Summary of the invention
The main purpose of the present invention is to provide a kind of control methods of massage robot, it is intended to which solution is pressed in the prior art
Rub robot not can accurately, it is effective, allow people to complete effective massaging action in the case where physically and mentally loosening.
To achieve the above object, the present invention provides a kind of control method of massage robot, and the massage robot includes
Massage robot main body, intelligent brain ring and Intelligent bracelet with massage robot main body communication connection, the massager
Device human agent includes massaging manipulator, the control method comprising steps of
The brain wave data obtained according to the E.E.G that preset sample frequency obtains the intelligent brain ring real-time monitoring user;
Judge the frequency of brain wave of the user within the specified sampling period whether less than according to the brain wave data
One preset value;
When the frequency of brain wave of the user is not less than first preset value within the specified sampling period,
The status information for determining the user is commander's state, using the frequency of brain wave of the user as input data, and according to
Preset E.E.G analysis model determines the E.E.G control instruction of the user, sends the E.E.G control instruction described in
Massaging manipulator executes operation corresponding with the E.E.G control instruction to control the massaging manipulator;
When the frequency of brain wave of the user is respectively less than first preset value within the specified sampling period, really
The status information of the fixed user is doubtful sleep state, and the operating state for controlling the massaging manipulator remains unchanged, and is sent out
Send Monitoring instruction to the Intelligent bracelet;
Obtain the obtained physiological data of user described in the Intelligent bracelet real-time monitoring;
Using the brain wave data of the user and the physiological data as input data, pass through neural network model
The User Status identification model of building, obtains the sleep state information of the user;
According to the sleep state information, corresponding massage mode control instruction is determined, send the massage mode control
The massaging manipulator is instructed, executes behaviour corresponding with the massage mode control instruction to control the massaging manipulator
Make.
More preferably, the status information of the user includes commander's state and doubtful sleep state, the doubtful sleep shape
State includes light state, latent meaning state, automatism;
The corresponding brain wave data of the light state is the frequency of brain wave of the user within the specified sampling period
Between the second preset value and the first preset value, wherein second preset value is less than first preset value;
The frequency of brain wave of the latent meaning state is between third preset value and the second preset value, wherein the third is pre-
If value is less than second preset value;
The frequency of brain wave without meaning state is under third preset value.
More preferably, first preset value is between 11 hertz to 13 hertz;
Second preset value is between 7 hertz to 9 hertz;
The third preset value is between 3 hertz to 5 hertz.
More preferably, the physiological data includes the palmic rate data and hand exercise trend data of the user;
It is described using the brain wave data of the user and the physiological data as input data, pass through neural network
The User Status identification model of model construction, the step of obtaining the sleep state information of the user include:
Determine that the user is specific according to value of the frequency of brain wave of the user within the specified sampling period
Doubtful sleep state;
By the palmic rate data, hand exercise trend data and the user, specifically doubtful sleep state is made
For input data, the User Status identification model constructed by neural network model obtains the sleep state letter of the user
Breath, the sleep state information includes awake mode, sleep pattern, deep sleep mode.
More preferably, according to the sleep state information, the step of determining corresponding massage mode control instruction, comprising:
When the sleep state information for detecting the user is awake mode, the massage mode control instruction is determined
For sky, current working condition is kept to continue to operate to control the massaging manipulator;
When the sleep state information for detecting the user is sleep pattern, the massage mode control instruction is determined
For diminuendo instruction, massage force is reduced according to a certain percentage to control the massaging manipulator, until being reduced to the diminuendo
Instruct corresponding minimum massage force;
When the sleep state information for detecting the user is deep sleep mode, the massage mode control is determined
Instruction is halt instruction, is stopped working with controlling the massaging manipulator.
More preferably, the neural network model is by the multilayer feedforward neural network according to the training of error backpropagation algorithm;
The input data is status information, the palmic rate data and the hand exercise trend data of the user;
Output is the sleep state information, including awake mode, sleep pattern, deep sleep mode.
More preferably, in the step of multilayer feedforward neural network, the error reversely relay the calculating process of algorithm by
Positive calculating process and retrospectively calculate process composition;
It is described forward direction calculating process, comprising: sample input data is successively handled through hidden unit layer, and turn to output as a result,
When output result obtains output and preset desired value is not met, it is transferred to retrospectively calculate;
The retrospectively calculate process, comprising: output knot generated when not meeting the output with preset desired value
Fruit, along algorithm backtracking, modifies the weight of each neuron in the neural network model as error signal, described in adjustment
In error signal to default range, the positive calculating process is returned.
