CN117351956A - Freight track generation and query method - Google Patents
Freight track generation and query method Download PDFInfo
- Publication number
- CN117351956A CN117351956A CN202311648258.8A CN202311648258A CN117351956A CN 117351956 A CN117351956 A CN 117351956A CN 202311648258 A CN202311648258 A CN 202311648258A CN 117351956 A CN117351956 A CN 117351956A
- Authority
- CN
- China
- Prior art keywords
- voice
- instruction
- keyword
- keywords
- transmitter
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 10
- 230000004044 response Effects 0.000 claims description 26
- 238000012360 testing method Methods 0.000 claims description 16
- 238000013480 data collection Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 238000012549 training Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The invention discloses a freight track generation and query method, which relates to the field of freight transmission and comprises the following steps: the big data establishes a voice recognition reaction mode, and the voice transmitter is controlled through the voice recognition reaction mode; starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, switching a voice transmitter to a corresponding function, and establishing a contact mechanism with a voice processor; under the corresponding function of the voice transmitter, the antenna of the voice transmitter receives the signal transmitted by the voice processor; the voice transmitter microphone receives the audio instruction, and the voice transmitter processes the audio instruction and converts the audio instruction into a signal; and after the communication is finished, starting a voice recognition reaction mode, and acquiring a control instruction. Through setting up big data processing module, big data training module, speech recognition module and speech transmitter control module, can liberate both hands to carry out other operations, and then promote freight transportation management's convenience and intelligent degree.
Description
Technical Field
The invention relates to the field of freight transportation, in particular to a freight track generation and query method.
Background
Transport is first considered as a "third profit source", which is a profit source for the business, the first profit source of the business being an increase in sales of the business, the second profit source being a decrease in production costs or shipping costs, and profit resulting from the decrease in costs being the first profit source of the business. Here, transportation is defined as a distribution of materials, including a series of processes of loading and unloading, transportation, storage, and handling by manufacturers and circulation providers, and importance of freight is raised to a level of cost reduction and profit increase, and the first turn of freight definition is made.
The prior art has the following defects when realizing the management of freight transportation: the input of the freight information can only be manually performed, the freight track is generated according to the freight information, and meanwhile, when the track is inquired, the input is required to be manually performed, and at the moment, if an operator is executing other operations, inconvenience is brought.
Disclosure of Invention
In order to solve the technical problems, the technical scheme provides a freight track generation and query method, and solves the defects of the prior art in the background art that when the management of freight is realized, the following defects are present: the input of the freight information can only be manually performed, the freight track is generated according to the freight information, and meanwhile, when the track is inquired, the input is required to be manually performed, and at the moment, if an operator is executing other operations, the inconvenience is brought.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a freight track generation and query method comprises the following steps:
the method comprises the steps that a voice recognition reaction mode is established for big data, the voice recognition reaction mode comprises a track generation mode and a freight inquiry mode, and a voice transmitter is controlled to realize each function application through the voice recognition reaction mode;
starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, switching the voice transmitter to a corresponding function, and establishing a contact mechanism with a voice processor to realize communication and exchange;
under the corresponding function of the voice transmitter, the antenna of the voice transmitter receives the signal transmitted by the voice processor, the voice transmitter processes the signal and converts the signal into audio, and the speaker of the voice transmitter transmits the audio;
the voice transmitter microphone receives the audio instruction, the voice transmitter processes the audio instruction and converts the audio instruction into a signal, and the voice transmitter transmits the signal through the antenna and transmits the signal to the voice processor for communication interaction;
and after the communication is finished, starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, canceling function switching by the voice transmitter, and disconnecting a contact mechanism with the voice processor.
Preferably, the big data establishing a voice recognition reaction mode includes the following steps:
the big data collection voice transmitter controls keywords related to the instruction, and the collected keywords form a keyword collection package;
carrying out association matching on the keyword set package by the big data to obtain an associated phrase, wherein at least one keyword is arranged in the associated phrase, and the big data is used for distributing a reaction instruction for the associated phrase;
judging the information transmission priority level according to the big data as the related phrase, and carrying out reaction instruction allocation with high information transmission priority level, and carrying out reaction instruction allocation according to queuing sequence at the same level;
the step of judging the information transmission priority level is as follows:
the keywords are scored according to the degree of urgency, the score with high degree of urgency is divided into three, the score with medium degree of urgency is divided into two, and the score with low degree of urgency is divided into one;
calculating an average urgency score of the associated phrase;
average urgency score pertains toThe information transmission priority level of (2) is one level;
average urgency score ofThe information transmission priority level of (2) is two levels;
average urgency score pertains toThe information transmission priority level of (2) is three-level;
the third-level priority is greater than the second-level priority, and the second-level priority is greater than the first-level priority;
the speech recognition reaction pattern is calibrated.
