Service activity data processing method, device, system, equipment, medium and product

Abstract

The present application provides a service activity data processing method, device, system, equipment, medium and product, which relates to the field of cloud computing technology. The method includes: first, obtaining a service entity and target service activity data associated with the service entity from the service activity data; then, identifying the service category corresponding to the target service activity data; determining service activity indicators of multiple dimensions from the target service activity data; and finally, generating a service activity analysis report based on the service entity, service category and service activity indicators of multiple dimensions. In this embodiment, a service activity analysis report is generated based on service entities, service categories and service activity indicators of multiple dimensions. The service activity indicators are used to characterize service quality and / or user emotional tendencies. In-depth analysis of service activities can be performed from multiple dimensions to provide reliable decision support for service activities.

Description

Technical Field

[0001] The present application relates to the field of cloud computing technology, and in particular to a service activity data processing method, device, system, equipment, medium and product. Background Art

[0002] Service activity data refers to the records of activities that companies and users interact with, such as customer service, technical support, and after-sales maintenance. As the scale of corporate services expands, it becomes increasingly difficult to manually process massive amounts of service activity data, which is not only inefficient, but also difficult to accurately capture subtle changes in customer needs and service quality.

[0003] In related technologies, service activity data analysis mostly relies on simple statistical analysis. The analysis results are of a single dimension and lack analysis depth, which cannot provide reliable decision support for service activities. Summary of the invention

[0004] The embodiments of the present application provide a service activity data processing method, device, system, equipment, medium and product, which can conduct in-depth analysis of service activities from multiple dimensions, generate analysis reports, and provide reliable decision support for service activities.

[0005] In a first aspect, an embodiment of the present application provides a method for processing service activity data, including:

[0006] Obtaining the service entity and the service activity data associated with the service entity from the service activity data;

[0007] Identify the service category corresponding to the target service activity data;

[0008] Determine service activity indicators of multiple dimensions from the target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendencies;

[0009] Generate service activity analysis reports based on service entities, service categories and service activity indicators.

[0010] In a second aspect, an embodiment of the present application provides a service activity data processing device, including:

[0011] A data acquisition module, used for acquiring service entities and service activity data associated with the service entities from service activity data;

[0012] A category identification module, used to identify the service category corresponding to the target service activity data;

[0013] An indicator determination module is used to determine service activity indicators of multiple dimensions from target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendencies;

[0014] The report generation module is used to generate service activity analysis reports based on service entities, service categories and service activity indicators.

[0015] In a third aspect, an embodiment of the present application provides a service activity data processing system, including:

[0016] Data collection module, used to collect service activity data from different channels;

[0017] A data processing module, used to obtain a service entity and target service activity data associated with the service entity from the service activity data, and identify a service category corresponding to the target service activity data;

[0018] A data analysis module, used to determine service activity indicators of multiple dimensions from target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendencies;

[0019] The report generation module is used to generate service activity analysis reports based on service entities, service categories and service activity indicators.

[0020] In a fourth aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the above methods when executing the computer program.

[0021] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any of the above methods is implemented.

[0022] In a sixth aspect, an embodiment of the present application provides a computer program product, the computer program product including a computer program, and the computer program implements any of the above methods when executed by a processor.

[0023] Compared with the prior art, this application has the following advantages:

[0024] The present application provides a method, apparatus, system, device, medium and product for processing service activity data. First, service entities and service activity data associated with the service entities are obtained from the service activity data; then, the service category corresponding to the target service activity data is identified; service activity indicators of multiple dimensions are determined from the target service activity data; finally, a service activity analysis report is generated based on the service entity, service category and service activity indicators of multiple dimensions. In this embodiment, a service activity analysis report is generated based on service entities, service categories and service activity indicators of multiple dimensions. The service activity indicators are used to characterize service quality and / or user emotional tendencies. In-depth analysis of service activities can be performed from multiple dimensions to provide reliable decision support for service activities.

[0025] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments according to the present application and should not be regarded as limiting the scope of the present application.

[0027] Figure 1 It is a schematic diagram of a service activity data processing system according to an embodiment of the present application.

[0028] Figure 2 This is a flowchart of a service activity data processing method according to an embodiment of the present application.

[0029] Figure 3 This is a flowchart of a service activity data processing method according to an embodiment of the present application.

