Holding state identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a holding state recognition method and device, electronic equipment and a storage medium. The method comprises the following steps: in response to the detection that a first user holds the electronic equipment, obtaining first information; wherein the first information comprises a motion parameter of the electronic equipment; determining a holding state of the first user holding the electronic device corresponding to the motion parameter based on the motion parameter and a predetermined mapping relationship among the motion parameter, user information and the holding state; wherein the holding state is at least used for adjusting operation parameters of the electronic equipment. According to the embodiment of the invention, the accuracy of the determined holding state of the first user can be improved, and the influence of the holding state of the first user on the performance of the electronic equipment is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of electronic devices but is not limited to the field of electronic devices, and in particular to a method and device for identifying a holding state, an electronic device and a storage medium. Background Art

[0002] When a user holds an electronic device, the holding state of the user holding the electronic device may affect the performance of the electronic device. In the related art, the holding state of the user holding the electronic device is often identified and the operating parameters of the electronic device are adjusted to reduce the impact of the user's holding state on the performance of the electronic device. However, the holding state of the user identified in the related art is not accurate enough. Here, in the process of adjusting the operating parameters of the electronic device according to the holding state, the operating parameters of the electronic device cannot be accurately adjusted based on the accurate holding state, resulting in the inability to effectively reduce the impact of the user's holding state on the performance of the electronic device. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure disclose a method, device, electronic device and storage medium for identifying a holding state.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for identifying a holding state is provided, the method being applied to an electronic device, the method comprising:

[0005] In response to detecting that a first user holds the electronic device, acquiring first information; wherein the first information includes a motion parameter of the electronic device;

[0006] Based on the motion parameters and a predetermined mapping relationship between the motion parameters, user information and holding state, the holding state of the electronic device held by the first user corresponding to the motion parameters is determined; the holding state is at least used to adjust the operating parameters of the electronic device.

[0007] In one embodiment, the method further comprises:

[0008] Based on the first information, determining a first feature vector; wherein the first feature vector includes a vector corresponding to a feature of the motion parameter;

[0009] The determining, based on the motion parameter and a predetermined mapping relationship among the motion parameter, user information and the holding state, the holding state of the electronic device held by the first user corresponding to the motion parameter, includes:

[0010] Based on the first feature vector, and a predetermined mapping relationship between the second feature vector, the user and the holding state, the holding state of the first user holding the electronic device corresponding to the first feature vector is determined; wherein the second feature vector includes a vector corresponding to a feature of a motion parameter of the electronic device, and the similarity between the first feature vector and the second feature vector is within a predetermined range; and the holding state is at least used to adjust the operating parameters of the electronic device.

[0011] In one embodiment, determining a first feature vector based on the first information includes:

[0012] Inputting the first information into a first algorithm model to obtain the first feature vector;

[0013] The first algorithm model is used to extract the first feature vector from the first information.

[0014] In one embodiment, the method further comprises:

[0015] Inputting a training sample into the first algorithm model to obtain a feature vector; wherein the training sample includes first information marked with a preset holding state;

[0016] Inputting the feature vector into a second algorithm model; wherein the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector;

[0017] The first algorithm model and the second algorithm model are jointly trained until the training conditions of the first algorithm model and the second algorithm model are met, thereby obtaining the trained first algorithm model and the trained second algorithm model.

[0018] In one embodiment, the method further comprises:

[0019] Outputting prompt information; wherein the prompt information is used to prompt the first user to hold the electronic device according to the preset holding state;

[0020] In response to detecting that the first user holds the electronic device according to the preset holding state, the training sample is acquired.

[0021] In one embodiment, the preset holding state includes a preset holding posture and / or a preset holding operation state; the preset holding posture is the posture of a user holding the electronic device, and the preset holding operation includes an operation performed on the electronic device when the user holds the electronic device.

[0022] In one embodiment, the preset holding posture includes at least one of the following:

[0023] A first posture, wherein the first posture is a posture of a user holding the electronic device with his left hand;

[0024] A second posture, wherein the second posture is a posture of the user holding the electronic device with his right hand; and

[0025] A third posture, wherein the third posture is a posture in which the user holds the electronic device with both hands.

[0026] In one embodiment, the preset holding operation includes at least one of the following:

[0027] Click the click action in the first area;

[0028] A sliding operation of sliding along a first track;

[0029] a holding operation to maintain a holding posture; and,

[0030] A rotation operation of rotating the electronic device.

[0031] In one embodiment, the method further comprises:

[0032] Generate a first feature vector template based on the model parameters of the trained second algorithm model; wherein the first feature vector template is a feature vector template corresponding to the first user; different users correspond to different feature vector templates; the first feature vector template includes the second feature vector having the predetermined mapping relationship with the holding state;

[0033] The determining, based on the first feature vector and a predetermined mapping relationship between the second feature vector, the user information and the holding state, the holding state of the electronic device held by the first user corresponding to the first feature vector includes:

[0034] Based on the first feature vector and the first feature vector template, a holding state of the first user holding the electronic device is determined.

[0035] In one embodiment, determining the holding state of the electronic device held by the first user based on the first feature vector and the first feature vector template includes:

[0036] Based on the first feature vector, determining the second feature vector from the first feature vector template;

[0037] The holding state of the electronic device held by the first user is determined based on the holding state having the predetermined mapping relationship with the second feature vector.

[0038] In one embodiment, the motion parameter includes at least one of the following:

[0039] the acceleration of the electronic device; and

[0040] The angular velocity of the electronic device.

[0041] In one embodiment, the first information further includes at least one of the following:

[0042] an electromagnetic wave absorption rate, where the electromagnetic wave absorption rate is used to determine a holding area of ​​the electronic device held by the first user; and

[0043] Information about a touch area, where the touch area is an area corresponding to a touch operation performed on the electronic device.

[0044] In one embodiment, the operating parameters include at least one of the following:

[0045] Parameters related to the transmit beam;

[0046] Parameters related to output audio information;

[0047] Parameters related to receiving audio information;

[0048] Parameters related to detecting sensor data;

[0049] Parameters related to accidental touch prevention operation;

[0050] Parameters related to a fingerprint recognition method, the fingerprint recognition method including a method of recognizing a fingerprint of a user's left hand and / or right hand; and,

[0051] Parameters related to a manipulation mode provided to a user, wherein the manipulation mode includes a mode in which the user manipulates the electronic device with his left hand and / or right hand.

[0052] According to a second aspect of an embodiment of the present disclosure, a device for identifying a holding state is provided, the device comprising:

[0053] An acquisition module, configured to acquire first information in response to detecting that a first user holds the electronic device; wherein the first information includes a motion parameter of the electronic device;

[0054] A determination module, used to determine a first feature vector based on the first information; wherein the first feature vector includes a vector corresponding to the characteristics of the motion parameter; based on the first feature vector, and a predetermined mapping relationship between a second feature vector, a user and a holding state, determine the holding state of the electronic device held by the first user corresponding to the first feature vector; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range; and the holding state is at least used to adjust the operating parameters of the electronic device.

[0055] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, the electronic device comprising:

[0056] processor;

[0057] a memory for storing instructions executable by the processor;

[0058] The processor is configured to implement the method described in any embodiment of the present disclosure when running the executable instructions.