Preferably, the keyword related to the manipulation instruction of the big data collection voice transmitter includes the following steps:
files related to the operation of the voice transmitter in the big data collection network;
extracting operation keywords in a file related to the operation of the voice transmitter from big data;
collecting the number B of the files with keywords in the network, and calculating the probability P that the files are related files of the voice transmitter under the condition that the keywords appear by using a conditional probability formula;
if the probability is greater than 0.7, the keyword is related to the control instruction of the voice transmitter;
if the probability is not more than 0.7, the keyword is not related to the control instruction of the voice transmitter;
the conditional probability formula is as follows:
wherein P is the probability that the file is related to the voice transmitter, A is the number of related files controlled by the voice transmitter in the files with keywords, and B is the number of files with keywords.
Preferably, the step of performing association matching on the keyword set package by the big data into a phrase comprises the following steps:
for any keyword I, collecting a file in which the keyword I appears in big data;
counting keywords in the file in the keyword set package, and marking the keywords as keyword candidate groups;
for any keyword II selected from the keyword candidate group, collecting files in which the keyword II appears in big data, wherein the number of the files is C, and counting the number D of the files in which the keyword I appears in the files;
calculating the conditional probability of the first occurrence of the keyword by using a conditional probability formula;
if the conditional probability is greater than 0.5, the second keyword is a phrase related to the first keyword;
if the conditional probability is not more than 0.5, the second keyword is not a phrase associated with the first keyword;
the conditional probability formula is as follows:
wherein Q is the conditional probability of the first keyword, D is the number of the first keyword in the files, and C is the number of the second keyword.
Preferably, the big data is a reaction instruction for distributing the related phrase, which comprises the following steps;
collecting a reaction instruction commonly used by a voice transmitter, and identifying keywords in the related phrase in the reaction instruction;
if all keywords in the related phrase are identified in the response instruction, the response instruction is distributed to the corresponding related phrase.
Preferably, the calibrating the voice recognition reaction mode includes the steps of:
collecting at least one test instruction by big data, and inputting the test instruction;
the voice recognition reaction mode intelligently recognizes the test instruction, and the voice transmitter is switched to a corresponding function according to the test instruction to establish a contact mechanism with the voice processor;
manually detecting the completion degree of the voice recognition reaction mode to the test instruction;
if the matching degree is higher than 99%, the voice recognition response mode is not corrected;
and if the matching degree is not more than 99%, correcting the voice recognition response mode.
Preferably, the voice recognition reaction mode intelligent recognition control instruction comprises the following steps:
extracting keywords in the operation instruction, wherein the extracted keywords are combined into an identification set;
in order to match the same associated phrase in the recognition set, a reaction instruction allocated to the associated phrase is called, and the reaction instruction is mapped to the recognition set;
the voice transmitter is automatically controlled according to the response instructions mapped to the recognition set.
Preferably, the matching the same associated phrase for the recognition set includes the following steps:
the keywords of the recognition set are arranged, and the keywords in the recognition set are sequentially taken;
for each obtained keyword, searching an associated phrase set containing the keyword, wherein each keyword corresponds to one associated phrase set;
making intersections of all the associated phrase sets to obtain candidate associated phrase sets;
and selecting the associated phrase with the number of the keywords in the associated phrase being consistent with that of the keywords in the recognition set from the associated phrase set, and taking the associated phrase as the associated phrase matched with the recognition set.
Preferably, the automatic control of the voice transmitter according to the reaction instruction mapped to the recognition set includes the following steps:
generating an electrical signal by the reaction instruction mapped to the identification set;
the electric signal is transmitted to a voice transmitter, and the voice transmitter adjusts the parameters according to the control of the electric signal;
the voice transmitter after the parameter adjustment switches the own mode and establishes a contact mechanism with the voice processor.
