Government affair service business evaluation method and device, computer device and storage medium

Abstract

The application belongs to the field of data processing, and relates to a government affair service business evaluation method and device, computer equipment and a storage medium. The government affair service business evaluation comprises: preprocessing multi-channel user evaluation information to obtain standard user evaluation information; associating the standard user evaluation information with service operations to construct a service behavior relationship graph; mapping data corresponding to each service in the service behavior relationship graph to a unified data structure to obtain a service data set; associating and fusing the service data set based on a preset data fusion technology to obtain a fused service data set; associating the service operation and the user evaluation information based on the fused service data set to construct a multi-terminal service evaluation model; and inputting real-time evaluation information into the multi-terminal service evaluation model to obtain a service evaluation score. The application can effectively generate a service evaluation score according to real-time evaluation of a user on a service business, so as to effectively comprehensively consider service quality.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, apparatus, computer equipment, and storage medium for evaluating government service operations. Background Technology

[0002] With the continuous development of internet technology, government services are gradually migrating online. Government service evaluation is a crucial means of measuring service quality and improving service processes. However, a significant problem exists in the current government service evaluation system: users often rely solely on the service outcome for subjective evaluation, neglecting the complexity and time involved in the service process. This evaluation method means that even if service personnel exert tremendous effort and achieve optimal service standards, they may still receive unsatisfactory evaluations because the results do not fully meet user expectations.

[0003] Specifically, the service process may involve multiple complex steps, each requiring significant time and effort from service personnel. However, users often focus solely on the final service outcome when providing feedback, lacking sufficient awareness and understanding of the difficulties and challenges encountered along the way. This information asymmetry makes it difficult for service personnel to obtain accurate and comprehensive service quality feedback from user reviews, thereby impacting subsequent service optimization and improvement.

[0004] Furthermore, inaccurate service evaluations can prevent departments and staff from clearly defining their service direction and areas for improvement, hindering the smooth operation of service activities. Therefore, establishing a more scientific and objective service evaluation system to comprehensively reflect various factors in the service process has become a pressing issue for the service industry. Summary of the Invention

[0005] The purpose of this application is to propose a method, apparatus, computer equipment, and storage medium for evaluating government services, in order to solve the problem that it is impossible to generate corresponding service evaluation scores based on users' real-time evaluations of service services, so as to effectively and comprehensively assess service quality.

[0006] To address the aforementioned technical problems, this application provides a method for evaluating government service operations, employing the following technical solution:

[0007] Obtain user review information from multiple channels, preprocess the user review information from multiple channels, and obtain standard user review information;

[0008] Based on the standard user evaluation information, service operations are correlated to construct a service behavior relationship graph;

[0009] According to the preset data mapping rule, the data corresponding to each service in the service behavior relationship graph is mapped to a unified data structure, and a service data set is obtained;

[0010] Based on the preset data fusion technology, the service data set is associated and fused to obtain a fused service data set;

[0011] According to the fused service data set, the service operations and user evaluation information of different channels are associated to construct a multi-terminal service evaluation model;

[0012] Obtain real-time evaluation information, input the real-time evaluation information into the multi-terminal service evaluation model, and obtain a service evaluation score.

[0013] Further, the step of obtaining multi-channel user evaluation information and preprocessing the multi-channel user evaluation information to obtain standard user evaluation information comprises:

[0014] Obtain user original evaluation information from a preset web page and software end;

[0015] According to the preset unified data standard specification, the original evaluation information is identified and coded to obtain the multi-channel user evaluation information;

[0016] According to the preset data field definition, data type, and value range rule, the multi-channel user evaluation information is data cleaned and filtered to obtain effective user evaluation information;

[0017] The effective user evaluation information is processed by natural language to obtain the standard user evaluation information.

[0018] Further, the step of associating the standard user evaluation information with service operations to construct a service behavior relationship graph comprises:

[0019] According to the standard user evaluation information, corresponding service operation data is extracted from the database;

[0020] The service operation data is standardized to obtain standardized service operation data;

[0021] A globally unique number is generated for each service operation in the standardized service operation data;

[0022] According to the globally unique number, the same type of service operations of different channels are associated to construct a service operation directed graph;

[0023] Based on the service operation directed graph, the service behavior relationship graph is constructed.

[0024] Further, the step of constructing the service behavior relationship graph based on the service operation directed graph specifically comprises:

[0025] performing community division on the service operation directed graph based on a community discovery algorithm to obtain a service operation community set;

[0026] performing association rule mining on each service operation community in the service operation community set based on an association rule mining algorithm to obtain a service association mode;

[0027] constructing the service behavior relationship graph according to the service operation community set and the service association mode.

[0028] Further, the step of mapping data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set specifically comprises:

[0029] obtaining service original data corresponding to each service operation in the service behavior relationship graph;

[0030] extracting key information from the service original data to obtain service key information;

[0031] organizing the service key information into a unified data structure to construct a standard service data record;

[0032] creating a relational data table and inserting the standard service data record into the relational data table to obtain the service data set.

[0033] Further, the step of associating and fusing the service data set based on a preset data fusion technology to obtain a fused service data set specifically comprises:

[0034] extracting a standard service data record from the service data set and preprocessing the standard service data record to obtain service key features;

[0035] calculating the similarity between the standard service data records according to the service key features and clustering the standard service data records according to the calculated similarity to obtain a service data clustering result;

[0036] identifying a data association mode according to the service data clustering result and constructing a service association rule between service behavior and service result based on the data association mode;

[0037] fusing the service data set according to the service association rule to obtain the fused service data set.

