A user voice call system and method based on big data processing

Abstract

The present invention discloses a user voice call system and method based on big data processing, relating to the field of voice interaction technology. The system comprises the following steps: collecting multimodal user data and preprocessing the multimodal user data; extracting features from the preprocessed multimodal user data and fusing them into user feature vectors; constructing a user knowledge graph and services based on the user feature vectors using a feature clustering algorithm, dynamically associating the user knowledge graph and the service graph to generate a comprehensive graph; reasoning the comprehensive graph using a graph neural network, calculating the matching degree between user nodes and service nodes, and generating a personalized call plan; generating a voice call script and synthesizing a voice file based on the personalized call plan, and initiating a call to the user via a voice outbound calling device. The present invention generates a user feature vector through feature extraction and fusion, and dynamically associating it to generate a comprehensive graph, thereby improving the ability to associate user needs with service characteristics.

Description

Technical Field

[0001] The present invention relates to the field of voice interaction technology, and in particular to a user voice calling system and method based on big data processing. Background Art

[0002] With the advancement of information technology and artificial intelligence, voice interaction, as a key method of human-computer interaction, has been widely used in intelligent customer service, voice assistants, and marketing. Voice call technology, through technologies such as speech recognition, natural speech processing, and speech synthesis, enables efficient interaction between humans and machines. In this process, the introduction of big data technology has significantly enhanced the personalization capabilities of voice call systems. By analyzing user voice, behavioral, and business data, it can identify user needs and interests, thereby generating targeted call content and strategies. However, current voice call technology still faces many challenges, such as the monotony of voice content, rigid call strategies, and the inability to respond to dynamic changes in user needs. These challenges result in insufficient call service accuracy and user satisfaction. In particular, existing technologies lack effective processing and analysis methods for multimodal data fusion and user profile construction, resulting in a poor match between user needs and service recommendations.

[0003] Existing voice call technology has shortcomings in the following two aspects: First, when processing multimodal user data (such as voice data, behavioral data, and business data), existing technologies often use a single data analysis method, which cannot fully explore the correlation between multimodal data, resulting in incomplete user portraits and lack of personalization of call content; second, in terms of calculating the matching degree between users and services, existing methods are mostly based on traditional similarity calculations, failing to effectively combine knowledge graphs and deep learning technologies, making it difficult to capture the complex semantic relationship between user needs and business characteristics, resulting in insufficient targeting of call content. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a user voice call method based on big data processing to solve the problems of insufficient multimodal data correlation mining and inaccurate calculation of user and service matching.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a user voice calling method based on big data processing, which includes collecting multimodal user data and preprocessing the multimodal user data; extracting features from the preprocessed multimodal user data and fusing them into user feature vectors; constructing a user knowledge graph and business based on the user feature vectors through a feature clustering algorithm, dynamically associating the user knowledge graph and the business graph to generate a comprehensive graph; reasoning the comprehensive graph through a graph neural network, calculating the matching degree between user nodes and business nodes, and generating a personalized call plan; based on the personalized call plan, generating a voice call script and synthesizing a voice file, and initiating a call to the user through a voice outbound calling device.

[0008] As a preferred solution of the user voice call method based on big data processing described in the present invention, the multimodal user data includes voice data, historical behavior data and business data.

[0009] As a preferred solution of the user voice call method based on big data processing of the present invention, wherein: the multimodal user data is pre-processed, the specific steps are as follows:

[0010] Remove noise from speech data through noise reduction algorithm;

[0011] Use data cleaning to fill missing values and remove duplicate data from historical behavior data;

[0012] Eliminate irrelevant information and standardize the format of business data through data filtering and conversion rules;

[0013] The normalization method is used to standardize the multimodal user data.

[0014] As a preferred solution of the user voice call method based on big data processing of the present invention, wherein: the feature extraction of the pre-processed multimodal user data is performed and fused into a user feature vector, the specific steps are as follows:

[0015] Extract semantic feature vectors from user voice data using BERT;

[0016] Use CNN to extract acoustic feature vectors from speech data;

[0017] Use LSTM to extract behavioral feature vectors from historical behavior data;

[0018] Extract business feature vectors from business data through Word2Vec;

[0019] Use the Attention mechanism to align time series of different feature vectors;

[0020] The geometric interaction of different modal eigenvectors is performed dimension by dimension to capture the high-order nonlinear relationship between the modes. At the same time, the linear superposition of all modal eigenvectors is supplemented and fused into the user eigenvector, which is expressed as:

[0021]

[0022] Among them, F is the user feature vector, F i represents the i-th modal eigenvector, ||F i ||2 represents the L2 norm of the i-th modal feature vector, γ is the weight coefficient controlling the linear superposition part in the final fusion result, α is the hyperparameter for adjusting the nonlinear effect of the modal feature, n represents the total number of modal features, F j represents the eigenvector of the jth mode.