[0059] According to a fourth aspect of an embodiment of the present disclosure, a computer storage medium is provided, wherein the computer storage medium stores a computer executable program, and when the executable program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0060] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0061] In an embodiment of the present disclosure, in response to detecting that a first user holds an electronic device, first information is obtained; wherein the first information includes motion parameters of the electronic device; based on the motion parameters, and a predetermined mapping relationship between the motion parameters, user information, and the holding state, the holding state of the first user holding the electronic device corresponding to the motion parameters is determined; wherein the holding state is at least used to adjust the operating parameters of the electronic device. Here, since the holding state of the first user holding the electronic device is determined based on the motion parameters of the first user holding the electronic device and a predetermined mapping relationship between the motion parameters, user information, and the holding state, the holding state is at least used to adjust the operating parameters of the electronic device, and therefore, the determined holding state can adapt to the mapping relationship between the user information, motion parameters, and holding state of the first user, and at this time, the operating parameters adjusted by the holding state can also adapt to the mapping relationship between the user information, motion parameters, and holding state of the first user. Compared with the method in the related art that cannot accurately identify the user's holding state, in the embodiment of the present disclosure, when adjusting the operating parameters of the electronic device held by the first user by using the holding state of the first user determined based on the predetermined mapping relationship between motion parameters, user information and holding state, the influence of the relationship between user information, motion parameters of the electronic device and holding state on the holding states of different users can be fully considered, so as to accurately distinguish the holding states corresponding to different users, obtain the accurate holding state corresponding to the first user, and use the accurate holding state to accurately adjust the operating parameters of the electronic device. In this way, the accuracy of the holding state of the first user determined can be improved, and the influence of the holding state of the first user on the performance of the electronic device can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0063] Figure 1 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0064] Figure 2 is a schematic diagram of a holding posture according to an exemplary embodiment;

[0065] Figure 3 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0066] Figure 4 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0067] Figure 5 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0068] Figure 6 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0069] Figure 7 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0070] Figure 8 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0071] Fig. 9 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0072] Fig.10 is a flow chart of a method for identifying a holding state according to an exemplary embodiment;

[0073] Fig.11 is a schematic structural diagram of a holding state recognition device according to an exemplary embodiment;

[0074] Fig.12 The figure is a schematic diagram showing the structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present invention. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.

[0076] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0077] In the following description, the terms "first / second / third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first / second / third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the invention described herein can be implemented in an order other than that illustrated or described herein.

[0078] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0079] like Figure 1 As shown, an embodiment of the present disclosure provides a method for identifying a holding state, the method is applied to an electronic device, and the method includes:

[0080] Step S0011, in response to detecting that a first user holds an electronic device, acquiring first information; wherein the first information includes motion parameters of the electronic device;

[0081] Step S0012, based on the motion parameters, and a predetermined mapping relationship between the motion parameters, user information and holding state, determine the holding state of the electronic device held by the first user corresponding to the motion parameters; wherein the holding state is at least used to adjust the operating parameters of the electronic device.

[0082] In one embodiment, the motion parameter may include parameters of the motion of the first user holding the electronic device.

[0083] In one embodiment, the motion parameter may be a displacement parameter of the electronic device and / or a motion speed of the electronic device when the user holds the electronic device. The displacement parameter may include at least one of the following: displacement distance and displacement direction. The motion speed may include at least one of the following: average speed, angular velocity, and acceleration.

[0084] It is understandable that when the user holds the electronic device and moves it, if the holding state of the user holding the electronic device is different, the displacement parameter of the electronic device and / or the movement speed of the electronic device are different. At this time, the holding state of the user holding the electronic device can be determined based on the displacement parameter and / or movement speed of the electronic device when the user holds the electronic device, and the predetermined mapping relationship between the movement parameter, the user information and the holding state.

[0085] In one embodiment, the motion parameters may be detected using sensors disposed on the electronic device.

[0086] In one embodiment, a predetermined mapping relationship between motion parameters, user information, and holding state can be established based on historical experience data of the electronic device when the user holds the electronic device and moves. The historical experience data may include historical holding states of the user holding the electronic device and / or historical motion parameters of the electronic device when the user holds the electronic device and moves.

[0087] In one embodiment, based on the motion parameters, and a predetermined mapping relationship between the motion parameters, user information and holding state, determining the holding state of the first user holding the electronic device corresponding to the motion parameters includes: inputting the user information corresponding to the first user and the motion parameters corresponding to the first user into an algorithm model to obtain the holding state of the first user holding the electronic device; the algorithm model is established according to the predetermined mapping relationship between the motion parameters, user information and holding state.

[0088] In one embodiment, the user information is used to indicate the user. Here, the specific information included in the user information may not be limited, and it is only necessary to ensure that the user information can be used to indicate the user. Exemplarily, the user information may include but is not limited to at least one of the following: the user's name, gender, and age.

[0089] In one embodiment, an algorithm model may be constructed for different users. The algorithm model is established according to a predetermined mapping relationship between motion parameters, user information, and holding state.

[0090] In one embodiment, the training samples can be input into the algorithm model for training until the training conditions of the algorithm model are met to obtain the trained algorithm model; the training samples include first information marked with a preset holding state, and the first information includes motion parameters of the electronic device when the user holds the electronic device. In one embodiment, the first information also includes user information for indicating the user. In one embodiment, the trained algorithm model can be built in an electronic device, and the algorithm model built in the electronic device is used to identify the holding state of the user holding the electronic device.

[0091] In one embodiment, in response to detecting the information of a newly added user holding an electronic device, a training sample corresponding to the newly added user is obtained; the training sample includes first information marked with a preset holding state; the training sample corresponding to the newly added user is input into the trained algorithm model for training until the training conditions of the algorithm model are met, and an updated algorithm model is obtained. In one embodiment, the algorithm model built in the electronic device can be updated based on the updated algorithm model. Here, detecting the information of a newly added user holding an electronic device may also refer to detecting the newly added user information.

[0092] In one embodiment, different algorithm models can be established for different users. The algorithm model is established according to a predetermined mapping relationship between motion parameters and holding states. There is a mapping relationship between the algorithm model and the user information of the user.

[0093] In one embodiment, for different users, the training samples corresponding to the users can be input into the algorithm model for training until the training conditions of the algorithm model are met, and the algorithm model corresponding to the user can be obtained; the training samples include first information marked with a preset holding state, and the first information includes the motion parameters of the electronic device when the user holds the electronic device and moves it according to the preset holding state. In response to detecting that the first user holds the electronic device, the first information is obtained; wherein the first information includes the motion parameters of the electronic device; the motion parameters include the parameters of the first user holding the electronic device and moving it. Based on the motion parameters, and the predetermined mapping relationship between the motion parameters, the user information and the holding state, determining the holding state of the first user holding the electronic device corresponding to the motion parameters includes: determining the algorithm model corresponding to the first user based on the user information of the first user; inputting the motion parameters corresponding to the first user into the algorithm model corresponding to the first user, and obtaining the holding state of the first user holding the electronic device.

