CN116628137A

CN116628137A - Data analysis method, device, equipment and storage medium based on artificial intelligence

Info

Publication number: CN116628137A
Application number: CN202310699562.9A
Authority: CN
Inventors: 袁美璐
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2023-06-13
Filing date: 2023-06-13
Publication date: 2023-08-22

Abstract

The embodiment of the application belongs to the field of artificial intelligence, and relates to a data analysis method based on artificial intelligence, which comprises the following steps: acquiring voice dialogue data of a user and an agent in a service communication process; converting the voice dialogue data into text data, and converting the text data to obtain dialogue text; classifying the dialogue text according to a preset rule to obtain a theme label corresponding to the dialogue text; constructing a corresponding directed graph based on the dialogue text and the topic label; and carrying out similarity analysis processing on the directed graphs based on a preset similarity analysis model, and generating a similarity result among the directed graphs. The application also provides a data analysis device, computer equipment and a storage medium based on the artificial intelligence. In addition, the present application relates to blockchain techniques in which similar results may be stored. The application analyzes the similarity relation of the topic paths using the conversation based on the similarity analysis model to realize quick and accurate obtaining of the corresponding similarity result.

Description

Data analysis method, device, equipment and storage medium based on artificial intelligence

Technical Field

The present application relates to the field of artificial intelligence development, and in particular, to an artificial intelligence-based data analysis method, apparatus, computer device, and storage medium.

Background

In the field of financial technology, an agent is generally required to perform business communication with a customer to make a business recommendation to the customer. At present, the conversation operation only stays in the topic classification of the conversation data, and the useful information cannot be provided for marketing of the agents according to the topic classification, so that effective assistance cannot be provided for the work of the agents. However, different dialogs often have similar logic, and how to find similar logic between different dialogs and make reasonable use of the similar logic is a technical problem that needs to be solved currently, so that more conditions are created for agent marketing.

Disclosure of Invention

The embodiment of the application aims to provide a data analysis method, a device, computer equipment and a storage medium based on artificial intelligence, which are used for solving the technical problems that the existing dialog operation is utilized and only stays in the topic classification of dialog data, useful information can not be provided for marketing of agents according to the topic classification, similar logic between different dialogs can not be found and reasonably utilized, and more conditions can not be created for the marketing of agents.

In order to solve the above technical problems, the embodiment of the present application provides an artificial intelligence based data analysis method, which adopts the following technical scheme:

acquiring voice dialogue data of a user and an agent in a service communication process;

converting the voice dialogue data into text data, and converting the text data according to a preset information type to obtain a corresponding dialogue text;

classifying the dialogue text according to a preset rule to obtain a theme label corresponding to the dialogue text;

constructing a corresponding directed graph based on the dialogue text and the theme label; wherein the number of directed graphs includes a plurality;

performing similarity analysis processing on the directed graphs based on a preset similarity analysis model to generate a similarity result among the directed graphs; the similarity analysis model consists of a graph convolution network, a tensor neural network and a full-connection layer.

Further, the step of performing a similarity analysis process on the directed graphs based on a preset similarity analysis model to generate a similarity result between the directed graphs specifically includes:

reconstructing the characteristics of each node in each directed graph through a graph convolution network in the similarity analysis model to obtain a corresponding node representation vector;

Coding each directed graph based on a preset attention mechanism to obtain graph feature vectors of each directed graph;

processing the graph feature vectors of each directed graph based on the tensor neural network in the similarity analysis model to obtain similarity vectors among the target directed graphs; the target directed graph is any two of all the directed graphs;

generating a histogram feature of the directed graph based on the node representation vector;

and processing the similarity vector between the target directed graphs and the target histogram features between the target directed graphs based on the full connection layer in the similarity analysis model to obtain a target similarity result between the target directed graphs.

Further, the step of generating the histogram feature of the directed graph based on the node representation vector specifically includes:

performing inner product calculation on the node representation vectors of the directed graph to obtain a corresponding correlation matrix;

and performing conversion processing on the correlation matrix to obtain a histogram feature corresponding to the directed graph.

