Insurance information determination method and device, equipment and storage medium
By obtaining and processing video and audio data during insurance sales, text conversion, face recognition and sentiment analysis, the problems of high labor costs and low automation are solved, information processing efficiency and accuracy are improved, and automated customers are realized Satisfaction assessment.
Patent Information
- Application Number
- CN202411080568.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-06
AI Technical Summary
The problems of high labor costs, low degree of automation, and low information processing efficiency and accuracy in the existing insurance sales process.
By obtaining video and audio data during insurance sales, text conversion, face recognition, sentiment analysis and compliance detection, key text information is automatically extracted to determine customer satisfaction. Specific steps include preprocessing of audio data, automatic speech recognition, error correction and natural language processing, preprocessing and face recognition of video data, application of emotion classification models, and use of generative semantic models to generate reports.
It reduces labor costs, improves the degree of automation and information processing efficiency, improves information accuracy, and realizes automated insurance information processing.
Smart Images

Figure CN119090531A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to an insurance information determination method, device, equipment and storage medium. Background Art
[0002] Traditional insurance dual recording technology solutions mainly rely on audio and video recording technology, combined with some basic analysis and processing tools to ensure compliance and customer service quality. First, the conversation between insurance sales staff and customers is recorded through dedicated audio and video equipment. These audio and video files are usually stored in cloud servers for subsequent review and analysis.
[0003] In terms of video processing, traditional solutions mainly perform basic processing, such as compression and cropping. Some systems may use basic facial recognition technology to verify the identity of customers and sales staff, but this is usually an independent process. Compliance testing mainly relies on quality inspectors to manually check the content of audio and video recordings to ensure that the sales process complies with regulatory requirements. Some systems may use simple rule engines for preliminary compliance testing. Customer satisfaction is usually conducted through post-surveys, such as telephone follow-up or online questionnaires. The collected customer feedback is manually sorted and analyzed to identify potential problems and improvement opportunities.
[0004] At present, the processing of relevant information in the insurance sales process mainly relies on manual work, which has high labor costs, low degree of automation, low information processing efficiency and low information accuracy. Summary of the invention
[0005] The present disclosure provides an insurance information determination method, device, equipment and storage medium to at least solve the existing problems of high labor cost, low automation, low information processing efficiency and low information accuracy.
[0006] The technical solution of the present disclosure is as follows:
[0007] The present disclosure provides a method for determining insurance information, including:
[0008] Acquire video and audio data during the insurance sales process;
[0009] Converting the audio data into text to obtain a transcribed text; and
[0010] Performing face recognition according to the video data to obtain a face recognition result;
[0011] When the face recognition result is a pass, extracting key text information from the transcribed text;
[0012] Performing sentiment analysis based on the key information of the text to obtain sentiment state information; and
[0013] Perform compliance testing based on the key information of the text to obtain compliance testing results;
[0014] Customer satisfaction with insurance sales is determined based on the emotional state information and the compliance test results.
[0015] Optionally, converting the audio data into text to obtain a transcribed text includes:
[0016] Performing a preprocessing operation on the audio data to obtain preprocessed audio data;
[0017] Using automatic speech recognition technology, converting the pre-processed audio data into initial text;
[0018] Inputting the initial text into an error correction model to perform text correction to obtain a corrected text;
[0019] The corrected text is segmented using natural language processing technology to obtain the transcribed text.
[0020] Optionally, extracting key text information from the transcribed text includes:
[0021] Performing a preprocessing operation on the transcribed text to obtain a preprocessed transcribed text;
[0022] Using natural language processing technology, segmenting and tagging the preprocessed transcribed text to obtain a segmented text;
[0023] Extracting keywords from the segmented text to obtain a keyword text;
[0024] The keyword text is input into a generative semantic model to obtain the key information of the text.
[0025] Optionally, performing sentiment analysis according to the text key information to obtain sentiment state information includes:
[0026] The text key information is input into the sentiment classification model to obtain the sentiment state information.
[0027] Optionally, determining customer satisfaction of insurance sales according to the emotional state information and the compliance detection result includes:
[0028] The emotional state information and the compliance test results are input into a satisfaction prediction model to obtain customer satisfaction with insurance sales.