More preferably, the circular of the positive calculating process includes:
Wherein, xiFor target signature information, bjFor threshold value, wijFor weight, SjTo export result;
It is that the retrospectively calculate process calculates the result is that threshold value b when+1 sample input data of jth calculatesj+1And power
Value wi(j+1), result reacts on the neural network model.
The present invention also provides a kind of massage robots, including massage robot main body and the massage robot main body to lead to
The intelligent brain ring and Intelligent bracelet, the massage robot main body for believing connection include massaging manipulator, control circuit plate unit
And power supply unit, the control circuit plate unit include communication module, memory, processor and are stored in the memory
In and the computer program that can run on the processor, the processor is realized above-mentioned when executing the computer program
Shopping guide robot control method the step of.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has computer
Program, the computer program realize the step of the control method of above-mentioned intelligent shopping guide robot system when being executed by processor
Suddenly.
In technical solution of the present invention, the E.E.G of intelligent brain ring real-time monitoring user is obtained according to preset sample frequency
Obtained brain wave data;Judge frequency of brain wave within the specified sampling period whether less than the first preset value;If it is not, then by E.E.G
Frequency inputs E.E.G analysis model, determines the E.E.G control instruction of the user, is sent to massaging manipulator and is implemented;
If so, sending Monitoring instruction to Intelligent bracelet;By the physiological data and brain wave data of the user of Intelligent bracelet real-time monitoring
The sleep state information of user is obtained by User Status identification model as input data;Believed according to the sleep state
Breath, determines corresponding massage mode control instruction, is sent to massaging manipulator implementation.Realize massage robot can accurately,
Effectively, people is allowed to complete the technology effectively massaged in the case where physically and mentally loosening.
Specific embodiment
The exemplary embodiment that the present invention will be described in more detail below with reference to accompanying drawings.Although showing the present invention in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here
It is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention
It is fully disclosed to those skilled in the art.
It is all using equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, directly or
It connects and is used in other related technical areas, be included within the scope of the present invention.
Fig. 1 and Fig. 2 are please referred to, provides a kind of massage robot 100, including robot master in a specific embodiment of the invention
Body 1, intelligent brain ring 2 and Intelligent bracelet 3 with 100 main body of massage robot communication connection;The massage robot master
Body 1 includes massaging manipulator 11, control circuit plate unit 13 and power supply unit 12, and the control circuit plate unit 13 includes logical
Believe module 131, memory 132, processor 133 and is stored in the memory 132 and can be transported on the processor 133
Capable computer program.
Wherein, massage robot 100 can carry out the massage work to user by massaging manipulator 11;Intelligent bracelet
2 communicate with massage robot ontology 1 respectively with Intelligent bracelet 3, communicate specifically, can be and pass through with massage robot ontology 1
Module 131 establish it is wired or be wirelessly connected, thus carry out data transmission, message send etc..
Intelligent brain ring 2 and Intelligent bracelet 3 in user's wearing, massage robot 100, which passes through the intelligent acquisition in real time of brain ring 2, to be made
The E.E.G of employment judges the status information of user:
When using artificial commander's state, the user is gone to send control instruction control massaging manipulator 11 with the latent meaning
Movement, including position command and dynamics instruction etc., the position command may include upper and lower, left and right etc., and the dynamics refers to
Order may include exacerbation, diminuendo, stopping etc.;
When using artificial doubtful sleep state, keeps massaging manipulator 11 to act constant, send a command to Intelligent bracelet
3, the physiological data detected by Intelligent bracelet 3, and the physiological data and brain wave data are combined and judge user
Sleep state information, massage robot 100 sends corresponding with sleep state information massage and instructs to massaging manipulator 11.
Specifically, determining the massage mode control when the sleep state information for detecting user is awake mode
Instruction is sky, keeps current working condition to continue to operate to control the massaging manipulator 11;
When the sleep state information for detecting user is sleep pattern, determine that the massage mode control instruction is gradually
Weak instruction reduces massage force to control the massaging manipulator 11 according to a certain percentage, refers to until being reduced to the diminuendo
Enable corresponding minimum massage force;
When the sleep state information for detecting user is deep sleep mode, the massage mode control instruction is determined
For halt instruction, stopped working with controlling the massaging manipulator 11.
Massage robot 100 in this way realizes that accurate, effective, to allow people to complete in the case where physically and mentally loosening effective
Massaging action function.
In the present embodiment, as shown in Fig. 2, the embodiment provides a kind of control method of massage robot 100,
Detailed process is as follows:
Step S1 is obtained according to the E.E.G that preset sample frequency obtains the intelligent 2 real-time monitoring user of brain ring
Brain wave data.
In the step S1, the E.E.G of intelligent 2 real-time monitoring user of brain ring, the processor 133 of massage robot 100 is pressed
Brain wave data is obtained according to certain sample frequency, is stored in memory 132, the sample frequency is the frequency being manually set, as
One preferred example, sample frequency are 2 hertz or more.
