WO2023206450A1

WO2023206450A1 - Method and electronic device for identifying limb movement intention

Info

Publication number: WO2023206450A1
Application number: PCT/CN2022/090522
Authority: WO
Inventors: 崔晗; 耿艳娟; 李光林
Original assignee: 中国科学院深圳先进技术研究院
Priority date: 2022-04-29
Filing date: 2022-04-29
Publication date: 2023-11-02

Abstract

The present invention relates to the technical field of man-machine interfaces, and provides a method for identifying a limb movement intention. The method comprises: by means of a light acquisition module, acquiring a plurality of light intensity signals at different positions on a target site of a living body, wherein the light acquisition module comprises: M light sources and N detectors, the M light sources are configured to irradiate the target site, the N detectors are configured to receive light intensity signals emitted from different positions on the target site, M is a positive integer, and N is a positive integer greater than 1; and according to the plurality of light intensity signals, identifying a limb movement intention. The described method can improve the accuracy of identifying the limb movement intention.

Description

A method and electronic device for identifying body movement intentions

Technical field

The present application relates to the field of human-machine interface technology, and in particular to a method and electronic device for identifying body movement intentions.

Background technique

With the rapid development of human-computer interface technology, people can directly control external devices (such as prostheses, wheelchairs, etc.) by decoding human neural information. For example, common human-computer interface technologies for decoding human neural information include brain-computer interface and muscle-machine interface technology. Among them, myo-machine interface technology refers to decoding human limbs through signals such as electromyography (EMG) signals and muscle deformation. Movement intention, and then a method to control the action of external devices. At present, because the method of using a near-infrared spectrometer alone to identify movement intentions does not require the application of conductive coupling materials on the surface of biological tissues and has high long-term stability, technicians usually use a single near-infrared spectrometer to detect the contraction of local muscles or a single muscle. Changes during the deformation process, and assist myoelectric signals to identify limb movement intentions based on local muscle detection results, thereby realizing the human body's control of external devices. However, since changes in the external morphology of human muscles are comprehensively affected by changes in multiple muscles, using only a single near-infrared spectrometer to identify limb movement intentions obviously cannot achieve a high accuracy in identifying limb movement intentions.

Therefore, how to improve the accuracy of identifying body movement intentions is an urgent problem that needs to be solved.

technical problem

One purpose of the embodiments of the present application is to provide a method and electronic device for identifying body movement intentions, aiming to solve the problem of how to improve the accuracy of identifying body movement intentions.

Technical solutions

The technical solutions adopted in the embodiments of this application are:

In a first aspect, a method for identifying limb movement intention is provided. The method includes: acquiring multiple light intensity signals at different locations on a target part of a living body through a light collection module, wherein the light collection module includes: M There are two light sources and N detectors. The M light sources are used to illuminate the target part. The N detectors are used to receive the light intensity signals emitted from different positions on the target part. The M is a positive integer, so N is a positive integer greater than 1; body movement intention is identified based on the multiple light intensity signals.

The above method may be executed by an electronic device or a chip in the electronic device. Compared with only using a single near-infrared spectrometer (i.e., a single light source and a single detector) to detect muscle deformation at a single location of the target part, the above method uses multiple detectors distributed at high density in the light collection module to collect multiple images at different locations on the target part. Light intensity signals (that is, collecting the deformation of muscles at multiple locations (i.e., multiple muscles) on the target part), and identifying limb movement intentions based on these multiple light intensity signals, can improve the accuracy of identifying limb movement intentions.

Optionally, the M light sources include a first light source and a second light source, and obtaining multiple light intensity signals at different locations on the target site through the light collection module includes: turning on the first light source; The light collection module obtains the light intensity signal emitted by the first light source on the target site; turns off the first light source; turns on the second light source; and obtains the location of the second light source through the light collection module. The light intensity signal emitted from the target part.

In this embodiment, when collecting multiple light intensity signals at different locations on the target site, the light collection module only turns on one light source (for example, the first light source) and turns off other light sources (for example, the second light source) at a time, so that The multiple detectors around the light source only acquire the multiple light intensity signals emitted by the light source from the target part each time, and so on, until the multiple light intensity signals emitted by the last light source from the target part are acquired. The reason why all light sources are not turned on at the same time is that turning on all light sources at the same time will cause the light intensity signals emitted by different light sources to be irradiated on the same detector at the same time, causing crosstalk between light intensity signals. This will not only affect multiple light intensity signal response targets. The accuracy of muscle deformation at different parts of the body also affects the accuracy of the electronic device in identifying the intention of limb movement based on the multiple light intensity signals.

