Method, apparatus, computer device, and storage medium for processing service data

Abstract

The embodiments of the present application belong to the field of artificial intelligence and are applied to the field of intelligent government affairs. It involves a method for processing business data, including obtaining business data corresponding to each business name; extracting data features in the business data by means of character matching, classifying the data features by means of a decision tree to determine the business type corresponding to the business name; comparing the business type with a preset type corresponding to the business name to generate an evaluation parameter, and updating the decision tree based on the evaluation parameter to generate a business processing model. In addition, the present application also involves blockchain technology, and business data can be stored in the blockchain. By the above method, the accuracy of the business processing model is improved, and then various types of businesses are classified based on the business processing model to conduct classified supervision and handling of the businesses, thereby improving the efficiency of business processing.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly to a method, device, computer device and storage medium for processing business data. Background Art

[0002] Under the background of the complexity of the global economic situation and economic globalization, digital transformation has become the main theme of the development of large enterprises in the financial industry. Business has continued to break through, the market position has been continuously improved, and technological strength has gradually become the guiding and innovative force in the banking industry. More and more technical personnel have joined to solve problems with technical means and serve aspects such as risk management, product design, process optimization, and marketing.

[0003] The comprehensive management system has accumulated a large amount of historical supervision behavior data, and the traditional expert experience-based supervision method has also made important contributions to ensuring the normal operation of work. However, with the continuous growth of IT personnel and matters, the expert model can no longer meet the timeliness requirements of supervision work, and the unified standard supervision method cannot distinguish individual differences and meet the needs of humanized management. The main challenges faced by the traditional supervision method are as follows: there are a large number of matters, and the IT comprehensive management system generates hundreds of supervision matters per day, involving a large number of employees and outsourced personnel; there are various types, and there are various types of matters that need to be approved, such as attendance approval, entry and exit of outsourced personnel, problem feedback, safety self-inspection, performance appraisal, etc.; there are many process nodes, and some matters involve multiple nodes. For example, in outsourced recruitment: after the project manager releases the employment requirements, the IT outsourcing management group reviews and prepares the budget and releases the recruitment requirements to the service provider. In summary, the above problems will lead to the problem of low system operation efficiency. Summary of the Invention

[0004] The purpose of the embodiments of this application is to propose a method, device, computer device and storage medium for processing business data to solve the problem of low system operation efficiency.

[0005] To solve the above technical problems, the embodiments of this application provide a method for processing business data, which adopts the following technical solutions: obtain business data corresponding to each business name; extract data features in the business data by means of character matching, classify the data features by means of a decision tree, and determine the business type corresponding to the business name; compare the business type with the preset type corresponding to the business name to generate an evaluation parameter; update the decision tree based on the evaluation parameter, and use the updated decision tree as a business processing model. When obtaining business information triggered by a user, classify the business information based on the business processing model, and obtain corresponding processing information according to the classification result for business processing.

[0006] In some embodiments of the present application, based on the foregoing solution, after the step of obtaining the service data corresponding to each service name, the method further includes: determining the attribute values of the service data corresponding to each of the preset data dimensions based on the service data and the preset data dimensions; and performing data cleaning on the service data based on the attribute values corresponding to the service data.

[0007] In one embodiment of the present application, based on the foregoing solution, the step of performing data cleaning on the service data based on the attribute values corresponding to the service data specifically includes: obtaining the normal data range corresponding to the preset data dimension; for the attribute values corresponding to the service data, retaining the service data whose attribute values are within the normal data range, or deleting the service data whose attribute values are not within the normal data range.

[0008] In some embodiments of the present application, based on the foregoing solution, the step of extracting the data features in the service data by character matching specifically includes: performing character matching on the service data based on the preset data dimension to determine the data composition of the service data corresponding to each of the data dimensions; and determining the data features corresponding to the data composition of the data dimension based on the correspondence between the preset threshold range and the data features for each of the data dimensions.

[0009] In some embodiments of the present application, based on the foregoing solution, the step of extracting the data features in the service data by character matching, classifying the data features by a decision tree, and determining the service type corresponding to the service name specifically includes: extracting the data features in the service data by character matching; classifying the data features by a decision tree to determine the service type corresponding to the service name.

[0010] In some embodiments of the present application, based on the foregoing solution, the step of classifying the data features by a decision tree and determining the service type corresponding to the service name specifically includes: calculating the Gini index corresponding to each service data; and classifying the service data by a decision tree based on the Gini index to determine the service type corresponding to the service name.

[0011] In some embodiments of the present application, based on the foregoing solution, the evaluation parameter includes at least one of the following parameters: precision, recall; the step of comparing the service type with the preset type corresponding to the service name to generate an evaluation parameter includes: calculating the precision in the following manner: where TP represents the number of cases where the actual high supervision level is predicted as the high supervision level; FP represents the number of cases where other supervision levels are predicted as the high supervision level; and / or calculating the recall in the following manner: Among them, FN represents the number of predicting other supervision levels as other supervision levels.