Step S2, according to the brain wave data judge the frequency of brain wave of the user within the specified sampling period whether
Less than the first preset value.
Specifically, the processor 133 of massage robot 100 first calculates E.E.G frequency in real time itself in the step S2
Whether rate, calculates the average frequency of E.E.G in the default sampling period, then judge its average frequency less than the first preset value.
Further, first preset value can be between 11 hertz to 13 hertz.
Step S21 is not less than described first in the frequency of brain wave of the user within the specified sampling period
When preset value, determine that the status information of the user is commander's state, using the frequency of brain wave of the user as input number
According to, and according to preset E.E.G analysis model, it determines the E.E.G control instruction of the user, sends the E.E.G control and refer to
The massaging manipulator 11 is enabled, executes operation corresponding with the E.E.G control instruction to control the massaging manipulator 11.
In the step S21, if judge average frequency in the step S2 not less than the first preset value, make described in determination
The status information of employment is commander's state, and the processor 133 determines the user according to preset E.E.G analysis model
E.E.G control instruction, the control instruction includes the position command of upper and lower, left and right etc. and the power of exacerbation, diminuendo, stopping etc.
Degree instruction.The E.E.G control instruction is sent to the massaging manipulator 11, to control the execution of massaging manipulator 11 and institute
State the corresponding operation of E.E.G control instruction.
It is pre- to be respectively less than described first in the frequency of brain wave of the user within the specified sampling period by step S22
If when value, determining that the status information of the user is doubtful sleep state, the operating state for controlling the mechanical massage hand is protected
Hold constant, transmission Monitoring instruction to the Intelligent bracelet 3.
In the step S22, if judge average frequency less than the first preset value in the step S2, the use is determined
The status information of people is doubtful sleep state, and the operating state for controlling the mechanical massage hand remains unchanged, the processor 133
Monitoring instruction is sent to the Intelligent bracelet 3.
Further, the status information of the user includes commander's state and doubtful sleep state, the user's
Doubtful sleep state includes light state, latent meaning state, automatism;
The corresponding brain wave data of the light state is the frequency of brain wave of the user within the specified sampling period
Between the second preset value and the first preset value, wherein second preset value is less than first preset value;
The frequency of brain wave of the latent meaning state is between third preset value and the second preset value, wherein the third is pre-
If value is less than second preset value;
The frequency of brain wave without meaning state is under third preset value.
Further, first preset value is between 11 hertz to 13 hertz, and second preset value is 7 hertz to 9
Between hertz, the third preset value is between 3 hertz to 5 hertz.
Step S3 obtains the obtained physiological data of user described in 3 real-time monitoring of Intelligent bracelet.
In the step S3, the processor 133 of massage robot 100 obtains to be made described in 3 real-time monitoring of Intelligent bracelet
The obtained physiological data of employment is stored in memory 132.
Further, the physiological data includes the palmic rate data and hand exercise trend number of the user
According to;
Step S4 passes through nerve using the brain wave data of the user and the physiological data as input data
The User Status identification model of network model building, obtains the sleep state information of the user.
In the step S4, the processor 133 of massage robot 100 read the brain wave data in memory 132 and
The physiological data calls the User Status identification model constructed by neural network model to defeated using it as input data
Enter data and carry out model evaluation, obtains the sleep state information of the user.
Further, the step S4 can be specifically included:
Step 1: the use is determined according to value of the frequency of brain wave of the user within the specified sampling period
The specific doubtful sleep state of people;
It specifically includes, the frequency of brain wave of the user described in corresponding brain wave data is within the specified sampling period
When between the second preset value and the first preset value, it is confirmed as the light state, wherein second preset value is less than described the
One preset value;
The frequency of brain wave of the user described in corresponding brain wave data is between third preset value and the second preset value
When, it is confirmed as the latent meaning state, wherein the third preset value is less than second preset value;
When the frequency of brain wave of the user described in corresponding brain wave data is under third preset value, it is confirmed as described
Without meaning state.
Further, first preset value is between 11 hertz to 13 hertz, and second preset value is 7 hertz to 9
Between hertz, the third preset value is between 3 hertz to 5 hertz.
Step 2: it doubtful sleeps the palmic rate data, hand exercise trend data and the user are specific
For dormancy state as input data, the User Status identification model constructed by neural network model obtains sleeping for the user
Dormancy status information, the sleep state information include awake mode, sleep pattern, deep sleep mode.
