CN117216228A - Psychological accompanying robot and interaction method thereof - Google Patents
Psychological accompanying robot and interaction method thereof Download PDFInfo
- Publication number
- CN117216228A CN117216228A CN202311473818.0A CN202311473818A CN117216228A CN 117216228 A CN117216228 A CN 117216228A CN 202311473818 A CN202311473818 A CN 202311473818A CN 117216228 A CN117216228 A CN 117216228A
- Authority
- CN
- China
- Prior art keywords
- interaction
- text
- interactive
- psychological
- robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 367
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000005457 optimization Methods 0.000 claims abstract description 64
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 230000003044 adaptive effect Effects 0.000 claims abstract description 21
- 238000012482 interaction analysis Methods 0.000 claims abstract description 10
- 230000002452 interceptive effect Effects 0.000 claims description 123
- 230000008859 change Effects 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000013210 evaluation model Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims 1
- 230000003340 mental effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 6
- 238000009472 formulation Methods 0.000 abstract description 3
- 239000000203 mixture Substances 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of robot interaction, and particularly discloses a psychological accompanying robot and an interaction method thereof, wherein the psychological accompanying robot comprises a robot main body and a robot interaction management system, the robot main body comprises a power supply system and a dialogue system, and the robot interaction management system comprises an interaction database, an interaction analysis module, an interaction optimization terminal and an interaction feedback terminal. According to the invention, through carrying out deep analysis on each input text during each interaction, the interaction satisfaction degree and interaction optimization demand degree of the user are counted, and the adaptive position ordering updating frequency of the reply text in the interaction language library is confirmed according to the interaction satisfaction degree and the interaction optimization demand degree, so that the problem that the fixed reply updating frequency is difficult to adjust according to the specific demand of each user is effectively solved, the interaction quality and the interaction effect of the psychological accompanying robot are ensured, the interaction accuracy of the psychological accompanying robot is improved, and the personalized formulation of the interaction optimization of the user is realized.
Description
Technical Field
The invention belongs to the technical field of robot interaction, and relates to a psychological accompanying robot and an interaction method thereof.
Background
With the increase of fast-paced life, high-pressure work, solitary old people and mental health problems in modern society, the demands of people for emotion support and mental health care are also increasing. Psychological accompanying robots have thus been developed, and their interactions need to be managed in order to secure the accompanying effect of the psychological accompanying robot.
The current psychological accompanying robot performs interaction based on pattern matching and a predefined script, and meanwhile, the interaction optimization is also based on preset updating frequency, and obviously, the current psychological accompanying robot interaction optimization mode has the following defects: 1. the fixed update frequency that replys is difficult to adjust according to every user's specific demand, and then can't ensure the timeliness of optimizing for interactive quality and interactive effect's guarantee nature is not strong, also can't improve interactive accuracy simultaneously.
2. The optimization accuracy cannot be guaranteed, the targeted optimization strategy is not formulated according to the actual interaction state of the psychological accompanying robot and the user in the period, and therefore the psychological accompanying robot is not high in optimization flexibility and reliability.
3. The interactive experience of the user cannot be guaranteed, the actual interaction state of the psychological accompanying robot and the user in the period is not deeply analyzed at present, and then interaction optimization is carried out, so that the interactive experience of the user is not strong, the psychological accompanying effect is difficult to guarantee, the interactive requirement of the user is also difficult to meet, and the satisfaction degree and the participation degree of the user cannot be improved.
Disclosure of Invention
In view of this, in order to solve the problems set forth in the background art, a psychological accompanying robot and an interaction method thereof are provided.
The aim of the invention can be achieved by the following technical scheme: the invention provides a psychological accompanying robot which comprises a robot main body and a robot interaction management system, wherein the robot main body comprises a power supply system and a dialogue system, the robot interaction management system comprises an interaction database, an interaction analysis module, an interaction optimization terminal and an interaction feedback terminal, the robot interaction management system is respectively connected with the power supply system and the dialogue system, and the interaction analysis module is respectively connected with the interaction database, the interaction optimization terminal and the interaction feedback terminal.
The interaction database is used for storing the conversation text, the interaction date and the accumulated conversation duration of the target user during each interaction in a set period, storing the set position updating frequency of the reply text in the interaction language library, and storing the content and the position ordering of each reply text in each interaction language library.
The interaction analysis module is used for counting the interaction satisfaction degree of the target user according to the conversation text of each interaction of the target user in the set periodAnd interaction optimization demand degree->And when the interactive satisfaction of the target user is less than the set interactive satisfaction +>Or the interaction optimization demand is greater than the set reference interaction demand>And when the method is used, confirming the updating frequency of the adaptive position of the reply text in the interactive language library.
And the interaction optimization terminal is used for carrying out corresponding updating according to the updating frequency of the adaptive position of the reply text in the interaction language library.
The interactive feedback terminal is used for carrying out interactive satisfaction feedback of the target user.
Further, the dialogue system comprises an image module and a voice module, wherein the image module comprises a camera and a display screen, and the voice module comprises a pickup and a voice broadcasting device.
Further, the power supply system comprises a storage battery, a charging device and a rectifier.
