CN114756669A - Intelligent analysis method and device for problem intention, electronic equipment and storage medium - Google Patents
Intelligent analysis method and device for problem intention, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114756669A CN114756669A CN202210446926.8A CN202210446926A CN114756669A CN 114756669 A CN114756669 A CN 114756669A CN 202210446926 A CN202210446926 A CN 202210446926A CN 114756669 A CN114756669 A CN 114756669A
- Authority
- CN
- China
- Prior art keywords
- intention
- track
- historical
- type
- classification model
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses an intelligent analysis method, an intelligent analysis device, electronic equipment and a storage medium for problem intention, wherein the method comprises the following steps: acquiring a training track sample and a corresponding annotation intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model; acquiring historical behavior data of a target user, and carrying out track classification on the historical behavior data to obtain a historical track category of the target user; and receiving the current question input by the target user, and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category. Furthermore, the invention relates to blockchain techniques, in which the historical behavior data may be stored. The invention can improve the identification accuracy of the problem intention.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to an intelligent problem analysis method and apparatus, an electronic device, and a computer-readable storage medium.
Background
When the intelligent customer service robot identifies the user problem, an accurate judgment is carried out on most user problems through a natural language processing technology, but when the query sentence consulted by the user is short and has low or very similar recognition degree, a plurality of post-selection intentions with similar scores can exist, at the moment, the intelligent customer service robot can usually give the result of the user problem according to the preset intention priority, the phenomenon of misjudgment can be caused when the intention of the user problem is replied easily, and therefore a scheme is urgently needed to improve the accuracy of the intelligent customer service robot in identifying the intention of the user problem.
Disclosure of Invention
The invention provides an intelligent analysis method and device for problem intentions, electronic equipment and a computer-readable storage medium, and mainly aims to improve the recognition accuracy of the problem intentions.
In order to achieve the above object, the present invention provides an intelligent analysis method for problem intentions, comprising:
acquiring a training track sample and a corresponding annotation intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model;
Acquiring historical behavior data of a target user, and carrying out track classification on the historical behavior data to obtain a historical track category of the target user;
and receiving the current question input by the target user, and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
Optionally, the training a pre-constructed intention classification model by using the training track sample and the labeled intention type to obtain a trained intention classification model includes:
performing feature extraction on the training track sample by using a feature extraction layer in the pre-constructed intention classification model to obtain a feature vector of the training track sample;
performing intention classification on the feature vectors by using an intention recognition layer in the pre-constructed intention classification model to obtain a predicted intention type of the training track sample;
calculating loss values of the prediction intention type and the annotation intention type by using a loss function in the pre-constructed intention classification model;
if the loss value is larger than a preset threshold value, returning to execute the step of performing feature extraction on the training track sample by using a feature extraction layer in the pre-constructed intention classification model after adjusting the model parameters in the pre-constructed intention classification model;
And if the loss value is not greater than the preset threshold value, obtaining a trained intention classification model.
Optionally, the loss function comprises:
wherein L(s) represents a loss value, sjRepresenting the difference between the predicted intention type and the labeled intention type, k representing the number of training track samples, yiDenotes the ith type of predictive intent, y'iAnd the ith annotation intention type is represented.
Optionally, the collecting historical behavior data of the target user includes:
detecting historical behavior events of the target user in an application program;
responding to the historical behavior event, and recording historical event characteristics and historical user characteristics of the historical behavior event by using a pre-constructed buried point frame;
and generating historical behavior data according to the historical event characteristics and the historical user characteristics.
Optionally, the performing track classification on the historical behavior data to obtain the historical track category of the target user includes:
detecting a behavior track of the historical behavior data, and identifying track characteristics of the behavior track;
and matching the track characteristics with track categories in a preset track category library, and taking the track categories successfully matched as the categories of the behavior tracks to obtain the historical track categories of the target user.