[0038] Further, the step of associating service operations and user evaluation information of different channels according to the fusion service data set to construct a multi-terminal service evaluation model specifically comprises:

[0039] According to the fusion service data set, a multi-dimensional service data cube is constructed with service platforms, service business types, and service times as dimensions and user evaluation scores and completion rates as measurement values.

[0040] The multi-dimensional service data cube is subjected to measurement value difference analysis to obtain key influence factors.

[0041] The multi-terminal service evaluation model is constructed according to the fusion service data set and the key influence factors.

[0042] To solve the above technical problems, the embodiment of the application further provides a government service business evaluation device, which adopts the technical scheme as follows:

[0043] An information processing module is configured to acquire multi-channel user evaluation information, preprocess the multi-channel user evaluation information, and obtain standard user evaluation information.

[0044] An information association module is configured to associate service operations according to the standard user evaluation information and construct a service behavior relationship graph.

[0045] A data mapping module is configured to map data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule, and obtain a service data set.

[0046] An association fusion module is configured to associate and fuse the service data set based on a preset data fusion technology, and obtain a fusion service data set.

[0047] A model construction module is configured to associate service operations and user evaluation information of different channels according to the fusion service data set, and construct a multi-terminal service evaluation model.

[0048] A service evaluation module is configured to acquire real-time evaluation information, input the real-time evaluation information into the multi-terminal service evaluation model, and obtain a service evaluation score.

[0049] To solve the above technical problems, the embodiment of the application further provides a computer device, which adopts the technical scheme as follows:

[0050] A computer device includes a memory and a processor, the memory stores computer readable instructions, and the processor executes the computer readable instructions to realize the steps of the government service business evaluation method according to any one of the above.

[0051] To solve the above technical problems, the embodiment of the present application also provides a computer readable storage medium, which adopts the technical scheme as follows:

[0052] A computer readable storage medium, which stores computer readable instructions, and the computer readable instructions are executed by a processor to implement the steps of the government service business evaluation method according to any one of the above.

[0053] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0054] In the embodiment, multi-channel user evaluation information is obtained, the multi-channel user evaluation information is preprocessed to obtain standard user evaluation information, the standard user evaluation information is associated with service operations to construct a service behavior relationship graph, data corresponding to each service in the service behavior relationship graph is mapped to a unified data structure according to a preset data mapping rule to obtain a service data set, the service data set is associated and fused based on a preset data fusion technology to obtain a fused service data set, service operations and user evaluation information of different channels are associated according to the fused service data set to construct a multi-terminal service evaluation model, real-time evaluation information is obtained, the real-time evaluation information is input into the multi-terminal service evaluation model to obtain a service evaluation score. Therefore, the corresponding service evaluation score is generated according to real-time evaluation of a user on a service business, the service quality is effectively comprehensively considered, and an effective and reliable basis is provided for optimization of subsequent service businesses. BRIEF DESCRIPTION OF DRAWINGS

[0055] To more clearly illustrate the solutions in the present application, the drawings needed in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0056] Figure 1 A flowchart of an embodiment of the government service business evaluation method according to the present application;

[0057] Figure 2 is Figure 1 A flowchart of an embodiment of step S10 in the method;

[0058] Figure 3 is Figure 1 A flowchart of an embodiment of step S20 in the method;

[0059] Figure 4 is Figure 3 A flowchart of an embodiment of step S205 in the method;

[0060] Figure 5 is Figure 1 a flow chart of one specific implementation of step S30 in

[0061] Figure 6 is Figure 1 a flow chart of one specific implementation of step S40 in

[0062] Figure 7 is Figure 1 a flow chart of one specific implementation of step S50 in

[0063] Figure 8 is a structural schematic diagram of one embodiment of the government service business evaluation device according to the present application;

[0064] Figure 9 is a structural schematic diagram of one embodiment of the computer device according to the present application. DETAILED DESCRIPTION

[0065] 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 this application belongs; the terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application; the description and the drawings are to be regarded as illustrative in nature and are not intended to limit the application; the terminology used in the description of the application herein including the abstract is not intended to be limiting of the application and is only used for the purpose of providing constructive reduction to practice of the application. The use of the terms "first", "second" and the like in the description of the application herein is only used for distinguishing between similar objects talking about and does not imply any kind of order, quantity, creation or occurrence of the objects about which it is used, unless specified otherwise.

[0066] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiments, or alternative or alternative embodiments.

[0067] In order for those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings.

[0068] With reference to Figure 1 , a flow chart of one embodiment of the method for testing the sound box production according to the present application is shown. The government service business evaluation method includes the following steps:

[0069] Step S10, obtaining multi-channel user evaluation information, preprocessing the multi-channel user evaluation information to obtain standard user evaluation information;

[0070] In the embodiment, the multi-channel user evaluation information is user evaluation data collected from multiple terminals such as preset web pages and software terminals. The user evaluation data is service evaluation of a user on a service operation of a unified service business platform. The service evaluation can include evaluation text content, evaluation score, evaluation level, etc. The preprocessing of the multi-channel user evaluation information includes data cleaning, filtering, natural language processing, etc. Through the preprocessing of the multi-channel user evaluation information, standard user evaluation information conforming to the format of subsequent processing is obtained.