[0030] Figure 4 This is a structural block diagram of a service activity data processing device according to an embodiment of the present application.

[0031] Figure 5 A block diagram of an electronic device used to implement an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the concept or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary in nature and not restrictive.

[0033] To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes the related technologies of the embodiments of the present application. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0034] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0035] The solution of the embodiment of the present application is applicable to various customer service management systems, enterprise-level customer relationship management (CRM) systems, information technology service desk software and monitoring and analysis platforms of cloud service providers, and aims to improve the automation level and data analysis capabilities of service management.

[0036] Figure 1 A schematic diagram of the service activity data processing system provided by this application. Figure 1 As shown, the service activity data processing system includes: a data collection module 101, a data processing module 102, a data analysis module 103 and a report generation module 104. The report generation module 104 includes a visualization processing unit and a report generation unit.

[0037] The data collection module 101 is used to collect service activity data from different service channels (such as emails, communication records, work order management systems, etc.). Specifically, the application programming interface (API) is used to connect with each service channel to pull service activity data in real time or at a scheduled time. The received service activity data is pre-processed, such as deduplication, format unification, timestamp standardization, etc., to ensure the consistency of subsequent processing. Databases (such as MySQL, MongoDB, etc.) or big data storage solutions (such as distributed file system Hadoop HDFS, search data analysis engine Elasticsearch) are used to efficiently store service activity data, and data models are designed to support efficient query and analysis.

[0038] The data processing module 102 includes an entity recognition unit and a data classification unit. The entity recognition unit is used to perform service entity recognition and relationship extraction. Specifically, first, a named entity recognition (NER) model is used to identify service entities such as user names and contact information in the text. The NER model can be obtained by fine-tuning a pre-trained text recognition model using a data set on the field corresponding to the service activity data, wherein the text recognition model, such as a bidirectional encoder model based on a transformer (Bidirectional Encoder Representations from Transformers, BERT), etc., can improve the recognition accuracy by fine-tuning the model. Then, a relationship extraction model is used to perform relationship extraction, identify the association between the service entity and the service activity data, such as the correspondence between the user identifier and the service request content, thereby obtaining the target service activity data associated with the service entity. The data classification unit is used to obtain the service category. Specifically, first, a keyword extraction model is used to extract keywords from the target service activity data associated with the service entity, and text features are constructed based on the keywords. Based on the constructed text features, a text classification model is applied for classification. Among them, keyword extraction models include but are not limited to: term frequency-inverse document frequency (TF-IDF) model, keyword extraction algorithm TextRank or attention mechanism of pre-trained model. Text classification models include but are not limited to: TextCNN model that uses convolutional neural network to classify text, Transformer-based model, etc. Text classification models are pre-trained on a large number of annotated service activity data sets, and service categories include but are not limited to: consultation, complaint, maintenance, etc.

[0039] The data analysis module 103 includes a statistical analysis unit, and optionally, may also include an anomaly detection unit. The statistical analysis unit is used to use statistical analysis tools to perform data aggregation and statistics, and calculate service activity indicators such as service activity frequency, service response time, satisfaction information (for example, service satisfaction in text form: excellent, good, poor; service satisfaction in icon form: a few stars; service satisfaction in numerical form: score). Among them, statistical analysis tools include but are not limited to: Structured Query Language (SQL) query tools, tabular data framework Pandas DataFrame, etc. The anomaly detection unit is used to identify abnormal service activities, such as abnormally high complaint rates or excessively long response times, based on service activity indicators, using statistical methods (such as box plot analysis) or machine learning models (such as Isolation Forest algorithm, Autoencoder model).

[0040] The report generation module 104 includes a visualization processing unit and a report generation unit. The visualization processing unit is used to convert the indicator values ​​of multiple service activity indicators into charts, such as bar charts, line charts, heat maps, etc., using data visualization tools (such as Matplotlib, Seaborn, Plotly or Tableau) to intuitively display the overview of service activities. Optionally, the anomaly detection results detected by the anomaly detection unit can also be converted into a chart form through a visualization tool. The report generation unit is used to automatically generate a report. Specifically, a report template is obtained, and a report template is generated using a report template engine (such as a Python-based template engine Jinja2, etc.), and the content is dynamically filled according to the analysis results. The service activity analysis report may include service activity entities, detailed analysis of service activity indicators, service activity trend forecasts, improvement suggestions, and other content. In addition, a web page creation tool can also be used to create an interactive report interface, allowing users to filter and sort data as needed to improve user experience. Among them, the web page creation tool includes but is not limited to: Hyper Text Mark-up Language (HTML), Cascading Style Sheets (CSS), JavaScript, Dash or Streamlit library, etc.