Optionally, the identifying, according to the historical track category, a final intention type of the current question using the trained intention classification model includes:
detecting a first intention type of the current question and an intention type probability corresponding to the first intention type by using the trained intention classification model, and selecting a second intention type of the current question from the historical track category;
determining a final intent type of the current question from the first intent type based on the second intent type and the intent type probability.
Optionally, the selecting a second intention type of the current question from the historical track category includes:
identifying a current trajectory of the current question;
and matching the current track with the historical track corresponding to the historical track category, and taking the category corresponding to the historical track which is successfully matched as a second intention type of the current problem.
In order to solve the above problem, the present invention also provides an intelligent analysis apparatus of problem intention, the apparatus including:
the classification model training module is used for acquiring a training track sample and a corresponding labeling intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the labeling intention type to obtain a trained intention classification model;
The data track classification module is used for collecting historical behavior data of a target user and carrying out track classification on the historical behavior data to obtain a historical track class of the target user;
and the intention type identification module is used for receiving the current question input by the target user and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores a computer program executable by the at least one processor to implement the intelligent analysis method of problem intent described above.
In order to solve the above problem, the present invention also provides a computer-readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the intelligent analysis method for problem intention described above.
It can be seen that, in the embodiment of the present invention, a training track sample and a corresponding annotation intention type are obtained, and a pre-constructed intention classification model is trained by using the training track sample and the annotation intention type to obtain a trained intention classification model, so as to ensure the recognition premise of the subsequent question intention; secondly, the historical behavior data of the target user are collected and subjected to track classification to obtain the historical track category of the target user, so that the behavior characteristics of the target user can be known, and the accuracy of subsequent problem intention type identification can be guaranteed; furthermore, the embodiment of the invention can recognize the final intention type of the current question by receiving the current question input by the target user and utilizing the trained intention classification model according to the historical track category, so that the behavior characteristics of the target user can be known, and the accuracy of subsequent question intention type recognition can be ensured. Therefore, the problem intention intelligent analysis method, the problem intention intelligent analysis device, the electronic equipment and the computer-readable storage medium provided by the embodiment of the invention can improve the problem intention identification accuracy.
Drawings
Fig. 1 is a schematic flowchart of an intelligent problem intention analysis method according to an embodiment of the present invention;
FIG. 2 is a block diagram of an intelligent analysis device for problem intention according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device implementing an intelligent problem intention analysis method according to an embodiment of the present invention;
the implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The embodiment of the invention provides an intelligent analysis method for problem intentions. The execution subject of the intelligent analysis method for the problem intention includes, but is not limited to, at least one of electronic devices, such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present invention. In other words, the intelligent analysis method of the problem intention may be performed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Fig. 1 is a schematic flow chart of an intelligent analysis method for problem intentions according to an embodiment of the present invention. In an embodiment of the present invention, the intelligent analysis method for the problem intention includes:
s1, obtaining a training track sample and a corresponding annotation intention type, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model.
In the embodiment of the present invention, the training track sample refers to training data for performing a subsequent intention classification model, which is generated based on different business scenarios, for example, in the financial field, the training track sample includes data of insurance, fund, stock, and the like, in the medical field, the training track sample includes data of departments, diseases, medical staff, and the like, and in the mall order field, the training track sample includes data of orders, after sales, logistics, and the like. Further, the annotation intention type refers to a data intention type of the training track sample, for example, for a training track sample of a product order, the annotation intention type may be product risk consultation, product purchase path consultation, recharge path consultation, or the like.
Further, in an optional embodiment of the present invention, the training track sample may be obtained by querying an enterprise background database or downloading from a professional website, and the annotation intent type may be implemented by using a similarity matching algorithm, that is, the training track sample is obtained by matching the training track sample with a preset intent type set, where the preset intent type set is a data set obtained by summarizing pre-collected intent types, and the similarity matching algorithm includes a cosine similarity algorithm. It should be further noted that, in the present invention, the training trajectory sample corresponds to one or more types of labeling intents, so as to ensure the model recognition capability in the subsequent model training process.
