CN119862263B - A method, system, medium and electronic device for realizing conversational digital employee human-computer interaction - Google Patents
A method, system, medium and electronic device for realizing conversational digital employee human-computer interactionInfo
- Publication number
- CN119862263B CN119862263B CN202510102134.2A CN202510102134A CN119862263B CN 119862263 B CN119862263 B CN 119862263B CN 202510102134 A CN202510102134 A CN 202510102134A CN 119862263 B CN119862263 B CN 119862263B
- Authority
- CN
- China
- Prior art keywords
- information
- reply
- setting
- robot
- feedback
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/338—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of large model interaction, in particular to a method, a system, a medium and electronic equipment for realizing man-machine interaction of conversational digital staff. The scheme comprises the steps of setting a memory button, an API interface and an online data access interface for a human-computer interaction system, providing feedback personnel for a robot, setting corresponding opening white display for different people, presetting an enhanced search mode, carrying out enhanced reply according to search information, feeding back directional suggestion information, setting key reminding information to be stored in the memory button, and reminding the robot in reply and information feedback each time. According to the scheme, an on-line question-answer system of digital staff is built, and accurate and efficient matching type question-answer is realized by combining a dynamically adjusted memory button.
Description
Technical Field
The invention relates to the technical field of large model interaction, in particular to a method, a system, a medium and electronic equipment for realizing man-machine interaction of conversational digital staff.
Background
In the current large model interaction field, the mode, meaning and importance of researching conversational man-machine interaction are reflected in how to realize efficient and intelligent communication between a user and a large-scale calculation model through a natural language processing technology. The interaction mode not only can promote user experience and enable people to communicate with the machine more naturally, but also has profound influence on promotion of development of artificial intelligence technology. With the continuous progress of technology, conversational man-machine interaction has become an important bridge connecting human intelligence with machine intelligence, and can not only promote quick circulation of information and sharing of knowledge, but also play a great role in multiple fields of education, medical treatment, customer service and the like, and greatly improve service efficiency and quality. Therefore, the search for a more intelligent and personalized conversational human-computer interaction method and a system design thereof is important to meet the requirements of the modern society for efficient and convenient information services.
Prior to the present technology, the existing conversational human-computer interaction method mainly adopts a system architecture based on modules such as speech recognition, natural language processing, conversation management, speech synthesis, etc. The system converts the voice input of the user into text information, then carries out semantic understanding and intention recognition by utilizing a natural language processing technology, and finally controls a dialogue flow and generates a response by a dialogue management module. However, there are often problems with understanding depth and context problems, and while large language models are able to generate fluent languages, they often lack the ability to understand deeply the context behind the problem and long term context. For example, in a multi-round conversation, it may forget the previous information or be inappropriately understood, resulting in an abrupt answer. Knowledge update lag-training data of large language models comes from a dataset at a particular point in time, so their knowledge base has a time lag. Over time, the model cannot automatically obtain new information. Accuracy and reliability of generated content problems the generated AI may sometimes generate inaccurate, erroneous or harmful content. For example, it may generate false information, ambiguous answers, etc.
Disclosure of Invention
In view of the above problems, the invention provides a method, a system, a medium and electronic equipment for realizing man-machine interaction of conversational digital staff, which are used for realizing accurate and efficient matching type question and answer by constructing a question-answer system of the digital staff on line and combining with a dynamically adjusted memory button.
According to a first aspect of the embodiment of the invention, a method for realizing man-machine interaction of conversational digital staff is provided.
In one or more embodiments, preferably, the method for implementing man-machine interaction of conversational digital staff includes:
setting a memory button, an API interface and an online data access interface for a human-computer interaction system;
providing a feedback person for the robot;
setting corresponding open-field white displays for different people;
presetting an enhanced search mode, and performing enhanced reply according to the search information;
feeding back directional suggestion information;
Setting key reminding information to be stored in the memory button, and reminding the robot in each reply and information feedback;
Extracting a declarative viewpoint ratio and a problematic viewpoint ratio after each digital employee feeds back a reply, wherein the declarative viewpoint ratio is the number of declarative sentences divided by the total number of sentences, the problematic viewpoint ratio is the number of problematic sentences divided by the total number of sentences, and increasing tendencies according to the declarative viewpoint ratio and the problematic viewpoint ratio demand in each questioning process according to demands, wherein the tendencies comprise increasing the declarative viewpoint ratio or the problematic viewpoint ratio;
After each feedback reply of the digital employee, extracting a reply sentence duty ratio containing a new noun, and when the new noun duty ratio is less than a preset value, requesting to increase the reply sentence duty ratio of the new noun, wherein the reply sentence duty ratio of the new noun is obtained by dividing a sentence in which a name exists by the total number of sentences in the given information.