Optionally, obtaining the light intensity signal emitted by the first light source on the target site through the light collection module includes: obtaining the first light intensity signal through K groups of detectors among the N detectors. The light intensity signal emitted by the light source on the target part, the K is an integer greater than 1.

In this embodiment, instead of using a single detector each time to obtain the light intensity signal emitted at a single position on the target site at one depth, this application uses K sets of detectors to obtain different signals of the first light source at different positions on the target site at one time. The light intensity signal emitted from the depth does not need to acquire the light intensity signal at different locations on the target part multiple times, thereby improving the efficiency of electronic equipment using the light collection module to acquire multiple light intensity signals.

Optionally, a plurality of detectors in any one of the K groups of detectors are equidistant from the first light source.

In this embodiment, since the distance between the detector and the first light source is different, the depth detected by the detector will be different. Therefore, if you want to detect the muscle deformation of the target part at the same depth but at different positions, multiple detectors in any set of detectors must be used. Each detector needs to be at an equal distance from the first light source, so that the electronic device can identify the intention of the limb movement based on multiple light intensity signals that reflect the muscle deformation at the same depth but at different positions of the target site.

Optionally, multiple detectors in any group of detectors in the K groups of detectors are equally spaced among each other.

In this embodiment, multiple detectors in any group of detectors are equally spaced. The purpose is that the light collection module can uniformly collect the deformation of the muscles at different positions of the target part, so as to avoid uneven distribution of detectors and This leads to the omission of collecting light intensity signals that reflect the muscle deformation at key locations.

Optionally, the distance between any two groups of detectors in the K groups of detectors and the first light source is different.

In this embodiment, since different distances between the detector and the first light source will result in different depths detected by the detector, different groups of detectors in the K group of detectors have different distances from the first light source, and different reaction target parts can be collected. The light intensity signals of the muscle deformation conditions at different positions and different depths are used to improve the accuracy of the electronic device in identifying the intention of limb movement based on the deformation conditions of the muscles at different positions and different depths.

Optionally, the M light sources are M multi-wavelength LED light sources.

In this embodiment, since different tissue components have different absorption results for different wavelengths, the use of multi-wavelength LED light sources can alternately emit light intensity signals of different wavelengths, which can prevent different tissue components from absorbing the wavelength when a single wavelength is used. The result is that the light intensity signal acquired by the detector cannot truly reflect the muscle deformation at different locations of the target part.

Optionally, identifying the body movement intention based on the multiple light intensity signals includes: filtering and feature extraction on the multiple light intensity signals to obtain a feature extraction result; and inputting the feature extraction result into a classifier , to obtain the limb movement intention.

In a second aspect, an electronic device is provided, including a processor and a memory. The memory is used to store a computer program. The processor is used to call and run the computer program from the memory, so that the electronic device executes The method according to any one of the first aspects.

In a third aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it causes the processor to execute any one of the first aspects. Methods.

The beneficial effects in the second and third aspects of the present application refer to the beneficial effects in the first aspect.

Description of the drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments or exemplary technologies will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of the present application. For some embodiments, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.

Figure 1 is a schematic flowchart of a method for identifying limb movement intentions in an embodiment of the present application;

Figure 2 is a schematic diagram of the propagation path of light intensity signals in biological tissues in an embodiment of the present application;

Figure 3 is a schematic structural diagram of a light collection module in an embodiment of the present application;

Figure 4 is a schematic structural diagram of another light collection module in an embodiment of the present application;

Figure 5 is a schematic structural diagram of another light collection module in an embodiment of the present application;

Figure 6 is a schematic diagram of the circuit structure of an electronic device for collecting and processing multiple light intensity signals in an embodiment of the present application;

Figure 7 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Embodiments of the invention

In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures and technologies are provided to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and/or components but does not exclude one or more other The presence or addition of features, integers, steps, operations, elements, components and/or collections thereof.

It will also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

In addition, in the description of this application and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

Reference in this specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Therefore, the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in other embodiments", etc. appearing in different places in this specification are not necessarily all References to the same embodiment are intended to mean "one or more, but not all, embodiments" unless otherwise specifically emphasized. The terms “including,” “includes,” “having,” and variations thereof all mean “including but not limited to,” unless otherwise specifically emphasized.

