corresponding multiple indicator data are arranged from small to large to obtain an indicator data list; for negative indicators, the corresponding individual indicator data are arranged from large to small to obtain an indicator data list.

[0052] By considering the positive and negative aspects of the indicators, that is, whether the indicators reflect positive or negative factors of the company's performance, an ordered list of indicator data can be obtained by arranging the indicators in a positive or negative direction. By calculating the ratio of the position of the target indicator in the indicator data list and the number of indicator data in the entire list, the larger the ratio, the better the performance of the target indicator among similar data, and the smaller the indicator, the worse the performance of the target indicator among similar data. This quantitative evaluation method makes the evaluation results more intuitive.

[0053] For several leaf nodes corresponding to the same parent node, determine the number of leaf nodes. If the number is 1, the initial score of the parent node is used as the initial score of the leaf node. If the number is not 1, the initial score of the parent node is proportionally distributed to its child nodes (i.e., leaf nodes) based on the relative position. Specifically, calculate the sum M of the relative positions of several leaf nodes. For any leaf node A among the several leaf nodes, mark the relative position of leaf node A as a, and represent the initial score of the parent node of leaf node A as B. Then the initial score of leaf node A = a / M×B. Refer to the above calculation process to calculate the initial score of each leaf node.

[0054] This embodiment obtains similar operating data of similar enterprises to ensure that the evaluation benchmark and reference system are comparable in the industry, making the evaluation results more accurate and meaningful, and helping to more comprehensively understand the position and performance of the target enterprise in the industry. It helps to more comprehensively understand the position and performance of the target enterprise in the industry. Based on the initial score of the parent node, weights are allocated according to the relative position of the leaf node, ensuring reasonable comparison and evaluation between different indicators at the same level. By aggregating the initial scores of the leaf nodes to the parent node, score calculation and evaluation from local to overall are realized, which helps to form a complete evaluation system.

[0055] A possible implementation of the embodiment of the present application is to perform iterative calculations from the leaf nodes to the root nodes of the multi-level rule tree based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node to obtain the final score of the target enterprise, including: Based on the indicator data corresponding to each leaf node, the indicator data of the child node of the first node is compared with the preset scoring rule of the first node to obtain a first rule satisfaction result, where the first node is any intermediate node in the second to last level of the multi-level rule tree; based on the first rule satisfaction result, the initial score of the first node is adjusted to obtain the score of the first node; Based on the scores of each intermediate node in the second-to-last level of the multi-level rule tree, the scores of the child nodes of the second node are compared with the preset scoring rules of the second node to obtain the second rule satisfaction result, and the second node is any intermediate node in the third-to-last level of the multi-level rule tree; based on the second rule satisfaction result, the initial score of the second node is adjusted to obtain the score of the second node; and so on, based on the initial scores corresponding to the root node and each intermediate node and the preset scoring rules, iterative calculations are performed from the leaf node to the root node of the multi-level rule tree, and the score of the root node finally determined is used as the final score of the target enterprise.

[0056] In this embodiment, the preset scoring rule is flexibly set and input by the technician. For the first node, its child nodes are leaf nodes, and the leaf nodes correspond to index data and initial scores. The preset scoring rule may include judging whether the index data or initial score of each child node of the first node reaches the corresponding threshold. If reached, the child node is judged to meet the rule, wherein the index data threshold and the initial score threshold of each leaf node can be flexibly set and input by the technician, and the first rule satisfaction result includes the rule satisfaction of each child node of the first node. If each child node of the first node satisfies the corresponding rule, the initial score of the first node can be used as the score of the first node, indicating that the first node obtains all the initial scores, and the highest initial score of the child nodes of the first node can also be determined as the initial score of the first node. If none of the child nodes of the first node meet the corresponding rule, the score of the first node can be determined to be 0, indicating that the first node has no score. If some of the child nodes of the first node meet the corresponding rule, the first number of child nodes of the first node and the second number of child nodes that meet the rule in the first number can be determined, and the calculation result of the initial score × the second number / the first number is used as the score of the first node.