[0071] Step S20, associating the service operation according to the standard user evaluation information to construct a service behavior relationship graph;

[0072] In the embodiment, the service operation is an operation record of the service business corresponding to the standard user evaluation information. The operation service includes operation time, operation type, operation result, associated user ID, etc. The standard user evaluation information includes evaluation content, evaluation time, sentiment tendency (positive, negative, neutral), associated service operation ID, etc. The service behavior relationship graph is graph data for representing the corresponding relationship between service operations. The node of the service behavior relationship graph represents the service operation, and the edge represents the association relationship between the service operations.

[0073] Step S30, mapping the data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set;

[0074] In the embodiment, the preset data mapping rule includes data extraction, key information extraction, unified data structure organization, and data insertion. The data corresponding to each service in the service behavior relationship graph refers to service original data corresponding to the service operation, including service operation data, user information data, service time data, evaluation content data, etc. The service operation data, user information data, service time data, and evaluation content data can be extracted from the standard user evaluation information and the database according to the type of the service operation. The service data set is a data set in which the key information of the service operation data, the user information data, the service time data, and the evaluation content data is effectively organized. The service data set is processed to facilitate subsequent processing.

[0075] Step S40, associating and fusing the service data set based on a preset data fusion technology to obtain a fused service data set;

[0076] In the embodiment, the preset data fusion technology includes feature extraction, similarity calculation, association rule construction and data fusion, and the fused service data set is a data set information obtained by a series of processing on the service data set according to the preset data fusion technology and finally data fusion.

[0077] In step S50, the service operation and user evaluation information of different channels are associated according to the fused service data set to construct a multi-terminal service evaluation model.

[0078] In the embodiment, the service operation and user evaluation information of different channels refer to different collection channels corresponding to the service operation and user evaluation information, including the preset web page, mobile terminal, website, APP application program, public number and the like. By analyzing the differences between the service operation and user evaluation information of different channels, the key influencing factors of evaluation between different channels are identified, and the multi-terminal service evaluation model is effectively constructed according to the key influencing factors, so that the model has the ability to adapt to the evaluation data obtained by multiple terminals and perform real service evaluation.

[0079] In step S60, real-time evaluation information is obtained, and the real-time evaluation information is input into the multi-terminal service evaluation model to obtain a service evaluation score.

[0080] In the embodiment, the real-time evaluation information is user evaluation data collected from the preset web page and software terminal of the service business system and the like. By inputting the collected user evaluation data into the multi-terminal service evaluation model, a service evaluation score reflecting the real evaluation of the service business is obtained, which considers the relationship between the service operation and the user evaluation to perform real and effective service effect evaluation.

[0081] The embodiment obtains multi-channel user evaluation information, pre-processes the multi-channel user evaluation information to obtain standard user evaluation information, associates the standard user evaluation information with service operation to construct a service behavior relationship graph, maps data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set, associates and fuses the service data set based on a preset data fusion technology to obtain a fused service data set, associates service operation and user evaluation information of different channels according to the fused service data set to construct a multi-terminal service evaluation model, obtains real-time evaluation information, inputs the real-time evaluation information into the multi-terminal service evaluation model to obtain a service evaluation score. Thus, the corresponding service evaluation score is generated according to the real-time evaluation of the user on the service business, the service quality is effectively comprehensively considered, and an effective and reliable basis is provided for subsequent optimization of the service business.

[0082] In the embodiment, the government service business evaluation method can be applied to a government service system. The user evaluation data collected from multiple terminals is analyzed and evaluated by the government service system to obtain a service evaluation score effectively reflecting the real service effect, thereby providing reliable data basis and support for subsequent service business adjustment and optimization.

[0083] With reference to the foregoing Figure 2 In some optional implementations of the embodiment, step S10 includes the following steps.

[0084] Step S101: obtaining user original evaluation information from preset web pages and software terminals;

[0085] In the embodiment, the preset web pages and software terminals belong to different service terminals of the same service system. The web pages can use network crawler technology (such as Python's BeautifulSoup, Scrapy, or Selenium tools) to crawl user original evaluation information from related websites, and the software terminals can obtain user original evaluation information through API interfaces or database queries.

[0086] Step S102: identifying and encoding the original evaluation information according to a preset unified data standard specification to obtain the multi-channel user evaluation information;

[0087] In the embodiment, the preset unified data standard specification refers to a data dictionary containing channel identifiers (such as web pages, Android terminals, iOS terminals, etc.) and platform identifiers (such as website platforms, WeChat public accounts, and service business APPs, etc.). According to the data dictionary, the corresponding channel and platform identifiers are added to each data item of the original evaluation information.

[0088] Step S103: data cleaning and filtering the multi-channel user evaluation information according to a preset data field definition, data type, and value range rule to obtain effective user evaluation information;

[0089] In the embodiment, the preset data field definition is used to specify which fields the user evaluation information needs to contain, such as user ID, evaluation content, evaluation time, score, etc. The data type and value range: define the data type (such as string, integer, date, etc.) and value range (such as the score should be between 1-5) for each field. By using the unique identifier (such as user ID+evaluation time) according to the data field definition, data type, and value range rule, the duplicate records are removed, and the data that does not meet the standard (such as the score is not between 1-5, the evaluation content is empty, etc.) is removed according to the data type and value range rule.

[0090] Step S104: performing natural language processing on the effective user evaluation information to obtain the standard user evaluation information.