Further, the step of processing the similarity vector between the target directed graphs and the target histogram feature between the target directed graphs based on the full-connection layer in the similarity analysis model to obtain a target similarity result between the target directed graphs specifically includes:

Performing stitching processing on the similarity vector between the target directed graphs and the target histogram features between the target directed graphs to obtain corresponding stitching features;

inputting the splicing characteristics into a full-connection layer in the similar analysis model, and obtaining an output result of the full-connection output, which corresponds to the target directed graph;

and taking the output result as the target similar result.

Further, the step of classifying the dialogue text according to a preset rule to obtain a theme label corresponding to the dialogue text specifically includes:

processing the dialogue text based on a preset text representation model, and generating text representation data of the dialogue text;

performing feature extraction on the text representation data based on a preset feature extraction model to obtain corresponding feature data;

and taking the characteristic data as the theme tag.

Further, the step of constructing a corresponding directed graph based on the dialog text and the theme label specifically includes:

acquiring a preset target field;

acquiring target data corresponding to the target field from the dialogue text based on the target field;

And constructing the directed graph based on the target data and the theme label.

Further, after the step of performing a similarity analysis process on the directed graphs based on the preset similarity analysis model to generate a similarity result between the directed graphs, the method further includes:

obtaining the similar result;

generating a corresponding dialogue analysis report based on the similar result;

storing the dialogue analysis report.

In order to solve the technical problems, the embodiment of the application also provides a data analysis device based on artificial intelligence, which adopts the following technical scheme:

the first acquisition module is used for acquiring voice dialogue data between a user and an agent in the service communication process;

the conversion module is used for converting the voice dialogue data into text data and converting the text data according to a preset information type to obtain a corresponding dialogue text;

the classification module is used for classifying the dialogue text according to a preset rule to obtain a theme label corresponding to the dialogue text;

the construction module is used for constructing a corresponding directed graph based on the dialogue text and the theme label; wherein the number of directed graphs includes a plurality;

The processing module is used for carrying out similarity analysis processing on the directed graphs based on a preset similarity analysis model to generate a similarity result among the directed graphs; the similarity analysis model consists of a graph convolution network, a tensor neural network and a full-connection layer.

In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:

In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

firstly, loading and acquiring voice dialogue data of a user and an agent in a service communication process; then converting the voice dialogue data into text data, and converting the text data according to a preset information type to obtain a corresponding dialogue text; classifying the dialogue text according to preset rules to obtain a theme label corresponding to the dialogue text; building a corresponding directed graph based on the dialogue text and the theme label; and finally, carrying out similarity analysis processing on the directed graphs based on a preset similarity analysis model, and generating a similarity result among the directed graphs. According to the embodiment of the application, the establishment of the directed graph is completed based on the dialogue text and the topic label of the dialogue text in the business communication process of the user and the seat, and then the similar analysis model is used for carrying out similar analysis processing on the established directed graph, so that a similar result between the directed graphs can be quickly and accurately generated, the generation efficiency of the similar result is improved, and the data accuracy of the similar result is ensured. According to the application, the analysis and research are carried out based on the similarity relation of the topic paths of the similarity analysis model dialogue operation so as to obtain corresponding similarity results, so that the seat end can be helped to find the common dialogue path from the voice dialogue data, and reasonable dialogue operation adjustment can be timely carried out based on the similarity logic of the common dialogue path so as to guide a user to form an optimal purchase path, and the seat work experience is improved.

Drawings

In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of an artificial intelligence based data analysis method in accordance with the present application;

FIG. 3 is a schematic diagram of one embodiment of an artificial intelligence based data analysis device in accordance with the application;

FIG. 4 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.

It should be noted that, the data analysis method based on artificial intelligence provided by the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the data analysis device based on artificial intelligence is generally disposed in the server/terminal device.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of an artificial intelligence based data analysis method in accordance with the present application is shown. The artificial intelligence-based data analysis method comprises the following steps:

Step S201, obtaining voice dialogue data between a user and an agent in the service communication process.

