Emotion detection method and apparatus

Abstract

The application provides an emotion detection method and device, and the method comprises the following steps: obtaining current dynamic category information of a target object; establishing a current three-dimensional dynamic portrait model of the target object according to the current dynamic category information of the target object; obtaining a current dynamic category result of the target object according to the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; and prompting according to the current dynamic category result. The technical scheme of the application can obtain more accurate and less error results when detecting the unknown dynamic category of the target object, improve the detection efficiency, and improve the user experience.

Description

Technical Field

[0001] This invention belongs to the field of smart device technology, specifically relating to an emotion detection method and device. Background Technology

[0002] In modern life, people's pace of life is getting faster and faster, and their emotions are becoming more and more sensitive. At the same time, as the quality of life improves, people are paying more and more attention to changes in their emotions. For example, a baby's cry can leave new parents at a loss, not knowing what the baby is trying to express. In their panic, new parents can only try various methods to soothe the baby and calm the baby down.

[0003] Currently, methods that use cameras to capture users' facial features and sound recording devices to infer users' current emotions have problems such as inaccurate judgments and large errors. Summary of the Invention

[0004] In view of the problems of inaccurate judgment results and large errors in using cameras to capture users' facial features and using sound recording devices to collect users' voices, the present invention provides an emotion detection method and an emotion detection device, which solves the technical problem of inaccurate judgment results and large errors in identifying the emotions of target objects.

[0005] A first aspect of the present invention provides an emotion detection method, the method comprising:

[0006] Get the current dynamic category information of the target object;

[0007] Based on the current dynamic category information of the target object, a current three-dimensional dynamic portrait model of the target object is established;

[0008] Based on the current 3D dynamic portrait model and the pre-trained emotion detection model, the current dynamic category result of the target object is obtained;

[0009] Provide suggestions based on the current dynamic category results.

[0010] In some embodiments, the current dynamic category information of the target object is obtained through sensors and cameras, wherein the current dynamic category information includes limb dynamic information and physiological information.

[0011] In some embodiments, establishing a current three-dimensional dynamic portrait model of the target object based on the target object's current dynamic category information includes:

[0012] A set of limb dynamic vectors is generated based on the current limb dynamic information of the target object. The set of limb dynamic vectors is then mapped to a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current limb dynamic vector of the target object.

[0013] A physiological information vector set is generated based on the current physiological information of the target object, and the physiological information vector set is mapped to a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current physiological information vector of the target object.

[0014] Based on the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data of the target object, a current three-dimensional dynamic portrait model of the target object is established.

[0015] In some embodiments, the training process of the emotion detection model includes:

[0016] Obtain the historical dynamic category information of the target object and its corresponding dynamic category results;

[0017] Based on the historical dynamic category information of the target object, a historical three-dimensional dynamic profile model of the target object is established;

[0018] A backpropagation neural network is trained based on historical 3D dynamic portrait models and dynamic category results to obtain an emotion detection model.

[0019] In some embodiments, suggestions are provided based on the current dynamic category result, including:

[0020] Select the corresponding indicator light color based on the current dynamic category result;

[0021] The indicator light color is used to provide prompts to the user.

[0022] A second aspect of the present invention provides an emotion detection device, the device comprising:

[0023] The acquisition module is used to obtain the current dynamic category information of the target object;

[0024] The module is used to create a current three-dimensional dynamic portrait model of the target object based on its current dynamic category information.

[0025] The detection module is used to obtain the current dynamic category result of the target object based on the current 3D dynamic portrait model and the pre-trained emotion detection model;

[0026] The prompt module is used to provide prompts based on the current dynamic category results.

[0027] In some embodiments, the acquisition module is used to acquire the current dynamic category information of the target object through sensors and cameras, wherein the current dynamic category information includes limb dynamic information and physiological information.

[0028] In some embodiments, the establishment module includes:

[0029] The generation submodule is used to generate a limb dynamic vector set based on the current limb dynamic information of the target object, and map the limb dynamic vector set to a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current limb dynamic vector of the target object; and,

[0030] A physiological information vector set is generated based on the current physiological information of the target object, and the physiological information vector set is mapped to a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current physiological information vector of the target object.

[0031] A submodule is created to build a current three-dimensional dynamic portrait model of the target object based on the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data of the target object.

[0032] In some embodiments, the apparatus further includes:

[0033] The training module is used to obtain the historical dynamic category information of the target object and its corresponding dynamic category results; to establish a historical three-dimensional dynamic portrait model of the target object based on the historical dynamic category information; and to obtain the emotion detection model by training the BP neural network based on the historical three-dimensional dynamic portrait model and the dynamic category results.

[0034] In some embodiments, the prompting module includes:

[0035] The selection sub-unit is used to select the corresponding indicator light color based on the current dynamic category result;

[0036] The prompt subunit is used to prompt the user by displaying the color of the indicator light.

[0037] Compared with the prior art, the technical solution of this application has the following advantages or beneficial effects:

[0038] A three-dimensional dynamic portrait model of the target object was established. Based on the data in the three-dimensional dynamic portrait model, a backpropagation neural network was trained to obtain an emotion detection model. The trained model is closer to the real dynamics of the target object, thus making the detection of unknown dynamic categories of the target object more accurate and with smaller errors, improving detection efficiency and enhancing the user experience. Attached Figure Description

[0039] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0040] Figure 1 A flowchart illustrating an emotion detection method provided in an embodiment of this application;

[0041] Figure 2 A flowchart illustrating another emotion detection method provided in an embodiment of this application;

[0042] Figure 3 This is a schematic diagram of the structure of an emotion detection device provided in an embodiment of this application. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the embodiments of this invention will be described in detail below with reference to the accompanying drawings and examples. This will allow for a full understanding of how this invention uses technical means to solve technical problems and achieve corresponding technical effects, and enable its implementation accordingly. The embodiments of this invention and the various features within them can be combined with each other without conflict, and all resulting technical solutions are within the protection scope of this invention.

[0044] Example 1

[0045] This embodiment provides an emotion detection method. Figure 1 This is a flowchart illustrating an emotion detection method provided in an embodiment of this application, as shown below. Figure 1 As shown, the method in this embodiment may include the following steps:

[0046] S100: Obtain the current dynamic category information of the target object.

[0047] In some embodiments, the current dynamic category information of the target object is obtained through sensors and cameras, wherein the current dynamic category information includes limb dynamic information and physiological information.

[0048] It should be noted that the sensor can be a set of sensors. Through the sensors and the camera, the target object's limb dynamic information (such as sound, sound volume, limb movements, facial expressions, etc.) and physiological information (such as body temperature, heart rate, blood pressure, etc.) can be detected.

[0049] S200. Based on the current dynamic category information of the target object, establish the current three-dimensional dynamic portrait model of the target object.

[0050] In some embodiments, the process of establishing a current three-dimensional dynamic portrait model of the target object may include the following sub-steps:

[0051] S201. Generate a limb dynamic vector set based on the current limb dynamic information of the target object, map the limb dynamic vector set to a three-dimensional coordinate system, and obtain the three-dimensional coordinate data of the current limb dynamic vector of the target object.

[0052] Specifically, when generating the limb dynamic vector set, the current limb dynamic information of the target object is sampled to generate the current limb dynamic vector set of the target object.

[0053] S202. Generate a physiological information vector set based on the current physiological information of the target object, and map the physiological information vector set onto a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current physiological information vector of the target object.

[0054] Specifically, when generating the physiological information vector set, the current physiological information of the target object is sampled to generate the current physiological information vector set of the target object.

[0055] S203. Based on the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data, establish the current three-dimensional dynamic portrait model of the target object.

[0056] S300. Based on the current three-dimensional dynamic portrait model and the pre-trained emotion detection model, obtain the current dynamic category result of the target object.

[0057] In some embodiments, before obtaining the current dynamic category result of the target object, the method further includes: training a BP neural network model based on the mapping relationship between the dynamic profile model and the dynamic category result to obtain an emotion detection model. The training process of the emotion detection model may include the following steps:

[0058] S301. Obtain the historical dynamic category information of the target object and its corresponding dynamic category results;

[0059] S302. Based on the historical dynamic category information of the target object, establish a historical three-dimensional dynamic portrait model of the target object;

[0060] S303. The BP neural network is trained based on the historical three-dimensional dynamic portrait model and dynamic category results to obtain the emotion detection model.

[0061] The emotion detection model stores the mapping relationship between the dynamic profile model of the target object and the dynamic category results.

[0062] Furthermore, based on the current three-dimensional dynamic portrait model of the target object, and according to the mapping relationship between the dynamic portrait model and the dynamic category result of the target object, the current dynamic category result of the target object is determined.

[0063] Furthermore, after determining the dynamic category result corresponding to the current 3D dynamic portrait model of the target object based on the pre-trained emotion detection model, the emotion detection model can be trained using the mapping relationship between the dynamic portrait model and the dynamic category result to obtain an updated emotion detection model.

[0064] S400: Provide a prompt based on the current dynamic category result.

[0065] In some embodiments, suggestions are provided based on the current dynamic category result, including:

[0066] Select the corresponding indicator light color based on the current dynamic category result;

[0067] The indicator light color is used to provide prompts to the user.

[0068] This application discloses an emotion detection method, comprising: acquiring the current dynamic category information of a target object; establishing a current three-dimensional dynamic portrait model of the target object based on the current dynamic category information; obtaining the current dynamic category result of the target object based on the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; and providing prompts based on the current dynamic category result. Using the emotion detection method of this invention, the trained model more closely approximates the real dynamics of the target object, thereby making the detection of unknown dynamic categories of the target object more accurate and with smaller errors, thus improving detection efficiency.

[0069] Example 2

[0070] The present invention provides a more detailed description of an emotion detection method. Figure 2 A flowchart illustrating another emotion detection method provided in this application embodiment is shown below. Figure 2 As shown, the method in this embodiment may include the following steps:

[0071] The first step is to obtain the current dynamic category information of the target object through sensors and cameras.

[0072] In some embodiments, the current dynamic category information of the target object is acquired through sensors and cameras, wherein the current dynamic category information includes limb dynamic information and physiological information.

[0073] It should be noted that the sensor can be a set of sensors. Through the sensors and the camera, the target object's limb dynamic information (such as sound, sound volume, limb movements, facial expressions, etc.) and physiological information (such as body temperature, heart rate, blood pressure, etc.) can be detected.

[0074] The second step is to establish a current three-dimensional dynamic portrait model of the target object.

[0075] In some embodiments, the process of establishing a current three-dimensional dynamic portrait model of the target object may include the following sub-steps:

[0076] 1. Generate a set of limb dynamic vectors based on the current limb dynamic information of the target object, and map the set of limb dynamic vectors to a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current limb dynamic vectors of the target object.

[0077] Specifically, when generating the limb dynamic vector set, the current limb dynamic information of the target object is sampled to generate the current limb dynamic vector set of the target object.

[0078] Specifically, the sampled limb dynamic vector set M[a1, a2, ... a n ], a n This represents the nth limb dynamic vector of the acquired target object's limb dynamics. The set of these limb dynamic vectors is M[a1, a2, ..., a...]. n Mapped to a three-dimensional coordinate system, forming three-dimensional coordinate data of limb dynamic vectors (X). M Y M Z M ).

[0079] 2. Generate a physiological information vector set based on the current physiological information of the target object, and map the physiological information vector set onto a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current physiological information vector of the target object.

[0080] Specifically, when generating the physiological information vector set, the current physiological information of the target object is sampled to generate the current physiological information vector set of the target object.

[0081] Specifically, the sampled physiological information vector set K[b1, b2, ... b n ], b n This represents the nth physiological information vector of the collected target object's physiological information. The set of these physiological information vectors is K[b1, b2, ..., b...]. n Mapped into a three-dimensional coordinate system, this forms physiological information vector three-dimensional coordinate data (X). K Y K Z K ).

[0082] 3. Based on the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data, establish the current three-dimensional dynamic portrait model of the target object.

[0083] Specifically, based on the target object's current limb dynamic vector three-dimensional coordinate data (X... M Y M Z M ) and the target object's current physiological information vector three-dimensional coordinate data (X K Y K Z K ), and establish the current three-dimensional dynamic portrait model L of the target object.

[0084] The third step is to obtain the current dynamic category result of the target object based on the current three-dimensional dynamic portrait model and the pre-trained emotion detection model.

[0085] In some embodiments, before obtaining the current dynamic category result of the target object, this step further includes: training a BP neural network model based on the mapping relationship between the dynamic profile model and the dynamic category result to obtain an emotion detection model. The training process of the emotion detection model may include the following steps:

[0086] 1. Obtain the historical dynamic category information of the target object and its corresponding dynamic category results;

[0087] 2. Based on the historical dynamic category information of the target object, establish a historical three-dimensional dynamic profile model of the target object;

[0088] 3. The BP neural network is trained based on the historical three-dimensional dynamic portrait model and dynamic category results to obtain the emotion detection model.

[0089] The emotion detection model stores the mapping relationship between the dynamic profile model of the target object and the dynamic category results.

[0090] Furthermore, based on the current three-dimensional dynamic portrait model of the target object, and according to the mapping relationship between the dynamic portrait model and the dynamic category result of the target object, the current dynamic category result of the target object is determined.

[0091] Furthermore, after determining the dynamic category result corresponding to the current 3D dynamic portrait model of the target object based on the pre-trained emotion detection model, the emotion detection model can be trained using the mapping relationship between the dynamic portrait model and the dynamic category result to obtain an updated emotion detection model.

[0092] Furthermore, if the current dynamic category result of the target object cannot be determined based on the mapping relationship between the dynamic profile model and the dynamic category result, the emotion detection model will repeatedly calculate the current dynamic category information of the target object until the current dynamic category result of the target object is determined.

[0093] The fourth step is to provide prompts based on the current dynamic category results.

[0094] In some embodiments, suggestions are provided based on the current dynamic category result, including:

[0095] Select the corresponding indicator light color based on the current dynamic category result;

[0096] The indicator light color is used to provide prompts to the user.

[0097] For example, different colored indicator lights can be used to express the current dynamic category information of the target object. For instance, green indicates a normal state, yellow indicates a hungry state, purple indicates a frightened state, and red indicates an abnormal body temperature state.

[0098] Specifically, if the target object's current dynamic category result is in a normal state, it means the target object is in a normal state, and the indicator light is on and displays green. If the target object's current dynamic category result is in an abnormal state, the indicator light is on and displays another color, prompting the user to take targeted actions based on the different dynamic category results. For example, when the target object is an infant, if the current dynamic category result is in a normal state, the indicator light is on and displays green, and no further action is needed; if the current dynamic category result is in a hungry state, the indicator light is on and displays yellow, and the parents need to prepare to feed the infant; if the current dynamic category result is in a state of abnormal body temperature, the indicator light is on and displays red, and the parents need to prepare to go to the hospital; if the current dynamic category result is in a state of fright, the indicator light is on and displays purple, and the parents need to comfort the infant by holding or kissing them.

[0099] It should be noted that normal states include: happy, playful, sound asleep, quiet, etc., while abnormal states include: angry, frightened, hungry, abnormal body temperature, abnormal heart rate, crying, etc.

[0100] In some embodiments, if the current dynamic category result of the target object is in an abnormal state, different colors can be displayed in conjunction with the number of flashing indicator lights to indicate the target object's current mood.

[0101] In some embodiments, if the current dynamic category result of the target object is in an abnormal state, playing some soothing music can also be used to alleviate the target object's emotions.

[0102] In some embodiments, if the current dynamic category result of the target object is in an abnormal state, a reminder message can be sent to the smart terminal to display the current status information of the target object, so as to remotely grasp the current dynamic category information of the target object.

[0103] Furthermore, when the current dynamic category result displayed on the smart terminal is in an abnormal state, the target's emotions can be alleviated by conducting a voice / video call with the target.

[0104] This application discloses another emotion detection method, including: acquiring the current dynamic category information of a target object; establishing a current three-dimensional dynamic portrait model of the target object; obtaining the current dynamic category result of the target object based on the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; and providing prompts based on the current dynamic category result. Using the emotion detection method of this invention, the trained model more closely approximates the real dynamics of the target object, thereby making the detection of unknown dynamic categories of the target object more accurate and with smaller errors, thus improving detection efficiency.

[0105] Example 3

[0106] This invention provides an emotion detection device. Figure 3 This is a schematic diagram of the structure of an emotion detection device provided in an embodiment of this application, as shown below. Figure 3 As shown, the emotion detection device in this embodiment may include:

[0107] The acquisition module 301 is used to acquire the current dynamic category information of the target object.

[0108] In some embodiments, the current dynamic category information of the target object is obtained through sensors and cameras, wherein the current dynamic category information includes limb dynamic information and physiological information.

[0109] It should be noted that the sensor can be a set of sensors. Through the sensors and the camera, the target object's limb dynamic information (such as sound, sound volume, limb movements, facial expressions, etc.) and physiological information (such as body temperature, heart rate, blood pressure, etc.) can be detected.

[0110] Module 302 is used to establish a current three-dimensional dynamic portrait model of the target object based on the target object's current dynamic category information.

[0111] In some embodiments, the process of establishing a current three-dimensional dynamic portrait model of the target object may include the following sub-steps:

[0112] 1. Generate a set of limb dynamic vectors based on the current limb dynamic information of the target object, and map the set of limb dynamic vectors to a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current limb dynamic vectors of the target object.

[0113] Specifically, when generating the limb dynamic vector set, the current limb dynamic information of the target object is sampled to generate the current limb dynamic vector set of the target object.

[0114] Specifically, the sampled limb dynamic vector set M[a1, a2, ... a n ], a nThis represents the nth limb dynamic vector of the acquired target object's limb dynamics. The set of these limb dynamic vectors is M[a1, a2, ..., a...]. n Mapped to a three-dimensional coordinate system, forming three-dimensional coordinate data of limb dynamic vectors (X). M Y M Z M ).

[0115] 2. Generate a physiological information vector set based on the current physiological information of the target object, and map the physiological information vector set onto a three-dimensional coordinate system to obtain the three-dimensional coordinate data of the current physiological information vector of the target object.

[0116] Specifically, when generating the physiological information vector set, the current physiological information of the target object is sampled to generate the current physiological information vector set of the target object.

[0117] Specifically, the sampled physiological information vector set K[b1, b2, ... b n ], b n This represents the nth physiological information vector of the collected target object's physiological information. The set of these physiological information vectors is K[b1, b2, ..., b...]. n Mapped into a three-dimensional coordinate system, this forms physiological information vector three-dimensional coordinate data (X). K Y K Z K ).

[0118] 3. Based on the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data, establish the current three-dimensional dynamic portrait model of the target object.

[0119] Specifically, based on the target object's current limb dynamic vector three-dimensional coordinate data (X... M Y M Z M ) and the target object's current physiological information vector three-dimensional coordinate data (X K Y K Z K ), and establish the current three-dimensional dynamic portrait model L of the target object.

[0120] The detection module 303 is used to obtain the current dynamic category result of the target object based on the current three-dimensional dynamic portrait model and the pre-trained emotion detection model.

[0121] In some embodiments, the device may further include a training module, configured to: acquire historical dynamic category information of the target object and its corresponding dynamic category results; establish a historical three-dimensional dynamic portrait model of the target object based on the historical dynamic category information of the target object; and obtain an emotion detection model by training a BP neural network based on the historical three-dimensional dynamic portrait model and the dynamic category results.

[0122] The emotion detection model stores the mapping relationship between the dynamic profile model of the target object and the dynamic category results.

[0123] Furthermore, before obtaining the current dynamic category result of the target object, the emotion detection model is obtained through the training module.

[0124] Furthermore, based on the current three-dimensional dynamic portrait model of the target object, and according to the mapping relationship between the dynamic portrait model and the dynamic category result of the target object, the current dynamic category result of the target object is determined.

[0125] Furthermore, after determining the dynamic category result corresponding to the current 3D dynamic portrait model of the target object based on the pre-trained emotion detection model, the emotion detection model can be trained using the mapping relationship between the dynamic portrait model and the dynamic category result to obtain an updated emotion detection model.

[0126] Furthermore, if the current dynamic category result of the target object cannot be determined based on the mapping relationship between the dynamic profile model and the dynamic category result, the emotion detection model will repeatedly calculate the current dynamic category information of the target object until the current dynamic category result of the target object is determined.

[0127] The prompt module 304 provides a prompt based on the current dynamic category result.

[0128] In some embodiments, suggestions are provided based on the current dynamic category result, including:

[0129] The selection subunit is used to select the corresponding indicator light color based on the current dynamic category result;

[0130] The prompting subunit is used to prompt the user by displaying the color of the indicator light.

[0131] In some embodiments, if the current dynamic category result of the target object is in an abnormal state, the current dynamic category information of the target object can be indicated by illuminating different colored indicator lights to prompt the user. For example, green indicates a normal state, yellow indicates a hungry state, purple indicates a frightened state, and red indicates an abnormal body temperature state.

[0132] Specifically, if the target object's current dynamic category result is in a normal state, it means the target object is in a normal state, and the indicator light is on and displays green. If the target object's current dynamic category result is in an abnormal state, the indicator light is on and displays another color, prompting the user to take targeted actions based on the different dynamic category results. For example, when the target object is an infant, if the current dynamic category result is in a normal state, the indicator light is on and displays green, and no further action is needed; if the current dynamic category result is in a hungry state, the indicator light is on and displays yellow, and the parents need to prepare to feed the infant; if the current dynamic category result is in a state of abnormal body temperature, the indicator light is on and displays red, and the parents need to prepare to go to the hospital; if the current dynamic category result is in a state of fright, the indicator light is on and displays purple, and the parents need to comfort the infant by holding or kissing them.

[0133] It should be noted that normal states include: happy, playful, sound asleep, quiet, etc., while abnormal states include: angry, frightened, hungry, abnormal body temperature, abnormal heart rate, crying, etc.

[0134] In some embodiments, if the current dynamic category result of the target object is in an abnormal state, different colors can be displayed in conjunction with the number of flashing indicator lights to indicate the target object's current mood.

[0135] In some embodiments, the prompting module also includes an audio / video playback subunit. If the current dynamic category result of the target object is in an abnormal state, some soothing music can be played to alleviate the target object's emotions.

[0136] In some embodiments, the prompting module further includes a communication subunit. If the current dynamic category result of the target object is in an abnormal state, a reminder message can be sent to the smart terminal to display the current status information of the target object, so as to remotely grasp the current dynamic category information of the target object.

[0137] Furthermore, when the current dynamic category result displayed on the smart terminal is in an abnormal state, the target's emotions can be alleviated by conducting a voice / video call with the target.

[0138] This application discloses an emotion detection device, comprising: an acquisition module for acquiring current dynamic category information of a target object; an establishment module for establishing a current three-dimensional dynamic portrait model of the target object based on the current dynamic category information; a detection module for obtaining the current dynamic category result of the target object based on the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; and a prompting module for providing prompts based on the current dynamic category result. The emotion detection device of this invention improves the accuracy of judgment, increases detection efficiency, and enhances the user experience by addressing the current dynamic category information of the target object.

[0139] In summary, the emotion detection method and emotion detection device provided in this application improve the accuracy of judging the current dynamic category information of the target object, reduce the complexity of operation, and enhance the user experience.

[0140] In the several embodiments provided by this invention, it can be used for intelligent emotion detection. Therefore, the beneficial effects it can achieve can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0141] It should also be understood that the methods disclosed in the several embodiments provided in this invention can also be implemented in other ways. The method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functions, and operations of possible implementations of methods and apparatus according to various embodiments of the invention. In this regard, each block in a flowchart or block diagram may represent a module, computer program segment, or part of a computer program, which includes one or more computer programs for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings, and may actually be executed substantially in parallel, or sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer programs.

[0142] In this invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, apparatus, or apparatus that includes that element; the use of terms such as "first," "second," etc., is for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly indicating the number or sequence of the indicated technical features; in the description of this invention, unless otherwise expressly defined, the terms "normal state," "abnormal state," "BP neural network," etc., should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the terms in this invention in conjunction with the specific content of the technical solution; in the description of this invention, unless otherwise stated, the terms "a plurality of" or "many" mean at least two.

[0143] Finally, it should be noted that in the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "a single example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0144] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are merely implementation methods adopted to facilitate understanding of the present invention, and are not intended to limit the present invention. Any person skilled in the art to which this invention pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of protection of the present invention shall still be determined by the scope defined in the appended claims.

Claims

1. A method of emotion detection, characterized by, The method comprises: obtaining current dynamic category information of a target object through a sensor or a camera, wherein the current dynamic category information comprises limb dynamic information and physiological information; wherein the limb dynamic information comprises sound, sound size and limb movement, and the physiological information comprises body temperature, heart rate and blood pressure; establishing a current three-dimensional dynamic portrait model of the target object according to the current dynamic category information of the target object; obtaining a current dynamic category result of the target object according to the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; wherein the current dynamic category result comprises a normal state and an abnormal state, the normal state comprises a happy state, a playful state, a sound sleep state and a quiet state, and the abnormal state comprises an angry state, a hungry state, a body temperature abnormal state, a frightened state, a heart rate abnormal state and a crying state; prompting according to the current dynamic category result, comprising: selecting a corresponding indicator light color according to the current dynamic category result; and prompting a user by displaying the indicator light color.

2. The method of claim 1, wherein, The method comprises: generating a limb dynamic vector set according to current limb dynamic information of the target object, mapping the limb dynamic vector set to a three-dimensional coordinate system to obtain current limb dynamic vector three-dimensional coordinate data of the target object; generating a physiological information vector set according to current physiological information of the target object, mapping the physiological information vector set to a three-dimensional coordinate system to obtain current physiological information vector three-dimensional coordinate data of the target object; establishing a current three-dimensional dynamic portrait model of the target object according to the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data.

3. The method of claim 1, wherein, The training process of the emotion detection model comprises: obtaining historical dynamic category information of a target object and a dynamic category result corresponding thereto; establishing a historical three-dimensional dynamic portrait model of the target object according to the historical dynamic category information of the target object; training a BP neural network according to the historical three-dimensional dynamic portrait model and the dynamic category result to obtain the emotion detection model.

4. An emotion detection apparatus characterized by comprising: The device comprises: an obtaining module configured to obtain current dynamic category information of a target object through a sensor or a camera, wherein the current dynamic category information comprises limb dynamic information and physiological information; wherein the limb dynamic information comprises sound, sound size and limb movement, and the physiological information comprises body temperature, heart rate and blood pressure; an establishing module configured to establish a current three-dimensional dynamic portrait model of the target object according to the current dynamic category information of the target object; and an obtaining module configured to obtain a current dynamic category result of the target object according to the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; wherein the current dynamic category result comprises a normal state and an abnormal state, the normal state comprises a happy state, a playful state, a sound sleep state and a quiet state, and the abnormal state comprises an angry state, a hungry state, a body temperature abnormal state, a frightened state, a heart rate abnormal state and a crying state. The detection module is configured to obtain a current dynamic category result of the target object according to the current three-dimensional dynamic portrait model and a pre-trained emotion detection model; the current dynamic category result includes a normal state and an abnormal state, the normal state includes a happy state, a playful state, a sleep state and a quiet state, and the abnormal state includes an angry state, a hungry state, a body temperature abnormal state, a frightened state, a heart rate abnormal state and a crying state; The prompting module is configured to prompt according to the current dynamic category result; the prompting module includes a selection subunit and a prompting subunit; the selection subunit is configured to select a corresponding indicator light color according to the current dynamic category result; and the prompting subunit is configured to prompt a user by displaying the indicator light color.

5. The apparatus of claim 4, wherein, The establishing module includes: The generation sub-module is configured to generate a limb dynamic vector set according to current limb dynamic information of the target object, map the limb dynamic vector set to a three-dimensional coordinate system, and obtain current limb dynamic vector three-dimensional coordinate data of the target object; and generate a physiological information vector set according to current physiological information of the target object, map the physiological information vector set to a three-dimensional coordinate system, and obtain current physiological information vector three-dimensional coordinate data of the target object; The establishing sub-module is configured to establish a current three-dimensional dynamic portrait model of the target object according to the current limb dynamic vector three-dimensional coordinate data and the current physiological information vector three-dimensional coordinate data.

6. The apparatus of claim 4, wherein, The device further includes: The training module is configured to obtain historical dynamic category information of a target object and a dynamic category result corresponding thereto, establish a historical three-dimensional dynamic portrait model of the target object according to the historical dynamic category information of the target object, and obtain an emotion detection model by training a BP neural network according to the historical three-dimensional dynamic portrait model and the dynamic category result.

Images