[0091] In the present embodiment, the natural language processing includes word segmentation, part-of-speech tagging, named entity recognition, keyword extraction and sentiment analysis. The word segmentation can be performed by using a Chinese word segmentation tool (such as jieba) to divide the evaluation content into words or phrases. The part-of-speech tagging refers to tagging the part of speech (such as noun, verb, adjective, etc.) for each word or phrase, which is helpful for subsequent sentiment analysis. The named entity recognition refers to identifying and extracting entities (such as names of people, places, product names, etc.) in the evaluation content, which is helpful for understanding the specific object of the evaluation. The keyword extraction can be performed by using TF-IDF, TextRank or other algorithms to extract keywords in the evaluation content. The sentiment analysis can use a sentiment dictionary or a machine learning model (such as SVM, BERT, etc.) to determine the sentiment (such as positive, negative, neutral) of the evaluation content.

[0092] The present embodiment obtains user original evaluation information from the preset web page and software end; identifies and encodes the original evaluation information according to the preset unified data standard specification, to obtain the multi-channel user evaluation information; performs data cleaning and filtering on the multi-channel user evaluation information according to the preset data field definition, data type and value range rules, to obtain effective user evaluation information; performs natural language processing on the effective user evaluation information, to obtain standard user evaluation information meeting the requirements of subsequent processing, so as to facilitate subsequent construction of a service behavior relationship graph according to the user evaluation information.

[0093] With reference to the foregoing description, the present embodiment further comprises the following steps: Figure 3 In some optional implementations of the present embodiment, step S20 comprises the following steps:

[0094] Step S201: extracting corresponding service operation data from a database according to the standard user evaluation information;

[0095] In the present embodiment, the evaluation information identifier corresponding to the standard user evaluation information is taken as a query condition, and a matching query is performed in the database of the system, to query and extract the service operation data corresponding to the evaluation information.

[0096] Step S202: performing standardized processing on the service operation data, to obtain standardized service operation data;

[0097] In the embodiment, the normalization processing includes data cleaning, data conversion, and data standardization. The data cleaning includes removing duplicate data, handling missing values, correcting erroneous data, etc. The data conversion refers to converting data in different formats to a unified format, such as converting a date from a string to a date type. The data standardization refers to standardizing certain numerical data, such as normalizing or standardizing to a certain range. Through the normalization processing including the above processing steps on the service operation data, standard and effective normalized service operation data are obtained.

[0098] In step S203, a globally unique number is generated for each service operation in the normalized service operation data.

[0099] In the embodiment, the globally unique number (GUID or UUID) generated for each service operation in the normalized service operation data is used to uniquely identify each service operation and serves as a basis for subsequent association and construction of a directed graph.

[0100] In step S204, according to the globally unique number, the same type of service operations in different channels are associated to construct a service operation directed graph.

[0101] In the embodiment, the globally unique number is used to associate the same type of service operations in different channels. The same type of service operations refers to service operations with the same or similar functions, such as "service consultation" and "personal information inquiry". The association process of the same type of service operations in different channels can include identifying the same type of service operations: identifying which service operations belong to the same type according to the type or description of the service operation. Establishing an association relationship: using the globally unique number to connect the same type of service operations in different channels to form an association relationship. The service operation directed graph is a graphical representation method, in which the nodes of the service operation directed graph represent service operations, and each node corresponds to a globally unique number of service operation. The directed edges of the service operation directed graph represent the association relationship between service operations, and the directed edges point from one service operation to another service operation, representing the sequence or dependency relationship in the service process. When constructing the service operation directed graph, a suitable graphical representation tool or library can be selected according to actual needs, such as Graphviz, D3.js, etc. In the embodiment, Graphviz can be used.

[0102] In step S205, the service behavior relationship graph is constructed based on the service operation directed graph.

[0103] In the embodiment, the service behavior relationship graph is used to describe the associated behavior or association degree between service operations. Through community division, association rule mining, and other processing on the service operation directed graph, the association information between service operations is obtained, and the service behavior relationship graph is constructed based on the association information.

[0104] The embodiment extracts corresponding service operation data from the database according to the standard user evaluation information; performs standardization processing on the service operation data to obtain standardized service operation data; generates a globally unique number for each service operation in the standardized service operation data; associates similar service operations of different channels according to the globally unique number to construct a service operation directed graph; and constructs the service behavior relationship graph based on the service operation directed graph. Thus, the service behavior relationship graph representing the relationship between service operations is effectively constructed based on the service operation data corresponding to the standard user evaluation information, so as to facilitate subsequent acquisition of service data sets.

[0105] With reference to the foregoing Figure 4 In some optional implementation modes of the embodiment, step S205 includes the following steps.

[0106] In step S2051, the service operation directed graph is divided into communities based on a community discovery algorithm to obtain a service operation community set.

