WO2019010682A1 - 机器人性格设定方法、装置和机器人 - Google Patents

机器人性格设定方法、装置和机器人 Download PDF

Info

Publication number
WO2019010682A1
WO2019010682A1 PCT/CN2017/092879 CN2017092879W WO2019010682A1 WO 2019010682 A1 WO2019010682 A1 WO 2019010682A1 CN 2017092879 W CN2017092879 W CN 2017092879W WO 2019010682 A1 WO2019010682 A1 WO 2019010682A1
Authority
WO
WIPO (PCT)
Prior art keywords
personality
attribute
value
user
feature
Prior art date
Application number
PCT/CN2017/092879
Other languages
English (en)
French (fr)
Inventor
骆磊
Original Assignee
深圳前海达闼云端智能科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳前海达闼云端智能科技有限公司 filed Critical 深圳前海达闼云端智能科技有限公司
Priority to CN201780003250.2A priority Critical patent/CN108472811B/zh
Priority to PCT/CN2017/092879 priority patent/WO2019010682A1/zh
Priority to JP2020501506A priority patent/JP6979115B2/ja
Publication of WO2019010682A1 publication Critical patent/WO2019010682A1/zh
Priority to US16/741,326 priority patent/US11045957B2/en

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J11/00Manipulators not otherwise provided for
    • B25J11/0005Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means

Definitions

  • the embodiments of the present application relate to the field of artificial intelligence, for example, to a robot personality setting method, apparatus, and robot.
  • Robots With the development of artificial intelligence technology, robots have brought a lot of convenience to human production and life. Robots have gradually occupied an important position in an unprecedented way and speed. Robots of various shapes and functions are gradually being developed.
  • the inventors found that at least the following problems exist in the related art: at present, the appearance, intelligence level, and personality characteristics of the robot are generally set at the time of leaving the factory, that is, their personality characteristics are fixed.
  • the robot faces different users. In many cases, the character of the robot cannot be enjoyed by the user, resulting in a lower user experience.
  • An object of the embodiments of the present application is to provide a new robot personality setting method, apparatus, and robot, which can perform personality feature adjustment according to user preferences, and the user experience is high.
  • an embodiment of the present application provides a robot personality setting method, where the personality setting method is applied to a robot, and the method includes:
  • the personality feature includes a plurality of personality attributes, each of the personality attributes having an attribute value;
  • the action or voice is performed according to the attribute value of the personality attribute in the current personality feature.
  • the embodiment of the present application further provides a robot personality setting device, where the personality setting device is applied to a robot, and the device includes:
  • An adjustment module configured to adjust an attribute value of a personality attribute in a preset personality feature according to a feedback of the user, where the personality feature includes a plurality of personality attributes, each of the personality attributes having an attribute value;
  • An execution module for performing an action or a voice according to an attribute value of a personality attribute in a current personality feature.
  • the embodiment of the present application further provides a robot, including:
  • At least one processor and,
  • the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.
  • the character setting method and apparatus provided by the embodiment of the present application can make the robot obtain the user's favorite by adjusting the attribute value of the personality attribute according to the feedback of the user and performing the corresponding action or voice according to the attribute value of the personality attribute in the current personality feature.
  • the character that is, the personality of the robot can be set according to the user's preference, and the user experience is good.
  • FIG. 1 is a schematic diagram of an application scenario of the method and apparatus of the present application.
  • FIG. 2 is a schematic diagram of an application scenario of the method and apparatus of the present application.
  • FIG. 3 is a flow chart of an embodiment of a personality setting method of the present application.
  • FIG. 4 is a flow chart of one embodiment of a personality setting method of the present application.
  • FIG. 5 is a schematic flow chart showing the steps of obtaining a user expectation value of a personality attribute in one embodiment of the personality setting method of the present application;
  • FIG. 6 is a schematic flow chart showing the steps of obtaining a user expectation value of a personality attribute in one embodiment of the personality setting method of the present application;
  • Figure 7 is a schematic structural view of an embodiment of the personality setting device of the present application.
  • FIG. 8 is a schematic structural view of an embodiment of a personality setting device of the present application.
  • FIG. 9 is a schematic structural diagram of an expectation value acquisition module in one embodiment of the personality setting device of the present application.
  • FIG. 10 is a schematic structural diagram of an expectation value acquisition module in one embodiment of the personality setting device of the present application.
  • FIG. 11 is a schematic structural view of an embodiment of a personality setting device of the present application.
  • FIG. 12 is a schematic structural view of an embodiment of a personality setting device of the present application.
  • FIG. 13 is a schematic diagram showing the hardware structure of a robot for setting a personality according to an embodiment of the present application.
  • the robot personality setting method and apparatus provided by the present application are applicable to the application scenarios as shown in FIG. 1 and FIG. 2, including the user 10 and the robot 20, and the robot 20 may be one or more (FIG. 1 shows a scene of a robot)
  • Figure 2 shows the scene of multiple robots).
  • multiple robots The two can communicate with each other through the network 30, wherein the network 30 can be, for example, a home or company local area network, or a specific network or the like.
  • the bot 20 has at least one network interface that establishes a communication connection with the network 30 to retrieve data or instructions from the network 30.
  • the user 10 can set up, issue commands, or talk to the robot 20 for a plurality of robots 20.
  • Each of the robots 20 has a personality feature, which may be set at the time of shipment, or the user 10 may select one of the plurality of preset personality features, and the robot 20 sets according to the instruction of the user 10. Alternatively, the robot 20 actively selects one of the plurality of preset personality features to set itself.
  • the plurality of personality features may be preset at the factory or may be downloaded through the cloud after leaving the factory.
  • the personality trait includes a plurality of personality attributes, each personality attribute has an attribute value, and the type of the personality attribute can be refined in the upgrading process, and the more detailed the character characterization is, the more accurate the character trait structure can be as follows Show:
  • personality trait 1 may be configured as follows:
  • Personality feature 2 may be configured as follows:
  • the degree of cheerfulness, the degree of active speaking, the degree of liveliness, and the like indicate the category of the personality attribute, and the numerical value indicates the attribute value of the personality attribute category.
  • the attribute value of a certain personality attribute can be adjusted according to the feedback of the user 10.
  • the robot 20 is set to the character feature 2, and the temper size value in the personality feature 2 is 8, and the user 10 complains that the temper of the robot 20 is too large, and the robot is expected not to have such a large temper, and the robot 20 adjusts the temper size to 6, However, the user was still not satisfied for the next two days, and the robot 20 continued to adjust the temper size to 4.
  • the attribute value of the personality attribute may be adjusted by the robot 20 according to the instruction of the user 10, or the robot 20 may determine the need to adjust according to the voice command or the content of the user, and then the personality attribute of the character.
  • the property values are adjusted.
  • the robot can obtain the character that the user likes, that is, the character setting of the robot can be performed according to the user's preference, and the user experience is high.
  • the embodiment of the present application provides a robot personality setting method, which may be performed by any of the robots 20 shown in FIG. 1 or FIG. 2, as shown in FIG. 3, the method includes:
  • Step 101 Adjust an attribute value of the personality attribute in the preset personality feature according to the feedback of the user, the personality feature includes a plurality of personality attributes, and each of the personality attributes has an attribute value.
  • the method further includes:
  • the preset personality feature comprising:
  • the preset personality feature of the robot 20 can be set in advance by selecting one of the plurality of preset personality features, wherein the character can be selected by the user, and then the robot performs personality feature setting according to the user's selection instruction. It can also be a robot selective lattice feature and set its own personality features. The preset character characteristics of the robot 20 can also be set when the robot is shipped from the factory.
  • the attribute value of the adjusted personality attribute may be adjusted by the robot according to a user's instruction, for example, the user is on the screen (either the screen of the robot itself or a remote screen such as a user)
  • the phone or tablet, etc. directly manipulates the value of the property of the robot's personality attribute, such as adjusting the level of care from 3 to 8.
  • the robot itself adjusts the attribute value of the personality attribute according to the feedback of the user.
  • the user's feedback may be a user's voice command or conversation content. For example, the user issues a voice command "Rachel, personality adjustment, then gentler", “Amanda, temper setting is reduced a little", and the like.
  • Step 102 Perform an action or a voice according to the attribute value of the personality attribute in the current personality feature.
  • the actions and languages that are expressed are not the same. It is no longer just a unified mechanical response, but a response with personality characteristics based on the attribute values of the attributes set above. For example, when the temper is small, the movement is gentle and the voice is gentle. As the temper size increases, the robot's motion amplitude increases and the voice becomes louder. In the case of low activity, a simple answer will be given to the user's question. As the value of the lively attribute becomes larger, more questions will be used for the same question. In the case of a low degree of active speaking, the user may not actively talk to the user. As the value of the active speaking attribute becomes larger, the frequency of actively talking with the user becomes larger.
  • the character setting method provided by the embodiment of the present application can enable the robot to actively cater to the user by adjusting the attribute value of the personality attribute according to the feedback of the user and performing the corresponding action or voice according to the attribute value of the personality attribute in the current personality feature. And gradually turned into a character that users like, and the user experience is high.
  • the method is in addition to steps 201, 202, and 203 (for details of steps 201, 202, and 203, refer to the foregoing embodiment), include:
  • Step 204 Adjust the attribute value of the personality attribute according to the feedback of the user, and obtain the expected value of the user attribute to a certain personality attribute.
  • the purpose of obtaining the user's expectation of a personality attribute is to obtain the character of the user's favorite robot to provide a reference for the user or other newly added robot. Because, for most people, they don't know what character they really like, or they think that their favorite character is not really a favorite character. After the user clearly understands the character of the robot he likes, when he newly joins the robot, he can directly set it according to his own preferences. Or when new robots are added, other robots broadcast the user expectation values of each personality attribute to the newly added robot. The newly added robot can directly set the attribute values of each attribute according to the user expectation value of each attribute, so that the newly added robot does not need to be adjusted. Can get the user's favorite personality, further improving the user's experience.
  • one-way convergence may be adopted.
  • the method obtains the expected value of the user's personality attribute. Includes the following steps:
  • Step 301 Set the personality trait of the user to the first personality trait in the first time period
  • Step 302 Adjust an attribute value of the personality attribute in the first personality feature according to feedback of the user
  • Step 303 Record an attribute value of the personality attribute after the adjustment is completed as a user expected value of the personality attribute.
  • the character characteristics of the robot are set to the same personality feature (for example, the character feature 2 described above), and for each one or a plurality of personality attributes, the attribute values of the personality attribute are continuously performed according to the feedback of the user. Adjust until the user is satisfied. For example, for personality feature 2, the user complains that the temper of the robot is too large, and the robot is expected not to have such a large temper. At this time, the robot determines that the user wants the temper size to be adjusted to 6, but the user is still not satisfied for the next two days. Then the robot continues to adjust to 4, after which the user does not continue to complain. The user expectation value of the robot to record the temper size attribute is 4. For details of the feedback of the user, refer to the explanation of the embodiment shown in FIG. 3, and details are not described herein again.
  • a bidirectional convergence method may also be used to obtain a user's expected value for a certain personality attribute. Includes the following steps:
  • Step 401 Set its own personality feature as the first personality feature in the first time period
  • Step 402 Adjust an attribute value of the personality attribute in the first personality feature according to feedback of the user;
  • Step 403 Set its own personality feature to the second personality feature in the second time period
  • Step 404 Adjust an attribute value of the personality attribute in the second personality feature according to feedback of the user;
  • Step 405 Determine an expected value of the personality attribute of the user according to the adjustment of the attribute value of the personality attribute in the first personality feature and the adjustment of the attribute value of the personality attribute in the second personality feature.
  • the robots are respectively set to different personality characteristics (for example, the above-described personality feature 1 and personality feature 2) in two different time periods.
  • the attribute value of the personality attribute is continuously adjusted according to the feedback of the user until the user is satisfied.
  • Adjusting the attribute value of the personality attribute in the first personality feature and adjusting the attribute value of the personality attribute in the second personality feature may cause the attribute value of the personality attribute to tend to the same value, that is, the first personality feature and The difference between the same attribute value in the second feature is smaller, and the final difference is less than a predetermined threshold (for example, less than 3 or less than 2), which indicates that the attribute value is converging to a small range, This situation can be used as the user expectation value for the personality attribute.
  • a predetermined threshold for example, less than 3 or less than 2
  • the method of bidirectional convergence is adopted, that is, the same personality attribute is adjusted under different personality characteristics, the convergence speed is faster, and the accuracy is higher.
  • the attribute value and the second character of the personality attribute in the first personality feature are If the absolute value of the difference between the attribute values of the personality attribute in the feature becomes smaller, and the absolute value after the end of the adjustment is less than the preset threshold, the attribute of the personality attribute in the first character feature after the adjustment is recorded is recorded.
  • the value of the attribute of the personality attribute in the second personality trait after the value and the end of the adjustment is taken as the value range of the end value as the user expectation value of the personality attribute.
  • the user sets the robot to character 1 (the temper attribute value is 1) in the first week.
  • the user In the user, the user expects the robot to be a little temper to be more cute.
  • the robot determines that the user may want the temper of the robot.
  • the size attribute value is 3, so the adjustment is made, and the user does not complain about this after the adjustment.
  • the user sets the robot to character 2 (the temper size attribute value is 8). The user complains that the robot has too much temper and expects the robot not to have such a big temper.
  • the robot determines that the user wants the temper size to be adjusted to 6, But in the next two days, the user is still not satisfied, and then the robot continues to adjust to 4 (the absolute value of the difference between the attribute values becomes smaller, and the final difference is less than 2), after which the user does not continue to complain. Based on these two personality traits settings, it can be determined that the user's expected temper size is 3-4.
  • the attribute value and the second character of the personality attribute in the first personality feature are If the absolute value of the difference between the attribute values of the personality attribute in the feature becomes larger, or the absolute value after the adjustment is greater than or equal to the preset threshold, the character attribute in the first character feature after the adjustment is recorded is recorded.
  • the attribute value is the user expectation value of the personality attribute of the exclusive first personality feature
  • the attribute value of the personality attribute in the second personality feature after the recording adjustment is the user expectation value of the personality attribute of the exclusive second personality feature.
  • the initial character of the first personality trait (if it is the character trait 1 above) has an initial value of 2
  • the second personality trait (if it is the personality trait 2 above) has an initial value of 3, after several adjustments.
  • the attribute value of the active degree in the first personality characteristic becomes 4
  • the attribute value of the active degree in the second personality characteristic becomes 2
  • the absolute value of the difference between the attribute values is 2, and the absolute value of the difference between the attribute value of the activity level in the personality characteristic 1 before adjustment and the attribute value of the activity level in the personality feature 2 is 1 and the difference becomes large.
  • the user expectation value of the liveness level of the special attribute feature 1 is 4, and the user expectation value of the liveness degree of the special attribute feature 2 is 2.
  • the initial value of the temper size in personality feature 1 is 1, and the initial value of temper size in personality feature 2 is 8. If the adjustment is made several times, the attribute value of the temper size in personality feature 1 is still 1, and the character feature 2 is The attribute value of the temper size becomes 7, although the absolute value of the difference becomes smaller, the absolute value of the difference is greater than the preset threshold 2, so that the attribute value does not converge to a certain range for a long time, that is, The user also likes two kinds of personalities, which need to be recorded separately.
  • first personality feature and the second personality feature are only for explaining that different personality characteristics are adopted in different time periods, and a specific personality feature is not specifically mentioned.
  • any other different personality traits may be used.
  • the adjusting the attribute value of the personality attribute according to the feedback of the user, obtaining the expected value of the user attribute attribute further includes:
  • intersection is taken as the new user expectation value of the personality attribute.
  • each robot can broadcast the user expectation values of the individual personality attributes obtained by the other robots. When different robots have intersections with the user expectation values of the same personality attribute, the intersection can be used as the character. A more accurate user expectation of the attribute. For example, if a robot determines that the temper size is preferred by 1-2 users, and another robot determines that the temper size is preferred by 2-3 users, the user expectation value of the temper size may be determined to be 2 based on the intersection of the two interval ranges. This network sharing mechanism will greatly speed up the convergence of personality analysis.
  • the user expectation values of the same personality attribute have an intersection, that is, if the same personality attribute has more than two user expected values, and the same The different user expectation values of the personality attributes have an intersection, and the intersection is taken as the new user expectation value of the personality attribute.
  • the robot sets the personality feature 1 in the first time period, and sets the personality feature 2 in the second time period, and adjusts the temper size according to the feedback of the user, and bidirectionally converges in the first time period and the second time period.
  • the user expectation value of temper size is 1-2.
  • the personality feature 3 is set in the third time period, and the personality feature 4 is set in the fourth time period, and the temper is adjusted according to the feedback of the user, and the temper is determined in the two-way convergence of the third time period and the fourth time period.
  • the size of the user expects a value of 2-3. That is, the temper size user expectation value has two 1-2 and 2-3, and the two user expected values have an intersection of 2, and the intersection 2 is taken as a new user expectation value of the temper size.
  • the method further includes: setting an attribute value of the personality attribute according to a user expected value of the personality attribute;
  • the user expectation value of the output personality attribute is the user expectation value of the output personality attribute.
  • the user expectation value of the personality attribute can be output to the user to provide the user with the robot character feature as a reference.
  • the robot can broadcast the user expectation value of the personality attribute to an existing robot or a newly joined machine in another local area network.
  • the attribute value of the corresponding personality attribute in the personality character can be set according to the user expectation value of the personality attribute. For example, if the user receives a user-like value between 7-9, the degree of thoughtfulness of the robot can be directly set to 8.
  • the method further includes:
  • the attribute value of the personality attribute is set according to the user expectation value of the personality attribute of the exclusive current personality feature
  • the attribute value of the personality attribute is set according to the user expectation value of the personality attribute.
  • the robot may output the user expectation value of the personality attribute of the specific personality feature to the user, or may broadcast the user expectation value of the personality attribute of the exclusive personality feature to the user.
  • Robots already in other LANs or newly added robots. If other robots receive the user expectation value of the personality attribute of the specific personality feature and the user expectation value of the personality attribute (not exclusive to a certain personality feature), you can first judge the current personality characteristics of the character, if the current personality feature has a unique personality The user expectation value of the attribute, the attribute value of the corresponding personality attribute is set according to the user expectation value of the personality attribute of the exclusive current personality feature. If the current personality feature does not have the user expected value of the exclusive personality attribute, the user expectation value according to the personality attribute is set correspondingly. The attribute value of the personality attribute.
  • the embodiment of the present application further provides a robot personality setting device, and the personality setting device is disposed in any of the robots shown in FIG. 1 or FIG. 2, as shown in FIG.
  • Apparatus 500 includes:
  • the adjustment module 501 is configured to adjust an attribute value of the personality attribute in the preset personality feature according to the feedback of the user, where the personality feature includes a plurality of personality attributes, each of the personality attributes having an attribute value;
  • the executing module 502 is configured to perform an action or a voice according to the attribute value of the personality attribute in the current personality feature.
  • the character setting method provided by the embodiment of the present application can enable the robot to actively cater to the user by adjusting the attribute value of the personality attribute according to the feedback of the user and performing the corresponding action or voice according to the attribute value of the personality attribute in the current personality feature. And gradually turned into a character that users like, and the user experience is high.
  • the device includes: an adjustment module 602 and an execution module 603,
  • the preset personality module is specifically configured to:
  • the device further includes:
  • the expectation value obtaining module 700 is configured to adjust an attribute value of the personality attribute according to the feedback of the user to obtain a desired value of the user for a certain personality attribute.
  • the expected value obtaining module 700 includes a first expected value obtaining sub-module 701, configured to:
  • the attribute value of the personality attribute after the adjustment is recorded is taken as the user expectation value of the personality attribute.
  • the expected value obtaining module 700 includes a second expected value obtaining sub-module 702, configured to:
  • the expected value of the personality attribute of the user is determined according to the adjustment of the attribute value of the personality attribute in the first personality feature and the adjustment of the attribute value of the personality attribute in the second personality feature.
  • the second expected value obtaining submodule 702 is further configured to:
  • the attribute value and the second character of the personality attribute in the first personality feature are If the absolute value of the difference between the attribute values of the personality attribute in the feature becomes smaller, and the absolute value after the end of the adjustment is less than the preset threshold, the attribute of the personality attribute in the first character feature after the adjustment is recorded is recorded.
  • the value of the attribute of the personality attribute in the second personality trait after the value and the end of the adjustment is taken as the value range of the end value as the user expectation value of the personality attribute.
  • the second expected value obtaining submodule 702 is further configured to:
  • the attribute value and the second character of the personality attribute in the first personality feature are If the absolute value of the difference between the attribute values of the personality attribute in the feature becomes larger, or the absolute value after the adjustment is greater than or equal to the preset threshold, the character attribute in the first character feature after the adjustment is recorded is recorded.
  • the attribute value is the user expectation value of the personality attribute of the exclusive first personality feature
  • the attribute value of the personality attribute in the second personality feature after the recording adjustment is the user expectation value of the personality attribute of the exclusive second personality feature.
  • the second expected value obtaining submodule 702 is further configured to:
  • intersection is taken as the new user expectation value of the personality attribute.
  • the second expected value obtaining submodule 702 is further configured to:
  • the same personality attribute has more than two user expectations and the different user expectations of the same personality attribute have an intersection, then the intersection is taken as the new user expectation of the personality attribute.
  • the adjusting the attribute value of the personality attribute according to the feedback of the user includes:
  • the attribute value of the personality attribute is adjusted according to a user's instruction.
  • the apparatus 800 includes: a preset personality module 801, an adjustment module 802, an execution module 803, and an expectation value obtaining module 804, further including:
  • the first attribute value setting module 805 is configured to set an attribute value of the personality attribute according to the user expected value of the personality attribute
  • the output module 806 outputs a user expected value of the personality attribute.
  • the apparatus 900 includes: in addition to the preset personality module 901, the adjustment module 902, the execution module 903, and the expected value obtaining module 904,
  • the second attribute value setting module 905 is configured to:
  • the attribute value of the personality attribute is set according to the user expectation value of the personality attribute of the exclusive current personality feature
  • the attribute value of the personality attribute is set according to the user expectation value of the personality attribute.
  • the personality setting device may perform the personality setting method provided by the embodiment of the present application, and has a function module and a beneficial effect corresponding to the execution method.
  • the technical details that are not described in detail in the embodiment of the personality setting device can be referred to the personality setting method provided by the embodiment of the present application.
  • FIG. 13 is a schematic diagram showing the hardware structure of the robot 20 in the robot personality setting method according to the embodiment of the present application. As shown in FIG. 13, the robot 20 includes:
  • One or more processors 21 and a memory 22 are exemplified by a processor 21 in FIG.
  • the processor 21 and the memory 22 can be connected by a bus or other means, as exemplified by a bus connection in FIG.
  • the memory 22 is a non-volatile computer readable storage medium, and can be used for storing a non-volatile software program, a non-volatile computer-executable program, and a module, such as a program corresponding to the personality setting method in the embodiment of the present application.
  • the instruction/module (for example, the preset personality module 601, the adjustment module 602, and the execution module 603 shown in FIG. 8).
  • the processor 21 executes various functional applications and data processing of the server by executing non-volatile software programs, instructions, and modules stored in the memory 22, that is, implementing the personality setting method of the above method embodiments.
  • the memory 22 may include a storage program area that stores an operating system, an application required for at least one function, and a storage data area that stores data created according to the use of the personality setting device, and the like. Further, the memory 22 may include a high speed random access memory, and may also include a nonvolatile memory such as at least one magnetic disk storage device, flash memory device, or other nonvolatile solid state storage device. In some embodiments, memory 22 may optionally include memory remotely located relative to processor 21, which may be coupled to the personality setting device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the one or more modules are stored in the memory 22, and when executed by the one or more processors 21, the personality setting method in any of the above method embodiments is performed, for example, performing the above described FIG. Method step 101 to step 102, method step 201 to step 204 in FIG. 4, method step 301 to step 303 in FIG. 5, method step 401 to step 405 in FIG. 6, and module 501- in FIG. 502, modules 601-603 in FIG. 8, modules 700 and sub-modules 701 in FIG. 9, modules 700 and sub-modules 702 in FIG. 10, modules 801-806 in FIG. 11, functions of modules 901-905 in FIG. .
  • the embodiment of the present application provides a non-transitory computer readable storage medium storing computer-executable instructions that are executed by one or more processors, such as in FIG. a processor 21, wherein the one or more processors may perform the personality setting method in any of the above method embodiments, for example, perform the method steps 101 to 102 in FIG. 3 described above, in FIG. Method step 201 to step 204, method step 301 to step 303 in FIG. 5, method step 401 to step 405 in FIG. 6, module 501-502 in FIG. 7, module 601-603 in FIG. 8, Fig. 9
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)
  • User Interface Of Digital Computer (AREA)
  • Toys (AREA)

Abstract

一种机器人性格设定方法、装置和机器人,所述方法包括:根据用户的反馈调整预设性格特征中性格属性的属性值(101),所述性格特征包括多个性格属性,每个所述性格属性具有属性值;根据当前性格特征中的性格属性的属性值执行动作或者语音(102)。该性格设定方法和装置,通过根据用户的反馈调整性格属性的属性值,并根据当前性格特征中的性格属性的属性值执行相应的动作或者语音,可以使机器人获得用户喜爱的性格,即能够根据用户的喜好进行机器人的性格设定,用户体验好。

Description

机器人性格设定方法、装置和机器人 技术领域
本申请实施例涉及人工智能领域,例如涉及一种机器人性格设定方法、装置和机器人。
背景技术
随着人工智能技术的发展,机器人为人类的生产生活带来了很多便利,机器人逐渐在以前所未有的方式和速度占据着重要的位置,各种形态、各种功能的机器人正逐步被研制出来。
在研究现有技术的过程中,发明人发现相关技术中至少存在如下问题:目前,机器人的外表、智能程度和性格特征等一般在出厂时进行设置,即其性格特征是固定不变的。但是机器人面对的是不同的用户,在很多情况下,机器人的性格并不能获得用户的喜爱,从而导致用户体验较低。
发明内容
本申请实施例的一个目的是提供一种新的机器人性格设定方法、装置和机器人,机器人能够根据用户的喜好进行性格特征调整,用户体验较高。
第一方面,本申请实施例提供了一种机器人性格设定方法,所述性格设定方法应用于机器人,所述方法包括:
根据用户的反馈调整预设性格特征中性格属性的属性值,所述性格特征包括多个性格属性,每个所述性格属性具有属性值;
根据当前性格特征中的性格属性的属性值执行动作或者语音。
第二方面,本申请实施例还提供了一种机器人性格设定装置,所述性格设定装置应用于机器人,所述装置包括:
调整模块,用于根据用户的反馈调整预设性格特征中性格属性的属性值,所述性格特征包括多个性格属性,每个所述性格属性具有属性值;
执行模块,用于根据当前性格特征中的性格属性的属性值执行动作或者语音。
第三方面,本申请实施例还提供了一种机器人,包括:
至少一个处理器;以及,
与所述至少一个处理器通信连接的存储器;其中,
所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如上所述的方法。
本申请实施例提供的性格设定方法和装置,通过根据用户的反馈调整性格属性的属性值,并根据当前性格特征中的性格属性的属性值执行相应的动作或者语音,可以使机器人获得用户喜爱的性格,即能够根据用户的喜好进行机器人的性格设定,用户体验好。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明,这些示例性说明并不构成对实施例的限定,附图中具有相同参考数字标号的元件表示为类似的元件,除非有特别申明,附图中的图不构成比例限制。
图1是本申请方法和装置的应用场景示意图;
图2是本申请方法和装置的应用场景示意图;
图3是本申请性格设定方法的一个实施例的流程图;
图4是本申请性格设定方法的一个实施例的流程图;
图5是本申请性格设定方法的一个实施例中获得性格属性的用户期望值的步骤的流程示意图;
图6是本申请性格设定方法的一个实施例中获得性格属性的用户期望值的步骤的流程示意图;
图7是本申请性格设定装置的一个实施例的结构示意图;
图8是本申请性格设定装置的一个实施例的结构示意图;
图9是本申请性格设定装置的一个实施例中期望值获取模块的结构示意图;
图10是本申请性格设定装置的一个实施例中期望值获取模块的结构示意图;
图11是本申请性格设定装置的一个实施例的结构示意图;
图12是本申请性格设定装置的一个实施例的结构示意图;以及
图13是本申请实施例提供的性格设定方法的机器人的硬件结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
本申请提供的机器人性格设定方法和装置适用于如图1和图2所示的应用场景,包括用户10和机器人20,机器人20可以为一个或者多个(图1示出了一个机器人的场景,图2示出了多个机器人的场景)。如图2所示,多个机器人 20之间可以通过网络30互相通信,其中,网络30可以是例如家庭或公司的局域网,或一个特定网络等。机器人20具有至少一个网络接口,与网络30建立通信连接,从网络30获取数据或者指令。用户10可以对多个机器人20进行设置、发布命令或者与机器人20进行交谈。
每个机器人20都具有性格特征,所述性格特征可以是出厂时设置好的,也可以是用户10从多个预置的性格特征中选择一个性格特征,机器人20根据用户10的指令进行设置的,也可以是机器人20主动从多个预置的性格特征中选择一个性格特征对自身进行设置的。
当性格特征由用户10或者机器人20从预置的多个性格特征中进行选择并设置时,多个所述性格特征可以在出厂时预置,也可以在出厂后通过云端下载。其中,所述性格特征包括多个性格属性,每个性格属性具有属性值,性格属性的种类可以在升级过程中不断细化,越细致则对性格的描绘越精确,性格特征的结构可以如下所示:
Figure PCTCN2017092879-appb-000001
例如,性格特征1,可能配置如下:
Figure PCTCN2017092879-appb-000002
性格特征2,可能配置如下:
Figure PCTCN2017092879-appb-000003
Figure PCTCN2017092879-appb-000004
其中,开朗程度、主动说话程度、活泼程度等表示性格属性的类别,数字值表示该性格属性类别的属性值。
机器人20设置成某一性格特征后,可以根据用户10的反馈来调整某一性格属性的属性值。例如,机器人20设置成性格特征2,性格特征2中的脾气大小值为8,用户10抱怨机器人20的脾气太大了,期望机器人不要这么大的脾气,此时机器人20调整脾气大小为6,但接下来的两天用户还是不满意,机器人20继续将脾气大小调整到4。
其中,调整性格属性的属性值,可以是机器人20根据用户10的指令对性格属性的属性值进行调整,也可以是机器人20根据用户的语音命令或者谈话内容判断需要调整,继而对自身的性格属性的属性值进行调整。
根据用户的反馈调整性格属性的属性值,可以使机器人获得用户喜爱的性格,即能够根据用户的喜好进行机器人的性格设定,用户体验度高。
需要说明的是,虽然在图1中仅示出了1个用户10和1个机器人20,在图2中仅显示了1个用户10、3个机器人20。但本领域技术人员可以理解的是,在实际应用过程中,该应用场景还可以包括更多的用户10和机器人20。
本申请实施例提供了一种机器人性格设定方法,所述方法可由图1或者图2所示的任一机器人20执行,如图3所示,所述方法包括:
步骤101:根据用户的反馈调整预设性格特征中性格属性的属性值,所述性格特征包括多个性格属性,每个所述性格属性具有属性值。
其中,在所述方法的某些实施例中,所述方法还包括:
预设性格特征,所述预设性格特征包括:
从预置的多种性格特征中选择性格特征;
将选中的性格特征设置为自身的性格特征。
即机器人20的预设性格特征可以事先从多个预置的性格特征中选择一个性格特征进行设置,其中,可以由用户选择性格特征,然后机器人根据用户的选择指令进行性格特征设置。也可以是机器人选择性格特征并对自身进行性格特征设置。机器人20的预设性格特征还可以是在机器人出厂时就设置好的。
其中,所述调整性格属性的属性值可以是机器人根据用户的指令进行调整,例如用户在屏幕上(可以是机器人自身的屏幕,也可以是远程的屏幕,如用户 的手机或平板电脑等等)直接操作调节机器人的性格属性的属性值,如将体贴程度从3调节到8。也可以是机器人自身根据用户的反馈对性格属性的属性值进行调整。所述用户的反馈可以是用户的语音命令或者谈话内容。例如,用户发布语音命令“Rachel,性格调整,再温柔一点”、“Amanda,脾气设定减小一点”等。或者用户对机器人说“你怎么这么多话啊,安静一点”、“这些不用你管,我自己就都能办了”等。或者用户与别人的谈话中说“Rachel的脾气太大了”、“Amanda话太多了”等。只要机器人的语意理解中可解析出用户不满意机器人当前性格设定中的某一性格属性(或几个属性),就会相应的修改该属性的属性值。
步骤102:根据当前性格特征中的性格属性的属性值执行动作或者语音。
在性格特征设置不同时,表现的动作和语言也不尽相同。不再只是进行统一的机械性地回答,而是根据如上设定属性的属性值进行具备性格特征的回复。例如,脾气小的场合动作轻柔、语音温柔,随着脾气大小值的变大,机器人的动作幅度变大、说话声音变响。活泼程度低的场合,对用户的问题会采用简洁的答复,随着活泼程度属性值的变大,对同一问题会用越多的话进行回复。主动说话程度低的场合可能不会主动与用户交谈,随着主动说话程度属性值的变大,主动与用户交谈的频率会变大。
本申请实施例提供的性格设定方法,通过根据用户的反馈调整性格属性的属性值,并根据当前性格特征中的性格属性的属性值执行相应的动作或者语音,可以使机器人能够主动迎合用户,并逐渐转变为用户喜欢的性格,用户体验度高。
可选的,如图4所示,在所述方法的其他实施例中,所述方法除了步骤201、202和203之外(步骤201、202和203的详细内容请参照上述实施例),还包括:
步骤204:根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值。
获取用户对某一性格属性的期望值的目的是能获得用户喜欢的机器人的性格,以给用户或者其他新加入的机器人提供参考。因为,对大多数人来说,其本身并不清楚自己真正喜欢的是什么性格,或者以为自己喜欢的性格并不是真正最喜欢的性格。用户清楚的了解自己喜欢的机器人的性格后,新加入机器人时,可以直接根据自己的喜好进行设置。或者新加入机器人时,其他机器人将各性格属性的用户期望值广播给新加入的机器人,新加入的机器人可以直接根据各属性的用户期望值设置各属性的属性值,这样新加入的机器人无需经过调整就能获得用户喜爱的性格,进一步提高了用户的体验度。
具体的,如图5所示,在所述方法的某些实施例中,可以采用单向收敛的 方法获得用户对某一性格属性的期望值。包括以下步骤:
步骤301:在第一时间段内将自身的性格特征设置为第一性格特征;
步骤302:根据用户的反馈调整第一性格特征中所述性格属性的属性值;
步骤303:记录调整结束后的所述性格属性的属性值作为所述性格属性的用户期望值。
即在一时间段内,将机器人的性格特征设置为同一性格特征(例如上述性格特征2),针对某一个或者某几个性格属性,根据用户的反馈对所述性格属性的属性值进行不断的调整,直至用户满意为止。例如,针对性格特征2,使用中用户抱怨机器人的脾气太大了,期望机器人不要这么大的脾气,此时机器人判定用户希望脾气大小值调整到6,但接下来的两天用户还是不满意,继而机器人继续调整到4,之后用户没有再继续抱怨。机器人记录脾气大小属性的用户期望值为4。其中,所述用户的反馈的详细内容请参见图3所示实施例的解释,在此不再赘述。
可选的,如图6所示,在所述方法的其他实施例中,还可以采用双向收敛的方法获得用户对某一性格属性的期望值。包括以下步骤:
步骤401:在第一时间段内将自身的性格特征设置为第一性格特征;
步骤402:根据用户的反馈调整第一性格特征中所述性格属性的属性值;
步骤403:在第二时间段内将自身的性格特征设置为第二性格特征;
步骤404:根据用户的反馈调整第二性格特征中所述性格属性的属性值;
步骤405:根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值。
即在两段不同的时间段内,分别将机器人设置成不同的性格特征(例如上述性格特征1和性格特征2)。在各时间段内,针对某一个或者某几个性格属性,根据用户的反馈对所述性格属性的属性值进行不断的调整,直至用户满意为止。
对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整可能会使性格属性的属性值趋于同一值,即第一性格特征和第二特征中的同一属性值的差值是变小的,且其最终差值会小于一预设阀值(例如小于3或者小于2),这说明属性值是在收敛到一个小范围的,这种情况可将该范围作为该性格属性的用户期望值。但有时对性格属性的属性值的调整方向并不一致或者说调整没有使属性值趋于同一值,因为实际上,有的用户喜爱的性格特征可能不止一种,比如既喜欢活泼型,同时又喜欢安静型,这种情况则应该分别来存储记录用户喜欢的性格特征和专属该性格特征的性格属性的用户期望值。
采用双向收敛的方法,即对同一性格属性分别在不同性格特征下进行调整,收敛速度更快,准确度更高。
所述根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值,具体包括:
如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变小,且调整结束后的所述绝对值小于预设阀值,则记录由调整结束后的第一性格特征中所述性格属性的属性值和调整结束后的第二性格特征中所述性格属性的属性值作为端值的取值范围作为所述性格属性的用户期望值。
例如,预设阀值为2,第一周用户将机器人设定为性格特征1(脾气大小属性值为1),使用中用户期望机器人有点小脾气才更可爱,机器人判定用户可能希望机器人的脾气大小属性值在3,于是进行调整,调整之后用户没有再抱怨这一点。第二周用户将机器人设定为性格特征2(脾气大小属性值为8),用户抱怨机器人脾气太大了,期望机器人不要这么大的脾气,此时机器人判定用户希望脾气大小值调整到6,但接下来的两天用户还是不满意,继而机器人继续调整到4(属性值之差的绝对值变小,且最终差值小于2),之后用户没有再继续抱怨。基于这两种性格特征设定,可确定用户对脾气大小的期望值为3-4。
如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变大,或者调整结束后的所述绝对值大于或者等于预设阀值,则记录调整结束后的第一性格特征中所述性格属性的属性值为专属第一性格特征的所述性格属性的用户期望值,和记录调整结束后的第二性格特征中所述性格属性的属性值为专属第二性格特征的所述性格属性的用户期望值。
例如第一性格特征(假如为如上的性格特征1)中活泼程度的初始值为2,第二性格特征(假如为如上的性格特征2)中活泼程度的初始值为3,经过几次调整后,第一性格特征中活泼程度的属性值变为4,而第二性格特征中活泼程度的属性值变为2,则调整后的性格特征1中活泼程度的属性值与性格特征2中活泼程度的属性值之差的绝对值为2,调整前的性格特征1中活泼程度的属性值与性格特征2中活泼程度的属性值之差的绝对值为1,差值变大。则记录专属性格特征1的活泼程度的用户期望值为4,专属性格特征2的活泼程度的用户期望值为2。又例如,性格特征1中脾气大小的初始值为1,性格特征2中脾气大小的初始值为8,如果经过几次调整后,性格特征1中脾气大小的属性值还是1,性格特征2中脾气大小的属性值变为7,虽然该差值的绝对值变小,但是该差值的绝对值大于预设阀值2,因此说明属性值长时间并没有收敛到一定范围内,即用 户喜欢的也是两种性格,需要分别记录。
需要说明的是,所述第一性格特征和第二性格特征只是为了说明在不同时间段内采用了不同的性格特征,而并不特指某一特定的性格特征。除了上述的性格特征1和性格特征2之外,还可以为任何其他的不同性格特征。
可选的,为了进一步加快用户期望值的收敛速度,在所述方法的其他实施例中,所述根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值,还包括:
广播各个性格属性的用户期望值;
获取其他机器人发送的各个性格属性的用户期望值;
如果相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
如果同一个局域网中有多个机器人,各个机器人可以向其他机器人广播自己获得的各个性格属性的用户期望值,当不同机器人对同一个性格属性的用户期望值有交集时,则可以将该交集作为该性格属性的更准确的用户期望值。例如,一个机器人判定脾气大小在1-2用户会比较喜欢,另一个机器人判定脾气大小在2-3用户会比较喜欢,则可以根据此两个区间范围的交集判定脾气大小的用户期望值为2。这种网络共享机制将大大加快性格分析的收敛速度。
可选的,为了加快用户期望值的收敛速度,同一个机器人的两次不同判定中,如果对同一个性格属性的用户期望值有交集时,即如果相同性格属性具有两个以上的用户期望值,且相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
例如机器人在第一时间段内设定性格特征1,在第二时间段内设定性格特征2,通过根据用户的反馈对脾气大小进行调整,在第一时间段和第二时间段的双向收敛确定脾气大小的用户期望值为1-2。在第三时间段内设定性格特征3,在第四时间段内设定性格特征4,通过根据用户的反馈对脾气大小进行调整,在第三时间段和第四时间段的双向收敛确定脾气大小的用户期望值为2-3。即脾气大小的用户期望值有两个1-2和2-3,且该两个用户期望值有交集为2,则将该交集2作为脾气大小的新的用户期望值。
可选的,在所述方法的其他实施例中,所述方法还包括:根据性格属性的用户期望值设置性格属性的属性值;
或者,
输出性格属性的用户期望值。
即机器人获得性格属性的用户期望值后,可以向用户输出该性格属性的用户期望值,以给用户设置机器人性格特征时作为参考。或者,机器人可以将该性格属性的用户期望值广播给其他局域网中已存在的机器人或者新加入的机器 人,其他机器人接收到性格属性的用户期望值后,可以根据性格属性的用户期望值设置自身性格特征中对应的性格属性的属性值。例如机器人接收到体贴程度的用户期望值在7-9之间,则可以直接将自身的体贴程度取值为8。
可选的,在所述方法的其他实施例中,所述方法还包括:
获取当前的性格特征;
如果具有专属当前性格特征的性格属性的用户期望值,则根据专属当前性格特征的性格属性的用户期望值设置所述性格属性的属性值;
否则,根据性格属性的用户期望值设置所述性格属性的属性值。
机器人在获得专属某一性格特征的性格属性的用户期望值之后,可以向用户输出该专属某一性格特征的性格属性的用户期望值,也可以将该专属某一性格特征的性格属性的用户期望值广播给其他局域网中已存在的机器人或者新加入的机器人。如果其他机器人同时接收到了这些专属某一性格特征的性格属性的用户期望值和性格属性的用户期望值(不专属某一性格特征),可以先判断自身当前的性格特征,如果当前性格特征有专属的性格属性的用户期望值,则根据专属当前性格特征的性格属性的用户期望值设定对应的性格属性的属性值,如果当前性格特征没有专属的性格属性的用户期望值,则根据性格属性的用户期望值设置对应的性格属性的属性值。
相应的,本申请实施例还提供了一种机器人性格设定装置,所述性格设定装置设置于图1或图2所示的任一机器人内,如图7所示,所述性格设定装置500包括:
调整模块501,用于根据用户的反馈调整预设性格特征中性格属性的属性值,所述性格特征包括多个性格属性,每个所述性格属性具有属性值;
执行模块502,用于根据当前性格特征中的性格属性的属性值执行动作或者语音。
本申请实施例提供的性格设定方法,通过根据用户的反馈调整性格属性的属性值,并根据当前性格特征中的性格属性的属性值执行相应的动作或者语音,可以使机器人能够主动迎合用户,并逐渐转变为用户喜欢的性格,用户体验度高。
可选的,如图8所示,在所述装置的其他实施例中,所述装置除了调整模块602和执行模块603之外,还包括:
预设性格模块601,用于预设性格特征;
所述预设性格模块具体用于:
从预置的多种性格特征中选择性格特征;
将选中的性格特征设置为自身的性格特征。
可选的,请参照图9,在所述装置的其他实施例中,所述装置还包括:
期望值获得模块700,用于根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值。
具体的,请参照图9,所述期望值获得模块700包括第一期望值获得子模块701,用于:
在第一时间段内将自身的性格特征设置为第一性格特征;
根据用户的反馈调整第一性格特征中所述性格属性的属性值;
记录调整结束后的所述性格属性的属性值作为所述性格属性的用户期望值。
可选的,请参照图10,在所述装置的其他实施例中,所述期望值获得模块700包括第二期望值获得子模块702,用于:
在第一时间段内将自身的性格特征设置为第一性格特征;
根据用户的反馈调整第一性格特征中所述性格属性的属性值;
在第二时间段内将自身的性格特征设置为第二性格特征;
根据用户的反馈调整第二性格特征中所述性格属性的属性值;
根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值。
可选的,在所述装置的其他实施例中,所述第二期望值获得子模块702还用于:
如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变小,且调整结束后的所述绝对值小于预设阀值,则记录由调整结束后的第一性格特征中所述性格属性的属性值和调整结束后的第二性格特征中所述性格属性的属性值作为端值的取值范围作为所述性格属性的用户期望值。
可选的,在所述装置的其他实施例中,所述第二期望值获得子模块702还用于:
如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变大,或者调整结束后的所述绝对值大于或者等于预设阀值,则记录调整结束后的第一性格特征中所述性格属性的属性值为专属第一性格特征的所述性格属性的用户期望值,和记录调整结束后的第二性格特征中所述性格属性的属性值为专属第二性格特征的所述性格属性的用户期望值。
可选的,在所述装置的其他实施例中,所述第二期望值获得子模块702还用于:
广播各个性格属性的用户期望值;
获取其他机器人发送的各个性格属性的用户期望值;
如果相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
可选的,在所述装置的其他实施例中,所述第二期望值获得子模块702还用于:
如果相同性格属性具有两个以上的用户期望值,且相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
可选的,在所述装置的其他实施例中,所述根据用户的反馈调整性格属性的属性值,包括:
根据用户的语音命令或者谈话内容,调整所述性格属性的属性值;
根据用户的指令调整所述性格属性的属性值。
可选的,如图11所示,在所述装置的其他实施例中,所述装置800除了预设性格模块801、调整模块802、执行模块803和期望值获得模块804之外,还包括:
第一属性值设置模块805,用于根据性格属性的用户期望值设置性格属性的属性值;
和/或,
输出模块806,输出性格属性的用户期望值。
可选的,如图12所示,在所述装置的其他实施例中,所述装置900除了预设性格模块901、调整模块902、执行模块903和期望值获得模块904之外还包括:
第二属性值设置模块905,用于:
获取当前的性格特征;
如果具有专属当前性格特征的性格属性的用户期望值,则根据专属当前性格特征的性格属性的用户期望值设置所述性格属性的属性值;
否则,根据性格属性的用户期望值设置所述性格属性的属性值。
需要说明的是,上述性格设定装置可执行本申请实施例所提供的性格设定方法,具备执行方法相应的功能模块和有益效果。未在性格设定装置实施例中详尽描述的技术细节,可参见本申请实施例所提供的性格设定方法。
图13是本申请实施例提供的机器人性格设定方法的机器人20的硬件结构示意图,如图13所示,该机器人20包括:
一个或多个处理器21以及存储器22,图13中以一个处理器21为例。
处理器21和存储器22可以通过总线或者其他方式连接,图13中以通过总线连接为例。
存储器22作为一种非易失性计算机可读存储介质,可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块,如本申请实施例中的性格设定方法对应的程序指令/模块(例如,附图8所示的预设性格模块601、调整模块602、执行模块603)。处理器21通过运行存储在存储器22中的非易失性软件程序、指令以及模块,从而执行服务器的各种功能应用以及数据处理,即实现上述方法实施例的性格设定方法。
存储器22可以包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需要的应用程序;存储数据区可存储根据性格设定装置的使用所创建的数据等。此外,存储器22可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中,存储器22可选包括相对于处理器21远程设置的存储器,这些远程存储器可以通过网络连接至性格设定装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器22中,当被所述一个或者多个处理器21执行时,执行上述任意方法实施例中的性格设定方法,例如,执行以上描述的图3中的方法步骤101至步骤102,图4中的方法步骤201至步骤204,图5中的方法步骤301至步骤303,图6中的方法步骤401至步骤405;实现图7中的模块501-502、图8中的模块601-603,图9中的模块700和子模块701,图10中的模块700和子模块702,图11中的模块801-806,图12中的模块901-905的功能。
上述产品可执行本申请实施例所提供的方法,具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节,可参见本申请实施例所提供的方法。
本申请实施例提供了一种非易失性计算机可读存储介质,所述计算机可读存储介质存储有计算机可执行指令,该计算机可执行指令被一个或多个处理器执行,例如图13中的一个处理器21,可使得上述一个或多个处理器可执行上述任意方法实施例中的性格设定方法,例如,执行以上描述的图3中的方法步骤101至步骤102,图4中的方法步骤201至步骤204,图5中的方法步骤301至步骤303,图6中的方法步骤401至步骤405;实现图7中的模块501-502、图8中的模块601-603,图9中的模块700和子模块701,图10中的模块700和子模块702,图11中的模块801-806,图12中的模块901-905的功能。
以上所描述的装置实施例仅仅是示意性的,其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述,本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现,当然也可以通过硬件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成,所述的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
最后应说明的是:以上实施例仅用以说明本申请的技术方案,而非对其限制;在本申请的思路下,以上实施例或者不同实施例中的技术特征之间也可以进行组合,步骤可以以任意顺序实现,并存在如上所述的本申请的不同方面的许多其它变化,为了简明,它们没有在细节中提供;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (27)

  1. 一种机器人性格设定方法,所述方法应用于机器人,其特征在于,所述方法包括:
    根据用户的反馈调整预设性格特征中性格属性的属性值,所述性格特征包括多个性格属性,每个所述性格属性具有属性值;
    根据当前性格特征中的性格属性的属性值执行动作或者语音。
  2. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    预设性格特征;
    所述预设性格特征包括:
    从预置的多种性格特征中选择性格特征;
    将选中的性格特征设置为自身的性格特征。
  3. 根据权利要求2所述的方法,其特征在于,所述方法还包括:
    根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值。
  4. 根据权利要求3所述的方法,其特征在于,所述根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值,包括:
    在第一时间段内将自身的性格特征设置为第一性格特征;
    根据用户的反馈调整第一性格特征中所述性格属性的属性值;
    记录调整结束后的所述性格属性的属性值作为所述性格属性的用户期望值。
  5. 根据权利要求3所述的方法,其特征在于,所述根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值,包括:
    在第一时间段内将自身的性格特征设置为第一性格特征;
    根据用户的反馈调整第一性格特征中所述性格属性的属性值;
    在第二时间段内将自身的性格特征设置为第二性格特征;
    根据用户的反馈调整第二性格特征中所述性格属性的属性值;
    根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值。
  6. 根据权利要求5所述的方法,其特征在于,所述根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值,包括:
    如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第 二性格特征中所述性格属性的属性值之差的绝对值变小,且调整结束后的所述绝对值小于预设阀值,则记录由调整结束后的第一性格特征中所述性格属性的属性值和调整结束后的第二性格特征中所述性格属性的属性值作为端值的取值范围作为所述性格属性的用户期望值。
  7. 根据权利要求5所述的方法,其特征在于,所述根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值,还包括:
    如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变大,或者调整结束后的所述绝对值大于或者等于预设阀值,则记录调整结束后的第一性格特征中所述性格属性的属性值为专属第一性格特征的所述性格属性的用户期望值,和记录调整结束后的第二性格特征中所述性格属性的属性值为专属第二性格特征的所述性格属性的用户期望值。
  8. 根据权利要求6所述的方法,其特征在于,所述根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值,还包括:
    广播各个性格属性的用户期望值;
    获取其他机器人发送的各个性格属性的用户期望值;
    如果相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
  9. 根据权利要求6所述的方法,其特征在于,所述根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值,还包括:
    如果相同性格属性具有两个以上的用户期望值,且相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
  10. 根据权利要求1-9任意一项所述的方法,其特征在于,所述根据用户的反馈调整性格属性的属性值,包括
    根据用户的语音命令或者谈话内容,调整所述性格属性的属性值;
    根据用户的指令调整所述性格属性的属性值。
  11. 根据权利要求6所述的方法,其特征在于,所述方法还包括:
    根据性格属性的用户期望值设置性格属性的属性值;
    和/或,
    输出性格属性的用户期望值。
  12. 根据权利要求7所述的方法,其特征在于,所述方法还包括:
    获取当前的性格特征;
    如果具有专属当前性格特征的性格属性的用户期望值,则根据专属当前性 格特征的性格属性的用户期望值设置所述性格属性的属性值;
    否则,根据性格属性的用户期望值设置所述性格属性的属性值。
  13. 一种机器人性格设定装置,所述装置应用于机器人,其特征在于,所述装置包括:
    调整模块,用于根据用户的反馈调整预设性格特征中性格属性的属性值,所述性格特征包括多个性格属性,每个所述性格属性具有属性值;
    执行模块,用于根据当前性格特征中的性格属性的属性值执行动作或者语音。
  14. 根据权利要求13所述的装置,其特征在于,所述装置还包括:
    预设性格模块,用于预设性格特征;
    所述预设性格模块具体用于:
    从预置的多种性格特征中选择性格特征;
    将选中的性格特征设置为自身的性格特征。
  15. 根据权利要求14所述的装置,其特征在于,所述装置还包括:
    期望值获得模块,用于根据用户的反馈调整性格属性的属性值,获得用户对某一性格属性的期望值。
  16. 根据权利要求15所述的装置,其特征在于,所述期望值获得模块包括第一期望值获得子模块,用于:
    在第一时间段内将自身的性格特征设置为第一性格特征;
    根据用户的反馈调整第一性格特征中所述性格属性的属性值;
    记录调整结束后的所述性格属性的属性值作为所述性格属性的用户期望值。
  17. 根据权利要求15所述的装置,其特征在于,所述期望值获得模块包括第二期望值获得子模块,用于:
    在第一时间段内将自身的性格特征设置为第一性格特征;
    根据用户的反馈调整第一性格特征中所述性格属性的属性值;
    在第二时间段内将自身的性格特征设置为第二性格特征;
    根据用户的反馈调整第二性格特征中所述性格属性的属性值;
    根据对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,确定用户对所述性格属性的期望值。
  18. 根据权利要求17所述的装置,其特征在于,所述第二期望值获得子模块还用于:
    如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变小,且调整结束后的所述 绝对值小于预设阀值,则记录由调整结束后的第一性格特征中所述性格属性的属性值和调整结束后的第二性格特征中所述性格属性的属性值作为端值的取值范围作为所述性格属性的用户期望值。
  19. 根据权利要求17所述的装置,其特征在于,所述第二期望值获得子模块还用于:
    如果对第一性格特征中所述性格属性的属性值的调整和对第二性格特征中所述性格属性的属性值的调整,使第一性格特征中所述性格属性的属性值和第二性格特征中所述性格属性的属性值之差的绝对值变大,或者调整结束后的所述绝对值大于或者等于预设阀值,则记录调整结束后的第一性格特征中所述性格属性的属性值为专属第一性格特征的所述性格属性的用户期望值,和记录调整结束后的第二性格特征中所述性格属性的属性值为专属第二性格特征的所述性格属性的用户期望值。
  20. 根据权利要求18所述的装置,其特征在于,所述第二期望值获得子模块还用于:
    广播各个性格属性的用户期望值;
    获取其他机器人发送的各个性格属性的用户期望值;
    如果相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
  21. 根据权利要求18所述的装置,其特征在于,所述第二期望值获得子模块还用于:
    如果相同性格属性具有两个以上的用户期望值,且相同性格属性的不同用户期望值具有交集,则将所述交集作为新的所述性格属性的用户期望值。
  22. 根据权利要求13-21任意一项所述的装置,其特征在于,所述根据用户的反馈调整性格属性的属性值,包括:
    根据用户的语音命令或者谈话内容,调整所述性格属性的属性值;
    根据用户的指令调整所述性格属性的属性值。
  23. 根据权利要求18所述的装置,其特征在于,所述装置还包括:
    第一属性值设置模块,用于根据性格属性的用户期望值设置性格属性的属性值;
    和/或,
    输出模块,用于输出性格属性的用户期望值。
  24. 根据权利要求19所述的装置,其特征在于,所述装置还包括:
    第二属性值设置模块,用于:
    获取当前的性格特征;
    如果具有专属当前性格特征的性格属性的用户期望值,则根据专属当前性 格特征的性格属性的用户期望值设置所述性格属性的属性值;
    否则,根据性格属性的用户期望值设置所述性格属性的属性值。
  25. 一种机器人,其特征在于,包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行权利要求1-12任一项所述的方法。
  26. 一种非易失性计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有计算机可执行指令,当所述计算机可执行指令被机器人执行时,使所述机器人执行执行权利要求1-12任一项所述的方法。
  27. 一种计算机程序产品,其特征在于,所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序,所述计算机程序包括程序指令,当所述程序指令被机器人执行时,使所述机器人执行权利要求1-12任一项所述的方法。
PCT/CN2017/092879 2017-07-14 2017-07-14 机器人性格设定方法、装置和机器人 WO2019010682A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN201780003250.2A CN108472811B (zh) 2017-07-14 2017-07-14 机器人性格设定方法、装置和机器人
PCT/CN2017/092879 WO2019010682A1 (zh) 2017-07-14 2017-07-14 机器人性格设定方法、装置和机器人
JP2020501506A JP6979115B2 (ja) 2017-07-14 2017-07-14 ロボットの性格設定方法、装置及びロボット
US16/741,326 US11045957B2 (en) 2017-07-14 2020-01-13 Robot character setting method and robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/092879 WO2019010682A1 (zh) 2017-07-14 2017-07-14 机器人性格设定方法、装置和机器人

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/741,326 Continuation US11045957B2 (en) 2017-07-14 2020-01-13 Robot character setting method and robot

Publications (1)

Publication Number Publication Date
WO2019010682A1 true WO2019010682A1 (zh) 2019-01-17

Family

ID=63266971

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/092879 WO2019010682A1 (zh) 2017-07-14 2017-07-14 机器人性格设定方法、装置和机器人

Country Status (4)

Country Link
US (1) US11045957B2 (zh)
JP (1) JP6979115B2 (zh)
CN (1) CN108472811B (zh)
WO (1) WO2019010682A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11461404B2 (en) * 2018-06-26 2022-10-04 Intuition Robotics, Ltd. System and method for adjustment of a device personality profile
US11154991B2 (en) * 2018-09-26 2021-10-26 Disney Enterprises, Inc. Interactive autonomous robot configured for programmatic interpretation of social cues
CN110008321B (zh) * 2019-03-07 2021-06-25 腾讯科技(深圳)有限公司 信息交互方法和装置,存储介质及电子装置
CN110120170A (zh) * 2019-04-19 2019-08-13 安徽智训机器人技术有限公司 一种具有情绪设定的教育机器人
US20240051147A1 (en) * 2021-01-05 2024-02-15 Sony Group Corporation Entertainment system and robot
JP6990472B1 (ja) 2021-03-23 2022-01-12 ユニロボット株式会社 人とコミュニケーションを行うシステム及びそのためのプログラム
CN115563395B (zh) * 2022-12-05 2023-03-24 安徽淘云科技股份有限公司 交互方法、装置、电子设备和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030182122A1 (en) * 2001-03-27 2003-09-25 Rika Horinaka Robot device and control method therefor and storage medium
CN104881108A (zh) * 2014-02-27 2015-09-02 青岛海尔机器人有限公司 一种智能人机交互方法及装置
CN106200959A (zh) * 2016-07-08 2016-12-07 北京光年无限科技有限公司 面向智能机器人的信息处理方法及系统
CN106503043A (zh) * 2016-09-21 2017-03-15 北京光年无限科技有限公司 一种用于智能机器人的交互数据处理方法

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3353651B2 (ja) * 1997-06-23 2002-12-03 松下電器産業株式会社 エージェントインタフェース装置
KR20020008848A (ko) * 2000-03-31 2002-01-31 이데이 노부유끼 로봇 장치, 로봇 장치의 행동 제어 방법, 외력 검출 장치및 외력 검출 방법
JP2002144259A (ja) * 2000-07-27 2002-05-21 Yamaha Motor Co Ltd 自律機能を有する電子機器
JP2002216026A (ja) * 2000-11-17 2002-08-02 Sony Corp 情報通信システム、エージェント端末、情報配信システム、エージェントプログラムが記憶された記憶媒体、エージェントアクセスプログラムが記憶された記憶媒体、専用処理プログラムが記憶された記憶媒体、エージェントプログラム、エージェントアクセスプログラム、及び、専用処理プログラム
JP2004174642A (ja) * 2002-11-26 2004-06-24 Matsushita Electric Ind Co Ltd 無線通信システム、携帯電話機用プログラム、ロボット装置、並びに、ロボット装置用プログラム
JP2006109923A (ja) * 2004-10-12 2006-04-27 Tomy Co Ltd 育成システム
JP4798431B2 (ja) * 2005-11-11 2011-10-19 株式会社ケンウッド エージェント装置、エージェント機能付車載用ナビゲーション装置、エージェント出力方法
US8996429B1 (en) * 2011-05-06 2015-03-31 Google Inc. Methods and systems for robot personality development
EP2862604B1 (en) * 2012-06-05 2018-05-02 Sony Corporation Information processing device, information processing method, program and toy system
US9992306B2 (en) * 2012-12-21 2018-06-05 E*Trade Financial Corporation Dynamic execution
CA3067177A1 (en) * 2015-02-10 2016-08-18 Mobileye Vision Technologies Ltd. Sparse map for autonomous vehicle navigation
CA2922625A1 (en) * 2015-03-06 2016-09-06 Simplehuman, Llc Foaming soap dispensers
EP3605439A4 (en) * 2017-03-31 2020-02-05 Sony Corporation INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM
WO2018235607A1 (ja) * 2017-06-20 2018-12-27 ソニー株式会社 情報処理装置、情報処理方法、およびプログラム
US11495018B2 (en) * 2017-06-20 2022-11-08 Stamps.Com Inc. Augmented reality system for facilitating item relocation via augmented reality cues and location based confirmation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030182122A1 (en) * 2001-03-27 2003-09-25 Rika Horinaka Robot device and control method therefor and storage medium
CN104881108A (zh) * 2014-02-27 2015-09-02 青岛海尔机器人有限公司 一种智能人机交互方法及装置
CN106200959A (zh) * 2016-07-08 2016-12-07 北京光年无限科技有限公司 面向智能机器人的信息处理方法及系统
CN106503043A (zh) * 2016-09-21 2017-03-15 北京光年无限科技有限公司 一种用于智能机器人的交互数据处理方法

Also Published As

Publication number Publication date
US20200147807A1 (en) 2020-05-14
CN108472811A (zh) 2018-08-31
CN108472811B (zh) 2021-06-04
JP2020527267A (ja) 2020-09-03
JP6979115B2 (ja) 2021-12-08
US11045957B2 (en) 2021-06-29

Similar Documents

Publication Publication Date Title
WO2019010682A1 (zh) 机器人性格设定方法、装置和机器人
US10065124B2 (en) Interacting with a remote participant through control of the voice of a toy device
US10848339B2 (en) Implementation system and method for internet of things based on artificial intelligence
US10264214B1 (en) System and methods for testing a video conference call using a virtual assistant
JP7033156B2 (ja) 音量調整方法、端末装置、記憶媒体及び電子機器
US20170076208A1 (en) Terminal application launching method, and terminal
US10897637B1 (en) Synchronize and present multiple live content streams
US11267121B2 (en) Conversation output system, conversation output method, and non-transitory recording medium
CN105141587A (zh) 一种虚拟玩偶互动方法及装置
US20220139383A1 (en) Real-time video conference chat filtering using machine learning models
US10979242B2 (en) Intelligent personal assistant controller where a voice command specifies a target appliance based on a confidence score without requiring uttering of a wake-word
US11972757B2 (en) Digital media environment for conversational image editing and enhancement
PH12019000098A1 (en) Virtual services rapid deployment tool
KR102367143B1 (ko) 얼굴 표정들에 기초한 음성 효과들
DE102018118349A1 (de) Verfahren und vorrichtung zum auswählen einer audioausgabeschaltung basierend auf prioritätsattributen
TW202325030A (zh) 用於基於視訊的串流同步之平台
JP2022111966A (ja) 音声及びビデオ会議アプリケーションの音量調節
US20220020363A1 (en) System and method for configurable control of voice command systems
US20180104813A1 (en) Animatronic feedback based upon social media activity
US11659239B2 (en) Managing user profiles on electronic devices
CN114303151A (zh) 经由使用组合神经网络的场景建模进行自适应对话的系统和方法
US20230122645A1 (en) Audio data processing
US20220239780A1 (en) Systems and methods for improved audio/video conferences
US10521255B2 (en) Interface and interruption management
KR102248313B1 (ko) 사전 제작된 인테리어 디자인 모델을 제공하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17917823

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020501506

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: 1205A 19.05.2020

122 Ep: pct application non-entry in european phase

Ref document number: 17917823

Country of ref document: EP

Kind code of ref document: A1