In this embodiment, the electronic device (e.g., the server/terminal device shown in fig. 1) on which the data analysis method based on artificial intelligence operates may acquire the voice dialogue data through a wired connection manner or a wireless connection manner. . It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection. Wherein the dialogue between the customer and the agent involves the jumping of different dialogue topics, which can be represented in the form of a graph by the construction of the topic path. There is often similar logic between these figures, how to find and make reasonable use of these logic, and it is critical to create more conditions for agent marketing. Prior dialog utilization stays only in the topic classification of dialog sentences, and similarity studies on dialog topic paths are not involved. Therefore, the application provides a similarity analysis scheme of the seat theme path based on the similarity analysis model.

Step S202, converting the voice dialogue data into text data, and converting the text data according to a preset information type to obtain a corresponding dialogue text.

In this embodiment, speech may be converted to text data in real-time by employing existing ASR techniques (e.g., the ASR technique of Kogaku fly). The above information types include session ID, agent ID, time stamp, dialogue content, etc., and text data may be converted based on the information types to form formatted data including session ID, agent ID, time stamp, dialogue content.

And step S203, classifying the dialogue text according to a preset rule to obtain a theme label corresponding to the dialogue text.

In this embodiment, the theme tag may specifically include confirming the willingness of quotation, confirming the quotation scheme, broadcasting the quotation and the cashback, broadcasting the value-added service, confirming the application information, introducing the payment process, recommending the credit card, and the like. Wherein a conversation may involve a back and forth jump of different topics, and the resulting topic paths may be inconsistent. There is often some distinction and association between different conversation paths corresponding to different conversation IDs. However, the similarity between them is not mined in the previous studies, so that the development and discussion of the commonality problem is missed, and thus the speaking adjustment of the navigation scene is affected. In addition, the above-mentioned classification processing is performed on the dialog text according to a preset rule, so as to obtain a specific implementation process of the theme label corresponding to the dialog text, which will be described in further detail in the following specific embodiments, which will not be described herein.

Step S204, constructing a corresponding directed graph based on the dialogue text and the theme label; wherein the number of directed graphs includes a plurality.

In this embodiment, the foregoing specific implementation process of constructing the corresponding directed graph based on the dialog text and the theme label will be described in further detail in the following specific embodiment, which is not described herein.

Step S205, carrying out similarity analysis processing on the directed graphs based on a preset similarity analysis model, and generating a similarity result among the directed graphs; the similarity analysis model consists of a graph convolution network, a tensor neural network and a full-connection layer.

In this embodiment, the foregoing specific implementation process of performing the similarity analysis processing on the directed graph based on the preset similarity analysis model to generate the similarity result between the directed graphs will be described in further detail in the following specific embodiments, which will not be described herein. Wherein, the training generation process of the similarity analysis model can comprise the following steps: after the training data set is built, carrying out normalization processing on the training data set, setting parameters of an initial directed graph depth neural network, then training the directed graph depth neural network on the training data set by adopting an Adam optimization algorithm, and iterating optimization model parameters to generate a final similarity analysis model.

Firstly, loading and acquiring voice dialogue data of a user and an agent in a service communication process; then converting the voice dialogue data into text data, and converting the text data according to a preset information type to obtain a corresponding dialogue text; classifying the dialogue text according to preset rules to obtain a theme label corresponding to the dialogue text; building a corresponding directed graph based on the dialogue text and the theme label; and finally, carrying out similarity analysis processing on the directed graphs based on a preset similarity analysis model, and generating a similarity result among the directed graphs. According to the application, the establishment of the directed graph is completed based on the dialogue text and the topic label of the dialogue text in the business communication process of the user and the seat, and then the similar analysis model is used for carrying out similar analysis processing on the established directed graph, so that the rapid and accurate generation of similar results among the directed graphs can be realized, the generation efficiency of the similar results is improved, and the data accuracy of the similar results is ensured. According to the application, the analysis and research are carried out based on the similarity relation of the topic paths of the similarity analysis model dialogue operation so as to obtain corresponding similarity results, so that the seat end can be helped to find the common dialogue path from the voice dialogue data, and reasonable dialogue operation adjustment can be timely carried out based on the similarity logic of the common dialogue path so as to guide a user to form an optimal purchase path, and the seat work experience is improved.