Since the deformation caused by muscle contraction contains the movement intention of human limbs, the movement intention of human limbs can be determined by detecting the deformation of human muscles. However, existing near-infrared spectrometers can only detect changes in local muscles of the human body or a single muscle during contraction and deformation, but cannot detect muscle deformation at multiple locations on the muscle deformation site. Changes in the external shape of human muscles are comprehensively affected by changes in multiple muscles. Therefore, the detection results of only local muscles by a near-infrared spectrometer cannot fully reflect the deformation of multiple muscles, which in turn affects the classifier's ability to identify limb movements based on muscle deformation. Intentional accuracy. Therefore, how to improve the accuracy of identifying body movement intentions is an urgent problem that needs to be solved.

The present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

Figure 1 is a schematic flowchart of a method for identifying body movement intentions in an embodiment of the present application. The method for identifying body movement intentions provided by an embodiment of the present application can be executed by an electronic device or a chip in the electronic device. The method includes:

S101, obtain multiple light intensity signals at different locations on the target part of the organism through a light collection module. The light collection module includes: M light sources and N detectors. The M light sources are used to illuminate the target part, and N detectors. The detector is used to receive light intensity signals emitted from different locations on the target part. M is a positive integer, and N is a positive integer greater than 1.

For example, the target parts of the above-mentioned living body can be arms, hands, face, back, chest, legs, etc. This application does not limit this. The user can select the part where muscle deformation needs to be collected according to the specific application scenario. The multiple light intensity signals mentioned above refer to the light intensity signals emitted from different positions of the target part detected by the detector from different positions of the target part. As shown in Figure 2, after the light intensity signal emitted by the light source enters the biological tissue surface (for example, the skin surface of the target site) along the light incident direction, it undergoes multiple scatterings and travels through an irregular arc-shaped optical path along the light path. The emission direction is from the surface of biological tissue. Since the distance S between the light source and the detector determines the depth D that the detector can detect inside the biological tissue (not shown in Figure 2), the detector is controlled to detect different differences in the biological tissue by adjusting the distance S between the light source and the detector. The muscle deformation at depth D, that is, depth D, is related to the distance S between the light source and the detector. The larger S is, the deeper the light intensity signal emitted by the light source is diffused into the muscle, and the deeper the muscle deformation information can be collected by the detector, that is, the larger D is. For example, in Figure 2, the detector is placed at a distance S from the light source. At this time, the detector can detect the light intensity signal scattered from the biological tissue at a depth of D, that is, the detector can detect the muscle at a depth of D in the biological tissue. Deformation conditions. Typically, the depth D is approximately half the distance S.

The above-mentioned electronic device acquires multiple light intensity signals emitted from different locations on the target part through a light collection module; the light collection module includes: M light sources and N detectors, where the M light sources and N detectors form a high-density distribution A plurality of collection channels, the plurality of collection channels are used to collect the above-mentioned multiple light intensity signals. For example, when the target part undergoes muscle deformation, the multiple collection channels of the light collection module can collect light intensity signals from multiple locations on the target part at one time, thus improving the collection efficiency of multiple light intensity signals. For example, M=1, N=2, the light source is placed at position A of the target part, detector 1 is placed at position B near the light source, detector 2 is placed at position C near the light source, the light source and detector 1 form collection channel 1, the light source and detector 2 form collection channel 2. When the light source emits a light intensity signal at the target site, the light intensity signal enters the tissue inside the target site for transmission. Through collection channel 1 (i.e. detector 1) and collection channel 2 (i.e. detector 2) The light intensity signal emitted from the tissue inside the target site can be received at locations B and C of the target site. These light intensity signals emitted from the tissues inside the target site can accurately reflect the deformation of multiple muscles in the target site.

It is hereby explained that the reason why multiple detectors at different positions around light source A can obtain the light intensity signal emitted by light source A from the target site is because multiple detectors at different positions around light source A form multiple collection channels with light source A. , among which, each of the multiple detectors will form a collection channel with the light source A. The light source A is any one of the M light sources. The multiple detectors at different positions around the light source A are N detectors. Multiple detectors.