[0107] In the embodiment, the community discovery algorithm can adopt the Louvain algorithm. The steps of dividing the service operation directed graph into communities by the Louvain algorithm include setting parameters: determining the parameters required by the Louvain algorithm, such as a resolution parameter (used to control the coarse-fine granularity of the number of communities) and a maximum number of iterations (to prevent infinite loop of the algorithm). Calculating the modularity: the modularity is an index for measuring the quality of community division, which reflects the tightness of the connection between nodes in a community relative to the tightness of the connection between nodes in different communities. In the initial stage of the Louvain algorithm, each node is regarded as an independent community. Node movement: the algorithm traverses each node in the graph and tries to move it to the community to which its neighbor nodes belong, so as to maximize the gain of the modularity. If moving a certain node can increase the modularity, the movement is performed. Aggregating nodes: nodes belonging to the same community are aggregated into a new node, and the weight (or "size") of the new node can be set as the sum of the weights of all nodes in the original community. Building new edges: in the new graph, the edge weights between the aggregated nodes are calculated according to the strength of the connection between nodes in the corresponding communities in the original graph. This step can be achieved by calculating the sum of the weights of all possible node pairs between the two communities. Iteration stage: the above two stages are repeated, i.e., the modularity optimization and node aggregation are performed on the new graph until a certain stopping condition (such as no longer significant increase in the modularity, reaching the maximum number of iterations, etc.) is reached. Community division: the algorithm finally outputs a community division result, in which each service operation is assigned to a community. All communities are aggregated to generate a service operation community set.

[0108] Step S2052, performing association rule mining on each service operation community in the service operation community set according to an association rule mining algorithm to obtain a service association pattern;

[0109] In this embodiment, the association rule mining algorithm can adopt the Apriori algorithm. The association rule mining algorithm performs association rule mining on each service operation community in the service operation community set through the Apriori algorithm. The steps include finding frequent item sets: setting a minimum support threshold, counting the number of occurrences (i.e., support) of each item set (service operation) in the service operation community set, and finding all item sets with a support greater than or equal to the minimum support threshold as frequent item sets. Generating association rules: setting a minimum confidence threshold, generating all possible association rules based on the frequent item sets, calculating the confidence of each rule, i.e., the ratio of the number of occurrences of the rule antecedent in the database to the number of occurrences of the rule as a whole, and finding all association rules with a confidence greater than or equal to the minimum confidence threshold. The finally obtained association rules are sorted to obtain the service association pattern.

[0110] Step S2053, constructing the service behavior relationship graph based on the service operation community set and the service association pattern.

[0111] In this embodiment, the service operations in the service operation community set are used as the nodes of the service behavior relationship graph, and the edges of the service behavior relationship graph are constructed based on the service association pattern to represent the association relationship between the service operations, thereby effectively constructing the service behavior relationship graph.

[0112] This embodiment performs community division on the service operation directed graph based on a community discovery algorithm to obtain a service operation community set, performs association rule mining on each service operation community in the service operation community set according to an association rule mining algorithm to obtain a service association pattern, and constructs the service behavior relationship graph based on the service operation community set and the service association pattern. Thus, the specific association relationship between service operations is effectively described to facilitate subsequent acquisition of a service data set based on the service behavior relationship graph.

[0113] With reference to Figure 5 In some optional implementations of this embodiment, step S30 includes the following steps:

[0114] Step S301, obtaining service raw data corresponding to each service operation in the service behavior relationship graph;

[0115] In this embodiment, the service original data includes service operation data (service type, operation action, operation parameter), user information data (user ID, user attribute), service time data (service start time, service end time, service duration), evaluation content data (evaluation text, evaluation level, evaluation time), etc.

[0116] In step S302, key information is extracted from the service original data to obtain service key information.

[0117] In this embodiment, the service key information extracted from the service original data includes service operation (such as service type, action performed, etc.), evaluation content (user feedback on the service), user information (such as user ID, name, etc.), and service time (timestamp of service occurrence).

[0118] In step S303, the service key information is organized in a unified data structure to construct a standard service data record.

[0119] In this embodiment, the format, type, length, etc. of the service data record are defined, and the service key information is organized in a data structure according to the defined format, type, length, etc. of the service data record, so as to ensure that each record contains the same information and is presented in the same way, effectively realizing the construction of the standard service data record.

[0120] In step S304, a relational data table is created, and the standard service data record is inserted into the relational data table to obtain the service data set.

[0121] In this embodiment, a relational database is a table-based data storage method that allows defining relationships between data. According to the extracted standard service data record, a corresponding relational data table needs to be created in the relational database, where each row of the data table represents a service record, and the columns correspond to various service key information. The insertion operation of inserting the standard service data record into the relational data table can be performed by writing an SQL statement or using a database management tool to obtain the service data set.

[0122] This embodiment obtains the service original data corresponding to each service operation in the service behavior relationship graph; extracts key information from the service original data to obtain service key information; organizes the service key information in a unified data structure to construct a standard service data record; creates a relational data table and inserts the standard service data record into the relational data table, thereby obtaining a service data set represented in a unified data structure, to facilitate subsequent data association and fusion.

[0123] With reference to Figure 6In some optional implementations of the embodiment, step S40 comprises the following steps:

[0124] Step S401, extracting standard service data records from the service data set, and preprocessing the standard service data records to obtain service key features;

[0125] In the embodiment, the preprocessing of the standard service data records includes data conversion, feature extraction, etc. By converting the standard service data records into suitable data, the converted standard service data records are extracted for features to obtain service key features. Among them, data conversion includes data formatting: ensuring the consistency of data format, such as date format, numerical format, etc. Data type conversion: converting some data types to another type, such as converting a string to a numerical type (if possible), or converting a date and time to a specific timestamp format. Data scaling: scaling numerical data to eliminate dimensional differences between different features, common methods include standardization (converting data to a distribution with a mean of 0 and a standard deviation of 1) and normalization (scaling data to a specific range, such as between 0 and 1). Data discretization: converting continuous data into discrete data, such as segmenting age into different intervals. Missing value processing: filling or deleting missing values, common methods include using mean, median, mode filling, or using interpolation method. Feature extraction includes statistical features: calculating statistical quantities of data, such as mean, median, mode, variance, standard deviation, etc. Text features: for text data, you can use bag-of-words model, TF-IDF (term frequency-inverse document frequency) method to extract text features. Time series features: for time series data, you can extract trend, seasonality, periodicity, etc. Domain-specific features: extract features with business significance in specific business domains, such as user behavior features, service performance indicators, etc.