In some alternative implementations, step S205 includes the steps of:

and reconstructing the characteristics of each node in each directed graph through a graph rolling network in the similarity analysis model to obtain a corresponding node representation vector.

In this embodiment, the features of each node in each directed graph may be weighted by using an aggregation function to perform the reconstruction process, and specifically, the following formula may be referred to:wherein u is _n Encode for n nodes->Is a weight matrix>For biasing, N (N) is an adjacency matrix, f ₁ (. Cndot.) is a ReLU activation function.

And carrying out coding processing on each directed graph based on a preset attention mechanism to obtain graph feature vectors of each directed graph.

In this embodiment, the attention mechanism may specifically be an Att attention mechanism. In order to obtain global features, the importance degree of each point in the global can be obtained by using an Att attention mechanism in the graph level coding link, and the following formula can be seen specifically:where h is the graph embedding, which is a weighted sum of point level encodings, u _m Encode m nodes, where W ₂ Is a weight matrix which can be learned, f ₂ (·)The function is activated for sigmoid.

Processing the graph feature vectors of each directed graph based on the tensor neural network in the similarity analysis model to obtain similarity vectors among the target directed graphs; wherein the target directed graph is any two of all the directed graphs.

In this embodiment, feature vectors of the graph are obtained after the graph level encoding, and in order to calculate the similarity between the two vectors, a tensor neural network (Neural Tensor Networks, NTN) may be used to calculate the correlation between each point in the two directed graphs, specifically, the graph h may be calculated by the following formula _i And figure h _j Relationship features between:wherein (1)>Is the weight tensor []For the connection operation, f ₃ (. Cndot.) is the activation function, K is the hyper-parameter.

Histogram features of the directed graph are generated based on the node representation vector.

In this embodiment, the specific implementation process of generating the histogram feature of the directed graph based on the node representation vector will be described in further detail in the following specific embodiment, which will not be described herein.

In this embodiment, the above-mentioned specific implementation process of obtaining the target similarity result between the target directed graphs based on the similarity vector between the target directed graphs and the target histogram feature between the target directed graphs by the fully connected layer in the similarity analysis model will be described in further detail in the following specific embodiments, which will not be described herein.

Firstly, reconstructing the characteristics of each node in each directed graph through a graph convolution network in the similarity analysis model to obtain a corresponding node representation vector; then, coding each directed graph based on a preset attention mechanism to obtain graph feature vectors of each directed graph; then, processing the graph feature vectors of each directed graph based on the tensor neural network in the similarity analysis model to obtain similarity vectors among the target directed graphs; generating a histogram feature of the directed graph based on the node representation vector; and finally, processing the similarity vector between the target directed graphs and the target histogram features between the target directed graphs based on the full connection layer in the similarity analysis model to obtain a target similarity result between the target directed graphs.

In some optional implementations of the present embodiment, the generating the histogram feature of the directed graph based on the node representation vector includes:

and carrying out inner product calculation on the node representation vectors of the directed graph to obtain a corresponding correlation matrix.

In this embodiment, in order to consider the information of the local nodes in the directed graph, an inner product is calculated on the representation vectors of the nodes, so as to obtain a correlation matrix.

The application obtains the corresponding correlation matrix person by carrying out inner product calculation on the node expression vector of the directed graph; and then, carrying out conversion processing on the correlation matrix to obtain a histogram feature corresponding to the directed graph so as to quickly acquire the histogram feature of the directed graph, and being beneficial to processing the similarity vector and the histogram feature of the directed graph based on a full-connection layer in a similarity analysis model so as to quickly and accurately generate a similarity result between the directed graphs. The method and the device for generating the similarity result based on the similarity analysis model perform similarity analysis processing on the directed graphs, can rapidly and accurately generate the similarity result between the directed graphs, improve the generation efficiency of the similarity result, and ensure the data accuracy of the similarity result.

In some optional implementations, the processing, by the full-connection layer in the similarity analysis type, the similarity vector between the target directed graphs and the target histogram feature between the target directed graphs to obtain a target similarity result between the target directed graphs includes the following steps:

And performing splicing processing on the similarity vector between the target directed graphs and the target histogram features between the target directed graphs to obtain corresponding splicing features.

And inputting the splicing characteristics into a full-connection layer in the similar analysis model, and obtaining an output result of the full-connection output, which corresponds to the target directed graph.

And taking the output result as the target similar result.

The method comprises the steps of performing splicing processing on similarity vectors between target directed graphs and target histogram features between the target directed graphs to obtain corresponding spliced features; inputting the splicing characteristics into a full-connection layer in the similar analysis model, and obtaining an output result, corresponding to the target directed graph, of the full-connection output; and taking the output result as the target similar result. The application processes the spliced features generated by the splicing process of the similarity vector and the histogram features of the directed graphs based on the use of the similarity analysis model, can realize the rapid and accurate generation of the similar results among the directed graphs, improves the generation efficiency of the similar results, and ensures the data accuracy of the similar results.

In some alternative implementations, the step S203 includes the steps of:

and processing the dialogue text based on a preset text representation model, and generating text representation data of the dialogue text.

In this embodiment, the text representation model may specifically be a RoBERTa text representation model. After the dialog text is input into the Roberta text representation model, semantic knowledge in the dialog text is fully mined by the Roberta text representation model and corresponding results are generated.

And carrying out feature extraction on the text representation data based on a preset feature extraction model to obtain corresponding feature data.

In this embodiment, the feature extraction model may specifically be an RCNN feature extraction model. The RCNN feature extraction model is an RNN network with a bidirectional circulation structure, context grammar and semantic information of an input text can be obtained based on the RCNN feature extraction model, then the most important features are automatically screened out by matching with the largest pooling CNN network, and finally a theme label corresponding to the input text is output.

And taking the characteristic data as the theme tag.

The method comprises the steps of processing the dialogue text based on a preset text representation model to generate text representation data of the dialogue text; then, carrying out feature extraction on the text representation data based on a preset feature extraction model to obtain corresponding feature data; and taking the characteristic data as the theme tag. The method and the device can realize quick and accurate generation of the topic label corresponding to the dialogue text through the use of the text representation model and the feature extraction model, effectively improve the generation efficiency of the topic label of the dialogue text and ensure the data accuracy of the topic label.

In some alternative implementations of the present embodiment, step S203 includes the steps of:

and acquiring a preset target field.

In this embodiment, the target field specifically includes fields such as a session ID, an agent ID, and a timestamp.

And acquiring target data corresponding to the target field from the dialogue text based on the target field.

In this embodiment, according to the target field, field data matching the target field in the dialog text, that is, the session ID, the agent ID, and the time stamp in the dialog text may be obtained.

In this embodiment, the process of building the directed graph of the dialog text topic may include: firstly, traversing the session ID of each group of sessions in the dialogue text, and making the session ID into a format which can be used by the torch_geometry; then, sequencing the topic label records of each agent according to the time stamp to obtain a dialogue topic sequence file of each agent; then Labelencoder coding is carried out on the dialogue theme sequence file so as to manufacture edge indexes numbered from 0, and the characteristic representation of the corresponding points is the coding of the source node and the next node which respectively generate each point; taking dialogue feedback topics of the agents as research objects, and taking each dialogue feedback topic as a point in the directed graph; determining the relation between each dialogue feedback topic and other dialogue feedback topics according to the upstream and downstream relation of various dialogue feedback topics, and connecting the points with causal relation by vectors; and all points and vectors are formed into a directed graph.

The method comprises the steps of obtaining a preset target field; then, based on the target field, acquiring target data corresponding to the target field from the dialogue text; and constructing the directed graph based on the target data and the theme label. According to the method and the device, the matched target data can be quickly and accurately obtained from the dialogue text through the use of the target field, further, the accurate construction of the directed graph can be completed based on the obtained target data and the theme label, and the constructed directed graph can be processed by using a similarity analysis model, so that a similarity result among all the directed graphs can be automatically and intelligently generated.