Exemplarily, the M light sources include a first light source and a second light source. Acquiring multiple light intensity signals at different locations on the target site through the light collection module includes: turning on the first light source; obtaining the first light source at the target through the light collection module. The light intensity signal emitted from the target part; turn off the first light source; turn on the second light source; obtain the light intensity signal emitted by the second light source on the target part through the light collection module. When the target part deforms, the turned on light source illuminates the target part, and within the same period of time, the turned on detector acquires the light intensity signals emitted from different positions of the target part. When acquiring multiple light intensity signals, the above-mentioned light collection module only turns on one light source and multiple detectors around the light source at a time. This can avoid turning on multiple light sources at the same time to form light intensity signal crosstalk at different locations of the target site. For example, when the light collection module acquires multiple light intensity signals, it first turns on the first light source and multiple detectors around the first light source, while other light sources (such as the second light source, the third light source, etc.) are turned off. . At this time, each detector in the plurality of detectors around the first light source and the first light source form a plurality of first collection channels; the plurality of first collection channels are used to obtain the images of the first light source emitted from different positions of the target part. Multiple light intensity signals. After collecting multiple light intensity signals emitted from different locations of the target part when the first light source is turned on, turn off the first light source and turn on the second light source and multiple detectors around the second light source, that is, in addition to the second light source, other light sources are all in a closed state; at this time, each detector in the plurality of detectors around the second light source forms a plurality of second collection channels with the second light source; the plurality of second collection channels are used to obtain the data from the second light source from the target Multiple light intensity signals emitted from different locations of the part. The method of obtaining multiple light intensity signals emitted from different positions of the target part when other light sources are turned on is similar to the method of obtaining multiple light intensity signals emitted from different positions of the target part when the first light source or the second light source is turned on, and will not be described again here. . After acquiring multiple light intensity signals emitted from different locations of the target part when all light sources are turned on, the acquisition of multiple light intensity signals from different locations of the target part by the light collection module is completed.

It can be seen that in this embodiment, the light collection module only turns on one light source (for example, the first light source) at a time when collecting multiple light intensity signals at different positions on the target part, while other light sources (for example, the second light source) Turn off, so that the multiple detectors around the light source only acquire the multiple light intensity signals emitted by the light source from the target site each time, and so on until the multiple light intensity signals emitted by the last light source from the target site are acquired. The reason why all light sources are not turned on at the same time is that turning on all light sources at the same time will cause the light intensity signals emitted by different light sources to be irradiated on the same detector at the same time, causing crosstalk between light intensity signals. This will not only affect multiple light intensity signal response targets. The accuracy of muscle deformation at different parts of the body also affects the accuracy of the electronic device in identifying the intention of limb movement based on the multiple light intensity signals.

Exemplarily, obtaining the light intensity signal emitted by the first light source on the target site through the light collection module includes: obtaining the light intensity signal emitted by the first light source on the target site through K sets of detectors among the N detectors, where , K is an integer greater than 1. The above-mentioned light collection module divides the N detectors into multiple groups of detectors according to the distance between each detector and the light source. Among them, the light intensity signals emitted by the first light source from different positions of the target part can be collected by K groups of detectors. A light source is any one of M light sources.

For example, Figure 3 shows the structure of a light collection module. The light collection module is composed of M=8 light sources and N=7 detectors. In the figure, S1 to S8 represent 8 light sources in sequence, and D1 to D7 in sequence. Indicates 7 detectors, CH1 to CH22 indicates 8 light sources and 7 detectors forming 22 collection channels with high density distribution. For example, S1 and D1 form the collection channel CH1, S4 and D1 form the collection channel CH6, S8 and D7 form Collection channel CH22, etc. The black horizontal line between the light source and the detector in Figure 3 represents the collection channel formed between the light source and the detector. For light source S1, detectors D1 and D3 can be the first group, because D1 and D3 are at the same distance from light source S1 respectively. The collection channel CH1 formed by D1 and S1 and the collection channel CH5 formed by D3 and S1 can detect the target part. Muscle deformation at the same depth. In the same way, D4 and D6 can be the second group, and D7 can be the third group alone; since the first group, the second group, and the third group are all at different distances from the light source, therefore, When the light source S1 is turned on, the first group, the second group and the third group of detectors are turned on at the same time to detect muscle deformation at different depths in the target part. It is also possible to turn on the first set of detectors and the second set of detectors at the same time when turning on the light source S1 to detect muscle deformation at different depths in the target part.

For another example, for light source S4, detectors D1, D3, D4 and D6 can be the first group, because D1, D3, D4 and D6 are at the same distance from light source S4 respectively, and the collection channels CH6 and D3 formed by D1 and S4 The acquisition channel CH10 formed by S4, the acquisition channel CH15 formed by D6 and S4, and the acquisition channel CH11 formed by D4 and S4 can detect the muscle deformation at the same depth in the target part. In the same way, D2 and D7 can be the second group, D5 It can be the third group separately; since the first group, the second group and the third group are all at different distances from the light source, when the light source S4 is turned on, the first group, the second group and the third group of detectors are turned on at the same time. It can detect muscle deformation at different depths in the target part. It is also possible to turn on the first set of detectors and the second set of detectors at the same time when turning on the light source S4 to detect muscle deformation at different depths in the target part.

