Control method of subject article and related system thereof

Abstract

The invention relates to a control method of a subject article and a related system. The control method comprises the following steps: identifying a behavior of a target person; analyzing the intention of the target person according to the behavior of the target person; and according to the intention of the target person, encoding a reaction mechanism for expressing emotion, wherein the reaction mechanism is related to the appearance role of the subject article. Therefore, the intention of the target person can be analyzed according to the behavior of the target person, and then a reaction mechanism for expressing the emotion is given, so that the target person can be better accompanied, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of smart device technology, and in particular to a control method for a subject item and a related system thereof. Background Art

[0002] Current theme objects, such as desktop robots and companion robots, usually have voice output capabilities or some action operations, such as storytelling or body movements. However, current theme objects can only accept user instructions and directly perform corresponding operations according to the instructions, such as accepting user instructions to tell the story of "mermaid" or user instructions to "dance". These instructions clearly know the user's intentions. However, they cannot recognize the user's intentions based on the user's potential actions or voices, such as understanding the user's emotions, and thus cannot achieve a good response effect. Summary of the invention

[0003] Based on this, it is necessary to provide a control method for a theme item and a related system for the above technical problems. The user's intention can be analyzed according to the user's behavior, and then a response mechanism for expressing emotions can be given, so that the user can get better care and improve the user experience.

[0004] In a first aspect, the present application provides a method for controlling a subject item, the method comprising:

[0005] Identify the target person’s behavior;

[0006] Analyzing the intention of the target person according to the behavior of the target person;

[0007] A response mechanism expressing emotions is encoded according to the intention of the target person.

[0008] In one of the embodiments, the behavior of the target person includes the voice of the target person;

[0009] The step of identifying the behavior of the target person also includes:

[0010] The initial sound of the surrounding environment is identified, and the initial sound is filtered to identify the voice of the target person.

[0011] In one embodiment, the step of filtering the initial sound further includes:

[0012] Decomposing the initial sound to obtain multiple subdivision signals;

[0013] Perform wavelet threshold denoising algorithm on each subdivided signal one by one to obtain a denoised sound signal;

[0014] The denoised sound signals are combined to form the target person's voice.

[0015] In one embodiment, the step of analyzing the intention of the target person according to the behavior of the target person further includes:

[0016] The emotional intention of the target person is analyzed based on the voice of the target person through a neural network algorithm.

[0017] In one of the embodiments, the target person's behavior includes the target person's actions;

[0018] The step of identifying the behavior of the target person also includes:

[0019] Obtaining the action of the target person;

[0020] The step of analyzing the intention of the target person according to the behavior of the target person also includes:

[0021] Matching a target action corresponding to a pre-stored action according to the action;

[0022] The corresponding intention is matched according to the target action.

[0023] In one embodiment, the step of encoding a reaction mechanism for expressing emotions according to the intention of the target person further includes:

[0024] Analyzing the target person's emotions according to the target person's intentions;

[0025] According to the target person's emotion, a corresponding emotional action or a corresponding emotional sound is matched.

[0026] The emotional actions and the emotional sounds conform to the character characteristics of the appearance character, or the emotional actions and the emotional sounds are anthropomorphic actions and sounds.

[0027] In one embodiment, the control method further includes:

[0028] The theme object is connected with surrounding real animals, and the real animals are of the same kind as the appearance character;

[0029] The intention of the target person is transmitted to surrounding real animals, so that the real animals emit corresponding reaction mechanisms to express emotions.

[0030] In a second aspect, the present application also provides a control system for a subject article, the control system comprising:

[0031] Recognition module, used to identify the behavior of the target person;

[0032] A parsing module, used for parsing the intention of the target person according to the behavior of the target person;

[0033] The reaction module is used to encode a reaction mechanism according to the intention of the target person.

[0034] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor is configured to implement the steps of the method described above when executing the computer-readable instructions.