[0029] Optionally, after determining the customer satisfaction of insurance sales according to the emotional state information and the compliance detection result, the method further includes:
[0030] generating a sentiment analysis report based on the emotional state information using a generative artificial intelligence model; and generating a compliance report based on the compliance detection results; and
[0031] A customer satisfaction report is generated based on the customer satisfaction.
[0032] The present disclosure also provides an insurance information determination device, including:
[0033] Data acquisition module, which acquires video data and audio data during the insurance sales process;
[0034] A text conversion module converts the audio data into text to obtain a transcribed text;
[0035] An identity recognition module performs face recognition based on the video data to obtain a face recognition result;
[0036] An information extraction module, when the face recognition result is a pass, extracts key text information from the transcribed text;
[0037] A sentiment analysis module performs sentiment analysis based on the key information of the text to obtain sentiment state information;
[0038] A compliance detection module performs compliance detection according to the key information of the text to obtain a compliance detection result;
[0039] The information determination module determines customer satisfaction with insurance sales based on the emotional state information and the compliance detection result.
[0040] The present disclosure also provides an electronic device, including:
[0041] processor;
[0042] a memory for storing processor-executable instructions;
[0043] The processor is configured to execute instructions to implement each step in the above method.
[0044] The embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step in the above method is implemented.
[0045] The embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, characterized in that the computer program / instruction implements each step of the above method when executed by a processor.
[0046] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:
[0047] In some embodiments of the present disclosure, video data and audio data of the insurance sales process are obtained; the audio data is converted into text to obtain a transcribed text; and face recognition is performed based on the video data to obtain a face recognition result; when the face recognition result is a passed recognition, key text information is automatically extracted from the transcribed text; sentiment analysis is automatically performed based on the key text information to obtain sentiment state information; and compliance detection is automatically performed based on the key text information to obtain a compliance detection result; customer satisfaction with insurance sales is automatically determined based on the sentiment state information and the compliance detection result; the present disclosure automatically processes insurance information, which reduces labor costs, improves the degree of automation, improves information processing efficiency, and enhances information accuracy compared to manual processing methods.
[0048] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.
[0050] Figure 1 A flowchart of a method for determining insurance information provided by an exemplary embodiment of the present disclosure;
[0051] Figure 2 A schematic diagram of the structure of an insurance information determination device provided for an exemplary embodiment of the present disclosure;
[0052] Figure 3 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION
[0053] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.
[0055] It should be noted that the user information involved in this disclosure includes but is not limited to: user device information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in this disclosure comply with the relevant laws and regulations and do not violate public order and good morals.
[0056] In response to the above technical problems, in some embodiments of the present disclosure, video data and audio data of the insurance sales process are obtained; the audio data is converted into text to obtain a transcribed text; and face recognition is performed based on the video data to obtain a face recognition result; when the face recognition result is a passed recognition, key text information is automatically extracted from the transcribed text; sentiment analysis is automatically performed based on the key text information to obtain sentiment state information; and compliance detection is automatically performed based on the key text information to obtain a compliance detection result; customer satisfaction with insurance sales is automatically determined based on the sentiment state information and the compliance detection result; the present disclosure automatically processes insurance information, which reduces labor costs, improves the degree of automation, improves information processing efficiency, and improves information accuracy compared to manual processing methods.
[0057] The technical solutions provided by various embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings.
[0058] Figure 1 The following is a flow chart of a method for determining insurance information provided by an exemplary embodiment of the present disclosure. Figure 1 As shown, the method includes:
[0059] S101: Acquire video data and audio data during insurance sales;
[0060] S102: Converting the audio data into text to obtain a transcribed text; and
[0061] S103: Perform face recognition according to the video data to obtain a face recognition result;
[0062] S104: When the face recognition result is a pass, extracting key text information from the transcribed text;
[0063] S105: Perform sentiment analysis based on key information of the text to obtain sentiment state information; and
[0064] S106: Perform compliance testing according to the key information of the text to obtain a compliance testing result;
[0065] S107: Determine customer satisfaction with insurance sales based on the emotional state information and compliance test results.
[0066] In this embodiment, the execution subject of the above method may be a terminal device or a server.
[0067] Among them, the terminal device includes but is not limited to a mobile station (MS), a mobile terminal, a mobile phone, a handset and a portable equipment, etc. The terminal device can communicate with one or more core networks via a radio access network (RAN). For example, the terminal device can be a mobile phone (or a "cellular" phone), a computer with a wireless communication function, etc. The terminal device can also be a computer with a wireless transceiver function, a virtual reality (VR) terminal device, an AR terminal device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc., and the operating system installed on the terminal device includes but is not limited to: IOS, Android, windows, linux, Mac OS and other operating systems. In different networks, the terminal may be called different names, such as user equipment, mobile station, subscriber unit, station, cellular phone, personal digital assistant, wireless modem, wireless communication device, handheld device, laptop computer, cordless phone, wireless local loop station, television, etc. For the convenience of description, it is referred to as terminal equipment in this embodiment.
[0068] In this embodiment, the implementation form of the server is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center, or other server devices. The server mainly includes a processor, a hard disk, a memory, a system bus, etc., and a general computer architecture type.
[0069] In order to better illustrate the present disclosure, the terms involved in the present disclosure are explained below.
[0070] Insurance dual recording, which records both audio and video during the insurance sales process, to record the communication process between sales staff and customers. The dual recording system is designed to ensure the transparency of sales practices, protect the rights and interests of customers and sales staff, and meet regulatory requirements.
[0071] Generative artificial intelligence is an AI system that generates text, images, or other media in response to prompts. Rather than simply classifying or predicting data, generative models learn the patterns and structure of input data and then generate new content that is similar to the training data but has a certain degree of novelty.
[0072] Natural Language Processing is a branch of artificial intelligence and linguistics. This field explores how to process and use natural language; natural language processing includes many aspects and steps, basically including cognition, understanding, generation and other parts.
[0073] In this embodiment, video data and audio data of the insurance sales process are obtained; the audio data is converted into text to obtain a transcribed text; and face recognition is performed based on the video data to obtain a face recognition result; when the face recognition result is a pass, key text information is automatically extracted from the transcribed text; sentiment analysis is automatically performed based on the key text information to obtain sentiment state information; and compliance detection is automatically performed based on the key text information to obtain a compliance detection result; customer satisfaction with insurance sales is automatically determined based on the sentiment state information and the compliance detection result; the present invention automatically processes insurance information, which reduces labor costs, improves the degree of automation, improves information processing efficiency, and enhances information accuracy compared to manual processing methods.
[0074] In some embodiments of the present disclosure, a microphone and a recording device are used to collect audio data between a customer and a salesperson, or a recording file is exported from a recording text system to obtain audio data.
[0075] In some embodiments of the present disclosure, a camera is used to record video data for face recognition and identity authentication, or a video file is exported from a video conferencing system to obtain video data.
[0076] In some embodiments of the present disclosure, audio data is converted to text to obtain a transcribed text. One achievable method is to perform a preprocessing operation on the audio data to obtain preprocessed audio data; use automatic speech recognition technology to convert the preprocessed audio data into initial text; input the initial text into an error correction model for text correction to obtain a corrected text; use natural language processing technology to segment the corrected text to obtain a transcribed text. Among them, the present disclosure converts the recording data into text data for subsequent analysis. The preprocessing techniques used include denoising, normalization and speech segmentation. Denoising uses filtering techniques, such as Gaussian filtering or adaptive filtering, to remove background noise in the recording and improve the quality of the speech signal; normalization adjusts the amplitude of the speech signal to a standard range to ensure that recordings of different volumes can be effectively processed; speech segmentation divides long recordings into short segments for subsequent processing and analysis. Use automatic speech recognition technology to convert audio data into initial text. This technology uses an acoustic model, a language model and a decoder to convert the preprocessed speech signal into text. Error correction uses the error correction model in the speech recognition system to correct errors that occur during the recognition process. Punctuation is added by natural language processing technology, which automatically adds punctuation according to the context, making the text more coherent and easier to read; segmentation divides long texts by semantics to facilitate subsequent analysis and processing. The text is stored and further processed according to needs. Storage technology: including saving text data to local storage for subsequent retrieval and use. Text data can also be further used in functional modules such as compliance detection, sentiment analysis and customer satisfaction evaluation.
[0077] In some embodiments of the present disclosure, face recognition and comparison are performed on video data to verify the identity of the customer. Before performing face detection, the video data needs to be preprocessed to improve the accuracy and efficiency of detection. The preprocessing techniques used include image scaling, grayscale and denoising. Image scaling adjusts the size of the video frame to meet the requirements of subsequent processing; grayscale converts color images into grayscale images to reduce computational complexity; denoising uses Gaussian filtering to remove noise in the image, improve image quality, and ensure the accuracy of face detection. Using a deep learning model, through a multi-task learning framework, the location and bounding box of the face are found in each frame of the image. The deep learning model is used to convert the face image into a 128-dimensional feature vector. These feature vectors can efficiently represent the unique features of the face, which is convenient for subsequent comparison. Cosine similarity evaluates the similarity by calculating the angle between two feature vectors. The smaller the angle, the higher the similarity. The feature vector of the face to be verified is compared with the feature vector of the known identity in the face database to be detected, and the degree of matching is determined by calculating the similarity. The comparison result is based on the set similarity threshold. If the similarity is higher than the threshold, the face recognition result is recognized as passed; otherwise, the recognition fails. The face recognition result is recorded and passed to other parts of the system for subsequent compliance testing.
[0078] In some embodiments of the present disclosure, text analysis, sentiment analysis, compliance detection, and customer satisfaction prediction are performed based on the transcribed text. These steps ensure that the system can efficiently and accurately analyze and process data and provide intelligent feedback and improvement suggestions through the combination of generative AI and related technologies. Text analysis extracts key information from the transcribed text for subsequent analysis and processing.
[0079] In some embodiments of the present disclosure, key information of the text is extracted from the transcribed text. One achievable method is to perform a preprocessing operation on the transcribed text to obtain a preprocessed transcribed text; use natural language processing technology to perform word segmentation and part-of-speech tagging on the preprocessed transcribed text to obtain a word segmentation text; perform keyword extraction on the word segmentation text to obtain a keyword text; input the keyword text into a generative semantic model to obtain key information of the text. Among them, the preprocessing operation on the transcribed text includes: data cleaning and normalizing text data. Among them, noise characters, repeated content and irrelevant information are removed to ensure data quality. The preprocessed transcribed text is segmented and part-of-speech tagged using natural language processing technology. Word segmentation divides the text into independent words or phrases, and the tagging process assigns a part-of-speech tag to each word to facilitate subsequent grammatical and semantic analysis. Use an algorithm to extract important keywords from the text and identify the core content of the text. A generative semantic model, such as a generative AI model, performs deep semantic analysis on the keyword text to extract the main meaning and emotional tendency of the text. Semantic analysis can identify entities, events and relationships in the text and provide richer semantic information.
[0080] In some embodiments of the present disclosure, sentiment analysis is performed based on key information of the text to obtain sentiment state information. One achievable method is to input the key information of the text into a sentiment classification model to obtain the sentiment state information. It should be noted that the sentiment state information includes: sentiment classification and sentiment intensity. Among them, sentiment analysis is used to analyze the changes in sentiment in the conversation and identify the emotional state of the customer. Use a sentiment dictionary to perform preliminary sentiment analysis by matching sentiment words. The sentiment dictionary contains a large number of sentiment words and their corresponding sentiment scores, which can quickly identify the sentiment tendency in the text. Use a deep learning model to perform sentiment classification on the text. The model can be trained to identify the sentiment categories in the text, such as positive, negative, neutral, etc. Calculate the sentiment intensity and evaluate the strength of the sentiment based on the frequency of occurrence of sentiment words and contextual relationships. Generate sentiment tags based on the analysis results to mark the sentiment changes in the text. Sentiment tags can be used for subsequent customer satisfaction prediction and service improvement.
[0081] In some embodiments of the present disclosure, customer satisfaction with insurance sales is determined based on emotional state information and compliance test results. One achievable method is to input emotional state information and compliance test results into a satisfaction prediction model to obtain customer satisfaction with insurance sales. Among them, compliance testing is used to detect whether the content of the conversation meets compliance requirements and identify potential risks. Load and preprocess compliance rules, and convert compliance rules into a machine-readable format. Perform natural language processing on the text to parse out key information in the text. NLP technology can identify elements such as entities, actions, and time in the text to facilitate rule matching. Use a rule engine to match the text content with preprocessed compliance rules. The rule engine identifies compliance issues in the text through logical judgment. According to the rule matching results, identify and record potential compliance risks. The risk detection results are used to generate compliance reports and provide improvement suggestions. Customer satisfaction prediction predicts customer satisfaction based on the conversation content and sentiment analysis results.