[0041] In this embodiment, the named entity recognition model is used to identify service entities, which can improve the accuracy and completeness of information extraction. Based on the service category and service activity indicators of multiple dimensions, a service activity analysis report is generated, and the service activities can be deeply analyzed from multiple dimensions according to the service category, which increases the depth and breadth of the analysis and can provide more insightful reports. In addition, the data acquisition module, data processing module, data analysis module and report generation module can be completely decoupled, and each module can be configured independently, which is convenient for adjustment and optimization according to different service requirements.

[0042] An embodiment of the present application provides a method for processing service activity data. The method in this embodiment can be applied to servers, terminal devices, platforms, devices, etc. with computing and processing capabilities, wherein the server can be a server cluster or a single server, a server deployed in the cloud, or a local server.

[0043] like Figure 2 The flowchart of the service activity data processing method according to an embodiment of the present application is shown, including:

[0044] Step S201: Acquire a service entity and target service activity data associated with the service entity from service activity data.

[0045] Service activity data refers to the activity records of the interaction between the enterprise and the user, such as data related to problem consultation, technical support, after-sales maintenance, etc. Service entities refer to the named entities involved in service activities, such as user identification, user contact information, operating system version, kernel version, etc.

[0046] Step S202: identifying the service category corresponding to the target service activity data.

[0047] The target service activity data associated with the service entity, for example, the service request content associated with user A, etc. Service categories include but are not limited to: consultation, complaint, maintenance, etc.

[0048] Step S203, determining service activity indicators of multiple dimensions from the target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendency.

[0049] The service activity indicators of multiple dimensions include at least two of the following: service activity frequency, service response time or service satisfaction score. Among them, indicators such as service activity frequency and service response time are used to characterize service quality, and service satisfaction score is used to characterize user emotional tendencies.

[0050] Step S204: Generate a service activity analysis report based on the service entity, service category and service activity indicator.

[0051] Based on the service entity, service category and service activity indicator, multiple dimensions of analysis and processing are performed, and a service activity analysis report is generated based on the analysis and processing results. The service activity analysis report can include multiple types of data, such as text, charts, etc. The service activity analysis report is convenient for helping users to quickly grasp the service dynamics and make timely strategy adjustments.

[0052] The service activity data processing method provided in the embodiment of the present application first obtains the service entity and the target service activity data associated with the service entity from the service activity data; then identifies the service category corresponding to the target service activity data; determines the service activity indicators of multiple dimensions from the target service activity data; and finally, generates a service activity analysis report based on the service entity, service category, and service activity indicators of multiple dimensions. In this embodiment, a service activity analysis report is generated based on the service entity, service category, and service activity indicators of multiple dimensions. The service activity indicators are used to characterize the service quality and / or user emotional tendencies, and can perform in-depth analysis of service activities from multiple dimensions to provide reliable decision support for service activities.

[0053] The specific implementation process of the above steps is described in detail below through multiple implementation methods.

[0054] In one implementation, step S201, obtaining a service entity and service activity data associated with the service entity, includes: identifying the service entity from the service activity data using a named entity recognition model; and based on the service entity, obtaining target service activity data associated with the service entity using a relationship extraction model.

[0055] Optionally, a NER model is used to identify service entities such as user names and contact information in the service activity data. The NER model can be obtained by fine-tuning a pre-trained text recognition model using a data set in the field corresponding to the service activity data. The text recognition model, such as the BERT model, can improve recognition accuracy by fine-tuning the model.

[0056] Then, the relationship extraction model is used to extract relationships and identify the association between service entities and service activity data, such as the correspondence between user identifiers and service request content, so as to obtain the target service activity data associated with the service entity. The relationship extraction model can use predefined patterns or rules to identify the relationship between service entities and service activity data, for example, based on trigger words or dependency patterns (syntax trees) for relationship extraction.

[0057] In this embodiment, the NER model is used to identify service entities, and the relationship extraction model is used to extract relationships, which can improve the accuracy and completeness of information extraction.