Compared with the prior art, the invention has the beneficial effects that:
through setting up big data processing module, big data training module, speech recognition module and speech transmitter control module, speech recognition reaction mode through big data training can use speech recognition function to discern operation instruction, use the parameter adjustment of voice transmitter of sound control to control the speech transmitter who is connected with speech transmitter signal, in actual operation, need not artifical manual input freight transportation information or inquiry information, intelligent recognition pronunciation, the freight transportation orbit of formation sea and land combination or carry out the orbit inquiry, can liberate both hands and carry out other operations, and then promote freight transportation management's convenience and intelligent degree.
Drawings
FIG. 1 is a flow chart of a freight track generation and query method of the present invention;
FIG. 2 is a schematic flow chart of a big data set voice recognition reaction mode according to the present invention;
FIG. 3 is a schematic diagram of a keyword flow associated with a command of a big data collection voice transmitter according to the present invention;
FIG. 4 is a schematic diagram of a keyword set package correlation matching process for big data of the present invention;
FIG. 5 is a schematic diagram of a flow of big data assignment reaction instructions for related phrases according to the present invention;
FIG. 6 is a flow chart of the calibration of the voice recognition response mode according to the present invention;
fig. 7 is a schematic diagram of a voice recognition reaction mode intelligent recognition control instruction flow according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, a freight track generation and query method includes:
the method comprises the steps that a voice recognition reaction mode is established for big data, the voice recognition reaction mode comprises a track generation mode and a freight inquiry mode, and a voice transmitter is controlled to realize each function application through the voice recognition reaction mode;
starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, switching the voice transmitter to a corresponding function, and establishing a contact mechanism with a voice processor to realize communication and exchange;
under the corresponding function of the voice transmitter, the antenna of the voice transmitter receives the signal transmitted by the voice processor, the voice transmitter processes the signal and converts the signal into audio, and the speaker of the voice transmitter transmits the audio;
the voice transmitter microphone receives the audio instruction, the voice transmitter processes the audio instruction and converts the audio instruction into a signal, and the voice transmitter transmits the signal through the antenna and transmits the signal to the voice processor for communication interaction;
and after the communication is finished, starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, canceling function switching by the voice transmitter, and disconnecting a contact mechanism with the voice processor.
Referring to fig. 2, the large data set-up voice recognition reaction mode includes the steps of:
the big data collection voice transmitter controls keywords related to the instruction, and the collected keywords form a keyword collection package;
carrying out association matching on the keyword set package by the big data to obtain an associated phrase, wherein at least one keyword is arranged in the associated phrase, and the big data is used for distributing a reaction instruction for the associated phrase;
judging the information transmission priority level according to the big data as the related phrase, and carrying out reaction instruction allocation with high information transmission priority level, and carrying out reaction instruction allocation according to queuing sequence at the same level;
when the parameter of the voice transmitter is adjusted, the module processing which needs to process the adjustment parameter has a sequence, so that the processing sequence needs to be adjusted according to the emergency degree;
the step of judging the information transmission priority level is as follows:
the keywords are scored according to the degree of urgency, the score with high degree of urgency is divided into three, the score with medium degree of urgency is divided into two, and the score with low degree of urgency is divided into one;
calculating an average urgency score of the associated phrase;
the number of keywords in the related phrase is G, and the score of each keyword is overlapped and divided by G to obtain an average urgency score;
average urgency score pertains toThe information transmission priority level of (2) is one level;
average urgency score ofThe information transmission priority level of (2) is two levels;
average urgency score pertains toThe information transmission priority level of (2) is three-level;
the third-level priority is greater than the second-level priority, and the second-level priority is greater than the first-level priority;
the speech recognition reaction pattern is calibrated.
Referring to fig. 3, the key words related to the manipulation instruction of the big data collection voice transmitter include the following steps:
files related to the operation of the voice transmitter in the big data collection network;
extracting operation keywords in a file related to the operation of the voice transmitter from big data;
collecting the number B of the files with keywords in the network, and calculating the probability P that the files are related files of the voice transmitter under the condition that the keywords appear by using a conditional probability formula;
if the probability is greater than 0.7, the keyword is related to the control instruction of the voice transmitter;
if the probability is not more than 0.7, the keyword is not related to the control instruction of the voice transmitter;
the conditional probability formula is as follows:
wherein P is the probability that the file is related to the voice transmitter, A is the number of related files controlled by the voice transmitter in the files with keywords, and B is the number of files with keywords.