[0094] Here, since the training samples corresponding to different users are different, the training samples include first information marked with a preset holding state, and the first information includes the motion parameters of the electronic device when the user holds the electronic device and moves it according to the preset holding state. Therefore, for different users, user-specific training samples that can characterize the user's holding habits can be obtained. At this time, the algorithm model trained using the training samples corresponding to the user can also be used to characterize the user's holding habits, and the holding state obtained based on the trained algorithm model corresponding to the user can also be accurately adapted to the holding habits of different users, so that when the holding state of the first user is determined based on a predetermined mapping relationship, the holding state that conforms to the holding habit of the first user can be determined, ensuring the accuracy of the determined holding state.

[0095] In one embodiment, in response to the number of preset users being less than a quantity threshold, an algorithm model corresponding to the preset user can be built in the electronic device; the algorithm model corresponding to the preset user is used to identify the holding state of the preset user holding the electronic device. Different preset users correspond to different algorithm models. Here, it is possible to quickly determine the holding state of the user holding the electronic device using the algorithm model corresponding to the user, while ensuring that the number of algorithm models built in the electronic device is not too large. In this way, the rate of determining the holding state of the user holding the electronic device can be increased while reducing the memory occupied in the electronic device.

[0096] In one embodiment, in response to the number of preset users being greater than a number threshold, a predetermined mapping relationship between user information, motion parameters, and holding state is established based on an algorithm model corresponding to the preset user. The algorithm model corresponding to the preset user is used to identify the holding state of the preset user holding the electronic device according to first information corresponding to the preset user, the first information including the motion parameters.

[0097] In one embodiment, a predetermined mapping relationship may be stored in the electronic device. In this case, there is no need to build too many algorithm models in the electronic device, and the holding state of each user can be identified based on the predetermined mapping relationship. In this way, the waste of computing power resources and storage resources of the electronic device in the process of identifying the holding state of the user can be reduced.

[0098] In one embodiment, the preset user is a user who holds the electronic device at a frequency greater than a predetermined frequency, or the preset user may be a user determined based on an input operation acting on a predetermined control.

[0099] In one embodiment, the holding state includes a holding posture and / or a holding operation state; the holding posture is a posture of a user holding the electronic device, and the holding operation includes an operation performed on the electronic device when the user holds the electronic device.

[0100] In one embodiment, the operating parameters of the electronic device may be adjusted based on the holding posture and / or holding operation in the holding state of the first user.

[0101] In one embodiment, the holding operation may be an operation performed by a user on an application on an electronic device, and in this case, the operating parameters of the electronic device that are adjusted may be parameters related to the operation of the application. Exemplarily, the holding operation may be an operation of browsing a display interface in an application, and in this case, the operating parameters of the electronic device that are adjusted may be parameters related to allocating device resources of the electronic device to the application. The device resources may be memory and / or network resources.

[0102] In one embodiment, the holding posture and / or holding operation may be used to determine the holding area where the user holds the electronic device.

[0103] In one embodiment, the holding operation includes at least one of the following: a click operation of clicking a first area; a sliding operation of sliding along a first trajectory; a holding operation of maintaining a holding posture; and a rotation operation of rotating the electronic device. In one embodiment, the holding posture includes at least one of the following: a first posture (such as Figure 2 ), the first posture is the posture of the user holding the electronic device with his left hand; the second posture (as shown Figure 2 As shown), the second posture is a posture in which the user holds the electronic device with his right hand; and the third posture, the third posture is a posture in which the user holds the electronic device with both hands.

[0104] In one embodiment, the holding area of ​​the electronic device held by the first user may be determined based on the holding posture and / or holding operation included in the holding state corresponding to the first user; and the operating parameters of the electronic device may be adjusted based on the area outside the holding area of ​​the electronic device.

[0105] In one embodiment, the operating parameter may be a parameter related to the transmission beam. In this case, the adjusted operating parameter may be used to transmit the beam using an antenna arranged in an area outside the holding area.

[0106] Exemplarily, the holding area of ​​the first user holding the electronic device can be determined as the first area based on the holding posture and / or holding operation included in the holding state corresponding to the first user. At this time, the parameters related to the transmitting beam can be adjusted based on the second area different from the first area, and the adjusted parameters can be used to indicate the use of the antenna arranged in the second area to transmit the beam.

[0107] In an embodiment of the present disclosure, in response to detecting that a first user holds an electronic device, first information is obtained; wherein the first information includes motion parameters of the electronic device; the motion parameters include parameters of the first user holding the electronic device for movement; based on the motion parameters, and a predetermined mapping relationship between the motion parameters, user information, and holding state, the holding state of the first user holding the electronic device corresponding to the motion parameters is determined; wherein the holding state is at least used to adjust the operating parameters of the electronic device. Here, since the holding state of the first user holding the electronic device is determined based on the motion parameters of the first user holding the electronic device for movement, and a predetermined mapping relationship between the motion parameters, user information, and holding state, the holding state is at least used to adjust the operating parameters of the electronic device, therefore, the determined holding state can adapt to the mapping relationship between the user information, motion parameters, and holding state of the first user, at this time, the operating parameters adjusted by the holding state can also adapt to the mapping relationship between the user information, motion parameters, and holding state of the first user. Compared with the method in the related art that cannot accurately identify the user's holding state, in the embodiment of the present disclosure, when adjusting the operating parameters of the electronic device held by the first user by using the holding state of the first user determined based on the predetermined mapping relationship between motion parameters, user information and holding state, the influence of the relationship between user information, motion parameters of the electronic device and holding state on the holding states of different users can be fully considered, so as to accurately distinguish the holding states corresponding to different users, obtain the accurate holding state corresponding to the first user, and use the accurate holding state to accurately adjust the operating parameters of the electronic device. In this way, the accuracy of the holding state of the first user determined can be improved, and the influence of the holding state of the first user on the performance of the electronic device can be effectively reduced.

[0108] In one embodiment, Figure 3 As shown, the method includes:

[0109] Step S0031, determining a first feature vector based on the first information; wherein the first feature vector includes a vector corresponding to the feature of the motion parameter;

[0110] The determining, based on the motion parameter and a predetermined mapping relationship among the motion parameter, user information and the holding state, the holding state of the electronic device held by the first user corresponding to the motion parameter, includes:

[0111] Step S0032, based on the first feature vector, and a predetermined mapping relationship between the second feature vector, user information and holding state, determine the holding state of the electronic device held by the first user corresponding to the first feature vector; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range; and the holding state is at least used to adjust the operating parameters of the electronic device.

[0112] In one embodiment, in response to detecting that a first user is holding an electronic device, first information is acquired; wherein the first information includes motion parameters of the electronic device; based on the first information, a first feature vector is determined; wherein the first feature vector includes a vector corresponding to a feature of the motion parameter; based on the first feature vector, and a predetermined mapping relationship between a second feature vector, user information and a holding state, a holding state of the electronic device held by the first user corresponding to the first feature vector is determined; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range; the holding state is at least used to adjust operating parameters of the electronic device.

[0113] In one embodiment, the second feature vector includes a vector corresponding to a feature of a motion parameter of the electronic device.

[0114] In one embodiment, the first feature vector may be the same as the second feature vector. Alternatively, the first feature vector may be different from the second feature vector. In one embodiment, the value of the similarity within the predetermined range is greater than or equal to a similarity threshold. The similarity between the first feature vector and the second feature vector is within the predetermined range, which may mean that the similarity between the first feature vector and the second feature vector may be greater than or equal to a similarity threshold.