[0057] For the second node, the child nodes of the second node are intermediate nodes, and the preset scoring rule of the second node can be whether the scores of each child node of the second node reach the preset score threshold. If each child node of the second node reaches it, the initial score of the second node is determined as the score of the second node. If each child node of the second node does not reach it, the score of the second node is determined to be 0. If some of the child nodes of the second node reach it, the third number of child nodes that have reached it and the fourth number of all child nodes of the second node are determined, and the initial score of the second node × the third number / the fourth number is used as the score of the second node.

[0058] For any intermediate node in the multi-level rule tree that is not outside the penultimate level, its preset scoring rule can refer to the second node. Similarly, based on the initial scores and preset scoring rules corresponding to the root node and each intermediate node, iterative calculations are performed from the leaf node to the root node of the multi-level rule tree, and the score of the root node finally determined is used as the final score of the target enterprise. Among them, the preset scoring rules of the root node and each intermediate node can be flexibly set by the technician, and this embodiment does not limit it.

[0059] This embodiment performs iterative calculations from the leaf nodes to the root nodes of the multi-level rule tree, and gradually adjusts and determines the scores of the nodes at each level based on the indicator data of each leaf node and the initial scores of the nodes at each level and the preset scoring rules, and finally obtains the final score of the target enterprise, thereby realizing dynamic adjustment and refined calculation of the evaluation process and ensuring the accuracy and comprehensiveness of the evaluation results.

[0060] In a possible implementation manner of the embodiment of the present application, the method further includes: Receive a new rule input by a user, where the new rule is a preset scoring rule for a new intermediate node, or a new leaf node and the business data of the new leaf node; Determine the location of the newly added rule from the multi-level rule tree, and update the multi-level rule tree based on the location; The final score of the target enterprise is determined based on the updated multi-level rule tree.

[0061] In this embodiment, the location of the newly added rule can be input by the user. After the multi-level rule tree is updated, the system recalculates the scores of all nodes from the leaf node to the root node.

[0062] This embodiment receives new rules input by users, including preset scoring rules for new intermediate nodes or new leaf nodes and their business data, and updates the multi-level rule tree accordingly, thereby achieving flexible adjustment and expansion of the evaluation model, ensuring the timeliness and accuracy of the evaluation results, and improving the applicability and practicality of the evaluation method.

[0063] The above embodiment introduces a dynamic matching scoring method from the perspective of method flow, and the following embodiment introduces a dynamic matching scoring system from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0064] The present application embodiment provides a dynamic matching scoring system, such as Figure 2 As shown, the system may include: The data acquisition module 201 is used to acquire the operating data of the target enterprise and determine the industry type of the target enterprise. The operating data includes multiple operating indicators and indicator data of each operating indicator. The rule retrieval module 202 is used to retrieve a multi-level rule tree corresponding to the industry type, wherein the root node and each intermediate node in the multi-level rule tree correspond to an initial score and a preset scoring rule, and each leaf node of the multi-level rule tree corresponds to an operating indicator; The rule matching module 203 is used to match the business data with the leaf nodes of the multi-level rule tree to obtain the indicator data corresponding to each leaf node in the multi-level rule tree; The enterprise scoring module 204 is used to perform iterative calculations from the leaf nodes to the root nodes of the multi-level rule tree based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node to obtain the final score of the target enterprise.

[0065] In a preferred example, the present application can be further configured as follows: when the enterprise scoring module 204 performs iterative calculations from the leaf nodes to the root nodes of the multi-level rule tree based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node to obtain the final score of the target enterprise, it is specifically used to: Based on the indicator data corresponding to each leaf node, the indicator data of the child node of the first node is compared with the preset scoring rule of the first node to obtain a first rule satisfaction result, where the first node is any intermediate node in the second to last level of the multi-level rule tree; based on the first rule satisfaction result, the initial score of the first node is adjusted to obtain the score of the first node; Based on the scores of each intermediate node in the second-to-last level of the multi-level rule tree, the scores of the child nodes of the second node are compared with the preset scoring rules of the second node to obtain the second rule satisfaction result, and the second node is any intermediate node in the third-to-last level of the multi-level rule tree; based on the second rule satisfaction result, the initial score of the second node is adjusted to obtain the score of the second node; and so on, based on the initial scores corresponding to the root node and each intermediate node and the preset scoring rules, iterative calculations are performed from the leaf node to the root node of the multi-level rule tree, and the score of the root node finally determined is used as the final score of the target enterprise.