Further, in an embodiment of the present invention, the pre-constructed intention classification model includes a BERT classification model, which is used for implementing intelligent classification of intention types of questions. As an embodiment of the present invention, the training a pre-constructed intention classification model by using the training track sample and the labeled intention type to obtain a trained intention classification model includes: performing feature extraction on the training track sample by using a feature extraction layer in the pre-constructed intention classification model to obtain a feature vector of the training track sample, performing intention classification on the feature vector by using an intention recognition layer in the pre-constructed intention classification model to obtain a predicted intention type of the training track sample, calculating loss values of the predicted intention type and the labeling intention type by using a loss function in the pre-constructed intention classification model, and if the loss value is greater than a preset threshold value, adjusting model parameters in the pre-constructed intention classification model, and returning to execute the step of performing feature extraction on the training track sample by using a feature extraction layer in the pre-constructed intention classification model, and if the loss value is not greater than the preset threshold value, obtaining the trained intention classification model.
Further, in an optional embodiment of the present invention, the feature extraction of the training track samples is implemented by a convolution kernel in the feature extraction layer, and the intention classification of the feature vectors is implemented by an activation function in the intention identification layer, such as a softmax function.
Further, in an optional embodiment of the present invention, the loss function includes:
wherein L(s) represents a loss value, sjRepresenting the difference between the prediction intention type and the annotation intention type, k representing the number of training track samples, yiDenotes the ith type of predicted intent, y'iIndicating the ith annotation intention type.
Further, in an optional embodiment of the present invention, the preset threshold may be set to 0.1, and may also be set according to an actual service scenario, and the model parameters in the pre-constructed intent classification model may be implemented by a gradient descent algorithm, such as a random gradient descent algorithm.
S2, collecting historical behavior data of the target user, and carrying out track classification on the historical behavior data to obtain the historical track category of the target user.
In the embodiment of the invention, the target user refers to a user needing problem intention type identification, the historical behavior data refers to data browsed by the target user in a page, such as user access data, user stay time, user page user operation data and the like, and behavior characteristics of the target user can be known based on the acquisition of the historical behavior data, so that the accuracy of subsequent problem intention type identification can be guaranteed.
As an embodiment of the present invention, the collecting historical behavior data of the target user includes: and detecting historical behavior events of the target user in an application program, responding to the historical behavior events, recording historical event characteristics and historical user characteristics of the historical behavior events by using a pre-constructed buried point frame, and generating historical behavior data according to the historical event characteristics and the historical user characteristics.
The application program is a program for improving data access of a user, the detection of the historical behavior event can be realized through an event trigger button which is preset in the application program, the event trigger button can be compiled through a JavaScript scripting language, the pre-constructed embedded point frame comprises a Flutter frame, and the event attribute refers to event data clicked by the user in the application program, such as click time, click objects, click times and the like.
Further, in order to ensure privacy and security of the historical behavior data, the historical behavior data may also be stored in a blockchain node.
Further, the history behavior data is subjected to trajectory classification, so as to determine a history access trajectory on the application program corresponding to the target user according to the collected history behavior data, for example, if the user accesses a login page and enters an account page, then a certain item page is opened on the account page, and a purchase button is clicked to enter a purchase page, then the history access trajectory of the history behavior data may be the login page- > account page- > item page- > purchase page.
As an embodiment of the present invention, the performing track classification on the historical behavior data to obtain a historical track category of the target user includes: and detecting the behavior track of the historical behavior data, identifying the track characteristics of the behavior track, matching the track characteristics with track types in a preset track type library, and taking the track type successfully matched as the type of the behavior track to obtain the historical track type of the target user.
The behavior track refers to a browsing track of a corresponding target user in an application program when the historical behavior data is generated, the track characteristics refer to attribute dimensions such as time and page positions used for representing the behavior track, and the preset track category refers to a category set which marks different track characteristics in advance.