[0058] In one implementation, step S202, identifying the service category corresponding to the target service activity data, includes: extracting keywords from the target service activity data, constructing text features based on the keywords; and obtaining the service category corresponding to the target service activity data using a service classification model based on the text features.

[0059] The keyword extraction model is used to extract keywords from the target service activity data. The keyword extraction model includes but is not limited to: TF-IDF model, keyword extraction algorithm TextRank or attention mechanism of pre-trained model. The text feature vector is constructed using keywords and input into the service classification model to obtain the service category.

[0060] Among them, the service classification model can be obtained by training a pre-trained text classification model using data from the corresponding field of the service activity data. The service classification model includes but is not limited to: TextCNN, a model that classifies text using a convolutional neural network, a Transformer-based model, etc. The service classification model is pre-trained on a large number of labeled service activity data sets, and the service categories are not limited to: consultation, complaint, maintenance, etc.

[0061] In this embodiment, by acquiring the service category, it is possible to perform service activity data analysis according to the service category, and obtain detailed analysis results of the service activity data.

[0062] In one implementation, step S203, determining service activity indicators in multiple dimensions from the target service activity data, includes: performing statistical analysis on the target service activity data to obtain service activity indicators in multiple dimensions.

[0063] Use statistical analysis tools to summarize data and calculate the indicator values ​​of service activity indicators in multiple dimensions, such as service activity frequency, service response time, service satisfaction information, etc.

[0064] Among them, statistical analysis tools include but are not limited to: SQL query tools, tabular data frame PandasDataFrame, etc.

[0065] In this embodiment, by performing statistical analysis on service activity indicators in multiple dimensions, multi-dimensional analysis of service activity data can be achieved, which can improve the depth and breadth of service activity data analysis.

[0066] In one implementation, after determining the service activity indicators of multiple dimensions in the target service activity data, the service activity data processing method also includes: determining the abnormal service activities corresponding to the service entities based on the service activity indicators of multiple dimensions; and determining the abnormal level of the abnormal service activities according to the degree of deviation between the service activity indicators of multiple dimensions and the preset indicator standard values ​​of multiple dimensions.

[0067] In practical applications, based on service activity indicators, statistical methods (such as box plot analysis) or machine learning models (such as isolation forest algorithm, autoencoder model) are used to identify abnormal service activities, such as abnormally high complaint rates or extremely long response times.

[0068] Set standard values ​​for indicators in multiple dimensions, compare the indicator values ​​of service activity indicators with the standard values, determine the degree of deviation based on the comparison results, and then determine the abnormal level of the service activity, and determine corresponding improvement suggestions based on the abnormal level.

[0069] In this embodiment, by performing abnormal analysis on the service activity data, it is convenient to remind users to pay attention to service dynamics and make timely adjustments.

[0070] In one implementation, step S204 generates a service activity analysis report based on service entities, service categories, and service activity indicators, including: visualizing the service entities, service categories, and service activity indicators to obtain a visualization chart; obtaining a report template from a report template engine, and generating a visualized service activity analysis report based on the visualization chart and the report template.

[0071] Specifically, data visualization tools (such as Matplotlib, Seaborn, Plotly, or Tableau) are used to convert the indicator values ​​and anomaly detection results of multiple service activity indicators into charts, such as bar charts, line charts, heat maps, etc., to intuitively display the overview of service activities.

[0072] Generate a report template using a report template engine (such as the Python-based template engine Jinja2, etc.), fill the visualization chart into the report template, and obtain a visualization service activity analysis report. The service activity analysis report can include service activity entities, detailed analysis of service activity indicators, service activity trend forecasts, improvement suggestions, and other content.

[0073] In this embodiment, by generating a visualized service activity analysis report, users can understand the dynamics of service activities more intuitively.

[0074] In one implementation, the service activity data processing method further includes: displaying a service activity analysis report using an interactive report interface; filtering or sorting display content in the service activity analysis report according to interactive operation instructions, and displaying the filtered or sorted display content to the user.

[0075] In actual applications, an interactive report interface can be created in advance and directly called when needed, or it can be created in real time. Specifically, an interactive report interface can be created using a web page creation tool, allowing users to filter and sort data as needed. The interactive operation instructions include but are not limited to clicking on any service entity, entering filtering conditions, setting sorting conditions, etc.