In some optional implementations of this embodiment, after step S205, the electronic device may further perform the following steps:

and obtaining the similar result.

And generating a corresponding dialogue analysis report based on the similar result.

In this embodiment, the dialog analysis report may be generated by acquiring a preset analysis report template, and then correspondingly filling the similar result into the analysis report template based on the data filling specification in the report template. The analysis report template is constructed and generated in advance according to actual service requirements.

Storing the dialogue analysis report.

In this embodiment, the storage manner of the dialogue analysis report is not particularly limited, and for example, a database storage manner, a cloud storage manner, a blockchain storage manner, and the like may be adopted.

The application obtains the similar result; then generating a corresponding dialogue analysis report based on the similar result; the dialog analysis report is subsequently stored. According to the application, the dialogue analysis report is generated and stored by utilizing the similar result, so that the follow-up agents can analyze the dialogue analysis report, the agent end can find the common dialogue path from the voice dialogue data, and reasonable dialogue adjustment is performed to guide the user to form the optimal purchase path, and the working experience of the agents can be improved.

It is emphasized that to further guarantee the privacy and security of the similar results, the similar results may also be stored in a blockchain node.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an artificial intelligence-based data analysis apparatus, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.

As shown in fig. 3, the artificial intelligence based data analysis apparatus 300 according to the present embodiment includes: a first acquisition module 301, a conversion module 302, a classification module 303, a construction module 304, and a processing module 305. Wherein:

The first obtaining module 301 is configured to obtain voice dialogue data during a service communication process between a user and an agent;

the conversion module 302 is configured to convert the voice dialogue data into text data, and convert the text data according to a preset information type to obtain a corresponding dialogue text;

the classification module 303 is configured to perform classification processing on the dialog text according to a preset rule, so as to obtain a theme label corresponding to the dialog text;

a construction module 304, configured to construct a corresponding directed graph based on the dialog text and the topic label; wherein the number of directed graphs includes a plurality;

the processing module 305 is configured to perform a similarity analysis process on the directed graphs based on a preset similarity analysis model, and generate a similarity result between the directed graphs; the similarity analysis model consists of a graph convolution network, a tensor neural network and a full-connection layer.

In this embodiment, the operations performed by the modules or units respectively correspond to the steps of the artificial intelligence-based data analysis method in the foregoing embodiment one by one, and are not described herein again.

In some alternative implementations of the present embodiment, the processing module 305 includes:

The first processing submodule is used for reconstructing the characteristics of each node in each directed graph through a graph convolution network in the similarity analysis model to obtain a corresponding node representation vector;

the sub-module is used for carrying out coding processing on each directed graph based on a preset attention mechanism to obtain graph feature vectors of each directed graph;

the second processing sub-module is used for processing the graph feature vectors of the directed graphs based on the tensor neural network in the similarity analysis model to obtain similarity vectors among the target directed graphs; the target directed graph is any two of all the directed graphs;

a first generation sub-module for generating histogram features of the directed graph based on the node representation vector;

and the third processing sub-module is used for processing the similarity vector between the target directed graphs and the target histogram features between the target directed graphs based on the full connection layer in the similarity analysis model to obtain a target similarity result between the target directed graphs.

In some optional implementations of this embodiment, the first generating sub-module includes:

the calculation unit is used for carrying out inner product calculation on the node representation vectors of the directed graph to obtain a corresponding correlation matrix;

and the conversion unit is used for carrying out conversion processing on the correlation matrix to obtain a histogram characteristic corresponding to the directed graph.

In this embodiment, the operations performed by the modules or units respectively correspond to the steps of the data analysis method based on artificial intelligence in the foregoing embodiment one by one, which is not described herein again.

In some optional implementations of this embodiment, the third processing sub-module includes:

the processing unit is used for performing splicing processing on the similarity vector between the target directed graphs and the target histogram features between the target directed graphs to obtain corresponding splicing features;

the acquisition unit is used for inputting the splicing characteristics into the full-connection layer in the similar analysis model and acquiring an output result of the full-connection output corresponding to the target directed graph;

and the determining unit is used for taking the output result as the target similar result.

