Terminal device and automatic control method thereof

Abstract

The present application discloses a terminal device and an automatic control method thereof. The terminal device includes an information collection device for collecting target information. The method includes: obtaining a recognition result of the target information; determining the confidence level of the recognition result; and determining a corresponding execution mode based on the confidence level. This embodiment accurately captures the user's confirmation intent, improves the accuracy of image recognition algorithms, and improves the accuracy of information confirmation. It also reduces the number of user interventions, reduces erroneous operations, and reduces the chance of user error correction, thereby improving the user experience.

Description

Technical Field

[0001] This article relates to terminal application technology, especially a terminal device and its automatic control method. Background Art

[0002] Currently, in mobile Internet application activities, there are many scenarios that require user confirmation operations, especially confirmation operations based on the recognition results of image information collected by the camera, such as: face recognition payment confirmation when paying for shopping on the mobile terminal; face recognition or fingerprint recognition confirmation operation when someone enters or exits the home smart door lock; confirmation operation when smart home appliances automatically cook dishes by recognizing the type of ingredients through images, etc.

[0003] The defect of the existing technology is that in the prompt box or confirmation page including "Confirm" and "Cancel" buttons, the user needs to confirm the operation by clicking or sliding the button, but the user may accidentally click or operate it due to inadvertent touch of the screen or other touch events, which brings inconvenience to the user and affects the user experience. Summary of the Invention

[0004] The present application provides a terminal device and an automatic control method thereof, which can accurately obtain the user's confirmation intention, improve the accuracy of image recognition algorithms, etc., reduce the number of user interventions, reduce erroneous operations, and reduce the chance of user error correction.

[0005] An embodiment of the present application provides an automatic control method for a terminal device, wherein the terminal device may include an information collection device for collecting target information; the method may include:

[0006] Obtaining an identification result of the target information;

[0007] Determining a confidence level of the recognition result;

[0008] A corresponding execution mode is determined according to the confidence level.

[0009] In an exemplary embodiment of the present application, the execution mode may include: automatic control mode and one-key confirmation mode.

[0010] In an exemplary embodiment of the present application, determining the corresponding execution mode according to the confidence level may include:

[0011] When the confidence level is greater than or equal to a first confidence level threshold, the automatic control mode is entered according to the recognition result.

[0012] In an exemplary embodiment of the present application, the automatic control mode may include: directly entering the execution process of the function corresponding to the recognition result.

[0013] In an exemplary embodiment of the present application, determining the corresponding execution mode according to the confidence level may include:

[0014] When the confidence level is less than a first confidence threshold and greater than or equal to a second confidence threshold, the one-key confirmation mode is entered; wherein the first confidence threshold is greater than the second confidence threshold.

[0015] In an exemplary embodiment of the present application, the one-key confirmation mode may include: providing one or more option controls to perform one-key confirmation through the option controls;

[0016] The option control is used to represent the correctness of the recognition result; or, to represent possible correct options.

[0017] In an exemplary embodiment of the present application, the execution mode may further include: a one-key cancellation mode;

[0018] Determining the corresponding execution mode according to the confidence level may include: entering the one-key cancellation mode when the confidence level is less than a second confidence level threshold; and / or,

[0019] The method may further include: after executing the automatic control mode, providing an option control for entering the one-key cancellation mode, so as to cancel the execution process corresponding to the automatic control mode after the option control of the one-key cancellation mode is triggered.

[0020] In an exemplary embodiment of the present application, the method may further include:

[0021] After obtaining the recognition result of the target information, the recognition result is verified; when the recognition result is verified to be correct, the confidence level of the recognition result is determined; when the recognition result is verified to be incorrect, a one-key return mode is entered.

[0022] In an exemplary embodiment of the present application, the method may further include: after obtaining the recognition result of the target information, determining a preference corresponding to the recognition result, and determining a corresponding execution mode according to the confidence and the preference.

[0023] An embodiment of the present application also provides a terminal device, which may include a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and is characterized in that when the instructions are executed by the processor, the automatic control method of the terminal device described in any one of the above is implemented.

[0024] The terminal device of an embodiment of the present application may include an information collection device for collecting target information; the method may include: obtaining a recognition result of the target information; determining the confidence level of the recognition result; and determining a corresponding execution mode based on the confidence level. Through this embodiment, the user's confirmation intention is accurately obtained, the accuracy of image recognition algorithms is improved, the accuracy of information confirmation is improved, the number of user interventions is reduced, the number of erroneous operations is reduced, the probability of user error correction is reduced, and the user experience is improved.

