CN111444729A - Information processing method, device, equipment and readable storage medium - Google Patents
Information processing method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111444729A CN111444729A CN202010139018.5A CN202010139018A CN111444729A CN 111444729 A CN111444729 A CN 111444729A CN 202010139018 A CN202010139018 A CN 202010139018A CN 111444729 A CN111444729 A CN 111444729A
- Authority
- CN
- China
- Prior art keywords
- preset
- question
- information
- client
- dialect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 41
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000003062 neural network model Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 15
- 238000003066 decision tree Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000011438 cord wood Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of big data, and discloses an information processing method, device, equipment and a computer readable storage medium, wherein the method comprises the following steps: displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information; detecting an operation instruction of a user based on a client icon, and acquiring preset client information corresponding to the client icon; determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text; simulating a preset customer to send a question according to a building block type question model, and acquiring dialect information answered by the user to the question; based on the preset dialect information corresponding to the question, the similarity between the dialect information and the preset dialect information is determined, and the target dialogue scene of the preset client is accurately predicted, so that the generated building block type question model can simulate the client to perform dialect training on the user more truly, and the dialect level of the user is improved.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for processing information.
Background
The technique of speaking in professional occasions and situations is called dialoging for short. For modern service industry, dialogies are language skills which can obviously improve the service communication capacity and level of business personnel and enable consumers to feel satisfied and comfortable to service organizations and personnel. With the popularization and application of internet finance, the online help seeking amount of users is larger and larger. As a last ring to solve the user problem, business personnel play an important role. However, in the process of communication between the business personnel and the client, aiming at the same question put forward by the client, different responses of the business personnel bring different feelings to the client, and the language expression of the business personnel is more effective. Business personnel need to receive surgery training and assessment before facing real customers. At present, business personnel mainly learn the speech by participating in on-site training or buying books and self-learning by video, however, the above mode has the defect that a single person cannot exercise, conversation flow is linear, namely, you go down one sentence by one sentence according to time lines like writing a script, and the business personnel cannot be simulated really, and the similarity between the speech of the business personnel and the preset speech is obtained.
Disclosure of Invention
The present application mainly aims to provide an information processing method, apparatus, device and computer readable storage medium for user's speech training to improve the effect of the user's speech training.
In a first aspect, the present application provides an information processing method, including:
displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information;
detecting an operation instruction of a user based on the client icon, and acquiring preset client information corresponding to the client icon;
determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text;
simulating a preset customer to send a question according to the building block type question model, and acquiring the dialect information of the user for answering the question;
and determining the similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the question.
In a second aspect, the present application also provides an information processing apparatus comprising:
the display module is used for displaying an operation interface, the operation interface comprises client icons, and different client icons correspond to different preset client information;
the first acquisition module is used for detecting an operation instruction of a user based on the client icon and acquiring preset client information corresponding to the operation instruction;
the generating module is used for determining a question and answer text corresponding to the preset customer information based on the preset customer information and generating a corresponding building block type question model according to the question and answer text;
the second acquisition module is used for simulating a preset client to send a question according to the building block type question model and acquiring the dialect information of the answer of the user to the question;
and the determining module is used for determining the similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the dialect information.
In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the method of information processing as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the steps of the method of information processing as described above.
The application provides a method, a device, equipment and a computer readable storage medium for information processing, which comprises the following steps: displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information; detecting an operation instruction of a user based on the client icon, and acquiring preset client information corresponding to the client icon; determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text; simulating a preset customer to send a question according to the building block type question model, and acquiring the dialect information of the user for answering the question; and determining the similarity between the voice skill information and the preset voice skill information based on the preset voice skill information corresponding to the question, and accurately predicting a target dialogue scene of a preset client through preset client information, so that the generated building block type question model can simulate the client to perform voice skill training on the user more truly, can grade each voice skill, and improves the voice skill level of the user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of an information processing method according to an embodiment of the present application;
FIG. 2 is a flow diagram illustrating sub-steps of a method of information processing of FIG. 1;
FIG. 3 is a flow diagram illustrating sub-steps of a method of information processing of FIG. 1;
FIG. 4 is a flow diagram illustrating sub-steps of a method of information processing of FIG. 1;
FIG. 5 is a flow chart illustrating another method for processing information according to an embodiment of the present disclosure;
fig. 6 is a schematic block diagram of an information processing apparatus according to an embodiment of the present application;
fig. 7 is a schematic block diagram of another information processing apparatus provided in an embodiment of the present application;
fig. 8 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The embodiment of the application provides an information processing method, an information processing device, computer equipment and a computer readable storage medium. The information processing method can be applied to terminal equipment, and the terminal equipment can be electronic equipment such as a mobile phone, a tablet computer, a notebook computer and a desktop computer.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating an information processing method according to an embodiment of the present disclosure.
As shown in fig. 1, the information processing method includes steps S100 to S500.
And S100, displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information.
And displaying an operation interface, wherein the operation interface displays client icons, different client icons correspond to different preset client information, and the types of the client icons include an explanatory icon, an interactive icon, a quasi-materialized icon, an application icon and the like, which is not limited. A plurality of client icons are arranged on an operation interface in advance, each client icon is provided with corresponding client information, and each client icon is provided with a client identifier.
And step S200, detecting an operation instruction of a user based on the client icon, and acquiring preset client information corresponding to the client icon.
And detecting an operation instruction of a user on the client icon in real time on an operation interface, and acquiring preset client information corresponding to the client icon. The operation instructions comprise click operation instructions, touch operation instructions and the like, wherein the preset client information is dimension information of different professions, ages, conversation scenes and the like which is obtained in advance, and the obtained dimension information is set as the client information.
In an embodiment, specifically referring to fig. 2, step S200 includes: substeps 201 to substep S202.
And the substep S201 is to detect the operation interface in real time, receive a click command sent by a user through the operation interface and determine a client icon corresponding to the click command.
Detecting an operation interface in real time, detecting a click command sent by a user on the operation interface, and determining a client icon corresponding to the click command. An example is that a user clicks an operation interface by a mouse to send a click instruction, and based on the fact that the operation interface receives the click instruction sent by the user clicking the operation interface, the client icon corresponding to the click instruction on the operation interface is determined.
And a substep S202, acquiring preset customer information corresponding to the customer identification based on the customer identification of the customer icon.
And acquiring preset customer information corresponding to the customer identification based on the customer identification of the customer icon. For example, a plurality of different client icons are displayed on the operation interface, the terminal detects a click command of a user in real time through the operation interface, when the click command of the user is detected, the client icon corresponding to the click command is determined, the client identifier of the client icon is obtained, each client identifier corresponds to different preset client information, and information of different occupation, age and income conditions is collected in advance to serve as the preset client information. And acquiring preset customer information corresponding to the customer identification based on the customer identification.
An example is that, after the client identifier is obtained, a preset database is accessed, the client identifier is used as a search condition to search in the preset database, and preset client information corresponding to the client identifier in a preset data path is obtained. And when the client identifier is the association code, accessing the preset database, acquiring information corresponding to the association code in the preset database, and taking the acquired information as the preset client information corresponding to the client identifier.
And S300, determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text.
The method comprises the steps of obtaining a conversation scene in preset customer information, and reading a question and answer text related to the conversation scene in a preset database through the conversation scene, wherein the question and answer text comprises a fixed-line conversation scene and a multi-line conversation scene. Each question has only one corresponding word, and the question-answering text comprises more than one fixed word conversation scene. And each question comprises more than one corresponding dialect, and the question and answer text comprises more than one multi-dialect dialog scene. The fixed phone technology scene and the multi-phone technology dialogue scene are combined according to the mode of stacking building blocks to generate a flow chart, and the generated flow chart is used as a building block type questioning model.
In an embodiment, specifically referring to fig. 3, step S300 includes: substeps S301 to substep S304.
And a substep S301 of analyzing the preset client information and reading the age, the gender and the occupation in the preset client information.
And acquiring preset client information and analyzing the preset client information. As an example, the terminal parses preset customer information, the preset customer information includes name, age, gender, occupation, income, family members, and the like, and reads the age, gender, and occupation from the preset customer information.
The substep S302, based on age, gender and occupation, determines a target dialog scenario related to age, gender and occupation.
And reading the age, the gender and the occupation in the preset client information, and determining a target conversation scene related to the age, the gender and the occupation according to the age, the gender and the occupation. As an example, the dialog scenes of different client consultation are related to age, sex and occupation, for example, female, whose age is under 30 years old, and generally consults the elderly for medical insurance, infant care, etc. according to the characteristics of occupation. Men, over the age of 35 years, consult business insurance, vehicle insurance, etc., depending on the nature of the occupation. The method comprises the steps of collecting clients and conversation scenes of different ages, professions and sexes in advance, and generating a neural network model for predicting the target conversation scene of the client in a machine learning mode and the like.
And a substep S303, acquiring a preset fixed question and answer text and a preset intention question and answer text based on the target conversation scene, and a question and answer text related to the target conversation scene in the preset fixed question and answer text and the preset intention question and answer text.
And acquiring a preset fixed question-answer text and a preset intention question-answer text and a question-answer text associated with the target dialogue scene in the preset fixed question-answer text and the preset intention question-answer text when the target dialogue scene corresponding to the preset client information is determined. The preset fixed question-answer text and the preset intention question-answer text comprise a plurality of dialogue scenes, wherein one dialogue scene in the preset fixed question-answer text comprises a question and corresponding dialect information, namely the question and the corresponding dialect information are used as the question-answer text. The preset intention question-answer text comprises a plurality of dialogue scenes, wherein one dialogue scene in the preset intention question-answer text comprises a question and a plurality of corresponding dialect information, namely the question and the plurality of corresponding dialect information are used as the question-answer text. When the target dialogue scene is obtained, determining keywords in the target dialogue scene, respectively obtaining preset fixed question and answer texts and dialogue scenes containing the keywords in the preset intention question and answer texts, and taking the obtained dialogue scenes as question and answer texts.
And a substep S304, generating a corresponding building block type question model according to the question and answer text.
And when the question and answer texts are obtained, combining the question and answer texts to generate a corresponding building block type question model. An illustrative example is that when the question and answer texts are obtained, the number of the question and answer texts is at least two, a flow chart is generated by the obtained question and answer texts according to a stacking building block mode, and the generated flow chart is used as a building block type question model.
Generating a building block questioning model includes: acquiring association frequency between the questions based on a preset decision tree model; and inserting question and answer texts corresponding to the questions into the nodes of the preset decision tree model according to the association frequency of the questions to generate a corresponding building block type question model.
And when a question and answer text associated with the target conversation scene is obtained, calling a preset decision tree model, and obtaining the association frequency among the questions. By taking the frequency relationship between the questions in the question and answer text as each node of the preset decision tree model, for example, by collecting the association frequency information between each question, comparing the association frequency of the question 2 presented by the customer after the question 1 with 5 times, the association frequency of the question 3 with 3 times, and the like, the association frequency information of each question before the question 1 is also collected. And taking the generated preset decision tree model as a building block type question model corresponding to the training instruction by using the association frequency information between each question as a trunk node to a branch node in the preset decision tree model according to the number of the trunk nodes to the branch nodes.
And S400, simulating a preset client to send a question according to the building block type question model, and acquiring the dialect information of the user for answering the question.
Simulating a preset customer to send a question according to the building block type question model, and acquiring the dialect information answered by the user to the question. The example is that a preset client is simulated to send a question in a building block type question model based on the building block type question model, a user replies corresponding dialect information of the question on an operation interface based on the question, and the user answers the corresponding dialect information of the question based on the operation interface.
And operating the building block type questioning model, and simulating and presetting the questioning corresponding to any node sent by the client through the building block type questioning model. Specifically, a terminal runs a building block type questioning model, preset customers are simulated through the building block type questioning model, and questioning in questioning and answering texts at any nodes of the building block type questioning model is obtained. For example, the terminal runs a building block type questioning model, and a preset customer is simulated to ask a question of the user through the building block type questioning model. Specifically, a building block type question model is operated to simulate a preset customer to train a user, a question at any node is extracted in the operation process of the building block type question model, and the question is used as a first question. And when the terminal detects first language and technology information input by the user to the first question through the operation interface, acquiring the first language and technology information. After the first tactical information is acquired, the building block question model extracts a second question at a next node after the dialogue scene.
And step S500, determining the similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the dialect information.
And when a stop instruction is received, reading preset dialect information corresponding to the question, wherein the preset dialect information is the dialect information corresponding to the question in the question and answer text. When the dialect information and the preset dialect information are acquired, the similarity of the dialect information and the preset dialect information is determined.
As an example, when each preset phonetic information includes a preset keyword and the number of the keywords is 10, it is determined whether the preset keyword is included in the phonetic information. When it is determined that the speech information includes the keyword, it is determined that the number of preset keywords included in the speech information is included. For example, when the dialect information includes 6 preset keywords, it is determined that the similarity between the dialect information and the preset dialect information is 60%, and when the dialect information includes 8 preset keywords, it is determined that the similarity between the dialect information and the preset dialect information is 80%.
In an embodiment, specifically referring to fig. 4, step S500 includes: substeps 501 to substep S502.
And a substep S501, acquiring preset dialect information corresponding to the dialect information, and taking the dialect information and the preset dialect information as input values of a preset twin neural network model.
And when the cordwood questioning model is determined to stop running, acquiring preset dialect information corresponding to the dialect information, calling a preset twin neural network model, and taking the dialect information and the preset dialect information as input values of the twin neural network model. For example, the dialect information and the preset dialect information are used as input layers of the twin neural network by calling a preset twin neural network model.
And a substep S502, determining the similarity between the output tactical information of the preset twin neural network model and the preset tactical information based on the preset twin neural network model.
According to the operation of the preset twin neural network model, the preset dialect information is used as a standard in the operation, and keyword extraction and semantic analysis are carried out through the dialect information and the preset dialect information to obtain the score of the dialect information. The example is that preset twin neural network model dialogue information and preset dialogue information are subjected to keyword extraction and semantic analysis, keywords contained in the dialogue information and semantic similarity between the dialogue information and the preset dialogue information are determined, and similarity between the dialogue information and the preset dialogue information is output.
In this embodiment, the target dialog scenario of the preset client is determined by acquiring the preset client information. The method comprises the steps of generating a building block type question model from a question and answer text associated with a target dialogue scene, simulating a preset client to train a user through the building block type question model, obtaining language and skill information of the user for sending question and answer to the building block type question model, comparing the language and skill information to obtain the similarity between the language and skill information, and accurately predicting the target dialogue scene of the preset client through the preset client information, so that the generated building block type question model more truly simulates the client to train the user to carry out the language and can grade the language every time, and the language and skill level of the user is improved.
Referring to fig. 5, fig. 5 is a flowchart illustrating another information processing method according to an embodiment of the present disclosure.
As shown in fig. 5, the information processing method includes steps S601 to 607.
Step S601, displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information. The operation interface displays client icons, different client icons correspond to different preset client information, and the types of the client icons include an explanatory icon, an interactive icon, a quasi-materialized icon, an application icon and the like, which is not limited. A user is provided with a plurality of client icons in advance on an operation interface of a terminal, each client icon is provided with corresponding client information, and each client icon is provided with a client identifier.
Step S602, detecting an operation instruction of a user based on the client icon, and acquiring preset client information corresponding to the client icon.
And detecting an operation instruction of a user on the client icon in real time on an operation interface, and acquiring preset client information corresponding to the client icon. The operation instructions comprise click operation instructions, touch operation instructions and the like, wherein the preset client information is dimension information of different professions, ages, conversation scenes and the like which is obtained in advance, and the obtained dimension information is set as the client information.
Step S603, determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text.
The method comprises the steps of obtaining a dialogue scene in preset customer information, and reading a question and answer text related to the dialogue scene in a preset database through the dialogue scene, wherein the question and answer text comprises a fixed question and answer text and an intention question and answer text. The fixed question-answer text is a fixed-phone conversation scene, each question only has one corresponding phone, and the fixed question-answer text comprises more than one fixed-phone conversation scene. The intended question-and-answer text is a multi-conversational dialogue scene, each question comprises more than one corresponding conversational language, and the intended question-and-answer text comprises more than one multi-conversational dialogue scene. The fixed question-answering text and the intention question-answering text are combined according to a stacking building block mode to generate a flow chart, and the generated flow chart is used as a building block type question model.
And S604, simulating a preset client to send a question according to the building block type question model, and acquiring the dialect information of the user for answering the question.
Simulating a preset customer to send a question according to the building block type question model, and acquiring the dialect information answered by the user to the question. The example is that a preset client is simulated to send a question in a building block type question model based on the building block type question model, a user replies the corresponding dialect information of the question on an operation interface based on the question, and the terminal acquires the dialect information corresponding to the user answering the question based on the operation interface.
Step S605 determines the similarity between the speech information and the preset speech information based on the preset speech information corresponding to the speech information.
And when a stop instruction is received, reading preset dialect information corresponding to the question, wherein the preset dialect information is the dialect information corresponding to the question in the question and answer text. When the dialect information and the preset dialect information are acquired, the similarity of the dialect information and the preset dialect information is determined. As an example, when each preset phonetic information includes a preset keyword and the number of the keywords is 10, it is determined whether the preset keyword is included in the phonetic information. When it is determined that the speech information includes the keyword, it is determined that the number of preset keywords included in the speech information is included. For example, when the dialect information includes 6 preset keywords, it is determined that the similarity between the dialect information and the preset dialect information is 60%, and when the dialect information includes 8 preset keywords, it is determined that the similarity between the dialect information and the preset dialect information is 80%.
Step S606, if the similarity is smaller than the preset threshold, determining the similar area of the dialogistic information and the preset dialogistic information, and marking the similar area.
And when the preset dialect information and the similarity of the dialect information are acquired, judging whether the similarity is smaller than a preset threshold value. An example is that when the similarity between the preset speech and operation information obtained by the terminal is 60%, if the preset threshold is 80%, if 60% is less than 80%, the similarity between the preset speech and operation information is judged to be less than the preset threshold, and a similar area between the preset speech and operation information is determined. For example, the preset area with the same preset keyword or the area with the same semantic meaning in the language information is a similar area, and the similar area is marked. The marking mode includes the way of thickening, emphasizing or marking the characters in the similar area.
And step S607, writing the questioning, similarity and marked dialect information and preset dialect information into a preset template, and displaying the preset template on an operation interface.
The method comprises the steps of obtaining a preset template, determining the positions of a question, the similarity, the phonetic information and the preset phonetic information in the preset template, respectively writing the question sent by a building block type question model, the similarity of the preset phonetic information and the phonetic information, and the marked phonetic information and the preset phonetic information into corresponding positions, and displaying the questions, the similarity, the phonetic information and the preset phonetic information on an operation interface.
In the embodiment, the terminal acquires preset customer information, determines a question and answer text corresponding to the preset customer information, generates a corresponding building block type question model according to the question and answer text, simulating a preset customer to send a question according to the building block type question model, acquiring the dialect information corresponding to the question and the similarity between the dialect information and the preset dialect information, if the similarity is smaller than a preset threshold value, determining the similar area of the dialect information and the preset dialect information, marking the similar area, writing the question, the similarity, the marked dialect information and the preset dialect information into a preset template, displaying on an operation interface, the method comprises the steps of generating a building block type question model through different preset customer information to simulate a customer to send a question, comparing the dialect information of the customer with the preset dialect information, and displaying a comparison result on an operation interface to improve the dialect level of the customer.
Referring to fig. 6, fig. 6 is a schematic block diagram of an information processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 6, the information processing apparatus 700 includes: the device comprises a display module 701, a first acquisition module 702, a generation module 703, a second acquisition module 704 and a determination module 705.
The display module 701 is configured to display an operation interface, where the operation interface includes client icons, and different client icons correspond to different preset client information.
A first obtaining module 702, configured to detect an operation instruction of a user based on a client icon, and obtain preset client information corresponding to the operation instruction.
The first obtaining module 702 is further specifically configured to:
detecting an operation interface in real time, receiving a click command sent by a user through the operation interface, and determining a client icon corresponding to the click command;
and acquiring preset customer information corresponding to the customer identification based on the customer identification of the customer icon.
The generating module 703 is configured to determine, based on the preset client information, a question-answer text corresponding to the preset client information, and generate a corresponding building block type question model according to the question-answer text.
Wherein, the generating module 703 is further specifically configured to:
analyzing preset client information, and reading age, gender and occupation in the preset client information;
determining a target dialogue scene related to the age, the gender and the occupation based on the age, the gender and the occupation;
acquiring a preset fixed question-answer text and a preset intention question-answer text based on a target conversation scene, and a question-answer text related to the target conversation scene in the preset fixed question-answer text and the preset intention question-answer text;
and generating a corresponding building block type question model according to the question and answer text.
Wherein, the generating module 703 is further specifically configured to:
acquiring association frequency between the questions based on a preset decision tree model;
and inserting question and answer texts corresponding to the questions into the nodes of the preset decision tree model according to the association frequency between the questions to generate corresponding building block type question models.
And a second obtaining module 704, configured to simulate a preset customer to send a question according to the building block question model, and obtain the conversational information of the user for answering the question.
The second obtaining module 704 is further specifically configured to:
and operating the building block type questioning model, and simulating and presetting a questioning corresponding to any node sent by the client through the building block type questioning model.
The determining module 705 is configured to determine similarity between the phonetic information and preset phonetic information based on preset phonetic information corresponding to the phonetic information.
Wherein, the determining module 705 is further specifically configured to:
acquiring preset dialect information corresponding to the question, and taking the dialect information and the preset dialect information as input values of a preset twin neural network model;
and determining the similarity between the output dialect information of the preset twin neural network model and the preset dialect information based on the preset twin neural network model.
It should be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the apparatus and each module and unit described above may refer to corresponding processes in the foregoing information processing method embodiment, and are not described herein again.
Referring to fig. 7, fig. 7 is a schematic block diagram of another information processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 7, the information processing apparatus 800 includes: a display module 801, a first acquisition module 802, a generation module 803, a second acquisition module 804, a determination module 805, a marking module 806, and a display module 807.
The display module 801 is configured to display an operation interface, where the operation interface includes client icons, and different client icons correspond to different preset client information.
The first obtaining module 802 is configured to detect an operation instruction of a user based on a client icon, and obtain preset client information corresponding to the operation instruction.
The first obtaining module 802 is further specifically configured to:
detecting an operation interface in real time, receiving a click command sent by a user through the operation interface, and determining a client icon corresponding to the click command;
and acquiring preset customer information corresponding to the customer identification based on the customer identification of the customer icon.
And the generating module 803 is configured to determine, based on the preset client information, a question and answer text corresponding to the preset client information, and generate a corresponding building block type question model according to the question and answer text.
Wherein, the generating module 803 is further specifically configured to:
analyzing preset client information, and reading age, gender and occupation in the preset client information;
determining a target dialogue scene related to the age, the gender and the occupation based on the age, the gender and the occupation;
acquiring a preset fixed question-answer text and a preset intention question-answer text based on a target conversation scene, and a question-answer text related to the target conversation scene in the preset fixed question-answer text and the preset intention question-answer text;
and generating a corresponding building block type question model according to the question and answer text.
Wherein, the generating module 803 is further specifically configured to:
acquiring association frequency between the questions based on a preset decision tree model;
and inserting question and answer texts corresponding to the questions into the nodes of the preset decision tree model according to the association frequency between the questions to generate corresponding building block type question models.
And the second obtaining module 804 is used for simulating a preset customer to send a question according to the building block type question model, and obtaining the dialect information of the answer of the user to the question.
The second obtaining module 804 is further specifically configured to:
and operating the building block type questioning model, and simulating and presetting a questioning corresponding to any node sent by the client through the building block type questioning model.
A determining module 805, configured to determine similarity between the language information and preset language information based on preset language information corresponding to the language information.
Wherein, the determining module 805 is further specifically configured to:
acquiring preset dialect information corresponding to the question, and taking the dialect information and the preset dialect information as input values of a preset twin neural network model;
and determining the similarity between the output dialect information of the preset twin neural network model and the preset dialect information based on the preset twin neural network model.
And the marking module 806 is configured to obtain preset dialect information corresponding to the question, and use the dialect information and the preset dialect information as input values of the preset twin neural network model.
A display module 807 for determining similarity between the preset twin neural network model output tactical information and the preset tactical information based on the preset twin neural network model.
It should be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the apparatus and each module and unit described above may refer to corresponding processes in the foregoing information processing method embodiment, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program, which can be run on a computer device as shown in fig. 8.
Referring to fig. 8, fig. 8 is a schematic block diagram illustrating a structure of a computer device according to an embodiment of the present disclosure. The computer device may be a terminal.
As shown in fig. 8, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program comprises program instructions which, when executed, cause a processor to perform any of the methods of information processing.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for running a computer program in the non-volatile storage medium, which, when executed by the processor, causes the processor to perform any of the methods of information processing.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
and displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information.
And detecting an operation instruction of a user based on the client icon, and acquiring preset client information corresponding to the operation instruction.
And determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text.
Simulating a preset customer to send a question according to the building block type question model, and acquiring the dialect information of the user for answering the question.
And determining the similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the dialect information.
In one embodiment, the processor, when implementing preset dialect information corresponding to the dialect information and determining similarity between the dialect information and the preset dialect information, is configured to implement:
acquiring preset dialect information corresponding to the question, and taking the dialect information and the preset dialect information as input values of a preset twin neural network model;
and determining the similarity between the output dialect information of the preset twin neural network model and the preset dialect information based on the preset twin neural network model.
In one embodiment, the processor, when enabled to determine a similarity of the preset twin neural network model output tactical information and the preset tactical information, is configured to enable:
if the similarity is smaller than a preset threshold value, determining similar areas of the dialect information and the preset dialect information, and marking the similar areas;
and writing the questioning, the similarity and the marked dialect information and the preset dialect information into a preset template and displaying the preset template on an operation interface.
In one embodiment, when the processor is used for detecting an operation instruction of a user based on a client icon and acquiring preset client information corresponding to the operation instruction, the processor is used for realizing that:
detecting an operation interface in real time, receiving a click command sent by a user through the operation interface, and determining a client icon corresponding to the click command;
and acquiring preset customer information corresponding to the customer identification based on the customer identification of the customer icon.
In one embodiment, the processor is configured to determine a question and answer text corresponding to preset customer information based on the preset customer information, and generate a corresponding building block type question model according to the question and answer text, and implement:
analyzing preset client information, and reading age, gender and occupation in the preset client information;
determining a target dialogue scene related to the age, the gender and the occupation based on the age, the gender and the occupation;
acquiring a preset fixed question-answer text and a preset intention question-answer text based on a target conversation scene, and a question-answer text related to the target conversation scene in the preset fixed question-answer text and the preset intention question-answer text;
and generating a corresponding building block type question model according to the question and answer text.
In one embodiment, the processor, when implementing generation of a corresponding building block type question model according to the question and answer text, is configured to implement:
acquiring association frequency between the questions based on a preset decision tree model;
and inserting question and answer texts corresponding to the questions into the nodes of the preset decision tree model according to the association frequency between the questions to generate corresponding building block type question models.
In one embodiment, the processor, when implementing simulating preset customer sending questions according to a building block type question model, is configured to implement:
and operating the building block type questioning model, and simulating and presetting a questioning corresponding to any node sent by the client through the building block type questioning model.
Embodiments of the present application also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and a method implemented when the program instructions are executed may refer to various embodiments of the method for information processing in the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method of information processing, comprising:
displaying an operation interface, wherein the operation interface comprises client icons, and different client icons correspond to different preset client information;
detecting an operation instruction of a user based on the client icon, and acquiring preset client information corresponding to the client icon;
determining a question and answer text corresponding to the preset customer information based on the preset customer information, and generating a corresponding building block type question model according to the question and answer text;
simulating a preset customer to send a question according to the building block type question model, and acquiring the dialect information of the user for answering the question;
and determining the similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the question.
2. The method of information processing according to claim 1, wherein the determining a similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the question includes:
acquiring preset dialect information corresponding to the question, and taking the dialect information and the preset dialect information as input values of a preset twin neural network model;
and determining the similarity of the preset twin neural network model to the output of the dialogistic information and the preset dialogistic information based on the preset twin neural network model.
3. The information processing method of claim 2, wherein after the determining that the preset twin neural network model outputs the similarity of the tactical information and the preset tactical information, further comprising:
if the similarity is smaller than a preset threshold value, determining a similar area of the dialect information and the preset dialect information, and marking the similar area;
writing the questioning, the similarity and the marked dialect information and the preset dialect information into a preset template, and displaying the written preset template on the operation interface.
4. The information processing method of claim 1, wherein the detecting that the user acquires the preset client information corresponding to the client icon based on the operation instruction of the client icon comprises:
detecting the operation interface in real time, receiving a click command sent by a user through the operation interface, and determining a client icon corresponding to the click command;
and acquiring preset customer information corresponding to the customer identification based on the customer identification of the customer icon.
5. The information processing method of claim 1, wherein the determining a question and answer text corresponding to the preset customer information based on the preset customer information and generating a corresponding building block type question model according to the question and answer text comprises:
analyzing the preset client information, and reading the age, the gender and the occupation in the preset client information;
determining a target dialog scenario related to the age, gender and occupation based on the age, gender and occupation;
acquiring a preset fixed question-answer text and a preset intention question-answer text based on the target conversation scene, and a question-answer text related to the target conversation scene in the preset fixed question-answer text and the preset intention question-answer text;
and generating a corresponding building block type question model according to the question and answer text.
6. The information processing method according to claim 5, wherein the question-and-answer texts are at least two and include a question and corresponding dialect information; generating a corresponding building block type question model according to the question and answer text, wherein the building block type question model comprises the following steps:
acquiring association frequency between the questions based on a preset decision tree model;
and inserting the question and answer text corresponding to the question into the nodes of the preset decision tree model according to the association frequency between the questions to generate a corresponding building block type question model.
7. The information processing method of claim 1, wherein simulating a pre-set customer to send a question according to the building block question model comprises:
and operating the building block type questioning model, and simulating and presetting a questioning corresponding to any node sent by a client through the building block type questioning model.
8. An information processing apparatus characterized by comprising:
the display module is used for displaying an operation interface, the operation interface comprises client icons, and different client icons correspond to different preset client information;
the first acquisition module is used for detecting an operation instruction of a user based on the client icon and acquiring preset client information corresponding to the operation instruction;
the generating module is used for determining a question and answer text corresponding to the preset customer information based on the preset customer information and generating a corresponding building block type question model according to the question and answer text;
the second acquisition module is used for simulating a preset client to send a question according to the building block type question model and acquiring the dialect information of the answer of the user to the question;
and the determining module is used for determining the similarity between the dialect information and the preset dialect information based on the preset dialect information corresponding to the dialect information.
9. A computer arrangement, characterized in that the computer arrangement comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, carries out the steps of the method of information processing according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, wherein the computer program, when executed by a processor, implements the steps of the method of information processing according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139018.5A CN111444729B (en) | 2020-03-02 | 2020-03-02 | Information processing method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139018.5A CN111444729B (en) | 2020-03-02 | 2020-03-02 | Information processing method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111444729A true CN111444729A (en) | 2020-07-24 |
| CN111444729B CN111444729B (en) | 2024-05-24 |
Family
ID=71652847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010139018.5A Active CN111444729B (en) | 2020-03-02 | 2020-03-02 | Information processing method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111444729B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112069304A (en) * | 2020-09-29 | 2020-12-11 | 龙马智芯（珠海横琴）科技有限公司 | Question answering method, device, server and storage medium for insurance business |
| CN113724036A (en) * | 2021-07-29 | 2021-11-30 | 阿里巴巴（中国）有限公司 | Method and electronic equipment for providing question consultation service |
| WO2022110637A1 (en) * | 2020-11-27 | 2022-06-02 | 平安科技（深圳）有限公司 | Question and answer dialog evaluation method and apparatus, device, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015032157A (en) * | 2013-08-02 | 2015-02-16 | 株式会社日立国際電気 | Customer service support system |
| CN107368948A (en) * | 2017-06-21 | 2017-11-21 | 厦门快商通科技股份有限公司 | A kind of simulation test checking system for customer service post |
| CN108280095A (en) * | 2017-01-06 | 2018-07-13 | 南通使爱智能科技有限公司 | Intelligent virtual customer service system |
| CN110647621A (en) * | 2019-09-27 | 2020-01-03 | 支付宝(杭州)信息技术有限公司 | Method and device for selecting dialogs in robot customer service guide conversation |
| CN110765244A (en) * | 2019-09-18 | 2020-02-07 | 平安科技（深圳）有限公司 | Method and device for acquiring answering, computer equipment and storage medium |
-
2020
- 2020-03-02 CN CN202010139018.5A patent/CN111444729B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015032157A (en) * | 2013-08-02 | 2015-02-16 | 株式会社日立国際電気 | Customer service support system |
| CN108280095A (en) * | 2017-01-06 | 2018-07-13 | 南通使爱智能科技有限公司 | Intelligent virtual customer service system |
| CN107368948A (en) * | 2017-06-21 | 2017-11-21 | 厦门快商通科技股份有限公司 | A kind of simulation test checking system for customer service post |
| CN110765244A (en) * | 2019-09-18 | 2020-02-07 | 平安科技（深圳）有限公司 | Method and device for acquiring answering, computer equipment and storage medium |
| CN110647621A (en) * | 2019-09-27 | 2020-01-03 | 支付宝(杭州)信息技术有限公司 | Method and device for selecting dialogs in robot customer service guide conversation |
Non-Patent Citations (1)
| Title |
|---|
| 陶晓峰;吕朋朋;缪平;娄保东;: "基于深度神经网络的工单采集模型研究", 自动化与仪器仪表, no. 02 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112069304A (en) * | 2020-09-29 | 2020-12-11 | 龙马智芯（珠海横琴）科技有限公司 | Question answering method, device, server and storage medium for insurance business |
| WO2022110637A1 (en) * | 2020-11-27 | 2022-06-02 | 平安科技（深圳）有限公司 | Question and answer dialog evaluation method and apparatus, device, and storage medium |
| CN113724036A (en) * | 2021-07-29 | 2021-11-30 | 阿里巴巴（中国）有限公司 | Method and electronic equipment for providing question consultation service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111444729B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Latham et al. | A conversational intelligent tutoring system to automatically predict learning styles | |
| 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 | |
| CN107357849B (en) | Interaction method and device based on test application | |
| CN109471915B (en) | Text evaluation method, device and equipment and readable storage medium | |
| Goldenthal et al. | Not all AI are equal: Exploring the accessibility of AI-mediated communication technology | |
| CN111444729B (en) | Information processing method, device, equipment and readable storage medium | |
| WO2020199600A1 (en) | Sentiment polarity analysis method and related device | |
| Chen et al. | Forecasting reading anxiety for promoting English-language reading performance based on reading annotation behavior | |
| CN109801527B (en) | Method and apparatus for outputting information | |
| CN111177307A (en) | Test scheme and system based on semantic understanding similarity threshold configuration | |
| Roll et al. | Artificial intelligence in education | |
| Yassin et al. | SeerahBot: An Arabic chatbot about prophet’s biography | |
| CN110852071A (en) | Knowledge point detection method, device, equipment and readable storage medium | |
| Maicher et al. | Artificial intelligence in virtual standardized patients: combining natural language understanding and rule based dialogue management to improve conversational fidelity | |
| CN110263346B (en) | Semantic analysis method based on small sample learning, electronic equipment and storage medium | |
| CN111046674A (en) | Semantic understanding method and device, electronic equipment and storage medium | |
| CN113312463B (en) | Intelligent evaluation method and device for voice questions and answers, computer equipment and storage medium | |
| CN111883111B (en) | Method, device, computer equipment and readable storage medium for processing speech training | |
| CN111680148B (en) | Method and device for intelligently responding to question of user | |
| CN114841157A (en) | Online interaction method, system, equipment and storage medium based on data analysis | |
| CN110895924B (en) | Method and device for reading document content aloud, electronic equipment and readable storage medium | |
| CN115408500A (en) | Question-answer consistency evaluation method and device, electronic equipment and medium | |
| CN116069850A (en) | Classroom activity courseware manufacturing method and device, storage medium and electronic equipment | |
| CN113704452A (en) | Data recommendation method, device, equipment and medium based on Bert model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |