CN109063595A - A kind of method and device that limb action is converted to computer language - Google Patents
A kind of method and device that limb action is converted to computer language Download PDFInfo
- Publication number
- CN109063595A CN109063595A CN201810768473.4A CN201810768473A CN109063595A CN 109063595 A CN109063595 A CN 109063595A CN 201810768473 A CN201810768473 A CN 201810768473A CN 109063595 A CN109063595 A CN 109063595A
- Authority
- CN
- China
- Prior art keywords
- solid
- motor unit
- meaning
- limb action
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
- Toys (AREA)
Abstract
The present invention provides a kind of method and devices that limb action is converted to computer language, this method comprises: the limb action track of acquisition user；Each motor unit that the limb action track includes is converted into corresponding binary data；For motor unit described in each, corresponding solid is generated according to the corresponding binary data of the motor unit, wherein the solid is used to identify at least one meaning that the motor unit can state, can use part of speech and special method rule；The corresponding solid of each motor unit is combined according to the sequence of the motor unit each in the limb action track, forms solid sequence as the corresponding computer language in the limb action track.The device includes: acquisition unit, converting unit, solid construction unit and solid assembled unit.This programme can be improved the accuracy that limb action is converted to computer language.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of method that limb action is converted into computer language
And device.
Background technique
With the continuous development and progress of image processing techniques, by being acquired to limb action and being converted to computer
The language that can be identified may be implemented to control computer by limb action, be widely used in intelligent appliance control,
The fields such as VR game, sign language interpreter.
Currently, limb action is usually converted to corresponding character when limb action is converted to computer language
String, then the character string according to made of conversion inquires corresponding text information in text library predetermined, realizes limb
Body movement is converted to the text information that computer can identify.
It is corresponding between limb action and text information for the method that limb action is converted to computer language at present
Relationship is pre-defined by program, and identical limb action can be converted into identical text envelope under any scene
Breath, but the meaning that actually identical limb action is stated under different scenes may be not identical.Therefore, by existing by limb
The method that body movement is converted to computer language converts limb action, computer language and limb action made of conversion
Gap between the practical expression meaning is larger, i.e. the accuracy of transformation result is lower.
Summary of the invention
The embodiment of the invention provides a kind of method and devices that limb action is converted to computer language, can be improved
The accuracy of transformation result.
In a first aspect, the embodiment of the invention provides a kind of methods that limb action is converted to computer language, comprising:
Acquire the limb action track of user；
Each motor unit that the limb action track includes is converted into corresponding binary data；
For motor unit described in each, generated according to the corresponding binary data of the motor unit corresponding
Solid, wherein the solid be used to identify at least one meaning that the motor unit can state, can with part of speech and
Special method rule；
Sequence according to the motor unit each in the limb action track is corresponding to each motor unit
The solid is combined, and forms solid sequence as the corresponding computer language in the limb action track.
Optionally,
It is described that corresponding solid is generated according to the corresponding binary data of the motor unit, comprising:
According to the corresponding binary data of the motor unit, inquired from the body language database being pre-created
The corresponding special method rule of at least one meaning and the motor unit that the motor unit can state；
Determine at least one corresponding available part of speech of at least one the described meaning inquired；
Determine at least one the corresponding voice broadcast information of at least one described meaning inquired；
Will at least one described meaning, the feature usage rule, at least one described available part of speech, it is described at least one
For the action sequence of voice broadcast information and the motor unit as 5 nodes, building is in the geometry of cube structure
Body.
Optionally,
After the formation solid sequence is as the corresponding computer language of the movement locus, further comprise:
For each described solid that the solid sequence includes, according to the special method rule to it is described extremely
A few meaning is screened, and determines basic meaning and part of speech that the solid characterizes in the solid sequence, and
Target voice corresponding with the basic meaning is selected to broadcast information from least one described voice broadcast information, wherein
The basic meaning is text information；
For each described solid that the solid sequence includes, the solid is updated, by institute
The basic meaning, part of speech and the target voice casting information of solid characterization are stated remaining 3 as the solid
Node.
Optionally,
It is described the solid is updated after, further comprise:
According to the basic meaning of the solid characterization of each in the solid sequence, determine that the limbs are dynamic
Make the meaning of track characterization；
The meaning characterized according to the limb action track, it is determined whether need to be returned for the limb action track
It answers；
If so, generating corresponding answer solid sequence for the solid sequence, and according to the feedback of setting
The reply message that form includes to the answer solid sequence is fed back.
Optionally,
Described each motor unit for including by the limb action track is converted to corresponding binary data, packet
It includes:
For motor unit described in each, at least one limb action that the motor unit includes is determined, wherein institute
Stating limb action includes upwards, downwards, to the left or to the right；
According to presetting to transformation rule, each described limb action is converted into corresponding binary system generation respectively
Code；
It is corresponding to each limb action according to the sequencing of the limb action each in the motor unit
The two-stage system code carry out sequence combination obtains the corresponding binary data of the motor unit.