[0066] In a preferred example, the present application can be further configured as follows: the system also includes a rule tree construction module, which is specifically used to: Construct an initial multi-level rule tree, in which the root node and each intermediate node correspond to a preset scoring rule, and each leaf node in the multi-level rule tree corresponds to a business indicator; Determine the importance of each intermediate node; Obtaining the initial score of the root node, assigning an initial score to each intermediate node based on the initial score of the root node and the importance of each intermediate node in the initial multi-level rule tree, and assigning an initial score to each leaf node based on the business data, to obtain a multi-level rule tree including initial scores and preset scoring rules; The sum of the initial scores of the child nodes of the target node is equal to the initial score of the target node, and the target node is the root node or any intermediate node.

[0067] In a preferred example, the present application can be further configured as follows: when the rule tree construction module determines the importance of each intermediate node, it is specifically used to: Determine the influence of the operating indicator corresponding to each leaf node on the target variable, and determine the importance of the operating indicator corresponding to each leaf node based on the influence; Determine the child nodes of the target intermediate node based on the initial multi-level rule tree, where the target intermediate node is any node in the initial multi-level rule tree; The sum of the importance of the child nodes of the target intermediate node is calculated based on the importance of each leaf node, and the sum of the importance is used as the importance of the target intermediate node.

[0068] In a preferred example, the present application can be further configured as follows: when the rule tree construction module is executing the allocation of an initial score to each leaf node based on the business data, it is specifically used to: Obtain similar operating data of similar enterprises in the same industry type as the target enterprise; Determine the relative position of the indicator data corresponding to each leaf node in the same type of business data; For a number of leaf nodes corresponding to the same parent node, initial scores corresponding to the leaf nodes are determined based on the initial score of the parent node and the relative positions of the leaf nodes.

[0069] In a preferred example, the present application can be further configured as follows: the system also includes a rule adding module, which is specifically used for: Receive a new rule input by a user, where the new rule is a preset scoring rule for a new intermediate node, or a new leaf node and the business data of the new leaf node; Determine the location of the newly added rule from the multi-level rule tree, and update the multi-level rule tree based on the location; The final score of the target enterprise is determined based on the updated multi-level rule tree.

[0070] A dynamic matching scoring system provided in the embodiment of the present application is applicable to the above method embodiment, which will not be described in detail here.

[0071] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0072] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0073] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0074] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0075] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above-mentioned embodiment of the dynamic matching scoring method.

[0076] Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0077] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the above-mentioned dynamic matching scoring method embodiment.

[0078] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0079] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A dynamic matching scoring method, characterized in that: include: Acquire the operating data of the target enterprise and determine the industry type of the target enterprise, wherein the operating data includes a plurality of operating indicators and indicator data of each operating indicator; Retrieving a multi-level rule tree corresponding to the industry type, wherein a root node and each intermediate node in the multi-level rule tree correspond to an initial score and a preset scoring rule, and each leaf node of the multi-level rule tree corresponds to an operating indicator; Matching the business data with the leaf nodes of the multi-level rule tree to obtain the indicator data corresponding to each leaf node in the multi-level rule tree; Based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node, iterative calculations are performed from the leaf nodes to the root nodes of the multi-level rule tree to obtain the final score of the target enterprise.