In statistics, operation keywords in files related to the operation of the voice transmitter are counted, but the operation keywords are not necessarily high in operation association degree with the voice transmitter, and cannot be used as keywords for insufficient operation keywords, so that the files with the keywords are searched based on the keywords, if the files are not voice transmitter related files, the keywords are not high in association degree with the voice transmitter, and therefore cannot be used as related keywords of the voice transmitter, and if the files are not voice transmitter related files, the keywords are high in association degree with the voice transmitter, and therefore can be used as related keywords of the voice transmitter.
Referring to fig. 4, the association matching of the big data to the keyword set package into the phrase includes the following steps:
for any keyword I, collecting a file in which the keyword I appears in big data;
counting keywords in the file in the keyword set package, and marking the keywords as keyword candidate groups;
for any keyword II selected from the keyword candidate group, collecting files in which the keyword II appears in big data, wherein the number of the files is C, and counting the number D of the files in which the keyword I appears in the files;
calculating the conditional probability of the first occurrence of the keyword by using a conditional probability formula;
if the conditional probability is greater than 0.5, the second keyword is a phrase related to the first keyword;
if the conditional probability is not more than 0.5, the second keyword is not a phrase associated with the first keyword;
the conditional probability formula is as follows:
wherein Q is the conditional probability of the first keyword, D is the number of the first keyword in the files, and C is the number of the second keyword;
for two keywords, whether the two keywords can be matched together or not needs to be judged, otherwise, a large number of related phrases which cannot be used are generated, the related phrases occupy space, but are not in actual instructions;
when the probability of Q is not more than 0.5, the probability of the two simultaneous occurrence is not high, so that the relevance is not high, and the two are not needed to be paired into a phrase.
Referring to fig. 5, the big data is a reaction instruction for distributing the associated phrase, which comprises the following steps;
collecting a reaction instruction commonly used by a voice transmitter, and identifying keywords in the related phrase in the reaction instruction;
if all keywords in the related phrase are identified in the response instruction, the response instruction is distributed to the corresponding related phrase;
and if all the keywords in the associated phrase correspond to the words of the response instruction, the keywords are mutually matched, and the response instruction can be distributed to the corresponding associated phrase.
Referring to fig. 6, calibrating the voice recognition reaction pattern includes the steps of:
collecting at least one test instruction by big data, and inputting the test instruction;
the voice recognition reaction mode intelligently recognizes the test instruction, and the voice transmitter is switched to a corresponding function according to the test instruction to establish a contact mechanism with the voice processor;
manually detecting the completion degree of the voice recognition reaction mode to the test instruction;
if the matching degree is higher than 99%, the voice recognition response mode is not corrected;
if the matching degree is not more than 99%, correcting the voice recognition response mode;
during correction, the related phrase with low completion degree of the test instruction and the response instruction are found out, the mapping between the related phrase and the response instruction is disconnected, the proper response instruction is found again, and the response instruction and the related phrase are re-corresponding.
Referring to fig. 7, the voice recognition reaction mode intelligent recognition manipulation instruction includes the steps of:
extracting keywords in the operation instruction, wherein the extracted keywords are combined into an identification set;
in order to match the same associated phrase in the recognition set, a reaction instruction allocated to the associated phrase is called, and the reaction instruction is mapped to the recognition set;
the voice transmitter is automatically controlled according to the response instructions mapped to the recognition set.
Matching the same associated phrase for the recognition set includes the steps of:
the keywords of the recognition set are arranged, and the keywords in the recognition set are sequentially taken;
for each obtained keyword, searching an associated phrase set containing the keyword, wherein each keyword corresponds to one associated phrase set;
making intersections of all the associated phrase sets to obtain candidate associated phrase sets;
the candidate associated phrases in the candidate associated phrase set all contain keywords of the recognition set, but at the same time, some of the candidate associated phrases also contain other keywords, wherein only exactly one of the candidate associated phrases is completely consistent with the keywords of the recognition set;
and selecting the associated phrase with the number of the keywords in the associated phrase being consistent with that of the keywords in the recognition set from the associated phrase set, and taking the associated phrase as the associated phrase matched with the recognition set.
The voice transmitter automatically controls according to the response instruction mapped to the recognition set, and comprises the following steps:
generating an electrical signal by the reaction instruction mapped to the identification set;
the electric signal is transmitted to a voice transmitter, and the voice transmitter adjusts the parameters according to the control of the electric signal;
the voice transmitter after the parameter adjustment switches the own mode and establishes a contact mechanism with the voice processor.
