CN114398903A - Intention recognition method and device, electronic equipment and storage medium - Google Patents

Intention recognition method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114398903A
CN114398903A CN202210074053.2A CN202210074053A CN114398903A CN 114398903 A CN114398903 A CN 114398903A CN 202210074053 A CN202210074053 A CN 202210074053A CN 114398903 A CN114398903 A CN 114398903A
Authority
CN
China
Prior art keywords
intention
data
node
target
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210074053.2A
Other languages
Chinese (zh)
Other versions
CN114398903B (en
Inventor
李平
马骏
王少军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN202210074053.2A priority Critical patent/CN114398903B/en
Publication of CN114398903A publication Critical patent/CN114398903A/en
Application granted granted Critical
Publication of CN114398903B publication Critical patent/CN114398903B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Machine Translation (AREA)

Abstract

The application provides an intention identification method, an intention identification device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring intention data to be identified; traversing the flow nodes of the outbound robot system to obtain node information; extracting original intention data and node attribute data of the node information, wherein the original intention data comprises an original intention field; performing data supplementation on the same original intention field according to the node attribute data to obtain first node data; performing semantic analysis on the first node data according to the intention category label to obtain a target intention characteristic; fine-tuning the first node data according to the target intention characteristics to obtain second node data; performing intention prediction processing on the data of the intention to be recognized through a preset target intention prediction model to obtain predicted intention data; and performing intention identification through an intention intersection algorithm, the prediction intention data and the second node data to obtain target intention data. The intention recognition efficiency can be improved.

Description

Intention recognition method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an intention recognition method and apparatus, an electronic device, and a storage medium.
Background
At present, in the process of identifying intentions, each problem of a predetermined flow is often required to correspond to a flow node, a plurality of predefined intention data are set at each flow node, and different intention data at each flow node are usually required to be identified by a separate intention identification model; therefore, when identifying intention data of a plurality of process nodes, it is necessary to train a plurality of corresponding intention identification models to identify consciousness data, and the identification efficiency is low. Therefore, how to provide a scheme capable of improving the intention recognition efficiency is a technical problem to be solved urgently.
Disclosure of Invention
The embodiments of the present application mainly aim to provide an intention identification method, an intention identification device, an electronic device, and a storage medium, which aim to improve intention identification efficiency.
To achieve the above object, a first aspect of an embodiment of the present application provides an intention identifying method, including:
acquiring intention data to be identified of the outbound robot system;
traversing a plurality of process nodes of the outbound robot system, and acquiring node information of each process node;
extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field;
performing data supplement on the same original intention field according to the node attribute data to obtain first node data
Performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention characteristic;
performing fine adjustment processing on the first node data according to the target intention characteristics to obtain second node data;
performing intention prediction processing on the intention data to be recognized through a preset target intention prediction model to obtain prediction intention data;
and performing intention identification through a preset intention intersection algorithm, the prediction intention data and the second node data to obtain target intention data.
In some embodiments, the step of performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention feature includes:
performing label intention classification on the first node data according to the intention category label to obtain label intention data;
performing semantic analysis processing on the label intention data to obtain node intention corpora;
and extracting the characteristics of the node intention corpus to obtain the target intention characteristics.
In some embodiments, the step of performing fine-tuning processing on the first node data according to the target intention characteristic to obtain second node data includes:
mapping the target intention features to a preset first vector space to obtain target intention feature vectors;
and performing data completion on the first node data according to the target intention characteristic vector to obtain the second node data.
In some embodiments, the target intention prediction model includes an MLP network, a pooling layer and a preset function, and the step of performing intention prediction processing on the intention data to be recognized through the preset target intention prediction model to obtain predicted intention data includes:
mapping the intention data to be identified to a preset second vector space through the MLP network to obtain an intention vector to be identified;
pooling the to-be-identified intention vector through the pooling layer to obtain pooling intention characteristics;
and performing intention prediction processing on the pooled intention characteristics through the preset function to obtain prediction intention data.
In some embodiments, the step of performing intent recognition through a preset intent intersection algorithm, the predicted intent data, and the second node data to obtain target intent data includes:
analyzing the second node data to obtain node intention data;
and performing intersection operation on the node intention data and the prediction intention data through the intention intersection algorithm to obtain the target intention data.
In some embodiments, before the step of performing intent prediction processing on the intent data to be recognized through a preset target intent prediction model to obtain predicted intent data, the method further includes pre-training the target intent prediction model, specifically including:
obtaining sample intent data;
inputting the sample intent data into an initial intent prediction model;
identifying the sample intention data through the initial intention prediction model to obtain a sample intention sentence vector;
calculating the similarity between the two sample intention sentence vectors through a loss function of the initial intention prediction model;
generating entangled corpus pairs according to the similarity and the sample intention sentence vectors;
and optimizing a loss function of the initial intention prediction model according to the entangled corpus so as to update the initial intention prediction model and obtain the target intention prediction model.
In some embodiments, before the step of pre-training the target intent prediction model, the method further includes pre-constructing the initial intent prediction model, specifically including:
acquiring an initial model, wherein the initial model is a Transformer encoder model;
and carrying out parameter fine adjustment on the initial model according to the obtained sample intention data to obtain the initial intention prediction model.
To achieve the above object, a second aspect of embodiments of the present application proposes an intention identifying apparatus, the apparatus including:
the system comprises a to-be-identified intention data acquisition module, a recognition module and a recognition module, wherein the to-be-identified intention data acquisition module is used for acquiring to-be-identified intention data of the outbound robot system;
the node information acquisition module is used for traversing a plurality of process nodes of the outbound robot system and acquiring node information of each process node;
the data extraction module is used for extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field;
the data supplement module is used for performing data supplement on the same original intention field according to the node attribute data to obtain first node data;
the semantic analysis module is used for performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention characteristic;
the fine tuning module is used for carrying out fine tuning processing on the first node data according to the target intention characteristics to obtain second node data;
the intention prediction module is used for carrying out intention prediction processing on the intention data to be recognized through a preset target intention prediction model to obtain predicted intention data;
and the intention identification module is used for carrying out intention identification through a preset intention intersection algorithm, the prediction intention data and the second node data to obtain target intention data.