[0115] In one embodiment, the second feature vector can be determined from the preset feature vector based on the matching algorithm and the first feature vector. The matching algorithm is used to calculate the similarity between the first feature vector and the preset feature vector, and there is a predetermined mapping relationship between the preset feature vector, user information and holding state; based on the predetermined mapping relationship between the second feature vector, user information and holding state, the holding state of the first user holding the electronic device corresponding to the first feature vector is determined.

[0116] In one embodiment, the matching algorithm can be used to calculate at least one of the Euclidean distance, Hamming distance, cosine similarity, and linear correlation between the first feature vector and the preset feature vector. It is understandable that by calculating at least one of the Euclidean distance, Hamming distance, cosine similarity, and linear correlation between the first feature vector and the preset feature vector, the similarity between the first feature vector and the preset feature vector can be determined.

[0117] In one embodiment, a feature vector template library may be provided, and the preset feature vector may be a feature vector in the feature vector template library.

[0118] In one embodiment, the feature vector template library includes at least two feature vector templates, the feature vector template includes a feature vector having a predetermined mapping relationship with the holding state, and different feature vector templates have a predetermined mapping relationship with different users. The holding state of the first user holding the electronic device corresponding to the first feature vector can be determined based on the first feature vector and the second feature vector in the feature vector template. Here, since different feature vector templates have a predetermined mapping relationship with different users, the feature vector template includes a feature vector having a predetermined mapping relationship with the holding state, therefore, in the process of determining the holding state of the first user holding the electronic device, it can be accurately adapted to the type of user, and the second feature vector in the feature vector template corresponding to the first user is used to quickly determine the holding state of the first user holding the electronic device. At this time, there is no need to perform related operations on the feature vectors corresponding to users other than the first user. In this way, the speed of determining the holding state of the first user holding the electronic device can be improved, ensuring that the determined holding state can accurately adapt to the holding habit of the first user holding the electronic device. It can be understood that by setting different feature vector templates for different users in the embodiment of the present disclosure, it is possible to accurately identify different palms of different groups of people in the process of identifying the user's corresponding grip state. Compared with other solutions, it can effectively solve the problems of individual differences and the problem of distinguishability among large groups of people.

[0119] In one embodiment, in response to detecting that a first user holds an electronic device, first information is obtained; wherein the first information includes motion parameters of the electronic device. Based on the first information, a first feature vector is determined; wherein the first feature vector includes a vector corresponding to the feature of the motion parameter. A first feature vector template corresponding to the first user can be determined from a feature vector template library based on the information of the first user; the first feature vector template library at least includes a second feature vector having a predetermined mapping relationship with a holding state. Based on the first feature vector and the first feature vector template, the holding state of the first user holding the electronic device corresponding to the first feature vector is determined; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range; the holding state is at least used to adjust the operating parameters of the electronic device. Here, without identifying the feature vectors in each feature vector template in the feature vector template library one by one, the first feature vector template corresponding to the first user including the second feature vector can be quickly determined based on the information of the first user, thereby using the predetermined mapping relationship between the second feature vector in the first feature vector template and the holding state to quickly determine the holding state of the first user holding the electronic device. In this way, the operation of identifying the second feature vector can be simplified, and the speed of determining the holding state of the first user holding the electronic device can be improved.

[0120] In one embodiment, a feature vector template corresponding to the user may be generated in advance based on the motion parameters of the electronic device when the user holds the electronic device and moves. Exemplarily, a feature vector template corresponding to the user may be generated in advance based on the motion parameters of the electronic device when the first user holds the electronic device and moves. In one embodiment, there is a mapping relationship between the feature vector template and the user information of the user, and the feature vector template corresponding to the user may refer to the feature vector template corresponding to the user information of the user. In one embodiment, a feature vector template corresponding to the user may be determined based on the user information of the user.

[0121] In one embodiment, the motion parameters of the electronic device when the user holds the electronic device and moves it can be obtained, and a feature vector can be extracted from the motion parameters corresponding to the user, and the feature vector includes a vector corresponding to the feature of the motion parameter. A feature vector template corresponding to the user is generated in advance based on the feature vector corresponding to the user. Exemplarily, the motion parameters of the electronic device when the first user holds the electronic device and moves it can be obtained, and a feature vector can be extracted from the motion parameters corresponding to the first user, and the feature vector includes a vector corresponding to the feature of the motion parameter. A first feature vector template corresponding to the first user is generated in advance based on the feature vector corresponding to the first user.

[0122] In one embodiment, Figure 4As shown, determining a first feature vector based on the first information includes:

[0123] Step S0041: input the first information into a first algorithm model to obtain the first feature vector; wherein the first algorithm model is used to extract the first feature vector from the first information.

[0124] In one embodiment, in response to detecting that a first user is holding an electronic device, first information is obtained; wherein the first information includes motion parameters of the electronic device. The first information is input into a first algorithm model to obtain the first feature vector; wherein the first feature vector includes a vector corresponding to the features of the motion parameters. Based on the first feature vector, and a predetermined mapping relationship between a second feature vector, user information, and a holding state, the holding state of the electronic device held by the first user corresponding to the first feature vector is determined; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range; the holding state is at least used to adjust the operating parameters of the electronic device.

[0125] Here, since the first information is input into the first algorithm model to obtain the first feature vector, the feature vector related to the motion parameters in the first information can be accurately extracted, thereby reducing the interference of interference information in the first information that is unrelated to the motion parameters on the determination of the holding state. At this time, compared with the related art method of directly determining the holding state based on the motion parameters in the unprocessed first information, the present embodiment will perform a feature extraction operation on the first information, so that the holding state of the first user holding the electronic device corresponding to the first feature vector can be determined based on more accurate information of the first feature vector, as well as a predetermined mapping relationship between the second feature vector, user information and holding state. In this way, the accuracy of the determined holding state can be ensured.

[0126] In one embodiment, Figure 5 As shown, the method also includes:

[0127] Step S0051, inputting a training sample into the first algorithm model to obtain a feature vector; wherein the training sample includes first information marked with a preset holding state;

[0128] Step S0052, inputting the feature vector into a second algorithm model; wherein the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector;

[0129] Step S0053: jointly train the first algorithm model and the second algorithm model until the training conditions of the first algorithm model and the second algorithm model are met, thereby obtaining the trained first algorithm model and the trained second algorithm model.

[0130] In one embodiment, a training sample is input into the first algorithm model to obtain a feature vector; wherein the training sample includes first information marked with a preset holding state; the feature vector is input into the second algorithm model; wherein the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector; the first algorithm model and the second algorithm model are jointly trained until the training conditions of the first algorithm model and the second algorithm model are met, and the trained first algorithm model and the trained second algorithm model are obtained. In response to detecting that the first user holds the electronic device, first information is obtained; wherein the first information includes motion parameters of the electronic device. The first information is input into the first algorithm model to obtain the first feature vector; wherein the first feature vector includes a vector corresponding to the feature of the motion parameter. Based on the first feature vector, and a predetermined mapping relationship between the second feature vector, user information and holding state, the holding state of the first user holding the electronic device corresponding to the first feature vector is determined; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range; the holding state is at least used to adjust the operating parameters of the electronic device.