For another example, for light source S4, detectors D1 and D3 can be divided into the first group, and D4 and D6 into the second group, because D1, D3, D4 and D6 are at the same distance from the light source S4 respectively, and D1 and S4 The acquisition channels formed by CH6, D3 and S4, the acquisition channels formed by CH10, D6 and S4, the acquisition channel CH15 formed by D4 and S4, and the acquisition channel CH11 formed by D4 and S4 can detect the muscle deformation at the same depth in the target part; because the first group and the The two groups are at the same distance from the light source. Therefore, when the light source S4 is turned on, the first group and the second group of detectors are turned on at the same time to detect muscle deformation at the same depth at different locations of the target part. Therefore, users can design according to the application scenario which groups of detectors need to be turned on when each light source is turned on and how to group the detectors around each light source. This application does not impose any restrictions on this.

It can be seen that in this embodiment, compared to using a single detector each time to obtain the light intensity signal emitted at a single position and one depth on the target site, this application uses K groups of detectors to obtain the first light source at the target site at one time. It detects light intensity signals emitted at different positions and at different depths without having to acquire light intensity signals at different locations on the target site multiple times, thereby improving the efficiency of electronic equipment using light collection modules to acquire multiple light intensity signals.

For example, the distance between multiple detectors in any group of detectors in the K group of detectors and the first light source is equal. The above-mentioned light collection module divides the N detectors into multiple groups of detectors according to the distance between each detector and the light source, where the distance between multiple detectors in each group of detectors and the first light source is equal.

For example, as shown in Figure 4, the light collection module includes a light source and eight detectors. The detectors D1, D2, D3 and D4 are distributed on a circle with the light source S1 as the center and a radius of r, while the detector D11 , D22, D33 and D44 are distributed on a circle with light source S1 as the center and radius R. For the light source S1, since the detectors D1, D2, D3 and D4 are at the same distance from the light source S1 respectively, that is, the four collection channels (not shown in Figure 4) formed by D1, D2, D3 and D4 respectively and the light source S1 can be Detect the muscle deformation at the same depth in the target part. Therefore, D1, D2, D3 and D4 can be the first group. Similarly, D11, D22, D33 and D44 can be the second group; each detection in the first group above The distance between the detector and the light source is the same, and the distance between each detector and the light source in the second group is also the same. Therefore, when the light source S1 is turned on, the first set of detectors can be turned on at the same time to detect muscle deformation at the same depth at different positions of the target part; similarly, when the light source S1 is turned on, the second set of detectors can be turned on at the same time to detect different positions of the target part. Muscle deformation at the same depth.

It can be seen that in this embodiment, due to the different distances between the detector and the first light source, the depth detected by the detector will be different. Therefore, if you want to detect the muscle deformation of the target part at the same depth but at different positions, any set of Multiple detectors in the detector need to be equidistant from the first light source, so that the electronic device can identify the intention of the limb movement based on multiple light intensity signals that reflect muscle deformation at the same depth but at different positions of the target site.

For example, multiple detectors in any group of detectors in the K group of detectors are equally spaced, that is, different detectors in the same group of detectors are not only at the same distance from the light source, but also are at the same distance between different detectors. As shown in Figure 4, the arc lengths of detectors D1, D2, D3 and D4 are distributed on a circle with light source S1 as the center and a radius of r; the arc lengths of detectors D11, D22, D33 and D44 are distributed on a circle with light source S1 as the center. is the center of the circle and is on the circumference of radius R. For example, for light source S1, D1, D2, D3 and D4 can evenly acquire light intensity signals at different locations at the same depth of the target part to avoid non-uniform distribution of the detectors, resulting in missing light intensity that reflects the muscle deformation at key locations. signal condition occurs.

For example, the distance between any two groups of detectors in the K group of detectors and the first light source is different. Since muscles are multi-layered structures, for example, the target site has a complex muscle structure, with one layer of muscle in the superficial layer and another layer of muscle in the deeper layer. Therefore, it is necessary to detect muscle deformation information in layers. At this time, the electronic device can detect muscle deformation information at different depths by adding detectors at different distances from each light source in the light collection module shown in Figure 3, as shown in Figure 5, to further improve the recognition of limb movements. intention.