In some alternative implementations of the present embodiment, the classification module 303 includes:

the second generation sub-module is used for processing the dialogue text based on a preset text representation model and generating text representation data of the dialogue text;

the extraction sub-module is used for carrying out feature extraction on the text representation data based on a preset feature extraction model to obtain corresponding feature data;

and the determining submodule is used for taking the characteristic data as the theme tag.

In some alternative implementations of the present embodiment, the building block 304 includes:

the first acquisition sub-module is used for acquiring a preset target field;

the second acquisition sub-module is used for acquiring target data corresponding to the target field from the dialogue text based on the target field;

and the construction submodule is used for constructing the directed graph based on the target data and the theme label.

In some optional implementations of the present embodiments, the artificial intelligence based data analysis apparatus further includes:

the second acquisition module is used for acquiring the similar result;

the generation module is used for generating a corresponding dialogue analysis report based on the similar result;

and the storage module is used for storing the dialogue analysis report.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of an artificial intelligence-based data analysis method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as executing computer readable instructions of the artificial intelligence based data analysis method.

The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.

in the embodiment of the application, firstly, the voice dialogue data of the user and the seat in the service communication process is loaded and obtained; then converting the voice dialogue data into text data, and converting the text data according to a preset information type to obtain a corresponding dialogue text; classifying the dialogue text according to preset rules to obtain a theme label corresponding to the dialogue text; building a corresponding directed graph based on the dialogue text and the theme label; and finally, carrying out similarity analysis processing on the directed graphs based on a preset similarity analysis model, and generating a similarity result among the directed graphs. According to the embodiment of the application, the establishment of the directed graph is completed based on the dialogue text and the topic label of the dialogue text in the business communication process of the user and the seat, and then the similar analysis model is used for carrying out similar analysis processing on the established directed graph, so that a similar result between the directed graphs can be quickly and accurately generated, the generation efficiency of the similar result is improved, and the data accuracy of the similar result is ensured. According to the application, the analysis and research are carried out based on the similarity relation of the topic paths of the similarity analysis model dialogue operation so as to obtain corresponding similarity results, so that the seat end can be helped to find the common dialogue path from the voice dialogue data, and reasonable dialogue operation adjustment can be timely carried out based on the similarity logic of the common dialogue path so as to guide a user to form an optimal purchase path, and the seat work experience is improved.

The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the artificial intelligence-based data analysis method as described above.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.

It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.

Claims

1. A data analysis method based on artificial intelligence, comprising the steps of:

2. The artificial intelligence based data analysis method according to claim 1, wherein the step of performing a similarity analysis process on the directed graphs based on a preset similarity analysis model to generate a similarity result between the directed graphs specifically comprises:

3. The artificial intelligence based data analysis method of claim 2, wherein the step of generating the histogram feature of the directed graph based on the node representation vector specifically comprises:

4. The artificial intelligence based data analysis method according to claim 2, wherein the step of processing the similarity vector between the target directed graphs and the target histogram feature between the target directed graphs based on the full connection layer in the similarity analysis model to obtain the target similarity result between the target directed graphs specifically comprises:

and taking the output result as the target similar result.

5. The artificial intelligence based data analysis method according to claim 1, wherein the step of classifying the dialog text according to a preset rule to obtain a theme tag corresponding to the dialog text specifically comprises:

and taking the characteristic data as the theme tag.

6. The method for analyzing data based on artificial intelligence according to claim 1, wherein the step of constructing a corresponding directed graph based on the dialog text and the topic label specifically comprises:

acquiring a preset target field;

7. The artificial intelligence based data analysis method according to claim 1, further comprising, after the step of performing a similarity analysis process on the directed graphs based on a preset similarity analysis model to generate a similarity result between the directed graphs:

obtaining the similar result;

storing the dialogue analysis report.

8. An artificial intelligence based data analysis device comprising:

9. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the artificial intelligence based data analysis method of any of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the artificial intelligence based data analysis method of any of claims 1 to 7.