In one or more embodiments, preferably, the man-machine interaction system sets a memory button, an API interface and an online data access interface, and specifically includes:
setting a memory button for storing the inquired information online;
setting an API interface for extracting question-answer information corresponding to the professional field for matching;
and setting an on-line data access interface for on-line data extraction and control.
In one or more embodiments, preferably, the provision of the feedback device for the robot specifically includes:
presetting feedback formats set by people, including roles, skills and notes;
Presetting a table corresponding to the person setting for selecting the person setting;
the output mode of feedback set by a person is preset.
In one or more embodiments, preferably, setting corresponding open-field white displays for different people specifically includes:
Selecting preset opening white according to the setting of the person;
when the robot corresponding to the person is inquired on line, the opening time corresponding to the robot corresponding to the person is called.
In one or more embodiments, preferably, the preset enhanced search mode performs enhanced reply according to the search information, and specifically includes:
Setting a mode and an order of screening information in a preset enhanced retrieval mode;
and screening and sequencing the retrieved information by presetting parameters and rules for enhancing the retrieval.
In one or more embodiments, preferably, the feedback orientation advice information specifically includes:
according to error information fed back by the robot in each dialogue, a direction of suggestion is definitely oriented;
the directional suggestions are made according to rules set by the questioner in each dialog.
In one or more embodiments, preferably, the setting key reminding information is stored in the memory button, and the robot is reminded in each reply and information feedback, which specifically includes:
when reply information is obtained each time, the explicit statement views are automatically extracted, numbered and stored in a memory button to be used as the explicit views;
Numbering the explicit views;
acquiring an input upper limit of each feedback reply, and calculating the number of residual words according to a first calculation formula;
Calculating the viewpoint number by using a second calculation formula;
Calculating an updated current viewpoint set by using a third calculation formula;
calculating the viewpoint number of each time by using a fourth calculation formula according to the updated current viewpoint set until a fifth calculation formula is met;
After the fifth calculation formula is met, updating all the clear views, and reusing the second, third and fourth calculation formulas to calculate the view numbers of the time;
In each reply, starting with the reminding, feeding back the clear views corresponding to the view numbers one by one;
The first calculation formula is as follows:
SX-YR=SY
wherein SX is the upper input limit, YR is the number of words already input, and SY is the number of remaining words;
the second calculation formula is as follows:
BC=Argmin(|SY-ΣGZ|)
SY-ΣGZ>0
BC∈JH
Argmin is a function for extracting the current viewpoint number that minimizes |sy- Σgz|, Σgz is the sum of the number of words of the current viewpoint, BC is the current viewpoint number, JH is the current viewpoint set;
The third calculation formula is as follows:
JHq=JH-BC
wherein JHq is the updated current view set;
The fourth calculation formula is as follows:
BCn=Argmin(|SY-ΣGZ|)
SY-ΣGZ>0
BCn∈JHq
Wherein BCn is the viewpoint number of each time;
the fifth calculation formula is:
JHq=kong
Wherein kong is an empty set.
According to a second aspect of the embodiment of the invention, a conversational digital employee man-machine interaction implementation system is provided.
In one or more embodiments, preferably, the conversational digital employee human-computer interaction implementation system includes:
the structure building module is used for setting a memory button, an API interface and an online data access interface for the human-computer interaction system;
The human setting generation module is used for prescribing feedback human setting for the robot;
The white-in-field module is arranged, the method is used for setting corresponding opening white display for different people;
the enhancement retrieval module is used for presetting an enhancement retrieval mode and carrying out enhancement reply according to the retrieval information;
The directional suggestion module is used for feeding back directional suggestion information;
the key memory information learning module is used for setting key reminding information to be stored in the memory button, and reminding the robot in each reply and information feedback.
According to a third aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to any of the first aspect of embodiments of the present invention.
According to a fourth aspect of embodiments of the present invention there is provided an electronic device comprising a memory and a processor, the memory being for storing one or more computer program instructions, wherein the one or more computer program instructions are executable by the processor to implement the method of any of the first aspects of embodiments of the present invention.
The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:
in the scheme of the invention, an explicit digital employee question-answering system is combined, and on-line question-answering is carried out according to a preset feedback person.
In the scheme of the invention, the question-answer information supplement based on the memory buttons is combined with dynamic adjustment, so that efficient and accurate question-answer feedback is realized.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that 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 implementing human-computer interaction for a conversational digital employee according to one embodiment of the invention.
Fig. 2 is a flowchart of setting a memory button, an API interface and an online data access interface for a human-computer interaction system in a method for implementing human-computer interaction of a conversational digital employee according to an embodiment of the invention.
Fig. 3 is a flowchart of a method for implementing interactive human-computer interaction of a conversational digital employee to define feedback settings for a robot according to one embodiment of the invention.
Fig. 4 is a flowchart of setting corresponding open time display for different settings in a method for implementing man-machine interaction of a conversational digital employee according to an embodiment of the invention.