To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, which includes a memory, a processor, a computer program stored on the memory and executable on the processor, and a data bus for implementing connection communication between the processor and the memory, wherein the computer program, when executed by the processor, implements the method of the first aspect.
To achieve the above object, a fourth aspect of the embodiments of the present application proposes a storage medium, which is a computer-readable storage medium for computer-readable storage, and the storage medium stores one or more computer programs, which are executable by one or more processors to implement the method of the first aspect.
The intention identification method, the intention identification device, the electronic equipment and the storage medium are used for acquiring intention data to be identified of the outbound robot system; the method comprises the steps of traversing a plurality of process nodes of the outbound robot system, obtaining node information of each process node, and conveniently obtaining the node information of the process nodes of the outbound robot system; and then extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field, performing data supplementation on the same original intention field according to the node attribute data to obtain first node data, and supplementing the node information reasonably by the method so as to improve the integrity of the node information. Furthermore, semantic analysis processing is carried out on the first node data according to a preset intention category label to obtain a target intention characteristic, fine tuning processing is carried out on the first node data according to the target intention characteristic to obtain second node data, and data fine tuning can be carried out on the process node according to the target intention characteristic, so that intention characteristics contained in the process node are more accurate and comprehensive, and the requirement of multi-intention identification is met. Finally, intention prediction processing is carried out on the intention data to be recognized through a preset target intention prediction model to obtain predicted intention data, intention recognition is carried out on the intention data and the second node data through a preset intention intersection algorithm to obtain target intention data.
Drawings
FIG. 1 is a flow chart of an intent recognition method provided by an embodiment of the present application;
fig. 2 is a flowchart of step S105 in fig. 1;
FIG. 3 is a flowchart of step S106 in FIG. 1;
FIG. 4 is another flow chart of an intent recognition method provided by an embodiment of the present application;
FIG. 5 is another flow chart of an intent recognition method provided by an embodiment of the present application;
fig. 6 is a flowchart of step S107 in fig. 1;
FIG. 7 is a flowchart of step S108 in FIG. 1;
FIG. 8 is a schematic structural diagram of an intention identifying apparatus provided in an embodiment of the present application;
fig. 9 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms first, second and the like in the description and in the claims, and the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
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 herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
First, several terms referred to in the present application are resolved:
artificial Intelligence (AI): is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produces a new intelligent machine that can react in a manner similar to human intelligence, and research in this field includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. The artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.
Natural Language Processing (NLP): NLP uses computer to process, understand and use human language (such as chinese, english, etc.), and belongs to a branch of artificial intelligence, which is a cross discipline between computer science and linguistics, also commonly called computational linguistics. Natural language processing includes parsing, semantic analysis, discourse understanding, and the like. Natural language processing is commonly used in the technical fields of machine translation, character recognition of handwriting and print, speech recognition and text-to-speech conversion, information intention recognition, information extraction and filtering, text classification and clustering, public opinion analysis and viewpoint mining, and relates to data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, linguistic research related to language calculation and the like related to language processing.
Information Extraction (NER): and extracting the fact information of entities, relations, events and the like of specified types from the natural language text, and forming a text processing technology for outputting structured data. Information extraction is a technique for extracting specific information from text data. The text data is composed of specific units, such as sentences, paragraphs and chapters, and the text information is composed of small specific units, such as words, phrases, sentences and paragraphs or combinations of these specific units. The extraction of noun phrases, names of people, names of places, etc. in the text data is text information extraction, and of course, the information extracted by the text information extraction technology can be various types of information.
Entity: refers to something that is distinguishable and exists independently. Such as a person, a city, a plant, etc., a commodity, etc. All things in the world are composed of specific things, which are referred to as entities. The entity is the most basic element in the knowledge graph, and different relationships exist among different entities.
Self-supervision learning: the self-supervision learning mainly utilizes a secondary task (pretext) to mine self supervision information from large-scale unsupervised data, and the network is trained by the constructed supervision information, so that valuable characteristics of downstream tasks can be learned. That is, the supervised information of the self-supervised learning is not labeled manually, but the algorithm automatically constructs the supervised information in large-scale unsupervised data to perform the supervised learning or training.
Text classification (text classification): given a classification system, each text in the text set is classified into a certain category or several categories, and this process is called text classification. Text classification is a guided learning (supervisual learning) process.
And (3) back propagation: the general principle of back propagation is: inputting training set data into an input layer of a neural network, passing through a hidden layer of the neural network, and finally reaching an output layer of the neural network and outputting a result; calculating the error between the estimated value and the actual value because the output result of the neural network has an error with the actual result, and reversely propagating the error from the output layer to the hidden layer until the error is propagated to the input layer; in the process of back propagation, adjusting the values of various parameters according to errors; and continuously iterating the process until convergence.
At present, in the process of intent recognition, each problem of a predetermined flow often needs to correspond to one flow node, and a plurality of predefined intentions are set at each flow node, so that each node needs to adopt a separate intent recognition model to respectively recognize different intent problems, which often fails to accurately recognize a plurality of intent problems, and affects intent recognition efficiency. Therefore, how to provide an intention recognition method which can improve the intention recognition efficiency is a technical problem to be solved urgently.
Based on this, the embodiment of the application provides an intention identification method, an intention identification device, an electronic device and a storage medium, and aims to improve intention identification efficiency.
The intention identification method, the intention identification device, the electronic device, and the storage medium provided in the embodiments of the present application are specifically described in the following embodiments, and first, the intention identification method in the embodiments of the present application is described.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes 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 the like.
The embodiment of the application provides an intention identification method, and relates to the technical field of artificial intelligence. The intention identification method provided by the embodiment of the application can be applied to a terminal, a server side and software running in the terminal or the server side. In some embodiments, the terminal may be a smartphone, tablet, laptop, desktop computer, or the like; the server side can be configured into an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and cloud servers for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN (content delivery network) and big data and artificial intelligence platforms; the software may be an application or the like implementing the intention recognition method, but is not limited to the above form.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Fig. 1 is an alternative flowchart of an intention identification method provided in an embodiment of the present application, and the method in fig. 1 may include, but is not limited to, steps S101 to S108.
Step S101, acquiring intention data to be identified of the outbound robot system;
step S102, traversing a plurality of process nodes of the outbound robot system, and acquiring node information of each process node;
step S103, extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field;
step S104, performing data supplement on the same original intention field according to the node attribute data to obtain first node data;
step S105, performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention characteristic;
step S106, carrying out fine adjustment processing on the first node data according to the target intention characteristics to obtain second node data;
step S107, carrying out intention prediction processing on the data of the intention to be recognized through a preset target intention prediction model to obtain predicted intention data;
and step S108, performing intention identification through a preset intention intersection algorithm, the prediction intention data and the second node data to obtain target intention data.
In steps S101 to S108 illustrated in the embodiment of the present application, original intention data and node attribute data in node information are extracted, where the original intention data includes an original intention field, and data supplementation is performed on the same original intention field according to the node attribute data to obtain first node data. The semantic analysis processing is carried out on the first node data through the preset intention category labels to obtain target intention characteristics, the fine tuning processing is carried out on the first node data according to the target intention characteristics to obtain second node data, and the data fine tuning can be carried out on the process nodes according to the target intention characteristics, so that the intention characteristics contained in the process nodes are more accurate and comprehensive, and the requirement of multi-intention recognition is met. And finally, performing intention prediction processing on the data to be recognized through a preset target intention prediction model to obtain predicted intention data, and performing intention recognition on the data to be recognized through a preset intention intersection algorithm, the predicted intention data and the second node data to obtain target intention data. According to the embodiment of the application, under the condition that a plurality of intention recognition models are not required to be set, a plurality of intention problems can be conveniently and accurately recognized, the intention recognition efficiency is improved, meanwhile, occupation of server resources is reduced, and the resource utilization rate is improved.
The robot calling system is also called a robot calling system, and is an intelligent system integrating advanced technologies such as NLP technology, various voice technologies, big data technology, deep learning algorithm technology and the like. The outbound robot system is mainly integrated in the outbound robot and can be used for identifying the intention of the user. In the credit card collection application scenario, "verify customer identity" is one user's awareness, and "the customer is willing to return arrears" is another user's awareness.
In step S101 of some embodiments, the intention data to be identified of the outbound robot system may be obtained by writing a web crawler, setting a data source, and then performing targeted crawling data. The intention data to be identified can also be directly acquired from the outbound robot system through data transmission. The intent-to-recognize data may include specific user intents such as "verify customer identity", "customer is willing to return arrears", etc. as described above.
In step S102 of some embodiments, a plurality of process nodes of the outbound robot system may be traversed according to a preset number of the process nodes of the outbound robot system or a plurality of sequences such as an initial name of the process node, so as to obtain node information of the process nodes, where the node information includes a node problem, a node intention, and the like. For example, the flow nodes numbered 2, 5, and 6 may be traversed sequentially according to the preset number of the flow node.
In step S103 of some embodiments, the original intention data and the node attribute data in the node information may be extracted according to a preset category anchor field, for example, the preset category anchor field includes "basic attribute", "number of characters", "intention", and the like. By inputting fields such as basic attribute, character number and the like, the content related to the node attribute data can be retrieved, the node attribute data can be extracted, and by inputting fields such as intention, the original intention data of the flow node can be retrieved and extracted, wherein the original intention data comprises a plurality of original intention fields which can be divided according to part of speech categories, sentence lengths and the like.
In step S104 of some embodiments, in order to improve the integrity of the node information, it is necessary to perform data completion on the same original intention field according to the node attribute data, so as to obtain the first node data. Specifically, the same original intention field is obtained by comparing the original intention fields of each process node, wherein the same original intention field refers to the original intention fields corresponding to different node problems in different process nodes, but the field content and the field have the same meaning, and the same original intention fields have different meanings according to the node problems corresponding to the process node where the same original intention field is located. In order to improve the intention identification precision and avoid causing ambiguity, the process nodes containing the same original intention field are marked to obtain a marked process node, the node attribute data of the marked process node is analyzed to obtain a key field of the node problem of the marked process node so as to clarify the real intention of the process node, and therefore the same original intention field is subjected to completion processing according to the key field, for example, sentence completion, entity rewriting, case rewriting, synonym transformation and the like are carried out on the same original intention field, and a target intention field corresponding to the node problem of each process node is formed. And then, adding the target intention fields into the corresponding process nodes, and performing data expansion on the original intention data through the target intention fields to obtain first node data. By the method, the node information can be reasonably supplemented, and the integrity of the node information is improved.
For example, in the credit card collection scenario, the original intent field named "yes" means "the receiver is the arrearage client himself" in the process node corresponding to the node problem of "verify client identity", but the original intent field means "the client is willing to return arrearage" in the process node corresponding to the node problem of "whether the client is willing to return arrearage". Since these two identical original intention fields are now completely different in meaning. Therefore, in order to avoid ambiguity, the original intention field needs to be supplemented, the original intention field of the process node corresponding to the node problem of "verifying the identity of the customer" is "supplemented as" is oneself ", and the original intention field of the process node corresponding to the node problem of" whether the customer is willing to return arrearages "is" supplemented as "willing to return payment".
Referring to fig. 2, in some embodiments, step S105 may include, but is not limited to, step S201 to step S203:
step S201, performing label intention classification on the first node data according to intention category labels to obtain label intention data;
step S202, semantic analysis processing is carried out on the label intention data to obtain node intention corpora;
step S203, extracting the characteristics of the node intention corpus to obtain the target intention characteristics.
In step S201 of some embodiments, the first node data is subjected to label intention classification according to intention category labels and a preset label classification model. In a credit card service scene, the intention category label can comprise borrowing, repayment, loan consultation and the like, and in other application scenes, the intention category label can be preset according to actual service handling requirements without limitation; the label classification model is a textCNN model and comprises an Embedding layer, a convolution layer, a pooling layer and an output layer. Generally, an algorithm such as ELMO, GLOVE, Word2Vector, Bert and the like can be adopted to generate a dense Vector from input first node data through an Embedding layer of a label classification model. And performing convolution processing and pooling processing on the dense vector through the convolution layer and the pooling layer to obtain a target feature vector, inputting the feature vector into an output layer, and performing label intention classification on the target feature vector through a preset function (such as a softmax function) and an intention type label in the output layer to obtain label intention data.
In step S202 and step S203 of some embodiments, the label intention data of each process node is traversed and compared through a preset dictionary tree, node intention corpora of different process nodes are identified and extracted, the node intention corpora are the same intention corpora of different process nodes, that is, the overlapped parts of the label intention data of two process nodes, and the node intention corpora are extracted separately as the same intention feature, so as to obtain the target intention feature.
Referring to fig. 3, in some embodiments, step S106 may include, but is not limited to, step S301 to step S302:
step S301, mapping the target intention features to a preset first vector space to obtain target intention feature vectors;
and S302, performing data completion on the first node data according to the target intention characteristic vector to obtain second node data.
In step S301 of some embodiments, the target intention feature vector is obtained by mapping the target intention feature to a preset first vector space by means of an intention mapping method using an MLP network. It should be noted that, by mapping the target intention feature to the first vector space, the target intention feature vector can meet the preset feature dimension requirement, for example, the feature dimension of the first vector space is 512 × 512.
In step S302 of some embodiments, data completion is performed on the first node data according to the target intention feature vector, for example, sentence completion, entity rewriting, case rewriting, synonym transformation, and the like are performed on the first node data, and second node data corresponding to the node problem of each process node is formed. By the method, data fine adjustment can be performed on the process nodes according to the target intention characteristics, so that the intention characteristics contained in the process nodes are more accurate and comprehensive, and the requirement of multi-intention identification is met.
For example, the annotation intention data of the same corpus X in the process node No. 1 is intention a, and the annotation intention data in the process node No. 2 is intention B. When multi-intention recognition is carried out, the intention A and the intention B of the corpus X are recognized, namely, the intention corpora of the overlapped parts of the label intention data of the two process nodes are recognized as the intention A and the intention B at the same time. In order to improve the intention identification accuracy, the intention corpus of the overlapped part can be extracted separately as a new intention C, namely, the intention A and the intention B are split. After intent splitting, only corpus X will be identified as intent C. Furthermore, the intention C is mapped to the intention a or the intention B by means of the intention mapping, that is, at the flow node No. 1, when the corpus X is identified as the intention C, the intention C is mapped to the intention a, and the outbound robot performs the same operation or reply as after the intention a is identified. Similarly, the processing is carried out in a similar mode at the No. 2 process node, so that the accuracy of intention identification is improved.
Referring to fig. 4, in some embodiments, before step S107, the method further includes pre-constructing an initial intent prediction model, which specifically includes:
step S401, obtaining an initial model, wherein the initial model is a Transformer encoder model;
and S402, carrying out parameter fine adjustment on the initial model according to the acquired sample intention data to obtain an initial intention prediction model.
In step S401 of some embodiments, the preset initial model may be a Transformer encoder model; and performing parameter fine adjustment by taking the Transformer encoder model as a basic model to update the Transformer encoder model so as to obtain an initial intention prediction model. The Transformer encoder model includes two Transformer layers. The intention prediction performance can be improved through a Transformer encoder model.
In step S402 of some embodiments, a loss function is constructed according to the sample intention data, and the loss function is calculated according to the sample intention data, for example, a similarity value between the sample intention data and the reference intention data is calculated by the loss function, and a loss parameter of the loss function is fine-tuned according to the similarity value, so that the loss parameter after the fine-tuning can satisfy a requirement that the similarity value is greater than or equal to a preset similarity threshold. And taking the fine-tuned loss function as a model parameter of the initial model to update the initial model to obtain an initial intention prediction model.
It is to be understood that other manners may also be adopted, the transform encoder model is used as a base model to be trained to obtain an initial intention prediction model, for example, the knowledge distillation manner may be adopted to train, and it is to be understood that the present application may be implemented by adopting a conventional knowledge distillation manner, and the present application is not limited in this embodiment.
Referring to fig. 5, in some embodiments, before step S107, the method further includes pre-training the target intention prediction model, specifically including:
step S501, sample intention data is obtained;
step S502, inputting sample intention data into an initial intention prediction model;
step S503, identifying the sample intention data through the initial intention prediction model to obtain a sample intention sentence vector;
step S504, calculating the similarity between the two sample intention sentence vectors through the loss function of the initial intention prediction model;
step S505, generating an entangled corpus pair according to the similarity and the sample intention sentence vector;
step S506, optimizing a loss function of the initial intention prediction model according to the entangled corpus so as to update the initial intention prediction model and obtain a target intention prediction model.
In step S501 and step S502 of some embodiments, the sample intention data may be obtained by writing a web crawler, and performing targeted crawling data after setting a data source. The sample intent data is then input into the initial intent prediction model.
In step S503 of some embodiments, the sample data is pooled and activated by the initial intention prediction model, so as to obtain a sample intention sentence vector.
In step S504 of some embodiments, the similarity between the two sample intention vectors may be calculated by a collaborative filtering algorithm such as cosine similarity algorithm through the loss function of the initial intention prediction model. For example, assuming that one of the sample intention vectors u and the other sample intention vector is v, the similarity between the two sample intention vectors is calculated according to the cosine similarity calculation method (as shown in formula (1)), where u isTIs the transpose of u.