[0023] As a preferred solution of the user voice call method based on big data processing described in the present invention, wherein: the user knowledge graph and business are constructed according to the user feature vector through the feature clustering algorithm, the knowledge graph and the business graph are dynamically associated to generate a comprehensive graph, and the specific steps are as follows:

[0024] Based on the user feature vector F, the Euclidean distance between the user feature vector and the cluster center is calculated using the feature clustering algorithm. The expression is:

[0025]

[0026] Among them, d(F i ,C k ) represents the user feature vector F i and the i-th cluster center C k The Euclidean distance between k represents the user feature vector of the kth cluster center, F i,r represents the value of the i-th user feature vector on the r-th feature dimension, C k,r represents the value of the k-th cluster center on the r-th feature dimension, and m represents the number of dimensions of the user feature vector;

[0027] Based on the Euclidean distance d(F i ,C k ), dynamically assign users to k cluster groups until the cluster centers converge, and finally generate k cluster groups;

[0028] Each user F iAs an independent node, each cluster group is converted into a group node. The user node and the group node are connected through the belonging relationship. The interest tags and behavior patterns in the user feature vector are extracted to generate feature nodes. These nodes are then associated with the user node and the group node through the owning feature relationship to form a structured user knowledge graph.

[0029] Extract entities from business data and generate business nodes;

[0030] Generate business feature nodes according to the business feature vector;

[0031] Connect business nodes with their feature nodes through attributes to establish business relationships, and store business nodes, business feature nodes, and business relationships in a structured manner to form a business knowledge graph;

[0032] Based on user behavior data, the user knowledge graph and the business knowledge graph are semantically associated using user features and business features to generate a comprehensive graph.

[0033] As a preferred solution of the user voice call method based on big data processing described in the present invention, wherein: the graph neural network is used to infer the comprehensive graph, calculate the matching degree between the user node and the service node, and generate a personalized call plan. The specific steps are as follows:

[0034] HetGNN is used to initialize the feature vectors of user nodes and business nodes in the comprehensive graph, and the attention mechanism is used to dynamically aggregate the feature information of neighboring nodes to generate a high-dimensional embedding vector for each node;

[0035] Based on the high-dimensional embedding vector of each node and the semantic features of the path in the comprehensive graph, the matching degree between the user node and the business node is calculated. The expression is:

[0036]

[0037] Among them, S(u,e) represents the matching degree between user node u and service node e, H u [i] represents the value of the embedding vector of user node u in the xth dimension, H e [x] represents the value of the embedding vector of the business node e in the xth dimension, H u represents the normalized norm of user node u, H e represents the normalized norm of the business node e, d represents the dimension of the embedding vector, and x is the index variable of the dimension;

[0038] Define the correlation threshold T based on historical data;

[0039] When S(u,e)≥T, the current user u is considered to be highly relevant to the current service e, and the call content focuses on content related to the current service;

[0040] When S(u,e)<T, it is considered that the current user u has a low correlation with the current service e, and the general voice call solution is adopted.

[0041] As a preferred solution of the user voice call method based on big data processing of the present invention, wherein: based on the personalized call solution, a voice call script is generated and a voice file is synthesized, and a call is initiated to the user through a voice outbound calling device. The specific steps are as follows:

[0042] Generate a voice call script based on the personalized call plan, including opening remarks, key business content, interactive guidance, and closing remarks;

[0043] The voice script is converted into a voice file through the TTS engine, and the speaking speed, intonation, and timbre are adjusted based on the interest tags in the user's feature vector. An outbound call device is used to initiate a call to the user.

[0044] In the second aspect, the present invention provides a user voice call system based on big data processing, including a data acquisition module, a feature fusion module, a graph construction module, a call plan generation module and a voice call module; the data acquisition module is used to collect multimodal user data and preprocess the multimodal user data; the feature fusion module is used to extract features from the preprocessed multimodal user data and fuse them into user feature vectors; the graph construction module is used to construct a user knowledge graph and business according to the user feature vector through a feature clustering algorithm, dynamically associate the user knowledge graph and the business graph, and generate a comprehensive graph; the plan generation module is used to infer the comprehensive graph through a graph neural network, calculate the matching degree between user nodes and business nodes, and generate a personalized call plan; the voice call module is used to generate a voice call script and synthesize a voice file based on the personalized call plan, and initiate a call to the user through a voice outbound call device.