For example, as shown in Figure 5, based on the light collection module shown in Figure 3, another detector is added between each detector and the light source. This can form a new collection channel so that the light collection module can collect more Multiple light intensity signals at different locations of multiple target parts (that is, collecting information on the deformation of more muscles in the target part). The light collection module shown in Figure 5 consists of M=8 light sources and N=29 detectors. In the figure, S1 to S8 represent 8 light sources in sequence, D1 to D29 represent 7 detectors in sequence, and CH1 represents light sources S1 and The collection channel formed by detector D1, CH1' represents the collection channel formed by light source S1 and detector D8, CH5 represents the collection channel formed by light source S1 and detector D3, CH5' represents the collection channel formed by light source S1 and detector D12, Figure The black horizontal line between the light source and the detector in 5 represents the collection channel formed between the light source and the detector. Except for S1, the channel numbers between other light sources and detectors are not shown in Figure 5.

For light source S1, detectors D8 and D12 can be the first group, because D8 and D12 are at the same distance from light source S1 respectively, and the collection channels CH1' and CH2' formed by D8 and S12 with light source S1 can detect the target part. Muscle deformation at the same depth. In the same way, D1 and D3 can be the second group, D17 and D13 can be the third group, D14, D18, D22 and D26 can be the fourth group, and D19, D23 and D27 can be the fifth group. group, D24 and D28 can be the sixth group; since the distance between the first group to the sixth group is getting farther and farther from the light source, and the detector is too far away from the light source, the light intensity signal may not be detected. Therefore, the user can In application scenarios (for example, the target parts are different), when turning on the light source S1, selectively turn on at least one of the first to sixth groups, so that the same depth at different positions of the target part can be obtained (for example, only one set of detection groups is turned on) detector) or at different depths (for example, turning on at least two sets of detectors).

For another example, as shown in Figure 5, for light source S5, detectors D19, D15, D24 and D20 can be the first group, because D19, D15, D24 and D20 are at the same distance from light source S4 respectively. The four acquisition channels formed by D24 and D20 and S4 respectively can detect the muscle deformation at the same depth in the target part. Similarly, D2, D4, D7 and D5 can be the second group; since the first group and the second group are respectively The distances of the light sources are all different. Therefore, when the light source S4 is turned on, the first group and the second group of detectors are turned on at the same time to detect muscle deformation at different depths in the target part.

It can be seen that in this embodiment, since the distance between the detector and the first light source is different, the depth of detection by the detector will be different. Therefore, different groups of detectors in the K group of detectors have different distances from the first light source, and can collect The light intensity signal reflects the muscle deformation at different positions and depths of the target part, so as to improve the accuracy of the electronic device in identifying the intention of limb movement based on the deformation of muscles at different positions and depths.

Exemplarily, the M light sources are M multi-wavelength LED light sources. Since different tissue components have different absorption results for different wavelengths, in order to prevent the light intensity signal detected by the detector from using one wavelength and different tissue components having the same absorption results for this wavelength, which cannot truly reflect the muscle deformation at different locations of the target site, This application uses a multi-wavelength LED light source. The electronic device controls the light source of the light collection module to alternately emit light intensity signals of different wavelengths at preset time intervals. In this way, the detector of the light collection module can collect different wavelengths at different locations of the target part illuminated by different wavelengths. of multiple light intensity signals.

For example, all multi-wavelength LED light sources of the light collection module can emit light intensity signals of two wavelengths. When the target part produces muscle deformation, all LED light sources of the light collection module first illuminate the target part with a light intensity signal of wavelength 1; After all detectors collect multiple light intensity signals of wavelength 1 emitted from different positions of the target part, all LED light sources then illuminate the target part with light intensity signals of wavelength 2, and all detectors continue to collect wavelengths emitted from different positions of the target part. 2 multiple light intensity signals. In this way, the light collection module can collect multiple light intensity signals of different wavelengths at different locations of the target part illuminated by different wavelengths. The electronic device can identify the body movement intention based on the multiple light intensity signals of different wavelengths, which can improve the accuracy of identifying the body movement intention.

It can be seen that in this embodiment, since different tissue components have different absorption results for different wavelengths, the use of multi-wavelength LED light sources can alternately emit light intensity signals of different wavelengths, which can prevent different tissue components from affecting the absorption of different wavelengths when a single wavelength is used. The absorption results of the wavelengths are the same, so the multiple light intensity signals acquired by the detector cannot truly reflect the muscle deformation at different locations of the target part.

Exemplarily, identifying the intention of limb movement based on multiple light intensity signals includes: filtering and feature extraction on multiple light intensity signals to obtain feature extraction results; inputting the feature extraction results into a classifier to obtain the limb movement intention.

For example, as shown in Figure 6, LED1 to LEDn represent light source 1 to light source n, PD1 to PDm represent detector 1 to detector m, where n is a positive integer and m is a positive integer greater than 1; in order to prevent all devices from being turned on at the same time, The light source (i.e., LED1 to LEDn) and all detectors (i.e., PD1 to PDm) cause multiple light intensity signals at different locations of the target site to form crosstalk. The electronic equipment uses a microprocessor to control each light source and each detector in the light collection module. Turning on and off, for example, turning on a light source and multiple corresponding detectors around the light source at a time to obtain multiple light intensity signals at different locations of the target part. The turn-on time of all light sources and all detectors in the light collection module and the detection range of the detectors can be set according to the application scenario, and this application does not limit this. Before the electronic device performs filtering and feature extraction on multiple light intensity signals to obtain the feature extraction results, the electronic device will perform analog-to-digital conversion, signal amplification and other processing on the multiple light intensity signals collected by the light collection module to obtain the amplified Multiple light intensity digital signals; after obtaining multiple light intensity digital signals, the electronic device performs feature extraction process on the multiple light intensity digital signals as follows:

First, the electronic device performs filtering on the collected multiple light intensity digital signals to filter out motion artifact interference. Secondly, the electronic device uses a moving window method to perform feature extraction on the filtered multiple light intensity digital signals, and extracts at least one of the time domain features and frequency domain features of the multiple light intensity digital signals. Specific data analysis windows may or may not overlap. The time domain and frequency domain characteristics of the light intensity digital signal corresponding to each acquisition channel are combined to form the feature vector of the acquisition channel, and the feature vectors of all acquisition channels are combined into the light intensity digital signal feature matrix. The time and frequency domain features that can be used include but are not limited to: amplitude (maximum, mean, variance), rise time, time course, average frequency, median frequency, and time-frequency features (wavelet coefficients, Wegener distribution, entropy, etc.) etc. The electronic device then uses the signal feature data to train a classifier, for example, using Linear Discriminant Analysis Analysis, LDA) to identify and control the spatial posture and action patterns of bionic prosthetics. Finally, feature extraction is performed on multiple light intensity signals collected in real time, and the light intensity digital signal feature matrix formed after feature extraction is input into the trained classifier; the electronic device generates control limbs based on the results of the classifier's recognition of limb movement intentions. Action control instructions are sent to the external device; the external device drives the limb movement after receiving the control instructions.

To sum up, compared with only using a single near-infrared spectrometer (i.e., a single light source and a single detector) to detect the muscle deformation at a single position of the target part, the above method uses multiple detectors distributed at a high density in the light collection module to collect the muscle deformation on the target part. Multiple light intensity signals at different locations (that is, collecting the deformation of muscles at multiple locations (i.e., multiple muscles) on the target part), and identifying limb movement intentions based on the multiple light intensity signals, can improve the identification of limb movement intentions.

Figure 7 shows a schematic structural diagram of an electronic device provided by this application. The dashed line in Figure 7 indicates that the unit or module is optional. The electronic device 700 may be used to implement the method described in the above method embodiment. Electronic device 700 may be a server or a chip.

The electronic device 700 includes one or more processors 701 , and the one or more processors 701 can support the electronic device 700 to implement the method in the method embodiment corresponding to FIG. 1 . Processor 701 may be a general-purpose processor or a special-purpose processor. For example, the processor 701 may be a central processing unit (Central Processing Unit, CPU). The CPU can be used to control the electronic device 700, execute software programs, and process data of the software programs. The electronic device 700 may also include a communication unit 705 to implement input (reception) and output (transmission) of signals.

For example, the electronic device 700 may be a chip and the communication unit 705 may be an input and/or output circuit of the chip, or the communication unit 705 may be a communication interface of the chip and the chip may be an integral part of the electronic device.

For another example, the communication unit 705 may be a transceiver of the electronic device 700 , or the communication unit 705 may be a transceiver circuit of the electronic device 700 .