Fig. 5 is a flowchart of a method for implementing a preset enhanced search mode in a conversational digital employee human-computer interaction method according to one embodiment of the invention, and performing an enhanced reply according to search information.
FIG. 6 is a flow chart of feedback directed suggestion information in a conversational digital employee human-computer interaction implementation according to one embodiment of the invention.
Fig. 7 is a flowchart of a method for implementing man-machine interaction of conversational digital staff according to an embodiment of the present invention, in which setting key reminding information is stored in the memory button, and a robot is reminded in each reply and information feedback.
FIG. 8 is a block diagram of a conversational digital employee human-computer interaction implementation system according to one embodiment of the invention.
Fig. 9 is a block diagram of an electronic device in one embodiment of the invention.
Detailed Description
In some of the flows described in the specification and claims of the present invention and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
In the current large model interaction field, the mode, meaning and importance of researching conversational man-machine interaction are reflected in how to realize efficient and intelligent communication between a user and a large-scale calculation model through a natural language processing technology. The interaction mode not only can promote user experience and enable people to communicate with the machine more naturally, but also has profound influence on promotion of development of artificial intelligence technology. With the continuous progress of technology, conversational man-machine interaction has become an important bridge connecting human intelligence with machine intelligence, and can not only promote quick circulation of information and sharing of knowledge, but also play a great role in multiple fields of education, medical treatment, customer service and the like, and greatly improve service efficiency and quality. Therefore, the search for a more intelligent and personalized conversational human-computer interaction method and a system design thereof is important to meet the requirements of the modern society for efficient and convenient information services.
Prior to the present technology, the existing conversational human-computer interaction method mainly adopts a system architecture based on modules such as speech recognition, natural language processing, conversation management, speech synthesis, etc. The system converts the voice input of the user into text information, then carries out semantic understanding and intention recognition by utilizing a natural language processing technology, and finally controls a dialogue flow and generates a response by a dialogue management module. However, there are often problems with understanding depth and context problems, and while large language models are able to generate fluent languages, they often lack the ability to understand deeply the context behind the problem and long term context. For example, in a multi-round conversation, it may forget the previous information or be inappropriately understood, resulting in an abrupt answer. Knowledge update lag-training data of large language models comes from a dataset at a particular point in time, so their knowledge base has a time lag. Over time, the model cannot automatically obtain new information. Accuracy and reliability of generated content problems the generated AI may sometimes generate inaccurate, erroneous or harmful content. For example, it may generate false information, ambiguous answers, etc.
The embodiment of the invention provides a method, a system, a medium and electronic equipment for realizing man-machine interaction of conversational digital staff. According to the scheme, an on-line question-answer system of digital staff is built, and accurate and efficient matching type question-answer is realized by combining a dynamically adjusted memory button.
According to a first aspect of the embodiment of the invention, a method for realizing man-machine interaction of conversational digital staff is provided.
FIG. 1 is a flow chart of a method for implementing human-computer interaction for a conversational digital employee according to one embodiment of the invention.
In one or more embodiments, preferably, the method for implementing man-machine interaction of conversational digital staff includes:
S101, setting a memory button, an API interface and an online data access interface for a human-computer interaction system;
s102, prescribing feedback personnel for the robot;
s103, setting corresponding open-field white displays for different people;
S104, presetting an enhanced retrieval mode, and performing enhanced reply according to the retrieval information;
s105, feeding back the directional suggestion information;
S106, setting key reminding information to be stored in the memory button, and reminding the robot in each reply and information feedback.
In the embodiment of the invention, the core is to create a digitalized robot, log in a button platform, click a button to generate the robot, enter a design page of the robot, create a man-machine set for the robot, describe the identity and task of the robot in a left man-machine set and reply logic panel, and write a plan. The robot's human setup and reply logic defines its basic human setup, which will continuously influence its reply effect in all sessions. In order to achieve the desired effect, the role of the model, the language style of the design reply, the answer range of the limited model and the like are specified in the human setting and reply logic, so that the dialogue is more in line with the expectations of the user.
Further, in order to make the feedback of the robot more solve the demand of questioning, a declarative viewpoint ratio and a problematic viewpoint ratio are extracted after each digital employee feeds back a reply, wherein the declarative viewpoint ratio is the number of declarative sentences divided by the total number of sentences, the problematic viewpoint ratio is the number of problematic sentences divided by the total number of sentences, and a tendency is increased according to the demand in each questioning process according to the demand, which includes increasing the declarative viewpoint ratio or the problematic viewpoint ratio according to the declarative viewpoint ratio, and a reply sentence ratio containing a new noun is extracted after each digital employee feeds back a reply, and when the new noun ratio is less than a preset value, an increase in reply sentence ratio of a new noun is required, wherein the reply sentence ratio of the new noun is the number of sentences divided by the total number of sentences which do not include the name in the given information.
Fig. 2 is a flowchart of setting a memory button, an API interface and an online data access interface for a human-computer interaction system in a method for implementing human-computer interaction of a conversational digital employee according to an embodiment of the invention.
As shown in fig. 2, in one or more embodiments, preferably, the man-machine interaction system sets a memory button, an API interface, and an online data access interface, and specifically includes:
S201, setting a memory button for storing inquiry information online;
S202, setting an API interface for extracting question-answer information corresponding to the professional field for matching;
s203, setting an on-line data access interface for on-line extraction and control of on-line data.
In the embodiment of the invention, an efficient man-machine interaction system is constructed, and the system optimizes user experience and improves the response capability of the system by integrating a memory button, an API interface and an online data access interface. First, the system is provided with a functional module called a "memory button", which functions like a human memory function and is capable of storing on-line the user's previous inquiry information. This storage mechanism allows the system to reference the previous information in subsequent conversations, thereby enabling a more personalized and consistent conversational experience. For example, if the user previously asked questions about weather, the system may actively provide weather forecast in a subsequent session without requiring the user to repeatedly ask questions. Secondly, the system is provided with API interfaces which are specially used for extracting and matching question and answer information in the corresponding professional field. Through the connection with an external knowledge base or database, the API interface can quickly retrieve and provide accurate answers according to the query request of the user. For example, when a user asks a medical-related problem, the API interface may connect to a specialized medical database, retrieving and returning related medical information. Finally, the system is also provided with an on-line data access interface, and the function of the interface is to extract on-line data on line for control. This means that the system can monitor dynamic data such as network status, user behavior, etc. in real time and adjust its own operation policy according to the data. For example, if an increase in network delay is detected, the system may automatically decrease the frequency of data transmission to ensure fluency of the conversation. In summary, through the cooperative work of the three key components, the man-machine interaction system provided by the invention not only can provide more intelligent and personalized services, but also can adapt to the change of external environment in real time, thereby remarkably improving the interaction experience of users.
Fig. 3 is a flowchart of a method for implementing interactive human-computer interaction of a conversational digital employee to define feedback settings for a robot according to one embodiment of the invention.
As shown in fig. 3, in one or more embodiments, preferably, the provision of the feedback device for the robot specifically includes:
s301, presetting feedback formats set by people, including roles, skills and notes;
s302, presetting a table corresponding to the person setting for selecting the person setting;
s303, presetting a feedback output mode set by a person.
In the embodiment of the invention, a robot feedback system with high customization and interactivity is designed. The system guides the behavior and communication mode of the robot through preset human settings (role settings), thereby providing a more personalized and contextualized user experience. First, the system specifies feedback settings for the robot, which include three core elements of role, skill, and notice. The character defines the identity of the robot in a particular context, such as a "friendly tour guide" or a "professional doctor assistant", which helps shape the personality and behavior pattern of the robot. The skills define the scope of tasks that the robot can perform, for example, a robot set as an "IT support expert" will have the ability to solve the technical problem. The precautions are to ensure that the robot follows certain behavioral criteria during the interaction, such as maintaining politics, avoiding sensitive topics, etc. The system then presets a table of corresponding settings as part of the user interface, allowing the user to select different settings as desired. The user can easily switch the roles of the robots through the table to adapt to different dialogue scenes. For example, if users need to conduct health consultation, they can select a "medical consultant" person setting, and if they need travel information, they can select a "travel guide" person setting. Finally, the system also presets the output mode of the human feedback. This means that the robot will keep its feedback content and style consistent with its settings when interacting with the user. For example, when a robot is set as a "humorous friend", its answer may contain more humorous elements and relaxed language, while as a "serious teacher", its feedback may be more educational and instructive. In this way, the embodiment of the invention not only enhances the interaction capability of the robot, so that the robot can better adapt to the diversified demands of users, but also improves the quality of user experience, and the robot can provide more natural and relevant services under different conditions.
Fig. 4 is a flowchart of setting corresponding open time display for different settings in a method for implementing man-machine interaction of a conversational digital employee according to an embodiment of the invention.
As shown in fig. 4, in one or more embodiments, preferably, the setting corresponding open-time display for different people specifically includes:
S401, selecting preset opening white according to the setting of the person;
s402, when the robot corresponding to the person is inquired online, calling the opening white corresponding to the robot corresponding to the person.
In the embodiment of the invention, an intelligent dialogue system is constructed, and the system can display the corresponding opening white according to different person settings (role settings) so as to enhance user experience and improve the naturalness of interaction. Firstly, the system presets a series of open whites corresponding to different people. These open turns are delicately designed sentences or paragraphs intended to reflect the personality, style and function set by a particular person. For example, for a robot set to "friendly tour guide", the starting time may be: "your good | i am your travel assistant, is it ready to explore this beautiful city together?" welcome legal consultation service you use, i will provide you with the most specialized advice. And then, when the user inquires the robot corresponding to the person on line, the system automatically calls out the opening time corresponding to the robot corresponding to the person. The process is realized through an algorithm, and the algorithm can identify the most suitable person setting according to the query content and the context information of the user and trigger the corresponding opening white. For example, if a user enters a question about travel through a chat interface, the system may recognize that the user needs travel-related information, and then automatically select a "friendly travel guide" personally set and display its corresponding travel time. This embodiment not only improves the response efficiency of the robot, but also enhances the user's immersion and satisfaction through personalized opening whites. The user can feel the role and individuality of the robot immediately, so that the trust feeling and interactive willingness can be built more easily. In addition, the method also enables the robot to be flexibly applied in various scenes, and whether customer service, education coaching or entertainment interaction is provided, the robot can provide proper opening time according to different people so as to meet diversified demands of users.
Fig. 5 is a flowchart of a method for implementing a preset enhanced search mode in a conversational digital employee human-computer interaction method according to one embodiment of the invention, and performing an enhanced reply according to search information.
As shown in fig. 5, in one or more embodiments, preferably, the preset enhanced search mode performs enhanced reply according to the search information, and specifically includes:
s501, setting a mode and an order of screening information in a preset enhanced search mode;
s502, screening and sorting the retrieved information by presetting parameters and rules for enhancing retrieval.
In the embodiment of the invention, an enhanced retrieval mode is designed to improve the accuracy and efficiency of information retrieval. The mode screens and sorts the searched information by means of preset information screening modes and sequences and enhanced search parameters and rules, so that more accurate and relevant answers are provided for users. First, the system presets an enhanced retrieval mode, which includes a manner and order of defining how to filter the information. For example, when a user queries "best restaurants," the system may first screen restaurants located near the user's current location, then further screen according to the user's historical preferences (e.g., cuisine, price intervals, etc.), and finally rank according to score or recommendation. This multi-level screening mechanism ensures that only the information that best meets the needs of the user will be presented. Then, the system optimizes the search result through preset enhanced search parameters and rules. These parameters may include keyword weights, time range limits, source credibility assessment, etc. For example, if the user is looking for the latest technical news, the system may set a time range parameter to retrieve only articles published in the past week, while, through source credibility evaluation, reports from well-known technical media are preferentially presented. This process is illustrated in a specific example assuming that the user wants to know information about the "artificial intelligence latest progress". The system first recognizes the keywords "artificial intelligence" and "recent progress" and then applies a preset enhanced retrieval mode. In this mode, the system may first screen out relevant articles that were published in the last month, then evaluate the credibility based on the sources of the articles (e.g., top academic journal, authoritative news website, etc.), and give a higher ranking to the articles of high credibility sources. And finally, the system presents the screened and sequenced results to the user, so that the user can be ensured to quickly obtain the most relevant and reliable information. In this way, the enhanced retrieval mode not only improves the information retrieval efficiency, but also remarkably improves the retrieval experience and satisfaction of users through a multi-dimensional screening and sorting mechanism.
FIG. 6 is a flow chart of feedback directed suggestion information in a conversational digital employee human-computer interaction implementation according to one embodiment of the invention.
As shown in fig. 6, in one or more embodiments, the feedback orientation advice information preferably specifically includes:
s601, according to error information fed back by a robot in each dialogue, a suggested direction is definitely oriented;
S602, according to rules set by a questioner in each dialogue, a directional suggestion is provided.
In the embodiment of the invention, an intelligent dialogue system is designed, and the system has the function of feeding back the directional suggestion information. This function aims at providing more accurate and targeted advice by analyzing the error information of the robot feedback in each dialogue and according to rules set by the questioner.
Fig. 7 is a flowchart of a method for implementing man-machine interaction of conversational digital staff according to an embodiment of the present invention, in which setting key reminding information is stored in the memory button, and a robot is reminded in each reply and information feedback.
As shown in fig. 7, in one or more embodiments, preferably, the setting key reminding information is stored in the memory button, and the method specifically includes:
S701, when reply information is obtained each time, the explicit statement views are automatically extracted, numbered and stored in a memory button to be used as the explicit views;
S702, numbering the clear views;
S703, obtaining an input upper limit of each feedback reply, and calculating the number of residual words according to a first calculation formula;
s704, calculating the viewpoint number by using a second calculation formula;
s705, calculating an updated current viewpoint set by using a third calculation formula;
S706, calculating the viewpoint number of each time by using a fourth calculation formula according to the updated current viewpoint set until the fifth calculation formula is satisfied;
s707, updating all the explicit views after the fifth calculation formula is satisfied, and calculating the view numbers by reusing the second, third and fourth calculation formulas;
s708, in each reply, starting with the beginning of the reply, feeding back the clear views corresponding to the view numbers of the time one by one;
The first calculation formula is as follows:
SX-YR=SY
wherein SX is the upper input limit, YR is the number of words already input, and SY is the number of remaining words;
the second calculation formula is as follows:
BC=Argmin(|SY-ΣGZ|)
SY-ΣGZ>0
BC∈JH
Argmin is a function for extracting the current viewpoint number that minimizes |sy- Σgz|, Σgz is the sum of the number of words of the current viewpoint, BC is the current viewpoint number, JH is the current viewpoint set;
The third calculation formula is as follows:
JHq=JH-BC
wherein JHq is the updated current view set;
The fourth calculation formula is as follows:
BCn=Argmin(|SY-ΣGZ|)
SY-ΣGZ>0
BCn∈JHq
Wherein BCn is the viewpoint number of each time;
the fifth calculation formula is:
JHq=kong
Wherein kong is an empty set.
In the embodiment of the invention, an intelligent dialogue system is designed, and the system has the function of feeding back the directional suggestion information. This function aims at providing more accurate and targeted advice by analyzing the error information of the robot feedback in each dialogue and according to rules set by the questioner. Specifically, the system first records and analyzes the error information of the robot feedback in each dialogue. Such error information may include questions that the robot cannot understand, inaccurate or irrelevant answers, etc. Through in-depth analysis of these error information, the system is able to identify common problem types and user demand patterns. For example, if a robot fails to properly understand a problem with a particular field many times, the system will mark this field as an important point for improvement. Next, the system will make directional suggestions based on rules set by the questioner in each dialog. These rules may be customized by the user to reflect their particular needs or preferences. For example, the user may set rules that require the robot to give both dressing advice and outdoor activity advice while providing weather information. When the robot detects that the user inquires about weather, the robot not only reports the current weather condition, but also provides additional suggestions according to the rules of the user, such as 'today's lower temperature, please add clothes properly 'or' today's sunny condition, and is suitable for outdoor exercises'. This process is illustrated in a specific example assuming that the user inquires about advice on a healthy diet, while the robot provides some basic diet guidelines. However, the user then indicates that they have a particular health condition, requiring more specific advice. In this case, the system will adjust its answer policy based on the user's feedback and set rules. In future conversations, when similar health conditions are mentioned, the robot will be able to provide more personalized and targeted suggestions, such as recommending low sugar recipes or high fiber food options. In this way, the intelligent dialog system of the present invention is able to learn from errors and improve its performance, but also to provide more careful services according to the personalized needs of the user. The mechanism for feeding back the directional suggestion information remarkably improves the user experience, so that the robot can better meet the diversified requirements of users.
According to a second aspect of the embodiment of the invention, a conversational digital employee man-machine interaction implementation system is provided.
FIG. 8 is a block diagram of a conversational digital employee human-computer interaction implementation system according to one embodiment of the invention.
In one or more embodiments, preferably, the conversational digital employee human-computer interaction implementation system includes:
the structure construction module 801 is used for setting a memory button, an API interface and an online data access interface for the human-computer interaction system;
A human set generation module 802 for specifying a feedback human set for the robot;
The setting white module 803 is used for setting corresponding setting white display for different people;
the enhanced retrieval module 804 is configured to preset an enhanced retrieval mode, and perform enhanced reply according to the retrieval information;
The directional suggestion module 805 is configured to feed back directional suggestion information;
the key memory information learning module 806 is configured to set key reminding information to be stored in the memory button, and remind the robot in each reply and information feedback.
In the embodiment of the invention, a system suitable for different structures is realized through a series of modularized designs, and the system can realize closed-loop, reliable and efficient execution through acquisition, analysis and control.
According to a third aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to any of the first aspect of embodiments of the present invention.
According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device. Fig. 9 is a block diagram of an electronic device in one embodiment of the invention. The electronic device shown in fig. 9 is a conversational digital employee man-machine interaction implementation apparatus, which includes a general purpose computer hardware structure including at least a processor 901 and a memory 902. The processor 901 and the memory 902 are connected by a bus 903. The memory 902 is adapted to store instructions or programs executable by the processor 901. The processor 901 may be a stand-alone microprocessor or may be a set of one or more microprocessors. Thus, the processor 901 performs the process of data and control of other devices by executing the instructions stored in the memory 902, thereby performing the method flow of the embodiment of the present invention as described above. Bus 903 connects the above components together, while connecting the above components to display controller 904 and display device and IO device 905.IO device 905 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, IO device 905 is connected to the system through IO controller 906.
The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:
in the scheme of the invention, an explicit digital employee question-answering system is combined, and on-line question-answering is carried out according to a preset feedback person.
In the scheme of the invention, the question-answer information supplement based on the memory buttons is combined with dynamic adjustment, so that efficient and accurate question-answer feedback is realized.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A method for realizing man-machine interaction of conversational digital staff is characterized by comprising the following steps:
setting a memory button, an API interface and an online data access interface for a human-computer interaction system;
providing a feedback person for the robot;
setting corresponding open-field white displays for different people;
presetting an enhanced search mode, and performing enhanced reply according to the search information;
feeding back directional suggestion information;
Setting key reminding information to be stored in the memory button, and reminding the robot in each reply and information feedback;
The process of setting key reminding information is stored in the memory button, and reminding a robot in each reply and information feedback comprises the steps of automatically extracting explicit statement views from reply information and numbering the explicit statement views, storing the explicit views into the memory button to serve as the explicit views, automatically reading the information in the memory button and extracting all statement views in the memory button in each reply and information feedback process, numbering the statement views, supplementing the current view number meeting a second calculation formula in all statement views according to the upper input limit of each reply, and updating all the explicit views after all the statement views are continuously replied for all feedback for a plurality of times;
the second calculation formula is as follows:
BC=Argmin(|SY-ΣGZ|)
SY-ΣGZ>0
BC∈JH
Argmin is a function for extracting the current viewpoint number that minimizes |sy- Σgz|, Σgz is the sum of the number of words of the current viewpoint, BC is the number of words of the current viewpoint, JH is the current viewpoint set, SY is the number of words remaining;
Extracting a declarative viewpoint ratio and a problematic viewpoint ratio after each digital employee feeds back a reply, wherein the declarative viewpoint ratio is the number of declarative sentences divided by the total number of sentences, the problematic viewpoint ratio is the number of problematic sentences divided by the total number of sentences, and increasing tendencies according to the declarative viewpoint ratio and the problematic viewpoint ratio demand in each questioning process according to demands, wherein the tendencies comprise increasing the declarative viewpoint ratio or the problematic viewpoint ratio;
After each feedback reply of the digital employee, extracting a reply sentence duty ratio containing a new noun, and when the new noun duty ratio is less than a preset value, requesting to increase the reply sentence duty ratio of the new noun, wherein the reply sentence duty ratio of the new noun is obtained by dividing a sentence in which a name exists by the total number of sentences in the given information.
2. The method for implementing man-machine interaction of conversational digital employee according to claim 1, wherein the man-machine interaction system is provided with a memory button, an API interface and an on-line data access interface, and the method specifically comprises:
setting a memory button for storing the inquired information online;
setting an API interface for extracting question-answer information corresponding to the professional field for matching;
and setting an on-line data access interface for on-line data extraction and control.
3. A method for implementing man-machine interaction of conversational digital employee according to claim 1, wherein said defining feedback personnel for the robot comprises:
presetting feedback formats set by people, including roles, skills and notes;
Presetting a table corresponding to the person setting for selecting the person setting;
the output mode of feedback set by a person is preset.
4. The method for implementing man-machine interaction of conversational digital staff as claimed in claim 1, wherein the setting of corresponding opening displays for different people specifically includes:
Selecting preset opening white according to the setting of the person;
when the robot corresponding to the person is inquired on line, the opening time corresponding to the robot corresponding to the person is called.
5. The method for implementing man-machine interaction of conversational digital employee according to claim 1, wherein the preset enhanced search mode is used for enhanced reply according to search information, and the method specifically comprises:
Setting a mode and an order of screening information in a preset enhanced retrieval mode;
and screening and sequencing the retrieved information by presetting parameters and rules for enhancing the retrieval.
6. A method for implementing man-machine interaction of a conversational digital employee according to claim 1, wherein the feedback of the directional suggestion information specifically includes:
according to error information fed back by the robot in each dialogue, a direction of suggestion is definitely oriented;
the directional suggestions are made according to rules set by the questioner in each dialog.
7. The method for realizing man-machine interaction of conversational digital staff as claimed in claim 1, wherein the setting key reminding information is stored in the memory button, and the robot is reminded in each reply and information feedback, specifically comprising:
Numbering the explicit views;
acquiring an input upper limit of each feedback reply, and calculating the number of residual words according to a first calculation formula;
Calculating the viewpoint number by using a second calculation formula;
Calculating an updated current viewpoint set by using a third calculation formula;
calculating the viewpoint number of each time by using a fourth calculation formula according to the updated current viewpoint set until a fifth calculation formula is met;
After the fifth calculation formula is met, updating all the clear views, and reusing the second, third and fourth calculation formulas to calculate the view numbers of the time;
in each reply, the words of 'what needs to be reminded' are used as the reply beginning, and the clear views corresponding to the view numbers of the time are fed back one by one;
The first calculation formula is as follows:
SX-YR=SY
wherein SX is the upper input limit, YR is the number of words already input, and SY is the number of remaining words;
The third calculation formula is as follows:
JHq=JH-BC
wherein JHq is the updated current view set;
The fourth calculation formula is as follows:
BCn=Argmin(|SY-ΣGZ|)
SY-ΣGZ>0
BCn∈JHq
Wherein BCn is the viewpoint number of each time;
the fifth calculation formula is:
JHq=kong
Wherein kong is an empty set.
8. A conversational digital employee human-computer interaction implementation system for implementing a method according to any one of claims 1-7, the system comprising:
the structure building module is used for setting a memory button, an API interface and an online data access interface for the human-computer interaction system;
The human setting generation module is used for prescribing feedback human setting for the robot;
The white-in-field module is arranged, the method is used for setting corresponding opening white display for different people;
the enhancement retrieval module is used for presetting an enhancement retrieval mode and carrying out enhancement reply according to the retrieval information;
The directional suggestion module is used for feeding back directional suggestion information;
the key memory information learning module is used for setting key reminding information to be stored in the memory button, and reminding the robot in each reply and information feedback.
9. A computer readable storage medium, on which computer program instructions are stored, which computer program instructions, when executed by a processor, implement the method of any of claims 1-7.
10. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510102134.2A CN119862263B (en) | 2025-01-22 | 2025-01-22 | A method, system, medium and electronic device for realizing conversational digital employee human-computer interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510102134.2A CN119862263B (en) | 2025-01-22 | 2025-01-22 | A method, system, medium and electronic device for realizing conversational digital employee human-computer interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119862263A CN119862263A (en) | 2025-04-22 |
| CN119862263B true CN119862263B (en) | 2025-09-23 |
Family
ID=95392707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510102134.2A Active CN119862263B (en) | 2025-01-22 | 2025-01-22 | A method, system, medium and electronic device for realizing conversational digital employee human-computer interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119862263B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105938484A (en) * | 2016-04-12 | 2016-09-14 | 华南师范大学 | Robot interaction method and system based on user feedback knowledge base |
| CN106168962A (en) * | 2016-06-30 | 2016-11-30 | 北京奇虎科技有限公司 | Searching method and the device of accurate viewpoint are provided based on natural Search Results |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7949617B1 (en) * | 2002-11-11 | 2011-05-24 | Linda Shawn Higgins | System and methods for facilitating user thinking and learning utilizing enhanced interactive constructs |
| CN110399484A (en) * | 2019-06-25 | 2019-11-01 | 平安科技（深圳）有限公司 | Sentiment analysis method, device, computer equipment and storage medium for long text |
| CN117743521A (en) * | 2023-07-26 | 2024-03-22 | 北京联想软件有限公司 | Conference problem processing method and electronic equipment |
-
2025
- 2025-01-22 CN CN202510102134.2A patent/CN119862263B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105938484A (en) * | 2016-04-12 | 2016-09-14 | 华南师范大学 | Robot interaction method and system based on user feedback knowledge base |
| CN106168962A (en) * | 2016-06-30 | 2016-11-30 | 北京奇虎科技有限公司 | Searching method and the device of accurate viewpoint are provided based on natural Search Results |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119862263A (en) | 2025-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Winter | Statistics for linguists: An introduction using R | |
| Badiru et al. | Fuzzy engineering expert systems with neural network applications | |
| US11410643B2 (en) | Response generation for conversational computing interface | |
| Maguire | An evaluation of published recommendations on the design of man-computer dialogues | |
| CN119691133B (en) | A dynamic question-answer matching method and system based on context awareness | |
| WO2022051436A1 (en) | Personalized learning system | |
| US11822584B2 (en) | Interpreting vague intent modifiers in visual analysis using word co-occurrence and sentiment analysis | |
| JP7641032B2 (en) | Generative AI management system, generative AI management method, and generative AI management program | |
| US20110238663A1 (en) | Search method and system using thinking system | |
| Singh | Exploring the role of large language model (llm)-based chatbots for human resources | |
| CN117874178A (en) | Method, device, equipment and medium for determining medical response text data | |
| Li et al. | Guiding the design of inclusive interactive systems: Do younger and older adults use the same image-schematic metaphors? | |
| JP7216449B2 (en) | Persona learning and usage methods, programs | |
| CN119862263B (en) | A method, system, medium and electronic device for realizing conversational digital employee human-computer interaction | |
| Jiang | Design and Implementation of Personalized Recommendation Algorithm in Alumni Using Natural Language Processing | |
| Ismael et al. | Chatbot system for mental health in Bahasa Malaysia | |
| US7930319B2 (en) | Search method and system using thinking system | |
| Mainaly | Bing, bard, and brainstorming: A triadic tenor of AI pedagogy | |
| Mishra et al. | Intelligent chatbot for guided navigation of repository contend | |
| Ambacher | Designing a user-friendly and optimized version of a user interface for a large language model (LLM) | |
| Aeiad | A framework for an adaptable and personalised e-learning system based on free web resources | |
| Silva Bravo et al. | Improving learning material repositories using student profiles | |
| EP4539058A1 (en) | Systems and methods for regulating provision of messages with content from disparate sources based on risk and feedback data | |
| Nehaniv et al. | Introduction: Current work and open problems: A road-map for research into the emergence of communication and language | |
| FAZIO | Meet-AI: heuristics and evaluation platform for AI-infused systems |
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 |