The voice transmitter processes the audio instructions and converts the audio instructions into signals comprising the steps of:
the microphone of the voice transmitter receives an audio instruction, the audio instruction is converted into an electric signal, the electric signal is amplified and processed, and enters a modulation circuit to be processed by matching with an oscillator to form rated radio frequency power, and the receiving and transmitting band-pass filter suppresses harmonic components in the electric signal and transmits the signal through an antenna.
The voice transmitter processes the signal and converts the signal to audio comprising the steps of:
once the information is received from the antenna, the signal is processed:
mixing an amplified signal from a radio frequency with a first local oscillator signal from a phase locked loop frequency synthesizer circuit at a first mixer and generating a first intermediate frequency signal;
the first intermediate frequency signal further eliminates clutter signals of adjacent channels through a crystal filter, then enters an intermediate frequency processing chip, and is mixed with a second local oscillation signal from a phase-locked loop frequency synthesizer circuit again to generate a second intermediate frequency signal;
the second intermediate frequency signal is amplified and frequency-discriminated after the useless stray signals are filtered by a ceramic filter, and an audio signal is generated;
the audio signal is processed by amplifying, band-pass filter, de-emphasis circuit, etc., and is converted into audio volume control circuit and power amplifier to amplify the audio and drive speaker to play audio.
Still further, the present disclosure provides a storage medium having a computer readable program stored thereon, the computer readable program when invoked performing the freight track generation and query method described above.
It is understood that the storage medium may be a magnetic medium, e.g., floppy disk, hard disk, magnetic tape; optical media such as DVD; or a semiconductor medium such as a solid state disk SolidStateDisk, SSD, etc.
In summary, the invention has the advantages that: through setting up big data processing module, big data training module, speech recognition module and speech transmitter control module, speech recognition reaction mode through big data training can use speech recognition function to discern operation instruction, use the parameter adjustment of voice transmitter of sound control to control the speech transmitter who is connected with speech transmitter signal, in actual operation, need not artifical manual input freight transportation information or inquiry information, intelligent recognition pronunciation, the freight transportation orbit of formation sea and land combination or carry out the orbit inquiry, can liberate both hands and carry out other operations, and then promote freight transportation management's convenience and intelligent degree.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A method for generating and querying a shipping track, comprising:
the method comprises the steps that a voice recognition reaction mode is established by big data, the voice recognition reaction mode comprises a track generation mode and a freight inquiry mode, the track generation mode is composed of sea transportation and land transportation, and a voice transmitter is controlled to realize each function application through the voice recognition reaction mode;
starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, switching the voice transmitter to a corresponding function, and establishing a contact mechanism with a voice processor to realize communication and exchange;
under the corresponding function of the voice transmitter, the antenna of the voice transmitter receives the signal transmitted by the voice processor, the voice transmitter processes the signal and converts the signal into audio, and the speaker of the voice transmitter transmits the audio;
the voice transmitter microphone receives the audio instruction, the voice transmitter processes the audio instruction and converts the audio instruction into a signal, and the voice transmitter transmits the signal through the antenna and transmits the signal to the voice processor for communication interaction;
and after the communication is finished, starting a voice recognition reaction mode, acquiring a control instruction, intelligently recognizing the control instruction by the voice recognition reaction mode, canceling function switching by the voice transmitter, and disconnecting a contact mechanism with the voice processor.
2. The freight trajectory generation and query method of claim 1, wherein the big data establishing a voice recognition reaction pattern comprises the steps of:
the big data collection voice transmitter controls keywords related to the instruction, and the collected keywords form a keyword collection package;
carrying out association matching on the keyword set package by the big data to obtain an associated phrase, wherein at least one keyword is arranged in the associated phrase, and the big data is used for distributing a reaction instruction for the associated phrase;
judging the information transmission priority level according to the big data as the related phrase, and carrying out reaction instruction allocation with high information transmission priority level, and carrying out reaction instruction allocation according to queuing sequence at the same level;
the step of judging the information transmission priority level is as follows:
the keywords are scored according to the degree of urgency, the score with high degree of urgency is divided into three, the score with medium degree of urgency is divided into two, and the score with low degree of urgency is divided into one;
calculating an average urgency score of the associated phrase;
average urgency score pertains toThe information transmission priority level of (2) is one level;
average urgency score ofThe information transmission priority level of (2) is two levels;
average urgency score pertains toThe information transmission priority level of (2) is three-level;
the third-level priority is greater than the second-level priority, and the second-level priority is greater than the first-level priority;
the speech recognition reaction pattern is calibrated.