[0025] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present application. Other advantages of the present application can be realized and obtained by the solutions described in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide an understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0027] Figure 1 This is a flow chart of the terminal interaction method according to an embodiment of the present application;

[0028] Figure 2 A schematic diagram of the one-key return interaction mode of an embodiment of the present application;

[0029] Figure 3 This is a flow chart of a method for determining the confidence level of information to be confirmed according to an embodiment of the present application;

[0030] Figure 4 This is a flow chart of a method for determining a processing preference for confirmation information according to an embodiment of the present application;

[0031] Figure 5 This is a first schematic diagram of the terminal interaction method according to an embodiment of the present application;

[0032] Figure 6 This is a second schematic diagram of the terminal interaction method according to an embodiment of the present application;

[0033] Figure 7 This is a schematic diagram of the automatic confirmation mode of an embodiment of the present application;

[0034] Figure 8 This is a schematic diagram of a one-key confirmation mode of an embodiment of the present application;

[0035] Figure 9 This is a schematic diagram of a one-key cancellation mode according to an embodiment of the present application;

[0036] Figure 10This is a schematic diagram of an embodiment of the present application in which the information to be confirmed is an image of food in an oven;

[0037] Figure 11 This is a schematic diagram of the terminal structure of an embodiment of the present application. DETAILED DESCRIPTION

[0038] This application describes multiple embodiments, but this description is exemplary rather than restrictive, and it will be apparent to those skilled in the art that there may be more embodiments and implementations within the scope of the embodiments described herein. Although many possible feature combinations are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with any other feature or element in any other embodiment, or may replace any other feature or element in any other embodiment.

[0039] This application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features, and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive solution defined by the claims. Any features or elements of any embodiment may also be combined with features or elements from other inventive solutions to form another unique inventive solution defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application may be implemented individually or in any appropriate combination. Therefore, except for the limitations made according to the appended claims and their equivalents, the embodiments are not subject to other limitations. In addition, various modifications and changes may be made within the scope of protection of the appended claims.

[0040] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a specific sequence of steps. However, to the extent that the method or process does not rely on the specific order of the steps described herein, the method or process should not be limited to the steps in the specific order described. As will be understood by those skilled in the art, other orders of steps are also possible. Therefore, the specific order of the steps set forth in the specification should not be interpreted as a limitation to the claims. In addition, the claims for the method and / or process should not be limited to performing their steps in the order written, and those skilled in the art can readily understand that these orders can be changed and still remain within the spirit and scope of the embodiments of the present application.

[0041] The embodiment of the present application provides an automatic control method for a terminal device, wherein the terminal device may include an information collection device for collecting target information; Figure 1 As shown, the method may include steps S101-S103:

[0042] S101, obtaining the recognition result of the target information;

[0043] S102, determining the confidence level of the recognition result;

[0044] S103: Determine a corresponding execution mode according to the confidence level.

[0045] In an exemplary embodiment of the present application, information to be confirmed about a control instruction may be received and used as the target information; the information to be confirmed may be feedback information for the control instruction.

[0046] In an exemplary embodiment of the present application, the control instructions may include, but are not limited to, voice control instructions, operation control instructions (e.g., touch operation on a display device, key operation on a preset key, etc.), gesture instructions, card swiping instructions, etc. For example, the operation of starting a function in a home appliance, access control card swiping operation, access control face recognition operation, payment operation, etc.

[0047] In an exemplary embodiment of the present application, the target information may include any one or more of the following: status description information, image information, biometric information, payment information, and sensor measurement data;

[0048] The biometric information may include any one of the following: iris information, fingerprint information, voice information, face information, and gesture information.

[0049] In exemplary embodiments of the present application, for example, when the embodiments of the present application are applied to a smart oven in the field of home appliances, the target information received by the terminal device may include an image of the ingredients in the oven, information about the type of ingredients after identification, and information about the position of baking trays and grills. When the embodiments of the present application are applied to management systems such as access control and attendance in the field of security, the target information received by the terminal device may include biometric information that uniquely identifies a natural person, such as facial image information, fingerprint image information, finger or palm vein image information, and iris information.

[0050] In an exemplary embodiment of the present application, the target information can be information to be confirmed issued by the terminal device itself, or it can be information to be confirmed sent by other devices or terminals. When the target information is information to be confirmed issued by the terminal itself, the embodiment of the present application can be independently implemented by the terminal device, and the terminal device can include: a request module, a display module, a response module, and a perception module. The request module is located in the terminal device and can be responsible for requesting the system to send the information to be confirmed. The display module is located in the terminal device and can be used as an implementation carrier for providing several confirmation interaction modes (confirmation execution modes). The response module is located in the terminal device and can be responsible for responding to the request instructions of various local applications and sending the generated information to be confirmed to the corresponding specific application. The perception module is located in the terminal device and can be used to collect original information data, including but not limited to images and video information captured by the camera on the terminal device, barcode and QR code information scanned by the camera, data information collected by various sensors, etc., and generate recognition results after processing by the local processor. This embodiment enables a security control method based on multiple confirmation interaction modes to be implemented in an application environment that does not require networking.