Further, the statistics of the interaction satisfaction degree of the target user includes: the content of each input text is positioned from the conversation text of each interaction of the target user in the set period, and then each text keyword of each input text of each interaction of the target user in the set period is identified through a keyword identification technology, so that a keyword set of each input text in each interaction is constructed.
Taking the first input text at each interaction as a reference text, taking other input texts as each comparison text, and counting the repetition tendencies of each comparison text and the reference text at each interactionI represents the interactive order number,/->，/>Representing the reference text number>。
If the repetition trend of a certain comparison text and a reference text is greater than 0 in certain interaction, the comparison text is used as the similar text of the reference text in the interaction, and the number of the similar texts corresponding to the reference text in each interaction is counted。
According to the interaction date of each interaction of the target user in the set period, counting the interaction utilization degree of the target user in the set period。
The accumulated conversation duration of each interaction of the target user in the set period and the set reference psychological accompany effective conversation duration are carried outComparing, if the accumulated session duration of a certain interaction is less than + ->The interaction is recorded as low-willingness interaction, and the low-willingness interaction times of the target user are counted>。
Statistics of interactive satisfaction of target users，，/>Representing the number of interactions +.>Representing the number of control texts,psychological companion robot regular interactive usage degree for setting reference, < >>Representing rounding down symbols.
Further, the counting the repetition tendencies of each comparison text and the reference text during each interaction includes: screening a keyword set of a reference text from a keyword set of each input text during each interactionAnd keyword set of each control text +.>。
Counting the repeat tendencies of each comparison text and reference text during each interaction，，/>For union sign +.>Is an intersection symbol.
Further, the statistics of the interactive usage degree of the target user in the set period includes: marking the interaction date in each interaction on a time number axis to obtain each marking point, forming two marking points into marking groups, dividing each marking point into each marking group according to the sequence of the interaction time, extracting the interval days between the two marking points in each marking group, and obtaining the average interval days between the two marking points in the marking group through average value calculation。
Marking a plurality of points in a two-dimensional coordinate system by taking the marking group order as an abscissa and taking the interval days as an ordinate, thereby constructing an interval days change curve, and positioning the number of fluctuation points from the interval days change curveAnd curve center point position.
Taking the arrow direction of the transverse axis in the two-dimensional coordinate system as the right side, extracting the slope of the curve positioned at the left side of the curve center point position and the right side of the curve center point position, and respectively marking asAnd->Simultaneously extracting the slope +.>。
Comparing the interaction dates of each interaction, recording the same interaction date as a comprehensive interaction date, and counting the number of the comprehensive interaction datesAnd the interaction times in each comprehensive interaction date, and further screening out the interaction times in each comprehensive interaction dateThe highest interaction times within the integrated interaction date +.>。
Counting interactive usage degree of target users in set period，，/>The difference between the interactive interval number of days, the overall interval number of days and the stage interval number of days and the difference between the interactive interval number of days, the overall interval number of days and the stage interval number of days are set as references>The number of fluctuations for the set reference interaction interval.
Further, the statistics of the interaction optimization desirability of the target user includes: and carrying out the same statistics according to the statistics mode of the number of the similar texts corresponding to the reference text in each interaction to obtain the number of the similar texts of each input text in each interaction.
If the ratio of the number of similar texts of a certain input text in a certain interaction to the number of input texts in the same interaction is larger thanThe interaction is noted as a repeated interaction and the input text at the time of the interaction is combined with its respective similar text into respective repeated input text.
Counting the number of repeated interactionsAnd locating the content of the reply text of the psychological accompanying robot corresponding to each repeated input text in each repeated interaction from the conversation text of each interaction of the target user in the set period, further locating the position order of the reply text content of the psychological accompanying robot corresponding to each repeated input text in the interactive language library in each repeated interaction from the interaction database,thereby confirming the number of interval sorting bits of the reply text at each repeated interaction>R denotes the repeat interactive sequence number, +.>。
If the interval sorting bit number of the reply text in a certain repeated interaction is larger than the set conventional interval sorting bit numberThe repeated interaction is recorded as deviation repeated interaction, and the deviation repeated interaction times are counted>。
Counting interaction optimization demand degree of target users，。
Further, the confirming the interval sorting bit number of the reply text when each repeated interaction comprises the following steps: and sequencing the repeated input texts of the target user in sequence according to the input time sequence during repeated interaction in a set period to obtain the input sequencing of the repeated input texts.
And recording the repeated input text of the first input order and the repeated input text of the last input order as the first text and the last text respectively.
And extracting the position ordering of the content of the reply text of the psychological accompanying robot corresponding to the head text and the tail text in the interactive language library during each repeated interaction, comparing to obtain the interval position ordering number between the content of the reply text of the psychological accompanying robot corresponding to the head text and the tail text during each repeated interaction, and taking the interval ordering number as the interval ordering number of the reply text during each repeated interaction.
Further, the reply text in the confirmation interactive language libraryThe adaptive position updating frequency comprises: locating a set location update frequency of reply text in an interaction database from the interaction database。
Obtaining the adaptive position updating frequency of the reply text in the interactive language library through the interactive language library frequency updating evaluation model evaluationWherein the interactive language library frequency update evaluation model is expressed as: />，Updating evaluation conditions for each set interactive language library frequency, respectively,>the frequency value is updated for the set compensation,optimizing an increased update frequency value corresponding to the demand level deviation for the set unit interaction, and +.>Optimizing the desirability for setting the interaction of the reference +.>Indicating that only +.>，/>Indicating that only +.>，/>Indicating the simultaneous presence +.>And。
the second aspect of the present invention also provides a psychological accompanying robot interaction method, which comprises: step 1, accompany interactive data extraction: and extracting the session text of the target user in each interaction in the set period.
Step 2, interaction satisfaction analysis and feedback: analyzing the session text of each interaction of the target user in a set period, obtaining the interaction satisfaction of the target user, and feeding back the interaction satisfaction;
step 3, analyzing the interaction update demand: and analyzing the session text of each interaction of the target user in a set period to obtain the interaction optimization demand of the target user.
Step 4, judging the interactive updating requirement: and (3) when the interaction optimization demand level of the target user is greater than the set interaction optimization demand level or when the interaction satisfaction level is less than the set interaction satisfaction level, judging that the interaction optimization is required, and executing the step (5), otherwise, judging that the interaction optimization is not required.
Step 5, confirming an interactive update strategy: and confirming the adaptive position updating frequency of the reply text in the interactive language library.
Step 6, interactive updating execution: and correspondingly updating according to the updating frequency of the adaptive position of the reply text in the interactive language library.
Compared with the prior art, the invention has the following beneficial effects: (1) According to the invention, the interactive satisfaction degree and the interactive optimization demand degree of the users are counted, and the adaptive position updating frequency of the reply text in the interactive language library is confirmed according to the interactive satisfaction degree and the interactive optimization demand degree, so that the problem that the fixed reply updating frequency is difficult to adjust according to the specific demands of each user is effectively solved, the interactive quality and the interactive effect of the psychological accompanying robot are ensured, the interactive accuracy of the psychological accompanying robot is also improved, and meanwhile, the targeted formulation of the interactive reply updating optimization strategy of the users is realized, so that the flexibility and the reliability of the psychological accompanying robot optimization and the psychological accompanying effect of the psychological accompanying robot are improved, and the interactive experience of the users is further ensured.
(2) According to the invention, through carrying out deep analysis on the conversation text interacted by the user for each time, further carrying out interaction satisfaction analysis from three dimensions of conversation wish, conversation content repetition condition and use condition of the psychological accompanying robot in a set period of the user, and feeding back, the defect that the interaction satisfaction analysis dimension of the current psychological accompanying robot is single and limited is effectively avoided, the convincing and reliability of the interaction satisfaction analysis result of the psychological accompanying robot are improved, and further development of the interaction optimization plan of the psychological accompanying robot is facilitated, and timeliness of interaction optimization of the psychological accompanying robot is ensured.
(3) According to the invention, through analyzing the change rule of the integral interaction interval days, the change rule of the staged interaction interval days and the coverage condition of the interaction dates according to the interaction dates of each interaction, the interactive use degree of a target user in a set period is counted, the multidimensional interactive use assessment of the psychological accompanying robot is realized, the rationality and the accuracy of the interactive use degree assessment result are ensured, thereby providing a reliable reference basis for the subsequent psychological accompanying robot interactive satisfaction analysis, and improving the authenticity and the referential of the subsequent psychological accompanying robot interactive satisfaction analysis.
(4) According to the invention, the repeated interaction times are confirmed by carrying out the deep analysis on each input text during each interaction, and the sequence of the positions of the reply texts of the psychological accompanying robot in the interactive language library during the repeated interaction is analyzed, so that the interaction optimization demand of a target user is counted, the reasonable situation of the position setting of the reply texts in the interactive language library and the adaptation situation of the reply texts and the user input texts are intuitively displayed, the defect that the single analysis is carried out only from the interaction repeated layer at present is avoided, the reference basis of the interaction optimization demand analysis is expanded, and the timeliness of interaction optimization is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is 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 schematic diagram of a psychological accompanying robot according to the present invention.
Fig. 2 is a schematic diagram of a conversation system of a psychological companion robot according to the present invention.
Fig. 3 is a schematic connection diagram of modules of the psychological accompanying robot interaction management system according to the present invention.
FIG. 4 is a flow chart of the steps of the method of the present invention.
Detailed Description
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 be within the scope of the invention.
Referring to fig. 1 and 3, the invention provides a psychological accompanying robot, which comprises a robot main body and a robot interaction management system, wherein the robot main body comprises a power supply system and a dialogue system, and the robot interaction management system comprises an interaction database, an interaction analysis module, an interaction optimization terminal and an interaction feedback terminal.
In the above, the robot interaction management system is connected with the power supply system and the dialogue system respectively, and the interaction analysis module is connected with the interaction database, the interaction optimization terminal and the interaction feedback terminal respectively.
In an embodiment of the present invention, further, referring to fig. 2, the dialogue system includes an image module and a voice module, where the image module includes a camera and a display screen, and the voice module includes a sound pickup and a voice broadcasting device.
In an embodiment of the present invention, further, the power supply system includes a storage battery, a charging device, and a rectifier.
In the embodiment of the invention, further, the interaction database is used for storing the session text, the interaction date and the accumulated session duration of each interaction of the target user in a set period, storing the set position updating frequency of the reply text in the interaction language library, and storing the content and the position ordering of each reply text in each interaction language library.
In the embodiment of the invention, the interaction analysis module is further used for counting the interaction satisfaction degree of the target user according to the session text of each interaction of the target user in the set periodAnd interaction optimization demand degree->And when the interactive satisfaction of the target user is less than the set interactive satisfaction +>Or the interaction optimization demand is greater than the set reference interaction demandAnd when the method is used, confirming the updating frequency of the adaptive position of the reply text in the interactive language library.
Illustratively, the statistics of the interactive satisfaction of the target user include: and E1, positioning the content of each input text from the conversation text of the target user in each interaction in the set period, and further identifying each text keyword of each input text of the target user in each interaction in the set period through a keyword identification technology, thereby constructing a keyword set of each input text in each interaction.
E2, taking the first input text at each interaction as a reference text, taking other input texts as each comparison text, and counting the repetition tendencies of each comparison text and the reference text at each interactionI represents the interactive sequence number,，/>representing the reference text number>。
Understandably, counting the repetition tendencies of each control text and reference text at each interaction includes: e2-1, screening the keyword set of the reference text from the keyword set of each input text in each interactionAnd keyword set of each control text +.>。
E2-2, counting the repetition tendencies of each comparison text and reference text in each interaction，，/>For union sign +.>Is an intersection symbol.
E3, if the repetition trend of a certain comparison text and a reference text is greater than 0 in certain interaction, using the comparison text as the similar text of the reference text in the interaction, and counting the number of the similar texts corresponding to the reference text in each interaction。
E4, counting the interactive use degree of the target user in the set period according to the interactive date of each interaction of the target user in the set period。
Understandably, counting the interactive usage of the target user in the set period includes: e4-1, marking the interaction date in each interaction on a time number axis to obtain each marking point, forming marking groups by the two marking points, dividing each marking point into each marking group according to the sequence of the interaction time, extracting the interval days between the two marking points in each marking group, and obtaining the average interval days between the two marking points in the marking group through mean value calculation。
E4-2, marking a plurality of points in a two-dimensional coordinate system by taking the marking group order as an abscissa and taking the interval days as an ordinate, thereby constructing an interval days change curve, and positioning the number of fluctuation points from the interval days change curveAnd curve center point position.
E4-3, taking the arrow direction of the transverse axis in the two-dimensional coordinate system as the right side, extracting the curve slopes positioned at the left side of the curve center point position and the right side of the curve center point position, and respectively marking asAnd->Simultaneously extracting the slope +.>。
E4-4, comparing the interaction dates of each interaction, marking the same interaction date as a comprehensive interaction date, and counting the number of the comprehensive interaction datesAnd the interaction times in each comprehensive interaction date, and further screening out the comprehensive interaction timesThe highest interaction times within the interaction date +.>。
E4-5, counting interactive usage degree of target users in set period，，/>The difference between the interactive interval number of days, the overall interval number of days and the stage interval number of days and the difference between the interactive interval number of days, the overall interval number of days and the stage interval number of days are set as references>The number of fluctuations for the set reference interaction interval.
In one embodiment of the present invention, in one embodiment,this part reflects the frequent interaction of the user with his psychological companion robot, +.>The change condition of the interaction interval in the whole period is reflected, when the number of the interaction interval is larger, the lower the interaction demand of the user on the psychological accompanying robot is, the lower the usage degree is, and the user is->The interaction interval change conditions in two interaction stages before and after the set period are reflected, and the fact that the interaction interval in the later stage is less than that in the former stage shows that the overall trend of interaction viscosity of a user on the psychological accompanying robot is increased, namely the use trend is frequent.
The slope refers to the slope of the regression line corresponding to the curve, i.eThe representation is located atSlope of regression line corresponding to left curve of curve center point position, +.>Represents the slope of the corresponding regression line of the curve to the right of the center point of the curve,the slope of the regression line corresponding to the change curve of days of interval is shown.
According to the embodiment of the invention, the change rule of the integral interaction interval days, the change rule of the staged interaction interval days and the coverage condition analysis of the interaction dates are carried out according to the interaction dates of each interaction, so that the interaction usage degree of a target user in a set period is counted, the multi-dimensional interaction usage assessment of the psychological accompanying robot is realized, the rationality and the accuracy of the interaction usage assessment result are ensured, a reliable reference basis is provided for the interaction satisfaction analysis of the subsequent psychological accompanying robot, and the authenticity and the reference of the interaction satisfaction analysis of the subsequent psychological accompanying robot are improved.
In one embodiment of the present invention, in one embodiment,this part reflects the coverage of the user on the interaction date of the psychological accompanying robot, and the more concentrated the interaction date, the lower the daily degree of interaction between the user and the psychological accompanying robot, namely the lower the interactive use degree.
In a further embodiment of the present invention,for evaluating the correction factor, when the number of fluctuation points is larger, the error of the result is larger, and the correction requirement is larger, wherein the fluctuation points refer to points with opposite left and right development trends in the curve, such as left-side rising and right-side falling or left-side falling and right-side rising points.
E5, integrating the conversation duration of each interaction of the target user in the set period and the conversation duration with the set reference psychological co-effectComparing, if the accumulated session duration of a certain interaction is less than + ->The interaction is recorded as low-willingness interaction, and the low-willingness interaction times of the target user are counted>。
E6, statistics of interactive satisfaction of target users，，/>Representing the number of interactions +.>Representing the number of control texts,psychological companion robot regular interactive usage degree for setting reference, < >>Representing rounding down symbols.
In a specific embodiment, when more repeated conversations in one interactive process indicate poorer interactive quality and interactive effect, that is, poorer desirability of reply, the satisfaction of interaction is lower, and when the conversation will be lower and the number of low will conversations is more, the interest of the user is lower, and further, the satisfaction of interaction is lower.
According to the embodiment of the invention, through carrying out deep analysis on the conversation text interacted by the user for each time, further carrying out interaction satisfaction analysis from three dimensions of conversation wish, conversation content repetition condition and use condition of the psychological accompanying robot in a set period of the user, and feeding back, the defect that the interaction satisfaction analysis dimension of the current psychological accompanying robot is single and limited is effectively avoided, the persuasion and reliability of the interaction satisfaction analysis result of the psychological accompanying robot are improved, and further development of the interaction optimization plan of the psychological accompanying robot is facilitated, and timeliness of interaction optimization of the psychological accompanying robot is ensured.
Illustratively, the statistics of the interaction optimization desirability of the target user include: q1, carrying out statistics in a similar way according to the number of similar texts corresponding to the reference text in each interaction to obtain the number of similar texts of each input text in each interaction.
Q2, if the ratio of the number of similar texts of a certain input text in a certain interaction to the number of input texts in the interaction is larger thanThe interaction is noted as a repeated interaction and the input text at the time of the interaction is combined with its respective similar text into respective repeated input text.
Q3, counting the repeated interaction timesThe content of the reply text of the psychological accompanying robot corresponding to each repeated input text in each repeated interaction is positioned from the conversation text of each interaction in a set period of a target user, and then the position order of the reply text content of the psychological accompanying robot corresponding to each repeated input text in the interactive language library in each repeated interaction is positioned from an interaction database, so that the interval order bit of the reply text in each repeated interaction is confirmed>R denotes the repeat interactive sequence number, +.>。
Understandably, confirming the number of spaced-order digits of the reply text at each repeated interaction includes: q3-1, sequentially sequencing the repeated input texts of the target user in each repeated interaction within the set period according to the input time sequence, and obtaining the input sequencing of the repeated input texts.
Q3-2, recording the repeated input text of the first input order and the repeated input text of the last input order as the first text and the last text respectively.
Q3-3, extracting the position sequence of the reply text content of the psychological accompanying robot corresponding to the first text and the last text in the interactive language library during each repeated interaction, comparing to obtain the interval position sequence number between the reply text content of the psychological accompanying robot corresponding to the first text and the last text during each repeated interaction, and taking the interval sequence number as the interval sequence number of the reply text during each repeated interaction.
In one particular embodiment, an example of analysis of the interval position ordering is: when the position ordering of the first text is the first bit and the position ordering of the last text is the eighth bit in repeated interaction, the interval ordering bit number of the reply text in repeated interaction is 7.
Q4, if the interval sequencing bit number of the reply text in a certain repeated interaction is larger than the set conventional interval sequencing bit numberThe repeated interaction is recorded as deviation repeated interaction, and the deviation repeated interaction times are counted>。
Q5, counting interaction optimization demand degree of target users，。
In a specific embodiment, the more the number of times the user repeatedly inputs the text indicates that the reply of the psychological accompanying robot deviates from the ideal reply of the user, that is, the reply effect is difficult to reach the overdue of the user, while the psychological accompanying robot carries out corresponding selection reply through the set reply weight when the set reply is general, that is, replies according to the set reply sequence, and when the interval sequencing bits between the initial reply and the last reply of the psychological accompanying robot for the same or similar problems are more, the poorer the rationality of the reply setting of the psychological accompanying robot is, the more the interactive requirement of the user is deviated, and further the higher the updating requirement of the position sequencing of the reply text in the interactive language library of the psychological accompanying robot is indicated.
According to the embodiment of the invention, the repeated interaction times are confirmed by carrying out the deep analysis on each input text during each interaction, and the position sequence of the reply text of the psychological accompanying robot in the interaction language library during the repeated interaction is analyzed, so that the interaction optimization demand of a target user is counted, the reasonable situation of the position setting of the reply text in the interaction language library and the adaptation situation of the reply text and the input text of the user are intuitively displayed, the defect that the single analysis is carried out only from the interaction repeated layer at present is avoided, the reference basis of the interaction optimization demand analysis is expanded, and the timeliness of interaction optimization is ensured.
Still another exemplary method for confirming the adaptive location update frequency of the reply text in the interactive corpus includes: the first step, locating the set position updating frequency of the replying text in the interactive language library from the interactive database。
Secondly, estimating and obtaining the adaptive position updating frequency of the reply text in the interactive language library through the interactive language library frequency updating estimation modelWherein the interactive language library frequency update evaluation model is expressed as:，/>updating evaluation conditions for each set interactive language library frequency, respectively,>updating the frequency value for the set compensation, +.>Optimizing an increased update frequency value corresponding to the demand level deviation for the set unit interaction, and +.>Optimizing the desirability for setting the interaction of the reference +.>Indicating that only +.>，/>Indicating the presence of only，/>Indicating the simultaneous presence +.>And->。
According to the embodiment of the invention, the interactive satisfaction degree and the interactive optimization demand degree of the user are counted, and the adaptive position updating frequency of the reply text in the interactive language library is confirmed according to the interactive satisfaction degree and the interactive optimization demand degree, so that the problem that the fixed reply updating frequency is difficult to adjust according to the specific demands of each user is effectively solved, the interactive quality and the interactive effect of the psychological accompanying robot are ensured, the interactive accuracy of the psychological accompanying robot is also improved, and meanwhile, the pertinence formulation of the interactive reply updating optimization strategy of the user is realized, so that the flexibility and the reliability of the psychological accompanying robot optimization and the psychological accompanying effect of the psychological accompanying robot are improved, and the interactive experience of the user is further ensured.
In the embodiment of the invention, further, the interaction optimization terminal is used for carrying out corresponding update according to the update frequency of the adaptive position of the reply text in the interaction language library.
In the embodiment of the invention, further, the interaction feedback terminal is used for performing interaction satisfaction feedback of the target user.
Referring to fig. 4, the invention further provides a psychological accompanying robot interaction method, which comprises the following steps: step 1, accompany interactive data extraction: and extracting the session text of the target user in each interaction in the set period.
Step 2, interaction satisfaction analysis and feedback: analyzing the session text of each interaction of the target user in a set period, obtaining the interaction satisfaction of the target user, and feeding back the interaction satisfaction;
step 3, analyzing the interaction update demand: and analyzing the session text of each interaction of the target user in a set period to obtain the interaction optimization demand of the target user.
Step 4, judging the interactive updating requirement: and (3) when the interaction optimization demand level of the target user is greater than the set interaction optimization demand level or when the interaction satisfaction level is less than the set interaction satisfaction level, judging that the interaction optimization is required, and executing the step (5), otherwise, judging that the interaction optimization is not required.
Step 5, confirming an interactive update strategy: and confirming the adaptive position updating frequency of the reply text in the interactive language library.
Step 6, interactive updating execution: and correspondingly updating according to the updating frequency of the adaptive position of the reply text in the interactive language library.
The foregoing is merely illustrative and explanatory of the principles of this invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this invention or beyond the scope of this invention as defined in the claims.
Claims (10)
1. The utility model provides a psychological accompanying robot, includes robot main part and robot interaction management system, the robot main part includes power supply system and dialogue system, its characterized in that: the robot interaction management system comprises an interaction database, an interaction analysis module, an interaction optimization terminal and an interaction feedback terminal, wherein the robot interaction management system is respectively connected with the power supply system and the dialogue system, and the interaction analysis module is respectively connected with the interaction database, the interaction optimization terminal and the interaction feedback terminal;
the interactive database is used for storing the conversation text, the interactive date and the accumulated conversation duration of each interaction of the target user in a set period, storing the set position updating frequency of the reply text in the interactive language library, and storing the content and the position ordering of each reply text in each interactive language library;
the interaction analysis module is used for counting the interaction satisfaction degree of the target user according to the conversation text of each interaction of the target user in the set periodAnd interaction optimization demand degree->And when the interactive satisfaction of the target user is less than the set interactive satisfaction +>Or the interaction optimization demand is greater than the set reference interaction demand>When the method is used, the updating frequency of the adaptive position of the reply text in the interactive language library is confirmed;
the interaction optimization terminal is used for carrying out corresponding updating according to the updating frequency of the adaptive position of the reply text in the interaction language library;
the interactive feedback terminal is used for carrying out interactive satisfaction feedback of the target user.
2. The psychological companion robot of claim 1 wherein: the dialogue system includes image module and voice module, and wherein, image module includes camera and display screen, and voice module includes adapter and voice broadcast ware.
3. The psychological companion robot of claim 1 wherein: the power supply system comprises a storage battery, a charging device and a rectifier.
4. The psychological companion robot of claim 1 wherein: the statistics of the interaction satisfaction degree of the target user comprises the following steps:
positioning the content of each input text from the conversation text of each interaction of the target user in the set period, and further identifying each text keyword of each input text of each interaction of the target user in the set period through a keyword identification technology, thereby constructing a keyword set of each input text of each interaction;
taking the first input text at each interaction as a reference text, taking other input texts as each comparison text, and counting the repetition tendencies of each comparison text and the reference text at each interactionI represents the interactive order number,/->，/>Representing the reference text number>；
If the repetition trend of a certain comparison text and a reference text is greater than 0 in certain interaction, the comparison text is used as the similar text of the reference text in the interaction, and the number of the similar texts corresponding to the reference text in each interaction is counted；
According to the interaction date of each interaction of the target user in the set period,counting interactive usage degree of target users in set period；
The accumulated conversation duration of each interaction of the target user in the set period and the set reference psychological accompany effective conversation duration are carried outComparing, if the accumulated session duration of a certain interaction is less than + ->The interaction is recorded as low-willingness interaction, and the low-willingness interaction times of the target user are counted>；
Statistics of interactive satisfaction of target users，，/>Representing the number of interactions +.>Representing the number of control texts,psychological companion robot regular interactive usage degree for setting reference, < >>Representing rounding down symbols.
5. The psychological companion robot of claim 4 wherein: and counting the repetition tendencies of each comparison text and the reference text in each interaction, wherein the method comprises the following steps of:
screening a keyword set of a reference text from a keyword set of each input text during each interactionAnd keyword set of each control text +.>；
Counting the repeat tendencies of each comparison text and reference text during each interaction，/>，/>For union sign +.>Is an intersection symbol.
6. The psychological companion robot of claim 4 wherein: the statistics of the interactive usage degree of the target user in the set period comprises the following steps:
marking the interaction date in each interaction on a time number axis to obtain each marking point, forming two marking points into marking groups, dividing each marking point into each marking group according to the sequence of the interaction time, extracting the interval days between the two marking points in each marking group, and obtaining the average interval days between the two marking points in the marking group through average value calculation；
Ordering by labeling group as abscissa, spacing days as ordinate,marking a plurality of points in a two-dimensional coordinate system, thereby constructing a change curve of the number of interval days, and positioning the number of fluctuation points from the change curve of the number of interval daysAnd the curve center point position;
taking the arrow direction of the transverse axis in the two-dimensional coordinate system as the right side, extracting the slope of the curve positioned at the left side of the curve center point position and the right side of the curve center point position, and respectively marking asAnd->Simultaneously extracting the slope +.>；
Comparing the interaction dates of each interaction, recording the same interaction date as a comprehensive interaction date, and counting the number of the comprehensive interaction datesAnd the interaction times in each comprehensive interaction date, and then screening out the highest interaction times in the comprehensive interaction date>；
Counting interactive usage degree of target users in set period，，/>The number of interaction interval days and the number of overall interval days are respectively increased for setting referenceDeviation of growth rate of long rate and days of stage interval, +.>The number of fluctuations for the set reference interaction interval.
7. The psychological companion robot of claim 4 wherein: the statistics of the interaction optimization demand degree of the target user comprises the following steps:
the similar text number of each input text in each interaction is obtained by carrying out the same statistics according to the statistical mode of the similar text number of the corresponding reference text in each interaction;
if the ratio of the number of similar texts of a certain input text in a certain interaction to the number of input texts in the same interaction is larger thanRecording the interaction as repeated interaction, and combining the input text and each similar text thereof during the interaction into each repeated input text;
counting the number of repeated interactionsThe content of the reply text of the psychological accompanying robot corresponding to each repeated input text in each repeated interaction is positioned from the conversation text of each interaction in a set period of a target user, and then the position order of the reply text content of the psychological accompanying robot corresponding to each repeated input text in the interactive language library in each repeated interaction is positioned from an interaction database, so that the interval order bit of the reply text in each repeated interaction is confirmed>R denotes the repeat interactive sequence number, +.>；
If the interval sorting number of the reply text in a certain repeated interaction is larger than the preset regular interval sortingNumber of sequence digitsThe repeated interaction is recorded as deviation repeated interaction, and the deviation repeated interaction times are counted>；
Counting interaction optimization demand degree of target users，/>。
8. The mental companion robot of claim 7 wherein: the method for confirming the interval sequencing digits of the reply text in each repeated interaction comprises the following steps:
sequentially sequencing all repeated input texts of a target user in a set period according to the input time sequence during repeated interaction to obtain the input sequencing of all the repeated input texts;
the repeated input text of the first input order and the repeated input text of the last input order are respectively recorded as a first text and a last text;
and extracting the position ordering of the content of the reply text of the psychological accompanying robot corresponding to the head text and the tail text in the interactive language library during each repeated interaction, comparing to obtain the interval position ordering number between the content of the reply text of the psychological accompanying robot corresponding to the head text and the tail text during each repeated interaction, and taking the interval ordering number as the interval ordering number of the reply text during each repeated interaction.
9. The psychological companion robot of claim 1 wherein: the method for confirming the adaptive position updating frequency of the reply text in the interactive language library comprises the following steps:
locating a set location update for reply text in an interaction databaseFrequency of；
Obtaining the adaptive position updating frequency of the reply text in the interactive language library through the interactive language library frequency updating evaluation model evaluationWherein the interactive language library frequency update evaluation model is expressed as: />，Updating evaluation conditions for each set interactive language library frequency, respectively,>the frequency value is updated for the set compensation,optimizing an increased update frequency value corresponding to the demand level deviation for the set unit interaction, and +.>Optimizing the desirability for setting the interaction of the reference +.>Indicating that only +.>，/>Indicating that only +.>，/>Indicating the simultaneous presence +.>And。
10. a psychological accompanying robot interaction method is characterized in that: the method comprises the following steps:
step 1, accompany interactive data extraction: extracting a conversation text of a target user during each interaction in a set period;
step 2, interaction satisfaction analysis and feedback: analyzing the session text of each interaction of the target user in a set period, obtaining the interaction satisfaction of the target user, and feeding back the interaction satisfaction;
step 3, analyzing the interaction update demand: analyzing a session text of each interaction of the target user in a set period to obtain interaction optimization demand of the target user;
step 4, judging the interactive updating requirement: when the interaction optimization demand level of the target user is larger than the set interaction optimization demand level or when the interaction satisfaction level is smaller than the set interaction satisfaction level, judging that the interaction optimization is required, and executing the step 5, otherwise, judging that the interaction optimization is not required;
step 5, confirming an interactive update strategy: confirming the updating frequency of the adaptive position of the reply text in the interactive language library;
step 6, interactive updating execution: and correspondingly updating according to the updating frequency of the adaptive position of the reply text in the interactive language library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473818.0A CN117216228B (en) | 2023-11-08 | 2023-11-08 | Psychological accompanying robot and interaction method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473818.0A CN117216228B (en) | 2023-11-08 | 2023-11-08 | Psychological accompanying robot and interaction method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117216228A true CN117216228A (en) | 2023-12-12 |
| CN117216228B CN117216228B (en) | 2024-02-02 |
Family
ID=89035636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311473818.0A Active CN117216228B (en) | 2023-11-08 | 2023-11-08 | Psychological accompanying robot and interaction method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216228B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190182382A1 (en) * | 2017-12-13 | 2019-06-13 | Genesys Telecomminications Laboratories, Inc. | Systems and methods for chatbot generation |
| US20190287524A1 (en) * | 2018-03-15 | 2019-09-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining speech interaction satisfaction |
| CN112988774A (en) * | 2021-03-23 | 2021-06-18 | 汪威 | User information updating method based on big data acquisition and information server |
| CN115512702A (en) * | 2022-10-11 | 2022-12-23 | 徐州工程学院 | Accompanying robot and emotion recognition system |
| CN116028823A (en) * | 2022-12-27 | 2023-04-28 | 有米科技股份有限公司 | Loss calculation method and device based on multi-mode semantic interaction |
| CN116737906A (en) * | 2023-07-03 | 2023-09-12 | 百度在线网络技术（北京）有限公司 | Information display method, device, electronic equipment and storage medium |
-
2023
- 2023-11-08 CN CN202311473818.0A patent/CN117216228B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190182382A1 (en) * | 2017-12-13 | 2019-06-13 | Genesys Telecomminications Laboratories, Inc. | Systems and methods for chatbot generation |
| US20190287524A1 (en) * | 2018-03-15 | 2019-09-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining speech interaction satisfaction |
| CN112988774A (en) * | 2021-03-23 | 2021-06-18 | 汪威 | User information updating method based on big data acquisition and information server |
| CN115512702A (en) * | 2022-10-11 | 2022-12-23 | 徐州工程学院 | Accompanying robot and emotion recognition system |
| CN116028823A (en) * | 2022-12-27 | 2023-04-28 | 有米科技股份有限公司 | Loss calculation method and device based on multi-mode semantic interaction |
| CN116737906A (en) * | 2023-07-03 | 2023-09-12 | 百度在线网络技术（北京）有限公司 | Information display method, device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王堃 等: "端到端对话系统意图语义槽联合识别研究综述", 计算机工程与应用, vol. 56, no. 14, pages 14 - 25 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117216228B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104869439B (en) | A kind of video pushing method and device | |
| CN103995870A (en) | Interactive searching method and device | |
| CN111383058A (en) | High-reliability online questionnaire survey method and system | |
| CN108733712B (en) | Question-answering system evaluation method and device | |
| CN109597808B (en) | Word sorting method and learning method according to word difficulty | |
| CN110515999A (en) | General record processing method, device, electronic equipment and storage medium | |
| CN112163081A (en) | Label determination method, device, medium and electronic equipment | |
| CN112529750A (en) | Learning event recommendation method and system based on graph neural network model | |
| CN110688471B (en) | Training sample obtaining method, device and equipment | |
| CN117216228B (en) | Psychological accompanying robot and interaction method thereof | |
| CN101739418A (en) | Method for sequencing multi-index comprehensive weight audio-video album | |
| CN116342074B (en) | Engineering project consultation expert base talent matching service system | |
| CN109961804A (en) | Smart machine satisfaction assessment method, apparatus and storage medium | |
| CN101739417A (en) | System for sequencing multi-index comprehensive weight audio-video album | |
| CN111091411B (en) | Questionnaire segmentation design method | |
| CN111933128A (en) | Method and device for processing question bank of questionnaire and electronic equipment | |
| CN113673609B (en) | Questionnaire data analysis method based on linear hidden variables | |
| CN110795630B (en) | Learning scheme recommendation method and device | |
| CN114550157A (en) | Bullet screen gathering identification method and device | |
| CN114939276B (en) | Game operation data analysis method, system and storage medium | |
| CN116579305A (en) | Intelligent word document editing and generating system | |
| CN115630173B (en) | User data management method based on interestingness analysis | |
| CN118081786A (en) | Mobile psychological service robot | |
| CN116805273A (en) | Teaching quality supervision system based on cloud computing | |
| CN112328645B (en) | Method and system for determining interests and hobbies of users based on knowledge graph |
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 |