[0035] In a fourth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, the computer program being used to implement the steps of the method described above when executed by a computer.

[0036] The above introduces a control method and related system of a theme item, and the control method includes: identifying the behavior of the target person; analyzing the intention of the target person according to the behavior of the target person; and encoding a reaction mechanism for expressing emotions according to the intention of the target person. Therefore, the present application can analyze the intention of the target person according to the behavior of the target person, and then provide a reaction mechanism for expressing emotions, so that the target person can be better accompanied and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of a control method of a subject item provided in an embodiment of the present application;

[0038] Figure 2 It is a flow chart of another method for controlling a subject item provided in an embodiment of the present application;

[0039] Figure 3 It is a flow chart of another method for controlling a subject item provided in an embodiment of the present application;

[0040] Figure 4 It is a flow chart of another method for controlling a subject item provided in an embodiment of the present application;

[0041] Figure 5 It is a flow chart of another method for controlling a subject item provided in an embodiment of the present application;

[0042] Figure 6 It is a structural schematic diagram of a control system of a subject item provided in an embodiment of the present application;

[0043] Figure 7 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] See also Figure 1 , Figure 1 1 is a flow chart of a method for controlling a subject item provided in an embodiment of the present application. Figure 1 As shown, the control method includes the following steps:

[0046] Step S1: Identify the behavior of the target person.

[0047] The theme items may be intelligent devices such as desktop robots, companion robots, etc. The theme items include characters of different appearances, such as cats, dogs, birds, etc.

[0048] Furthermore, the theme item also includes a base, and the appearance characters include multiple ones, such as the cat, dog and bird mentioned above. Multiple appearance characters can be selectively set on the base. In other words, these appearance characters can all match a base, and the base can serve as a controller of the appearance character to control the appearance character to perform various operations, such as voice interaction with the target character, action interaction with the target character, etc.

[0049] The behavior of the target person can be the voice or action of the target person. Specifically, the theme object can be equipped with a microphone and a camera on the appearance character or the base, and the voice of the target person can be recognized by the microphone, or the action of the target person can be obtained by the camera.

[0050] Step S2: Analyze the intention of the target person according to the behavior of the target person.

[0051] The target person's behavior is often used to express an intention, such as expressing a certain emotion: tired, angry, sad, excited, happy, etc. Each emotion will be expressed in different words or actions. For example, if you are tired, you will speak slower, or express tiredness in your words; or when you are sad, your face will usually frown, your eyes will lose their brightness, become dull and lifeless, and the corners of your mouth will droop slightly, forming a sad arc.

[0052] The subject object can obtain the above-mentioned voice behavior and action behavior through a microphone or camera. Then, the target person's intention is analyzed based on the acquired voice behavior or action behavior to obtain the target person's emotional characteristics, etc., so that a suitable response mechanism can be given later.

[0053] Step S3: Encode a reaction mechanism for expressing emotions according to the intention of the target person, wherein the reaction mechanism is related to the appearance of the subject object, or the reaction mechanism is personified.

[0054] After the target person's intention is parsed in step S2, step S3 encodes a corresponding emotional response according to the intention to respond to the target person, so that the target person's intention is fed back. For example, when it is parsed that the target person is currently expressing the intention of being tired, the target person is actively comforted or hugged to relieve the target person's tiredness. Or when it is parsed that the target person is currently expressing the intention of scaring the target person, a frightened expression is actively given to respond to the target person.

[0055] Among them, the reaction mechanism can be related to the appearance of the theme object, which means that the reaction mechanism given by the theme object is matched with the appearance. For example, when comforting the target person through voice, if the theme object is a cat appearance, a very gentle cat cry can be made. If the theme object is a dog appearance, a gentle dog cry can be made. Similarly, if the reaction mechanism is to give an action, it is also in line with the character characteristics of the appearance. For example, if the appearance is a cat, the action of showing fright can be wide eyes, open mouth and shortness of breath. If the appearance is a dog, the action of showing fright can be erecting ears, stiff body and other actions.

[0056] The reaction mechanism can also be personified, which means that the reaction mechanism given by the subject object is the same as that of a person. For example, when comforting the target person through voice, you can directly output human language and ask the target person: "Why are you unhappy? Are you too tired from work?", etc., or directly comfort the target person: "Let me hug you; it's okay, everything will be fine", etc. Similarly, if the reaction mechanism given is an action reaction mechanism, you can also stretch out your hands like a person, or make various different actions like a person, etc.

[0057] A specific implementation scheme may be: the base may identify the appearance character set on the base through near field communication technology. Near field communication technology may include NFC (Near Field Communication) technology, Bluetooth technology, radio frequency identification technology, infrared communication technology, camera, and wireless local area network technology. After the base analyzes the intention of the target person, the base controls the appearance character to make an appropriate response according to the character characteristics of the appearance character.

[0058] Therefore, the subject item of this embodiment identifies the behavior of the target person, then analyzes the target person's intention based on the behavior of the target person, and finally encodes a reaction mechanism for expressing emotions based on the intention of the target person. Therefore, the present application can analyze the target person's intention based on the behavior of the target person, and then provide a reaction mechanism for expressing emotions, so that the target person can be better accompanied and the user experience can be improved.

[0059] The “behavior of identifying the target person” in the above step S1 may specifically include first identifying the initial sound of the surrounding environment, and then filtering the initial sound to identify the voice of the target person.

[0060] See also Figure 2 , wherein the step of filtering the initial sound further comprises the following steps:

[0061] Step S21: Decompose the initial sound to obtain a plurality of subdivided signals.

[0062] For example, the initial sound can be decomposed by CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) to obtain multiple IMF signals. Specifically, the steps are as follows:

[0063] Step 1: Add Gaussian white noise to the initial sound signal to be decomposed to obtain a new signal;

[0064] Step 2: Perform ensemble empirical mode decomposition (EEMD) on the new signal to obtain a series of eigenstate functions, i.e., IMF signals;

[0065] Step 3: Perform complementary ensemble empirical mode decomposition (CEEMD) on each IMF signal to obtain the final IMF signal, and repeat steps 2 and 3 until all IMFs are decomposed.

[0066] In the process of implementing the algorithm, it is necessary to determine the number of times M to add noise, and obtain M initial quantities sM(t)=s(t)+βk-1Ek(wM). The EMD algorithm is used for the M initial quantities to obtain the first-order residual component, and the average value is obtained to obtain the first-order average residual component r1r_1r1. The first-order average IME component is obtained by the formula c1(1)=s(t)-r1c_1(1)=s(1)-r_1c1(t)=s(t)-r1, and then s(t)=r1s(t)=r1s(t)=r1. Repeat the above steps, and so on, to obtain the second-order, third-order IME components, etc.

[0067] Step S22: performing a wavelet threshold denoising algorithm on each subdivided signal one by one to obtain a denoised sound signal.

[0068] Step S23: combining the denoised sound signals to form the target person's voice.

[0069] By decomposing the initial sound signal into multiple subdivision signals and then filtering each subdivision signal, that is, granulating the initial sound signal and then filtering the granulated subdivision signal, the noise of the initial sound signal can be effectively filtered out.

[0070] Among them, the "analyzing the intention of the target person according to the behavior of the target person" in the previous step S2 can specifically be analyzing the emotional intention of the target person according to the voice of the target person through a neural network algorithm.

[0071] Specifically, firstly, the sound information obtained in step S1 is analyzed to obtain the text after speech recognition, and then the emotion of the target person is judged according to the content of the text. In speech emotion recognition, for example, the emotional state of the target person can be analyzed based on the characteristics of the sound (such as fundamental frequency, energy, tone, etc.) and the characteristics of the speech (such as speaking speed, intonation, phonemes, etc.).

[0072] When the target person's action is acquired, the above step S2 of "analyzing the target person's intention according to the target person's action" also includes Figure 3 The following steps are shown:

[0073] Step S31: Match the target action corresponding to the pre-stored action according to the action.

[0074] That is, before step S31, various actions of the target person expressing different intentions need to be stored. After the actions of the target person are acquired, the stored actions can be traversed in the memory to match the corresponding target actions.

[0075] Step S32: Match the corresponding intention according to the target action.

[0076] Furthermore, when storing various actions of the target person expressing different intentions, it is necessary to further store the mapping relationship between the actions and the intentions.

[0077] After matching the target action, the corresponding intent can be obtained according to the mapping relationship.

[0078] Since each person's actions to express different intentions are different, when there are multiple users, the users who fail can be distinguished and stored separately. When identifying the target person, it is first necessary to identify the user's characteristics and identify the specific user as the target person.

[0079] See also Figure 4 The step of "encoding a reaction mechanism for expressing emotions according to the intention of the target person" in the above step S3 further includes the following steps:

[0080] Step S41: Analyze the target person's emotions according to the target person's intentions.

[0081] Step S42: matching corresponding emotional actions or emitting corresponding emotional sounds according to the target character's emotions, wherein the emotional actions and emotional sounds conform to the character characteristics of the appearance character, or the emotional actions and emotional sounds are anthropomorphic actions and sounds.

[0082] It is understandable that different emotions require different response mechanisms. For example, when the target person is depressed or tired, he or she may need gentle comfort and companionship. At this time, if the matched response mechanism is emotional sound, it should be soft, etc. If the matched response mechanism is emotional action, it should be gentle, etc.

[0083] In addition, emotional actions and emotional sounds can conform to the character characteristics of the appearance character. For example, if the appearance character is a cat, the emotional sound emitted is the sound of a cat, and the emotional actions are also actions exclusive to cats; for example, if the appearance character is a dog, the emotional sound emitted is the sound of a dog, and the emotional actions are also actions exclusive to dogs.

[0084] Emotional actions and emotional sounds can also be anthropomorphic actions and sounds. For example, when comforting the target person through emotional sounds, you can directly output human language and ask the target person: "Why are you unhappy? Are you too tired from work?", etc., or directly comfort the target person: "Let me hug you; it's okay, everything will be fine", etc. Similarly, if a response mechanism is given through emotional actions, you can also stretch out your hands like a human, or make various different actions like a human, etc.

[0085] The previous article introduced that the theme objects identify the emotions of the target person and then match the corresponding reaction mechanism so that the target person can get the corresponding response, thereby improving the user experience.

[0086] For further information, see Figure 5 , the control method further comprises the following steps:

[0087] Step S51: The theme object is connected with surrounding real animals, and the real animals are of the same kind as the appearance character.

[0088] That is, after the theme object is parsed into the target person's intention, it builds a connection with the real animals of the same kind around it. For example, if the theme object's appearance is a cat, then the theme object can build a connection with the real cats around it to achieve the purpose of communication. Similarly, if the theme object's appearance is a dog, then it can build a connection with the real dogs around it to achieve the purpose of communication.

[0089] Specifically, the theme object can first collect various sounds of the appearance character through a microphone, such as meows, purrs, barking dogs, etc. These sounds are then analyzed using a machine learning algorithm to identify different sound patterns and features. Further, based on the analyzed sound patterns and features, animal-like sounds are synthesized to try to communicate with real animals. In addition, the behavior and expressions of animals can be captured through cameras to understand the emotions and needs of animals. For example, when a cat shows hunger or thirst, these signals can be identified and corresponding actions can be taken, such as providing food or water. It is also possible to attract the attention of animals and interact with them by moving, rotating, or emitting specific lights or sounds, and then understand the habits and hobbies of animals to achieve the purpose of communication.

[0090] When the theme object constantly interacts with the real animals around it, it can master the technology of connecting with the real animals around it. After identifying the intention of the target person, it can establish connection with the same type of animals around it to convey the intention of the target person.

[0091] Step S52: conveying the intention of the target person to surrounding real animals, so that the real animals emit corresponding reaction mechanisms to express emotions.

[0092] Through the expression between the same kind, the intention of the target person is conveyed to the real animals around, so that the real animals around can know the emotions of the target person and thus make corresponding response mechanisms.

[0093] For example, if a real cat knows that a target person is in a bad mood, it can run to the target person's side, accompany the target person, or gently rub the target person with its body to comfort the target person, or make a soft cat cry to show comfort, etc.

[0094] It should be understood that after the theme object conveys the intention of the target person to the real animal, the theme object can also react together with the real animal. Specifically, the theme object can react in the same way as the real animal, for example, when the target person is in a bad mood, the theme object can also comfort the target person with actions and sounds. The theme object can also cooperate with the real animal, with the real animal comforting the target person with actions and the theme object comforting the target person with sounds. Alternatively, the theme object can only react with the real animal.

[0095] Therefore, when the subject item conveys the intention of the target person, it can only convey the intention, or it can convey the specific reaction mechanism after conveying the intention.

[0096] Therefore, this embodiment can not only use the theme object to react according to the intention of the target person, but also convey it to real animals of the same kind, so that the real animals can react to obtain a more realistic effect and improve the user experience.

[0097] This application also provides a voice control system for a subject article, which is applied to the voice recognition method described above. Figure 6 , Figure 6 is a schematic diagram of the structure of a voice control system of a subject item provided in an embodiment of the present application, such as Figure 6 As shown, the control system 60 includes:

[0098] The recognition module 610 is used to recognize the behavior of the target person. The theme object can be a smart device such as a desktop robot or a companion robot. The theme object includes different appearance characters, such as a cat, a dog, a bird, etc.

[0099] Furthermore, the theme item also includes a base, and the appearance characters include multiple ones, such as the cat, dog and bird mentioned above. Multiple appearance characters can be selectively set on the base. In other words, these appearance characters can all match a base, and the base can serve as a controller of the appearance character to control the appearance character to perform various operations, such as voice interaction with the target character, action interaction with the target character, etc.

[0100] The behavior of the target person can be the voice or action of the target person. Specifically, the theme object can be equipped with a microphone and a camera on the appearance character or the base, and the voice of the target person can be recognized by the microphone, or the action of the target person can be obtained by the camera.

[0101] When the target person's voice is recognized, the initial voice may be filtered first, and the specific filtering process is as described above, which will not be repeated here. Similarly, when the target person's action is obtained, the specific recognition scheme is as described above, which will not be repeated here.

[0102] The analysis module 620 is used to analyze the intention of the target person according to the behavior of the target person.

[0103] The target person's behavior is often used to express an intention, such as expressing a certain emotion: tired, angry, sad, excited, happy, etc. Each emotion has different language or action expressions. For example, when tired, the person will speak slower, or the words will express tiredness; or when sad, the face will usually frown, the eyes will lose their brightness, become dull and lifeless, and the corners of the mouth will droop slightly, forming a sad arc.

[0104] The subject object can obtain the above-mentioned voice behavior and action behavior through a microphone or camera. Then, the target person's intention is analyzed based on the acquired voice behavior or action behavior to obtain the target person's emotional characteristics, etc., so that a suitable response mechanism can be given later.

[0105] The reaction module 630 is used to encode a reaction mechanism according to the intention of the target person, wherein the reaction mechanism is related to the appearance character of the subject object, or the reaction mechanism is anthropomorphic.