[0045] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the user voice call method based on big data processing as described in the first aspect of the present invention is implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the user voice call method based on big data processing as described in the first aspect of the present invention.

[0047] The beneficial effects of the present invention are: by collecting and preprocessing multimodal user data, the high quality of data input is ensured; by generating user feature vectors through feature extraction and fusion, the correlation of multimodal data is fully explored; by utilizing feature clustering to construct user knowledge graphs and business graphs, and dynamically associating to generate comprehensive graphs, the ability to associate user needs with business features is improved; by reasoning on the comprehensive graph through graph neural networks, the matching degree between users and businesses is accurately calculated, and personalized call plans are generated; based on the plan, voice scripts are generated and voice files are synthesized, which are efficiently reached through outbound call equipment, solving the problems of insufficient personalization of call content and inaccurate matching, and improving the accuracy of voice call services and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a flowchart of the user voice call method based on big data processing in Example 1.

[0050] Figure 2 Schematic diagram of the user voice call system based on big data processing in Example 1. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0054] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a user voice call method based on big data processing, comprising the following steps:

[0055] S1: Collect multimodal user data and preprocess the multimodal user data.

[0056] S1.1: Multimodal user data includes voice data, historical behavior data, and business data.

[0057] The purpose of collecting voice data, historical behavior data and business data is to comprehensively obtain multi-dimensional information about users, laying a data foundation for subsequent feature extraction, user portrait construction and personalized solution generation.

[0058] S1.2: Remove noise from speech data using a noise reduction algorithm;

[0059] For example, noisy background sounds (such as wind or traffic noise) in user call recordings are filtered out, retaining only clear voice content to facilitate subsequent semantic feature extraction.

[0060] S1.3: Use data cleaning to fill missing values and remove duplicate data in historical behavior data;

[0061] For example, missing transaction date information is filled in user purchase records, and duplicate records of the same product are removed to ensure data integrity and accuracy.

[0062] S1.4: Eliminate irrelevant information and standardize the format of business data through data filtering and conversion rules;

[0063] For example, remove operation records that are not related to the user from the business log, and convert the amount field into a standard two-decimal format to facilitate subsequent calculations.

[0064] S1.5: Use normalization methods to standardize multimodal user data.

[0065] For example, the user age value (such as 18-60) and consumption amount (such as 100-10,000 yuan) are normalized to the interval [0,1] to eliminate the dimensional differences between features and facilitate model processing.

[0066] S2: Extract features from the preprocessed multimodal user data and fuse them into user feature vectors.

[0067] S2.1: Extract semantic feature vectors from user speech data using BERT;

[0068] Specifically, the BERT model is used to perform semantic analysis on user voice data, converting the voice content into a high-dimensional semantic feature vector to represent user intention and semantic information.

[0069] S2.2: Extract acoustic feature vectors from speech data using CNN;

[0070] Specifically, the speech data is converted into a time-frequency domain representation, such as a spectrogram or Mel-frequency cepstral coefficients (MFCC), as the input of the CNN; then, the convolution layer is used to extract features of the local area of the input data to identify key acoustic patterns in the speech signal (such as pitch, timbre, frequency changes, etc.); then, the pooling layer is used to reduce the dimensionality of the convolution features, retaining important information while reducing redundancy and computational complexity; finally, high-level acoustic features are further extracted through multi-layer convolution and pooling operations, and finally a high-dimensional acoustic feature vector is output to characterize the sound characteristics of the speech data, providing support for subsequent user profiling and voice interaction.

[0071] S2.3: Use LSTM to extract behavioral feature vectors from historical behavioral data;

[0072] Specifically, the process of using LSTM to extract behavioral feature vectors from historical behavioral data is as follows: the user's historical behavioral data is input into the LSTM model in chronological order, and its memory and forgetting mechanisms are used to capture the temporal dependency and dynamic changes of the behavior, and finally a high-dimensional feature vector is output to comprehensively characterize the user's behavioral characteristics.

[0073] S2.4: Extract business feature vectors from business data using Word2Vec;

[0074] Specifically, the process of extracting business feature vectors from business data through Word2Vec is: input business-related text data (such as product descriptions or service tags) into the Word2Vec model, learn the semantic associations of vocabulary through training, and convert business keywords into low-dimensional dense feature vectors to represent the semantic relationships and characteristics between businesses.

[0075] S2.5: Use the Attention mechanism to align time series of different feature vectors;

[0076] Specifically, the process of using the Attention mechanism to align different feature vectors in time series is as follows: by calculating the importance weight of each feature vector in the time series, dynamically focusing on key features, adjusting the temporal order relationship between modalities, and achieving alignment and fusion of different feature vectors, providing consistency and accuracy support for subsequent analysis.

[0077] S2.6: Perform geometric interaction on different modal eigenvectors dimension by dimension to capture the high-order nonlinear relationship between modes. At the same time, linear superposition of all modal eigenvectors is supplemented and fused into the user eigenvector, which is expressed as:

[0078]

[0079] Among them, F is the user feature vector, F irepresents the i-th modal eigenvector, ||F i ||2 represents the L2 norm of the i-th modal feature vector, γ is the weight coefficient controlling the linear superposition part in the final fusion result, α is the hyperparameter for adjusting the nonlinear effect of the modal feature, n represents the total number of modal features, F j represents the eigenvector of the jth mode.

[0080] F i and F j Represent the eigenvectors of the i-th and j-th modes respectively. The difference between them is: F i It is the feature vector under a specific mode, representing the features generated after feature extraction of the i-th mode (such as voice, behavior or business data); and F j is the eigenvector of another mode, representing the characteristics of the jth mode. The geometric interaction in the formula (such as the product operation) realizes the information fusion between the eigenvectors of different modes, and calculates F dimension by dimension. i and F j The relationship between the modalities captures the high-order nonlinear relationship between the modalities, thereby integrating the characteristics of different modalities to form the final user feature vector F.

[0081] S3: Through the feature clustering algorithm, the user knowledge graph and business are constructed according to the user feature vector, and the user knowledge graph and business graph are dynamically associated to generate a comprehensive graph.

[0082] S3.1: Based on the user feature vector F, the Euclidean distance between the user feature vector and the cluster center is calculated using the feature clustering algorithm. The expression is:

[0083]

[0084] Among them, d(F i ,C k ) represents the user feature vector F i and the i-th cluster center C k The Euclidean distance between k represents the user feature vector of the kth cluster center, F i,r represents the value of the i-th user feature vector on the r-th feature dimension, C k,r represents the value of the k-th cluster center on the r-th feature dimension, and m represents the number of dimensions of the user feature vector;

[0085] It should be noted that the user feature vector F is calculated by the feature clustering algorithm i and cluster center C kThe Euclidean distance between user characteristics and different cluster centers can quantify the similarity between user characteristics and dynamic user groups, thereby dynamically dividing users into the most suitable cluster groups. This process improves the accuracy and reliability of user grouping by accurately capturing the differences and similarities between user characteristics and group characteristics, providing a clear structured foundation for the subsequent construction of user knowledge graphs, and ultimately achieving more accurate user demand analysis and personalized matching results.

[0086] S3.2: Based on the Euclidean distance d(F between the user feature vector and the cluster center i ,C k ), dynamically assign users to k cluster groups until the cluster centers converge, and finally generate k cluster groups;

[0087] It should be noted that by dynamically assigning users to k clusters based on the Euclidean distance between their feature vectors and cluster centers until the cluster centers converge, users can be efficiently and adaptively clustered. This process effectively integrates the characteristic information of similar users, revealing similarities within groups and differences between groups, providing a structured foundation for the refined construction of user profiles. Ultimately, this dynamic clustering method improves the accuracy of user demand classification and the hierarchical nature of knowledge graph construction, providing reliable support for personalized services and recommendations.

[0088] S3.3: For each user F i As an independent node, each cluster group is converted into a group node. The user node and the group node are connected through the belonging relationship. The interest tags and behavior patterns in the user feature vector are extracted to generate feature nodes. These nodes are then associated with the user node and the group node through the owning feature relationship to form a structured user knowledge graph.

[0089] Furthermore, based on the construction of a structured user knowledge graph, the interest tags and behavioral patterns in user feature vectors are utilized to connect user nodes, group nodes, and feature nodes through associations, forming a multi-layered graph structure. This graph not only intuitively represents the subordinate relationships between individual users and groups, but also demonstrates the deep correlation between user characteristics and behavioral patterns, providing rich semantic information for user needs analysis. Ultimately, this structured graph lays the foundation for precise recommendations, user behavior prediction, and personalized services.

[0090] S3.4: Extract entities from business data and generate business nodes;

[0091] Specifically, business data (such as product descriptions, service information, etc.) is parsed through natural speech processing technology, key entities (such as product names, service types, attributes, etc.) are identified, and these entities are converted into business nodes as the basic units of the business knowledge graph, providing structured data support for subsequent business feature modeling and user matching.

[0092] S3.5: Generate a business feature node based on the business feature vector;

[0093] Specifically, by quantizing key entities extracted from business data (such as product attributes and service types), a low-dimensional vector space representation of business features is generated using feature extraction methods (such as Word2Vec or other embedding models). These business feature vectors are then converted into business feature nodes, which are then connected to corresponding business nodes through attribute relationships to construct a feature layer structure within the business knowledge graph, providing accurate feature support for the refined representation of business content and user matching.

[0094] S3.6: Connect the business nodes and their feature nodes through attributes to establish business relationships. Structured storage of business nodes, business feature nodes, and business relationships forms a business knowledge graph.

[0095] It should be noted that key attributes are extracted based on the characteristics of business nodes (such as product category and service type), and these attributes are associated with corresponding business feature nodes to establish attribute relationships between nodes. Then, business nodes, business feature nodes, and the relationships between them are stored in a structured form, forming a business knowledge graph with clear relationships and a clear hierarchy. This graph can comprehensively describe business entities and their characteristic attributes, providing efficient support for business analysis, association mining, and user matching.

[0096] S3.7: Based on user behavior data, the user knowledge graph and the business knowledge graph are semantically associated using user features and business features to generate a comprehensive graph.

[0097] It should be noted that by analyzing user behavior data (such as browsing, purchase, or review records), the association between user feature vectors and business feature vectors is extracted. Combined with semantic similarity calculations, connections are established between user nodes and business nodes. Subsequently, user nodes, business nodes, and their feature nodes are connected through interactive relationships to generate a comprehensive graph that integrates user interests and business characteristics. This fully reflects the relationship between users and businesses, providing support for precise recommendations and personalized services.

[0098] S4: Use graph neural networks to infer the comprehensive graph, calculate the matching degree between user nodes and business nodes, and generate personalized call plans.

[0099] S4.1: Use HetGNN to initialize the feature vectors of user nodes and business nodes in the comprehensive graph, and use the attention mechanism to dynamically aggregate the feature information of neighboring nodes to generate a high-dimensional embedding vector for each node;

[0100] Furthermore, the initial feature vectors of user nodes and business nodes are encoded through the HetGNN model, and the basic representation is completed using the structural information and node features in the graph. Then, the neighboring nodes of each node are dynamically aggregated based on the attention mechanism, and different weights are assigned to different neighboring nodes to highlight the influence of key nodes. Finally, a high-dimensional embedding vector is generated for each node by combining the feature information of the neighboring nodes and its own features, which accurately represents the semantic relationship and structural information of the node in the comprehensive graph, providing support for further analysis and matching.

[0101] S4.2: Based on the high-dimensional embedding vector of each node and the semantic features of the path in the comprehensive graph, the matching degree between the user node and the business node is calculated. The expression is:

[0102]

[0103] Among them, S(u,e) represents the matching degree between user node u and service node e, H u [i] represents the value of the embedding vector of user node u in the xth dimension, H e [x] represents the value of the embedding vector of the business node e in the xth dimension, H u represents the normalized norm of user node u, H e represents the normalized norm of the business node e, d represents the dimension of the embedding vector, and x is the index variable of the dimension;

[0104] It should be noted that by calculating the matching degree S(u,e) between user nodes and service nodes, we can quantify the correlation between user needs and service characteristics based on the high-dimensional embedding vectors of the nodes and the semantic features in the comprehensive graph. This method, combined with dimension-by-dimensional nonlinear transformations and normalization of the embedding vectors, comprehensively captures the complex semantic and structural relationships between users and services, avoiding the limitations of single-feature matching. Ultimately, this matching degree calculation method significantly improves the accuracy of user needs and service recommendations, providing greater efficiency and reliability for personalized services and intelligent recommendations.

[0105] S4.3: Define the relevance threshold T based on historical data;

[0106] When S(u,e)≥T, the current user u is considered to be highly relevant to the current service e, and the call content focuses on content related to the current service;

[0107] For example, if calculation shows that a user's matching degree for the "new smartphone" service is higher than a threshold value T, the call will focus on introducing the relevant discounts and functional highlights of the smartphone.

[0108] When S(u,e)<T, it is considered that the current user u has a low correlation with the current service e, and the general voice call solution is adopted.

[0109] For example, if it is detected that a user's matching degree for the "financial services" business is lower than the threshold T, a general voice call solution is adopted, which only provides general greetings and basic business introductions.

[0110] S5: Based on the personalized call plan, generate a voice call script and synthesize a voice file, and initiate a call to the user through the voice outbound calling device.

[0111] S5.1: Generate a voice call script based on the personalized call plan, including opening remarks, key business content, interactive guidance, and closing remarks;

[0112] It should be noted that a friendly opening should be used to attract the user's attention; then, based on the compatibility between the user and the business, the business content related to the user's needs should be introduced in detail; then, interactive guidance should be designed to encourage the user to respond or ask questions; finally, a polite closing statement should be used to ensure that the call process is smooth and attractive, thereby improving the user experience and communication effect.

[0113] S5.2: The voice script is converted into a voice file using the TTS engine. The speech speed, intonation, and timbre are adjusted based on the interest tags in the user's feature vector. An outbound call is then initiated to the user using an outbound calling device.

[0114] It should be noted that the generated voice script is converted into a natural and fluent voice file using a TTS (text-to-speech) engine. The speech rate, intonation, and timbre are adjusted based on the interest tags in the user's feature vector to better align the voice style with user preferences and enhance the personalized call experience. Finally, a voice call is initiated to the user via an outbound calling device, ensuring accurate communication and improving user acceptance of the service.

[0115] This embodiment also provides a user voice call system based on big data processing, including: a data acquisition module, a feature fusion module, a graph construction module, a call plan generation module and a voice call module; the data acquisition module is used to collect multimodal user data and preprocess the multimodal user data; the feature fusion module is used to extract features from the preprocessed multimodal user data and fuse them into user feature vectors; the graph construction module is used to construct a user knowledge graph and business based on the user feature vector through a feature clustering algorithm, dynamically associate the user knowledge graph and the business graph, and generate a comprehensive graph; the plan generation module is used to infer the comprehensive graph through a graph neural network, calculate the matching degree between user nodes and business nodes, and generate a personalized call plan; the voice call module is used to generate a voice call script and synthesize a voice file based on the personalized call plan, and initiate a call to the user through a voice outbound call device.

[0116] This embodiment also provides a computer device, which is suitable for the user voice call method based on big data processing, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the user voice call method based on big data processing proposed in the above embodiment.

[0117] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0118] This embodiment also provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for implementing a user voice call based on big data processing as proposed in the above embodiment is implemented. The storage medium 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.

[0119] In summary, the present invention achieves this by: collecting and preprocessing multimodal user data to ensure high quality of data input; generating user feature vectors through feature extraction and fusion to fully explore the correlation between multimodal data; utilizing feature clustering to construct user knowledge graphs and business graphs, and dynamically associating them to generate comprehensive graphs, thereby improving the ability to associate user needs with business features; inferring the comprehensive graph through graph neural networks to accurately calculate the matching degree between users and businesses and generate personalized call plans; generating voice scripts and synthesizing voice files based on the plan, which are efficiently reached through outbound call equipment, thereby solving the problems of insufficient personalization of call content and inaccurate matching, and improving the accuracy of voice call services and user experience.

[0120] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a user voice call method based on big data processing is provided.

[0121] To verify the effectiveness of this method for user voice calling based on big data processing and to compare the shortcomings of existing voice calling systems, we designed an experimental scenario to simulate actual business application processes. This experiment collected multimodal data from five users, including their voice data, historical behavior data, and business interaction data. The experimental process was divided into the following steps:

[0122] First, the experiment collected multimodal user data, including voice data, historical behavior data, and business data, through voice acquisition devices, user behavior logs, and business interaction records. This data was then preprocessed. This preprocessing step included noise reduction for voice data, missing value filling and duplicate data cleaning for historical behavior data, and format standardization and removal of irrelevant information for business data. Finally, normalization was used to unify the multimodal data into the same feature space.

[0123] Next, feature extraction and fusion are performed on the preprocessed multimodal data. BERT is used to extract speech semantic feature vectors, CNN to extract acoustic feature vectors, LSTM to extract historical behavior feature vectors, and Word2Vec to extract business feature vectors. The multimodal features are then aligned in time series using the Attention mechanism. Subsequently, geometric interaction and linear superposition methods are used to fuse these modal features into a user feature vector that comprehensively represents user interests and needs.

[0124] Take user A as an example:

[0125] The parameters involved in the expression and their values are shown in Table 1:

[0126] Table 1

[0127] Parameter name symbol Numerical Phonetic and semantic matching <![CDATA[F 1. ]]> 0.78 Behavioral characteristic matching <![CDATA[F 2. ]]> 0.74 Business feature matching <![CDATA[F 3. ]]> 0.83 Nonlinear weights α 1 Linear stacking weights γ 0.5 Number of modal features n 3

[0128]

[0129] The calculation results of user AE are shown in Table 2:

[0130] Table 2

[0131] user User feature vector F User A 1.435 User B 1.012 User C 1.574 User D 0.921 User E 1.429

[0132] Next, based on user and business feature vectors, a feature clustering algorithm is used to construct user and business knowledge graphs, and a comprehensive graph is generated using semantic associations. Embedding vectors for user and business nodes in the comprehensive graph are initialized using HetGNN. The attention mechanism is then used to dynamically aggregate feature information from neighboring nodes to generate a high-dimensional embedding vector. A matching formula is used to calculate the matching degree between user and business nodes, and a threshold T is set to distinguish between highly and low-relevance users.

[0133] Take user A as an example:

[0134] The parameters involved in the expression and their values are shown in Table 3:

[0135] Table 3

[0136] symbol describe value Hu[1] User A's voice matching degree 0.78 Hu[2] User A's behavioral characteristics matching degree 0.74 Hu[3] User A's business feature matching degree 0.83 He[1] Voice feature matching degree of service nodes 0.75 He[2] Behavioral feature matching degree of business nodes 0.65 He[3] Business feature matching degree of business nodes 0.80

[0137]

[0138] The calculation results of the comprehensive matching degree S(u,e) are shown in Table 4:

[0139] Table 4

[0140]

[0141]

[0142] Finally, a personalized or universal call plan is generated based on the matching results. For users with a matching score above the threshold, a personalized call script is generated, including an opening statement, key business points, interaction guidance, and a closing statement. For users with a matching score below the threshold, a universal call script is generated. Finally, a TTS engine is used to convert the script into a voice file, dynamically adjusting the speaking speed, intonation, and timbre. The call is then completed through an outbound calling device, validating the significant advantages of this method in user matching and call accuracy.

[0143] The details are shown in Table 5 below:

[0144] Table 5

[0145]

[0146] Analysis of the data in the table above demonstrates that this method integrates speech semantics, behavioral characteristics, and service features to accurately calculate the comprehensive match between users and services (S(u,e)). Based on this match, personalized or universal call plans are dynamically generated. For example, user C's comprehensive match is 0.84, so a personalized plan is generated to precisely meet their needs. User D, with a match of 0.55, uses a universal plan to optimize resource allocation. This method significantly improves call efficiency, user satisfaction, and resource utilization, demonstrating the innovative and practical value of the technology.

[0147] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A user voice calling method based on big data processing, characterized by: include, Collect multimodal user data and preprocess the multimodal user data; Extract features from the pre-processed multimodal user data and fuse them into user feature vectors; Through the feature clustering algorithm, the user knowledge graph and business are constructed according to the user feature vector, and the user knowledge graph and business graph are dynamically associated to generate a comprehensive graph; The graph neural network is used to infer the comprehensive graph, calculate the matching degree between user nodes and business nodes, and generate personalized call plans; Based on the personalized call plan, generate a voice call script and synthesize a voice file, and initiate a call to the user through the voice outbound calling device; The steps of extracting features from the pre-processed multimodal user data and fusing them into user feature vectors are as follows: Extract semantic feature vectors from user voice data using BERT; Use CNN to extract acoustic feature vectors from speech data; Use LSTM to extract behavioral feature vectors from historical behavior data; Extract business feature vectors from business data through Word2Vec; Use the Attention mechanism to align time series of different feature vectors; The geometric interaction of different modal eigenvectors is performed dimension by dimension to capture the high-order nonlinear relationship between the modes. At the same time, the linear superposition of all modal eigenvectors is supplemented and fused into the user eigenvector, which is expressed as: Among them, F is the user feature vector, F i represents the i-th modal eigenvector, ||F i ||2 represents the L2 norm of the i-th modal feature vector, γ is the weight coefficient controlling the linear superposition part in the final fusion result, α is the hyperparameter for adjusting the nonlinear effect of the modal feature, n represents the total number of modal features, F j represents the eigenvector of the jth mode.

2. The user voice call method based on big data processing according to claim 1, characterized in that: The multimodal user data includes voice data, historical behavior data and service data.

3. The user voice call method based on big data processing according to claim 2, characterized in that: The specific steps of preprocessing multimodal user data are as follows: Remove noise from speech data through noise reduction algorithm; Use data cleaning to fill missing values and remove duplicate data from historical behavior data; Eliminate irrelevant information and standardize the format of business data through data filtering and conversion rules; The normalization method is used to standardize the multimodal user data.

4. The user voice calling method based on big data processing according to claim 3, characterized in that: The feature clustering algorithm is used to construct user knowledge graphs and services based on user feature vectors, and the knowledge graphs and business graphs are dynamically associated to generate a comprehensive graph. The specific steps are as follows: Based on the user feature vector F, the Euclidean distance between the user feature vector and the cluster center is calculated using the feature clustering algorithm. The expression is: Among them, d(F i ,C k ) represents the user feature vector F and the i-th cluster center C k The Euclidean distance between k represents the user feature vector of the kth cluster center, F i,r represents the value of the i-th user feature vector on the r-th feature dimension, C k,r represents the value of the k-th cluster center on the r-th feature dimension, and m represents the number of dimensions of the user feature vector; Based on the Euclidean distance d(F i ,C k ), dynamically assign users to k cluster groups until the cluster centers converge, and finally generate k cluster groups; Each user F i As an independent node, each cluster group is converted into a group node. The user node and the group node are connected through the belonging relationship. The interest tags and behavior patterns in the user feature vector are extracted to generate feature nodes. These nodes are then associated with the user node and the group node through the owning feature relationship to form a structured user knowledge graph. Extract entities from business data and generate business nodes; Generate business feature nodes according to the business feature vector; Connect business nodes with their feature nodes through attributes to establish business relationships, and store business nodes, business feature nodes, and business relationships in a structured manner to form a business knowledge graph; Based on user behavior data, the user knowledge graph and the business knowledge graph are semantically associated using user features and business features to generate a comprehensive graph.

5. The user voice calling method based on big data processing according to claim 4, characterized in that: The graph neural network is used to reason about the comprehensive graph, calculate the matching degree between the user node and the service node, and generate a personalized call plan. The specific steps are as follows: HetGNN is used to initialize the feature vectors of user nodes and business nodes in the comprehensive graph, and the attention mechanism is used to dynamically aggregate the feature information of neighboring nodes to generate a high-dimensional embedding vector for each node; Based on the high-dimensional embedding vector of each node and the semantic features of the path in the comprehensive graph, the matching degree between the user node and the business node is calculated. The expression is: Among them, S(u,e) represents the matching degree between user node u and service node e, H u [i] represents the value of the embedding vector of user node u in the xth dimension, H e [x] represents the value of the embedding vector of the business node e in the xth dimension, H u represents the normalized norm of user node u, H e represents the normalized norm of the business node e, d represents the dimension of the embedding vector, and x is the index variable of the dimension; Define the correlation threshold T based on historical data; When S(u,e)≥T, the current user u is considered to be highly relevant to the current service e, and the call content focuses on content related to the current service; When S(u,e)<T, it is considered that the current user u has a low correlation with the current service e, and the general voice call solution is adopted.

6. The user voice calling method based on big data processing according to claim 5, characterized in that: Based on the personalized call plan, the voice call script is generated and the voice file is synthesized, and a call is initiated to the user through the voice outbound calling device. The specific steps are as follows: Generate a voice call script based on the personalized call plan, including opening remarks, key business content, interactive guidance, and closing remarks; The voice script is converted into a voice file through the TTS engine, and the speaking speed, intonation, and timbre are adjusted based on the interest tags in the user's feature vector. An outbound call device is used to initiate a call to the user.

7. A user voice call system based on big data processing, based on the user voice call method based on big data processing according to any one of claims 1 to 6, characterized in that: Including data acquisition module, feature fusion module, graph construction module, call plan generation module and voice call module; A data acquisition module is used to collect multimodal user data and pre-process the multimodal user data; The feature fusion module is used to extract features from the pre-processed multimodal user data and fuse them into user feature vectors; The graph construction module is used to construct user knowledge graphs and business graphs based on user feature vectors through feature clustering algorithms, dynamically associate user knowledge graphs and business graphs, and generate a comprehensive graph; The plan generation module is used to reason about the comprehensive graph through a graph neural network, calculate the matching degree between user nodes and service nodes, and generate a personalized call plan; The voice call module is used to generate a voice call script and synthesize a voice file based on a personalized call plan, and initiate a call to the user through a voice outbound calling device.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the user voice call method based on big data processing according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the user voice call method based on big data processing according to any one of claims 1 to 6 are implemented.

Images