[0076] Among them, web page creation tools include but are not limited to: Hyper Text Mark-up Language (HTML), Cascading Style Sheets (CSS), JavaScript, Dash or Streamlit library, etc.

[0077] In this embodiment, by generating an interactive service activity analysis report, the user's interactive operation needs can be met and the user experience can be improved.

[0078] An embodiment of the present application provides a method for processing service activity data. The method in this embodiment can be applied to servers, terminal devices, platforms, devices, etc. with computing and processing capabilities, wherein the server can be a server cluster or a single server, a server deployed in the cloud, or a local server.

[0079] like Figure 3 The flowchart of the service activity data processing method according to an embodiment of the present application is shown, including:

[0080] Step S301: identifying service entities from service activity data using a named entity recognition model.

[0081] The NER model is used to identify service entities such as user names and contact information in the service activity data. The NER model can be obtained by fine-tuning a pre-trained text recognition model using a data set in the field corresponding to the service activity data, where the text recognition model is, for example, a BERT model.

[0082] Step S302: Based on the service entity, the target service activity data associated with the service entity is acquired using a relationship extraction model.

[0083] Relationship extraction models are used to extract relationships and identify the association between service entities and service activity data, such as the correspondence between user identifiers and service request content, so as to obtain target service activity data associated with service entities. Relationship extraction models can use predefined patterns or rules to identify the relationship between service entities and service activity data, for example, based on trigger words or dependency patterns (syntax trees) for relationship extraction.

[0084] Step S303: extract keywords from the target service activity data, and construct text features based on the keywords.

[0085] Use the keyword extraction model to extract keywords from the target service activity data. The keyword extraction model includes but is not limited to: TF-IDF model, keyword extraction algorithm TextRank or attention mechanism of pre-trained model.

[0086] Step S304: based on the text features and using the service classification model, obtain the service category corresponding to the target service activity data.

[0087] The service classification model can be obtained by training a pre-trained text classification model using data from the field corresponding to the service activity data. The service classification model includes but is not limited to: TextCNN, a model that uses a convolutional neural network to classify text, a Transformer-based model, etc. The service classification model is pre-trained on a large number of labeled service activity data sets. Service categories include but are not limited to: consultation, complaint, maintenance, etc.

[0088] Step S305: Statistically analyze the target service activity data to obtain service activity indicators in multiple dimensions.

[0089] Use statistical analysis tools to summarize data and calculate the indicator values ​​of service activity indicators in multiple dimensions, such as service activity frequency, service response time, service satisfaction information, etc.

[0090] Among them, statistical analysis tools include but are not limited to: SQL query tools, tabular data frame PandasDataFrame, etc.

[0091] Step S306: Visualize the service entities, service categories, and service activity indicators to obtain visualization charts.

[0092] Use data visualization tools (such as Matplotlib, Seaborn, Plotly, or Tableau) to convert the indicator values ​​and anomaly detection results of multiple service activity indicators into charts, such as bar charts, line charts, heat maps, etc., to intuitively display the overview of service activities.

[0093] Step S307, obtaining a report template from a report template engine, and generating a visualized service activity analysis report based on the visualized chart and the report template.

[0094] Generate a report template using a report template engine (such as the Python-based template engine Jinja2, etc.), fill the visualization chart into the report template, and obtain a visualization service activity analysis report. The service activity analysis report can include service activity entities, detailed analysis of service activity indicators, service activity trend forecasts, improvement suggestions, and other content.

[0095] Step S308: display the service activity analysis report using an interactive report interface.

[0096] An interactive report interface can be created in advance and called directly when needed, or it can be created in real time. Specifically, an interactive report interface can be created using a web page creation tool, allowing users to filter and sort data as needed. Web page creation tools include, but are not limited to: Hyper Text Mark-up Language (HTML), Cascading Style Sheets (CSS), JavaScript, Dash or Streamlit libraries, etc.

[0097] Step S309: filtering or sorting the display content in the service activity analysis report according to the interactive operation instruction, and displaying the filtered or sorted display content to the user.

[0098] Among them, the interactive operation instructions include but are not limited to clicking on any service entity, entering filtering conditions, setting sorting conditions, etc.