[0106] According to the intention, a corresponding emotional response is encoded to respond to the target person, so that the target person's intention is fed back. For example, when it is analyzed that the target person is currently expressing the intention of being tired, the target person is actively comforted or hugged to relieve the target person's tiredness. Or when it is analyzed that the target person is currently expressing the intention of scaring the target person, a frightened expression is actively given to respond to the target person.

[0107] The reaction mechanism is related to the appearance of the theme object, which means that the reaction mechanism given by the theme object matches the appearance of the character. For example, when comforting the target person through voice, if the theme object is a cat-shaped character, a very gentle cat cry can be made. If the theme object is a dog-shaped character, a gentle dog cry can be made. Similarly, if the reaction mechanism is given by action, it also conforms to the character characteristics of the appearance. For example, if the appearance of the cat shows a frightened action, the action can be wide-eyed, open-mouthed, and short of breath. If the appearance of the dog shows a frightened action, the action can be erecting ears, stiff body, etc.

[0108] The reaction mechanism can also be personified, which means that the reaction mechanism given by the subject object is the same as that of a person. For example, when comforting the target person through voice, you can directly output human language and ask the target person: "Why are you unhappy? Are you too tired from work?", etc., or directly comfort the target person: "Let me hug you; it's okay, everything will be fine", etc. Similarly, if the reaction mechanism given is an action reaction mechanism, you can also stretch out your hands like a person, or make various different actions like a person, etc.

[0109] A specific implementation scheme may be: the base may identify the appearance character set on the base through near field communication technology. Near field communication technology may include NFC (Near Field Communication) technology, Bluetooth technology, radio frequency identification technology, infrared communication technology, camera, and wireless local area network technology. After the base analyzes the intention of the target person, the base controls the appearance character to make an appropriate response according to the character characteristics of the appearance character.

[0110] Specifically, the target person's emotions can be analyzed according to the target person's intentions. Then, the corresponding emotional actions or emotional sounds are matched according to the target person's emotions. The emotional actions and emotional sounds conform to the character characteristics of the appearance character.

[0111] It is understandable that different emotions require different response mechanisms. For example, when the target person is depressed or tired, he or she may need gentle comfort and companionship. At this time, if the matched response mechanism is emotional sound, it should be soft, etc. If the matched response mechanism is emotional action, it should be gentle, etc.

[0112] In addition, the emotional actions and emotional sounds need to conform to the character characteristics of the appearance character. For example, if the appearance character is a cat, the emotional sounds emitted are the sounds of a cat, and the emotional actions are also actions that are exclusive to cats. For another example, if the appearance character is a dog, the emotional sounds emitted are the sounds of a dog, and the emotional actions are also actions that are exclusive to dogs.

[0113] Furthermore, the theme items can also establish connections with surrounding real animals, and the real animals are of the same type as the appearance characters.

[0114] That is, after the theme object is parsed into the target person's intention, it builds a connection with the real animals of the same kind around it. For example, if the theme object's appearance is a cat, then the theme object can build a connection with the real cats around it to achieve the purpose of communication. Similarly, if the theme object's appearance is a dog, then it can build a connection with the real dogs around it to achieve the purpose of communication.

[0115] Specifically, the theme object can first collect various sounds of the appearance character through a microphone, such as meows, purrs, barking dogs, etc. These sounds are then analyzed using a machine learning algorithm to identify different sound patterns and features. Further, based on the analyzed sound patterns and features, animal-like sounds are synthesized to try to communicate with real animals. In addition, the behavior and expressions of animals can be captured through cameras to understand the emotions and needs of animals. For example, when a cat shows hunger or thirst, these signals can be identified and corresponding actions can be taken, such as providing food or water. It is also possible to attract the attention of animals and interact with them by moving, rotating, or emitting specific lights or sounds, and then understand the habits and hobbies of animals to achieve the purpose of communication.

[0116] When the theme object constantly interacts with the real animals around it, it can master the technology of connecting with the real animals around it. After identifying the intention of the target person, it can establish connection with the same type of animals around it to convey the intention of the target person.

[0117] The intention of the target person is then transmitted to the surrounding real animals, causing the real animals to emit corresponding reaction mechanisms to express emotions.

[0118] Through the expression between the same kind, the intention of the target person is conveyed to the real animals around, so that the real animals around can know the emotions of the target person and thus make corresponding response mechanisms.

[0119] For example, if a real cat knows that a target person is in a bad mood, it can run to the target person's side, accompany the target person, or gently rub the target person with its body to comfort the target person, or make a soft cat cry to show comfort, etc.

[0120] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0121] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with components 61-63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0122] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0123] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various information management operating systems installed on the computer device 6, such as computer-readable instructions of the control method of the subject item, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0124] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run computer-readable instructions or process data stored in the memory 61, such as computer-readable instructions of the control method of the subject article.

[0125] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0126] The present application also provides another embodiment, namely, providing a computer program product, wherein the computer program product stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the control method of the subject article as described above.

[0127] This application introduces a control method and related system for a theme item, the control method includes: identifying the behavior of a target person; analyzing the intention of the target person based on the behavior of the target person; encoding a reaction mechanism for expressing emotions based on the intention of the target person, wherein the reaction mechanism is related to the appearance character of the theme item. Therefore, this application can analyze the intention of the target person based on the behavior of the target person, and then provide a reaction mechanism for expressing emotions, so that the target person can be better accompanied and the user experience can be improved.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0129] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0130] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for controlling a theme item, characterized in that: The control method comprises: Identify the target person’s behavior; Analyzing the intention of the target person according to the behavior of the target person; A response mechanism expressing emotions is encoded according to the intention of the target person.

2. The control method according to claim 1, characterized in that: The behavior of the target person includes the voice of the target person; The step of identifying the behavior of the target person also includes: The initial sound of the surrounding environment is identified, and the initial sound is filtered to identify the voice of the target person.

3. The control method according to claim 2, characterized in that: The step of filtering the initial sound further includes: Decomposing the initial sound to obtain multiple subdivision signals; Perform wavelet threshold denoising algorithm on each subdivided signal one by one to obtain a denoised sound signal; The denoised sound signals are combined to form the target person's voice.

4. The control method according to claim 2, characterized in that: The step of analyzing the intention of the target person according to the behavior of the target person also includes: The emotional intention of the target person is analyzed based on the voice of the target person through a neural network algorithm.

5. The control method according to claim 1, characterized in that: The target person's behavior includes the target person's actions; The step of identifying the behavior of the target person also includes: Obtaining the action of the target person; The step of analyzing the intention of the target person according to the behavior of the target person also includes: Matching a target action corresponding to a pre-stored action according to the action; The corresponding intention is matched according to the target action.

6. The control method according to any one of claims 1 to 5, characterized in that: The step of encoding a reaction mechanism for expressing emotions according to the intention of the target person also includes: Analyzing the target person's emotions according to the target person's intentions; According to the target person's emotion, a corresponding emotional action or a corresponding emotional sound is matched. The emotional actions and the emotional sounds conform to the character characteristics of the appearance character, or the emotional actions and the emotional sounds are anthropomorphic actions and sounds.

7. The control method according to any one of claims 1 to 5, characterized in that: The control method further comprises: The theme object is connected with surrounding real animals, and the real animals are of the same kind as the appearance character; The intention of the target person is transmitted to surrounding real animals, so that the real animals emit corresponding reaction mechanisms to express emotions.

8. A control system for a subject item, characterized in that: The control system comprises: Recognition module, used to identify the behavior of the target person; A parsing module, used for parsing the intention of the target person according to the behavior of the target person; The reaction module is used to encode a reaction mechanism according to the intention of the target person.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor is configured to implement the steps of the method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer program product, characterized in that The computer program product comprises a computer program for implementing the method according to any one of claims 1 to 7 when the computer program is executed by a computer.

Images