Second aspect, the embodiment of the invention also provides a kind of device that limb action is converted to computer language, packets
It includes: acquisition unit, converting unit, solid construction unit and solid assembled unit；
The acquisition unit, for acquiring the limb action track of user；
The converting unit, each for including by the collected limb action track of the acquisition unit are moved
Making cell translation is corresponding binary data；
The solid construction unit is converted for being directed to each described motor unit according to by the converting unit
The corresponding binary data of the motor unit formed generates corresponding solid, wherein the solid is used for
It identifies at least one meaning that the motor unit can state, part of speech and special method rule can be used；
The solid assembled unit, for according to the sequence of the motor unit each in the movement locus to described
The corresponding solid of each motor unit of solid construction unit building is combined, and is formed solid sequence and is made
For the corresponding computer language in the limb action track.
Optionally,
The solid construction unit is specifically used for executing following steps:
According to the corresponding binary data of the motor unit, inquired from the body language database being pre-created
The corresponding special method rule of at least one meaning and the motor unit that the motor unit can state；
Determine at least one corresponding available part of speech of at least one the described meaning inquired；
Determine at least one the corresponding voice broadcast information of at least one described meaning inquired；
Will at least one described meaning, the feature usage rule, at least one described available part of speech, it is described at least one
For the action sequence of voice broadcast information and the motor unit as 5 nodes, building is in the geometry of cube structure
Body.
Optionally,
The device further comprises: solid updating unit；
The solid updating unit, each described solid for including for the solid sequence, according to
The special method rule screens at least one described meaning, determines solid table in the solid sequence
The basic meaning and part of speech of sign, and selection is corresponding with the basic meaning from least one described voice broadcast information
Target voice broadcast information, wherein the basic meaning be text information, and for the solid sequence include it is each
A solid, is updated the solid, the basic meaning that the solid is characterized, part of speech and described
Target voice broadcasts information as remaining 3 nodes of the solid.
Optionally,
The device further comprises: feedback unit:
The feedback unit, for described the containing substantially according to the solid characterization of each in the solid sequence
Justice determines the meaning of the limb action track characterization, and the meaning characterized according to the limb action track, it is determined whether need
It to be responded for the limb action track, if so, generating corresponding answer geometry for the solid sequence
Body sequence, and fed back according to the reply message that the feedback form of setting includes to the answer solid sequence.
Optionally,
The converting unit is specifically used for executing following steps:
For motor unit described in each, at least one limb action that the motor unit includes is determined, wherein institute
Stating limb action includes upwards, downwards, to the left or to the right；
According to presetting to transformation rule, each described limb action is converted into corresponding binary system generation respectively
Code；
It is corresponding to each limb action according to the sequencing of the limb action each in the motor unit
The two-stage system code carry out sequence combination obtains the corresponding binary data of the motor unit.
The method and device provided in an embodiment of the present invention that limb action is converted to computer language, is collecting user
Limb action track after, each motor unit that limb action track includes is converted into corresponding binary data,
Corresponding solid can be generated according to the corresponding binary data of each motor unit respectively later, and then can basis
The sequence of each motor unit is combined the corresponding solid of each motor unit in limb action track, obtains solid
Sequence is as the corresponding computer language in acquired limb action track.Due to according to binary data solid mark generated
At least one meaning that corresponding motor unit can state is known, part of speech and special method rule can have been used, according to special use
Method rule can determine each solid corresponding concrete meaning and part of speech in solid sequence, and then according to each geometry
The corresponding concrete meaning of body and part of speech can determine the meaning that solid sequence is stated, it can according to each solid
Special method rule determines the meaning that limb action track is stated under corresponding scene, so that as the several of computer language
The meaning what body sequence is stated can be more nearly the practical meaning expressed of user's limb action, so as to improve limbs
Movement is converted to the accuracy of computer language.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of process of method that limb action is converted to computer language provided by one embodiment of the present invention
Figure；
Fig. 2 is a kind of structural schematic diagram of solid provided by one embodiment of the present invention；
Fig. 3 is that a kind of device place that limb action is converted to computer language provided by one embodiment of the present invention is set
Standby schematic diagram；
Fig. 4 is a kind of signal of device that limb action is converted to computer language provided by one embodiment of the present invention
Figure；
Fig. 5 is showing for another device that limb action is converted to computer language provided by one embodiment of the present invention
It is intended to；
Fig. 6 be it is provided by one embodiment of the present invention another the device that limb action is converted to computer language is shown
It is intended to.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, the embodiment of the invention provides a kind of method that limb action is converted to computer speech, the party
Method may comprise steps of:
Step 101: acquiring the limb action track of user；
Step 102: each motor unit that limb action track includes is converted into corresponding binary data；
Step 103: being directed to each motor unit, generated according to the corresponding binary data of motor unit corresponding several
He Ti, wherein solid is used to identify at least one meaning that motor unit can state, can be advised with part of speech and special method
Then；
Step 104: according to the sequence of motor unit each in movement locus to the corresponding solid of each motor unit into
Row combination forms solid sequence as the corresponding computer language in limb action track.
The embodiment of the invention provides a kind of methods that limb action is converted to computer language, are collecting user's
Behind limb action track, each motor unit that limb action track includes is converted into corresponding binary data, it
After corresponding solid can be generated according to the corresponding binary data of each motor unit respectively, and then can be according to limb
The sequence of each motor unit is combined the corresponding solid of each motor unit in body movement locus, obtains solid sequence
Column are as the corresponding computer language in acquired limb action track.Due to being identified according to binary data solid generated
At least one meaning that corresponding motor unit can state can use part of speech and special method rule, according to special method
Rule can determine each solid corresponding concrete meaning and part of speech in solid sequence, and then according to each solid
Corresponding concrete meaning and part of speech can determine the meaning that solid sequence is stated, it can according to the spy of each solid
Different usage rule determines the meaning that limb action track is stated under corresponding scene, so that the geometry as computer language
The meaning that body sequence is stated can be more nearly the practical meaning expressed of user's limb action, move limbs so as to improve
Be converted to the accuracy of computer language.
Optionally, on the basis of conversion method shown in Fig. 1, step 103 is according to the corresponding binary data of motor unit
When generating solid, can specifically it be accomplished in that for each motor unit
According to the corresponding binary data of motor unit, the movement list is inquired from the body language database being pre-created
The corresponding special method rule of at least one meaning and the motor unit that member can be stated；
For each meaning that the motor unit can state, at least one corresponding available part of speech of the meaning is determined；
For each meaning that the motor unit can state, determine required when being broadcasted by voice to the meaning
The voice broadcast information wanted；
Each meaning, corresponding special method rule, each meaning that the motor unit can be stated are corresponding each
It can be with part of speech, the corresponding each voice broadcast information of each meaning and the corresponding action sequence of the motor unit respectively as one
A node is in the solid of cube structure using this 5 nodes as 5 nodes building in 8 nodes of cube.
Specifically, for any one motor unit, Fig. 2 characterizes solid corresponding to the motor unit.Wherein, it saves
Point h has recorded each meaning that the motor unit can state, and meaning is recorded with Textual information；It is dynamic that node f has recorded this
Make the corresponding special method rule of unit, such as head shaking movement, some countries indicate negative, and country also indicates to agree
Fixed, the meaning that special method rule identifies motor unit under different scenes is defined；Node b has recorded the movement list
Each meaning corresponding available part of speech, such as verb, noun, pronoun etc. that member can be stated；It is dynamic that node c has recorded this
Make the corresponding language casting information of each meaning that unit can state, for example motor unit can state containing for affirmative
Justice, then the corresponding voice broadcast information of the meaning can be the voice played file of "Yes"；Node g has recorded the motor unit pair
The action sequence answered, such as the motor unit are to move right after moving downward, then after the action sequence of node g record is first lower
It is right.
The information that each motor unit is stated is recorded by one in the solid of cube structure, solid
5 nodes in 8 nodes are recorded as each meaning, the corresponding special method of motor unit that motor unit can state respectively
Rule, the corresponding available part of speech of each meaning, the corresponding voice broadcast information of each meaning and the motor unit are corresponding
Action sequence, according to solid record every terms of information can determine what corresponding actions unit was stated under different scenes
The meaning, and then guarantee that the solid sequence being made of solid can accurately reflect user's limb action meaning to be expressed
Think, and then guarantees that computer can make correct feedback action according to solid sequence.
In the every terms of information that solid is recorded, the meaning of motor unit is text information, can be with a participle or text
Word, voice broadcast information are the audio file that can be played, and action sequence has recorded the action sequence of motor unit, to calculate
Machine can be carried out according to Feedback Rule predetermined by forms such as text output, voice broadcast, control robot motions anti-
Feedback, can satisfy the demand of different user.
In addition, the information for solid record includes that text information, audio-frequency information and action sequence information, computer exist
When making feedback action according to solid, can output character, casting voice or control robot motion according to demand, these are anti-
Feedback can directly be carried out according to the information that solid includes, and without progress information conversion again, for example be not necessarily to text information
Voice broadcast is being carried out after being converted to voice messaging, due to reducing the number of information conversion, it is possible to reduce information conversion process
The problem of middle distortion amplification leads to feedback result bigger error, guarantee the accuracy of feedback result.
Optionally, solid sequence is generated by being combined to solid, and using solid sequence as machine word
After speech, each solid that can include to solid sequence is analyzed, and is tied with each clear solid currently
The meaning stated in fit sequence, for each solid that solid sequence includes, the mistake that it is made a concrete analysis of
Journey can be accomplished in that
The special method rule recorded according to solid, records each meaning to the solid and screens, therefrom really
Make the basic meaning that the solid characterizes in solid sequence；
According to the solid record special method rule, to the solid record the basic meaning it is corresponding it is each can
It is screened with part of speech, determines the corresponding part of speech of the basic meaning；
According to the special method rule of solid record, to the corresponding each language of the basic meaning of solid record
Sound casting information is screened, and determines the corresponding target voice casting information of the basic meaning；
The solid is recorded in the basic meaning determined, the corresponding part of speech of basic meaning, target voice casting information
In on 3 nodes being not used by, realize the update of solid.
Specifically, as shown in Fig. 2, determining the corresponding basic meaning of a solid, the corresponding part of speech of basic meaning
And after target voice casting information, basic meaning is recorded in node e, the corresponding part of speech of basic meaning is recorded in node a,
Target voice casting information is recorded in node d.
By being updated to solid, determine the corresponding basic meaning of solid, the corresponding part of speech of basic meaning with
And target voice broadcasts information, and the basic meaning determined, the corresponding part of speech of basic meaning and target voice are broadcasted and believed
Three nodes as solid are ceased, the 8 of solid node, which records, at this time corresponding information, and solid can be with table
It levies determining meaning (single word or word) and there is determining part of speech, which is uniquely characterized dynamic with limbs
Make the corresponding meaning of scene, so that including that can uniquely to express user's limbs dynamic for the solid sequences of multiple solids
Make the expressed meaning under limb action scene.
Determine that the corresponding basic meaning of solid, basic meaning are corresponding in the special method rule recorded according to solid
Part of speech and target voice casting information when, specifically need to match limb action scene with special method rule, into
And determine meaning, part of speech and target voice casting letter that motor unit corresponding to a solid is stated under limb action scene
Breath, limb action scene includes environment voice messaging, scene geographical location information, scene time information, personage gender information
Deng, and limb action scene can be inputted by user, can also be acquired by various sensors.
In addition, since same word has different parts of speech under different application scenarios, and have under different scenes
There is different articulation types, it is therefore desirable to the part of speech and target voice that basic meaning is recorded in solid broadcast information, with
It can more accurately reflect the meaning that corresponding actions unit is stated.
Optionally, each combination that solid sequence includes is being updated to determine that each solid is stated
The meaning after, can determine the meaning that solid sequence is stated, and make accordingly when there are feedback requirements for solid
Feedback action, detailed process are as follows:
According to the basic meaning that each solid in solid sequence characterizes, determine that limbs corresponding to solid sequence are dynamic
Make the meaning of track characterization；
The meaning characterized according to limb action rule, it is determined whether need to push memory to limb action and respond；
If so, generating corresponding answer solid sequence for solid sequence, and according to preset feedback
Form is answered the reply message that complex analytic geometry body sequence includes and is fed back.
After determining the corresponding basic meaning of each solid and the corresponding part of speech of basic meaning, comprehensive each geometry
Basic meaning corresponding to body and part of speech can determine the meaning that solid sequence is characterized, and determine solid sequence
The voice (statement voice or query voice) of characterized meaning, if the characterized meaning of solid sequence is query voice, needs
Execute corresponding feedback action.It should be noted that in above-mentioned each embodiment, meaning that solid sequence is stated
(meaning) is the meaning (meaning) that the rule of limb action corresponding to solid sequence is stated.
When determination needs to be responded for limb action track, characterized according to solid corresponding to limb action track
Meaning, generate answer solid sequence for being replied the limb action track.Solid sequence is replied equally to wrap
Multiple solids are included, each solid is in cube structure, is stored with corresponding information on 8 nodes of solid.According to
The information that each solid is recorded in solid sequence is replied, it is dynamic that correspondingly feedback can be executed according to answer solid sequence
Make.Specifically, there are basic meaning (text information), corresponding language due to replying each solid in solid sequence and recording
Sound broadcasts information and action sequence, therefore can pass through the different feedback shapes such as text output, voice broadcast, control robot motion
Formula is fed back for limb action track.
According to the meaning that solid sequence is characterized, the answer that can be formed for being replied limb action track is several
What body sequence can be fed back according to solid sequence is replied by the way that text output, voice broadcast, control robot motion etc. are different
Form is responded for limb action track, can be applied to the different technologies such as intelligent appliance control, sign language interpreter, VR game
Field guarantees that this method has stronger applicability.
Optionally, on the basis of conversion method shown in Fig. 1, step 102 moves each that limb action track includes
Making cell translation is corresponding binary data, and detailed process can be accomplished in that
For each motor unit that limb action track includes, at least one limbs that the motor unit includes are determined
Movement, wherein single limb action can be for upwards, downwards, to the left or to the right；
According to preset transformation rule, each limb action is converted into corresponding binary code respectively；
The sequencing that each limb action occurs according to included by motor unit, to each limbs included by motor unit
Corresponding binary code carry out sequence combination is acted, the corresponding binary data of motor unit is obtained.
What the limb action track of user was made of multiple motor units, each motor unit includes one or more
Limb action, limb action are the basic units for forming motor unit, including upward, downward, leftward or rightward.For example, one
Motor unit can first be moved downward for hand and be moved right again, be can also be and only moved downward.
By presetting transformation rule, each limb action for including by motor unit be converted to corresponding two into
Code processed obtains the corresponding binary system of motor unit by being combined to binary code corresponding to each limb action later
Data.For example, transformation rule define the corresponding binary code of upward limb action be 00, downward limb action corresponding two into
Code processed is 11, and the corresponding binary code of limb action is 10 to the left, and the corresponding binary code of limb action is 01 to the right.
If limb action included by a motor unit be to the left-downwards-to the right, the corresponding binary data of the motor unit
It is 101101.
Below by specific example to the method provided in an embodiment of the present invention that limb action is converted to computer language
It is described in further detail, this method may comprise steps of:
S1: by video capturing device, sign language or the active component motion track of other body languages are captured；
S2: recording the displacement information of these active components, converts standardized binary data for displacement information, such as:
00 indicates upwards, and 11 indicate downwards, and 10 indicate to the left, and 01 indicates to the right；
S3: according to the meaning of body language data base querying difference this kind of displacement information of body part, further according to given zone
Domain information corrects the special method of these related meanings；
S4: body language representation manners are serialized, and are carried out space geometric from data space according to syntax rule and are turned
It changes, generates computer gender neutral language solid sequence；
S5: the grammer meaning of the solid sequence in analysis data space, the i.e. basic meaning of the statement, such as: interrogative sentence
It indicates inquiry request, then needs to respond the request；
S6: the ordering relation of analysis solid sequence substitutes into meaning of a word attribute, and analysis special method be associated with etc. with phrase to be believed
Breath, the orientation range of effective information is gradually reduced according to filtering algorithm, finally understands the concrete meaning of the statement；
S7: according to the analysis in S6 as a result, the solid sequence of feedback information is combined into data space, at each
The text, voice, limbs expression method of the participle or text are all contained on solid, are automatically selected accordingly according to feedback form
Information feed back behavior.
As shown in Figure 3, Figure 4, the embodiment of the invention provides a kind of devices that limb action is converted to computer language.
Installation practice can also be realized by software realization by way of hardware or software and hardware combining.From hardware view
For, as shown in figure 3, for equipment where the device provided in an embodiment of the present invention that limb action is converted to computer language
A kind of hardware structure diagram is implemented other than processor shown in Fig. 3, memory, network interface and nonvolatile memory
Equipment in example where device can also include usually other hardware, such as be responsible for the forwarding chip of processing message.With software
For realization, as shown in figure 4, being to be deposited by the CPU of equipment where it by non-volatile as the device on a logical meaning
Corresponding computer program instructions are read into memory what operation was formed in reservoir.It is provided in this embodiment to convert limb action
For the device of computer language, comprising: acquisition unit 401, converting unit 402, solid construction unit 403 and solid combination
Unit 404；
Acquisition unit 401, for acquiring the limb action track of user；
Converting unit 402, each motor unit for including by the collected limb action track of acquisition unit 401
Be converted to corresponding binary data；
Solid construction unit 403, for being directed to each motor unit, according to what is formed by the conversion of converting unit 402
The corresponding binary data of motor unit generates corresponding solid, wherein solid can be with table for identifying motor unit
At least one meaning for stating can use part of speech and special method rule；
Solid assembled unit 404 constructs solid for the sequence according to motor unit each in movement locus single
The corresponding solid of each motor unit of 403 building of member is combined, and forms solid sequence as limb action track pair
The computer language answered.
Optionally, on the basis of the device shown in Fig. 4 that limb action is converted to computer language, solid building is single
Member 403 is specifically used for executing following steps:
According to the corresponding binary data of motor unit, the query actions unit from the body language database being pre-created
The corresponding special method rule of at least one meaning and motor unit that can be stated；
Determine at least one corresponding available part of speech of at least one meaning inquired；
Determine at least one the corresponding voice broadcast information of at least one meaning inquired；
By at least one meaning, feature usage rule, at least one available part of speech, at least one voice broadcast information and
For the action sequence of motor unit as 5 nodes, building is in the solid of cube structure.
Optionally, on the basis of the device shown in Fig. 4 that limb action is converted to computer language, as shown in figure 5, should
Further comprise by the device that limb action is converted to computer language: solid updating unit 505；
Solid updating unit 505, each solid for including for solid sequence, is advised according to special method
Then at least one meaning is screened, determines the basic meaning and part of speech that solid characterizes in solid sequence, and from
Corresponding with basic meaning target voice casting information is selected at least one voice broadcast information, wherein basic meaning is
Text information, and for each solid that solid sequence includes, solid is updated, solid is characterized
Basic meaning, part of speech and target voice casting information as remaining 3 nodes of solid.
Optionally, on the basis of the device shown in Fig. 5 that limb action is converted to computer language, as shown in fig. 6, should
Further comprise by the device that limb action is converted to computer language: feedback unit 606；
Feedback unit 606, the basic meaning for being characterized according to each solid in solid sequence determine that limbs are dynamic
Make track characterization meaning, and according to limb action track characterize meaning, it is determined whether need for limb action track into
Row is responded, if so, generating corresponding answer solid sequence for solid sequence, and according to the feedback form pair of setting
The reply message that solid sequence includes is replied to be fed back.
Optionally, on the basis of fig. 4 to fig. 6 any shown device that limb action is converted to computer language, turn
Unit 402 is changed to be specifically used for executing following steps:
For each motor unit, at least one limb action that motor unit includes is determined, wherein limb action packet
It includes upward, downward, leftward or rightward；
According to presetting to transformation rule, each limb action is converted into corresponding binary code respectively；
According to the sequencing of limb action each in motor unit, to the corresponding two-stage system code of each limb action into
Row sequence combines, and obtains the corresponding binary data of motor unit.
It should be noted that the contents such as information exchange, implementation procedure between each unit in above-mentioned apparatus, due to this
Inventive method embodiment is based on same design, and for details, please refer to the description in the embodiment of the method for the present invention, no longer superfluous herein
It states.
The embodiment of the invention also provides a kind of readable mediums, including execute instruction, when the processor of storage control is held
When executing instruction described in row, what the storage control executed that above-mentioned each embodiment provides is converted to computer for limb action
The method of language.
The embodiment of the invention also provides a kind of storage controls, comprising: processor, memory and bus；
The memory is executed instruction for storing, and the processor is connect with the memory by the bus, when
When the storage control is run, the processor executes the described of memory storage and executes instruction, so that the storage
Controller executes the method that limb action is converted to computer language that above-mentioned each embodiment provides.
In conclusion the method and dress that limb action is converted to computer language that each embodiment of the present invention provides
It sets, at least has the following beneficial effects:
1, in embodiments of the present invention, after collecting the limb action track of user, include by limb action track
Each motor unit is converted to corresponding binary data, later can be respectively according to each motor unit corresponding two
Binary data generates corresponding solid, and then can be according to the sequence of motor unit each in limb action track to each
The corresponding solid of motor unit is combined, and obtains solid sequence as the corresponding computer in acquired limb action track
Language.At least one that can be stated due to identifying corresponding motor unit according to binary data solid generated contains
Justice can use part of speech and special method rule, each solid can be determined in solid sequence according to special method rule
In corresponding concrete meaning and part of speech, and then solid sequence can be determined according to the corresponding concrete meaning of each solid and part of speech
Arrange stated meaning, it can determine limb action track in respective fields according to the special method rule of each solid
The meaning stated under scape, the meaning that the solid sequence as computer language is stated are more nearly user's limb
Body acts the meaning actually expressed, so as to improve the accuracy that limb action is converted to computer language.
2, the information that in embodiments of the present invention, each motor unit is stated is by one in the several of cube structure
What body is recorded, and 5 nodes in 8 nodes of solid are recorded as each meaning that motor unit can state, dynamic respectively
Make the corresponding voice broadcast letter of the corresponding special method rule of unit, the corresponding available part of speech of each meaning, each meaning
Breath and the corresponding action sequence of the motor unit can determine corresponding actions unit according to the every terms of information that solid records
The meaning stated under different scenes, and then guarantee that the solid sequence being made of solid can accurately reflect user's limb
Body acts the meaning to be expressed, and then guarantees that computer can make correct feedback action according to solid sequence.
3, in embodiments of the present invention, in the every terms of information that solid is recorded, the meaning of motor unit is text envelope
Breath can be the audio file that can be played with a participle or text, voice broadcast information, and action sequence has recorded motor unit
Action sequence, thus computer can according to Feedback Rule predetermined pass through text output, voice broadcast, control machine
The forms such as human action are fed back, and can satisfy the demand of different user.
4, in embodiments of the present invention, the information for solid record includes text information, audio-frequency information and movement sequence
Column information, computer when making feedback action according to solid, can according to demand output character, casting voice or control machine
Device human action, these feedbacks can directly be carried out according to the information that solid includes, without progress information conversion again, such as
Without carrying out voice broadcast after text information is converted to voice messaging, due to reducing the number of information conversion, can subtract
The problem of distortion amplification leads to feedback result bigger error in few information conversion process, guarantee the accuracy of feedback result.
5, the meaning in embodiments of the present invention, characterized according to solid sequence can be formed for limb action
The answer solid sequence that track is replied can pass through text output, voice broadcast, control according to solid sequence is replied
The difference feedback form such as robot motion is responded for limb action track, can be applied to intelligent appliance control, sign language
The different technologies fields such as translation, VR game guarantee that this method has stronger applicability.
It should be noted that, in this document, such as first and second etc relational terms are used merely to an entity
Or operation is distinguished with another entity or operation, is existed without necessarily requiring or implying between these entities or operation
Any actual relationship or order.Moreover, the terms "include", "comprise" or its any other variant be intended to it is non-
It is exclusive to include, so that the process, method, article or equipment for including a series of elements not only includes those elements,
It but also including other elements that are not explicitly listed, or further include solid by this process, method, article or equipment
Some elements.In the absence of more restrictions, the element limited by sentence " including one ", is not arranged
Except there is also other identical factors in the process, method, article or apparatus that includes the element.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can store in computer-readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
In the various media that can store program code such as disk.
Finally, it should be noted that the foregoing is merely presently preferred embodiments of the present invention, it is merely to illustrate skill of the invention
Art scheme, is not intended to limit the scope of the present invention.Any modification for being made all within the spirits and principles of the present invention,
Equivalent replacement, improvement etc., are included within the scope of protection of the present invention.
Claims (10)
1. a kind of method that limb action is converted to computer language characterized by comprising
Acquire the limb action track of user；
Each motor unit that the limb action track includes is converted into corresponding binary data；
For motor unit described in each, generated according to the corresponding binary data of the motor unit corresponding several
He Ti, wherein the solid is used to identify at least one meaning that the motor unit can state, can use part of speech and special
Usage rule；
It is corresponding to each motor unit described according to the sequence of the motor unit each in the limb action track
Solid is combined, and forms solid sequence as the corresponding computer language in the limb action track.
2. the method according to claim 1, wherein described according to the corresponding binary system of the motor unit
Data generate corresponding solid, comprising:
According to the corresponding binary data of the motor unit, from the body language database being pre-created described in inquiry
The corresponding special method rule of at least one meaning and the motor unit that motor unit can state；
Determine at least one corresponding available part of speech of at least one the described meaning inquired；
Determine at least one the corresponding voice broadcast information of at least one described meaning inquired；
It will at least one described meaning, the feature usage rule, described at least one available part of speech, at least one described voice
The action sequence of information and the motor unit is broadcasted as 5 nodes, building is in the solid of cube structure.
3. according to the method described in claim 2, it is characterized in that, in the formation solid sequence as the movement locus
After corresponding computer language, further comprise:
For each described solid that the solid sequence includes, according to the special method rule to described at least one
A meaning is screened, and determines basic meaning and part of speech that the solid characterizes in the solid sequence, and from institute
It states and selects target voice casting information corresponding with the basic meaning at least one voice broadcast information, wherein is described
Basic meaning is text information；
For each described solid that the solid sequence includes, the solid is updated, it will be described several
The basic meaning, part of speech and the target voice casting information of what body surface sign are as remaining 3 nodes of the solid.
4. according to the method described in claim 3, it is characterized in that, it is described the solid is updated after, into one
Step includes:
According to the basic meaning of the solid characterization of each in the solid sequence, the limb action rail is determined
The meaning of mark characterization；
The meaning characterized according to the limb action track, it is determined whether need to be responded for the limb action track；
If so, generating corresponding answer solid sequence for the solid sequence, and according to the feedback form of setting
The reply message for including to the answer solid sequence is fed back.
5. according to claim 1 to any method in 4, which is characterized in that described to include by the limb action track
Each motor unit be converted to corresponding binary data, comprising:
For motor unit described in each, at least one limb action that the motor unit includes is determined, wherein the limb
Body movement includes upwards, downwards, to the left or to the right；
According to presetting to transformation rule, each described limb action is converted into corresponding binary code respectively；
It is corresponding to each limb action described according to the sequencing of the limb action each in the motor unit
Two-stage system code carry out sequence combination, obtains the corresponding binary data of the motor unit.
6. a kind of device that limb action is converted to computer language characterized by comprising acquisition unit, converting unit,
Solid construction unit and solid assembled unit；
The acquisition unit, for acquiring the limb action track of user；
The converting unit, each movement for including by the collected limb action track of the acquisition unit are single
Member is converted to corresponding binary data；
The solid construction unit is formed for being directed to each described motor unit according to being converted by the converting unit
The corresponding binary data of the motor unit generate corresponding solid, wherein the solid is for identifying
At least one meaning that the motor unit can state can use part of speech and special method rule；
The solid assembled unit, for according to the sequence of the motor unit each in the movement locus to the geometry
The corresponding solid of each motor unit of body construction unit building is combined, and forms solid sequence as institute
State the corresponding computer language in limb action track.
7. device according to claim 6, which is characterized in that
The solid construction unit is specifically used for executing following steps:
According to the corresponding binary data of the motor unit, from the body language database being pre-created described in inquiry
The corresponding special method rule of at least one meaning and the motor unit that motor unit can state；
Determine at least one corresponding available part of speech of at least one the described meaning inquired；
Determine at least one the corresponding voice broadcast information of at least one described meaning inquired；
It will at least one described meaning, the feature usage rule, described at least one available part of speech, at least one described voice
The action sequence of information and the motor unit is broadcasted as 5 nodes, building is in the solid of cube structure.
8. device according to claim 7, which is characterized in that further comprise: solid updating unit；
The solid updating unit, each described solid for including for the solid sequence, according to described
Special method rule screens at least one described meaning, determines what the solid characterized in the solid sequence
Basic meaning and part of speech, and target corresponding with the basic meaning is selected from least one described voice broadcast information
Voice broadcast information, wherein the basic meaning is text information, and for each institute that the solid sequence includes
Solid is stated, the solid is updated, the basic meaning, part of speech and the target that the solid is characterized
Voice broadcast information is as remaining 3 nodes of the solid.
9. device according to claim 8, which is characterized in that further comprise: feedback unit:
The feedback unit, the basic meaning for being characterized according to the solid of each in the solid sequence,
Determine the meaning of the limb action track characterization, and the meaning characterized according to the limb action track, it is determined whether need
It is responded for the limb action track, if so, generating corresponding answer solid for the solid sequence
Sequence, and fed back according to the reply message that the feedback form of setting includes to the answer solid sequence.
10. according to the device any in claim 6 to 9, which is characterized in that
The converting unit is specifically used for executing following steps:
For motor unit described in each, at least one limb action that the motor unit includes is determined, wherein the limb
Body movement includes upwards, downwards, to the left or to the right；
According to presetting to transformation rule, each described limb action is converted into corresponding binary code respectively；
It is corresponding to each limb action described according to the sequencing of the limb action each in the motor unit
Two-stage system code carry out sequence combination, obtains the corresponding binary data of the motor unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810768473.4A CN109063595B (en) | 2018-07-13 | 2018-07-13 | Method and device for converting limb movement into computer language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810768473.4A CN109063595B (en) | 2018-07-13 | 2018-07-13 | Method and device for converting limb movement into computer language |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109063595A true CN109063595A (en) | 2018-12-21 |
| CN109063595B CN109063595B (en) | 2020-11-03 |
Family
ID=64816398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810768473.4A Active CN109063595B (en) | 2018-07-13 | 2018-07-13 | Method and device for converting limb movement into computer language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063595B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111146654A (en) * | 2019-12-16 | 2020-05-12 | 嵊州市法佳电器有限公司 | Wireless socket for capturing body language |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764890A (en) * | 2003-03-25 | 2006-04-26 | 英国电讯有限公司 | Apparatus for generating behaviour in an object |
| CN102200829A (en) * | 2010-03-24 | 2011-09-28 | 南京大学 | Body movement recognition device used for virtual reality input |
| US20110242305A1 (en) * | 2010-04-01 | 2011-10-06 | Peterson Harry W | Immersive Multimedia Terminal |
| CN105021204A (en) * | 2014-04-24 | 2015-11-04 | 深圳市赛格导航科技股份有限公司 | Non-contact vehicle-mounted navigation system and navigation method |
| CN107783968A (en) * | 2017-11-23 | 2018-03-09 | 浪潮金融信息技术有限公司 | A kind of language transfer method, device, computer-readable recording medium and storage control |
| CN108062533A (en) * | 2017-12-28 | 2018-05-22 | 北京达佳互联信息技术有限公司 | Analytic method, system and the mobile terminal of user's limb action |
-
2018
- 2018-07-13 CN CN201810768473.4A patent/CN109063595B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764890A (en) * | 2003-03-25 | 2006-04-26 | 英国电讯有限公司 | Apparatus for generating behaviour in an object |
| CN102200829A (en) * | 2010-03-24 | 2011-09-28 | 南京大学 | Body movement recognition device used for virtual reality input |
| US20110242305A1 (en) * | 2010-04-01 | 2011-10-06 | Peterson Harry W | Immersive Multimedia Terminal |
| CN105021204A (en) * | 2014-04-24 | 2015-11-04 | 深圳市赛格导航科技股份有限公司 | Non-contact vehicle-mounted navigation system and navigation method |
| CN107783968A (en) * | 2017-11-23 | 2018-03-09 | 浪潮金融信息技术有限公司 | A kind of language transfer method, device, computer-readable recording medium and storage control |
| CN108062533A (en) * | 2017-12-28 | 2018-05-22 | 北京达佳互联信息技术有限公司 | Analytic method, system and the mobile terminal of user's limb action |
Non-Patent Citations (2)
| Title |
|---|
| RAUTARAY, S.S. 等: "Vision based hand gesture recognition for human computer interaction: a survey", 《ARTIFICIAL INTELLIGENCE REVIEW》 * |
| 桑海峰 等: "面向人机交互的快速人体动作识别系统", 《HTTP://KNS.CNKI.NET/KCMS/DETAIL/11.2127.TP.20180620.1050.008.HTML》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111146654A (en) * | 2019-12-16 | 2020-05-12 | 嵊州市法佳电器有限公司 | Wireless socket for capturing body language |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109063595B (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180090132A1 (en) | Voice dialogue system and voice dialogue method | |
| CN109313910A (en) | The constant training of displacement of the more speaker speech separation unrelated for talker | |
| JP6415929B2 (en) | Speech synthesis apparatus, speech synthesis method and program | |
| US20210056950A1 (en) | Presenting electronic communications in narrative form | |
| CN106340308A (en) | Speech reply method and device | |
| WO2019214456A1 (en) | Gesture language translation system and method, and server | |
| JP2016118991A (en) | Image generation device, image generation method, and program | |
| CN106067310A (en) | Recording data processing method and processing device | |
| CN109782997B (en) | Data processing method, device and storage medium | |
| CN105718503A (en) | Voice retrieval apparatus, and voice retrieval method | |
| JP2012043046A (en) | Conference minute creation system and program | |
| CN109063595A (en) | A kind of method and device that limb action is converted to computer language | |
| KR20120129015A (en) | Method for creating educational contents for foreign languages and terminal therefor | |
| CN114048299A (en) | Dialogue method, apparatus, device, computer-readable storage medium, and program product | |
| JP2000231427A (en) | Multi-modal information analyzing device | |
| CN106708789A (en) | Text processing method and device | |
| JP6641045B1 (en) | Content generation system and content generation method | |
| JP2022003447A (en) | Learning method, content reproduction device, and content reproduction system | |
| CN112348932A (en) | Mouth shape animation recording method and device, electronic equipment and storage medium | |
| JP2019057095A (en) | Document generation device, model generation device, calibration device and computer program | |
| WO2017051577A1 (en) | Emotional response inducement system and emotional response inducement method | |
| CN111695670A (en) | Neural network model training method and device | |
| JP6627315B2 (en) | Information processing apparatus, information processing method, and control program | |
| CN108877806A (en) | System is verified in the test for testing instruction type speech control system | |
| JP2019197084A (en) | Sign language cg interpretation and edit system, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210805 Address after: 215100 building 3, Fumin phase III plant, No. 818, Songjia Road, Guoxiang street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Patentee after: INSPUR FINANCIAL INFORMATION TECHNOLOGY Co.,Ltd. Address before: 215100 Building 1, 178 Tayun Road, Yuexi street, Wuzhong District, Suzhou City, Jiangsu Province Patentee before: SUZHOU INSPUR INTELLIGENT SOFTWARE Co.,Ltd. |