[0082] Among them, predicting customer satisfaction includes the following steps.
[0083] Data integration: Integrate sentiment analysis and compliance detection results to form a complete data set. The data integration process needs to ensure the consistency and integrity of the data.
[0084] Feature Engineering: Extract and select key features such as sentiment scores, keyword frequency, compliance issues, etc. Feature engineering can improve the prediction accuracy of the model.
[0085] Model training: Use machine learning models (such as regression models and classification models) for training. Train the model with historical data so that it can accurately predict customer satisfaction.
[0086] Satisfaction score: Calculate the customer satisfaction score based on the trained model. The satisfaction score result is used to generate a customer satisfaction report and provide personalized improvement suggestions.
[0087] This disclosure ensures that the system can provide intelligent services and improvement suggestions efficiently and accurately by comprehensively utilizing generative AI and related technologies.
[0088] In some embodiments of the present disclosure, smart tags and indexes are intended to generate smart tags and indexes for transcribed texts to facilitate retrieval and query. Use natural language processing technology to extract important keywords from the text. These keywords reflect the main content and theme of the text. Generative AI is used to generate smart tags based on keywords and semantic information. Smart tags can summarize the content of the text, making the text easier to understand and retrieve. Use indexing tools to create an index of the text. The index can speed up the retrieval of the text and improve the response efficiency of the system. The generated tags and indexes are stored in a database, providing an efficient retrieval function, and users can quickly find relevant content through keywords.
[0089] In some embodiments of the present disclosure, the automatically generated compliance report is used to automatically generate a detailed compliance report based on the compliance test results. Use NLP technology and rule engines to parse and detect compliance issues in the conversation content. The rule engine can automatically identify potential risks in the text. Predefine a template for the compliance report, including the structure and format of the report. The template can be customized according to different compliance requirements. Using generative AI and template generation technology, fill the test results into the report template to automatically generate a detailed compliance report. The report includes a description of the compliance issue, the basis for detection, and suggestions for improvement. The generated compliance report is output and stored, and can be automatically sent to relevant departments for review and processing when necessary.
[0090] In some embodiments of the present disclosure, a sentiment analysis report is used to generate a detailed sentiment analysis report to show the changes in customer sentiment. Use a sentiment analysis model to analyze the changes in sentiment in a conversation. The sentiment analysis results include sentiment categories and sentiment intensity. A template for a predefined sentiment analysis report includes the structure and format of the report. The template can be customized according to different analysis requirements. Based on the sentiment analysis results, a sentiment analysis report is generated using generative AI and template generation technology. The report includes a detailed record and analysis of the changes in sentiment during the conversation. The generated sentiment analysis report is stored and displayed to the user, who can view and analyze the changes in the customer's sentiment.
[0091] In some embodiments of the present disclosure, customer satisfaction improvement suggestions are generated based on customer satisfaction prediction results to generate specific suggestions for improving customer satisfaction. A machine learning model is used to predict customer satisfaction based on the conversation content and sentiment analysis results. The prediction results include customer satisfaction scores and key influencing factors. Generative AI is used to generate personalized improvement suggestions based on satisfaction prediction results and analysis. The suggestions include specific improvement measures and strategies to improve customer satisfaction. A template for predefined customer satisfaction improvement suggestions includes the structure and format of the suggestion report. The template can be customized according to different service requirements. The generated satisfaction improvement suggestion report is stored for actual service improvement and customer management work.
[0092] The present disclosure implements real-time processing of compliance detection, sentiment analysis, and customer satisfaction evaluation, and provides immediate feedback and improvement suggestions. Generative artificial intelligence and real-time analysis technology are used to improve the real-time and response speed of the system, and problems are discovered and solved in a timely manner. Multimodal data analysis is performed using audio, video, and text data to improve data integration and processing capabilities. Generative artificial intelligence and natural language processing technology are used to automatically perform speech transcription, text analysis, and compliance detection, and improve the utilization efficiency of computing resources and human resources. Through automation and intelligent processing, manual operations are reduced and the overall efficiency of the system is improved.
[0093] In the above method embodiment of the present disclosure, video data and audio data in the insurance sales process are obtained; the audio data is converted into text to obtain a transcribed text; and face recognition is performed based on the video data to obtain a face recognition result; when the face recognition result is a pass, key text information is automatically extracted from the transcribed text; sentiment analysis is automatically performed based on the key text information to obtain sentiment state information; and compliance detection is automatically performed based on the key text information to obtain a compliance detection result; customer satisfaction with insurance sales is automatically determined based on the sentiment state information and the compliance detection result; the present disclosure automatically processes insurance information, which reduces labor costs, improves the degree of automation, improves information processing efficiency, and improves information accuracy compared to manual processing methods.
[0094] Figure 2 FIG. 2 is a schematic diagram of the structure of an insurance information determination device 20 provided by an exemplary embodiment of the present disclosure. Figure 2 As shown, the insurance information determination device 20 includes: a data acquisition module 21, a text conversion module 22, an identity recognition module 23, an information extraction module 24, a sentiment analysis module 25, a compliance detection module 26 and an information determination module 27.
[0095] Wherein, the data acquisition module 21 acquires video data and audio data during the insurance sales process;
[0096] The text conversion module 22 converts the audio data into text to obtain a transcribed text;
[0097] The identity recognition module 23 performs face recognition based on the video data to obtain a face recognition result;
[0098] The information extraction module 24 extracts key information from the transcribed text when the face recognition result is a pass;
[0099] Sentiment analysis module 25, performs sentiment analysis based on key information of the text to obtain sentiment state information;
[0100] A compliance detection module 26 performs compliance detection according to the key information of the text and obtains a compliance detection result;
[0101] The information determination module 27 determines the customer satisfaction of insurance sales based on the emotional state information and the compliance detection results.
[0102] Optionally, when converting audio data into text to obtain transcribed text, the text conversion module 22 is used to: preprocess the audio data to obtain preprocessed audio data; convert the preprocessed audio data into initial text using automatic speech recognition technology; input the initial text into an error correction model to perform text correction to obtain corrected text; and segment the corrected text using natural language processing technology to obtain transcribed text.
[0103] Optionally, when extracting key text information from the transcribed text, the information extraction module 24 is used to:
[0104] Performing a preprocessing operation on the transcribed text to obtain a preprocessed transcribed text;
[0105] Use natural language processing technology to perform word segmentation and part-of-speech tagging on the pre-processed transcribed text to obtain the word segmentation text;
[0106] Extract keywords from the segmented text to obtain keyword text;
[0107] Input the keyword text into the generative semantic model to obtain the key information of the text.
[0108] Optionally, when the sentiment analysis module 25 performs sentiment analysis based on the key information of the text to obtain the sentiment state information, it is used to:
[0109] Input the key information of the text into the sentiment classification model to obtain the sentiment state information.
[0110] Optionally, when determining the customer satisfaction of insurance sales according to the emotional state information and the compliance detection result, the information determination module 27 is used to:
[0111] The emotional state information and compliance test results are input into the satisfaction prediction model to obtain the customer satisfaction of insurance sales.
[0112] Optionally, after determining the customer satisfaction of insurance sales according to the emotional state information and the compliance detection result, the information determination module 27 can also be used to:
[0113] Generate sentiment analysis reports based on emotional state information using generative AI models; and
[0114] Generate compliance reports based on compliance test results; and
[0115] Generate customer satisfaction reports based on customer satisfaction.
[0116] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0117] Figure 3 FIG. 1 is a schematic diagram of a structure of an electronic device provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the electronic device includes: a memory 31 and a processor 32. In addition, the electronic device also includes a power supply component 33 and a communication component 34.
[0118] The memory 31 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application program or method operating on the electronic device.
[0119] The memory 31 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0120] The communication component 34 is used for data transmission with other devices.
[0121] The processor 32 can execute computer instructions stored in the memory 31 to: obtain video data and audio data in the insurance sales process; convert the audio data into text to obtain a transcribed text; and perform face recognition based on the video data to obtain a face recognition result; when the face recognition result is a pass, extract text key information from the transcribed text; perform sentiment analysis based on the text key information to obtain sentiment state information; and perform compliance testing based on the text key information to obtain a compliance testing result; determine customer satisfaction with insurance sales based on the sentiment state information and the compliance testing result.
[0122] Accordingly, the present disclosure also provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors execute Figure 1 Each step in the method embodiment.
[0123] Accordingly, the present disclosure also provides a computer program product, the computer program product includes a computer program / instruction, the computer program / instruction is executed by a processor Figure 1 Each step in the method embodiment.
[0124] Above Figure 3 The communication component in is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0125] Above Figure 3 The power supply component in the device provides power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply component is located.
[0126] The electronic device also includes a display screen and an audio component.
[0127] The display screen includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
[0128] The audio component may be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.
[0129] In the embodiments of the above-mentioned apparatus, device, storage medium and computer program product disclosed in the present invention, video data and audio data in the insurance sales process are obtained; the audio data is converted into text to obtain a transcribed text; and face recognition is performed based on the video data to obtain a face recognition result; when the face recognition result is a pass, key text information is automatically extracted from the transcribed text; sentiment analysis is automatically performed based on the key text information to obtain sentiment state information; and compliance detection is automatically performed based on the key text information to obtain a compliance detection result; customer satisfaction with insurance sales is automatically determined based on the sentiment state information and the compliance detection result; the present invention automatically processes insurance information, which reduces labor costs, improves the degree of automation, improves information processing efficiency, and enhances information accuracy compared to manual processing methods.
[0130] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0131] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0134] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0135] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0136] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0137] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0138] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for determining insurance information, characterized in that: include: Acquire video and audio data during the insurance sales process; Convert the audio data into text to obtain a transcribed text; as well as Performing face recognition according to the video data to obtain a face recognition result; When the face recognition result is a pass, extracting key text information from the transcribed text; Perform sentiment analysis based on the key information of the text to obtain sentiment state information; as well as Perform compliance testing based on the key information of the text to obtain a compliance testing result; Customer satisfaction with insurance sales is determined based on the emotional state information and the compliance test results.
2. The method according to claim 1, characterized in that The step of converting the audio data into text to obtain a transcribed text includes: Performing a preprocessing operation on the audio data to obtain preprocessed audio data; Using automatic speech recognition technology, converting the pre-processed audio data into initial text; Inputting the initial text into an error correction model to perform text correction to obtain a corrected text; The corrected text is segmented using natural language processing technology to obtain the transcribed text.
3. The method according to claim 1, characterized in that The step of extracting key text information from the transcribed text includes: Performing a preprocessing operation on the transcribed text to obtain a preprocessed transcribed text; Using natural language processing technology, segmenting and part-of-speech tagging the preprocessed transcribed text to obtain a segmented text; Extracting keywords from the segmented text to obtain a keyword text; The keyword text is input into a generative semantic model to obtain the key information of the text.
4. The method according to claim 1, characterized in that The step of performing sentiment analysis based on the key information of the text to obtain sentiment state information includes: The text key information is input into the sentiment classification model to obtain the sentiment state information.
5. The method according to claim 1, characterized in that Determining customer satisfaction of insurance sales based on the emotional state information and the compliance detection result includes: The emotional state information and the compliance detection result are input into a satisfaction prediction model to obtain customer satisfaction of insurance sales.
6. The method according to claim 1, characterized in that After determining the customer satisfaction of insurance sales according to the emotional state information and the compliance test result, the method further includes: generating a sentiment analysis report based on the sentiment state information using a generative artificial intelligence model; and generating a compliance report based on the compliance test results; and A customer satisfaction report is generated based on the customer satisfaction.
7. An insurance information determination device, characterized in that: include: Data acquisition module, which acquires video data and audio data during the insurance sales process; A text conversion module converts the audio data into text to obtain a transcribed text; An identity recognition module performs face recognition based on the video data to obtain a face recognition result; An information extraction module, when the face recognition result is a pass, extracts key text information from the transcribed text; A sentiment analysis module performs sentiment analysis based on the key information of the text to obtain sentiment state information; A compliance detection module performs compliance detection according to the key information of the text to obtain a compliance detection result; The information determination module determines customer satisfaction with insurance sales based on the emotional state information and the compliance detection result.
8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute instructions to implement each step in the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method according to any one of claims 1 to 6 is implemented.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.
