A method for preventing false awakening of digital people in public places, related devices and storage medium

Abstract

The present invention provides a method for preventing a digital person from being woken up by mistake in a public place, a related device and a storage medium. The method comprises: collecting audio information and live face information in real time; judging whether preliminary wake-up information and deep wake-up information are collected in sequence based on the audio information, and judging whether live face information is detected; if preliminary wake-up information and deep wake-up information are collected in sequence and live face information is detected, controlling the digital person to wake up; the digital person is controlled to wake up only after the above-mentioned multiple conditions are met respectively, and in addition, the deep wake-up information is wake-up inquiry information output after the preliminary wake-up information is collected, and the corresponding wake-up confirmation information; that is, after obtaining the preliminary wake-up information, a question-and-answer process is required with the user to confirm the user's need to wake up the digital person; it is not awakened by the user's unilateral audio or face image, which reduces the false awakening rate and the energy consumption of the digital person.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and more specifically, relates to a method for preventing digital people from being woken up by mistake in public places, a related device and a storage medium. Background Art

[0002] With the continuous advancement of science and technology and the continuous development of digital human technology, digital humans have gradually entered thousands of households. Many digital humans have also appeared on the market, bringing convenience and fun to people's lives. Among them, interactive robots, as a type of intelligent robot, can interact with people and provide convenience to people's lives.

[0003] With the development of social productivity and the improvement of living standards, people spend more and more time on leisure and entertainment, which greatly promotes the development of the service industry. In recent years, the population flow in public places, such as airports and shopping malls, has increased dramatically.

[0004] At present, the probability of false awakening is very high when the digital human is only detected by infrared human body in public places, and the probability of false awakening is very high when it is only awakened by key information, because the communication information and broadcast information of people in the place are everywhere, and the probability of false awakening is also very high. In other words, the digital human is in the awake state for a long time, the false awakening rate is high, and its energy consumption is large. Summary of the invention

[0005] In view of this, the object of the present invention is to provide a method for preventing false awakening of a digital human in a public place, a related device and a storage medium, so as to reduce the false awakening rate and the energy consumption of the digital human.

[0006] The first aspect of the present application discloses a method for preventing a digital person from being woken up by mistake in a public place, comprising:

[0007] Collect audio information and live face information in real time;

[0008] Based on the audio information, determining whether preliminary awakening information and deep awakening information are collected in sequence, and determining whether the living face information is detected; wherein the deep awakening information is the awakening inquiry information output after the preliminary awakening information is collected, and its corresponding awakening confirmation information;

[0009] If the preliminary awakening information and the deep awakening information are collected in sequence and the living face information is detected, the digital human is controlled to wake up.

[0010] Optionally, in the above-mentioned method for preventing false awakening of a digital person in a public place, judging whether preliminary awakening information and deep awakening information are collected in sequence based on the audio information includes:

[0011] Determining whether preset wake-up keyword information is collected based on the audio information; the wake-up keyword information is the preliminary wake-up information;

[0012] If yes, the interactive response mode is started and the wake-up inquiry message is output;

[0013] Based on the audio information, it is determined whether the wake-up confirmation information corresponding to the wake-up query information is collected.

[0014] Optionally, in the above-mentioned method for preventing false awakening of a digital person in a public place, starting the interactive response mode and outputting the awakening inquiry information includes:

[0015] Starting the interactive response mode;

[0016] After the preset time period of starting the interactive answering mode, a wake-up inquiry message is output.

[0017] Optionally, in the above-mentioned method for preventing false awakening of a digital person in a public place, after the preset time of starting the interactive response mode, outputting the awakening inquiry information includes:

[0018] If the user's consultation information is collected within the preset time length of starting the interactive response mode, wake-up inquiry information based on the consultation information is output.

[0019] Optionally, in the above-mentioned method for preventing false awakening of a digital person in a public place, after the preset time of starting the interactive response mode, outputting the awakening inquiry information includes:

[0020] If the user's consultation information is not collected within the preset time length of starting the interactive response mode, the preset wake-up inquiry information is output.

[0021] Optionally, in the above-mentioned method for preventing the digital human from being woken up by mistake in a public place, controlling the digital human to wake up includes:

[0022] Activate the network communication mode; start picking up sounds and sending them to the server for digital human services.

[0023] Optionally, in the above-mentioned method for preventing false awakening of a digital person in a public place, judging whether the living face information is detected includes:

[0024] Based on the facial image information collected when collecting live face information in real time, determining whether the facial image information is the frontal facial image information of the user;

[0025] If so, it is determined that the living face information is detected; if not, it is determined that the living face information is not detected.

[0026] The second aspect of the present application discloses a device for preventing a digital person from being woken up by mistake in a public place, comprising:

[0027] The acquisition module is used to collect audio information and live face information in real time;

[0028] a judgment module, configured to judge whether preliminary awakening information and deep awakening information are collected in sequence based on the audio information, and to judge whether the living face information is detected; the deep awakening information is the awakening confirmation information corresponding to the awakening query information output after the preliminary awakening information is collected;

[0029] The wake-up module is used to control the wake-up of the digital human if the preliminary wake-up information and the deep wake-up information are collected in sequence and the living face information is detected.

[0030] Optionally, in the above-mentioned public place digital person anti-false awakening device, the judgment module includes:

[0031] A first judgment unit is used to judge whether preset wake-up keyword information is collected based on the audio information; the wake-up keyword information is the preliminary wake-up information;

[0032] An interactive response module, configured to start an interactive response mode and output a wake-up inquiry message if the judgment result of the judgment unit is yes;

[0033] The first determination unit is further configured to determine whether the wake-up confirmation information corresponding to the wake-up query information is collected based on the audio information.

[0034] Optionally, in the above-mentioned public place digital personal anti-false awakening device, the interactive response module is used to start the interactive response mode and output the awakening inquiry information, specifically for:

[0035] Starting the interactive response mode;

[0036] After the preset time period of starting the interactive answering mode, a wake-up inquiry message is output.

[0037] Optionally, in the above-mentioned public place digital personal anti-false awakening device, the interactive response module is used to output the awakening inquiry information after the preset time length of the interactive response mode is started, specifically for:

[0038] If the user's consultation information is collected within the preset time length of starting the interactive response mode, wake-up inquiry information based on the consultation information is output.

[0039] Optionally, in the above-mentioned public place digital personal anti-false awakening device, when the interactive response module outputs the awakening inquiry information after starting the preset time of the interactive response mode, it is specifically used to:

[0040] If the user's consultation information is not collected within the preset time length of starting the interactive response mode, the preset wake-up inquiry information is output.

[0041] Optionally, in the above-mentioned digital human anti-mis-awakening device in public places, the awakening module is used to control the awakening of the digital human, specifically for:

[0042] Activate the network communication mode; start picking up sounds and sending them to the server for digital human services.

[0043] Optionally, in the above-mentioned public place digital person anti-false awakening device, the judgment module further includes:

[0044] A second judgment unit is used to judge whether the facial image information is the frontal facial image information of the user based on the facial image information collected when the living facial information is collected in real time;

[0045] If so, it is determined that the living face information is detected; if not, it is determined that the living face information is not detected.

[0046] The third aspect of the present application discloses an electronic device, comprising:

[0047] one or more processors;

[0048] a storage device having one or more programs stored thereon;

[0049] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for preventing false awakening of a digital person in a public place as described in any one of the first aspects of the present application.

[0050] A fourth aspect of the present application discloses a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for preventing false awakening of a digital person in a public place as described in any one of the first aspects of the present application is implemented.

[0051] It can be seen from the above technical scheme that the present invention provides a method for preventing false awakening of digital humans in public places, including: real-time collection of audio information and live face information; judging whether preliminary awakening information and deep awakening information are collected in sequence based on audio information, and judging whether live face information is detected; if preliminary awakening information and deep awakening information are collected in sequence and live face information is detected, controlling the digital human to wake up; the digital human is controlled to wake up only after the above multiple conditions are met respectively, and in addition, the deep awakening information is the awakening inquiry information output after the preliminary awakening information is collected, and its corresponding awakening confirmation information; that is, after obtaining the preliminary awakening information, a question-and-answer process is required with the user to confirm the user's need to wake up the digital human; it is not awakened by the user's unilateral audio or face image, which reduces the false awakening rate and reduces the energy consumption of the digital human. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 It is a schematic diagram of an application environment provided by an embodiment of the present invention and applicable to an embodiment of the present application;

[0054] Figure 2 It is a flow chart of a method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0055] Figure 3 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0056] Figure 4 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0057] Figure 5 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0058] Figure 6 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0059] Figure 7 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0060] Figure 8 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0061] Fig. 9 is a flow chart of another method for preventing a digital person from being woken up by mistake in a public place provided by an embodiment of the present invention;

[0062] Fig.10 It is a schematic diagram of a digital person anti-false awakening device in a public place provided by an embodiment of the present invention;

[0063] Fig.11 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0066] See also Figure 1 , Figure 1 A schematic diagram of an application environment applicable to the embodiment of the present application is shown. The data processing method provided in the embodiment of the present application can be used for Figure 1 The interactive system 100 shown in FIG. 1 includes a terminal device 101 and a server 102, and the server 102 is in communication connection with the terminal device 101. The server 102 may be a traditional server or a cloud server, which is not specifically limited here.

[0067] The terminal device 101 may be any electronic device having a display screen, a data processing module, a camera, audio input / output, and other functions, and supporting data input, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, a self-service terminal, and a wearable electronic device. Specifically, data input may be based on voice input through a voice module on the electronic device, character input through a character input module, and the like. Specifically, the terminal device 101 may be a digital human in the following embodiments.

[0068] Among them, the terminal device 101 may be installed with a client application, and the user may communicate with the digital human based on the client application (such as an APP, a WeChat applet, etc.), wherein the conversational digital human of this embodiment is also a client application configured in the terminal device 101. The user may register a user account on the server 102 based on the client application, and communicate with the server 102 based on the user account, for example, the user logs in to the user account on the client application, and inputs through the client application based on the user account, and may input text information or voice information, etc. After the client application receives the information input by the user, it may send the information to the server 102, so that the server 102 may receive the information and process and store it, and the server 102 may also receive the information and return a corresponding output information to the terminal device 101 according to the information.

[0069] In some implementations, the device for processing the data to be identified may also be disposed on the terminal device 101 , so that the terminal device 101 can interact with the user without relying on the server 102 to establish communication. In this case, the interactive system 100 may only include the terminal device 101 .

[0070] The embodiment of the present application provides a method for preventing false awakening of a digital human in a public place, which is used to solve the problem that the probability of false awakening of a digital human in a public place is very high when infrared human body monitoring is used in the prior art, and the false awakening probability is very high when key information is used for awakening, because the communication information and broadcast information of people in the place are everywhere, that is, the false awakening rate is high, and the energy consumption is high.

[0071] See also Figure 2 The method for preventing false awakening of a digital person in a public place includes:

[0072] S101. Collect audio information and live face information in real time.

[0073] It should be noted that the digital human has a collection device, such as collecting audio information through an audio collector and collecting live face information through a face collector.

[0074] The live face information may include a live face image, which may be a two-dimensional image, a three-dimensional image, an infrared image, etc., which is not specifically limited here and depends on the actual situation, and all are within the protection scope of this application.

[0075] S102: Determine whether preliminary awakening information and deep awakening information are collected in sequence based on the audio information, and determine whether living face information is detected.

[0076] Specifically, step S102 can be divided into two judgments; only when both judgment results are yes, it can be said that the judgment result of step S102 is that preliminary wake-up information and deep wake-up information are collected in sequence and living face information is detected.

[0077] It should be noted that the specific process of determining whether the preliminary awakening information and the deep awakening information are collected in sequence based on the audio information may be: converting the collected audio information into text information, and then determining whether the preliminary awakening information and the deep awakening information exist in the text information.

[0078] Among them, the deep awakening information is the awakening inquiry information output after the preliminary awakening information is collected, and its corresponding awakening confirmation information.

[0079] That is, after the preliminary wake-up information is collected, the wake-up query information is output; after the wake-up query information is output, it is determined whether the wake-up confirmation information corresponding to the wake-up query information is collected based on the currently collected audio information.

[0080] The specific process of determining whether preliminary wake-up information and deep wake-up information are collected in sequence based on audio information will not be described in detail here. It will depend on the actual situation and is within the scope of protection of this application.

[0081] The specific process of determining whether live face information is detected may be: determining whether the collected face image meets preset conditions; the preset conditions may include: the proportion of the collected face, whether it is live information, etc.

[0082] The specific process of determining whether live face information is detected will not be described in detail here. It will depend on the actual situation and is within the scope of protection of this application.

[0083] The two judgment steps in step S102 are parallel, that is, they have no order relationship. Therefore, step S102 can be that when the two judgment results are yes at the same time, it is determined that the preliminary awakening information and the deep awakening information are collected in sequence and the live face information is detected.

[0084] It is also possible to set a time difference between the two judgments; specifically, if any one judgment result is yes, and the other judgment result is yes within a preset time length, it is determined that preliminary wake-up information and deep wake-up information are collected in sequence and living face information is detected.

[0085] If the preliminary awakening information and the deep awakening information are collected in sequence and the living face information is detected, step S103 is executed.

[0086] S103, controlling the digital human to wake up.

[0087] It should be noted that after the digital human is awakened, it can provide corresponding services to the user.

[0088] If the user asks the digital human about the process of applying for a credit card, the digital human will show the user the process of applying for a credit card. Specifically, the process can be displayed on the digital human's own display, and the audio of the process of applying for a credit card can also be output at the same time.

[0089] It should be noted that step S101 is collected in real time, that is, the actions of steps S102 and S103 do not affect the execution of step S101. Similarly, since step S101 collects data in real time, step S102 also needs to make judgments in real time to keep up with the pace of step S101 and make judgments on all collected data.

[0090] In actual applications, if the preliminary awakening information and the deep awakening information are not collected in sequence, or the living face information is detected, step S103 is not executed.

[0091] In this embodiment, audio information and live face information are collected in real time; based on the audio information, it is determined whether preliminary wake-up information and deep wake-up information are collected in sequence, and whether live face information is detected; if preliminary wake-up information and deep wake-up information are collected in sequence and live face information is detected, the digital human is controlled to wake up; the digital human is controlled to wake up only after the above multiple conditions are met respectively. In addition, the deep wake-up information is the wake-up inquiry information output after the preliminary wake-up information is collected, and its corresponding wake-up confirmation information; that is, after obtaining the preliminary wake-up information, a question-and-answer process is required with the user to confirm the user's need to wake up the digital human; it is not awakened by the user's unilateral audio or face image, which reduces the false awakening rate and reduces the energy consumption of the digital human.

[0092] In the above embodiment, the step S102 involves determining whether preliminary awakening information and deep awakening information are collected in sequence based on audio information, see Figure 3 ,include:

[0093] S201: Determine whether preset wake-up keyword information is collected based on audio information.

[0094] Among them, the wake-up keyword information is preliminary wake-up information.

[0095] The wake-up keyword information can be the name of the digital person, such as "Xiaoyi", etc.; of course, it can also be other information, which is not specifically limited here and can be determined according to the actual situation, all of which are within the scope of protection of this application.

[0096] The wake-up keyword information may be multiple, such as: "Xiaoyi", "Hello", etc.; of course, it can also be one; there is no specific limitation here, it depends on the actual situation, and it is all within the protection scope of this application.

[0097] If it is determined based on the audio information whether the preset wake-up keyword information is collected, step S202 is executed.

[0098] S202: Start the interactive response mode and output the wake-up inquiry information.

[0099] It should be noted that the digital human is internally provided with an interactive response module, and the interactive response mode can be started by controlling the interactive response module to start.

[0100] The digital human may have two levels of awakening, such as preliminary awakening and deep awakening. The awakening in step S103 is deep awakening.

[0101] Specifically, the digital human may include a collection module, an interactive response module and a network communication module. When the digital human is powered on, the collection module continues to work.

[0102] When the interactive response module is started, the digital human is in the primary awakening state; at this time, the energy consumption of the digital human is greater than the energy consumption when only the acquisition module is working.

[0103] When all network communication modules are started, the digital human is in deep awakening; at this time, the energy consumption of the digital human is greater than that of the primary awakening.

[0104] S203: Determine whether wake-up confirmation information corresponding to the wake-up query information is collected based on the audio information.

[0105] That is to say, in the interactive response mode, the digital human can interact with the user and determine whether deep awakening is required by asking and receiving the user's response.

[0106] It should be noted that if the corresponding wake-up confirmation information is collected within the first time after the wake-up query information is output, it is determined that deep wake-up is required. If the corresponding wake-up confirmation information is not collected within the first time after the wake-up query information is output, or the wake-up cancellation information is collected, it is determined that deep wake-up is not required.

[0107] For example, if the wake-up inquiry message is: Do you want to ask a question to the first grader?, the wake-up confirmation message can be: yes, right, etc., which carry certain words; the wake-up cancellation message can be: no, no, etc., which carry negative words.

[0108] Of course, the information is not limited to the above descriptions, and will not be elaborated here one by one. It will depend on the actual situation and is within the scope of protection of this application.

[0109] In this embodiment, a two-level awakening method is used for awakening, wherein deep awakening is performed after the digital human obtains confirmation information corresponding to the inquiry information, thereby avoiding false awakening of the digital human and reducing the power consumption of the digital human.

[0110] In practical applications, see Figure 4 The specific process of step S202 may be:

[0111] S301, start interactive response mode.

[0112] S302: After the preset duration of the interactive response mode is started, a wake-up inquiry message is output.

[0113] That is to say, after the interactive response mode is started, the wake-up inquiry information is not output directly, but after waiting for a preset time, the wake-up inquiry information is output.

[0114] The value of the preset duration is not specifically limited here and may be determined according to actual conditions and is within the scope of protection of this application.

[0115] Of course, the present application does not exclude the solution of directly outputting the wake-up inquiry information after starting the interactive response mode, which will not be elaborated here one by one. It depends on the actual situation and is within the protection scope of the present application.

[0116] For example, the interactive answering mode is started, and one minute after the interactive answering mode is started, a wake-up inquiry message "Are you sure you want to wake up Xiaoyi?" is output.

[0117] The above process is only an example and will not be described in detail here. It will depend on the actual situation and is within the scope of protection of this application.

[0118] In this embodiment, by outputting the wake-up inquiry information after a preset time period of starting the interactive answering mode, instead of outputting the wake-up inquiry information immediately, the preset time period can be reserved for data processing.

[0119] In practical applications, see Figure 5 The specific process of step S302 is:

[0120] S401: Determine whether the user's consultation information is collected within the preset time length of starting the interactive response mode.

[0121] The specific value of the preset duration is not specifically limited here and may be determined according to actual conditions, and is within the scope of protection of this application.

[0122] If the user's consultation information is collected within the preset time period of starting the interactive answering mode, step S402 is executed.

[0123] S402: Output wake-up inquiry information based on the consultation information.

[0124] Specifically, the wake-up inquiry information is mainly used to determine the user's needs. That is, if consultation information is collected, it is necessary to confirm whether the consultation information is the information that the user needs to consult the digital human.

[0125] For example, the user says to the digital human "I want to consult the credit card application process", that is, the user's consultation information is: credit card application process. At this time, the digital human outputs to the user "Are you sure you want to consult the credit card application process?", that is, the wake-up inquiry information based on the consultation information is: Are you sure you want to consult the credit card application process?

[0126] In this embodiment, by judging whether the user's consultation information is collected within the preset time of starting the interactive answering mode, and when the user's consultation information is collected within the preset time of starting the interactive answering mode, the wake-up inquiry information based on the consultation information is output, so that the wake-up inquiry information output by the digital human is related to the user's consultation information, making the digital human more humanized.

[0127] In practical applications, see Figure 6 The specific working process of step S302 is:

[0128] S501: Determine whether the user's consultation information is collected within the preset time length of starting the interactive response mode.

[0129] If the user's consultation information is not collected within the preset time length of starting the interactive answering mode, step S502 is executed.

[0130] S502: Output preset wake-up inquiry information.

[0131] Specifically, the wake-up inquiry information is mainly used to determine the user's need for wake-up, that is, if the inquiry information is not collected, it is necessary to confirm whether the user needs to wake up the digital human.

[0132] The preset wake-up inquiry message may be: Are you sure you want to wake up Xiaoyi? Of course, it is not limited to the above example. The preset wake-up inquiry message will not be repeated here. It depends on the actual situation and is within the protection scope of this application.

[0133] In this embodiment, by judging whether the user's consultation information is collected within the preset time length of starting the interactive answering mode, and when the user's consultation information is not collected within the preset time length of starting the interactive answering mode, the preset wake-up inquiry information is output; that is, the default wake-up inquiry information of the digital person is set, so as to make the interaction information between the digital person and the user clear.

[0134] In practical applications, the embodiments Figure 5 and Figure 6 Can be used alone or in combination. Figure 7 , step S501 and step S401 are consistent, so one of them can be omitted, Figure 7 The example of omitting step S501 is used for demonstration.

[0135] Specifically, the combined process is:

[0136] S401: Determine whether the user's consultation information is collected within the preset time length of starting the interactive response mode.

[0137] If the user's consultation information is collected within the preset time period of starting the interactive answering mode, step S402 is executed.

[0138] S402: Output wake-up inquiry information based on the consultation information.

[0139] If the user's consultation information is not collected within the preset time length of starting the interactive answering mode, step S502 is executed.

[0140] S502: Output preset wake-up inquiry information.

[0141] In this embodiment, wake-up query information is set in two situations, that is, the wake-up query information output by the digital human is related to the user's query information, or it is the default wake-up query information to humanize the digital human. There are corresponding wake-up query information in various situations.

[0142] In the above embodiments, see Figure 8 (In Figure 7 The specific process of step S103, controlling the digital human to wake up, is as follows:

[0143] S601, activating the network communication mode; and starting to pick up sounds and send them to the server to provide digital human services.

[0144] It should be noted that the digital human has a network communication module, and the network communication mode can be activated by controlling the network communication module to start.

[0145] After activating the network communication mode, the digital human can interact with the network communication module; specifically.

[0146] Specifically, the sound collection is the process of collecting sound. That is, the digital human sends the collected user consultation information to the server, the server processes the consultation information, and then feeds back the corresponding solution to the digital human, which is then displayed to the user.

[0147] At the same time, the server also renders digital humans to make them closer to real people, such as displaying the virtual face of the digital human on the display and rendering corresponding expressions, such as pouting and shyness, etc.; it can also control the limbs of the digital human to make the digital human more vivid, such as indicating directions through the digital human's limbs.

[0148] In this embodiment, the network communication mode is activated; and the sound is picked up and sent to the server to provide digital human services, realize intelligent services, and improve the service efficiency of digital humans.

[0149] In the above embodiments, see Fig. 9 (In Figure 3 The specific process of determining whether living face information is detected in step S102 is as follows:

[0150] S701. Based on the facial image information collected when collecting live face information in real time, determine whether the facial image information is the frontal facial image information of the user.

[0151] If so, it is determined that live face information is detected; if not, it is determined that live face information is not detected.

[0152] The process of determining whether it is frontal face image information can be accomplished by determining whether the face image information reaches a preset ratio, or whether the line connecting the two eyes is perpendicular to the nose, etc. Other implementation methods of determining whether it is frontal face image information will not be described here one by one, and are all within the scope of protection of this application.

[0153] It is worth noting that other implementation methods of determining whether live face information is detected, such as determining whether it is live face information through pupil detection, etc., will not be described here one by one, and all are within the scope of protection of this application.

[0154] In this embodiment, based on the facial image information collected when collecting live facial information in real time, it is judged whether the facial image information is the user's frontal facial image information, so as to avoid using facial image information such as side face whose line of sight is not directed to the digital human as live facial information, further reducing the probability of false awakening and reducing the power consumption of the digital human.

[0155] Another embodiment of the present application provides a device for preventing a digital person from being woken up by mistake in a public place.

[0156] See also Fig.10 The public place digital person anti-false awakening device comprises:

[0157] The acquisition module 10 is used to acquire audio information and living face information in real time.

[0158] The acquisition module 10 may include an audio acquisition module and a live face acquisition module;

[0159] The audio acquisition module is used to collect audio information.

[0160] The live face collection module is used to collect live face information.

[0161] The judgment module 20 is used to judge whether the preliminary awakening information and the deep awakening information are collected in sequence based on the audio information, and to judge whether the living face information is detected.

[0162] The deep awakening information is the awakening confirmation information corresponding to the awakening inquiry information output after the preliminary awakening information is collected.

[0163] The awakening module 30 is used to control the awakening of the digital human if the preliminary awakening information and the deep awakening information are collected in sequence and the living face information is detected.

[0164] For details on the working process and principle of each module, please refer to the above embodiments. Figure 2 , which will not be described one by one here, and are all within the protection scope of this application.

[0165] In this embodiment, the acquisition module 10 acquires audio information and live face information in real time; the judgment module 20 determines whether preliminary awakening information and deep awakening information are collected in sequence based on the audio information, and determines whether live face information is detected; if the awakening module 30 collects preliminary awakening information and deep awakening information in sequence and detects live face information, it controls the digital human to wake up; the digital human is controlled to wake up only after the above-mentioned multiple conditions are met respectively. In addition, the deep awakening information is the awakening inquiry information output after the preliminary awakening information is collected, and its corresponding awakening confirmation information; that is, after obtaining the preliminary awakening information, a question-and-answer process is required with the user to confirm the user's need to wake up the digital human; it is not awakened by the user's unilateral audio or face image, which reduces the false awakening rate and reduces the energy consumption of the digital human.

[0166] Optionally, in the above-mentioned public place digital person anti-false awakening device, the judgment module 20 includes:

[0167] The first judgment unit is used to judge whether preset wake-up keyword information is collected based on the audio information; the wake-up keyword information is preliminary wake-up information.

[0168] The interactive response module is used to start the interactive response mode and output the wake-up inquiry information if the judgment result of the judgment unit is yes.

[0169] The first determination unit is further configured to determine whether wake-up confirmation information corresponding to the wake-up inquiry information is collected based on the audio information.

[0170] The working process and principle of each module unit are detailed in the above embodiments. Figure 3 , which will not be described one by one here, and are all within the protection scope of this application.

[0171] Optionally, in the above-mentioned public place digital personal anti-false awakening device, the interactive response module is used to start the interactive response mode and output the awakening inquiry information, specifically for:

[0172] Start interactive answer mode.

[0173] After the preset duration of the interactive answering mode is started, a wake-up inquiry message is output.

[0174] The interactive response module is used to start the interactive response mode and output the specific process of the wake-up inquiry information. For details, please refer to the above embodiment. Figure 4 , which will not be described one by one here, and are all within the protection scope of this application.

[0175] Optionally, in the above-mentioned public place digital personal anti-false awakening device, the interactive response module is used to output the awakening inquiry information after the preset time of starting the interactive response mode, specifically for:

[0176] If the user's consultation information is collected within the preset time length of starting the interactive answering mode, a wake-up inquiry message based on the consultation information is output.

[0177] The interactive response module is used to output the specific process of the wake-up inquiry information after the preset time of the interactive response mode is started. For details, please refer to the above embodiment, such as the embodiment Figure 5 , which will not be described one by one here, and are all within the protection scope of this application.

[0178] Optionally, in the above-mentioned public place digital personal anti-false awakening device, when the interactive response module outputs the awakening inquiry information after starting the interactive response mode for a preset time, it is specifically used to:

[0179] If the user's inquiry information is not collected within the preset time length of starting the interactive answering mode, the preset wake-up inquiry information is output.

[0180] The interactive response module is used to output the specific process of the wake-up inquiry information after the preset time of the interactive response mode is started. For details, please refer to the above embodiment, such as the embodiment Figure 6 , which will not be described one by one here, and are all within the protection scope of this application.

[0181] Optionally, in the above-mentioned digital human anti-mis-awakening device in public places, the awakening module 30 is used to control the awakening of the digital human, specifically for:

[0182] Activate the network communication mode; start picking up sounds and sending them to the server for digital human services.

[0183] The awakening module 30 is used to control the specific process of awakening the digital human. For details, see the above embodiments. Figure 8 , which will not be described one by one here, and are all within the protection scope of this application.

[0184] Optionally, in the above-mentioned public place digital person anti-false awakening device, the judgment module 20 further includes:

[0185] The second judgment unit is used to judge whether the facial image information is the frontal facial image information of the user based on the facial image information collected when the living facial information is collected in real time.

[0186] If so, it is determined that live face information is detected; if not, it is determined that live face information is not detected.

[0187] For details on the specific process and principle of the second judgment unit, please refer to the above embodiment. Fig. 9 , which will not be described one by one here, and are all within the protection scope of this application.

[0188] Another embodiment of the present application provides an electronic device.

[0189] See also Fig.11 , the electronic device comprising:

[0190] One or more processors 110 .

[0191] The storage device 120 stores one or more programs.

[0192] When one or more programs are executed by one or more processors 110, the one or more processors 110 implement the method for preventing false awakening of a digital person in a public place as provided in the above embodiment.

[0193] The working process and principle of the method for preventing false awakening of digital people in public places are detailed in the above embodiments and will not be described in detail here, and all are within the protection scope of this application.

[0194] Another embodiment of the present application provides a storage medium.

[0195] The storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for preventing false awakening of a digital person in a public place provided in the above embodiment is implemented.

[0196] The working process and principle of the method for preventing false awakening of digital people in public places are detailed in the above embodiments and will not be described in detail here, and all are within the protection scope of this application.

[0197] The features recorded in the various embodiments in this specification can be replaced or combined with each other, and the same and similar parts between the various embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0198] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0199] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for preventing false awakening of a digital person in a public place, characterized in that: include: Collect audio information and live face information in real time; Based on the audio information, determining whether preliminary awakening information and deep awakening information are collected in sequence, and determining whether the living face information is detected; The determining whether preliminary wake-up information and deep wake-up information are collected in sequence based on the audio information includes: determining whether preset wake-up keyword information is collected based on the audio information; the wake-up keyword information is the preliminary wake-up information; if so, starting the interactive response mode; if the user's consultation information is collected within the preset time length of starting the interactive response mode, outputting the wake-up inquiry information based on the consultation information; determining whether the wake-up confirmation information corresponding to the wake-up inquiry information is collected based on the audio information; If the preliminary awakening information and the deep awakening information are collected in sequence and the living face information is detected, the digital human is controlled to wake up.

2. The method for preventing false awakening of a digital person in a public place according to claim 1, characterized in that: After the preset time of starting the interactive answering mode, outputting a wake-up inquiry message includes: If the user's consultation information is not collected within the preset time length of starting the interactive response mode, the preset wake-up inquiry information is output.

3. The method for preventing false awakening of a digital person in a public place according to claim 1 or 2, characterized in that: Controlling the digital human to wake up, including: Activate the network communication mode; start picking up sounds and sending them to the server for digital human services.

4. The method for preventing false awakening of a digital person in a public place according to claim 1 or 2, characterized in that: Determining whether the living face information is detected includes: Based on the facial image information collected when collecting live face information in real time, determining whether the facial image information is the frontal facial image information of the user; If so, it is determined that the living face information is detected; if not, it is determined that the living face information is not detected.

5. A digital person anti-false awakening device in public places, characterized in that: include: The acquisition module is used to collect audio information and live face information in real time; A judgment module, used to judge whether preliminary awakening information and deep awakening information are collected in sequence based on the audio information, and whether the living face information is detected; The determining whether preliminary wake-up information and deep wake-up information are collected in sequence based on the audio information includes: determining whether preset wake-up keyword information is collected based on the audio information; the wake-up keyword information is the preliminary wake-up information; if so, starting the interactive response mode; if the user's consultation information is collected within the preset time length of starting the interactive response mode, outputting the wake-up inquiry information based on the consultation information; determining whether the wake-up confirmation information corresponding to the wake-up inquiry information is collected based on the audio information; The wake-up module is used to control the wake-up of the digital human if the preliminary wake-up information and the deep wake-up information are collected in sequence and the living face information is detected.

6. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for preventing false awakening of a digital person in a public place as described in any one of claims 1 to 4.

7. A storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the method for preventing a digital person in a public place from being woken up by mistake as claimed in any one of claims 1 to 4 is implemented.

Images