For example, being light state or automatism in doubtful sleep state, the palmic rate data are steady, hand
The regular slight oscillatory of movement tendency data, it is believed that the sleep state information of the user is awake mode, at this moment
It may be user's spirit emptying at this time, and touch finger;In another example being latent meaning state, the heartbeat in doubtful sleep state
Frequency data are palmic rate data when user sleeps, and hand has sudden movement, it is believed that the user's
Sleep state information is sleep pattern;In another example being automatism in doubtful sleep state, the palmic rate data are to make
Palmic rate data when employment is slept, hand have sudden movement and stop quickly, it is believed that the user's sleeps
Dormancy status information is deep sleep mode.
Therefore, the physiological data and brain wave data detected by Intelligent bracelet combines the sleep shape for judging user
State information can reduce erroneous judgement.
Further, the neural network model is by the multilayer feedforward nerve net according to the training of error backpropagation algorithm
Network;The input data is the user specifically doubtful sleep state information, the palmic rate data and the hand
Portion's movement tendency data;Output is the sleep state information, including awake mode, sleep pattern, deep sleep mode.
In a preferable embodiment, the User Status identification model of the neural network model building can lead in advance
It crosses training to obtain, for example, user is allowed to wear intelligent brain ring and intelligence under waking state and doubtful sleep state respectively in advance
Energy bracelet acquires corresponding brain wave data, palmic rate and hand trend, is awake shape by collected data man-made division
State and doubtful sleep state, as initial data training neural network model.
Further, in the step of multilayer feedforward neural network, the error reversely relays the calculating process of algorithm
It is made of positive calculating process and retrospectively calculate process;
It is described forward direction calculating process, comprising: sample input data is successively handled through hidden unit layer, and turn to output as a result,
When output result obtains output and preset desired value is not met, it is transferred to retrospectively calculate;
The retrospectively calculate process, comprising: output knot generated when not meeting the output with preset desired value
Fruit, along algorithm backtracking, modifies the weight of each neuron in the neural network model as error signal, described in adjustment
In error signal to default range, the positive calculating process is returned.
Further, the circular of the positive calculating process includes:
Wherein, xiFor target signature information, bjFor threshold value, wijFor weight, SjTo export result;
It is that the retrospectively calculate process calculates the result is that threshold value b when+1 sample input data of jth calculatesj+1And power
Value wi(j+1), result reacts on the neural network model.
Step S5 determines corresponding massage mode control instruction according to the sleep state information, sends the massage mould
Formula control instruction is executed and the massage mode control instruction to the massaging manipulator 11 with controlling the massaging manipulator 11
Corresponding operation.
The step S5, the sleep state information according to step of processor 133 of massage robot 100, send and its
The corresponding massage mode control instruction of sleep state information is held to the massaging manipulator 11 with controlling the massaging manipulator 11
Row operation corresponding with the massage mode control instruction.
Further, according to the sleep state information, the step of determining corresponding massage mode control instruction, comprising:
When the sleep state information for detecting the user is awake mode, the massage mode control instruction is determined
For sky, current working condition is kept to continue to operate to control the massaging manipulator 11;
When the sleep state information for detecting the user is sleep pattern, the massage mode control instruction is determined
For diminuendo instruction, massage force is reduced according to a certain percentage to control the massaging manipulator 11, until described in being reduced to gradually
It is weak to instruct corresponding minimum massage force;
When the sleep state information for detecting the user is deep sleep mode, the massage mode control is determined
Instruction is halt instruction, is stopped working with controlling the massaging manipulator 11.
Referring again to Fig. 1-Fig. 3, in massage robot 100 provided by the invention, the processor 133 executes the meter
The step of control method of massage robot 100 described in as above any one embodiment is realized when calculation machine program.
There is a kind of computer readable storage medium in the present invention, the computer-readable recording medium storage has computer journey
Sequence realizes the control of massage robot 100 described in as above any one embodiment when the computer program is executed by processor 133
The step of method processed.
Illustratively, the computer program of computer readable storage medium includes computer program code, the computer
Program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer can
Reading medium may include: any entity or device, recording medium, USB flash disk, mobile hard that can carry the computer program code
Disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..
It should be noted that the computer program due to computer readable storage medium is realized when being executed by processor 53
The step of isolation access method for the multi-tenant database stated, therefore all embodiments of the above method are suitable for the computer
Readable storage medium storing program for executing, and can reach the same or similar beneficial effect.
In the description of this specification, reference term " embodiment ", " another embodiment ", " other embodiments " or "
The description of one embodiment~X embodiment " etc. mean specific features described in conjunction with this embodiment or example, structure, material or
Person's feature is included at least one embodiment or example of the invention.In the present specification, to the schematic table of above-mentioned term
Stating may not refer to the same embodiment or example.Moreover, specific features, structure, material, method and step or the spy of description
Point can be combined in any suitable manner in any one or more of the embodiments or examples.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, service
Device, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.