2. The dynamic matching scoring method according to claim 1, characterized in that: The method of iteratively calculating from the leaf nodes to the root nodes of the multi-level rule tree based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node to obtain the final score of the target enterprise includes: Based on the indicator data corresponding to each leaf node, comparing the indicator data of the child node of the first node with the preset scoring rule of the first node to obtain a first rule satisfaction result, where the first node is any intermediate node in the second to last level of the multi-level rule tree; adjusting the initial score of the first node based on the first rule satisfaction result to obtain the score of the first node; Based on the scores of each intermediate node in the second-to-last level of the multi-level rule tree, the scores of the child nodes of the second node are compared with the preset scoring rules of the second node to obtain the second rule satisfaction result, and the second node is any intermediate node in the third-to-last level of the multi-level rule tree; based on the second rule satisfaction result, the initial score of the second node is adjusted to obtain the score of the second node; and so on, based on the initial scores corresponding to the root node and each intermediate node and the preset scoring rules, iterative calculations are performed from the leaf nodes to the root nodes of the multi-level rule tree, and the score of the root node finally determined is used as the final score of the target enterprise.

3. The dynamic matching scoring method according to claim 1, characterized in that: The method further comprises: Constructing an initial multi-level rule tree, wherein a root node and each intermediate node in the initial multi-level rule tree correspond to a preset scoring rule, and each leaf node in the multi-level rule tree corresponds to a business indicator; Determine the importance of each intermediate node; Obtaining an initial score of the root node, assigning an initial score to each intermediate node based on the initial score of the root node and the importance of each intermediate node in the initial multi-level rule tree, and assigning an initial score to each leaf node based on the business data, to obtain a multi-level rule tree including initial scores and preset scoring rules; The sum of the initial scores of the child nodes of the target node is equal to the initial score of the target node, and the target node is the root node or any intermediate node.

4. The dynamic matching scoring method according to claim 3, characterized in that: The step of determining the importance of each intermediate node includes: Determine the influence degree of the operating indicator corresponding to each leaf node on the target variable, and determine the importance degree of the operating indicator corresponding to each leaf node based on the influence degree; Determine a child node of a target intermediate node based on the initial multi-level rule tree, wherein the target intermediate node is any node in the initial multi-level rule tree; The sum of the importance levels of the child nodes of the target intermediate node is calculated based on the importance level of each leaf node, and the sum of the importance levels is used as the importance level of the target intermediate node.

5. The dynamic matching scoring method according to claim 3, characterized in that: The allocating an initial score to each leaf node based on the business data comprises: Obtain similar operating data of similar enterprises in the same industry type as the target enterprise; Determine the relative position of the indicator data corresponding to each leaf node in the same type of business data; For a number of leaf nodes corresponding to the same parent node, initial scores corresponding to the leaf nodes are determined based on the initial score of the parent node and the relative positions of the leaf nodes.

6. The dynamic matching scoring method according to claim 1, characterized in that: The method further comprises: Receive a new rule input by a user, wherein the new rule is a preset scoring rule for a new intermediate node, or a new leaf node and the business data of the new leaf node; Determine the position of the newly added rule from the multi-level rule tree, and update the multi-level rule tree based on the position; The final score of the target enterprise is determined based on the updated multi-level rule tree.

7. A dynamic matching scoring system, characterized in that: include: A data acquisition module, used to acquire the operating data of a target enterprise and determine the industry type of the target enterprise, wherein the operating data includes a plurality of operating indicators and indicator data of each operating indicator; A rule retrieval module, used to retrieve a multi-level rule tree corresponding to the industry type, wherein a root node and each intermediate node in the multi-level rule tree correspond to an initial score and a preset scoring rule, and each leaf node of the multi-level rule tree corresponds to an operating indicator; A rule matching module, used to match the business data with the leaf nodes of the multi-level rule tree to obtain the indicator data corresponding to each leaf node in the multi-level rule tree; The enterprise scoring module is used to iterate the calculation from the leaf node to the root node of the multi-level rule tree based on the indicator data corresponding to each leaf node and the initial scores and preset scoring rules corresponding to the root node and each intermediate node to obtain the final score of the target enterprise.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the dynamic matching scoring method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the dynamic matching scoring method according to any one of claims 1 to 6.

Images