Financial system review processing method and device, electronic equipment and storage medium

Abstract

The application provides a financial system comment processing method and device, electronic equipment and a storage medium, and belongs to the technical field of financial services. The method comprises the following steps: obtaining business comment data from a target financial system; determining a target comment rule model matched with the target financial system from a plurality of preset candidate comment rule models according to the target financial system; performing multi-dimensional comment identification processing on the business comment data based on the target comment rule model to obtain a target identification result; analyzing the target identification result based on a preset monitoring response rule to obtain a business response strategy for the business comment data; and triggering a corresponding business processing flow according to the business response strategy. The application can improve the efficiency of financial system comment processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of financial services, and in particular to a financial system comment processing method and device, an electronic device and a storage medium. BACKGROUND

[0002] In the field of financial services, various financial systems are needed to carry out daily work. In order to continuously optimize system functions and improve user experience, it is necessary to obtain and process system comment information of system users in a timely manner. Comment information includes opinion feedback, function evaluation, complaints, etc., which is of great guiding significance to system optimization and business development.

[0003] In related technologies, financial insurance system comment processing often relies on manual summary reporting by local branches or automated tools based on simple keyword matching. The manual summary method has multiple hierarchical transfers, low efficiency and is prone to information distortion, making it difficult to handle massive feedback information. At the same time, the automated tool based on keyword matching has low recognition accuracy when dealing with insurance professional terms and complex business scenarios, making it difficult to meet the precision and intelligence requirements of insurance business for comment processing. Therefore, there is an urgent need for a more efficient and accurate financial system comment processing method. SUMMARY

[0004] The main purpose of the embodiments of the present application is to provide a financial system comment processing method and device, an electronic device and a storage medium, which aims to improve the efficiency of financial system comment processing.

[0005] To achieve the above purpose, the first aspect of the embodiments of the present application provides a financial system comment processing method, which comprises:

[0006] Obtaining business comment data from a target financial system;

[0007] According to the target financial system, determining a target comment rule model matched to the target financial system among a plurality of preset candidate comment rule models;

[0008] Based on the target comment rule model, performing multi-dimensional comment identification processing on the business comment data to obtain a target identification result;

[0009] Based on a preset monitoring response rule, analyzing the target identification result to obtain a business response strategy for the business comment data;

[0010] According to the business response strategy, triggering a corresponding business processing flow.

[0011] In some embodiments, the target comment rule model matched to the target financial system among a plurality of preset candidate comment rule models comprises:

[0012] obtaining system characteristics of the target financial system, wherein the system characteristics comprise business type identification and function module identification;

[0013] performing keyword processing on the business comment data to extract key field characteristics;

[0014] determining, according to the system characteristics and the key field characteristics, a target comment rule model matching the target financial system from a plurality of preset candidate comment rule models.

[0015] In some embodiments, the determining, according to the system characteristics and the key field characteristics, a target comment rule model matching the target financial system from a plurality of preset candidate comment rule models comprises:

[0016] matching the system characteristics with applicable scenarios in the candidate comment rule models to obtain a first matching degree score;

[0017] matching the key field characteristics with rule items in the candidate comment rule models to obtain a second matching degree score;

[0018] performing weighted calculation on the first matching degree score and the second matching degree score to obtain a target matching degree score;

[0019] sorting the target matching degree scores of the candidate comment rule models to determine a candidate comment rule model with a highest target matching degree score as the target comment rule model.

[0020] In some embodiments, the performing, based on the target comment rule model, multi-dimensional comment identification processing on the business comment data to obtain a target identification result comprises:

[0021] performing scanning on the business comment data based on sensitive word rules in the target comment rule model to identify financial sensitive information to obtain a to-be-processed comment text;

[0022] performing keyword extraction and feature vector calculation on the to-be-processed comment text to obtain comment text characteristics;

[0023] performing, based on the target comment rule model, multi-dimensional comment identification processing on the to-be-processed comment text and the comment text characteristics to obtain a target identification result.

[0024] In some embodiments, the performing, based on the target comment rule model, multi-dimensional comment identification processing on the to-be-processed comment text and the comment text characteristics to obtain a target identification result comprises:

[0025] perform text clustering analysis on the to-be-processed comment text based on the comment text features, to obtain a comment category of the to-be-processed comment text;

[0026] perform context semantic analysis on the to-be-processed comment text based on a semantic recognition rule in the target comment rule model, to obtain a comment tendency of the to-be-processed comment text;

[0027] calculate a text similarity of different business comment data according to the comment text features, and mark corresponding business comment data as a hot comment when the text similarity is greater than a preset threshold;

[0028] integrate the comment category, the comment tendency, and the hot comment, to generate the target recognition result.

[0029] In some embodiments, the integrating the comment category, the comment tendency, and the hot comment, to generate the target recognition result, includes:

[0030] generating a category label of the business comment data according to the comment category, where the category label is used to represent a belonging type of the business comment data;

[0031] performing grade division on the business comment data according to a positive and negative nature of the comment tendency and a preset sentiment grading standard, to obtain a sentiment grade of the business comment data;

[0032] determining a focus grade of the business comment data based on a marked state of the hot comment;

[0033] obtaining the target recognition result according to the belonging type, the sentiment grade, and the focus grade.

[0034] In some embodiments, the analyzing the target recognition result based on a preset monitoring response rule, to obtain a business response strategy for the business comment data, includes:

[0035] determining a processing priority of the business comment data according to a belonging type, a sentiment grade, and a focus grade in the target recognition result;

[0036] determining a target response rule from a plurality of preset response rules based on the processing priority;

[0037] generating a business response strategy for the business comment data according to the target response rule, where the business response strategy includes a processing department, a processing time limit, and a processing manner.

[0038] To achieve the above object, a second aspect of the embodiments of the present application provides a financial system comment processing device, which comprises:

[0039] an acquisition module configured to acquire service comment data from a target financial system;

[0040] a matching module configured to determine, according to the target financial system, a target comment rule model matched to the target financial system from a plurality of preset candidate comment rule models;

[0041] an identification module configured to perform multi-dimensional comment identification processing on the service comment data based on the target comment rule model to obtain a target identification result;

[0042] a strategy module configured to analyze the target identification result based on a preset monitoring response rule to obtain a service response strategy for the service comment data;

[0043] a response module configured to trigger a corresponding service processing flow according to the service response strategy.