3. The freight trajectory generation and query method of claim 2, wherein the big data collection voice transmitter manipulation instruction related keywords comprise the steps of:
files related to the operation of the voice transmitter in the big data collection network;
extracting operation keywords in a file related to the operation of the voice transmitter from big data;
collecting the number B of the files with keywords in the network, and calculating the probability P that the files are related files of the voice transmitter under the condition that the keywords appear by using a conditional probability formula;
if the probability is greater than 0.7, the keyword is related to the control instruction of the voice transmitter;
if the probability is not more than 0.7, the keyword is not related to the control instruction of the voice transmitter;
the conditional probability formula is as follows:
wherein P is the probability that the file is related to the voice transmitter, A is the number of related files controlled by the voice transmitter in the files with keywords, and B is the number of files with keywords.
4. A method for generating and querying a freight track according to claim 3, wherein the step of performing association matching on the keyword set package by the big data into a phrase comprises the following steps:
for any keyword I, collecting a file in which the keyword I appears in big data;
counting keywords in the file in the keyword set package, and marking the keywords as keyword candidate groups;
for any keyword II selected from the keyword candidate group, collecting files in which the keyword II appears in big data, wherein the number of the files is C, and counting the number D of the files in which the keyword I appears in the files;
calculating the conditional probability of the first occurrence of the keyword by using a conditional probability formula;
if the conditional probability is greater than 0.5, the second keyword is a phrase related to the first keyword;
if the conditional probability is not more than 0.5, the second keyword is not a phrase associated with the first keyword;
the conditional probability formula is as follows:
wherein Q is the conditional probability of the first keyword, D is the number of the first keyword in the files, and C is the number of the second keyword.
5. The method for generating and querying a freight track according to claim 4, wherein the assigning a reaction instruction to the related phrase by the big data comprises the steps of;
collecting a reaction instruction commonly used by a voice transmitter, and identifying keywords in the related phrase in the reaction instruction;
if all keywords in the related phrase are identified in the response instruction, the response instruction is distributed to the corresponding related phrase.
6. The method of claim 5, wherein calibrating the voice recognition response pattern comprises:
collecting at least one test instruction by big data, and inputting the test instruction;
the voice recognition reaction mode intelligently recognizes the test instruction, and the voice transmitter is switched to a corresponding function according to the test instruction to establish a contact mechanism with the voice processor;
manually detecting the completion degree of the voice recognition reaction mode to the test instruction;
if the matching degree is higher than 99%, the voice recognition response mode is not corrected;
and if the matching degree is not more than 99%, correcting the voice recognition response mode.
7. The method for generating and querying a shipping track according to claim 6, wherein the voice recognition response mode intelligent recognition manipulation instruction comprises the steps of:
extracting keywords in the operation instruction, wherein the extracted keywords are combined into an identification set;
in order to match the same associated phrase in the recognition set, a reaction instruction allocated to the associated phrase is called, and the reaction instruction is mapped to the recognition set;
the voice transmitter is automatically controlled according to the response instructions mapped to the recognition set.
8. The method of claim 7, wherein said matching the same associated phrase for the identified set comprises the steps of:
the keywords of the recognition set are arranged, and the keywords in the recognition set are sequentially taken;
for each obtained keyword, searching an associated phrase set containing the keyword, wherein each keyword corresponds to one associated phrase set;
making intersections of all the associated phrase sets to obtain candidate associated phrase sets;
and selecting the associated phrase with the number of the keywords in the associated phrase being consistent with that of the keywords in the recognition set from the associated phrase set, and taking the associated phrase as the associated phrase matched with the recognition set.