Figure BDA0003483187760000111
In step S505 of some embodiments, the magnitude relationship between the similarity and the preset similarity threshold is compared, and if the similarity is greater than or equal to the similarity threshold, an entangled corpus pair is generated according to the sample intention sentence vector.
It should be noted that the degree of similarity between the entangled corpus and the query represented by two corpora query1 and query2 is high, but the labeling intentions of the two corpora query2 are different, the labeling intention of the corpus query1 is label1, the labeling intention of the corpus query2 is label2, the similarity score is a real number, score belongs to [0,1], and a larger score indicates that the semantic similarity between query1 and query2 is higher. The preset similarity threshold may be 0.9. When the similarity is greater than a preset similarity threshold value, the labeling intentions of the two corresponding corpora are different, the two corpora are considered to be entangled with each other, and are called entangled corpus pairs, and the labeling of at least one of the corpora is considered to be wrong. Therefore, all the entangled corpus pairs are output to a preset rechecking table to indicate the data annotation personnel to re-label the corpora.
In step S506 of some embodiments, the loss function is propagated backward according to the entangled corpus to update the initial intent prediction model by optimizing the loss function, and update internal parameters (i.e., loss parameters) of the initial intent prediction model to obtain the target intent prediction model. It is to be understood that the back propagation principle can be applied to a conventional back propagation principle, and the embodiments of the present application are not limited thereto.
It should be noted that, due to the correction process of the entangled corpus pair, it may not be possible to completely find out the corpuses with the wrong or missing label in the training set. Therefore, after the correction of the entangled linguistic data is completed for one time, the corrected business data is needed to be used for fine tuning the initial intention prediction model again, the process is repeated continuously, the entanglement condition of the training set is calculated, and the found entangled linguistic data is re-labeled for the labeling personnel. Until the data in the training set is no longer entangled, the optimization of the initial intent prediction model is stopped.
Referring to fig. 6, in some embodiments, the target intention prediction model includes an MLP network, a pooling layer and a preset function, and step S107 may further include, but is not limited to, steps S601 to S603:
step S601, mapping the intention data to be identified to a preset second vector space through an MLP network to obtain an intention vector to be identified;
step S602, performing pooling processing on the vectors of the intentions to be recognized through a pooling layer to obtain pooling intention characteristics;
step S603, performing intent prediction processing on the pooled intent features through a preset function to obtain prediction intent data.
In step S601 in some embodiments, an MLP network may be used to perform multiple mapping processes from a semantic space to a vector space on the intention data to be recognized, and map the intention data to be recognized to a preset second vector space to obtain an intention vector to be recognized. It should be noted that, by mapping the intention data to be identified to the first vector space, the intention vector to be identified can be made to meet the preset characteristic dimension requirement, for example, the characteristic dimension of the second vector space is 256 × 256.
In step S602 of some embodiments, maximum pooling and average pooling are performed on the to-be-identified intention vector by the pooling layer, and the result of the maximum pooling and the result of the average pooling are concatenated to obtain the pooled intention feature.
In step S603 of some embodiments, the preset function may be a softmax function, a tanh function, or the like. Taking the softmax function as an example, the softmax function may create a probability distribution on a preset intention category label, so as to perform label classification on the feature vectors according to the probability distribution, thereby obtaining predicted intention data. The skirt, the predicted intention data is mainly word embedding vector containing intention category label and intention probability value corresponding to each intention category.
Referring to fig. 7, in some embodiments, step S108 may further include, but is not limited to, step S701 to step S702:
step S701, analyzing the second node data to obtain node intention data;
step S702, performing intersection operation on the node intention data and the prediction intention data through an intention intersection algorithm to obtain target intention data.
In step S701 of some embodiments, the second node data is parsed through a parsing function and an intention category tag to obtain a plurality of node intention fields, and a node intention list is generated according to the plurality of node intention fields to obtain node intention data.
For example, first, performing word segmentation processing on second node data through an analytic function and an intention category label, generating a directed acyclic graph corresponding to the second node data by referring to a dictionary in a preset jieba word segmentation device, finding a shortest path on the directed acyclic graph through the analytic function, a preset selection mode and the dictionary, and intercepting the second node data according to the shortest path, or directly intercepting the second node data to obtain a plurality of node intention fields.
Further, for the node intention field not in the dictionary, new word discovery may be performed using HMM (hidden markov model). Specifically, the position B, M, E, S of the character in the node intention field is taken as a hidden state, and the character is an observed state, wherein B/M/E/S represents the occurrence in the beginning of a word, in the word, at the end of a word, and in the word-forming word, respectively. The representation probability matrix, the initial probability vector, and the transition probability matrix between the characters are respectively stored using a dictionary file. And solving the maximum possible hidden state by utilizing a Viterbi algorithm so as to obtain a node intention field.
And finally, filling the plurality of node intention fields into a preset excel table, and generating a node intention list so as to obtain node intention data.
In step S702 of some embodiments, the node intention data and the prediction intention data are subjected to intersection operation by an intention intersection algorithm, and intention features existing in both the node intention data and the prediction intention data are extracted, so as to obtain target intention data. For example, if the predicted intention data includes intention a and intention B, but the node intention data included in the intention list of the current flow node is intention a, intention X, and intention Y, it may be determined that the user intention is intention a under the current flow node according to the intention intersection algorithm. However, if the node intention list of the current process node contains node intention data of intention X, intention Y and intention Z, the user corpus cannot be processed at the current process node through intersection operation, and prompt information of 'refusal identification' can be output through the outbound robot system.
It should be noted that the above-mentioned intention intersection algorithm may be a set intersection algorithm, and specifically, when the set intersection algorithm is used for intersection operation, it is first necessary to create a sym () function, accept two or more arrays through the sym () function, and return a symmetric difference (symmetric difference) of the given arrays, for example, to give two sets (e.g., set a ═ 1,2,3} and set B ═ 2,3,4}), and a set of mathematical term "symmetric difference" refers to a set composed of all elements in only one of the two sets (a Δ B ═ C {1,4}), for an incoming additional set (e.g., D ═ 2,3}), the result of the former two sets and the peer set of the new set can be obtained according to the set intersection algorithm (C Δ D ═ 1,4}, Δ {2,3} {1,2,3}, 4}).
According to the method and the device, the intention data to be identified of the outbound robot system are obtained; the method comprises the steps of traversing a plurality of process nodes of the outbound robot system, obtaining node information of each process node, and conveniently obtaining the node information of the process nodes of the outbound robot system; and then extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field, performing data supplementation on the same original intention field according to the node attribute data to obtain first node data, and supplementing the node information reasonably by the method so as to improve the integrity of the node information. Furthermore, semantic analysis processing is carried out on the first node data according to a preset intention category label to obtain a target intention characteristic, fine tuning processing is carried out on the first node data according to the target intention characteristic to obtain second node data, and data fine tuning can be carried out on the process node according to the target intention characteristic, so that intention characteristics contained in the process node are more accurate and comprehensive, and the requirement of multi-intention identification is met. Finally, intention prediction processing is carried out on the intention data to be recognized through a preset target intention prediction model to obtain predicted intention data, intention recognition is carried out on the intention data and the second node data through a preset intention intersection algorithm to obtain target intention data.
Referring to fig. 8, an intention recognition apparatus is further provided in an embodiment of the present application, which can implement the intention recognition method, and the apparatus includes:
an intention data to be identified acquiring module 801, configured to acquire intention data to be identified of the outbound robot system;
a node information obtaining module 802, configured to traverse multiple process nodes of the outbound robot system, and obtain node information of each process node;
a data extraction module 803, configured to extract original intention data and node attribute data in the node information, where the original intention data includes an original intention field;
a data supplement module 804, configured to perform data supplement on the same original intention field according to the node attribute data, so as to obtain first node data;
the semantic analysis module 805 is configured to perform semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention feature;
the fine-tuning module 806 is configured to perform fine-tuning processing on the first node data according to the target intention characteristic to obtain second node data;
an intention prediction module 807, configured to perform intention prediction processing on the to-be-recognized intention data through a preset target intention prediction model to obtain predicted intention data;
and the intention identification module 808 is configured to perform intention identification through a preset intention intersection algorithm, the predicted intention data and the second node data to obtain target intention data.
The specific implementation of the intention identifying device is substantially the same as the specific implementation of the intention identifying method, and is not described herein again.
An embodiment of the present application further provides an electronic device, where the electronic device includes: a memory, a processor, a computer program stored on the memory and executable on the processor, and a data bus for enabling a connection communication between the processor and the memory, the computer program, when executed by the processor, implementing the above-mentioned intent recognition method. The electronic equipment can be any intelligent terminal including a tablet computer, a vehicle-mounted computer and the like.
Referring to fig. 9, fig. 9 illustrates a hardware structure of an electronic device according to another embodiment, where the electronic device includes:
the processor 901 may be implemented by a general-purpose CPU (central processing unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits, and is configured to execute a relevant program to implement the technical solution provided in the embodiment of the present application;
the memory 902 may be implemented in the form of a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a Random Access Memory (RAM). The memory 902 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present disclosure is implemented by software or firmware, the relevant program codes are stored in the memory 902 and called by the processor 901 to execute the intention identification method of the embodiments of the present disclosure;
an input/output interface 903 for implementing information input and output;
a communication interface 904, configured to implement communication interaction between the device and another device, where communication may be implemented in a wired manner (e.g., USB, network cable, etc.), or in a wireless manner (e.g., mobile network, WIFI, bluetooth, etc.);
a bus 905 that transfers information between various components of the device (e.g., the processor 901, the memory 902, the input/output interface 903, and the communication interface 904);
wherein the processor 901, the memory 902, the input/output interface 903 and the communication interface 904 enable a communication connection within the device with each other through a bus 905.
Embodiments of the present application further provide a storage medium, which is a computer-readable storage medium for computer-readable storage, and the storage medium stores one or more computer programs, and the one or more computer programs are executable by one or more processors to implement the above-mentioned intent recognition method.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
According to the intention identification method, the intention identification device, the electronic equipment and the storage medium, the intention data to be identified of the outbound robot system are obtained; the method comprises the steps of traversing a plurality of process nodes of the outbound robot system, obtaining node information of each process node, and conveniently obtaining the node information of the process nodes of the outbound robot system; and then extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field, performing data supplementation on the same original intention field according to the node attribute data to obtain first node data, and supplementing the node information reasonably by the method so as to improve the integrity of the node information. Furthermore, semantic analysis processing is carried out on the first node data according to a preset intention category label to obtain a target intention characteristic, fine tuning processing is carried out on the first node data according to the target intention characteristic to obtain second node data, and data fine tuning can be carried out on the process node according to the target intention characteristic, so that intention characteristics contained in the process node are more accurate and comprehensive, and the requirement of multi-intention identification is met. Finally, the intention prediction processing is carried out on the data of the intention to be recognized through a preset target intention prediction model to obtain predicted intention data, the intention recognition is carried out on the data of the preset intention intersection algorithm, the predicted intention data and the second node data to obtain target intention data, a plurality of intention problems can be accurately recognized, and the accuracy of intention recognition is improved. According to the embodiment of the application, under the condition that a plurality of intention recognition models are not required to be arranged, a plurality of intention problems can be conveniently and accurately recognized, and the intention recognition efficiency is improved; meanwhile, the intention identification method does not need to perform independent model training on different intention problems respectively, so that the occupation of server resources and the model training cost can be effectively reduced.
The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation to the technical solutions provided in the embodiments of the present application, and it is obvious to those skilled in the art that the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems with the evolution of technology and the emergence of new application scenarios.