The electronic device 700 may include one or more memories 702 on which a program 704 is stored. The program 704 may be run by the processor 701 to generate an instruction 703, so that the processor 701 executes the method described in the above method embodiment according to the instruction 703. Optionally, data may also be stored in the memory 702 . Optionally, the processor 701 can also read data stored in the memory 702. The data may be stored at the same storage address as the program 704, or the data may be stored at a different storage address than the program 704.

The processor 701 and the memory 702 can be provided separately or integrated together, for example, on a System On Chip (SOC) of the electronic device.

For the specific manner in which the processor 701 performs the method of identifying body movement intention, please refer to the relevant descriptions in the method embodiments.

It should be understood that each step of the above method embodiment can be completed by a logic circuit in the form of hardware or instructions in the form of software in the processor 701 . The processor 701 may be a CPU, a digital signal processor (Digital Signal Processor) Processor, DSP), Field Programmable Gate Array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

This application also provides a computer program product, which when executed by the processor 701 implements the method described in any method embodiment in this application.

The computer program product may be stored in the memory 702, such as a program 704. The program 704 is finally converted into an executable object file that can be executed by the processor 701 through processes such as preprocessing, compilation, assembly, and linking.

This application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a computer, the method described in any method embodiment of this application is implemented. The computer program may be a high-level language program or an executable object program.

The computer-readable storage medium is memory 702, for example. Memory 702 may be volatile memory or non-volatile memory, or memory 702 may include both volatile memory and non-volatile memory. Among them, non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically removable memory. Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash memory. Volatile memory may be Random Access Memory (RAM), which is used as an external cache. By way of illustration, but not limitation, many forms of RAM are available, such as static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (SynchLink DRAM, SLDRAM) ) and Direct Rambus RAM (DRRAM).

Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes and technical effects produced by the above-described devices and equipment can be referred to the corresponding processes and technical effects in the foregoing method embodiments. Herein No longer.

In the several embodiments provided in this application, the disclosed systems, devices and methods can be implemented in other ways. For example, some features of the method embodiments described above may be omitted, or not performed. The device embodiments described above are only illustrative, and the division of units is only a logical function division. In actual implementation, there may be other division methods, and multiple units or components may be combined or integrated into another system. In addition, the coupling between units or the coupling between components may be direct coupling or indirect coupling, and the above-mentioned coupling includes electrical, mechanical or other forms of connection.

The above-described embodiments are only used to illustrate the technical solution of the present application, but are not intended to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent substitutions for some of the technical features, and these Modifications or substitutions will not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of this application, and shall be included in the protection scope of this application.

Claims

A method for identifying body movement intentions, characterized in that the method includes:

Multiple light intensity signals at different locations on the target part of the organism are obtained through a light collection module, where the light collection module includes: M light sources and N detectors, and the M light sources are used to illuminate the target part. , the N detectors are used to receive light intensity signals emitted from different positions on the target part, the M is a positive integer, and the N is a positive integer greater than 1;

Identify body movement intentions based on the multiple light intensity signals.
The method of claim 1, wherein the M light sources include a first light source and a second light source, and obtaining multiple light intensity signals at different locations on the target site through the light collection module includes:

Turn on the first light source;

Obtain the light intensity signal emitted by the first light source on the target part through the light collection module;

Turn off the first light source;

Turn on the second light source;

The light intensity signal emitted by the second light source on the target site is acquired through the light collection module.
The method according to claim 2, wherein obtaining the light intensity signal emitted by the first light source on the target site through the light collection module includes:

The light intensity signal emitted by the first light source on the target site is acquired through K groups of detectors among the N detectors, where K is an integer greater than 1.
The method according to claim 3, characterized in that the distance between multiple detectors in any one group of detectors in the K groups of detectors and the first light source is equal.
The method according to claim 4, characterized in that multiple detectors in any group of detectors among the K groups of detectors are equally spaced among each other.
The method according to claim 4 or 5, characterized in that any two groups of detectors in the K groups of detectors are at different distances from the first light source.
The method according to any one of claims 1 to 5, characterized in that the M light sources are M multi-wavelength LED light sources.
The method according to any one of claims 1 to 5, characterized in that identifying the body movement intention based on the plurality of light intensity signals includes:

Perform filtering and feature extraction on the multiple light intensity signals to obtain feature extraction results;

The feature extraction results are input into the classifier to obtain the limb movement intention.
An electronic device, characterized in that the electronic device includes a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program from the memory, so that the electronic device The device performs the method of any one of claims 1 to 8.
A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute any one of claims 1 to 8. method described.