Further, in an optional embodiment of the present invention, the behavior trace of the historical behavior data is implemented by using an automated script, the automated script may be implemented by using a script language, the trace feature of the behavior trace is identified by using an information gain algorithm, and the trace feature is matched with a trace category in a preset trace category library by using a similarity algorithm, such as a cosine similarity algorithm.
And S3, receiving the current question input by the target user, and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
In the embodiment of the present invention, the current question refers to data of the current consulting intention category of the target user, which is generated based on different user requirements, for example, how the current question of the user a is a market of the fund, and the current question of the user B is a future upgrade condition of the fund. Furthermore, according to the historical track category, the final intention type of the current problem is identified by using the trained intention classification model, so that the result of intention classification of the current problem by the trained intention classification model is corrected by combining the historical behavior track of the target user, and the intention classification accuracy of the current problem is guaranteed.
In an embodiment of the present invention, the identifying the final intention type of the current question by using the trained intention classification model according to the historical track category includes: and detecting a first intention type of the current question and an intention type probability corresponding to the first intention type by using the trained intention classification model, selecting a second intention type of the current question from the historical track category, and determining a final intention type of the current question from the first intention type according to the second intention type and the intention type probability.
Wherein the intention type probability refers to an intention type prediction probability for detecting the current question through the trained intention classification model.
Further, in an optional embodiment of the present invention, the selecting the second intention type of the current question from the historical track category includes: and identifying the current track of the current question, matching the current track with the historical tracks corresponding to the historical track categories, and taking the category corresponding to the historical tracks which are successfully matched as a second intention type of the current question.
Illustratively, detecting the first intent type of the current question and its corresponding intent type probability by the intent detection model comprises: product risk consultation (60%), product purchase consultation (55%) and recharge path consultation (10%), selecting a second intention type of the current problem from the historical track category as 'product purchase consultation', and generating a final intention type of the current problem as 'product purchase consultation' according to the second intention type and the intention type probability.
It can be seen that, in the embodiment of the present invention, a training track sample and a corresponding annotation intention type are obtained, and a pre-constructed intention classification model is trained by using the training track sample and the annotation intention type to obtain a trained intention classification model, so as to ensure the recognition premise of the subsequent question intention; secondly, the historical behavior data of the target user are collected and subjected to track classification to obtain the historical track category of the target user, so that the behavior characteristics of the target user can be known, and the accuracy of subsequent problem intention type identification can be guaranteed; furthermore, the embodiment of the invention can recognize the final intention type of the current question by receiving the current question input by the target user and utilizing the trained intention classification model according to the historical track category, so that the behavior characteristics of the target user can be known, and the accuracy of subsequent question intention type recognition can be ensured. Therefore, the problem intention intelligent analysis method provided by the embodiment of the invention can improve the problem intention identification accuracy.
FIG. 2 is a functional block diagram of an intelligent analyzer according to the present invention.
The intelligent analysis device 100 according to the present invention may be installed in an electronic device. According to the implemented functions, the intelligent analysis device for question intentions may include a classification model training module 101, a data trajectory classification module 102, and an intention type identification module 103. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and which are stored in a memory of the electronic device.
In the present embodiment, the functions of the respective modules/units are as follows:
the classification model training module 101 is configured to obtain a training track sample and a corresponding annotation intention type thereof, and train a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model;
the data track classification module 102 is configured to collect historical behavior data of a target user, perform track classification on the historical behavior data, and obtain a historical track class of the target user;
The intention type identification module 103 is configured to receive the current question input by the target user, and identify a final intention type of the current question according to the historical track category by using the trained intention classification model.
In detail, the modules in the intelligent analysis device 100 for problem intentions in the embodiment of the present invention adopt the same technical means as the intelligent analysis method for problem intentions described in fig. 1, and can produce the same technical effects, and are not described herein again.
Fig. 3 is a schematic structural diagram of an electronic device 1 for implementing the intelligent problem analysis method according to the present invention.
The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as an intelligent analysis program for problem intention, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device 1, connects various components of the electronic device 1 by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., an intelligent analysis program for executing a problem intention, etc.) stored in the memory 11 and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, and the like. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, e.g. a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of intelligent analysis programs for problem intentions, etc., but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device 1 and other devices, and includes a network interface and an employee interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices 1. The employee interface may be a Display (Display), an input unit, such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visual staff interface, among other things.
Fig. 3 shows only the electronic device 1 with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the embodiments described are for illustrative purposes only and that the scope of the claimed invention is not limited to this configuration.
The intelligent analysis program of the problem intention stored in the memory 11 of the electronic device 1 is a combination of a plurality of computer programs, which when run in the processor 10, can realize:
acquiring a training track sample and a corresponding annotation intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model;
Acquiring historical behavior data of a target user, and carrying out track classification on the historical behavior data to obtain a historical track category of the target user;
and receiving the current question input by the target user, and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-volatile computer-readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device 1, may implement:
Acquiring a training track sample and a corresponding annotation intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model;
acquiring historical behavior data of a target user, and carrying out track classification on the historical behavior data to obtain a historical track category of the target user;
and receiving the current question input by the target user, and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention 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, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the invention 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.
Furthermore, it will be obvious that the term "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not to denote any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method for intelligent analysis of problem intent, the method comprising:
Acquiring a training track sample and a corresponding annotation intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model;
acquiring historical behavior data of a target user, and carrying out track classification on the historical behavior data to obtain a historical track category of the target user;
and receiving the current question input by the target user, and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
2. The intelligent analysis method for question intention according to claim 1, wherein the training of the pre-constructed intention classification model by using the training track samples and the annotation intention types to obtain the trained intention classification model comprises:
performing feature extraction on the training track sample by using a feature extraction layer in the pre-constructed intention classification model to obtain a feature vector of the training track sample;
performing intention classification on the feature vectors by using an intention recognition layer in the pre-constructed intention classification model to obtain a predicted intention type of the training track sample;
Calculating loss values of the prediction intention type and the annotation intention type by using a loss function in the pre-constructed intention classification model;
if the loss value is larger than a preset threshold value, returning to execute the step of performing feature extraction on the training track sample by using a feature extraction layer in the pre-constructed intention classification model after adjusting the model parameters in the pre-constructed intention classification model;
and if the loss value is not greater than the preset threshold value, obtaining a trained intention classification model.
3. The intelligent analysis method of question intent according to claim 2, characterized in that said loss function comprises:
wherein L(s) represents a loss value, sjRepresenting the difference between the predicted intention type and the labeled intention type, k representing the number of training track samples, yiDenotes the ith type of predictive intent, y'iAnd the ith annotation intention type is represented.
4. The intelligent analysis method for question intent according to claim 1, wherein said collecting historical behavior data of the target user comprises:
detecting historical behavior events of the target user in an application program;
responding to the historical behavior event, and recording historical event characteristics and historical user characteristics of the historical behavior event by using a pre-constructed buried point frame;
And generating historical behavior data according to the historical event characteristics and the historical user characteristics.
5. The intelligent analysis method for question intention according to claim 1, wherein said performing track classification on said historical behavior data to obtain a historical track category of said target user comprises:
detecting a behavior track of the historical behavior data, and identifying track characteristics of the behavior track;
and matching the track characteristics with track categories in a preset track category library, and taking the track categories successfully matched as the categories of the behavior tracks to obtain the historical track categories of the target user.
6. The intelligent analysis method for question intention according to any one of claims 1 to 5, characterized in that said identifying a final intention type of the current question by using the trained intention classification model according to the historical track category comprises:
detecting a first intention type of the current question and an intention type probability corresponding to the first intention type by using the trained intention classification model, and selecting a second intention type of the current question from the historical track category;
determining a final intent type of the current question from the first intent type based on the second intent type and the intent type probability.
7. The intelligent analysis method of question intent according to claim 6, wherein said selecting a second intent type for said current question from said historical track category comprises:
identifying a current trajectory of the current question;
and matching the current track with the historical tracks corresponding to the historical track categories, and taking the categories corresponding to the historical tracks which are successfully matched as second intention types of the current problems.
8. An intelligent analysis apparatus of a question intention, the apparatus comprising:
the classification model training module is used for acquiring a training track sample and a corresponding annotation intention type thereof, and training a pre-constructed intention classification model by using the training track sample and the annotation intention type to obtain a trained intention classification model;
the data track classification module is used for collecting historical behavior data of a target user and carrying out track classification on the historical behavior data to obtain a historical track class of the target user;
and the intention type identification module is used for receiving the current question input by the target user and identifying the final intention type of the current question by using the trained intention classification model according to the historical track category.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a method of intelligent analysis of problem intentions as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, implements the intelligent analysis method of question intention of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210446926.8A CN114756669A (en) | 2022-04-26 | 2022-04-26 | Intelligent analysis method and device for problem intention, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210446926.8A CN114756669A (en) | 2022-04-26 | 2022-04-26 | Intelligent analysis method and device for problem intention, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114756669A true CN114756669A (en) | 2022-07-15 |
Family
ID=82333870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210446926.8A Pending CN114756669A (en) | 2022-04-26 | 2022-04-26 | Intelligent analysis method and device for problem intention, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114756669A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116244278A (en) * | 2023-05-11 | 2023-06-09 | 江苏博纳汇数字智能科技有限公司 | Warehouse data supervision system and method based on artificial intelligence |
| CN116777947A (en) * | 2023-06-21 | 2023-09-19 | 上海汉朔信息科技有限公司 | User track recognition prediction method and device and electronic equipment |
-
2022
- 2022-04-26 CN CN202210446926.8A patent/CN114756669A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116244278A (en) * | 2023-05-11 | 2023-06-09 | 江苏博纳汇数字智能科技有限公司 | Warehouse data supervision system and method based on artificial intelligence |
| CN116777947A (en) * | 2023-06-21 | 2023-09-19 | 上海汉朔信息科技有限公司 | User track recognition prediction method and device and electronic equipment |
| CN116777947B (en) * | 2023-06-21 | 2024-02-13 | 上海汉朔信息科技有限公司 | User track recognition prediction method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115002200B (en) | Message pushing method, device, equipment and storage medium based on user portrait | |
| CN114756669A (en) | Intelligent analysis method and device for problem intention, electronic equipment and storage medium | |
| CN113704429A (en) | Semi-supervised learning-based intention identification method, device, equipment and medium | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN115081538A (en) | Customer relationship identification method, device, equipment and medium based on machine learning | |
| CN113706249B (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN114416939A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114220536A (en) | Disease analysis method, device, equipment and storage medium based on machine learning | |
| CN116843481A (en) | Knowledge graph analysis method, device, equipment and storage medium | |
| CN114708073B (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium | |
| CN115203364A (en) | Software fault feedback processing method, device, equipment and readable storage medium | |
| CN114662005A (en) | Message pushing method, device, equipment and storage medium for user behavior track | |
| CN115221323A (en) | Cold start processing method, device, equipment and medium based on intention recognition model | |
| CN115525761A (en) | Method, device, equipment and storage medium for article keyword screening category | |
| CN114996386A (en) | Business role identification method, device, equipment and storage medium | |
| CN115510219A (en) | Method and device for recommending dialogs, electronic equipment and storage medium | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN114219367A (en) | User scoring method, device, equipment and storage medium | |
| CN114610854A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114595321A (en) | Question marking method and device, electronic equipment and storage medium | |
| CN114518993A (en) | System performance monitoring method, device, equipment and medium based on business characteristics | |
| CN113312482A (en) | Question classification method and device, electronic equipment and readable storage medium | |
| CN115392206B (en) | Method, device and equipment for quickly querying data based on WPS/EXCEL and storage medium | |
| CN113486145B (en) | User consultation reply method, device, equipment and medium based on network node |
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 |