[0131] In one embodiment, the first algorithm model may be a feature extraction network model. Exemplarily, the first algorithm model may be a feedforward neural network model. The first algorithm model may also be a recurrent neural network model, or the first algorithm model may also be a long short-term memory network model.

[0132] In one embodiment, the training condition may be the convergence of the loss functions of the first algorithm model and the second algorithm model. In one embodiment, the loss function includes the first loss function and / or the second loss function, and the first loss function may be used to calculate the mean absolute error between the true value and the predicted value of the first algorithm model and / or the second algorithm model. The second loss function may be used to calculate the mean square error between the true value and the predicted value of the first algorithm model and / or the second algorithm model.

[0133] The first loss function and the second loss function both converge. The first loss function is the loss function of the first algorithm model, and the second loss function can be the loss function of the second algorithm model.

[0134] In one embodiment, the training condition may be that the number of training times for training the first algorithm model and / or the second algorithm model is greater than or equal to a preset number.

[0135] In one embodiment, during the process of training the first algorithm model and training the second algorithm model, the model parameters of the first algorithm model and the second algorithm model can be continuously corrected until the error between the predicted holding state and the preset holding state is within a preset range, and it is determined that the training conditions of the first algorithm model and the second algorithm model are met. The model parameters include weight coefficients and bias parameters of each network layer in the algorithm model.

[0136] In one embodiment, Figure 6 As shown, the method also includes:

[0137] Step S0061, outputting prompt information; wherein the prompt information is used to prompt the first user to hold the electronic device according to the preset holding state;

[0138] Step S0062: in response to detecting that the first user holds the electronic device according to the preset holding state, acquiring the training sample.

[0139] In one embodiment, a prompt message is output; wherein, the prompt message is used to prompt the first user to hold the electronic device according to the preset holding state. In response to detecting that the first user holds the electronic device according to the preset holding state, the training sample is obtained. The training sample is input into the first algorithm model to obtain a feature vector; wherein, the training sample includes first information marked with a preset holding state; the feature vector is input into the second algorithm model; wherein, the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector; the first algorithm model and the second algorithm model are jointly trained until the training conditions of the first algorithm model and the second algorithm model are met, and the trained first algorithm model and the trained second algorithm model are obtained.

[0140] Here, in response to detecting that the first user holds the electronic device according to the preset holding state, the training sample is obtained, and the training sample includes the first information marked with the preset holding state, and the first information includes the motion parameters of the electronic device. Therefore, the obtained training sample can adapt to the real holding state of the first user holding the electronic device and the real motion parameters of the electronic device. At this time, compared with the method of training the algorithm model based on a preset data set in the related art, the first algorithm model and the second algorithm model can be trained according to the real data that conforms to the holding habit of the first user holding the electronic device as the training sample in the embodiment of the present disclosure. In this way, the prediction effect of the first algorithm model and the second algorithm model can be improved.

[0141] In one embodiment, in response to detecting a touch operation acting on a first control, it is determined that the first user is holding the electronic device according to the preset holding state. The first control may be a control displayed as "Confirm Holding". In one embodiment, the touch operation may be a click operation.

[0142] In one embodiment, in response to detecting preset audio information, it is determined that the first user is detected holding the electronic device in a preset holding state. The preset audio information may be voice information output by the user. The audio content of the preset audio information may indicate that the user has held the device in a preset holding state. Exemplarily, the audio content of the preset audio information may be "I have held the device in a preset holding state".

[0143] In one embodiment, in response to detecting that the first user holds the electronic device in a preset holding state within the first time period, a training sample is obtained; or, in response to not detecting that the first user holds the electronic device in the preset holding state within the first time period, no training sample is obtained.

[0144] In one embodiment, the first time period may be a time period preset by a user, for example, the first time period may be preset to 30 seconds, or the first time period may be preset to 1 minute.

[0145] Here, since the training sample is obtained in response to detecting that the first user holds the electronic device in a preset holding state within the first time period, if the first user does not hold the electronic device in the preset holding state, it will not be detected whether the first user holds the electronic device in the preset holding state all the time, and the detection time for detecting whether the first user holds the electronic device in the preset holding state can be controlled to be no longer than the first time period. In this way, the waste of resources caused by constantly detecting the holding state of the first user can be reduced.

[0146] In one embodiment, in response to not detecting that the first user is holding the electronic device in a preset holding state within the first time period, prompt information is output based on a predetermined period until the number of times the prompt information is output is greater than or equal to a threshold number of times.

[0147] In one embodiment, the preset holding state includes a preset holding posture and / or a preset holding operation state; the preset holding posture is the posture of a user holding the electronic device, and the preset holding operation includes an operation performed on the electronic device when the user holds the electronic device.

[0148] In one embodiment, the preset holding posture includes at least one of the following: a first posture, the first posture is the posture of the user holding the electronic device with the left hand; a second posture, the second posture is the posture of the user holding the electronic device with the right hand; and a third posture, the third posture is the posture of the user holding the electronic device with both hands.

[0149] In one embodiment, the preset holding operation includes at least one of the following: a click operation of clicking the first area; a sliding operation of sliding along the first trajectory; a holding operation of maintaining the holding posture; and a rotation operation of rotating the electronic device. Here, it can be understood that under different preset holding operations, the motion parameters of the electronic device are different. For example, when the preset holding operation is a rotation operation, the movement amplitude of the electronic device is large, and when the preset holding operation is a click operation, the movement amplitude of the electronic device is small.

[0150] In one embodiment, the first area may be a display area on a touch screen of an electronic device. The electronic device may output a prompt message, the prompt message being used to prompt the user to perform a click operation in the first area. In one embodiment, the first area indicated in the prompt message output at different times may be different. Alternatively, the user may be prompted to perform click operations in different first areas respectively through one prompt message. Here, the first area may be a dynamically changing area.

[0151] In one embodiment, the first trajectory may be a trajectory of sliding in a predetermined direction. The predetermined direction may be upward, downward, left or right. The electronic device may output prompt information, and the prompt information is used to prompt the user to perform a sliding operation of sliding along the first trajectory on the touch screen of the electronic device. The first trajectory may include a combination of multiple trajectories. In one embodiment, the first trajectory indicated in the prompt information output at different times may be different. Here, the first trajectory may be variable.

[0152] In one embodiment, prompt information is output; wherein, the prompt information is used to prompt the first user to hold the electronic device according to the preset holding posture and perform a preset holding operation on the electronic device; in response to detecting that the first user holds the electronic device according to the preset holding posture and performs a preset holding operation on the electronic device, the training sample is obtained.

[0153] In one embodiment, the training samples include positive samples and / or negative samples. In response to detecting that the first user holds the electronic device according to the preset holding posture and performs a preset holding operation on the electronic device, a positive sample in the training samples is obtained; and / or in response to detecting that the first user does not hold the electronic device according to the preset holding posture and / or does not perform a preset holding operation on the electronic device, a negative sample in the training samples is obtained.

[0154] In one embodiment, the training samples include positive samples and / or negative samples. In response to detecting that the first user holds the electronic device according to the preset holding posture, a positive sample in the training samples is obtained; and / or in response to not detecting that the first user holds the electronic device according to the preset holding posture, a negative sample in the training samples is obtained.