[0044] To achieve the above object, a third aspect of embodiments of the present application provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.

[0045] To achieve the above object, a fourth aspect of embodiments of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0046] The financial system comment processing method and device, electronic device and storage medium provided by the present application acquire service comment data from a target financial system, determine a target comment rule model matched to the target financial system from a plurality of preset candidate comment rule models according to the target financial system, perform multi-dimensional comment identification processing on the service comment data based on the target comment rule model to obtain a target identification result, analyze the target identification result based on a preset monitoring response rule to obtain a service response strategy for the service comment data, and trigger a corresponding service processing flow according to the service response strategy.

[0047] The application firstly acquires business comment data of a target financial system, introduces a plurality of preset candidate comment rule models, can select the most suitable comment rule model according to the business characteristics of different financial systems, improves the pertinence of comment processing, avoids the insufficient accuracy caused by single-dimensional identification based on the multidimensional identification method of the target comment rule model, analyzes through the preset monitoring response rule, realizes the systematic comment response management, better meets the comment processing demand of the financial system, establishes the quick response mechanism between comment identification and business processing through the formulation of business response strategy, triggers the corresponding business processing flow according to the business response strategy, and improves the efficiency of financial system comment processing. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a flowchart of the financial system comment processing method provided by the embodiment of the application;

[0049] Figure 2 is a flowchart of step S102 in Figure 1 ;

[0050] Figure 3 is a flowchart of step S203 in Figure 2 ;

[0051] Figure 4 is a flowchart of step S103 in Figure 1 ;

[0052] Figure 5 is a flowchart of step S403 in Figure 4 ;

[0053] Figure 6 is a flowchart of step S504 in Figure 5 ;

[0054] Figure 7 is a flowchart of step S104 in Figure 1 ;

[0055] Figure 8 is a schematic diagram of the financial system comment processing method provided by the embodiment of the application;

[0056] Figure 9 is still another schematic diagram of the financial system comment processing method provided by the embodiment of the application;

[0057] Figure 10 is a structural schematic diagram of the financial system comment processing device provided by the embodiment of the application;

[0058] Figure 11 is a hardware structural schematic diagram of the electronic equipment provided by the embodiment of the application. DETAILED DESCRIPTION

[0059] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0060] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0062] First, the terms involved in the present application are analyzed:

[0063] Financial system (Financial System): refers to an information system that provides business processing, transaction management, customer service, etc. for financial institutions. It includes but is not limited to banking systems, securities trading systems, insurance business systems, payment and clearing systems, etc. These systems carry the core business processes of financial institutions, and have high requirements for system stability, security and user experience. For example, the securities trading system needs to support real-time trading, market query, fund transfer and other functions, and the banking system needs to support deposit and withdrawal, transfer, financial management and other financial businesses.

[0064] Based on this, the embodiments of the present application provide a financial system comment processing method and device, electronic equipment and storage medium, which aims to improve the efficiency of financial system comment processing.

[0065] The financial system comment processing method and device, electronic equipment and storage medium provided by the embodiments of the present application are specifically described by the following embodiments, first the financial system comment processing method in the embodiments of the present application is described.

[0066] The financial system comment processing method provided by the embodiments of the present application relates to the technical field of financial services. The financial system comment processing method provided by the embodiments of the present application can be applied to a terminal, can also be applied to a server end, and can also be software running in the terminal or the server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as a stand-alone physical server, can also be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and big data and artificial intelligence platforms; and the software can be an application that implements the financial system comment processing method, but is not limited to the above forms.

[0067] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor 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, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0068] It should be noted that in each specific embodiment of the present application, when relevant processing needs to be performed on data related to the identity or characteristics of the user, such as user information, user behavior data, user history data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain sensitive personal information of the user, the separate permission or separate consent of the user will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for enabling the embodiments of the present application to normally operate will be obtained.

[0069] Figure 1 is an optional flowchart of the financial system comment processing method provided by the embodiments of the present application, Figure 1 The method in can include but is not limited to steps S101 to S105.

[0070] In step S101, business comment data from a target financial system is acquired.

[0071] In step S102, a target comment rule model that matches the target financial system is determined from among a plurality of preset candidate comment rule models according to the target financial system.

[0072] In step S103, multi-dimensional comment identification processing is performed on the business comment data based on the target comment rule model, and a target identification result is obtained.

[0073] In step S104, a business response strategy for the business comment data is obtained by analyzing the target identification result based on a preset monitoring response rule.

[0074] In step S105, a corresponding business processing flow is triggered according to the business response strategy.

[0075] The steps S101 to S105 shown in the embodiments of the present application first acquire business comment data of a target financial system, introduce a plurality of preset candidate comment rule models, and can select the most suitable comment rule model according to the business characteristics of different financial systems to improve the pertinence of comment processing. The multi-dimensional identification method based on the target comment rule model avoids the lack of accuracy caused by single-dimensional identification, analyzes through the preset monitoring response rule, realizes systematic comment response management, better meets the comment processing needs of the financial system, establishes a quick response mechanism between comment identification and business processing through the formulation of a business response strategy, triggers the corresponding business processing flow according to the business response strategy, and improves the efficiency of financial system comment processing.

[0076] In step S101 of some embodiments, the business comment data generated by the target financial system of the user in each business scenario is acquired in real time through an API interface. The business comment data includes but is not limited to various types of comment information such as opinion feedback, function evaluation, complaints, etc. The opinion feedback mainly involves the improvement suggestions of the user on the functions and business processes of the target financial system. The function evaluation includes the scoring and use experience description of the user on each function module of the target financial system. The complaint information contains various problems and dissatisfaction encountered by the user in the process of using the target financial system. The business comment data is preliminarily processed, including removing duplicate data, supplementing comment time and source metadata information, and storing in the corresponding database according to different comment types. At the same time, the context information of the comment is saved, such as the user operation track, system response time, etc. These information has important value for subsequent comment analysis and problem positioning.

[0077] For example, the business comment data of the opinion feedback type includes "the business operation process is complex, and it is suggested to simplify the approval link", "the mobile banking transfer limit setting is unreasonable, and it is suggested to provide a more flexible quota adjustment method"; the function evaluation type includes "the operation of the financial product purchase function is convenient, and the interface is clear", "the online banking login verification method is complicated and needs to be improved"; the complaint type includes "the system response is slow, affecting the timeliness of transactions", "the customer information update fails, causing business handling to be blocked", and the like.

[0078] In step S102 of some embodiments, the preset multiple candidate comment rule models are evaluated and selected. The candidate comment rule models can include different rule models of custom business feedback type, function evaluation, complaint, opinion feedback, etc. Each candidate comment rule model contains complete rule definition, covering comment classification standard, keyword library, sensitive word library, business terminology correspondence table, and rule configuration of multiple dimensions. According to the specific characteristics of the target financial system, such as business type, user group characteristics, comment data characteristics, etc., a specific algorithm is used to select the most matched target comment rule model from multiple candidate comment rule models. In the model selection process, multiple factors such as the application scope of the model, the historical application effect, and the rule coverage are considered comprehensively to ensure that the selected model can meet the comment processing needs of the target financial system to the greatest extent.

[0079] Please refer to Figure 2 In some embodiments, step S102 can include but is not limited to steps S201 to S203:

[0080] Step S201, acquiring the system characteristics of the target financial system.

[0081] Among them, the system characteristics include business type identification and function module identification.

[0082] Step S202, performing keyword processing on the business comment data to extract key field characteristics.

[0083] Step S203, according to the system characteristics and the key field characteristics, determining the target comment rule model matched to the target financial system from the multiple preset candidate comment rule models.

[0084] In step S201 of some embodiments, the system characteristics of the target financial system are obtained through interface calls or configuration file reading, including system type, deployment environment, user scale, and other basic parameters. The business type identifier is extracted, such as securities trading, insurance sales, financial product business type information, which directly reflects the business attributes and service areas of the target financial system. At the same time, the function module identifier is obtained, including specific function module division, inter-module dependency relationship, core function characteristics, and other information. These system characteristic information is stored in a structured manner for subsequent model matching analysis.

[0085] For example, for an insurance sales system, the business type identifier obtained includes "personal insurance", "group insurance", "insurance claims", etc., and the function module identifier includes "product display", "online insurance", "policy management", "claims service", and other specific function module identifier information. For a securities trading system, the business type identifier may include "stock trading", "fund trading", "futures trading", etc., and the function module identifier includes "market query", "transaction order", "fund transfer", "account management", etc. These system characteristics provide a basis for subsequent rule model matching.

[0086] In step S202 of some embodiments, a complete keyword processing mechanism is established to extract valuable key field features from business comment data. First, the business comment data is preprocessed, including text segmentation, stop word removal, standardization, and other basic operations, and then through natural language processing technology, the keywords and phrases in the business comment data are identified, which may involve specific business terms, function descriptions, problem phenomena, etc. Then, the keywords are frequency counted and importance analyzed to filter out the most representative key fields. At the same time, the association between these key fields is analyzed to build a key field network, so as to more comprehensively understand the characteristics of the business comment data content.

[0087] For example, for business comment data such as "system response is slow, transaction confirmation is delayed, and seriously affects the trading experience", the key fields "slow response", "transaction confirmation", and "delay" are extracted, and their association with system performance, transaction function, and other aspects is labeled. According to historical data and expert experience, different key fields are assigned weights, such as performance-related word weight 0.8, function-related word weight 0.6, and experience-related word weight 0.4, to highlight the influence of important features.

[0088] In step S203 of some embodiments, by constructing an intelligent model matching mechanism, the most suitable target comment rule model is selected from a plurality of preset candidate comment rule models. First, according to system characteristics such as business type identifier and function module identifier, the candidate comment rule model is preliminarily screened, and a possible applicable model set is filtered out, then the rule characteristics of these candidate models are analyzed, including rule coverage, applicable scene, historical application effect and other dimensions, the extracted key field characteristics are matched with the rule characteristics of the candidate comment rule model, the matching degree of each candidate model with the current scene is calculated, and the target comment rule model matched with the target financial system is determined.

[0089] For example, when the system characteristics obtained show that this is a target financial system related to securities trading, and the key field characteristics frequently appear "stock trading", "order placement", "market query" and other transaction-related terms, the matching mechanism will preferentially select the comment rule model optimized for the securities trading scene. By comprehensively scoring the business field matching degree, function coverage degree, keyword matching degree and historical effect score, the candidate comment rule model with the highest score is selected as the target comment rule model.

[0090] Through the above steps S201 to S203, by obtaining the system characteristics of the target financial system and the key field characteristics of the business comment data, the matching comment rule model can be more accurately selected, and the precision of model selection is improved; by analyzing the system characteristics and the key field characteristics, the errors that may be caused by simply relying on experience to select the model are avoided, the intelligence of model selection is realized, and the individualized needs of different financial systems are better met.

[0091] Please refer to Figure 3 In some embodiments, step S203 can include but is not limited to steps S301 to S304:

[0092] Step S301, match the system characteristics with the applicable scene in the candidate comment rule model to obtain a first matching degree score.

[0093] Step S302, match the key field characteristics with the rule items in the candidate comment rule model to obtain a second matching degree score.

[0094] Step S303, weighted calculation is performed on the first matching degree score and the second matching degree score to obtain a target matching degree score.

[0095] Step S304, the target matching degree scores of the candidate comment rule models are sorted, and the candidate comment rule model with the highest target matching degree score is determined as the target comment rule model.

[0096] In step S301 of some embodiments, by establishing the mapping relationship between system features and model applicable scenarios, accurate matching degree evaluation is realized. First, the system features are standardized, including the standardized representation of business type identification and function module identification, and then the standardized system features are matched with the pre-defined applicable scenarios in the candidate comment rule model, the similarity between the feature vectors is calculated, and the first matching degree score is obtained. In the matching process, the cosine similarity algorithm can be used to calculate the distance between the feature vectors, and the score range is a real number between 0 and 1.

[0097] For example, for a securities trading system, its system features include business type identification such as "stock trading" and "fund trading", and function module identification such as "transaction order" and "fund transfer". When matched with the applicable scenario of a certain candidate comment rule model, if the model is specifically designed for the securities trading field and covers the related function modules, a higher first matching degree score, such as 0.85, can be obtained; otherwise, if the model is designed for other financial fields, a lower score, such as 0.3, can be obtained. The matching score based on system features provides an important reference for subsequent target comment rule model selection.

[0098] In step S302 of some embodiments, a refined scoring mechanism is established for the matching of key field features and rule items. The extracted key field features are vectorized, a feature vector is constructed, and the feature vector is matched with the rule items in the candidate comment rule model to calculate the matching degree between them. The matching process not only considers the direct matching of keywords, but also considers semantic correlation such as synonyms and near-synonyms, and uses a word vector model to calculate semantic similarity, and finally obtains a second matching degree score. For example, if the key field features include performance-related words such as "transaction delay" and "slow system response", and are matched with a candidate comment rule model that specifically handles system performance problems, a higher second matching degree score, such as 0.9, can be obtained; while matched with a candidate comment rule model that handles other types of problems, a lower score, such as 0.4, can be obtained. This semantic-level matching score further improves the accuracy of model selection.

[0099] In step S303 of some embodiments, a scientific weighting calculation method is used to reasonably combine the first matching degree score and the second matching degree score. When setting the weight coefficient, it can be based on actual application experience, for example, the weight of system feature matching degree is set to 0.6, and the weight of key field feature matching degree is set to 0.4. The target matching degree score comprehensively reflects the applicability of the candidate comment rule model in both system feature and key field feature dimensions.

[0100] In step S304 of some embodiments, based on the calculated target matching degree score, a strict target review rule model selection mechanism is established. First, the target matching degree scores of all candidate review rule models are sorted in descending order to generate a sorted list, and then the candidate review rule model ranked first, i.e., the candidate review rule model with the highest target matching degree score, is selected as the final target review rule model. If multiple candidate review rule models have the same target matching degree score, the time efficiency and resource consumption of the model are further considered as secondary factors for screening.

[0101] Through steps S301 to S304 described above, by respectively scoring the matching degrees of system features and key field features and combining the weighted calculation method, the applicability of the candidate review rule model can be more comprehensively and objectively evaluated; through the final sorting selection method, the optimal target review rule model is ensured to be selected, improving the accuracy and scientificity of model selection.

[0102] In step S103 of some embodiments, based on the selected target review rule model, a complete multi-dimensional review identification processing mechanism is established. First, the business review data is preprocessed, including text cleaning, word segmentation, and removal of stop words for basic processing; then, through a deep learning algorithm, the review information is automatically classified, and the business review data is accurately divided into the corresponding business categories; then, a pre-trained language model is used for sensitive word identification to timely discover content that may involve sensitive information or have risks; at the same time, through semantic understanding and text clustering algorithms, hot issues and issues that users generally pay attention to are identified; finally, natural language processing technology is used for review opinion extraction to extract key demands, emotional tendencies, and specific suggestions in the business review data.

[0103] For example, for a piece of business review data "The mobile banking transfer function often malfunctions, and transfer failures have occurred multiple times, but the funds have been deducted. This seriously affects the user experience, and it is hoped that it will be resolved as soon as possible", through multi-dimensional identification processing, the following target identification results can be obtained: the review type is a function complaint, it involves mobile banking transfer business, the problem type is transaction anomaly, the emotional tendency is strong dissatisfaction, and the core demand is to repair the transfer function and ensure fund safety. These target identification results provide a clear direction for subsequent processing.

[0104] Please refer to Figure 4 In some embodiments, step S103 can include but is not limited to steps S401 to S403:

[0105] Step S401, based on the sensitive word rules in the target review rule model, scanning the business review data to identify financial sensitive information, and obtaining the to-be-processed review text.

[0106] Step S402, keyword extraction and feature vector calculation are performed on the to-be-processed review text to obtain review text features.

[0107] Step S403, multi-dimensional review identification processing is performed on the to-be-processed review text and the review text features based on the target review rule model to obtain a target identification result.

[0108] In step S401 of some embodiments, a complete sensitive information identification mechanism is established for the particularity of the financial field. First, a pre-defined sensitive word rule library in the target review rule model is loaded, which contains sensitive word entries in multiple categories such as account information, transaction data, and personal privacy. A multi-mode matching algorithm is used to perform full-text scanning on the business review data to identify possible sensitive information. The identified sensitive information is desensitized or marked to generate the to-be-processed review text.

[0109] In step S402 of some embodiments, natural language processing techniques are used to analyze the to-be-processed review text in depth. First, a word segmentation algorithm is used to segment the to-be-processed review text to obtain basic morpheme units. Then, keywords in the to-be-processed review text are extracted based on the algorithm, considering multiple feature dimensions such as word frequency, position, and semantics. The extracted keywords are converted into feature vectors, and word embedding techniques are used to map the to-be-processed review text information to a high-dimensional feature space to obtain quantifiable review text features.

[0110] For example, for the to-be-processed review text "the system response is particularly slow, often appears to be stuck, affecting transaction efficiency", the morpheme units "system / response / particularly / slow / often / appears / stuck / affect / transaction / efficiency" are obtained through word segmentation, the keywords "system response", "stuck", and "transaction efficiency" are extracted, and their feature weights are calculated to generate a review text feature vector that fully represents the core features of the to-be-processed review text. These review text features provide an important basis for subsequent multi-dimensional identification.

[0111] In step S403 of some embodiments, the to-be-processed comment text is comprehensively analyzed based on the multi-dimensional identification rules in the target comment rule model. According to the comment text features, the comment type is identified, the to-be-processed comment text is divided into different categories such as function evaluation, complaint feedback, and suggestion opinion, then the sentiment tendency analysis is performed to judge the positive, negative or neutral characteristics of the to-be-processed comment text, then the specific business field and problem type involved in the to-be-processed comment text are identified through topic clustering analysis, and finally the specific appeal and suggestion content in the to-be-processed comment text are extracted in combination with the context information. For example, for a to-be-processed comment text and its comment text features, the multi-dimensional comment identification processing may obtain the following target identification results: the comment type is "function complaint", the sentiment tendency is "strong dissatisfaction", the involved theme is "system performance problem", the specific appeal is "improve system response speed", and the urgency level is "high".

[0112] Through the above steps S401 to S403, first, sensitive information identification is performed to ensure the compliance of business comment data; then feature extraction and vectorization processing are performed to provide a basis for subsequent multi-dimensional identification; and finally, comprehensive identification analysis is performed based on the target comment rule model to realize accurate identification and classification of business comment data.

[0113] Please refer to Figure 5 In some embodiments, step S403 can include but is not limited to steps S501 to S504:

[0114] Step S501, based on the comment text features, performing text clustering analysis on the to-be-processed comment text to obtain the comment category of the to-be-processed comment text.

[0115] Step S502, based on the semantic identification rules in the target comment rule model, performing context semantic analysis on the to-be-processed comment text to obtain the comment tendency of the to-be-processed comment text.

[0116] Step S503, according to the comment text features, calculating the text similarity of different business comment data, and when the text similarity is greater than a preset threshold, marking the corresponding business comment data as a hot comment.

[0117] Step S504, integrating the comment category, comment tendency and hot comment to generate a target identification result.

[0118] In step S501 of some embodiments, a text clustering technique is used to classify the to-be-processed review texts. A feature space is constructed based on the features of the review texts, each to-be-processed review text is represented as a vector in the feature space, a clustering algorithm such as K-means is used to automatically cluster the vectors according to the distance relationship between the vectors, and the clustering results are semantically annotated based on business knowledge to obtain clear classification of the review categories.

[0119] For example, for a batch of to-be-processed review texts of a financial system, the clustering analysis may obtain the following review categories: function abnormality category (such as "transaction failure", "system lag"), business consultation category (such as "product purchase process", "account opening requirement"), service experience category (such as "complicated operation", "unfriendly interface"), etc. Each review category has its specific feature vector center, and a new to-be-processed review text can be determined to belong to a review category by calculating the distance from the new to-be-processed review text to the center.

[0120] In step S502 of some embodiments, a deep learning-based natural language processing technique is used to analyze the review tendency. Semantic recognition rules in the target review rule model are loaded, including sentiment dictionaries, semantic rule libraries, etc., semantic dependency analysis is performed on the to-be-processed review texts, core viewpoints and sentiment tables are recognized, and the real review tendency of the to-be-processed review texts is accurately understood through context relationship analysis, avoiding judgment bias caused by relying solely on keywords.

[0121] For example, for the to-be-processed review text "the function design is good, but the response is too slow, which completely affects the use experience", through context semantic analysis, it can be recognized that although the function design is positively evaluated, the overall review tendency is negative, and the main dissatisfaction is the system performance. A detailed review tendency analysis result is given, including positive factors, negative factors, and their respective weights.

[0122] In step S503 of some embodiments, a text similarity calculation model is constructed to identify hot review. A word vector model is used to calculate the text similarity between different to-be-processed review texts, and a cosine similarity algorithm is used for quantitative calculation. A preset threshold of text similarity is set, when the text similarity between a group of to-be-processed review texts exceeds the preset threshold, the group of to-be-processed review texts is marked as a related review cluster, and then based on the number of reviews, time distribution, etc., it is determined whether the review cluster constitutes a hot review.

[0123] For example, if multiple to-be-processed review texts with similar content appear within a short period of time, such as "unable to log in to the system", "login page cannot be opened", "login verification fails", etc., and the text similarity between them all exceeds the preset threshold, then this group of business review data is marked as a hot review, indicating that the login function may have a universal problem and needs to be prioritized.

[0124] In step S504 of some embodiments, a multi-dimensional comment result integration mechanism is adopted. First, a unified result representation model is established to organize the information of comment categories, comment tendencies and hot comment labels according to a predefined format, set weight coefficients for the recognition results of different dimensions to reflect their importance in the overall evaluation of the target recognition result, generate a structured target recognition result containing complete analysis information of the comment text to be processed.

[0125] For example, the target recognition result of a comment text to be processed can include: comment category = "function abnormality category", comment tendency = "strong dissatisfaction", problem type = "system performance", hot comment = "yes", influence range = "extensive", and urgency = "high". The multi-dimensional structured target recognition result provides sufficient basis for subsequent accurate processing and analysis. The confidence of the target recognition result can also be calculated during the integration process to ensure the reliability of the result.

[0126] Through the above steps S501 to S504, the comment is accurately classified through text clustering analysis, the comment tendency is accurately grasped through semantic analysis, the hot issues are identified through similarity calculation, and finally the multi-dimensional analysis results are integrated to form a comprehensive target recognition result, which improves the accuracy and efficiency of comment processing.

[0127] Please refer to Figure 6 In some embodiments, step S504 can include but is not limited to steps S601 to S604:

[0128] Step S601, generating a category label of business comment data according to the comment category.

[0129] The category label is used to represent the type of business comment data.

[0130] Step S602, dividing the business comment data into levels according to the positive and negative of the comment tendency and the preset sentiment grading standard to obtain the sentiment level of the business comment data.

[0131] Step S603, determining the attention level of the business comment data based on the label state of the hot comment.

[0132] Step S604, obtaining the target recognition result according to the type, sentiment level and attention level.

[0133] In step S601 of some embodiments, a standardized category label system is established, and the comment categories are mapped into a pre-defined label system according to the characteristics of the business field. The system includes two levels of main labels and sub-labels. The main labels represent the main business direction of the business comment data, such as "function class", "business class", "service class", etc. The sub-labels further subdivide specific problem types, such as "system performance", "operation experience", "business consultation", etc. This hierarchical label system can accurately reflect the attribution type of the business comment data.

[0134] In step S602 of some embodiments, a multi-level sentiment rating evaluation system is constructed. The comment tendency is preliminarily divided according to its positive or negative nature, and then combined with pre-set sentiment grading standards for fine-grained grading. The sentiment grading standards can include five levels: extremely positive, positive, neutral, negative, and extremely negative. By evaluating the intensity of sentiment words and the degree of modifier words in the business comment data, the final sentiment rating is determined.

[0135] For example, for the business comment data "the system interface design is very bad, the operation is extremely inconvenient, and it seriously affects work efficiency", by analyzing the sentiment words "bad", "inconvenient" and the degree words "very", "extremely", and "seriously", it is determined that the sentiment rating is extremely negative. The detailed basis for the sentiment determination, including the key words and their weights, is recorded to provide sufficient support for the determination of the sentiment rating.

[0136] In step S603 of some embodiments, a scientific attention level division method is adopted. Based on the marked state of the hot comment, combined with factors such as the time density, user range, and impact degree of the business comment data, an attention level evaluation model is established. For example, the attention level is divided into four levels: emergency, high attention, ordinary attention, and general. For the business comment data that has been marked as a hot comment, the specific attention level is determined according to its characteristic parameters.

[0137] For example, if a certain type of business comment data appears a large number of similar content in a short time, and involves core business functions, such as "transfer function cannot be used", it may be classified as an emergency level of attention. The determination of the attention level considers multiple quantitative indicators, such as the number of similar comments exceeding a threshold value, the number of affected users exceeding a benchmark value, etc., to ensure the scientificity of the attention level division.

[0138] In step S604 of some embodiments, a complete target recognition result generation mechanism is constructed. A unified result representation format is established, which includes information of the three core dimensions of attribution type, sentiment rating, and attention level. According to the importance of different dimensions, weight coefficients are set to generate a comprehensive evaluation score, forming a structured target recognition result, which provides detailed reference for subsequent processing and analysis.

[0139] Through the above steps S601 to S604, through the standardization processing and grade division of multi-dimensional features, the fine classification and grading of business comment data are realized, and clear priority basis is provided for subsequent response processing, improving the pertinence and efficiency of comment processing.

[0140] In step S104 of some embodiments, by constructing a monitoring response rule system, the target recognition result is analyzed in depth and a business response strategy is formulated. The monitoring response rule contains multiple dimensional configurations, including response priority division standards of different types of comments, response time limit requirements, processing flow definition, response mode selection standards, etc. According to the importance, urgency, influence range and other characteristics of the business comment data, the most suitable business response strategy is automatically generated by referring to the monitoring response rule. In the strategy formulation process, multiple factors such as resource status and processing capacity are considered to ensure the executability of the business response strategy, and a dynamic adjustment mechanism is established to optimize and adjust the business response strategy according to the actual execution situation.

[0141] Please refer to Figure 7 In some embodiments, step S104 can include but is not limited to steps S701 to S703:

[0142] Step S701, according to the ownership type, emotion level and attention level in the target recognition result, the processing priority of the business comment data is determined.

[0143] Step S702, based on the processing priority, the target response rule is determined from the preset multiple response rules.

[0144] Step S703, according to the target response rule, the business response strategy for the business comment data is generated.

[0145] Among them, the business response strategy includes processing department, processing time limit and processing mode.

[0146] In step S701 of some embodiments, the basic weight is set for the ownership type of the business comment data, such as the function class problem weight is higher than the general consultation class problem, then the weight is adjusted combined with the emotion level, the negative emotion level will improve the processing priority, finally the influence of the attention level is considered, for the hot issue or high attention problem, higher processing priority is given, through the comprehensive calculation of the three dimensions, the final processing priority is obtained. For example, for a piece of business comment data, its ownership type is "function class-transaction exception", emotion level is "extremely negative", and attention level is "urgent", if the processing priority is divided into first level, second level, third level and fourth level, the business comment data can be divided into the highest first level for priority processing.

[0147] In step S702 of some embodiments, standard processing procedures for different types of problems are defined in the preset response rule library, including processing steps, response time limits, escalation mechanisms, etc. According to the processing priority of business comment data, the target response rule of the corresponding level is matched. For high processing priority problems, more stringent target response rules are matched, including shorter response time limits and higher level processing personnel.

[0148] In step S703 of some embodiments, the processing department is determined according to the target response rule, such as the technical department, the business department, the customer service department, etc. The processing time limit is set, including the first response time, the solution providing time, the final processing completion time, etc. The specific processing method is determined, including problem repair, process optimization, user communication, etc.

[0149] Through the above steps S701 to S703, the processing priority is determined through comprehensive evaluation of multi-dimensional features, and the corresponding target response rule is selected based on the priority, and finally the specific business response strategy is generated, which realizes the precision and standardization of comment processing and improves the response efficiency.

[0150] In step S105 of some embodiments, based on the formulated business response strategy, a complete business processing flow triggering mechanism is established. First, according to the priority and urgency of the business response strategy, the starting order of the business processing flow is determined. For high priority problems such as system serious failure and important customer complaints, emergency processing flow is triggered immediately, including creating emergency work order, notifying relevant responsible person, starting emergency plan, etc. For regular function evaluation and suggestion, it is included in the product optimization library and analyzed and evaluated regularly and included in the iteration plan. A full-process task tracking mechanism is established to ensure that each business comment data can be processed in time and effectively through task status update, processing progress monitoring, delay warning, etc. Provide multiple response notification channels, including email notification, SMS reminder, system message, etc. According to the needs of different roles, choose the appropriate notification method to ensure that the information transmission in the processing process is timely and accurate. After processing, generate processing report to record processing process, solution and processing result, and deposit related experience and best practice into knowledge base to provide reference for subsequent similar problem processing. The whole business processing flow is built on the high availability architecture, through cache mechanism, task queue, failure retry, etc. Technical means to ensure the stability and reliability of business processing flow.

[0151] Please refer to Figure 8 , Figure 8is a schematic diagram of a financial system comment processing method provided by an embodiment of the present application, applied to a comment processing platform. First, a comment writing module acquires business comment data from a target financial system, such as opinion feedback, function evaluation, complaint information, and the like, and collects various comment data generated by users in the process of using various business systems of the financial system in real time. A rule model module is responsible for managing and applying various comment rule models, including self-defined evaluation rules, sensitive word management, keyword management, rule matching analysis, and the like, and realizes personalized rule configuration and model matching for different target financial systems through these functions. A comment recognition module realizes multi-dimensional analysis and processing of business comment data, including automatic classification and recognition, sensitive word recognition, hot issue recognition, context semantic recognition, text clustering, comment opinion extraction, and the like, and realizes comprehensive analysis and understanding of comment data through these functions. Then, a storage module can use diversified storage schemes, including cache, database, big data, data flow, ES, and the like, to realize efficient storage and rapid retrieval of different types of data, and the combination of these storage schemes guarantees high performance and reliability. A list module can provide display and management functions of comment data, including comment list, detail viewing, statistical analysis, metadata management, and hot issue display, and the like, to facilitate management personnel to master comment conditions in real time and make analysis and decision. A monitoring response module is responsible for formulating and executing response strategies, including monitoring platform access, email monitoring, SMS monitoring, threshold alarm, and manual reply, and the like, and realizes timely response and processing of comment problems through these functions. At the bottom layer of the entire financial system, a one-key access mechanism is used to realize rapid access of different business systems, and this mechanism supports convenient access of multiple business systems to the comment processing platform through access credentials, to realize unified management and processing of comment functions.

[0152] Please refer to Figure 9 , Figure 9is a schematic diagram of a financial system comment processing method provided by the embodiment of the present application. The financial system comment processing method provided by the embodiment of the present application adopts a high-availability architecture design. The entire architecture is divided into an API interface layer, a service layer, a processing layer and a storage layer from top to bottom, and realizes full-process management from business comment data acquisition to target recognition result response. The API interface layer supports fast access of different target financial systems to the comment processing platform through open standardized API interfaces. The service layer adopts a distributed architecture and deploys multiple functional service nodes. Among them, the comment processing service node is responsible for the preprocessing and preliminary classification of business comment data; the rule matching service node performs selection and application of the target comment rule model; and the response processing service node generates a business response strategy according to the target recognition result. Each service node supports horizontal expansion, and the high availability of the system is ensured through load balancing. The service nodes are decoupled through a message queue to improve the fault tolerance of the system. The processing layer includes two core modules, hot spot processing and storage processing. The hot spot processing module is responsible for the deep processing of business comment data, including comment classification, sensitive word identification, context semantic analysis and comment opinion extraction and other functions. The storage layer can realize efficient data management through data sharding, multi-level caching and other mechanisms, and also provides data backup and recovery and archiving and cleaning functions. The high availability of the entire architecture is guaranteed through multiple technical means. First, the service layer adopts multi-node deployment, and the requests are distributed through a load balancer, so that a single node failure will not affect the overall service; second, the storage layer adopts master-slave replication and data sharding to improve the availability and access performance of data; and finally, through mechanisms such as fusing and downgrading, the normal operation of core functions is ensured when the system pressure is too large. For example, when a certain service node has too high a load, the load balancer will automatically distribute new requests to other nodes; when a certain storage node fails, the system will automatically switch to a backup node to ensure service continuity. This multi-level fault tolerance mechanism improves the stability and reliability of the system.

[0153] The financial system comment processing method and device, the electronic device and the storage medium provided by the present application obtain business comment data from a target financial system; determine a target comment rule model matched with the target financial system from a plurality of preset candidate comment rule models according to the target financial system; perform multi-dimensional comment identification processing on the business comment data based on the target comment rule model to obtain a target recognition result; analyze the target recognition result based on a preset monitoring response rule to obtain a business response strategy for the business comment data; and trigger a corresponding business processing flow according to the business response strategy.

[0154] The application firstly acquires business comment data of a target financial system, introduces a plurality of preset candidate comment rule models, can select the most suitable comment rule model according to the business characteristics of different financial systems, improves the pertinence of comment processing, and avoids the insufficient accuracy caused by single-dimensional identification through a multi-dimensional identification method based on the target comment rule model, analyzes through a preset monitoring response rule, realizes systematic comment response management, better meets the comment processing needs of the financial system, establishes a quick response mechanism between comment identification and business processing through the formulation of a business response strategy, triggers the corresponding business processing flow according to the business response strategy, and improves the efficiency of financial system comment processing.

[0155] Please refer to Figure 10 The embodiment of the application further provides a financial system comment processing device, which can implement the financial system comment processing method.

[0156] The acquisition module is configured to acquire business comment data from a target financial system.

[0157] The matching module is configured to determine, according to the target financial system, a target comment rule model matched to the target financial system from a plurality of preset candidate comment rule models.

[0158] The identification module is configured to perform multi-dimensional comment identification processing on the business comment data based on the target comment rule model, and obtain a target identification result.

[0159] The strategy module is configured to analyze the target identification result based on a preset monitoring response rule, and obtain a business response strategy for the business comment data.

[0160] The response module is configured to trigger a corresponding business processing flow according to the business response strategy.

[0161] The specific implementation of the financial system comment processing device is basically the same as that of the above-mentioned specific embodiment of the financial system comment processing method, and will not be repeated here.

[0162] The embodiment of the application further provides an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned financial system comment processing method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer and the like.

[0163] Please refer to Figure 11 , Figure 11 The hardware structure of the electronic device of another embodiment is illustrated, which includes:

[0164] The processor 1101 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided by the embodiments of the present application.

[0165] The memory 1102 can be implemented by a read-only memory (Read Only Memory, ROM), a static storage device, a dynamic storage device, or a random access memory (Random Access Memory, RAM). The memory 1102 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 1102 and are called and executed by the processor 1101 to implement the financial system comment processing method of the embodiments of the present application.

[0166] The input / output interface 1103 is configured to realize information input and output.

[0167] The communication interface 1104 is configured to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WI FI, Bluetooth, etc.).

[0168] The bus 1105 is configured to transmit information between various components (for example, the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104) of the device.

[0169] The processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104 are connected to each other through the bus 1105 to realize the communication connection between the device.

[0170] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by the processor to implement the above-mentioned financial system comment processing method.

[0171] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory that is remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0172] The financial system comment processing method and device, the electronic equipment and the storage medium provided by the present application can obtain business comment data from a target financial system, determine a target comment rule model matched with the target financial system from a plurality of preset candidate comment rule models according to the target financial system, perform multi-dimensional comment identification processing on the business comment data based on the target comment rule model to obtain a target identification result, analyze the target identification result based on a preset monitoring response rule to obtain a business response strategy for the business comment data, and trigger a corresponding business processing flow according to the business response strategy.

[0173] The present application first obtains business comment data of a target financial system, introduces a plurality of preset candidate comment rule models, can select the most suitable comment rule model according to the business characteristics of different financial systems, improves the pertinence of comment processing, avoids the inaccuracy caused by single-dimensional identification based on the multi-dimensional identification method of the target comment rule model, analyzes through the preset monitoring response rule, realizes systematic comment response management, better meets the comment processing needs of the financial system, establishes a quick response mechanism between comment identification and business processing through the formulation of a business response strategy, triggers the corresponding business processing flow according to the business response strategy, and improves the efficiency of financial system comment processing.

[0174] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0175] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than the figures shown, or combine certain steps or different steps.

[0176] The apparatus embodiments described above are merely exemplary, and the units described as separate units can or can not be physically separate, i.e., can be located in one place, or can be distributed over multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0177] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and appropriate combinations thereof.

[0178] The terms "first", "second", "third", "fourth" and the like in the description of the application and in the claims of the foregoing drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so

[0179] It should be understood that in this application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that there are three cases: only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents that the associated objects before and after are a "or" relationship. "At least one of the following" or the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c, can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0180] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the above units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0181] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they can be located in one place or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0182] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0183] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that makes a contribution or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0184] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, but this does not limit the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method for processing comments in a financial system, characterized in that, include: Obtain business comment data from the target financial system; Based on the target financial system, determine the target comment rule model that matches the target financial system from among multiple preset candidate comment rule models; Based on the target comment rule model, the business comment data is processed for multi-dimensional comment recognition to obtain the target recognition result; The target identification results are analyzed based on preset monitoring response rules to obtain a business response strategy for the business comment data; According to the business response strategy, the corresponding business processing flow is triggered.

2. The financial system comment processing method according to claim 1, characterized in that, The step of determining the target comment rule model that matches the target financial system from multiple preset candidate comment rule models includes: Obtain the system characteristics of the target financial system, wherein the system characteristics include business type identifiers and functional module identifiers; Keyword processing is performed on the business review data to extract key field features; Based on the system characteristics and the key field characteristics, a target comment rule model matching the target financial system is determined from multiple preset candidate comment rule models.

3. The financial system comment processing method according to claim 2, characterized in that, The step of determining the target comment rule model matching the target financial system from multiple preset candidate comment rule models based on the system characteristics and the key field characteristics includes: The system features are matched with the applicable scenarios in the candidate comment rule model to obtain a first matching score; The key field features are matched with the rule items in the candidate comment rule model to obtain the second matching score; The first matching score and the second matching score are weighted and calculated to obtain the target matching score; The target matching scores of the candidate comment rule models are sorted, and the candidate comment rule model with the highest target matching score is determined as the target comment rule model.

4. The financial system comment processing method according to claim 1, characterized in that, The process of performing multi-dimensional comment recognition on the business comment data based on the target comment rule model to obtain the target recognition result includes: Based on the sensitive word rules in the target comment rule model, the business comment data is scanned to identify financial sensitive information and obtain the comment text to be processed; Keyword extraction and feature vector calculation are performed on the comment text to be processed to obtain the comment text features; Based on the target comment rule model, multi-dimensional comment recognition processing is performed on the comment text to be processed and the comment text features to obtain the target recognition result.

5. The financial system comment processing method according to claim 4, characterized in that, The process of performing multi-dimensional comment recognition processing on the comment text to be processed and the comment text features based on the target comment rule model to obtain the target recognition result includes: Based on the features of the comment text, text clustering analysis is performed on the comment text to be processed to obtain the comment category of the comment text to be processed; Based on the semantic recognition rules in the target comment rule model, the contextual semantic analysis of the comment text to be processed is performed to obtain the comment tendency of the comment text to be processed. Based on the characteristics of the comment text, the text similarity of different business comment data is calculated. When the text similarity is greater than a preset threshold, the corresponding business comment data is marked as a hot comment. The target identification result is generated by integrating the comment categories, comment trends, and trending comments.

6. The financial system comment processing method according to claim 5, characterized in that, The process of integrating the comment categories, comment trends, and trending comments to generate the target identification result includes: Category labels are generated for the business comment data based on the comment categories, wherein the category labels are used to characterize the type to which the business comment data belongs; Based on the positive or negative sentiment of the comments and a preset sentiment rating standard, the business comment data is classified into different levels to obtain the sentiment rating of the business comment data. Based on the tagging status of the trending comments, the level of attention for the business comment data is determined; The target identification result is obtained based on the attribution type, the sentiment level, and the attention level.

7. The financial system comment processing method according to claim 6, characterized in that, The analysis of the target identification results based on preset monitoring response rules yields a business response strategy for the business comment data, including: Based on the attribution type, sentiment level, and attention level in the target identification results, the processing priority of the business comment data is determined; Based on the processing priority, a target response rule is determined from a set of preset response rules; Based on the target response rules, a business response strategy is generated for the business comment data, wherein the business response strategy includes the processing department, processing time limit, and processing method.

8. A financial system comment processing device, characterized in that, include: The acquisition module is used to acquire business comment data from the target financial system; The matching module is used to determine the target comment rule model that matches the target financial system from multiple preset candidate comment rule models. The identification module is used to perform multi-dimensional comment identification processing on the business comment data based on the target comment rule model to obtain the target identification result; The strategy module is used to analyze the target identification results based on preset monitoring response rules to obtain a business response strategy for the business comment data. The response module is used to trigger the corresponding business processing flow according to the business response strategy.

9. An electronic device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the financial system comment processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the financial system comment processing method as described in any one of claims 1 to 7.

Images