CN116012128A - User experience analysis method and device for bank counter business product - Google Patents
User experience analysis method and device for bank counter business product Download PDFInfo
- Publication number
- CN116012128A CN116012128A CN202310156975.2A CN202310156975A CN116012128A CN 116012128 A CN116012128 A CN 116012128A CN 202310156975 A CN202310156975 A CN 202310156975A CN 116012128 A CN116012128 A CN 116012128A
- Authority
- CN
- China
- Prior art keywords
- emotion
- business
- text
- product
- bank counter
- 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
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user experience analysis method and a device of a bank counter business product, which relate to the technical field of natural language processing, and the method comprises the following steps: respectively forming a business product word stock and a business product function word stock; word segmentation is carried out on emotion tendentiousness texts of the bank counter business to be judged; matching the word segmentation result with keywords in a business product word stock and a business product function word stock, and determining a bank counter business product or function pointed by the text according to the matched keywords; carrying out emotion tendentiousness classification on the emotion tendentiousness text by using a text emotion classification model to obtain an affiliated emotion category; the user experience of the counter business product or function is analyzed based on emotion classification. According to the method and the device, the specific product or function corresponding to the text can be accurately positioned, emotion analysis is carried out on the specific product or function, the analysis result can describe the local experience of the user in a finer granularity, the continuous improvement of the product and the function is facilitated, and the labor cost of traditional evaluation collection can be saved.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to a user experience analysis method and device of a bank counter business product.
Background
The banking counter business is very popular, details in actual situations of the same business are different, and different processing flows are needed to solve the business problem. In the current products facing counter business, the evaluation of the product functions is generally collected by a special demand operation team facing a certain number of basic colleagues and comprehensively evaluated by combining feedback channels specially provided in the products. While related art has also emerged in the art that utilizes artificial intelligence algorithms for user experience analysis, the data sources involved to be analyzed are all predetermined to belong to a certain product. Therefore, the following technical defects exist in the user experience analysis of the bank counter business product:
the complexity of bank counter business causes that an artificial intelligence algorithm cannot accurately position products and specific functions aimed at by a data source to be analyzed, and manual collection and evaluation opinions consume labor cost and resource cost, so that sustainable collection work cannot be developed.
Disclosure of Invention
In view of the foregoing, the present invention provides a method and apparatus for analyzing a user experience of a banking counter business product to solve at least one of the above-mentioned problems.
In order to achieve the above purpose, the present invention adopts the following scheme:
according to a first aspect of the present invention, there is provided a method of user experience analysis of a banking counter service product, the method comprising: forming a business product word stock and a business product function word stock respectively based on the bank counter business product information and the business product function information; word segmentation is carried out on emotion tendentiousness texts of the bank counter business to be judged; matching the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain matching keywords, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be determined according to the matching keywords; carrying out emotion tendency classification on the emotion tendency text of the bank counter business to be judged by using a text emotion classification model to obtain an emotion category to which the emotion tendency text of the bank counter business to be judged belongs; and analyzing user use experience corresponding to the bank counter business product or function based on the emotion type.
According to a second aspect of the present invention there is provided a user experience analysis device for a banking counter service product, the device comprising: the word stock generating unit is used for respectively forming a business product word stock and a business product function word stock based on the bank counter business product information and the business product function information; the word segmentation unit is used for segmenting the emotion tendentiousness text of the bank counter business to be judged; the matching unit is used for matching the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain matching keywords, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be judged according to the matching keywords; the emotion classification unit is used for classifying emotion tendencies of the emotion tendentioustexts of the bank counter business to be judged by using a text emotion classification model to obtain emotion categories of the emotion tendentioustexts of the bank counter business to be judged; and the experience analysis unit is used for analyzing the user use experience corresponding to the bank counter business product or function based on the emotion type.
According to a third aspect of the present invention there is provided an electronic device comprising a memory, a processor and a computer program stored on said memory and executable on said processor, the processor implementing the steps of the above method when executing said computer program.
According to a fourth aspect of the present invention there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
According to a fifth aspect of the present invention there is provided a computer program product comprising computer programs/instructions which when executed by a processor implement the steps of the above method.
According to the technical scheme, the user experience analysis method and the user experience analysis device for the bank counter business product firstly generate the bank counter business product word stock and the business product function word stock, then divide words of texts to be judged, match the business product word stock and the business product function word stock, and obtain keywords related to products or functions, so that specific products or functions corresponding to the texts to be judged can be accurately positioned when the complicated counter business products are faced, emotion analysis is carried out on the specific products or functions, and the obtained analysis results can be used for describing the local experience of users to the bank counter business products in a finer granularity mode, and are beneficial to continuous improvement of the products and the functions. In addition, the invention can save the labor cost of traditional evaluation collection.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a flow chart of a method for analyzing user experience of a banking counter business product according to an embodiment of the present application;
fig. 2 is a schematic diagram of a training flow of a text emotion classification model according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for analyzing a user experience of a banking counter business product according to another embodiment of the present application;
FIG. 4 is a schematic diagram of a training process of an entity recognition model according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a method for analyzing a user experience of a banking counter business product provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a user experience analysis device for a banking counter business product according to an embodiment of the present application;
fig. 7 is a schematic block diagram of a system configuration of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
In order to solve the problems that in the prior art, continuous collection work cannot be carried out for the bank counter business type-oriented products and the evaluation of functions thereof, and comprehensive evaluation on the functions of the products cannot be obtained due to limited quantity of basic staff facing in the evaluation collection process, the invention provides a user experience analysis method of the bank counter business products, which is used for continuously and effectively analyzing preference trends of users in the process of using the bank counter business products and providing better data support for the product function requirement design stage.
As shown in fig. 1, which is a flow chart of a method for analyzing user experience of a banking counter service product according to an embodiment of the present application, it should be noted that an analysis data source for the present invention is data such as questions, answers, comments, replies, etc. of short texts exchanged between employees in a basic service support platform in a bank, and the method includes the following steps:
step S101: and forming a business product word stock and a business product function word stock respectively based on the bank counter business product information and the business product function information.
In this embodiment, the service product information and the service product function information may refer to a service product name and a service product function name, so that related names of banking counter service products used in banks may be carded and summarized to form a service product word stock, and related function names of banking counter service products used in banks may be carded and summarized to form a service product function word stock.
Step S102: and carrying out word segmentation on the emotion tendentiousness text of the bank counter business to be judged.
The emotion tendentiousness text of the bank counter business to be judged is information such as questions, answers, comments, replies and the like of short texts communicated among employees collected from a basic service support platform in the bank in a designated period. For the emotion tendentiousness text, natural language processing technology (Natural Language Processing, NLP) may be used to segment the text, such as product or function segmentation extraction using a joeba segmentation tool. Specifically, the business product word stock and the business product function word stock can be used as a custom dictionary of a bargain word segmentation tool, and then the bargain word segmentation processing is carried out on the emotion tendentioustext of the bank counter business to be judged, wherein the specific operation processing process comprises the following formula:
Segm text ＝jieba(text)
wherein Segm text Representing the result of text segmentation; text represents the emotion tendentiousness text of the bank counter business to be judged.
Step S103: and matching the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain matching keywords, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be determined according to the matching keywords. Because the product names and the function names are stored in the business product word stock and the business product function word stock, the product or the function pointed by the text can be determined by matching keywords.
This step can be expressed as:
res segm ＝Match(Segm text ,Lib)
wherein res segm Representation word segmentation recognitionThe bank counter of the bank counter is specific to business products or functions, and Lib represents a business product word stock and a business product function word stock.
Step S104: and carrying out emotion tendency classification on the emotion tendency text of the bank counter business to be judged by using a text emotion classification model to obtain the emotion category to which the emotion tendency text of the bank counter business to be judged belongs. It should be noted that this step may be performed simultaneously with step S102 and step S103, and this step is used as the analysis basis of step S105 together with the result of step S103.
Preferably, as shown in fig. 2, the text emotion classification model is trained by:
step S1041: and acquiring related information of different products or functions. The relevant information here refers to historical question, answer, comment and reply data of various products and functions in the bank. It should be noted that, the collected historical data may be the historical data of the basic service support platform in the bank or the historical data of the user or the bank staff on the internet.
Step S1042: labeling the related information with emotion tendentiousness labels to obtain an emotion classification data set.
The emotion tendentiousness labels herein may be labels such as "better experience", "normal experience", "poor experience", etc., and of course, the present application may also label more other emotion labels, which is not limited in this embodiment of the present invention.
Step S1043: and training by using the emotion classification data set to obtain a text emotion classification model. The text emotion classification model can be obtained by training by using the existing deep learning method, so that the text emotion classification model can process the input text so as to output the emotion classification of the user.
Step S105: and analyzing user use experience corresponding to the bank counter business product or function based on the emotion type.
According to the technical scheme, the user experience analysis method of the bank counter business product provided by the invention firstly generates the bank counter business product word stock and the business product function word stock, then performs word segmentation on the text to be judged, and matches the business product word stock and the business product function word stock to obtain the keywords related to the product or the function, so that the specific product or the function corresponding to the text to be judged can be accurately positioned when facing the complex counter business product, and then emotion analysis is performed on the specific product or the function, and the obtained analysis result can be used for describing the local experience of the user on the bank counter business product in a finer granularity, thereby being beneficial to the continuous improvement of the product and the function. In addition, the invention can save the labor cost of traditional evaluation collection.
Fig. 3 is a flow chart of a method for analyzing user experience of a banking counter business product according to another embodiment of the present application, the method includes the following steps:
step S301: and forming a business product word stock and a business product function word stock respectively based on the bank counter business product information and the business product function information.
Step S302: and carrying out word segmentation on the emotion tendentiousness text of the bank counter business to be judged.
Step S303: and matching the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain matching keywords.
Step S304: and carrying out text entity recognition on the emotion tendentiousness text of the bank counter business to be judged by using the entity recognition model, and outputting recognition keywords corresponding to the emotion tendentiousness text of the bank counter business to be judged.
If the business products or functions are located only by using the word segmentation matching method, the context semantic information of the related content in the whole text content can be ignored, so that the situation that the part of the text content is possibly analyzed in error can be caused. Aiming at the problem, the embodiment forms a large number of entity data sets to train out an entity recognition model for entity recognition by collecting a large number of text information related to products or functions and the products or functions corresponding to the text information.
Preferably, as shown in fig. 4, the entity recognition model is trained by:
step S3041: text information related to a banking counter service product or function is acquired.
In the embodiment, a large amount of evaluation information of products or functions used by users can be acquired from the Internet or a bank internal platform, text contents of the products or functions definitely designated by the users are screened out, and millions of comment text information are collected.
Step S3042: and labeling the text information with an entity label, and labeling the specific product or function pointed by the text information to form an entity identification data set.
Step S3043: and training the entity recognition model by utilizing the entity recognition data set to obtain the entity recognition model. The entity recognition model adopted in the embodiment may be a Mengzi network model, the pre-trained Mengzi model may be used as an initialized network parameter, the learning rate and the iteration number in the training process are set, and preferably, the learning rate in the embodiment may be set to be 1×10e -5 The iteration times can be set to be 5 times, and a model with the best classification result in the verification set in the training process is saved as an entity identification model.
The text content text of emotion tendentiousness of the bank counter business product or function to be judged is obtained by using the trained entity recognition model Mengzi, and the process of text entity recognition can be expressed as the following formula:
res ner ＝Mengzi(text)
wherein res ner Representing the specific business products or functions of the bank counter identified by the entity identification model.
Step S305: and carrying out fusion analysis on the matching keywords and the identification keywords by utilizing a voting method to determine the bank counter business products or functions pointed by the emotion tendentiousness text of the bank counter business to be determined.
This step can be expressed by the following formula:
res cont ＝Vote(res segm ,res ner )
res cont representing the bank counter business products or functional results obtained by voting.
The voting method refers to that when the two methods of step S303 and step S304 match or identify the corresponding business product or function word, the business product or function is determined, that is, when the matching keyword and the identifying keyword are the same, the bank counter business product or function pointed to by the emotion tendentiousness text of the bank counter business to be determined is determined based on the same keyword.
Therefore, in the method, the entity recognition is performed by introducing the entity recognition model, so that the keywords can be matched with the context semantic relation of the whole text, and then fusion analysis is performed with the word segmentation recognition result, so that the product or function is more accurately recognized finally.
Step S306: and carrying out emotion tendency classification on the emotion tendency text of the bank counter business to be judged by using a text emotion classification model to obtain the emotion category to which the emotion tendency text of the bank counter business to be judged belongs.
Step S307: and analyzing user use experience corresponding to the bank counter business product or function based on the emotion type.
The principle of each step can be represented by fig. 5, as shown in fig. 5, the emotion tendentiousness text of the banking counter business to be determined (i.e. the text content described by the user of the banking counter business in fig. 5) is respectively subjected to the operations of positioning the product or function descriptor and classifying the emotion tendentiousness, and then fusion analysis is performed on the two operation results to obtain the emotion analysis result of the user for the product or function. The method comprises the steps of carrying out text product or function description positioning by combining two parts of results, outputting emotion analysis results by using a text emotion classification model, and finally obtaining the emotion analysis results of the accurately positioned text to be judged by combining.
According to the technical scheme, the user experience analysis method of the bank counter business product provided by the invention firstly generates the bank counter business product word stock and the business product function word stock, then performs word segmentation on the text to be judged, and matches the business product word stock and the business product function word stock to obtain the keywords related to the product or the function, so that the specific product or the function corresponding to the text to be judged can be accurately positioned when facing the complex counter business product, and then emotion analysis is performed on the specific product or the function, and the obtained analysis result can be used for describing the local experience of the user on the bank counter business product in a finer granularity, thereby being beneficial to the continuous improvement of the product and the function and saving the labor cost of traditional evaluation collection. In addition, the method for matching the word segmentation not only locates service products or functions, but also considers the context semantic information of related contents in the whole text content, and performs entity identification on the text to be determined by using an entity identification model, so that the possible error analysis condition of the text content to be determined is effectively reduced, and the product and functions to which the text to be determined belongs are located more accurately.
Fig. 6 is a schematic structural diagram of a user experience analysis device for a banking counter business product according to an embodiment of the present application, where the device includes: a thesaurus generation unit 610, a word segmentation unit 620, a matching unit 630, an emotion classification unit 640, and an experience analysis unit 650. The word stock generating unit 610 is respectively connected with the word segmentation unit 620 and the matching unit 630, the matching unit 630 is also respectively connected with the word segmentation unit 620 and the experience analysis unit 650, and the emotion classification unit 640 is connected with the experience analysis unit 650.
The thesaurus generating unit 610 is configured to form a business product thesaurus and a business product function thesaurus based on the bank counter business product information and the business product function information, respectively.
The word segmentation unit 620 is configured to segment the emotion tendentioustext of the banking counter service to be determined.
The matching unit 630 is configured to match the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain a matching keyword, and determine, according to the matching keyword, a banking counter business product or function to which the emotion tendency text of the banking counter business to be determined points.
The emotion classification unit 640 is configured to classify emotion tendentiousness of the emotion tendentiousness text of the banking counter to be determined by using a text emotion classification model, so as to obtain an emotion category to which the emotion tendentiousness text of the banking counter to be determined belongs.
The experience analysis unit 650 is configured to analyze user usage experiences corresponding to banking counter business products or functions based on the emotion types.
Preferably, the apparatus of this embodiment further includes: and the entity identification unit is used for carrying out text entity identification on the emotion tendentiousness text of the bank counter business to be judged by utilizing the entity identification model, and outputting identification keywords corresponding to the emotion tendentiousness text of the bank counter business to be judged. The matching unit 630 determines, according to the matching keyword, a banking counter service product or function to which the emotion tendentiousness text of the banking counter service to be determined points further includes: and carrying out fusion analysis on the matching keywords and the identification keywords by utilizing a voting method to determine the bank counter business products or functions pointed by the emotion tendentiousness text of the bank counter business to be determined.
Preferably, the matching unit 630 of the present embodiment performs fusion analysis on the matching keyword and the identifying keyword by using a voting method, so as to determine a banking counter service product or function pointed to by the emotion tendentiousness text of the banking counter service to be determined, where the banking counter service product or function includes: and carrying out fusion analysis on the matching keywords and the identification keywords by using a voting method, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be determined based on the same keywords when the matching keywords and the identification keywords are the same.
Preferably, the entity recognition model is obtained through training in the following manner: acquiring text information related to a bank counter business product or function; labeling the text information with entity labels, and labeling specific products or functions pointed by the text information to form an entity identification data set; and training the entity recognition model by utilizing the entity recognition data set to obtain the entity recognition model.
Preferably, the entity recognition model is a Mengzi network model, and training the entity recognition model by using the entity recognition data set to obtain the entity recognition model includes: the training rate and the iteration number in the training process are set by using the pre-trained Mengzi model as the initialized network parameters, and preferably, the training rate can be set to be 1×10e in the embodiment -5 The iteration times can be set to be 5 times, and a model with the best classification result in the verification set in the training process is saved as an entity identification model.
Preferably, the text emotion classification model is obtained by training in the following manner: acquiring related information of different products or functions; labeling the related information with emotion tendentiousness labels to obtain an emotion classification data set; and training by using the emotion classification data set to obtain a text emotion classification model.
According to the technical scheme, the user experience analysis device of the bank counter business product provided by the invention firstly generates the bank counter business product word stock and the business product function word stock, then performs word segmentation on the text to be judged, and matches the business product word stock and the business product function word stock to obtain the keywords related to the product or the function, so that the specific product or the function corresponding to the text to be judged can be accurately positioned when facing the complex counter business product, and then emotion analysis is performed on the specific product or the function, and the obtained analysis result can be used for describing the local experience of the user on the bank counter business product in a finer granularity, thereby being beneficial to the continuous improvement of the product and the function. In addition, the invention can save the labor cost of traditional evaluation collection.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the method when executing the program.
Embodiments of the present invention also provide a computer program product comprising a computer program/instruction which, when executed by a processor, performs the steps of the above method.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program for executing the method.
As shown in fig. 7, the electronic device 600 may further include: a communication module 110, an input unit 120, an audio processor 130, a display 160, a power supply 170. It is noted that the electronic device 600 need not include all of the components shown in fig. 7; in addition, the electronic device 600 may further include components not shown in fig. 7, to which reference is made to the related art.
As shown in fig. 7, the central processor 100, sometimes also referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 100 receives inputs and controls the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 100 can execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides an input to the central processor 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, or the like. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. Memory 140 may also be some other type of device. Memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage 142, the application/function storage 142 for storing application programs and function programs or a flow for executing operations of the electronic device 600 by the central processor 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. A communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and to receive audio input from the microphone 132 to implement usual telecommunication functions. The audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 130 is also coupled to the central processor 100 so that sound can be recorded locally through the microphone 132 and so that sound stored locally can be played through the speaker 131.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method for analyzing user experience of a banking counter service product, the method comprising:
forming a business product word stock and a business product function word stock respectively based on the bank counter business product information and the business product function information;
word segmentation is carried out on emotion tendentiousness texts of the bank counter business to be judged;
matching the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain matching keywords, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be determined according to the matching keywords;
carrying out emotion tendency classification on the emotion tendency text of the bank counter business to be judged by using a text emotion classification model to obtain an emotion category to which the emotion tendency text of the bank counter business to be judged belongs;
and analyzing user use experience corresponding to the bank counter business product or function based on the emotion type.
2. The method of claim 1, further comprising: performing text entity recognition on the emotion tendentiousness text of the bank counter business to be judged by using an entity recognition model, and outputting recognition keywords corresponding to the emotion tendentiousness text of the bank counter business to be judged;
the determining the bank counter service product or function pointed by the emotion tendentiousness text of the bank counter service to be determined according to the matching keyword further comprises:
and carrying out fusion analysis on the matching keywords and the identification keywords by utilizing a voting method to determine the bank counter business products or functions pointed by the emotion tendentiousness text of the bank counter business to be determined.
3. The method for analyzing the user experience of a banking side business product according to claim 2, wherein the step of performing fusion analysis on the matching keyword and the recognition keyword by voting to determine the banking side business product or function to which the emotion tendentiousness text of the banking side business to be determined points includes:
and carrying out fusion analysis on the matching keywords and the identification keywords by using a voting method, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be determined based on the same keywords when the matching keywords and the identification keywords are the same.
4. The method for analyzing the user experience of a banking product of claim 2, wherein the entity identification model is trained by:
acquiring text information related to a bank counter business product or function;
labeling the text information with entity labels, and labeling specific products or functions pointed by the text information to form an entity identification data set;
and training the entity recognition model by utilizing the entity recognition data set to obtain the entity recognition model.
5. The method for analyzing a user experience of a banking product of claim 4, wherein the entity identification model is a Mengzi network model, and wherein training the entity identification model using the entity identification data set to obtain the entity identification model includes: and setting the learning rate and the iteration times in the training process by using the pre-trained Mengzi model as an initialized network parameter, and storing a model with the best classification result in the verification set in the training process as an entity recognition model.
6. The method for analyzing the user experience of a banking side business product according to claim 1, wherein the word segmentation of emotion tendentiousness text of the banking side business to be determined includes:
and taking the business product word stock and the business product function word stock as custom dictionaries of a bargain word segmentation tool, and then carrying out bargain word segmentation processing on emotion tendentioustexts of the bank counter business to be judged.
7. The method for analyzing the user experience of a banking product of claim 1, wherein the text emotion classification model is trained by:
acquiring related information of different products or functions;
labeling the related information with emotion tendentiousness labels to obtain an emotion classification data set;
and training by using the emotion classification data set to obtain a text emotion classification model.
8. A user experience analysis device for a banking counter service product, the device comprising:
the word stock generating unit is used for respectively forming a business product word stock and a business product function word stock based on the bank counter business product information and the business product function information;
the word segmentation unit is used for segmenting the emotion tendentiousness text of the bank counter business to be judged;
the matching unit is used for matching the word segmentation result with keywords in the business product word stock and the business product function word stock to obtain matching keywords, and determining a bank counter business product or function pointed by the emotion tendency text of the bank counter business to be judged according to the matching keywords;
the emotion classification unit is used for classifying emotion tendencies of the emotion tendentioustexts of the bank counter business to be judged by using a text emotion classification model to obtain emotion categories of the emotion tendentioustexts of the bank counter business to be judged;
and the experience analysis unit is used for analyzing the user use experience corresponding to the bank counter business product or function based on the emotion type.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310156975.2A CN116012128A (en) | 2023-02-13 | 2023-02-13 | User experience analysis method and device for bank counter business product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310156975.2A CN116012128A (en) | 2023-02-13 | 2023-02-13 | User experience analysis method and device for bank counter business product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116012128A true CN116012128A (en) | 2023-04-25 |
Family
ID=86032126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310156975.2A Pending CN116012128A (en) | 2023-02-13 | 2023-02-13 | User experience analysis method and device for bank counter business product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116012128A (en) |
-
2023
- 2023-02-13 CN CN202310156975.2A patent/CN116012128A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6799574B2 (en) | Method and device for determining satisfaction with voice dialogue | |
| CN112346567B (en) | Virtual interaction model generation method and device based on AI (Artificial Intelligence) and computer equipment | |
| CN111708869B (en) | Processing method and device for man-machine conversation | |
| WO2009158581A2 (en) | System and method for spoken topic or criterion recognition in digital media and contextual advertising | |
| CN108305618B (en) | Voice acquisition and search method, intelligent pen, search terminal and storage medium | |
| CN111651497B (en) | User tag mining method and device, storage medium and electronic equipment | |
| JP2011066794A (en) | Meeting management device, and meeting management method | |
| Kaushik et al. | Automatic sentiment detection in naturalistic audio | |
| CN111653274B (en) | Wake-up word recognition method, device and storage medium | |
| CN113095204B (en) | Double-recording data quality inspection method, device and system | |
| CN111581347B (en) | Sentence similarity matching method and device | |
| CN111666408A (en) | Method and device for screening and displaying important clauses | |
| CN114782110A (en) | Demand mining method and system based on logistic regression two-classification and JMTS | |
| CN116012128A (en) | User experience analysis method and device for bank counter business product | |
| CN112035666B (en) | Text robot cross-validation optimization method and device | |
| CN113868271A (en) | Method and device for updating knowledge base of intelligent customer service, electronic equipment and storage medium | |
| CN113868415A (en) | Knowledge base generation method and device, storage medium and electronic equipment | |
| CN112784607A (en) | Client intention identification method and device | |
| CN111428018B (en) | Intelligent question-answering method and device | |
| CN114373448B (en) | Topic detection method and device, electronic equipment and storage medium | |
| CN117992601B (en) | Document generation method and device based on artificial intelligence | |
| CN113140210B (en) | Audio correction method, device, electronic equipment and storage medium | |
| CN112786023B (en) | Mark model construction method and voice broadcasting system | |
| KR102185784B1 (en) | Method and apparatus for searching sound data | |
| CN115564481A (en) | Customer comment information analysis method and device |
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 |