[0099] In this embodiment, the named entity recognition model is used to identify service entities, which can improve the accuracy and completeness of information extraction. Based on the service category and service activity indicators of multiple dimensions, a service activity analysis report is generated, and the service activities can be deeply analyzed from multiple dimensions according to the service category, which increases the depth and breadth of the analysis and can provide a more insightful report. By generating an interactive service activity analysis report, the user's interactive operation needs can be met and the interactivity of decision support can be improved.

[0100] Corresponding to the application scenario and method of the method provided in the embodiment of the present application, the embodiment of the present application also provides a service activity data processing device. Figure 4 The figure is a structural block diagram of a service activity data processing device according to an embodiment of the present application, the device comprising:

[0101] The data acquisition module 401 is used to acquire a service entity and target service activity data associated with the service entity from the service activity data.

[0102] The category identification module 402 is used for identifying the service category corresponding to the target service activity data.

[0103] The indicator determination module 403 is used to determine service activity indicators of multiple dimensions from the target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendency.

[0104] The report generation module 404 is used to generate a service activity analysis report based on the service entity, service category and service activity indicator.

[0105] The service activity data processing device provided in the embodiment of the present application first obtains the service entity and the target service activity data associated with the service entity from the service activity data; then identifies the service category corresponding to the target service activity data; determines the service activity indicators of multiple dimensions from the target service activity data; and finally, generates a service activity analysis report based on the service entity, service category, and service activity indicators. In this embodiment, a service activity analysis report is generated based on the service entity, service category, and service activity indicators of multiple dimensions. The service activity indicators are used to characterize the service quality and / or user emotional tendencies, and can perform in-depth analysis of service activities from multiple dimensions to provide reliable decision support for service activities.

[0106] In one implementation, the data acquisition module 401 is used to: identify service entities from service activity data using a named entity recognition model; the named entity recognition model is obtained by training a pre-trained text recognition model using data in a field corresponding to the service activity data; based on the service entity, the target service activity data is acquired using a relationship extraction model.

[0107] In one implementation, the category identification module 402 is used to: extract keywords from the target service activity data, and construct text features based on the keywords; based on the text features, use a service classification model to obtain the service category corresponding to the service activity data associated with the service entity, and the service classification model is obtained by training a pre-trained text classification model using data in the field corresponding to the service activity data.

[0108] In one implementation, the indicator determination module 403 is used to: perform statistical analysis on the target service activity data to obtain service activity indicators of multiple dimensions; the service activity indicators of multiple dimensions include at least two of the following: service activity frequency, service response time, and service satisfaction information.

[0109] In one implementation, the service activity data processing device is also used to: after determining the service activity indicators of multiple dimensions from the target service activity data, determine the abnormal service activities corresponding to the service entity based on the service activity indicators of multiple dimensions; and determine the abnormal level of the abnormal service activity according to the degree of deviation between the service activity indicators of multiple dimensions and the preset indicator standard values ​​of multiple dimensions.

[0110] In one implementation, the report generation module 404 is used to: visualize service entities, service categories, and service activity indicators to obtain visualization charts; obtain report templates from a report template engine, and generate a visualized service activity analysis report based on the visualization charts and report templates.

[0111] In one implementation, the service activity data processing device is also used to: display the service activity analysis report using an interactive report interface; filter or sort the display content in the service activity analysis report according to interactive operation instructions, and display the filtered or sorted display content to the user.

[0112] The functions of each module in the embodiment of the present application can be referred to the corresponding description in the above method, and have corresponding beneficial effects, which will not be repeated here.

[0113] Figure 5 FIG. 1 is a block diagram of an electronic device used to implement an embodiment of the present application. Figure 5 As shown, the electronic device includes: a memory 510 and a processor 520. The memory 510 stores a computer program that can be run on the processor 520. When the processor 520 executes the computer program, the method in the above embodiment is implemented. The number of the memory 510 and the processor 520 can be one or more.

[0114] The electronic device also includes:

[0115] The communication interface 530 is used to communicate with external devices and perform data exchange transmission.

[0116] If the memory 510, the processor 520 and the communication interface 530 are implemented independently, the memory 510, the processor 520 and the communication interface 530 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0117] Optionally, in a specific implementation, if the memory 510, the processor 520 and the communication interface 530 are integrated on a chip, the memory 510, the processor 520 and the communication interface 530 can communicate with each other through an internal interface.

[0118] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.

[0119] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0120] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0121] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.

[0122] It should be understood that the above processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0123] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0124] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0125] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0126] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0127] Any process or method described in the flow chart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0128] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0129] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0130] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0131] The above is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope recorded in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for processing service activity data, characterized in that: The method comprises: Acquire a service entity and target service activity data associated with the service entity from the service activity data; Identify the service category corresponding to the target service activity data; Determine service activity indicators of multiple dimensions from the target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendency; the service activity indicators of multiple dimensions include at least two of the following: service activity frequency, service response time, and service satisfaction information; Generate a service activity analysis report based on the service entity, the service category and the service activity indicator; The identifying the service category corresponding to the target service activity data includes: Extracting keywords from the target service activity data, and constructing text features based on the keywords; Based on the text features, a service classification model is used to obtain the service category corresponding to the target service activity data. The service classification model is obtained by training a pre-trained text classification model using data in a field corresponding to the service activity data.

2. The method according to claim 1, characterized in that The acquiring of a service entity and target service activity data associated with the service entity includes: Using a named entity recognition model to identify the service entity from the service activity data; the named entity recognition model is obtained by training a pre-trained text recognition model using data in a field corresponding to the service activity data; Based on the service entity, a relationship extraction model is used to obtain target service activity data associated with the service entity.

3. The method according to claim 1, characterized in that Determining service activity indicators in multiple dimensions from the target service activity data includes: Statistical analysis is performed on the target service activity data to obtain service activity indicators in the multiple dimensions.

4. The method according to any one of claims 1 to 3, characterized in that: After determining the service activity indicators in multiple dimensions from the target service activity data, the method further includes: Determining abnormal service activities corresponding to the service entity based on the service activity indicators of the multiple dimensions; The abnormal level of the abnormal service activity is determined according to the degree of deviation between the service activity indicators of the multiple dimensions and the preset indicator standard values ​​of the multiple dimensions.

5. The method according to any one of claims 1 to 3, characterized in that: The generating a service activity analysis report based on the service entity, the service category and the service activity indicator comprises: Performing visualization processing on the service entity, the service category and the service activity indicator to obtain a visualization chart; A report template is obtained from a report template engine, and a visualized service activity analysis report is generated based on the visualization chart and the report template.

6. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Using an interactive reporting interface to display the service activity analysis report; According to the interactive operation instruction, the display content in the service activity analysis report is filtered or sorted, and the filtered or sorted display content is displayed to the user.

7. A service activity data processing device, characterized in that: The device comprises: A data acquisition module, used to acquire a service entity and target service activity data associated with the service entity from the service activity data; A category identification module, used to identify the service category corresponding to the target service activity data; An indicator determination module is used to determine service activity indicators of multiple dimensions from the target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendencies; the service activity indicators of multiple dimensions include at least two of the following: service activity frequency, service response time, and service satisfaction information; A report generation module, used to generate a service activity analysis report based on the service entity, the service category and the service activity indicator Among them, the category identification module is specifically used for: Keywords are extracted from the target service activity data, and text features are constructed based on the keywords. Based on the text features, a service classification model is used to obtain the service category corresponding to the target service activity data, and the service classification model is obtained by training a pre-trained text classification model using data in the field corresponding to the service activity data.

8. A service activity data processing system, characterized in that: The system comprises: Data collection module, used to collect service activity data from different channels; A data processing module, configured to obtain a service entity and target service activity data associated with the service entity from the service activity data, and identify a service category corresponding to the target service activity data; A data analysis module, used to determine service activity indicators of multiple dimensions from the target service activity data; the service activity indicators are used to characterize service quality and / or user emotional tendencies; the service activity indicators of multiple dimensions include at least two of the following: service activity frequency, service response time, and service satisfaction information; A report generation module, configured to generate a service activity analysis report based on the service entity, the service category and the service activity indicator; Wherein, when the data processing module identifies the service category corresponding to the target service activity data, it is used to: Keywords are extracted from the target service activity data, and text features are constructed based on the keywords. Based on the text features, a service classification model is used to obtain the service category corresponding to the target service activity data, and the service classification model is obtained by training a pre-trained text classification model using data in the field corresponding to the service activity data.

9. An electronic device, characterized in that: The electronic device comprises a memory, a processor and a computer program stored in the memory, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images