[0126] Step S402, calculating the similarity between the standard service data records according to the service key features, and clustering the standard service data records according to the calculated similarity to obtain service data clustering results;

[0127] In the embodiment, the similarity between the service key features and the standard service data records can be obtained by calculating the cosine similarity. First, these features and data records need to be converted into vector form, which can be done by mapping each feature or data point to a specific numerical value to form a corresponding multi-dimensional vector, and then using the cosine similarity formula to calculate the similarity between the two vectors. For example, a service key feature vector A and a standard service data record vector B, both composed of multiple dimensions (such as response time, quality, price, etc.). We can use the following formula to calculate the cosine similarity between them:

[0128] Cosine similarity = (A · B) / (|A| x |B|) ;

[0129] where A · B denotes the dot product of vectors A and B, and |A| and |B| denote the modulus (i.e. length) of vectors A and B, respectively.

[0130] After the similarity is calculated, the standard service data records are clustered by the K-means clustering method, which includes determining the value of K and selecting K initial cluster centers (also known as centroids), which will serve as the starting point for iteration to assign data points to the nearest cluster. The similarity (or distance) of each standard service data record (now regarded as a data point) to all K cluster centers is calculated, and each data point is assigned to the cluster where the nearest cluster center is located. When all data points are assigned to clusters, the cluster centers of each cluster are recalculated, which can be achieved by calculating the average value (centroid) of all data points in the cluster. The steps of data point assignment and cluster center selection are repeated until the cluster centers no longer change significantly (i.e. the algorithm converges), or a preset number of iterations is reached, at which time the resulting service data clustering result is obtained, in which the data records in each cluster have a high similarity, while the data records between different clusters have a low similarity.

[0131] In step S403, a data association pattern is identified according to the service data clustering result, and a service association rule between service behaviors and service results is constructed based on the data association pattern.

[0132] In this embodiment, the data association pattern can be represented as an association between certain features, an association between clusters, or an association over time series, etc. Based on the data association pattern, the service association rule between service behaviors and service results is constructed, which describes how service behaviors affect service results, or the association relationship between different service behaviors.

[0133] In step S404, the service data set is fused according to the service association rule to obtain the fused service data set.

[0134] In this embodiment, the service data set can be fused by merging similar service records, adjusting the weight or attribute of service records according to the service association rule, etc. The purpose of fusion is to obtain a more refined, accurate and valuable association information containing service data set, which is used for subsequent analysis, prediction or decision support.

[0135] The embodiment obtains index correlation information by performing correlation analysis on the industry advantage index, the regional advantage index, the enterprise self-risk information, and the enterprise correlation risk information; acquires a preset weight distribution table, maps the industry advantage index, the regional advantage index, the enterprise self-risk information, and the enterprise correlation risk information to the weight distribution table, and obtains index weight information; and fuses the industry advantage index, the regional advantage index, the enterprise self-risk information, and the enterprise correlation risk information according to the index correlation information, so as to effectively obtain an enterprise characteristic index set integrating multiple indexes and risk information, to facilitate subsequent text generation processing.

[0136] With reference to the foregoing Figure 7 In some optional implementations of the embodiment, step S50 includes the following steps:

[0137] Step S501: constructing a multi-dimensional service data cube with service platforms, service business types, and service times as dimensions, and user evaluation scores and completion rates as measurement values according to the fused service data set;

[0138] In the embodiment, the step of constructing a multi-dimensional service data cube includes determining dimensions: service platforms (such as PC terminals, mobile terminals, and applets), service business types (such as query, submission for audit, and consultation), and service times (which can be specific time points, time periods, or dates). Determining measurement values: user evaluation scores (usually a numerical value representing user satisfaction with the service) and completion rates (representing the percentage of services successfully completed). Constructing a data cube: constructing a multi-dimensional data cube according to the above dimensions and measurement values. The cube will contain measurement value data under different dimension combinations.

[0139] Step S502: performing measurement value difference analysis on the multi-dimensional service data cube to obtain key influencing factors;

[0140] In the embodiment, the step of measurement value difference analysis includes comparing measurement values (user evaluation scores and completion rates) under different dimension combinations to find out the difference items between them. Analyzing the difference items to identify which dimensions have a significant impact on the measurement values. For example, user evaluation scores on a certain service platform may be generally low, or the completion rate in a certain time period may be particularly high. If we find that user evaluation scores on mobile terminals are generally higher than on PC terminals, the service experience on mobile terminals may be better. If we find that the completion rate in a certain time period (such as night) is particularly low, we may need to investigate whether there are problems in the service process during that time period.

[0141] Step S503: constructing the multi-terminal service evaluation model according to the fused service data set and the key influencing factors.

[0142] In the present embodiment, the step of constructing the multi-terminal service evaluation model includes selecting key influencing factors: based on the results of the difference analysis of the metric values, we select the dimensions that have a significant impact on the metric values as the key influencing factors. Constructing the model: using these key influencing factors and the fused service dataset to construct a multi-terminal service evaluation model, and using the verification dataset to verify the accuracy of the model and optimize it as needed. The multi-terminal service evaluation model can be used to predict the service evaluation score under different dimension combinations, which reflects the true score of the service business, providing a reliable basis for subsequent service business optimization.