[0155] In one embodiment, the training samples include positive samples and / or negative samples. In response to detecting that the first user performs the preset holding operation on the electronic device, a positive sample in the training samples is obtained; and / or in response to not detecting that the first user performs the preset holding operation, a negative sample in the training samples is obtained.

[0156] In one embodiment, in response to the training samples at least including the positive sample, the first algorithm model and the second algorithm model are trained using the training sample pairs.

[0157] In one embodiment, Figure 7 As shown, the method also includes:

[0158] Step S0071, generating a first feature vector template based on the model parameters of the trained second algorithm model; wherein the first feature vector template is a feature vector template corresponding to the first user; different users correspond to different feature vector templates; the first feature vector template includes the second feature vector having the predetermined mapping relationship with the holding state;

[0159] The determining, based on the first feature vector and a predetermined mapping relationship between the second feature vector, the user information and the holding state, the holding state of the electronic device held by the first user corresponding to the first feature vector includes:

[0160] Step S0072: determining a holding state of the electronic device held by the first user based on the first feature vector and the first feature vector template.

[0161] In one embodiment, a prompt message is output; wherein the prompt message is used to prompt the first user to hold the electronic device according to the preset holding state. In response to detecting that the first user holds the electronic device according to the preset holding state, the training sample is obtained. The training sample is input into the first algorithm model to obtain a feature vector; wherein the training sample includes the first information marked with the preset holding state; the feature vector is input into the second algorithm model; wherein the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector; the first algorithm model and the second algorithm model are jointly trained until the training conditions of the first algorithm model and the second algorithm model are met, and the trained first algorithm model and the trained second algorithm model are obtained. Based on the model parameters of the trained second algorithm model, a first feature vector template is generated; wherein the first feature vector template is the feature vector template corresponding to the first user; different users correspond to different feature vector templates; the first feature vector template includes the second feature vector having the predetermined mapping relationship with the holding state. In response to detecting that the first user holds the electronic device, first information is obtained; wherein the first information includes the motion parameters of the electronic device. Based on the first information, a first feature vector is determined, wherein the first feature vector includes a vector corresponding to the feature of the motion parameter. Based on the first feature vector and the first feature vector template, a holding state of the first user holding the electronic device is determined.

[0162] Here, since the first feature vector template is generated based on the model parameters of the trained second algorithm model, the model parameters of the second algorithm model are actually obtained based on the training samples corresponding to the first user, and the second algorithm model can output the predicted holding state of the first user based on the input feature vector, therefore, the first feature vector template generated according to the model parameters of the second algorithm model can be used to characterize the feature vectors corresponding to different holding states of the first user. On the one hand, in the process of determining the holding state of the first user based on the first feature vector and the first feature vector template, the feature vector in the first feature vector template that matches the first feature vector can be used to accurately determine the holding state of the first user, thereby ensuring the reliability of identifying the holding state of the first user. On the other hand, there is no need to build a second algorithm model in the electronic device, but the holding state of the first user can be directly determined based on the first feature vector template that occupies less memory, thereby saving storage resources of the electronic device.

[0163] In one embodiment, the same first algorithm model can be trained for different users, and different second algorithm models can be trained for different users. The second algorithm model corresponding to the user is used to predict the holding state of the user holding the electronic device.

[0164] For example, for the first user, the first algorithm model A and the second algorithm model B can be trained using the training samples corresponding to the first user; for the second user, the first algorithm model A and the second algorithm model C can be trained using the training samples corresponding to the second user. At this time, the second algorithm model B is used to predict the holding posture of the first user holding the electronic device. The second algorithm model C is used to predict the holding state of the second user holding the electronic device.

[0165] In one embodiment, a feature vector template corresponding to the user may be generated based on a second algorithm model corresponding to the user.

[0166] In one embodiment, a first feature vector template may be generated based on model parameters of the trained first algorithm model and the second algorithm model; wherein the first algorithm model is used to obtain a feature vector input into the second algorithm model.

[0167] In one embodiment, the preset first information can be input into the trained first algorithm model and the second algorithm model; the feature vector of the first algorithm model input into the second algorithm model and the holding state output by the second algorithm model are obtained; and based on the mapping relationship between the feature vector and the holding state, a first feature vector template is generated.

[0168] In one embodiment, Figure 8 As shown, the determining, based on the first feature vector and the first feature vector template, the holding state of the first user holding the electronic device includes:

[0169] Step S0081, based on the first feature vector, determining the second feature vector from the first feature vector template;

[0170] Step S0082: determining the holding state of the electronic device held by the first user based on the holding state having the predetermined mapping relationship with the second feature vector.

[0171] In one embodiment, a prompt message is output; wherein the prompt message is used to prompt the first user to hold the electronic device according to the preset holding state. In response to detecting that the first user holds the electronic device according to the preset holding state, the training sample is obtained. The training sample is input into the first algorithm model to obtain a feature vector; wherein the training sample includes the first information marked with the preset holding state. The feature vector is input into the second algorithm model; wherein the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector. The first algorithm model and the second algorithm model are jointly trained until the training conditions of the first algorithm model and the second algorithm model are met, and the trained first algorithm model and the trained second algorithm model are obtained. Based on the model parameters of the trained second algorithm model, a first feature vector template is generated; wherein the first feature vector template is the feature vector template corresponding to the first user; different users correspond to different feature vector templates; and the first feature vector template includes the second feature vector having the predetermined mapping relationship with the holding state. In response to detecting that the first user holds the electronic device, first information is obtained; wherein the first information includes the motion parameters of the electronic device. Based on the first information, a first feature vector is determined; wherein the first feature vector includes a vector corresponding to the feature of the motion parameter. Based on the first feature vector, a second feature vector is determined from the first feature vector template; based on the holding state having the predetermined mapping relationship with the second feature vector, a holding state of the first user holding the electronic device is determined.

[0172] Here, since the second feature vector is determined from the first feature vector template based on the first feature vector, and the holding state of the first user holding the electronic device is determined based on the holding state corresponding to the second feature vector, the matching range of the second feature vector similar to the first feature vector can be narrowed, so that the second feature vector corresponding to the first feature vector can be quickly matched from the first feature vector template, and the mapping relationship between the second feature vector and the holding state can be quickly used to directly determine the holding state of the first user holding the electronic device. In this way, the speed of determining the second feature vector can be accelerated, and the efficiency of determining the holding state based on the second feature vector can be improved.

[0173] In one embodiment, the second feature vector may be determined from the first feature vector template based on the matching algorithm and the first feature vector described in any one of the embodiments of the present disclosure; wherein the similarity between the first feature vector and the second feature vector is within a predetermined range.

[0174] In one embodiment, the motion parameter includes at least one of the following: acceleration of the electronic device; and angular velocity of the electronic device.

[0175] In one embodiment, a first sensor and a second sensor are provided on the electronic device, the first sensor is used to detect the acceleration of the electronic device, and the second sensor is used to detect the angular velocity of the electronic device. In one embodiment, the second sensor may be a gyroscope sensor. Here, there is no need to set up additional malicious hardware on the electronic device, and the motion parameters can be detected based on the common sensors of the mobile phone itself. At this point, the embodiment of the present disclosure can reduce the cost of detecting motion parameters in the process of training an algorithm model based on motion parameters or identifying a holding state.

[0176] In one embodiment, the acceleration of the electronic device may be determined by a first sensor provided on the electronic device; and / or the angular velocity of the electronic device may be determined by a second sensor provided on the electronic device.

[0177] In one embodiment, the first information further includes at least one of the following:

[0178] Electromagnetic wave absorption rate, the electromagnetic wave absorption rate is used to determine the holding area of ​​the electronic device held by the first user; and information of the touch area, the touch area is the area corresponding to the touch operation acting on the electronic device.

[0179] In one embodiment, in response to detecting that a first user holds an electronic device, first information is obtained; wherein the first information at least includes motion parameters of the electronic device; the first information also includes at least one of the following: information on electromagnetic wave absorption rate and touch area; the electromagnetic wave absorption rate is used to determine the holding area of ​​the electronic device held by the first user; the touch area is an area corresponding to the touch operation acting on the electronic device. Determining the holding state of the electronic device held by the first user corresponding to the motion parameters based on the motion parameters and a predetermined mapping relationship between the motion parameters, the user and the holding state includes: determining the holding state of the electronic device held by the first user corresponding to the first information based on the first information and a predetermined mapping relationship between the first information, the user and the holding state. The holding state is at least used to adjust the operating parameters of the electronic device.

[0180] Here, since the first information also includes at least one of the electromagnetic wave absorption rate and the touch area information, the electromagnetic wave absorption rate and the touch area are actually information closely related to the holding state of the user holding the electronic device, therefore, in the process of determining the holding state of the first user holding the electronic device corresponding to the first information based on the first information and the predetermined mapping relationship between the first information, the user information and the holding state, the holding state of the first user holding the electronic device can be determined based on more comprehensive information related to the holding state of the electronic device. In this way, the accuracy of the determined holding state can be improved.

[0181] In one embodiment, the electronic device may be provided with a third sensor, and the third sensor is used to detect the electromagnetic wave absorption rate. The third sensor may be an electromagnetic wave absorption rate (SAR, Specific Absorption Rate) sensor.

[0182] In one embodiment, the operating parameters include at least one of the following:

[0183] Parameters related to the transmit beam;

[0184] Parameters related to output audio information;

[0185] Parameters related to receiving audio information;

[0186] Parameters related to detecting sensor data;

[0187] Parameters related to accidental touch prevention operation;

[0188] Parameters related to a fingerprint recognition method, the fingerprint recognition method including a method of recognizing a fingerprint of a user's left hand and / or right hand; and,

[0189] Parameters related to a manipulation mode provided to a user, wherein the manipulation mode includes a mode in which the user manipulates the electronic device with his left hand and / or right hand.

[0190] In one embodiment, the holding area of ​​the electronic device held by the first user may be determined based on the holding state of the electronic device held by the first user; and the operating parameters of the electronic device may be adjusted based on the holding area of ​​the electronic device held by the first user.

[0191] In one embodiment, the parameters related to the transmission beam can be adjusted based on the holding area of ​​the electronic device held by the first user. In one embodiment, the adjusted parameters are parameters for transmitting the beam using an antenna set in a non-holding area. The non-holding area is an area on the electronic device other than the holding area.

[0192] In one embodiment, the parameters related to the output audio information can be adjusted based on the holding area of ​​the electronic device held by the first user. In one embodiment, the adjusted parameters are used to output the parameters of the audio information using a speaker device set in a non-holding area. The speaker device here can be a speaker.

[0193] In one embodiment, the parameters related to receiving audio information can be adjusted based on the holding area of ​​the electronic device held by the first user. In one embodiment, the adjusted parameters are used to receive audio information using a sound receiving device disposed in a non-holding area. The sound receiving device here can be a microphone.

[0194] In one embodiment, the parameters related to detecting the sensor data can be adjusted based on the holding area of ​​the electronic device held by the first user. In one embodiment, the adjusted parameters are used to detect the sensor data using a sensor disposed in a non-holding area.

[0195] In one embodiment, the parameters related to the accidental touch prevention operation can be adjusted based on the holding area of ​​the electronic device held by the first user. In one embodiment, the adjusted parameters are used to determine the accidental touch prevention area from the non-holding area.

[0196] In one embodiment, the holding state includes a state of a holding posture; the holding posture is a posture of a user holding the electronic device. The holding posture includes at least one of the following: a first posture, the first posture is a posture of the user holding the electronic device with the left hand; a second posture, the second posture is a posture of the user holding the electronic device with the right hand; and a third posture, the third posture is a posture of the user holding the electronic device with both hands. Based on the holding posture of the first user holding the electronic device, the operating parameters of the electronic device are adjusted.

[0197] In one embodiment, parameters related to fingerprint recognition are adjusted based on the holding posture of the first user holding the electronic device.

[0198] Exemplarily, if the first user holds the electronic device in the left hand holding an e-book device, the parameters related to fingerprint recognition are adjusted, and the adjusted parameters are used to determine the fingerprint recognition method as a method of recognizing the fingerprint of the user's left hand.

[0199] In one embodiment, based on the holding posture of the first user holding the electronic device, parameters related to the control mode provided to the user are adjusted.

[0200] Exemplarily, if the first user holds the electronic device in the left hand, the parameters related to the control mode provided to the user are adjusted, and the adjusted parameters are used to determine that the control mode is a fingerprint method of controlling the electronic device with the left hand.

[0201] To better understand the methods provided in the embodiments of the present disclosure, see Fig. 9 , Fig. 9 A process of obtaining a feature vector template is shown exemplarily:

[0202] Step S0091, outputting prompt information; wherein the prompt information is used to prompt the user to hold the electronic device according to the preset holding state;

[0203] Step S0092, obtaining first information corresponding to when the user holds the electronic device in a preset holding state; wherein the first information includes motion parameters of the electronic device; the motion parameters include acceleration detected by the first sensor and angular velocity detected by the second sensor; the second sensor is a gyroscope sensor;

[0204] Step S0092, inputting the motion parameters into the first algorithm model to obtain a feature vector template corresponding to the user;

[0205] Step S0093, updating the feature vector template library;

[0206] The updated feature vector template library includes the obtained feature vector template.

[0207] To better understand the methods provided in the embodiments of the present disclosure, see Fig.10 , Fig.10 A process of using a feature vector template is shown exemplarily:

[0208] Step S1001, obtaining first information corresponding to when a user holds an electronic device; wherein the first information includes motion parameters of the electronic device; the motion parameters include acceleration detected by a first sensor and angular velocity detected by a second sensor; the second sensor is a gyroscope sensor;

[0209] Step S1002, inputting the first information into the first algorithm model to obtain a first feature vector;

[0210] Step S1003, matching the first feature vector with feature vectors in a feature template library based on a matching algorithm;

[0211] There is a mapping relationship between the feature vector in the feature template library and the grip state; the matching algorithm here may be any matching algorithm described in the embodiments of the present disclosure; the feature vector in the feature template library may be a feature vector in a feature vector template corresponding to the user;

[0212] Step S1004, outputting the matching result and the holding status;

[0213] The holding state outputted here may be the holding state corresponding to the second feature vector in the feature template library, where the second feature vector is a vector whose similarity with the first feature vector is within a predetermined range.