It will be appreciated by those skilled in the art that the solutions shown in fig. 1-7 are not intended to limit the embodiments of the present application and may include more or fewer steps than those shown, or some of the steps may be combined, or different steps may be included.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The preferred embodiments of the present application have been described above with reference to the accompanying drawings, and the scope of the claims of the embodiments of the present application is not limited thereto. Any modifications, equivalents and improvements that may occur to those skilled in the art without departing from the scope and spirit of the embodiments of the present application are intended to be within the scope of the claims of the embodiments of the present application.

Claims (10)

1. An intent recognition method, the method comprising:
acquiring intention data to be identified of the outbound robot system;
traversing a plurality of process nodes of the outbound robot system, and acquiring node information of each process node;
extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field;
performing data supplementation on the same original intention field according to the node attribute data to obtain first node data;
performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention characteristic;
performing fine adjustment processing on the first node data according to the target intention characteristics to obtain second node data;
performing intention prediction processing on the intention data to be recognized through a preset target intention prediction model to obtain prediction intention data;
and performing intention identification through a preset intention intersection algorithm, the prediction intention data and the second node data to obtain target intention data.
2. The method for identifying the intention according to claim 1, wherein the step of performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention characteristic comprises:
performing label intention classification on the first node data according to the intention category label to obtain label intention data;
performing semantic analysis processing on the label intention data to obtain node intention corpora;
and extracting the characteristics of the node intention corpus to obtain the target intention characteristics.
3. The method according to claim 1, wherein the step of performing a fine-tuning process on the first node data according to the target intention characteristic to obtain second node data comprises:
mapping the target intention features to a preset first vector space to obtain target intention feature vectors;
and performing data completion on the first node data according to the target intention characteristic vector to obtain the second node data.
4. The intent recognition method according to claim 1, wherein the target intent prediction model comprises an MLP network, a pooling layer and a preset function, and the step of performing intent prediction processing on the intent data to be recognized through the preset target intent prediction model to obtain predicted intent data comprises:
mapping the intention data to be identified to a preset second vector space through the MLP network to obtain an intention vector to be identified;
pooling the to-be-identified intention vector through the pooling layer to obtain pooling intention characteristics;
and performing intention prediction processing on the pooled intention characteristics through the preset function to obtain prediction intention data.
5. The intention identifying method according to claim 1, wherein the step of performing intention identification through a preset intention intersection algorithm, the predicted intention data and the second node data to obtain target intention data comprises:
analyzing the second node data to obtain node intention data;
and performing intersection operation on the node intention data and the prediction intention data through the intention intersection algorithm to obtain the target intention data.
6. The intention recognition method according to any one of claims 1 to 5, wherein before the step of performing intention prediction processing on the intention data to be recognized through a preset target intention prediction model to obtain predicted intention data, the method further comprises pre-training the target intention prediction model, specifically comprising:
obtaining sample intent data;
inputting the sample intent data into an initial intent prediction model;
identifying the sample intention data through the initial intention prediction model to obtain a sample intention sentence vector;
calculating the similarity between the two sample intention sentence vectors through a loss function of the initial intention prediction model;
generating entangled corpus pairs according to the similarity and the sample intention sentence vectors;
and optimizing a loss function of the initial intention prediction model according to the entangled corpus so as to update the initial intention prediction model and obtain the target intention prediction model.
7. The intent recognition method according to claim 6, wherein, prior to the step of pre-training the target intent prediction model, the method further comprises pre-constructing the initial intent prediction model, in particular comprising:
acquiring an initial model, wherein the initial model is a Transformer encoder model;
and carrying out parameter fine adjustment on the initial model according to the obtained sample intention data to obtain the initial intention prediction model.
8. An intent recognition apparatus, characterized in that the apparatus comprises:
the system comprises a to-be-identified intention data acquisition module, a recognition module and a recognition module, wherein the to-be-identified intention data acquisition module is used for acquiring to-be-identified intention data of the outbound robot system;
the node information acquisition module is used for traversing a plurality of process nodes of the outbound robot system and acquiring node information of each process node;
the data extraction module is used for extracting original intention data and node attribute data in the node information, wherein the original intention data comprises an original intention field;
the data supplement module is used for performing data supplement on the same original intention field according to the node attribute data to obtain first node data;
the semantic analysis module is used for performing semantic analysis processing on the first node data according to a preset intention category label to obtain a target intention characteristic;
the fine tuning module is used for carrying out fine tuning processing on the first node data according to the target intention characteristics to obtain second node data;
the intention prediction module is used for carrying out intention prediction processing on the intention data to be recognized through a preset target intention prediction model to obtain predicted intention data;
and the intention identification module is used for carrying out intention identification through a preset intention intersection algorithm, the prediction intention data and the second node data to obtain target intention data.
9. An electronic device, characterized in that the electronic device comprises a memory, a processor, a computer program stored on the memory and executable on the processor, and a data bus for enabling connection communication between the processor and the memory, the computer program, when executed by the processor, implementing the steps of the intent recognition method according to any of claims 1 to 7.
10. A storage medium, which is a computer-readable storage medium, for computer-readable storage, characterized in that the storage medium stores one or more computer programs, which are executable by one or more processors, to implement the steps of the intent recognition method of any of claims 1-7.
CN202210074053.2A 2022-01-21 2022-01-21 Intention recognition method, device, electronic equipment and storage medium Active CN114398903B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210074053.2A CN114398903B (en) 2022-01-21 2022-01-21 Intention recognition method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210074053.2A CN114398903B (en) 2022-01-21 2022-01-21 Intention recognition method, device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114398903A true CN114398903A (en) 2022-04-26
CN114398903B CN114398903B (en) 2023-06-20

Family

ID=81232023

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210074053.2A Active CN114398903B (en) 2022-01-21 2022-01-21 Intention recognition method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114398903B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117196035A (en) * 2023-08-31 2023-12-08 摩尔线程智能科技(北京)有限责任公司 Reply content processing method and device, electronic equipment and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019024162A1 (en) * 2017-08-04 2019-02-07 平安科技（深圳）有限公司 Intention obtaining method, electronic device, and computer-readable storage medium
CN109815489A (en) * 2019-01-02 2019-05-28 深圳壹账通智能科技有限公司 Collection information generating method, device, computer equipment and storage medium
CN111274797A (en) * 2020-01-13 2020-06-12 平安国际智慧城市科技股份有限公司 Intention recognition method, device and equipment for terminal and storage medium
US20200242486A1 (en) * 2019-01-29 2020-07-30 Ricoh Company, Ltd. Method and apparatus for recognizing intention, and non-transitory computer-readable recording medium
US20200242302A1 (en) * 2019-01-29 2020-07-30 Ricoh Company, Ltd. Intention identification method, intention identification apparatus, and computer-readable recording medium
CN111563144A (en) * 2020-02-25 2020-08-21 升智信息科技(南京)有限公司 Statement context prediction-based user intention identification method and device
CN111931513A (en) * 2020-07-08 2020-11-13 泰康保险集团股份有限公司 Text intention identification method and device
CN112380870A (en) * 2020-11-19 2021-02-19 平安科技（深圳）有限公司 User intention analysis method and device, electronic equipment and computer storage medium
CN112988963A (en) * 2021-02-19 2021-06-18 平安科技（深圳）有限公司 User intention prediction method, device, equipment and medium based on multi-process node
CN113220828A (en) * 2021-04-28 2021-08-06 平安科技（深圳）有限公司 Intention recognition model processing method and device, computer equipment and storage medium
CN113515594A (en) * 2021-04-28 2021-10-19 京东数字科技控股股份有限公司 Intention recognition method, intention recognition model training method, device and equipment
CA3123387A1 (en) * 2021-06-28 2021-11-10 Ada Support Inc. Method and system for generating an intent classifier

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019024162A1 (en) * 2017-08-04 2019-02-07 平安科技（深圳）有限公司 Intention obtaining method, electronic device, and computer-readable storage medium
CN109815489A (en) * 2019-01-02 2019-05-28 深圳壹账通智能科技有限公司 Collection information generating method, device, computer equipment and storage medium
US20200242486A1 (en) * 2019-01-29 2020-07-30 Ricoh Company, Ltd. Method and apparatus for recognizing intention, and non-transitory computer-readable recording medium
US20200242302A1 (en) * 2019-01-29 2020-07-30 Ricoh Company, Ltd. Intention identification method, intention identification apparatus, and computer-readable recording medium
CN111274797A (en) * 2020-01-13 2020-06-12 平安国际智慧城市科技股份有限公司 Intention recognition method, device and equipment for terminal and storage medium
CN111563144A (en) * 2020-02-25 2020-08-21 升智信息科技(南京)有限公司 Statement context prediction-based user intention identification method and device
CN111931513A (en) * 2020-07-08 2020-11-13 泰康保险集团股份有限公司 Text intention identification method and device
CN112380870A (en) * 2020-11-19 2021-02-19 平安科技（深圳）有限公司 User intention analysis method and device, electronic equipment and computer storage medium
CN112988963A (en) * 2021-02-19 2021-06-18 平安科技（深圳）有限公司 User intention prediction method, device, equipment and medium based on multi-process node
CN113220828A (en) * 2021-04-28 2021-08-06 平安科技（深圳）有限公司 Intention recognition model processing method and device, computer equipment and storage medium
CN113515594A (en) * 2021-04-28 2021-10-19 京东数字科技控股股份有限公司 Intention recognition method, intention recognition model training method, device and equipment
CA3123387A1 (en) * 2021-06-28 2021-11-10 Ada Support Inc. Method and system for generating an intent classifier

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117196035A (en) * 2023-08-31 2023-12-08 摩尔线程智能科技(北京)有限责任公司 Reply content processing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN114398903B (en) 2023-06-20

Similar Documents

Publication Publication Date Title
CN113792818B (en) Intention classification method and device, electronic equipment and computer readable storage medium
CN113887215A (en) Text similarity calculation method and device, electronic equipment and storage medium
CN111666399A (en) Intelligent question and answer method and device based on knowledge graph and computer equipment
CN114722069A (en) Language conversion method and device, electronic equipment and storage medium
CN114358007A (en) Multi-label identification method and device, electronic equipment and storage medium
CN113849661A (en) Entity embedded data extraction method and device, electronic equipment and storage medium
CN114926039A (en) Risk assessment method, risk assessment device, electronic device, and storage medium
CN116258137A (en) Text error correction method, device, equipment and storage medium
CN115510232A (en) Text sentence classification method and classification device, electronic equipment and storage medium
CN114861598A (en) Annotating method, annotating device, electronic equipment and storage medium
CN114722174A (en) Word extraction method and device, electronic equipment and storage medium
CN114358020A (en) Disease part identification method and device, electronic device and storage medium
CN113342944B (en) Corpus generalization method, apparatus, device and storage medium
CN114398903B (en) Intention recognition method, device, electronic equipment and storage medium
CN113761151A (en) Synonym mining method, synonym mining device, synonym question answering method, synonym question answering device, computer equipment and storage medium
CN116719999A (en) Text similarity detection method and device, electronic equipment and storage medium
CN116956925A (en) Electronic medical record named entity identification method and device, electronic equipment and storage medium
CN116701604A (en) Question and answer corpus construction method and device, question and answer method, equipment and medium
CN116775875A (en) Question corpus construction method and device, question answering method and device and storage medium
CN115795007A (en) Intelligent question-answering method, intelligent question-answering device, electronic equipment and storage medium
CN114090778A (en) Retrieval method and device based on knowledge anchor point, electronic equipment and storage medium
CN115204300A (en) Data processing method, device and storage medium for text and table semantic interaction
CN115270746A (en) Question sample generation method and device, electronic equipment and storage medium
CN114998041A (en) Method and device for training claim settlement prediction model, electronic equipment and storage medium
CN114611529A (en) Intention recognition method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant