CN111444729B - Information processing method, device, equipment and readable storage medium - Google Patents
Information processing method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111444729B CN111444729B CN202010139018.5A CN202010139018A CN111444729B CN 111444729 B CN111444729 B CN 111444729B CN 202010139018 A CN202010139018 A CN 202010139018A CN 111444729 B CN111444729 B CN 111444729B
- Authority
- CN
- China
- Prior art keywords
- preset
- question
- information
- client
- speaking
- 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.)
- Active
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 40
- 238000003672 processing method Methods 0.000 title abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims description 26
- 238000003066 decision tree Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004088 simulation Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 8
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 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
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
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; based on preset client information, determining a question-answer text corresponding to the preset client information, and generating a corresponding building block question model according to the question-answer text; simulating a preset client to send a question according to a building block question model, and acquiring speaking and operation information of a user for answering the question; based on the preset voice information corresponding to the question, the similarity between the voice information and the preset voice information is determined, and the target dialogue scene of the preset client is accurately predicted, so that the generated building block question model simulates the client to perform voice training on the user more truly, and the voice 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 information processing.
Background
Professional occasions, techniques of situational speaking, simply speaking. For modern service industry, the speech technology is a language skill which can obviously improve the service communication capacity and level of business personnel and enable consumers to feel satisfied and comfortable with service institutions and personnel. With popularization and application of internet finance, the help seeking amount on the user line is larger and larger. As a final ring to solve the user problem, business personnel play an important role. However, in the process of communicating with the client, the feelings brought by different answers of the service personnel to the client are different aiming at the same problem which is presented by the client, so that the expression of the conversation of the service personnel is more effective. Before facing a real customer, business personnel need to receive speech training and assessment. To master and proficiency use these specialized services, at present, the business staff mainly study the services by taking part in on-site training or buying books and video self-learning, however, the above-mentioned methods have the defect that a single person cannot practice, the dialogue flow is linear, i.e. you go down by time line like writing a script, and the consumer cannot be truly simulated, and the similarity of the business staff's speech and the preset speech can not be obtained.
Disclosure of Invention
The application mainly aims to provide an information processing method, device, equipment and computer readable storage medium, which are used for user speaking training so as to improve the effect of the user speaking training.
In a first aspect, the present application provides a method of information processing, the method of information processing comprising the steps of:
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;
based on the preset client information, determining a question-answer text corresponding to the preset client information, and generating a corresponding building block question model according to the question-answer text;
Simulating a preset client to send a question according to the building block question model, and acquiring speaking and operation information of the user for answering the question;
And determining the similarity between the speaking information and the preset speaking information based on the preset speaking information corresponding to the question.
In a second aspect, the present application also provides an information processing apparatus including:
The display module is used for displaying an operation interface, wherein 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 generation module is used for determining a question-answer text corresponding to the preset client information based on the preset client information and generating a corresponding building block question model according to the question-answer text;
The second acquisition module is used for simulating a preset client to send a question according to the building block question model and acquiring speaking and operation information of the user for answering the question;
And the determining module is used for determining the similarity between the conversation information and the preset conversation information based on the preset conversation information corresponding to the conversation 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 also provides a computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of a method of information processing as described above.
The application provides an information processing method, a device, equipment and a computer readable storage medium, comprising 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; based on the preset client information, determining a question-answer text corresponding to the preset client information, and generating a corresponding building block question model according to the question-answer text; simulating a preset client to send a question according to the building block question model, and acquiring speaking and operation information of the user for answering the question; based on the preset speaking information corresponding to the question, the similarity between the speaking information and the preset speaking information is determined, the target dialogue scene of the preset client is accurately predicted through the preset client information, and therefore the generated building block question model simulates the client to conduct speaking training on the user more truly, scores each speaking, and improves the speaking level of the user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for processing information according to an embodiment of the present application;
FIG. 2 is a flow chart of sub-steps of the method of information processing in FIG. 1;
FIG. 3 is a flow chart of sub-steps of the method of information processing in FIG. 1;
FIG. 4 is a flow chart of sub-steps of the method of information processing in FIG. 1;
FIG. 5 is a flowchart of another information processing method according to an embodiment of the present application;
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 by an embodiment of the present application;
fig. 8 is a schematic block diagram of a computer device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
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 mobile phones, tablet computers, notebook computers, desktop computers and the like.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart of a method for processing information according to an embodiment of the application.
As shown in fig. 1, the information processing method includes steps S100 to S500.
Step 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 comprise explanatory icons, interactive icons, pseudo-materialized icons, application icons and the like, and are not limited to the explanation icons, the interactive icons, the pseudo-materialized icons, the application icons and the like. The method comprises the steps that a plurality of client icons are arranged on an operation interface in advance, corresponding client information is set on each client icon, and each client icon is provided with a client identifier.
Step 200, 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 clicking operation instructions, touching operation instructions and the like, wherein client information is preset to obtain dimension information of different professions, ages, dialogue scenes and the like in advance, and the obtained dimension information is set as client information.
In one embodiment, referring specifically to fig. 2, step S200 includes: substep S201 to substep S202.
And step S201, 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.
Detecting an operation interface in real time, detecting a click command sent by a user at the operation interface, and determining a client icon corresponding to the click command. The example is that a user clicks an operation interface in a mouse mode to send a click command, and based on the operation interface receiving the click command sent by the user clicking the operation interface, the client icon corresponding to the click command on the operation interface is determined.
And step S202, based on the client identifier of the client icon, acquiring preset client information corresponding to the client identifier.
Based on the client identifier of the client icon, preset client information corresponding to the client identifier is acquired. 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 identifications of the client icons are obtained, each client identification 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. Based on the client identification, obtaining preset client information corresponding to the client identification.
In an exemplary case, when a 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. When the client identifier is the association code, accessing a preset database, acquiring information corresponding to the association code in the preset database, and taking the acquired information as preset client information corresponding to the client identifier.
Step S300, based on preset client information, determining a question-answer text corresponding to the preset client information, and generating a corresponding building block question model according to the question-answer text.
And acquiring a dialogue scene in the preset client information, and reading a question-answer text associated with the dialogue scene in a preset database through the dialogue scene, wherein the question-answer text comprises a fixed-line dialogue scene and a multi-line dialogue scene. The fixed-phone conversation scene is that each question has only one corresponding phone, and the question-answering text comprises more than one fixed-phone conversation scene. The multi-phone conversation scene, each question includes more than one corresponding phone, and the question-answer text includes more than one multi-phone conversation scene. The fixed phone operation scene and the multi-phone operation dialogue scene are combined in a building block stacking mode to generate a flow chart, and the generated flow chart is used as a building block questioning model.
In one embodiment, referring specifically to fig. 3, step S300 includes: substep S301 to substep S304.
And step 301, analyzing the preset client information, and reading the age, sex and occupation in the preset client information.
And acquiring preset client information, and analyzing the preset client information. As an example, the terminal parses preset client information including name, age, gender, occupation, income situation, family members, etc., and reads the age, gender, and occupation in the preset client information.
Substep S302, determining a target dialogue scenario related to age, gender and occupation based on age, gender and occupation.
And reading the age, the gender and the occupation in the preset client information, and determining the target dialogue scene related to the age, the gender and the occupation according to the age, the gender and the occupation. As an example, the dialogue scenario of different customer consultations is related to age, gender and occupation, for example, women, ages under 30 years, and according to the characteristics of occupation, elderly medical insurance, child care insurance, etc. will generally be consulted. Men, over 35 years old, will consult business insurance, vehicle insurance, etc. according to professional characteristics. Clients and dialogue scenes of different ages, different professions and different sexes are collected in advance, and a neural network model is generated to predict target dialogue scenes of the clients through machine learning and other modes.
In the substep S303, based on the target dialogue scene, a preset fixed question-answer text and a preset intention question-answer text are obtained, and the question-answer text associated with the target dialogue scene in the preset fixed question-answer text and the preset intention question-answer text is obtained.
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 determining the target dialogue scene corresponding to the preset client information. The preset fixed question-answering text and the preset intention question-answering text comprise a plurality of dialogue scenes, wherein one dialogue scene in the preset fixed question-answering text comprises a question and corresponding speaking information, namely one question and one corresponding speaking information are used as the question-answering text. The preset intention question-answering text comprises a plurality of dialogue scenes, wherein one dialogue scene in the preset intention question-answering text comprises a question and a plurality of corresponding speaking information, namely, one question and a plurality of corresponding speaking information are used as question-answering texts. When a target dialogue scene is acquired, keywords in the target dialogue scene are determined, dialogue scenes containing the keywords in a preset fixed question-answering text and a preset intention question-answering text are respectively acquired, and the acquired dialogue scenes are used as question-answering texts.
And step S304, generating a corresponding building block question model according to the question-answering text.
When the question and answer text is obtained, the question and answer text is combined, and a corresponding building block type question model is generated. In an exemplary case, when the question-answering texts are obtained, wherein the number of the question-answering texts is at least two, a flow chart is generated according to the obtained question-answering texts in a mode of stacking building blocks, and the generated flow chart is used as a building block question model.
Generating the building block type question model comprises the following steps: based on a preset decision tree model, acquiring the association frequency between the questions; and inserting question and answer texts corresponding to the questions into the nodes according to the association frequency among the questions at the nodes of the preset decision tree model to generate a corresponding building block question model.
And when acquiring the question and answer text associated with the target dialogue scene, calling a preset decision tree model, and acquiring the association frequency among all questions. By taking the frequency relation among questions in the question and answer text as each node of the preset decision tree model, for example, by collecting the associated frequency information among each question, the associated frequency of the questions 2 presented by the client after the question 1 is compared to 5 times, the associated frequency of the questions 3 is 3 times, and the like, and the associated frequency information of each question before the question 1 is also collected. The method comprises the steps that the association frequency information among all questions is used as trunk nodes to branch nodes in a preset decision tree model according to more or less, and the generated preset decision tree model is used as a building block question model corresponding to a training instruction.
Step S400, simulating a preset client to send a question according to a building block question model, and acquiring speaking information of a user answering the question.
And simulating a preset client to send a question according to the building block question model, and acquiring the speaking and operation information of the user for answering the question. The example is that based on the building block type question model, a preset client sends a question in the building block type question model, a user replies the corresponding speaking information of the question on the basis of the question on an operation interface, and the user answers the corresponding speaking information of the question on the basis of the operation interface.
And running a building block type question model, and simulating and presetting the question corresponding to any node by a client through the building block type question model. The terminal runs a building block type question model, a preset client is simulated through the building block type question model, and questions in question and answer texts at any node of the building block type question model are obtained. For example, the terminal runs a building block question model by which a preset customer is simulated to question the user. The building block type question model is operated to simulate a preset client to train a user, and a question at any node is extracted in the running process of the building block type question model and is taken as a first question. And when the terminal detects the first conversation information input by the user to the first question through the operation interface, acquiring the first conversation information. After the first speech information is acquired, the building block question model extracts a second question at a next node after the dialogue scene.
Step S500, based on the preset conversation information corresponding to the conversation information, the similarity between the conversation information and the preset conversation information is determined.
And when receiving a stop instruction, reading preset speaking information corresponding to the question, wherein the preset speaking information is speaking information corresponding to the question in the question-answering text. When the conversation information and the preset conversation information are obtained, the similarity of the conversation information and the preset conversation information is determined.
In an exemplary embodiment, each preset session information includes preset keywords, and when the number of the keywords is 10, it is determined whether the preset keywords are included in the session information. When it is determined that the speech information includes the included keyword, the number of preset keywords included in the speech information is determined. If the conversation information includes 6 preset keywords, the similarity between the conversation information and the preset conversation information is determined to be 60%, and if the conversation information includes 8 preset keywords, the similarity between the conversation information and the preset conversation information is determined to be 80%.
In one embodiment, referring specifically to fig. 4, step S500 includes: substep S501 to substep S502.
And step S501, obtaining preset voice information corresponding to the voice information, and taking the voice information and the preset voice information as input values of a preset twin neural network model.
And after determining that the building block type question model stops running, acquiring preset telephone operation information corresponding to the telephone operation information, invoking a preset twin neural network model, and taking the telephone operation information and the preset telephone operation information as input values of the twin neural network model. For example, by invoking a preset twin neural network model, the microphone information and the preset microphone information are used as input layers of the twin neural network.
And step S502, determining the similarity of the preset twinning neural network model output speech information and the preset speech information based on the preset twinning neural network model.
According to the operation of the preset twin neural network model, the operation takes the preset voice operation information as a standard, keyword extraction and semantic analysis are carried out through the voice operation information and the preset voice operation information, and the score of the voice operation information is obtained. The exemplary embodiment is that keyword extraction and semantic analysis are performed on dialogue information and preset dialogue information of a preset twin neural network model, 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 dialogue scene of the preset client is determined by acquiring the preset client information. And generating a building block type question-asking model by using a question-answering text associated with the target dialogue scene, simulating a preset customer to train the user through the building block type question-asking model, acquiring the speaking information of the question-asking answer sent by the user to the building block type question-asking model, comparing the speaking information with the preset speaking information to obtain the similarity between the speaking information and the preset speaking information, accurately predicting the target dialogue scene of the preset customer through the preset customer information, so that the generated building block type question-asking model simulates the more realistic simulation customer to train the speaking of the user, scoring each speaking, and improving the speaking level of the user.
Referring to fig. 5, fig. 5 is a flowchart illustrating another information processing method according to an embodiment of the application.
As shown in fig. 5, the information processing method includes steps S601 to 607.
Step S601, displaying an operation interface, where the operation interface includes 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 explanatory icons, interactive icons, pseudo-physical icons, application icons and the like, which are not limited. The user sets a plurality of client icons on an operation interface of the terminal in advance, each client icon sets 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 clicking operation instructions, touching operation instructions and the like, wherein client information is preset to obtain dimension information of different professions, ages, dialogue scenes and the like in advance, and the obtained dimension information is set as client information.
Step S603, based on preset client information, determining a question-answer text corresponding to the preset client information, and generating a corresponding building block question model according to the question-answer text.
And acquiring a dialogue scene in the preset client information, and reading a question-answer text associated with the dialogue scene in a preset database through the dialogue scene, wherein the question-answer text comprises a fixed question-answer text and an intention question-answer text. The fixed question-answering text is a fixed-phone conversation scene, each question has only one corresponding phone, and the fixed question-answering text comprises more than one fixed-phone conversation scene. The intention question-answering text is a multi-phone conversation scene, each question includes more than one corresponding phone, and the intention question-answering text includes more than one multi-phone conversation scene. And combining the fixed question-answering text and the intention question-answering text in a building block stacking mode to generate a flow chart, and taking the generated flow chart as a building block question model.
Step S604, simulating a preset client to send a question according to a building block question model, and acquiring speaking information of a user answering the question.
And simulating a preset client to send a question according to the building block question model, and acquiring the speaking and operation information of the user for answering the question. The example is that based on the building block type question model, the preset client sends the question in the building block type question model, the user replies the corresponding speaking information of the question on the basis of the question on the operation interface, and the terminal obtains the speaking information corresponding to the question on the basis of the operation interface.
Step S605, based on the preset conversation information corresponding to the conversation information, the similarity between the conversation information and the preset conversation information is determined.
And when receiving a stop instruction, reading preset speaking information corresponding to the question, wherein the preset speaking information is speaking information corresponding to the question in the question-answering text. When the conversation information and the preset conversation information are obtained, the similarity of the conversation information and the preset conversation information is determined. In an exemplary embodiment, each preset session information includes preset keywords, and when the number of the keywords is 10, it is determined whether the preset keywords are included in the session information. When it is determined that the speech information includes the included keyword, the number of preset keywords included in the speech information is determined. If the conversation information includes 6 preset keywords, the similarity between the conversation information and the preset conversation information is determined to be 60%, and if the conversation information includes 8 preset keywords, the similarity between the conversation information and the preset conversation information is determined to be 80%.
Step S606, if the similarity is smaller than the preset threshold, determining the similar areas of the conversation information and the preset conversation information, and marking the similar areas.
When the similarity of the preset conversation information and the conversation information is obtained, judging whether the similarity is smaller than a preset threshold value or not. In an exemplary embodiment, when the terminal obtains that the similarity between the preset voice information and the voice information is 60%, the preset threshold is 80%, and the similarity between the preset voice information and the voice information is determined to be smaller than the preset threshold because 60% is smaller than 80%, so that a similar area between the preset voice information and the voice information is determined. If the preset speech information and the region with the same preset keywords or the region with the same semantics in the speech information are similar regions, marking the similar regions. The marking mode includes thickening, emphasizing or marking color of the text in the similar area.
Step S607, the question, the similarity and the marked speaking information are written into a preset template and displayed on an operation interface.
And acquiring a preset template, determining the question, the similarity and the conversation information and the position of the preset conversation information in the preset template, writing the question, the similarity of the preset conversation information and the conversation information sent by the building block question model, the marked conversation information and the preset conversation information into corresponding positions respectively, and displaying the positions on an operation interface.
In this embodiment, a terminal obtains preset client information, determines a question-answer text corresponding to the preset client information, generates a corresponding building block question model according to the question-answer text, simulates a preset client to send a question according to the building block question model, obtains question-corresponding conversation information and similarity between the conversation information and the preset conversation information, determines similar areas of the conversation information and the preset conversation information if similarity reading is smaller than a preset threshold value, marks the similar areas, writes the question, the similarity and the marked conversation information and the preset conversation information into a preset template, displays the preset template on an operation interface, generates a building block question model through different preset client information to simulate the client to send the question, compares the conversation information of the user with the preset conversation information, displays a comparison result on the operation interface, and improves conversation level of the user.
Referring to fig. 6, fig. 6 is a schematic block diagram of an information processing apparatus according to an embodiment of the present application.
As shown in fig. 6, the information processing apparatus 700 includes: 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.
The first obtaining module 702 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 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;
Based on the client identifier of the client icon, preset client information corresponding to the client identifier is obtained.
The generating module 703 is configured to determine a question-answer text corresponding to the preset client information based on the preset client information, and generate a corresponding building block question model according to the question-answer text.
The generating module 703 is specifically further configured to:
Analyzing preset client information, and reading the age, sex and occupation in the preset client information;
Determining a target dialog scenario associated with the age, sex, and occupation based on the age, sex, and occupation;
based on the target dialogue scene, acquiring a preset fixed question-answering text and a preset intention question-answering text, and acquiring the question-answering text associated with the target dialogue scene in the preset fixed question-answering text and the preset intention question-answering text;
And generating a corresponding building block type question model according to the question and answer text.
The generating module 703 is specifically further configured to:
Based on a preset decision tree model, acquiring the association frequency between the questions;
And inserting question and answer texts corresponding to the questions into the nodes according to the association frequency among the questions at the nodes of the preset decision tree model to generate corresponding building block question models.
And the second obtaining module 704 is configured to simulate the preset client to send a question according to the building block question model, and obtain the speaking information of the answer of the question.
The second obtaining module 704 is further specifically configured to:
And running a building block type question model, and simulating and presetting a question corresponding to any node by a client through the building block type question model.
The determining module 705 is configured to determine a similarity between the conversation information and the preset conversation information based on the preset conversation information corresponding to the conversation information.
The determining module 705 is further specifically configured to:
Acquiring preset speaking operation information corresponding to the question, and taking the speaking operation information and the preset speaking operation information as input values of a preset twin neural network model;
And determining the similarity of the preset twinning neural network model output speech information and the preset speech information based on the preset twinning neural network model.
It should be noted that, for convenience and brevity of description, specific working processes of the above-described apparatus and modules and units may refer to corresponding processes in the foregoing information processing method embodiments, 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 application.
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;
Based on the client identifier of the client icon, preset client information corresponding to the client identifier is obtained.
The generating module 803 is configured to determine a question-answer text corresponding to the preset client information based on the preset client information, and generate a corresponding building block question model according to the question-answer text.
The generating module 803 is further specifically configured to:
Analyzing preset client information, and reading the age, sex and occupation in the preset client information;
Determining a target dialog scenario associated with the age, sex, and occupation based on the age, sex, and occupation;
based on the target dialogue scene, acquiring a preset fixed question-answering text and a preset intention question-answering text, and acquiring the question-answering text associated with the target dialogue scene in the preset fixed question-answering text and the preset intention question-answering text;
And generating a corresponding building block type question model according to the question and answer text.
The generating module 803 is further specifically configured to:
Based on a preset decision tree model, acquiring the association frequency between the questions;
And inserting question and answer texts corresponding to the questions into the nodes according to the association frequency among the questions at the nodes of the preset decision tree model to generate corresponding building block question models.
The second obtaining module 804 is configured to simulate, according to the building block type question model, a preset client to send a question, and obtain speaking information of a user answering the question.
The second obtaining module 804 is further specifically configured to:
And running a building block type question model, and simulating and presetting a question corresponding to any node by a client through the building block type question model.
The determining module 805 is configured to determine a similarity between the conversation information and the preset conversation information based on the preset conversation information corresponding to the conversation information.
The determining module 805 is further specifically configured to:
Acquiring preset speaking operation information corresponding to the question, and taking the speaking operation information and the preset speaking operation information as input values of a preset twin neural network model;
And determining the similarity of the preset twinning neural network model output speech information and the preset speech information based on the preset twinning neural network model.
The marking module 806 is configured to obtain preset speaking information corresponding to the question, and use the speaking information and the preset speaking information as input values of the preset twin neural network model.
And a display module 807, configured to determine, based on the preset twin neural network model, a similarity between the preset twin neural network model output speech information and the preset speech information.
It should be noted that, for convenience and brevity of description, specific working processes of the above-described apparatus and modules and units may refer to corresponding processes in the foregoing information processing method embodiments, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program which may be run on a computer device as shown in fig. 8.
Referring to fig. 8, fig. 8 is a schematic block diagram of a computer device according to an embodiment of the present application. 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 non-volatile 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 a number of information processing methods.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium that, when executed by a processor, causes the processor to perform any of a number of information processing methods.
The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by those skilled in the art that the structure shown in FIG. 8 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the Processor may be a central processing unit (Central Processing Unit, CPU), it may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Wherein the 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 run 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.
Detecting an operation instruction of a user based on a client icon, and acquiring preset client information corresponding to the operation instruction.
Based on preset client information, determining a question and answer text corresponding to the preset client information, and generating a corresponding building block question model according to the question and answer text.
And simulating a preset client to send a question according to the building block question model, and acquiring the speaking and operation information of the user for answering the question.
And determining the similarity between the conversation information and the preset conversation information based on the preset conversation information corresponding to the conversation information.
In one embodiment, the processor is configured to, when implementing preset conversation information corresponding to conversation information, determine similarity between the conversation information and the preset conversation information, implement:
Acquiring preset speaking operation information corresponding to the question, and taking the speaking operation information and the preset speaking operation information as input values of a preset twin neural network model;
And determining the similarity of the preset twinning neural network model output speech information and the preset speech information based on the preset twinning neural network model.
In one embodiment, the processor is configured to, after implementing determining the similarity between the preset twinning neural network model output speech information and the preset speech information, implement:
If the similarity is smaller than a preset threshold, determining a similar area of the conversation information and the preset conversation information, and marking the similar area;
And writing the question, the similarity and the marked speaking information into a preset template, and displaying the information and the preset speaking information on an operation interface.
In one embodiment, the processor is configured to, when implementing detection of an operation instruction based on a client icon by a user and obtaining preset client information corresponding to the operation instruction, implement:
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;
Based on the client identifier of the client icon, preset client information corresponding to the client identifier is obtained.
In one embodiment, the processor is configured to, when implementing a question-answer text corresponding to preset client information based on preset client information, generate a corresponding building block question model according to the question-answer text, implement:
Analyzing preset client information, and reading the age, sex and occupation in the preset client information;
Determining a target dialog scenario associated with the age, sex, and occupation based on the age, sex, and occupation;
based on the target dialogue scene, acquiring a preset fixed question-answering text and a preset intention question-answering text, and acquiring the question-answering text associated with the target dialogue scene in the preset fixed question-answering text and the preset intention question-answering text;
And generating a corresponding building block type question model according to the question and answer text.
In one embodiment, the processor is configured to, when implementing generating the corresponding building block question model according to the question-answering text, implement:
Based on a preset decision tree model, acquiring the association frequency between the questions;
And inserting question and answer texts corresponding to the questions into the nodes according to the association frequency among the questions at the nodes of the preset decision tree model to generate corresponding building block question models.
In one embodiment, the processor, when implementing simulating a preset client sending a question according to a building block question model, is configured to implement:
And running a building block type question model, and simulating and presetting a question corresponding to any node by a client through the building block type question model.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, the computer program comprising program instructions which, when executed, implement methods that can be referred to various embodiments of the methods of information processing of the present application.
The computer readable storage medium may be an internal storage unit of the computer device according to 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 memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are 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 one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (8)
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;
Based on the preset client information, determining a question-answer text corresponding to the preset client information, and combining the question-answer text in a building block stacking mode to generate a corresponding flow chart as a building block question model;
Simulating a preset client to send a question according to the building block question model, and acquiring speaking and operation information of the user for answering the question;
Determining the similarity between the speaking information and the preset speaking information based on the preset speaking information corresponding to the question;
The question and answer texts are at least two and comprise questions and corresponding speaking and operation information; the question and answer texts are combined in a building block stacking mode, a corresponding flow chart is generated as a building block question model, and the method comprises the following steps:
Based on a preset decision tree model, acquiring the association frequency between the questions;
Inserting the question and answer text corresponding to the questions into the nodes at the nodes of the preset decision tree model according to the association frequency among the questions, and generating a corresponding flow chart as a building block question model;
The step of simulating preset clients to send questions according to the building block question model comprises the following steps:
and running the building block type question model, and simulating and presetting a client to send a question corresponding to any node through the building block type question model.
2. The method of information processing according to claim 1, wherein the determining the similarity of the speaking information and the preset speaking information based on the preset speaking information corresponding to the question includes:
Acquiring preset speaking information corresponding to the question, and taking the speaking information and the preset speaking information as input values of a preset twin neural network model;
And determining the similarity of the preset twin neural network model output the speaking information and the preset speaking information based on the preset twin neural network model.
3. The method of information processing according to claim 2, wherein after determining that the preset twin neural network model outputs the similarity of the microphone information and the preset microphone information, further comprising:
If the similarity is smaller than a preset threshold, determining a similar area of the conversation information and the preset conversation information, and marking the similar area;
writing the question, the similarity and the marked speaking information and the marked preset speaking information into a preset template, and displaying the written preset template on the operation interface.
4. The method for processing information according to claim 1, wherein the detecting the user to obtain preset client information corresponding to the client icon based on the operation instruction of the client icon includes:
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 client information corresponding to the client identifier based on the client identifier of the client icon.
5. The method for information processing according to claim 1, wherein said determining a question-answer text corresponding to said preset client information based on said preset client information comprises:
Analyzing the preset client information, and reading the age, sex and occupation in the preset client information;
determining a target dialog scenario associated with the age, sex, and occupation based on the age, sex, and occupation;
And acquiring preset fixed question-answering texts and preset intention question-answering texts based on the target dialogue scene, and acquiring question-answering texts associated with the target dialogue scene in the preset fixed question-answering texts and the preset intention question-answering texts.
6. An information processing apparatus, characterized in that the information processing apparatus comprises:
The display module is used for displaying an operation interface, wherein 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 generation module is used for determining a question-answer text corresponding to the preset client information based on the preset client information, combining the question-answer text according to a building block stacking mode, and generating a corresponding flow chart as a building block question model;
The second acquisition module is used for simulating a preset client to send a question according to the building block question model and acquiring speaking and operation information of the user for answering the question;
the determining module is used for determining the similarity between the speaking information and the preset speaking information based on the preset speaking information corresponding to the speaking information;
The system comprises a question and answer text generation module, a question and answer text generation module and a question and answer text generation module, wherein the question and answer text generation module comprises at least two questions and corresponding speaking and operation information, and the question and answer text generation module is further used for acquiring association frequency among the questions based on a preset decision tree model; inserting the question and answer text corresponding to the questions into the nodes at the nodes of the preset decision tree model according to the association frequency among the questions, and generating a corresponding flow chart as a building block question model;
The second acquisition module is further used for running the building block type question model, and sending questions corresponding to any node through the building block type question model simulation preset clients.
7. A computer device, characterized in that it comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when being executed by the processor, realizes the steps of the method of information processing according to any of claims 1 to 5.
8. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method of information processing according to any one of claims 1 to 5.
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 CN111444729A (en) | 2020-07-24 |
| CN111444729B true 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) |
Families Citing this family (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 |
| CN112487140B (en) * | 2020-11-27 | 2024-06-07 | 平安科技（深圳）有限公司 | Question-answer dialogue evaluating method, device, equipment and storage medium |
| CN113724036B (en) * | 2021-07-29 | 2024-10-01 | 杭州淘天电子商务科技有限公司 | Method for providing problem consultation service and electronic equipment |
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 |
|---|
| 基于深度神经网络的工单采集模型研究;陶晓峰;吕朋朋;缪平;娄保东;;自动化与仪器仪表(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111444729A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nguyen et al. | An integrated model of voice-user interface continuance intention: the gender effect | |
| CN111444729B (en) | Information processing method, device, equipment and readable storage medium | |
| CN107357849A (en) | Exchange method and device based on test class application | |
| CN112685550B (en) | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium | |
| Guasch et al. | Effects of the degree of meaning similarity on cross-language semantic priming in highly proficient bilinguals | |
| CN111177307A (en) | Test scheme and system based on semantic understanding similarity threshold configuration | |
| CN116796857A (en) | LLM model training method, device, equipment and storage medium thereof | |
| WO2022018676A1 (en) | Natural language enrichment using action explanations | |
| CN111046674A (en) | Semantic understanding method and device, electronic equipment and storage medium | |
| CN117520497A (en) | Large model interaction processing method, system, terminal, equipment and medium | |
| CN112434144A (en) | Method, device, electronic equipment and computer readable medium for generating target problem | |
| CN113220847B (en) | Neural network-based knowledge mastering degree evaluation method and device and related equipment | |
| CN114925206A (en) | Artificial intelligence body, voice information recognition method, storage medium and program product | |
| CN110263346B (en) | Semantic analysis method based on small sample learning, electronic equipment and storage medium | |
| CN110895924B (en) | Method and device for reading document content aloud, electronic equipment and readable storage medium | |
| Strimling | Beyond accuracy: What documentation quality means to readers | |
| CN111883111B (en) | Method, device, computer equipment and readable storage medium for processing speech training | |
| CN111159403B (en) | Intelligent classroom perception method and system | |
| CN110717020B (en) | Voice question-answering method, device, computer equipment and storage medium | |
| CN114462376A (en) | RPA and AI-based court trial record generation method, device, equipment and medium | |
| CN110516246B (en) | Communication assistance method, device and storage medium | |
| CN116069850A (en) | Classroom activity courseware manufacturing method and device, storage medium and electronic equipment | |
| CN113312463A (en) | Intelligent evaluation method and device for voice question answering, computer equipment and storage medium | |
| Rodrigues et al. | Studying natural user interfaces for smart video annotation towards ubiquitous environments | |
| CN111680148A (en) | Method and device for intelligently responding to question of user |
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 |