[0051] In an exemplary embodiment of the present application, the terminal device may include but is not limited to: home appliances, home control units, mobile phones, handheld computers, smart wearable devices, etc.

[0052] In an exemplary embodiment of the present application, the human-computer interaction method adopted by the terminal device may include: display interaction and / or voice interaction.

[0053] In an exemplary embodiment of the present application, display interaction can be performed through a display module (such as a display screen, a touch display screen, etc.), and voice interaction can be performed through a voice recognition and playback module.

[0054] In an exemplary embodiment of the present application, the method may further include: after obtaining the recognition result of the target information, performing information verification on the recognition result; when the recognition result is verified to be correct, determining the confidence level of the recognition result; when the recognition result is verified to be incorrect, entering a one-key return mode.

[0055] In an exemplary embodiment of the present application, the method may further include: after receiving the target information, performing information verification on the target information; when the target information verification is correct, identifying the target information; when the target information verification is incorrect, entering a one-key return mode.

[0056] In an exemplary embodiment of the present application, after receiving the target information, the target information can be first verified by a preset security control module. When the target information verification error occurs, it indicates that the target information itself is wrong. Therefore, you can return to request interaction again with one click, such as Figure 2 As shown, when the target information or recognition result verification error occurs, a one-click return can be implemented on the current terminal. The terminal can include a display module (such as a touch display module), and the main area of ​​the display module can display but is not limited to request failure information or return error information. The one-click return can be implemented by detecting the user's triggering operation on the request failure information or return error information, switching to the initial page; or, automatically switching to the initial page after a limited time expires, so as to re-request the desired function (such as clicking a button to re-request).

[0057] In an exemplary embodiment of the present application, a one-key return mode (such as a sliding undo confirmation event) enables convenient operation when the user's intention changes, avoiding the interactive drawbacks of manual return and multiple operations by the user.

[0058] In an exemplary embodiment of the present application, when the target information and the recognition result are verified to be correct, the confidence level of the recognition result can be determined; and a corresponding execution mode can be determined based on the confidence level.

[0059] In an exemplary embodiment of the present application, the execution mode may include: automatic control mode and one-key confirmation mode.

[0060] In an exemplary embodiment of the present application, the automatic control mode may include: directly entering the execution process of the function corresponding to the recognition result.

[0061] In an exemplary embodiment of the present application, the automatic control mode may also be referred to as an automatic confirmation mode, which may include but is not limited to: directly providing confirmed result information of the target information through human-computer interaction (such as display or voice), and directly entering the execution process of the function corresponding to the confirmed information when no change command or cancellation command for the result is detected within a preset time period;

[0062] In an exemplary embodiment of the present application, the one-key confirmation mode may include: providing one or more option controls to perform one-key confirmation through the option controls;

[0063] The option control is used to represent the correctness of the recognition result; or, to represent possible correct options.

[0064] In an exemplary embodiment of the present application, the one-click confirmation mode may include but is not limited to: providing one or more options to be confirmed (i.e., the above-mentioned option control) through the human-computer interaction method, wherein the one or more options to be confirmed may include the target information; the options other than the target information in the options to be confirmed may be alternative options sorted in descending order according to confidence and / or preference; when any one of the one or more options to be confirmed is selected, one-click confirmation is achieved, and the execution process of the function corresponding to the selected option is directly entered.

[0065] In an exemplary embodiment of the present application, determining the corresponding execution mode according to the confidence level may include:

[0066] When the confidence level is greater than or equal to a first confidence level threshold, the automatic control mode is entered according to the recognition result.

[0067] In an exemplary embodiment of the present application, determining the corresponding execution mode according to the confidence level may further include:

[0068] When the confidence level is less than a first confidence threshold and greater than or equal to a second confidence threshold, the one-key confirmation mode is entered; wherein the first confidence threshold is greater than the second confidence threshold.

[0069] In the exemplary embodiments of the present application, Figure 5 As shown, when the target information received by the terminal passes the security control module (that is, the confidence is greater than or equal to the first confidence threshold, and the recognition result is confirmed to be credible), the terminal can automatically perform a confirmation operation and display the confirmed result information in the display module. When the target information received by the terminal does not pass the security control module (that is, the confidence is less than the first confidence threshold and greater than or equal to the second confidence threshold, and the recognition result is unreliable), the terminal can display the recognition result in the display module and request the user to select the target option according to his or her intention and complete the confirmation operation, and then display the confirmed result information in the display module. Finally, the terminal device responds to the event after this confirmation operation.

[0070] In an exemplary embodiment of the present application, the logic control method within the safety control module can be as follows: Figure 6As shown, the target information confidence (or reliability, security, score, etc., which are parameters that identify the credibility of the target information) and the user habit preference can be arranged in descending order, and then it is determined whether the comprehensive confidence of the target information exceeds the set threshold (such as the first confidence threshold mentioned above). If it exceeds the threshold, the automatic confirmation interaction method can be called; if it does not exceed the threshold, it can continue to determine whether the comprehensive user habit preference of the target information exceeds the set threshold; if it exceeds the threshold, the one-key confirmation interaction method can be called and the project information with the highest preference can be set as the default selected option. If it does not exceed the threshold, the one-key confirmation interaction method can be called and the project information with the highest confidence can be set as the default selected option.

[0071] In the exemplary embodiment of the present application, the automatic confirmation mode, namely the automatic control mode or the automatic confirmation interaction mode, is as follows: Figure 7 As shown, after the recognition result passes the security control module, this interaction mode can be executed according to the confidence level (for example, confirming that the recognition result is credible), and this interaction mode can be implemented on the terminal device. The terminal can include a display module (such as a touch display module), and the main body area of ​​the display module displays the confirmation result information. This area can attract the user's attention through technologies such as color, font, flashing, and dynamic visual effects. If the user's intention is consistent with the displayed confirmation result information, no other operation is required, and the confirmation event can be automatically completed after the specified time is reached. The automatic confirmation mode realizes automatic confirmation of high-confidence information, which can effectively obtain the user's intention and avoid the situation where the user accidentally clicks or operates incorrectly during the confirmation interaction.

[0072] In the exemplary embodiment of the present application, the one-key confirmation mode, i.e., the one-key confirmation interaction mode, is as follows: Figure 8 As shown, this interaction mode can be executed after the target information passes the security control module (for example, the recognition result is unreliable), and this interaction mode can be implemented on the terminal device. The terminal device can include a display module (such as a touch display module), and the main area of ​​the display module can include result information and confirmation buttons for the user to click (that is, one or more option controls provided in the above-mentioned one-key confirmation mode). The result information with high reliability, high confidence, high score, and high user preference can be placed at the top of the area by default and in a selected state. If the default item information is inconsistent with the user's intention, Figure 1 If the default option information does not match the user's intent, the user can manually select the target option and then click the confirmation button to automatically execute the action without clicking again, completing the one-click confirmation interaction mode. The one-click confirmation mode pushes the most likely option as the default selected option, which can infer the user's intent. The single-button setting avoids accidental clicks and misoperations during confirmation interactions.

[0073] In an exemplary embodiment of the present application, the execution mode may further include: a one-key cancellation mode;

[0074] Determining the corresponding execution mode according to the confidence level may include: entering the one-key cancellation mode when the confidence level is less than a second confidence level threshold; and / or,

[0075] The method may further include: after executing the automatic control mode, providing an option control for entering the one-key cancellation mode, so as to cancel the execution process corresponding to the automatic control mode after the option control of the one-key cancellation mode is triggered.

[0076] In an exemplary embodiment of the present application, the one-key undo mode can provide the target information corresponding selection items and a one-key undo option through human-computer interaction; when the one-key undo option is selected, the execution process corresponding to the automatic control mode is canceled.

[0077] In an exemplary embodiment of the present application, the one-key cancellation mode can adopt a sliding cancellation confirmation event interaction method, such as Figure 9 As shown, this interaction method can be executed when the confirmation result information displayed in the main part area of ​​the display module is inconsistent with the user's intention, and this interaction method can be implemented on the terminal. The terminal can include a touch display module, and the main part of the display module can display the confirmation result information. If the user's intention is inconsistent with the displayed confirmation result information, the user can click on the main part area, and then the undo button can be activated to slide out from the bottom of the display module. The user can drag the selected main part area to the undo button, and the one-key sliding undo confirmation event operation is completed. One-key return and re-request realizes automatic return and re-request after the information self-check error, avoiding the interactive disadvantages of manual return and multiple operations by the user.

[0078] In an exemplary embodiment of the present application, the one-key cancellation mode can also allow the user to cancel the current execution process with one key when an execution process error corresponding to the automatic control mode is found.

[0079] In an exemplary embodiment of the present application, the display and touch functions of the above-mentioned display module can also be replaced by the voice broadcast and voice control functions of the voice interaction module.

[0080] In an exemplary embodiment of the present application, the method may further include: after obtaining the recognition result of the target information, determining a preference corresponding to the recognition result, and determining a corresponding execution mode according to the confidence and the preference.

[0081] In an exemplary embodiment of the present application, only a confidence judgment or only a preference judgment can be performed on the recognition result, or both a confidence judgment and a processing preference judgment can be performed on the target information at the same time, for example, a confidence judgment is performed first, and then a processing preference judgment is performed.

[0082] In an exemplary embodiment of the present application, the confidence judgment and preference judgment schemes can be implemented through a preset security control module.

[0083] In the exemplary embodiments of the present application, confidence judgment and preference judgment are respectively introduced in detail below.

[0084] In the exemplary embodiments of the present application, Figure 3 As shown, the confidence judgment of the recognition result may include steps S201-S203:

[0085] S201, detecting a matching degree between an execution function corresponding to a control instruction corresponding to the target information and a function description and / or function display fed back in the recognition result;

[0086] S202: assigning a corresponding confidence score according to the matching degree;

[0087] S203. Compare the confidence score with a pre-stored confidence threshold (such as the first confidence threshold mentioned above). When the confidence score is greater than or equal to the confidence threshold, determine that the recognition result is credible; when the confidence score is less than the confidence threshold, determine that the recognition result is unreliable.

[0088] In an exemplary embodiment of the present application, the confidence level may be replaced by any parameter that identifies the credibility of the recognition result, such as reliability, security, matching degree, matching score, etc.

[0089] In an exemplary embodiment of the present application, the above-mentioned degree of matching can be judged by the degree of conformity of one or more functional features of the two (the execution function corresponding to the control instruction and the functional description and / or functional display fed back in the recognition result). For example, when the control instruction is to bake pizza, the ingredients corresponding to the execution function should be pizza, the corresponding heating method is simultaneous heating of the upper and lower parts, and the baking tray position is the middle layer; if the recognition result of the control instruction for baking pizza is the image information of the ingredients in the oven, then the ingredient information, heating method information, baking tray position information, etc. contained in the ingredient image should be the same as the information corresponding to the above-mentioned execution function, at least the ingredient information should be the same. Therefore, according to the degree of conformity of at least one of the functional features such as the ingredient information, heating method information, baking tray position information, etc. in the two, the degree of matching between the two can be confirmed. When the degree of matching between the two is high, a higher confidence score can be given, and when the degree of matching between the two is low, a lower confidence score can be given.

[0090] In an exemplary embodiment of the present application, the aforementioned multiple functional features may be compared, and different matching scores may be assigned based on different degrees of matching, wherein the higher the matching degree, the higher the matching degree score may be, and the lower the matching degree, the lower the matching degree score may be. After the comparison is completed, the obtained multiple matching degree scores may be weighted and calculated to ultimately determine the confidence score, wherein the weight coefficients used in the weighted calculation may be set to different values ​​based on different functional features, with the greater the importance of the functional feature, the greater the weight coefficient, and the less important the functional feature, the smaller the weight coefficient.

[0091] In the exemplary embodiments of the present application, the set confidence threshold (such as the first confidence threshold) may not be fixed in the embodiment of the present application and may vary according to the usage scenario of the recognition result. For example, in a scenario where the intelligent cooking device confirms the ingredient information after identifying the ingredients and executes the automatic cooking program, the confidence threshold of the recognition result may be required to be no less than 90%; in a scenario where the face recognition confirms the information and performs the monetary payment operation, the confidence threshold of the recognition result may be required to be no less than 95%; in a scenario where the fire monitoring device confirms the information after detecting the fire and performs the warning operation, the confidence threshold of the recognition result may be higher, such as 98%.

[0092] In an exemplary embodiment of the present application, the set confidence threshold can produce different subsequent responses for the same recognition result, so the set confidence threshold can also be different. For example, after the recognition result generated by face recognition is confirmed, one response may be monetary payment and the other response may be access control. In this case, the set confidence threshold for the former must be higher.

[0093] In the exemplary embodiments of the present application, Figure 4 As shown, judging the preference of the target information may include steps S301-S304:

[0094] S301: Obtain preference-related data for the function corresponding to the function description and / or function display fed back in the recognition result.

[0095] In an exemplary embodiment of the present application, obtaining preference-related data for a function corresponding to the function description and / or function presentation fed back in the recognition result may include:

[0096] Obtaining historical execution data of the function corresponding to the function description and / or function presentation fed back in the recognition result;

[0097] calculating execution preferences for the functions based on the historical execution data;

[0098] Sorting the multiple execution parameters of the function according to the execution preference; wherein the sorting according to the execution preference includes: arranging in descending order according to the order of gradually decreasing execution preference;

[0099] The arranged multiple execution parameters are used as the preference-related data.

[0100] In an exemplary embodiment of the present application, the user's habitual preference is obtained from a lot of historical data (i.e., historical execution data) after the user issues such a request, and the user's operation intention for such a request is statistically evaluated based on the historical data, thereby obtaining the execution preference for such a request, and thus obtaining preference-related data.

[0101] In an exemplary embodiment of the present application, for example, for the control scheme of the range hood, the historical execution data may include: 7:10-7:25 high-speed rotation for 10 minutes and then low-speed operation for 5 minutes, 18:20-18:38 high-speed rotation for 15 minutes and then low-speed operation for 3 minutes, 7:11-7:29 high-speed rotation for 13 minutes and then low-speed operation for 5 minutes, 19:00-19:15 high-speed rotation for 11 minutes and then low-speed operation for 4 minutes; 7:15-7:25 high-speed rotation for 8 minutes and then low-speed operation for 2 minutes, 18:00-18:20 high-speed rotation for 17 minutes and then low-speed operation for 3 minutes. Through these historical execution data, preference-related data can be statistically obtained, including: starting the range hood at 7:10-7:30, high-speed rotation for 10-15 minutes, low-speed rotation for 2-5 minutes, and starting the range hood at 18:00-18:30.

[0102] In an exemplary embodiment of the present application, the historical execution data shows that among the preferred execution data for starting the range hood between 7:10 AM and 7:30 AM, high speed for 10-15 minutes, low speed for 2-5 minutes, and between 6:00 PM and 6:30 PM, starting the range hood between 7:10 AM and 7:30 AM has the highest execution preference, followed by low speed for 2-5 minutes, high speed for 10-15 minutes, and finally starting the range hood between 6:00 PM and 6:30 PM. This execution preference ranking can be used as preference-related data in the range hood control solution.

[0103] S302: Compare the execution parameters involved in the function description and / or function presentation with the preference-related data.

[0104] In an exemplary embodiment of the present application, for example, when the execution parameters involved in the function description and / or function display are 7:15-7:30 high-speed rotation for 8 minutes followed by 7 minutes of low-speed operation, compared with the above-mentioned preference-related data, it can be seen that 7:15-7:30 meets the maximum preference of starting the range hood at 7:10-7:30, but 7 minutes of low-speed operation after 8 minutes of high-speed rotation does not meet the preference of 10-15 minutes of high-speed rotation and 2-5 minutes of low-speed rotation.

[0105] S303: Calculate the preference score of the recognition result according to the comparison result.

[0106] In an exemplary embodiment of the present application, calculating the preference score of the recognition result according to the comparison result may include:

[0107] Obtaining execution parameters involved in the function description and / or function presentation that match the preference-related data;

[0108] Performing weighted calculation on the matched execution parameters according to corresponding weighted values ​​to obtain the preference score;

[0109] The weighted value is set according to the preference of the corresponding execution parameter; the higher the preference, the larger the weighted value, and the lower the preference, the smaller the weighted value.

[0110] In an exemplary embodiment of the present application, a preference compliance score can be obtained according to the degree of compliance with different preference-related data, wherein the higher the degree of compliance, the higher the preference compliance score can be. Finally, a weighted calculation can be performed on the multiple preference compliance scores obtained, wherein the weighting coefficient can be determined according to the preference degree of different preference-related data. The higher the preference degree of a certain preference-related data, the higher the corresponding weighting coefficient can be. Conversely, the lower the preference degree of a certain preference-related data, the lower the corresponding weighting coefficient can be.

[0111] In the exemplary embodiment of the present application, as can be seen from the above embodiment, 7:15-7:30 meets the maximum preference for starting the range hood between 7:10-7:30, but 8 minutes of high-speed rotation followed by 7 minutes of low-speed operation does not meet the preferences for 10-15 minutes of high-speed rotation and 2-5 minutes of low-speed rotation. Furthermore, the time point between 7:15-7:30 has a high degree of compliance with the preference for starting the range hood between 7:10-7:30, and thus can receive a higher preference compliance score. Since 8 minutes of high-speed rotation followed by 7 minutes of low-speed operation does not meet the preferences for 10-15 minutes of high-speed rotation and 2-5 minutes of low-speed rotation, the preference compliance scores for the latter two items can be lower, for example, 0. Furthermore, since the preference for starting the range hood between 7:10-7:30 is the highest, the corresponding weighting coefficient of the preference compliance score corresponding to 7:15-7:30 is also relatively high.

[0112] S304. Compare the preference score with a pre-stored preference threshold. When the preference score is greater than or equal to the preference threshold, determine that the recognition result is preference information; when the preference score is less than the preference threshold, determine that the recognition result is non-preference information.

[0113] In an exemplary embodiment of the present application, the set preference threshold (or habitual preference threshold) can be comprehensively determined based on the frequency and historical records of confirmation operations for such requests in the terminal.

[0114] In an exemplary embodiment of the present application, whether the recognition result of the current target information is the user's habit information or preference information can be determined by comparing the calculated preference score with the preference threshold.

[0115] In an exemplary embodiment of the present application, performing confidence judgment and preference judgment on the recognition result may include:

[0116] When the result of the confidence judgment on the recognition result is that the confidence score is less than the confidence threshold (such as the first confidence threshold mentioned above), a preference judgment is performed on the recognition result, and the preference judgment result of the recognition result is used as the judgment result of the recognition result; or,

[0117] The recognition results are respectively subjected to confidence judgment and preference judgment, and the confidence score obtained in the confidence judgment and the preference score obtained in the preference judgment are weighted to obtain a comprehensive judgment score, and the comprehensive judgment score is compared with a preset comprehensive judgment threshold. When the comprehensive judgment score is greater than or equal to the comprehensive judgment threshold, the recognition result is confirmed to be credible; when the comprehensive judgment score is less than the comprehensive judgment threshold, the recognition result is confirmed to be unreliable.

[0118] In the exemplary embodiments of the present application, this embodiment provides two processing embodiments for executing both confidence judgment and preference judgment.

[0119] In an exemplary embodiment of the present application, a corresponding execution mode is provided according to the judgment result (confidence judgment and / or preference judgment), thereby realizing preliminary automatic processing of the recognition result.

[0120] In the exemplary embodiments of the present application, Figure 6 As shown, providing a corresponding execution mode according to the judgment result to perform preliminary automatic processing on the target information may include:

[0121] When it is determined that the target information is credible and / or the target information is preferred information, providing the automatic confirmation mode;

[0122] When it is determined that the target information is not credible and the target information is preference information, providing the one-key confirmation mode;

[0123] When it is determined that the target information is not credible and / or the target information is not preferred information, the one-key cancellation mode is provided.

[0124] In the exemplary embodiments of the present application, the embodiment scheme of the present application is explained below through several specific embodiments.

[0125] In the exemplary embodiments of the present application, in the application embodiments of smart cooking devices, for example, rice cookers, ovens and other smart cooking devices are based on interactive solutions based on image recognition. When the confidence level of the image-recognized ingredients is higher than a threshold, the automatic cooking control process is entered without interacting with the user; when the confidence level is lower than the threshold, an interaction occurs for user confirmation. The adoption of this solution reduces the number of user interventions on the one hand, and on the other hand, reduces the chance of user error correction, thereby improving the accuracy of the image recognition algorithm.

[0126] In the exemplary embodiment of the present application, in the application embodiment of the smart oven in the field of home appliances, as shown in FIG. Figure 10 As shown, when the target information received by the terminal is the image of the ingredients in the oven, the type of ingredients after ingredient identification, and the position information of the baking tray and grill, the threshold parameter (such as the confidence threshold) in the safety control module is the confidence score value of the ingredient identification result. The set confidence threshold can be 90 points. The user habit preferences stored in the safety control module can be moderate, crispy, soft and tender taste preferences for ingredients cooked in the oven.

[0127] In an exemplary embodiment of the present application, after placing ingredients in the oven, you can click the one-click cooking button for ingredient identification. If the confidence score of the ingredient identification result is higher than the set threshold (i.e., the confidence threshold, such as 90 points), you can execute an automatic confirmation interaction method. For example, the main display area displays the image of the ingredients in the oven and the confirmation result information after the ingredients are identified, and then responds to the confirmation operation event, that is, automatically calls the corresponding cooking process to bake the ingredients.

[0128] In an exemplary embodiment of the present application, if the confidence score of the ingredient recognition result is lower than the set threshold (such as 90 points), a one-click confirmation interaction method can be executed, and the main display area displays the image of the ingredients in the oven and the options of the ingredient types (the ingredient type with the highest confidence score can be at the top and can be selected by default). When the default selected ingredient type is consistent with the user's intended option, you can click the one-click cooking button. When the default selected ingredient type is inconsistent with the user's intended option, the one-click cooking button can automatically enable confirmation after clicking the target option.

[0129] In an exemplary embodiment of the present application, in an application embodiment of voice interaction in the field of home appliances, if the target information received by the terminal is voice command information for controlling home appliances, the threshold parameter (confidence threshold, such as the first confidence threshold) in the security control module can be a numerical value that measures the reliability score of the voice command information after voice recognition, and the user habit preference in the security control module can be the user's expression habit preference for expressing a certain control command by voice. Taking a range hood with a voice interaction function as an example, when a user issues a voice command to start, shut down, or adjust the air volume, if the reliability score (confidence score) of the voice command recognition result is higher than a set threshold (confidence threshold, such as the first confidence threshold), an automatic confirmation interaction mode can be executed (i.e., an automatic confirmation mode is provided), and the voice interaction module can broadcast the confirmed command result information, and then respond to the event of the confirmation operation, i.e., automatically control the working status of the range hood. If the reliability score of the voice command recognition result is lower than the set threshold, a one-key confirmation interaction method can be executed (i.e., a one-key confirmation mode is provided). The voice interaction module can broadcast the recognized voice command result in an inquiry manner. When the user intends to give a positive answer to the inquiry, just answer with an affirmative word. When the user intends to give a negative answer to the inquiry, answer with a negative word and interact again.

[0130] In an exemplary embodiment of the present application, in an application embodiment of a management system such as access control and attendance in the security field, the target information received by the terminal can be biometric information that uniquely identifies a natural person, such as facial image information, fingerprint image information, finger vein or palm vein image information, and the threshold parameter (confidence threshold, such as a first confidence threshold) within the security control module is the matching degree of the biometric information that uniquely identifies the natural person. When a living person approaches the data acquisition device, the device automatically captures and identifies the biometric information. If the matching score (confidence score) of the biometric recognition result is higher than a set threshold (confidence threshold, such as the first confidence threshold), an automatic confirmation interaction mode (i.e., providing an automatic confirmation mode) can be executed, and the main display area can display the target person's confirmation result information, followed by a response to a confirmation operation event, such as verification passed, gate opening, or attendance information entry. If the matching score of the biometric recognition result is lower than the set threshold, a one-click confirmation interaction mode (i.e., providing a one-click confirmation mode) can be executed, and the main display area can prompt the user to re-verify, enter a password for verification, or request assistance from an administrator.

[0131] In an exemplary embodiment of the present application, the terminal confirmation interaction method of the embodiment of the present application is that when the recognition result received by the terminal passes the verification of the security control module (that is, the recognition result is credible and / or the recognition result is preference information), the terminal automatically performs a confirmation operation and displays the confirmed result information in the display module. When the recognition result received by the terminal does not pass the verification of the security control module (that is, the recognition result is not credible and / or the recognition result is not preference information), the terminal displays the recognition result in the display module and requests the user to select the target option according to his or her intention and complete the confirmation operation, and then displays the confirmed result information in the display module. Finally, the terminal responds to the event after this confirmation operation. The embodiment of the present application can more accurately obtain the user's confirmation intention, avoid the user's repetitive confirmation operations for highly reliable recognition results, and also avoid the losses caused by the user's accidental clicks and erroneous operations, thereby improving the user interaction experience.

[0132] The present application embodiment also provides a terminal device 1, such as Figure 11 As shown, it may include a processor 11 and a computer-readable storage medium 12, wherein the computer-readable storage medium 12 stores instructions. When the instructions are executed by the processor 11, any one of the above-mentioned automatic control methods of the terminal device is implemented.

[0133] In an exemplary embodiment of the present application, the terminal device 1 may further include a human-computer interaction module 13 , and when the instruction is executed by the processor 11 and the human-computer interaction module 13 , the terminal interaction method described above is implemented.

[0134] In the exemplary embodiments of the present application, any embodiment in the above method embodiments can be applied to the terminal embodiment, and will not be described one by one here.

[0135] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As is well known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable, and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media generally embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

Claims

1. A method for automatically controlling a terminal device, characterized in that: The terminal device includes an information collection device for collecting target information; the method includes: Obtaining an identification result of the target information; Determining a confidence level of the recognition result; Determine a corresponding execution mode according to the confidence level; the execution modes include: automatic control mode and one-key confirmation mode; the method also includes: after obtaining the recognition result of the target information, determine the preference level corresponding to the recognition result, and determine a corresponding execution mode according to the confidence level and the preference level, wherein the confidence level and the preference level are arranged in descending order, and then determine whether the confidence level of the target information exceeds a first confidence threshold. If it exceeds the first confidence threshold, the automatic control mode can be called. If it does not exceed the first confidence threshold, continue to determine whether the preference level of the target information exceeds a set threshold. If it exceeds the set threshold, the one-key confirmation mode can be called and the project information with the highest preference level is set as the default selected option. If it does not exceed the set threshold, the one-key confirmation mode can be called and the project information with the highest confidence level is set as the default selected option.

2. The automatic control method of a terminal device according to claim 1, characterized in that: The automatic control mode includes: directly entering the execution process of the function corresponding to the recognition result.

3. The automatic control method of terminal equipment according to claim 1, characterized in that: Determining the corresponding execution mode according to the confidence level includes: When the confidence level is less than a first confidence threshold and greater than or equal to a second confidence threshold, the one-key confirmation mode is entered; wherein the first confidence threshold is greater than the second confidence threshold.

4. The automatic control method of a terminal device according to claim 1 or 3, characterized in that: The one-key confirmation mode includes: providing one or more option controls to perform a confirmation through the option controls; The option control is used to represent the correctness of the recognition result; or, to represent possible correct options.

5. The automatic control method of terminal equipment according to claim 1, characterized in that: The execution mode also includes: a one-key cancellation mode; Determining the corresponding execution mode according to the confidence level includes: entering the one-key cancellation mode when the confidence level is less than a second confidence level threshold; and / or, The method further includes: after executing the automatic control mode, providing an option control for entering the one-key cancellation mode, so as to cancel the execution process corresponding to the automatic control mode after the option control of the one-key cancellation mode is triggered.

6. The automatic control method of a terminal device according to any one of claim 1, characterized in that: The method further comprises: After obtaining the recognition result of the target information, the recognition result is verified; when the recognition result is verified to be correct, the confidence level of the recognition result is determined; when the recognition result is verified to be incorrect, a one-key return mode is entered.

7. A terminal device, characterized in that: The method comprises a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and is characterized in that when the instructions are executed by the processor, the automatic control method of the terminal device according to any one of claims 1 to 6 is implemented.

Images