[0143] The present embodiment constructs a multi-dimensional service data cube according to the fused service dataset, taking the service platform, service business type, and service time as dimensions, and taking the user evaluation score and completion rate as metric values; performs difference analysis of the metric values on the multi-dimensional service data cube to obtain key influencing factors; and constructs the multi-terminal service evaluation model according to the fused service dataset and the key influencing factors. Thus, the key influencing factors of the fused dataset are effectively used to construct a multi-terminal service evaluation model that can accurately evaluate the operation results of service businesses.

[0144] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by computer readable instructions instructing related hardware, which can be stored in a computer readable storage medium. The program, when executed, can include the processes of the above-mentioned embodiments. The storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0145] It should be understood that although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with other steps or sub-steps or stages of other steps.

[0146] Further reference is made to Figure 8 , as to the above Figure 1To achieve the method, the application provides an embodiment of a government service business evaluation device, which is applied to Figure 1 The device embodiment corresponds to the method embodiment, and the device can be applied to various electronic devices.

[0147] As Figure 8 shown, the government service business evaluation device 700 comprises an information processing module 701, an information association module 702, a data mapping module 703, an association fusion module 704, a model construction module 705, and a service evaluation module 706.

[0148] The information processing module 701 is configured to obtain multi-channel user evaluation information, pre-process the multi-channel user evaluation information, and obtain standard user evaluation information.

[0149] The information association module 702 is configured to associate the standard user evaluation information with service operations, and construct a service behavior relationship graph.

[0150] The data mapping module 703 is configured to map data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule, and obtain a service data set.

[0151] The association fusion module 704 is configured to associate and fuse the service data set based on a preset data fusion technology, and obtain a fused service data set.

[0152] The model construction module 705 is configured to associate service operations and user evaluation information of different channels based on the fused service data set, and construct a multi-terminal service evaluation model.

[0153] The service evaluation module 706 is configured to obtain real-time evaluation information, input the real-time evaluation information into the multi-terminal service evaluation model, and obtain a service evaluation score.

[0154] The embodiment obtains multi-channel user evaluation information, pre-processes the multi-channel user evaluation information to obtain standard user evaluation information, associates service operations according to the standard user evaluation information, constructs a service behavior relationship graph, maps data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set, associates and fuses the service data set based on a preset data fusion technology to obtain a fused service data set, associates service operations and user evaluation information of different channels according to the fused service data set to construct a multi-terminal service evaluation model, obtains real-time evaluation information, inputs the real-time evaluation information into the multi-terminal service evaluation model to obtain a service evaluation score. Thus, the corresponding service evaluation score is generated according to the real-time evaluation of the user on the service business, the quality of service is effectively comprehensively considered, and an effective and reliable basis is provided for subsequent optimization of the service business.

[0155] To solve the above technical problems, the embodiment of the present application further provides a computer device. For details, please refer to Figure 9 , Figure 9 The basic structure block diagram of the computer device of the embodiment is shown in the figure.

[0156] The computer device 9 comprises a memory 81, a processor 82 and a network interface 83 which are connected to each other through a system bus. It should be pointed out that only the computer device 8 with components 81-83 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 can understand that the computer device here is a device capable of automatically performing numerical calculation 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.

[0157] The computer device can be a desktop computer, a notebook computer, a palm computer and a cloud server, etc. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad or a voice control device, etc.

[0158] The memory 81 includes at least one type of readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or a memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 8. Of course, the memory 81 can also include both an internal storage unit and an external storage device of the computer device 8. In this embodiment, the memory 81 is generally used to store an operating system and various application software installed on the computer device 8, such as computer readable instructions of the government service business evaluation method, etc. In addition, the memory 81 can also be used to temporarily store various data that have been output or will be output.

[0159] The processor 82 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer readable instructions or process data stored in the memory 81, such as computer readable instructions of the government service business evaluation method.

[0160] The network interface 83 can include a wireless network interface or a wired network interface, which is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0161] The embodiment can obtain multi-channel user evaluation information by using the computer device, pre-process the multi-channel user evaluation information to obtain standard user evaluation information, associate the standard user evaluation information with service operations to construct a service behavior relationship graph, map data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set, associate and fuse the service data set based on a preset data fusion technology to obtain a fused service data set, associate service operations and user evaluation information of different channels according to the fused service data set to construct a multi-terminal service evaluation model, obtain real-time evaluation information, input the real-time evaluation information into the multi-terminal service evaluation model, and obtain a service evaluation score. Therefore, the corresponding service evaluation score can be generated according to real-time evaluation of a user on a service business, the service quality can be effectively comprehensively considered, and an effective and reliable basis is provided for optimization of subsequent service businesses.

[0162] The application also provides another implementation, that is, a computer readable storage medium storing computer readable instructions, which can be executed by at least one processor to enable the at least one processor to perform the steps of the government service business evaluation method as described above.

[0163] The embodiment can obtain multi-channel user evaluation information by using the computer device, pre-process the multi-channel user evaluation information to obtain standard user evaluation information, associate the standard user evaluation information with service operations to construct a service behavior relationship graph, map data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set, associate and fuse the service data set based on a preset data fusion technology to obtain a fused service data set, associate service operations and user evaluation information of different channels according to the fused service data set to construct a multi-terminal service evaluation model, obtain real-time evaluation information, input the real-time evaluation information into the multi-terminal service evaluation model, and obtain a service evaluation score. Therefore, the corresponding service evaluation score can be generated according to real-time evaluation of a user on a service business, the service quality can be effectively comprehensively considered, and an effective and reliable basis is provided for optimization of subsequent service businesses.

[0164] Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the method described in each embodiment of the present application.

[0165] Obviously, the above-described embodiments are only some of the embodiments of the present application, not all the embodiments, and the drawings show the preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing specific embodiments, or make equivalent replacements to some of the technical features. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the scope of the patent protection of the present application.

Claims

1. A government service business evaluation method characterized by comprising: The method comprises the following steps: obtaining multi-channel user evaluation information, preprocessing the multi-channel user evaluation information to obtain standard user evaluation information; associating the standard user evaluation information with service operations to construct a service behavior relationship graph; mapping the data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set; associating and fusing the service data set based on a preset data fusion technology to obtain a fused service data set; associating the service operations and user evaluation information of different channels based on the fused service data set to construct a multi-terminal service evaluation model; obtaining real-time evaluation information and inputting the real-time evaluation information into the multi-terminal service evaluation model to obtain a service evaluation score; The step of associating the standard user evaluation information with service operations to construct a service behavior relationship graph comprises the following steps: extracting corresponding service operation data from a database according to the standard user evaluation information; normalizing the service operation data to obtain standardized service operation data; generating a globally unique number for each service operation in the standardized service operation data; associating the same type of service operations of different channels based on the globally unique number to construct a service operation directed graph; constructing the service behavior relationship graph based on the service operation directed graph; The step of constructing the service behavior relationship graph based on the service operation directed graph comprises the following steps: performing community division on the service operation directed graph based on a community discovery algorithm to obtain a service operation community set; performing association rule mining on each service operation community in the service operation community set based on an association rule mining algorithm to obtain a service association mode; constructing the service behavior relationship graph based on the service operation community set and the service association mode, wherein the service operations in the service operation community set are used as nodes of the service behavior relationship graph, and the service association mode is used to construct edges of the service behavior relationship graph to represent the association relationship between the service operations.

2. The government service business evaluation method according to claim 1, characterized by, The step of obtaining multi-channel user evaluation information and preprocessing the multi-channel user evaluation information to obtain standard user evaluation information comprises the following steps: obtaining user original evaluation information from a preset web page and software end; identifying and encoding the original evaluation information according to a preset unified data standard specification to obtain the multi-channel user evaluation information; performing data cleaning and filtering on the multi-channel user evaluation information according to a preset data field definition, data type and value range rule to obtain valid user evaluation information; performing natural language processing on the valid user evaluation information to obtain the standard user evaluation information.

3. The government service business evaluation method according to claim 1, characterized by, The step of mapping the data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set comprises the following steps: obtaining service original data corresponding to each service operation in the service behavior relationship graph; extracting service key information from the service original data to obtain service key information; The service key information is organized in a unified data structure, and a standard service data record is constructed; A relational data table is created, the standard service data record is inserted into the relational data table, and the service data set is obtained.

4. The government service business evaluation method according to claim 1, characterized by, The step of associating and fusing the service data set based on the preset data fusion technology specifically includes: The standard service data record is extracted from the service data set, and the standard service data record is preprocessed to obtain service key features; The similarity between the standard service data records is calculated according to the service key features, and the standard service data records are clustered according to the calculated similarity to obtain a service data clustering result; According to the service data clustering result, a data association mode is identified, and a service association rule between service behavior and service result is constructed based on the data association mode; According to the service association rule, the service data set is fused to obtain the fused service data set.

5. The government service business evaluation method according to claim 1, characterized by, The step of associating the service operation and user evaluation information of different channels according to the fused service data set to construct a multi-terminal service evaluation model specifically includes: According to the fused service data set, a multi-dimensional service data cube is constructed with service platform, service business type, and service time as dimensions and user evaluation score and completion rate as measurement values; The multi-dimensional service data cube is subjected to measurement value difference analysis to obtain key influencing factors; The multi-terminal service evaluation model is constructed according to the fused service data set and the key influencing factors.

6. A government service business evaluation device characterized by comprising: The government service business evaluation device is used to implement the government service business evaluation method according to any one of claims 1-5, and the government service business evaluation device comprises: An information processing module is configured to obtain multi-channel user evaluation information, preprocess the multi-channel user evaluation information, and obtain standard user evaluation information; An information association module is configured to associate service operations according to the standard user evaluation information and construct a service behavior relationship graph; A data mapping module is configured to map data corresponding to each service in the service behavior relationship graph to a unified data structure according to a preset data mapping rule to obtain a service data set; An association fusion module is configured to associate and fuse the service data set based on a preset data fusion technology to obtain a fused service data set; A model construction module is configured to associate service operations and user evaluation information of different channels according to the fused service data set to construct a multi-terminal service evaluation model; A service evaluation module is configured to obtain real-time evaluation information, input the real-time evaluation information into the multi-terminal service evaluation model, and obtain a service evaluation score.

7. A computer device, comprising: The memory stores computer readable instructions, and the processor executes the computer readable instructions to implement the steps of the government service business evaluation method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the steps of the government service business evaluation method in any one of claims 1 to 5.

Images