[0214] like Fig.11 As shown, an embodiment of the present disclosure provides a holding state recognition device, the device comprising:

[0215] The acquisition module 111 is configured to acquire first information in response to detecting that a first user holds an electronic device; wherein the first information includes motion parameters of the electronic device; and the motion parameters include parameters of the motion of the first user holding the electronic device;

[0216] The determination module 112 is used to determine the holding state of the electronic device held by the first user corresponding to the motion parameters based on the motion parameters and a predetermined mapping relationship between the motion parameters, the user and the holding state; the holding state is at least used to adjust the operating parameters of the electronic device.

[0217] Fig.12 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. The disclosed method can be applied to the electronic device.

[0218] Reference Fig.12 , the electronic device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .

[0219] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0220] The memory 604 is configured to store various types of data to support operations on the device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0221] The power supply component 606 provides power to the various components of the electronic device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 600.

[0222] The multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0223] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), and when the electronic device 600 is in an operation mode, such as a call mode, a recording mode, and a voice determination mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 604 or sent via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0224] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0225] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the electronic device 600. For example, the sensor assembly 614 can detect the open / closed state of the device 600, the relative positioning of components, such as the display and keypad of the electronic device 600, and the sensor assembly 614 can also detect the position change of the electronic device 600 or a component of the electronic device 600, the presence or absence of contact between the user and the electronic device 600, the orientation or acceleration / deceleration of the electronic device 600, and the temperature change of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0226] The communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices. The electronic device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency determination (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0227] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0228] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the instructions can be executed by the processor 820 of the electronic device 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0229] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed in this disclosure.

[0230] It will be appreciated that the present invention is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A method for identifying a holding state, characterized in that: The method is applied to an electronic device, and the method comprises: In response to detecting that a first user holds the electronic device, acquiring first information; wherein the first information includes a motion parameter of the electronic device; Based on the motion parameters, and a predetermined mapping relationship between the motion parameters, user information and holding state, the holding state of the first user holding the electronic device corresponding to the motion parameters is determined; wherein the holding state is at least used to adjust the operating parameters of the electronic device.

2. The method according to claim 1, characterized in that The method further comprises: Based on the first information, determining a first feature vector; wherein the first feature vector includes a vector corresponding to a feature of the motion parameter; The determining, based on the motion parameter and a predetermined mapping relationship among the motion parameter, user information and the holding state, the holding state of the electronic device held by the first user corresponding to the motion parameter, includes: Based on the first feature vector, and a predetermined mapping relationship between the second feature vector, user information and holding state, the holding state of the first user holding the electronic device corresponding to the first feature vector is determined; wherein the second feature vector includes a vector corresponding to the characteristics of the motion parameters of the electronic device, and the similarity between the first feature vector and the second feature vector is within a predetermined range; the holding state is at least used to adjust the operating parameters of the electronic device.

3. The method according to claim 2, characterized in that The determining a first feature vector based on the first information includes: Inputting the first information into a first algorithm model to obtain the first feature vector; The first algorithm model is used to extract the first feature vector from the first information.

4. The method according to claim 3, characterized in that The method further comprises: Inputting a training sample into the first algorithm model to obtain a feature vector; wherein the training sample includes first information marked with a preset holding state; Inputting the feature vector into a second algorithm model; wherein the second algorithm model is used to predict the holding state of the user holding the electronic device according to the input feature vector; The first algorithm model and the second algorithm model are jointly trained until the training conditions of the first algorithm model and the second algorithm model are met, thereby obtaining the trained first algorithm model and the trained second algorithm model.

5. The method according to claim 4, characterized in that The method further comprises: Outputting prompt information; wherein the prompt information is used to prompt the first user to hold the electronic device according to the preset holding state; In response to detecting that the first user holds the electronic device according to the preset holding state, the training sample is acquired.

6. The method according to claim 4 or 5, characterized in that: The preset holding state includes a preset holding posture and / or a preset holding operation state; the preset holding posture is the posture of a user holding the electronic device, and the preset holding operation includes an operation performed on the electronic device when the user holds the electronic device.

7. The method according to claim 6, characterized in that The preset holding posture includes at least one of the following: A first posture, wherein the first posture is a posture of a user holding the electronic device with his left hand; A second posture, where the second posture is a posture of the user holding the electronic device with his right hand; as well as, A third posture, wherein the third posture is a posture in which the user holds the electronic device with both hands.

8. The method according to claim 6, characterized in that The preset holding operation includes at least one of the following: Click the click action in the first area; A sliding operation of sliding along a first track; a holding operation to maintain a holding posture; and, A rotation operation of rotating the electronic device.

9. The method according to claim 4, characterized in that The method further comprises: Generate a first feature vector template based on the model parameters of the trained second algorithm model; wherein the first feature vector template is a feature vector template corresponding to the first user; different users correspond to different feature vector templates; the first feature vector template includes the second feature vector having the predetermined mapping relationship with the holding state; The determining, based on the first feature vector and a predetermined mapping relationship between the second feature vector, the user information and the holding state, the holding state of the electronic device held by the first user corresponding to the first feature vector includes: Based on the first feature vector and the first feature vector template, a holding state of the first user holding the electronic device is determined.

10. The method according to claim 9, characterized in that The determining, based on the first feature vector and the first feature vector template, a holding state of the electronic device held by the first user includes: Based on the first feature vector, determining the second feature vector from the first feature vector template; The holding state of the electronic device held by the first user is determined based on the holding state having the predetermined mapping relationship with the second feature vector.

11. The method according to claim 1, characterized in that: The motion parameters include at least one of the following: the acceleration of the electronic device; and The angular velocity of the electronic device.

12. The method according to claim 1, characterized in that The first information also includes at least one of the following: an electromagnetic wave absorption rate, where the electromagnetic wave absorption rate is used to determine a holding area of ​​the electronic device held by the first user; and Information about a touch area, where the touch area is an area corresponding to a touch operation performed on the electronic device.

13. The method according to claim 1, characterized in that The operating parameters include at least one of the following: Parameters related to the transmit beam; Parameters related to output audio information; Parameters related to receiving audio information; Parameters related to detecting sensor data; Parameters related to accidental touch prevention operation; Parameters related to a fingerprint recognition method, the fingerprint recognition method including a method of recognizing a fingerprint of a user's left hand and / or right hand; and, Parameters related to a manipulation mode provided to a user, wherein the manipulation mode includes a mode in which the user manipulates the electronic device with his left hand and / or right hand.

14. A holding state recognition device, characterized in that: The device comprises: An acquisition module, configured to acquire first information in response to detecting that a first user holds the electronic device; wherein the first information includes a motion parameter of the electronic device; A determination module is used to determine the holding state of the electronic device held by the first user corresponding to the motion parameters based on the motion parameters and a predetermined mapping relationship between the motion parameters, user information and the holding state; wherein the holding state is at least used to adjust the operating parameters of the electronic device.

15. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: implement the method described in any one of claims 1 to 13 when running the executable instructions.

16. A computer-readable storage medium, characterized in that: The readable storage medium stores an executable program, wherein the executable program implements the method according to any one of claims 1 to 13 when executed by a processor.

Images