[0012] In some embodiments of the present application, based on the foregoing solution, updating the decision tree based on the evaluation parameter and using the updated decision tree as a service processing model includes: obtaining the associated parameters involved in the calculation in the decision tree; updating the associated parameters based on the evaluation parameter to obtain an updated decision tree, and generating the service processing model.

[0013] In some embodiments of the present application, based on the foregoing solution, the classification result includes the matter attribute corresponding to the service information; when obtaining the service information triggered by the user, classifying the service information based on the service processing model, and obtaining the corresponding processing information according to the classification result for service processing, includes: obtaining the service information triggered by the user, classifying the service information through the service processing model to determine the matter attribute corresponding to the service information; generating a reminder message corresponding to the service information based on the matter attribute; and sending the reminder message to the associated party corresponding to the service information based on the matter attribute.

[0014] To solve the above technical problems, an embodiment of the present application further provides a processing device for service data, including: an obtaining module, configured to obtain service data corresponding to each service name; a classification module, configured to extract data features in the service data by character matching, classify the data features by a decision tree, and determine the service type corresponding to the service name; a comparison module, configured to compare the service type with a preset type corresponding to the service name to generate an evaluation parameter; a generation module, configured to update the decision tree based on the evaluation parameter and use the updated decision tree as a service processing model; and an application module, configured to classify the service information based on the service processing model when obtaining the service information triggered by the user, and obtain the corresponding processing information according to the classification result for service processing.

[0015] In some embodiments of the present application, based on the foregoing solution, the processing device for service data further includes: an attribute determination module, configured to determine the attribute value corresponding to the service data in each preset data dimension based on the service data and the preset data dimension; and a data cleaning module, configured to perform data cleaning on the service data based on the attribute value corresponding to the service data.

[0016] In an embodiment of the present application, based on the foregoing solution, the step of performing data cleaning on the service data based on the attribute value corresponding to the service data specifically includes: obtaining the normal data range corresponding to the preset data dimension; for the attribute value corresponding to the service data, retaining the service data with the attribute value within the normal data range, or deleting the service data with the attribute value not within the normal data range.

[0017] In some embodiments of the present application, based on the foregoing solution, the step that the classification module includes extracting the data features in the service data by character matching specifically includes: a matching sub-module, configured to perform character matching on the service data based on the preset data dimension to determine the data composition of the service data corresponding to each data dimension; a feature sub-module, configured to determine the data features corresponding to the data composition of the data dimension based on the corresponding relationship between the preset threshold range and the data features for each data dimension.

[0018] In some embodiments of the present application, based on the foregoing solution, the feature classification sub-module includes: a Gini index calculation unit, configured to calculate the Gini index corresponding to each service data; an index classification unit, configured to classify the service data in a decision tree manner based on the Gini index to determine the service type corresponding to the service name.

[0019] In some embodiments of the present application, based on the foregoing solution, the evaluation parameters include at least one of the following parameters: precision, recall rate, and the comparison module includes:

[0020] A first comparison sub-module, configured to calculate the precision rate in the following manner: Wherein, TP represents the number of cases where the actual high supervision level is predicted as the high supervision level; FP represents the number of cases where other supervision levels are predicted as the high supervision level; and / or

[0021] A second comparison sub-module, configured to calculate the recall rate in the following manner: Wherein, FN represents the number of cases where other supervision levels are predicted as other supervision levels.

[0022] In some embodiments of the present application, based on the foregoing solution, the generation module includes: a parameter acquisition sub-module, configured to acquire the associated parameters participating in the calculation in the decision tree; a model generation sub-module, configured to update the associated parameters based on the evaluation parameters to obtain an updated decision tree, and generate the service processing model.

[0023] In some embodiments of the present application, based on the foregoing solution, the classification result includes the matter attribute corresponding to the service information; the application module further includes: an attribute acquisition sub-module, configured to acquire the service information triggered by the user, classify the service information through the service processing model, and determine the matter attribute corresponding to the service information; an information generation sub-module, configured to generate reminder information corresponding to the service information based on the matter attribute; and an information reminder sub-module, configured to send the reminder information to the associated party corresponding to the service information based on the matter attribute.

[0024] To solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solution: acquiring service data corresponding to each service name; extracting data features in the service data by means of character matching, classifying the data features by means of a decision tree, and determining the service type corresponding to the service name; comparing the service type with a preset type corresponding to the service name to generate an evaluation parameter; updating the decision tree based on the evaluation parameter, and using the updated decision tree as a service processing model.

[0025] To solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution: acquiring service data corresponding to each service name; extracting data features in the service data by means of character matching, classifying the data features by means of a decision tree, and determining the service type corresponding to the service name; comparing the service type with a preset type corresponding to the service name to generate an evaluation parameter; updating the decision tree based on the evaluation parameter, and using the updated decision tree as a service processing model.

[0026] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: by acquiring service data corresponding to each service name, classifying the service name by means of a decision tree based on the data features in the service data, determining the service type corresponding to the service name, and then comparing the service type with a preset type corresponding to the service name to generate an evaluation parameter, updating the decision tree based on the evaluation parameter to generate a service processing model, improving the accuracy of the service processing model, and further classifying various types of services based on the service processing model to classify and supervise the services, thereby improving the efficiency of service processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] To more clearly illustrate the solutions in the present application, the following briefly introduces the drawings required for the description of the embodiments of the present application. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

[0029] Figure 2 Flowchart of an embodiment of a method for processing service data according to the present application;

[0030] Figure 3 Flowchart of another embodiment of a method for processing service data according to the present application;

[0031] Figure 4 is a schematic structural diagram of an embodiment of a device for processing service data according to the present application;

[0032] Figure 5 is Figure 4 schematic structural diagram of a specific embodiment of the illustrated computing module;

[0033] Figure 6 is a schematic structural diagram of an embodiment of a computer device according to the present application. Detailed implementation manners

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0035] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0036] In order to enable those skilled in the art of this technology to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings.

[0037] Such as Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0038] Users can use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0039] The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, and desktop computers, etc.

[0040] The server 105 may be a server providing various services, such as a background server supporting the pages displayed on the terminal devices 101, 102, 103.

[0041] The embodiments of this application may acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0042] In the embodiments of the present application, the server may be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0043] It should be noted that the method for processing service data provided in the embodiments of the present application is generally executed by a server or a terminal device. Correspondingly, the device for processing service data is generally arranged in the server or the terminal device.

[0044] It should be understood that Figure 1 the numbers of terminal devices, networks, and servers in

[0045] Continuing to refer to Figure 2 , a flowchart of an embodiment of the method for processing service data according to the present application is shown. The method for processing service data includes the following steps:

[0046] Step S201, obtaining service data corresponding to each service name.

[0047] In this embodiment, the electronic device (such as the server or terminal device shown in Figure 1 ) on which the method for processing service data runs can obtain the service data corresponding to each service name through a wired connection method or a wireless connection method. It should be noted that the above wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future-developed wireless connection methods.

[0048] The service processing model in this embodiment mainly targets various affairs in the operation process of an enterprise, specifically including various affairs that need to be processed by each department, position, and employee. The service names in this embodiment mainly include the following: common service scenarios such as signing reports, attendance anomalies, resume screening, Zhiniao learning, project due processing, outsourcing entry and exit processing, etc.; and matters that require approval such as attendance approval, outsourcing personnel entry and exit, problem feedback, safety self-inspection, performance appraisal, etc.; in addition, it also includes the IT outsourcing management group's review and preparation of budgets, release of recruitment requirements to service providers, and service providers' recommendation of resumes, etc.

[0049] In this embodiment, the business data can be obtained by collecting data from employees in each department, or by periodically obtaining various business applications in the management system to determine various types of business data based on the business applications.

[0050] Step S202: Extract the data features in the business data by character matching, classify the data features by means of a decision tree, and determine the business type corresponding to the business name.

[0051] In this embodiment, after obtaining the business data, the data features in the business data are classified by means of a decision tree to determine the business type corresponding to each business name. The decision tree in this embodiment is a supervised learning, that is, through the obtained business data and the preset types set artificially, a classifier is obtained through learning, and this classifier can give a correct classification to newly emerging businesses, realizing machine learning based on artificial intelligence.

[0052] In practical applications, the decision tree is a decision analysis method that, based on the known probabilities of various situations, evaluates project risks and judges its feasibility by constructing a decision tree to obtain the probability that the expected value of the net present value is greater than or equal to zero. It is an intuitive graphical method using probability analysis. Since the decision branches are drawn in a graph very similar to the branches of a tree. In machine learning, a decision tree is a prediction model that represents a mapping relationship between object attributes and object values. A decision tree is a tree structure, where each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a category. In this embodiment, the input to the decision tree is business data, and the output through the decision tree is the business type of the business data.

[0053] Optionally, the business type in this embodiment represents the processing method or urgency required for the business. For example, the business types in this embodiment may include verification supervision, important supervision, general supervision, etc., where the importance or urgency of supervision decreases from high to low.

[0054] Identify the business type corresponding to the business data in the form of a decision tree, and feedback and adjust the parameters in the decision tree based on the recognition result, thereby improving the recognition accuracy of the decision tree and the accuracy and stability of classifying the business data.

[0055] Step S203: Compare the business type with the preset type corresponding to the business name to generate an evaluation parameter.

[0056] In this embodiment, a corresponding preset type is preset based on business data. After determining the business type corresponding to the business data during decision-making, the business type is compared with the preset type corresponding to the business name to generate an evaluation parameter.

[0057] The preset types in this embodiment mainly target common business scenarios in actual applications, such as work sign reports, attendance anomalies, resume screening, project due processing, outsourcing departure and arrival processing, etc. Samples of supervision events and supervision decision labels required for modeling are screened out, the classification of event supervision (verification supervision, important supervision, general supervision) is extracted, and the rationality of the classification is confirmed with comprehensive human resource managers as the classification labels for model training, which are used as preset types. The evaluation parameters in this embodiment include at least one of the following: indicators such as accuracy (AUC), recall rate (Recall), and precision rate (Precision) to evaluate the effect of the algorithm model. Specifically, accuracy, also known as accuracy, refers to the accurate degree of business type recognition. When calculating, it is calculated by the degree of closeness between the observed value of a certain test index or trait in an experiment or survey and its true value, or the degree of coincidence between the average value measured multiple times under certain experimental conditions and the true value, and the accuracy is expressed by the error. In this embodiment, the recall rate is for our original samples, which represents how many samples of a certain business type in the samples are predicted correctly and is used to represent the number of the business type recalled from all the to-be-processed businesses. The precision rate is for the prediction results in this embodiment, which represents how many of the prediction results are predicted correctly.

[0058] Step S204: Update the decision tree based on the evaluation parameter, and use the updated decision tree as the business processing model.

[0059] After calculating the evaluation parameter, the evaluation parameter is input into the decision function in the decision tree to update the classification strategy of the decision tree, and the updated decision tree is obtained. Then, based on the above prediction and update methods, the updated decision tree is continuously trained to obtain the final business processing model.

[0060] Step S205: When obtaining the business information triggered by the user, classify the business information based on the business processing model, and obtain the corresponding processing information according to the classification result for business processing.

[0061] In an embodiment of the present application, after generating the business processing model, the business information is classified based on the business processing model to obtain the classification result of the business information, and then the corresponding processing information is obtained according to the classification result for business processing according to the processing information.

[0062] Optionally, the service processing in this embodiment includes services such as requests for services, execution, reminder, notification, retrospective analysis, and summary.

[0063] In an embodiment of the present application, the classification result includes the matter attributes corresponding to the service information; the service includes a reminder service for various service events. When the service information triggered by the user is obtained in step S205, the service information is classified based on the service processing model, and the corresponding processing information is obtained according to the classification result for service processing, including the following steps:

[0064] S5: Obtain the service information triggered by the user, classify the service information through the service processing model, and determine the matter attributes corresponding to the service information;

[0065] S6: Generate reminder information corresponding to the service information based on the matter attributes;

[0066] S7: Based on the matter attributes, send the reminder information to the associated party corresponding to the service information.

[0067] In this embodiment, after obtaining the service processing model, service supervision can be performed based on the service triggered by the user. Specifically, the matter attributes corresponding to the service information are determined through the service processing model. For example, urgent, complex, etc. Then, reminder information is generated based on the matter attributes to send the reminder information to the associated party corresponding to the service information. For example, if the matter attribute is class = 1, that is, a high supervision level, a high-level reminder information is generated and reminded based on the first preset period; if the matter attribute is class = 0, that is, a low supervision importance level, a low-level reminder information is generated and reminded based on the second preset period; where the first preset period is shorter than the second preset period. Through the above method, the security and convenience of service flow are improved, and the efficiency of service processing is further enhanced.

[0068] Through the above steps, the present application obtains the service data corresponding to each service name, classifies the service names by means of a decision tree based on the data characteristics in the service data, determines the service types corresponding to the service names, and then compares the service types with the preset types corresponding to the service names to generate evaluation parameters, so as to update the decision tree based on the evaluation parameters to generate a service processing model, improve the accuracy of the service processing model, and then classify various types of services based on the service processing model to classify and process the services, improving the efficiency of service processing.

[0069] In this embodiment, the implementation example of the supervision process realizes online operation, indexing, and algorithmization. The intelligent supervision project starts from internal data, performs data cleaning, constructs an index variable system, and extracts the behavioral characteristics of employees in the supervised matters; based on machine learning algorithms, a supervision model is constructed to automatically obtain high, medium, and low classifications of the supervision level of a matter or node, namely high supervision level, medium supervision level, and low supervision level, and the supervision process is completely online; the model can gradually understand the supervision object in depth, and the accuracy of the model is correspondingly improved. As the attributes and behaviors of the supervised person change, the supervision method changes automatically, effectively improving the efficiency of daily work management and enhancing the management quality.

[0070] In some optional implementation manners of this embodiment, after obtaining the service data corresponding to each service name in step 201, before step S202 extracts the data features in the service data by means of character matching and classifies the data features by means of a decision tree to determine the service type corresponding to the service name, the above electronic device may further execute the following steps:

[0071] S11: Based on the service data and preset data dimensions, determine the attribute values corresponding to the service data in each of the preset data dimensions;

[0072] S12: Based on the attribute values corresponding to the service data, perform data cleaning on the service data.

[0073] In this embodiment, after obtaining the service data, based on the preset data dimensions, determine the attribute values corresponding to these service data in each dimension. Among them, the preset data dimensions include at least one of the following: event attribute, supervised personnel attribute, nature of daily work, and historical supervision behavior.

[0074] After determining the corresponding attribute values, in this embodiment, each preset data dimension has its corresponding normal data range. Based on the normal data ranges corresponding to each attribute value, screen the service data to complete the cleaning of the service data.

[0075] In an embodiment of the present application, the process of performing data cleaning on the service data based on the attribute values corresponding to the service data specifically includes the following steps:

[0076] Obtain the normal data ranges corresponding to the preset data dimensions;

[0077] For the attribute values corresponding to the service data, retain the service data with attribute values within the normal data range, or delete the service data with attribute values not within the normal data range.

[0078] Specifically, the data cleaning process in this embodiment can be as follows: First, determine the normal data range corresponding to the preset data dimension and the attribute values corresponding to the business data. Then, retain the business data whose attribute values are within this normal data range, or delete the business data whose attribute values are not within this normal data range. By the above method, the accuracy of the data is improved, the data redundancy is reduced, and thus the efficiency and accuracy of model construction are improved.

[0079] The data features of this embodiment include the numerical values of business data in each data dimension. Specifically, the method of extracting data features in this embodiment can be obtained by character matching. Exemplarily, in the matter attribute dimension, the data dimensions include the project urgency level, the project complexity level, various data of the task design department, the number of times the task has been supervised, etc.; among them, the data feature values corresponding to each data dimension are high, medium, and low respectively.

[0080] In some alternative implementation manners, the step of extracting the data features in the business data by character matching specifically includes:

[0081] Based on the preset data dimension, perform character matching on the business data to determine the data composition of the business data corresponding to each of the data dimensions;

[0082] Based on the corresponding relationship between the preset threshold range and the data features for each of the data dimensions, determine the data features corresponding to the data composition of this data dimension.

[0083] In this embodiment, based on the preset data dimensions, namely the project urgency level, the project complexity level, various data of the task design department, the number of times the task has been supervised, etc.

[0084] In this embodiment, first perform character matching on the business data to determine the data composition of the business data corresponding to each data dimension. For example, match and screen out the data composition that matches the project urgency level from the business data. The data composition corresponding to the project urgency level may include time information, such as the current time and the deadline time. It is also possible to determine the processing time based on the current time and the deadline time, as the data composition in this embodiment.

[0085] The corresponding relationship between the threshold range and the data features in this embodiment can be the feature degree corresponding to each specific numerical range. For example, the preset threshold ranges for the project urgency level are respectively greater than 3 days, equal to 3 days, and less than 3 days, and the corresponding data features are respectively low urgency level, medium urgency level, and high urgency level.

[0086] After that, based on the correspondence between the preset threshold range and the data characteristics for each data dimension, determine the data characteristic value corresponding to the data composition of that data dimension. For example, after obtaining the data composition, the data characteristic corresponding to a processing time greater than 3 days is low urgency, less than 3 days is high urgency, and equal to 3 days is medium urgency. Through the above method, the status corresponding to each business data can be determined efficiently and accurately.

[0087] In some alternative implementation manners, the data characteristics include the Gini index. Step S22: Classify the data characteristics by means of a decision tree to determine the process of the business type corresponding to the business name, which specifically includes the following steps:

[0088] S221: Calculate the Gini index corresponding to each business data;

[0089] S221: Based on the Gini index, classify the business data by means of a decision tree to determine the business type corresponding to the business name.

[0090] In this embodiment, a decision tree model is mainly used to classify the supervision tasks. Specifically, a Classification and Regression Trees (CART) decision tree is used, and the Gini index is used as an evaluation index to build a decision tree model for the supervision tasks. In this embodiment, the Gini index represents the probability that a randomly selected sample in the sample set is misclassified. The smaller the Gini index, the smaller the probability that the selected sample in the set is misclassified, that is, the higher the purity of the set. Conversely, the set is less pure. The calculation method of the Gini index in this embodiment is:

[0091]

[0092] where p k represents the probability that the sample belongs to the kth category, and k is a natural number greater than or equal to 1.

[0093] In this embodiment, the CART tree is a binary tree. For a specific feature with multiple values (more than 2), it is necessary to calculate the purity Gini(D, Ai) of the subset after dividing the sample D with each value as the division point, and then find the division with the smallest Gini index from all possible divisions Gini(D, Ai). The division point of this division is the best division point for dividing the sample set D using the feature A. By classifying the business data through this division point, the final business type of the business data can be obtained.

[0094] In this embodiment, the decision tree is constructed in a top-down recursive manner. Methods such as the Gini coefficient are used to select an attribute for branching at each node, so that the output on each branch is as "pure" as possible, which is suitable for exploratory knowledge discovery. The above figure determines the supervision importance of a certain matter node according to the division of the tree: class = 1 represents a high supervision degree, and class = 0 represents a low one. To improve the stability of the model, strong rules can be induced according to the division path of the tree, with the rule model taking precedence and the algorithm model assisting.

[0095] In an embodiment of the present application, the evaluation parameter includes precision. In step S203, comparing the service type with the preset type corresponding to the service name to generate the evaluation parameter includes the following steps:

[0096] S31: The evaluation parameter includes precision, and the precision is calculated as follows:

[0097] Among them, TP represents the number of cases where the actual high supervision degree is predicted as the high supervision degree; FP represents the number of cases where other supervision degrees are predicted as the high supervision degree.

[0098] In this embodiment, the supervision importance of a certain matter node is determined based on the division of the decision tree, that is, class = 1 represents a high supervision degree, and class = 0 represents a low supervision importance degree. The precision represents the proportion of the actual high supervision degree among the instances classified as the high supervision degree. The precision can be used to measure the prediction ability of the model and the accuracy of the judgment.

[0099] In an embodiment of the present application, the evaluation parameter includes recall. In step S203, comparing the service type with the preset type corresponding to the service name to generate the evaluation parameter includes the following steps:

[0100] The recall is calculated as follows:

[0101]

[0102] Among them, FN represents the number of cases where other supervision degrees are predicted as other supervision degrees.

[0103] In this embodiment, the recall represents the proportion of all instances with an actual high supervision degree that are predicted as the high supervision degree, which is equivalent to sensitivity. The higher the recall, the higher the accuracy of the service processing model.

[0104] In an embodiment of the present application, in step S204, updating the decision tree based on the evaluation parameter and using the updated decision tree as the service processing model includes the following steps:

[0105] S41: Obtain the associated parameters involved in the calculation in the decision tree;

[0106] S42: Update the associated parameters based on the evaluation parameters to obtain an updated decision tree, and generate the service processing model.

[0107] In this embodiment, after the evaluation parameters are calculated, the decision tree can be updated based on the evaluation parameters. Specifically, when updating, first obtain the associated parameters involved in the calculation in the decision tree, such as the calculation parameters of the event type and the statistical accuracy of the residence time. Then update the associated parameters based on the evaluation parameters. For example, when the accuracy is less than the set accuracy threshold, the statistical accuracy of the residence time can be increased based on the set step size. After updating the associated parameters, an updated decision tree is obtained to generate the service processing model.

[0108] Through the above steps, this application obtains the service data corresponding to each service name, classifies the service names in the form of a decision tree based on the data characteristics in the service data, determines the service type corresponding to the service name, and then compares the service type with the preset type corresponding to the service name to generate evaluation parameters, so as to update the decision tree based on the evaluation parameters to generate a service processing model, improving the accuracy of the service processing model. Furthermore, various types of services are classified based on the service processing model to conduct classified supervision and processing of services, improving the efficiency of service processing.

[0109] The implementation example of this embodiment realizes the online, metric-based, and algorithmic supervision process. The intelligent supervision project starts from internal data, performs data cleaning, constructs an index variable system, and extracts the behavioral characteristics of employees in supervision matters; constructs a supervision model based on machine learning algorithms to automatically obtain high, medium, and low classifications of the supervision level of a matter or node, and the supervision process is completely online; the model can gradually understand the supervision object in depth, and the accuracy of the model is correspondingly improved. As the attributes and behaviors of the supervised person change, the supervision method changes automatically, effectively improving the efficiency of daily work management and enhancing the management quality.

[0110] It should be emphasized that to further ensure the privacy and security of the above service data, the above service data can also be stored in a node of a blockchain.

[0111] The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. Blockchain, in essence, is a decentralized database, a string of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity (anti-counterfeiting) of the information and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer, etc.

[0112] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0113] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), etc., or a random access memory (RAM), etc.

[0114] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially according to the order indicated by the arrows. Unless clearly stated herein, the execution of these steps has no strict order restriction, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0115] Further reference Figure 4 to Figure 2 As an implementation of the method shown above, an embodiment of an apparatus for processing service data is provided in this application. This apparatus embodiment corresponds to the method embodiment shown in Figure 2 and this apparatus can be specifically applied to various electronic devices.

[0116] Such as Figure 4As shown in the figure, the processing device 400 for service data according to this embodiment includes: an acquisition module 401, a classification module 402, a comparison module 403, and a display module 404. Among them:

[0117] The acquisition module 401 is used to acquire service data corresponding to each service name; the classification module 402 is used to extract data features in the service data by means of character matching, classify the data features by means of a decision tree, and determine the service type corresponding to the service name; the comparison module 403 is used to compare the service type with a preset type corresponding to the service name to generate an evaluation parameter; the generation module 404 is used to update the decision tree based on the evaluation parameter, and use the updated decision tree as a service processing model; the application module 405 is used to, when acquiring service information triggered by a user, classify the service information based on the service processing model, and acquire corresponding processing information according to the classification result for service processing.

[0118] Refer to Figure 5 , in some embodiments of the present application, based on the foregoing solution, the processing device 400 for service data further includes: an attribute determination module 4011, which is used to determine attribute values corresponding to the service data in each of the preset data dimensions based on the service data and the preset data dimensions; a data cleaning module 4012, which is used to perform data cleaning on the service data based on the attribute values corresponding to the service data.

[0119] In an embodiment of the present application, based on the foregoing solution, the data cleaning module 4012 specifically includes: a range acquisition subunit, which is used to acquire a normal data range corresponding to a preset data dimension; a deletion and retention subunit, which is used to, for the attribute values corresponding to the service data, retain the service data with attribute values within the normal data range, or delete the service data with attribute values not within the normal data range.

[0120] In some embodiments of the present application, based on the foregoing solution, the step of the classification module extracting data features in the service data by means of character matching specifically includes: a matching sub-module, which is used to perform character matching on the service data based on a preset data dimension to determine the data composition corresponding to the service data in each of the data dimensions; a feature sub-module, which is used to determine the data features corresponding to the data composition of this data dimension based on the correspondence between a preset threshold range for each of the data dimensions and the data features.

[0121] In some embodiments of the present application, based on the foregoing solution, the feature classification sub-module includes: an exponential calculation unit for calculating the Gini index corresponding to each piece of business data; an exponential classification unit for classifying the business data in the manner of a decision tree based on the Gini index to determine the business type corresponding to the business name.

[0122] In some embodiments of the present application, based on the foregoing solution, the evaluation parameters include at least one of the following parameters: precision, recall rate, and the comparison module 403 includes:

[0123] A first comparison sub-module for calculating the precision rate in the following manner: where TP represents the number of actual high supervision levels predicted as high supervision levels; FP represents the number of other supervision levels predicted as high supervision levels; and / or

[0124] A second comparison sub-module for calculating the recall rate in the following manner: where FN represents the number of other supervision levels predicted as other supervision levels.

[0125] In some embodiments of the present application, based on the foregoing solution, the generation module includes: a parameter acquisition sub-module for acquiring the associated parameters involved in the calculation in the decision tree; a model generation sub-module for updating the associated parameters based on the evaluation parameters to obtain an updated decision tree and generating the business processing model.

[0126] In some embodiments of the present application, based on the foregoing solution, the classification result includes the matter attribute corresponding to the business information; the processing device 400 for the business data further includes: an attribute acquisition sub-module for acquiring the business information triggered by the user, classifying the business information through the business processing model to determine the matter attribute corresponding to the business information; an information generation sub-module for generating reminder information corresponding to the business information based on the matter attribute; an information reminder sub-module for sending the reminder information to the associated party corresponding to the business information based on the matter attribute.

[0127] In the embodiments of the present application, by acquiring the business data corresponding to each business name, and based on the data features in the business data, classifying the business name in the manner of a decision tree to determine the business type corresponding to the business name, and then comparing the business type with the preset type corresponding to the business name to generate evaluation parameters, and updating the decision tree based on the evaluation parameters to generate a business processing model, the accuracy of the business processing model is improved. Furthermore, various types of businesses are classified based on the business processing model to classify and process the businesses, thereby improving the efficiency of business processing.

[0128] In the embodiments of the present application, by obtaining the service data corresponding to each service name, and based on the data characteristics in the service data, classifying the service names by means of a decision tree, determining the service type corresponding to the service name, and then comparing the service type with the preset type corresponding to the service name to generate an evaluation parameter, and updating the decision tree based on the evaluation parameter to generate a service processing model, the accuracy of the service processing model is improved. Furthermore, various types of services are classified based on the service processing model to classify, supervise, and process the services, thereby improving the efficiency of service processing.

[0129] To solve the above technical problems, the embodiments of the present application also provide a computer device. Specifically, please refer to Figure 6 , Figure 6 which is the basic structural block diagram of the computer device in this embodiment.

[0130] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are communicatively connected to each other through a system bus. It should be noted that only the computer device 6 with components 61 - 63 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art of the present technology can understand that a computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0131] The computer device can be a desktop computer, a notebook, a palm computer, a cloud server, and other computing devices. The computer device can perform human-computer interaction with the user through a keyboard, a mouse, a remote control, a touchpad, a voice control device, or other means.

[0132] The memory 61 includes at least one type of readable storage medium, which includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc. equipped on the computer device 6. Of course, the memory 61 may also include both the internal storage unit and the external storage device of the computer device 6. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions for the processing method of service data. In addition, the memory 61 may also be used to temporarily store various types of data that have been output or will be output.

[0133] In some embodiments, the processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run the computer-readable instructions stored in the memory 61 or process data, such as running the computer-readable instructions for the processing method of the service data.

[0134] The network interface 63 may include a wireless network interface or a wired network interface, and this network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0135] In the embodiment of the present application, by obtaining the service data corresponding to each service name, and based on the data characteristics in the service data, classifying the service names by means of a decision tree, determining the service type corresponding to the service name, and then comparing the service type with the preset type corresponding to the service name to generate an evaluation parameter, and updating the decision tree based on the evaluation parameter to generate a service processing model, the accuracy of the service processing model is improved. Furthermore, based on the service processing model, various types of services are classified to classify and supervise the services for processing, thereby improving the efficiency of service processing.

[0136] The present application also provides another implementation manner, that is, to provide a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor, so that the at least one processor executes the steps of the method for processing service data as described above.

[0137] In the embodiment of the present application, by obtaining service data corresponding to each service name, and based on the data characteristics in the service data, classifying the service names in the way of a decision tree to determine the service types corresponding to the service names, and then comparing the service types with the preset types corresponding to the service names to generate evaluation parameters, so as to update the decision tree based on the evaluation parameters to generate a service processing model, which improves the accuracy of the service processing model. Furthermore, various types of services are classified based on the service processing model to classify and supervise the services for processing, which improves the efficiency of service processing.

[0138] Through the description of the above implementation manners, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0139] Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all the embodiments. The preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing specific implementation manners, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields is similarly within the scope of the patent protection of the present application.

Claims

1. A method for processing service data, characterized in that, it includes the following steps: Obtain service data corresponding to each service name; Extract data features in the service data by means of character matching, classify the data features by means of a decision tree, and determine the service type corresponding to the service name; Compare the service type with a preset type corresponding to the service name to generate an evaluation parameter; Update the decision tree based on the evaluation parameter, and use the updated decision tree as a service processing model; When obtaining service information triggered by a user, classify the service information based on the service processing model, and obtain corresponding processing information according to the classification result for service processing; Among them, the step of extracting data features in the service data by means of character matching specifically includes: Perform character matching on the service data through preset data dimensions to determine the data composition in each data dimension corresponding to the service data; Based on the corresponding relationship between the preset threshold range for each data dimension and the data features, determine the data features corresponding to the data composition of this data dimension; Among them, the corresponding relationship between the threshold range and the data features is the feature degree corresponding to each specific numerical range.

2. The method for processing service data according to claim 1, characterized in that, after the step of obtaining service data corresponding to each service name, it further includes: Based on the service data and preset data dimensions, determine the attribute values corresponding to the service data in each preset data dimension; Perform data cleaning on the service data based on the attribute values corresponding to the service data.

3. The method for processing service data according to claim 2, characterized in that, the step of performing data cleaning on the service data based on the attribute values corresponding to the service data specifically includes: Obtain the normal data range corresponding to the preset data dimension; For the attribute values corresponding to the service data, retain the service data with attribute values within the normal data range, or delete the service data with attribute values not within the normal data range.

4. The method for processing service data according to claim 1, characterized in that, the step of classifying the data features by means of a decision tree to determine the service type corresponding to the service name specifically includes: Calculate the Gini index corresponding to each service data; Based on the Gini index, classify the service data by means of a decision tree to determine the service type corresponding to the service name.

5. The method for processing service data according to claim 1, characterized in that, updating the decision tree based on the evaluation parameter and using the updated decision tree as a service processing model includes: Obtain the associated parameters participating in the calculation in the decision tree; Update the associated parameters based on the evaluation parameter, obtain the updated decision tree, and generate the service processing model.

6. The method for processing service data according to claim 1, characterized in that, The classification result includes the matter attributes corresponding to the service information; when the service information triggered by the user is obtained, the service information is classified based on the service processing model, and the corresponding processing information is obtained according to the classification result for service processing, including: Obtain the service information triggered by the user, classify the service information through the service processing model, and determine the matter attributes corresponding to the service information; Generate reminder information corresponding to the service information based on the matter attributes; Based on the matter attributes, send the reminder information to the associated party corresponding to the service information.

7. A processing device for service data, characterized in that, it includes: An acquisition module for acquiring service data corresponding to each service name; A classification module for extracting data features in the service data by means of character matching, classifying the data features by means of a decision tree, and determining the service type corresponding to the service name; A comparison module for comparing the service type with the preset type corresponding to the service name to generate an evaluation parameter; A generation module for updating the decision tree based on the evaluation parameter and using the updated decision tree as a service processing model; An application module for classifying the service information based on the service processing model when the service information triggered by the user is obtained, and obtaining the corresponding processing information according to the classification result for service processing; Wherein, the classification module includes: a matching sub-module for performing character matching on the service data based on a preset data dimension to determine the data composition in each data dimension corresponding to the service data; a feature sub-module for determining the data features corresponding to the data composition of this data dimension based on the corresponding relationship between the preset threshold range for each data dimension and the data features; Wherein, the corresponding relationship between the threshold range and the data features is the feature degree corresponding to each specific numerical range.

8. A computer device, including a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, the steps of the service data processing method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that, computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the steps of the service data processing method according to any one of claims 1 to 6 are implemented.

Images