9. The method of claim 8, wherein the voice transmitter automatically controls according to the response command mapped to the recognition set, comprising the steps of:
generating an electrical signal by the reaction instruction mapped to the identification set;
the electric signal is transmitted to a voice transmitter, and the voice transmitter adjusts the parameters according to the control of the electric signal;
the voice transmitter after the parameter adjustment switches the own mode and establishes a contact mechanism with the voice processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311648258.8A CN117351956A (en) | 2023-12-05 | 2023-12-05 | Freight track generation and query method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311648258.8A CN117351956A (en) | 2023-12-05 | 2023-12-05 | Freight track generation and query method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117351956A true CN117351956A (en) | 2024-01-05 |
Family
ID=89357888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311648258.8A Pending CN117351956A (en) | 2023-12-05 | 2023-12-05 | Freight track generation and query method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117351956A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09258774A (en) * | 1996-03-27 | 1997-10-03 | Tadano Ltd | Voice command device for working machine |
| JP2003158586A (en) * | 2001-11-20 | 2003-05-30 | Fujitsu General Ltd | System of reception processing of urgent message and reception processing method |
| KR20100106718A (en) * | 2009-03-24 | 2010-10-04 | 엔에이치엔(주) | System and method for classifying search keyword using cluster for related keyword |
| KR20120089963A (en) * | 2010-12-31 | 2012-08-16 | 엔에이치엔(주) | Method and system for providing reprsentation words of real-time popular keyword |
| US20140244269A1 (en) * | 2013-02-28 | 2014-08-28 | Sony Mobile Communications Ab | Device and method for activating with voice input |
| CN105138523A (en) * | 2014-05-30 | 2015-12-09 | 富士通株式会社 | Method and device for determining semantic keywords in text |
| US20160112554A1 (en) * | 2013-06-26 | 2016-04-21 | Kyocera Corporation | Mobile phone, mobile terminal, and voice operation method |
| US20160117345A1 (en) * | 2014-10-22 | 2016-04-28 | Institute For Information Industry | Service Requirement Analysis System, Method and Non-Transitory Computer Readable Storage Medium |
| CN110415067A (en) * | 2019-06-10 | 2019-11-05 | 天津五八到家科技有限公司 | Ordering method, equipment and storage medium |
| CN110780745A (en) * | 2019-11-15 | 2020-02-11 | 中国船舶工业系统工程研究院 | Ship control man-machine interaction system based on voice recognition |
| WO2020232724A1 (en) * | 2019-05-23 | 2020-11-26 | 深圳博芯科技股份有限公司 | Voice interaction smart bracelet |
-
2023
- 2023-12-05 CN CN202311648258.8A patent/CN117351956A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09258774A (en) * | 1996-03-27 | 1997-10-03 | Tadano Ltd | Voice command device for working machine |
| JP2003158586A (en) * | 2001-11-20 | 2003-05-30 | Fujitsu General Ltd | System of reception processing of urgent message and reception processing method |
| KR20100106718A (en) * | 2009-03-24 | 2010-10-04 | 엔에이치엔(주) | System and method for classifying search keyword using cluster for related keyword |
| KR20120089963A (en) * | 2010-12-31 | 2012-08-16 | 엔에이치엔(주) | Method and system for providing reprsentation words of real-time popular keyword |
| US20140244269A1 (en) * | 2013-02-28 | 2014-08-28 | Sony Mobile Communications Ab | Device and method for activating with voice input |
| US20160112554A1 (en) * | 2013-06-26 | 2016-04-21 | Kyocera Corporation | Mobile phone, mobile terminal, and voice operation method |
| CN105138523A (en) * | 2014-05-30 | 2015-12-09 | 富士通株式会社 | Method and device for determining semantic keywords in text |
| US20160117345A1 (en) * | 2014-10-22 | 2016-04-28 | Institute For Information Industry | Service Requirement Analysis System, Method and Non-Transitory Computer Readable Storage Medium |
| WO2020232724A1 (en) * | 2019-05-23 | 2020-11-26 | 深圳博芯科技股份有限公司 | Voice interaction smart bracelet |
| CN110415067A (en) * | 2019-06-10 | 2019-11-05 | 天津五八到家科技有限公司 | Ordering method, equipment and storage medium |
| CN110780745A (en) * | 2019-11-15 | 2020-02-11 | 中国船舶工业系统工程研究院 | Ship control man-machine interaction system based on voice recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10482903B2 (en) | Method, device and apparatus for selectively interacting with multi-devices, and computer-readable medium | |
| CN101065945B (en) | Method and system for implementing madie content synchronization between portable media player and media host device | |
| CN102103634B (en) | Information processing apparatus and method | |
| CN103280216B (en) | Improve the speech recognition device the relying on context robustness to environmental change | |
| CN110795528A (en) | Data query method and device, electronic equipment and storage medium | |
| US8892565B2 (en) | Method and apparatus for accessing an audio file from a collection of audio files using tonal matching | |
| CA3158353A1 (en) | Audio-outputting method and system thereof | |
| CN100578524C (en) | Appratus and method for changing data of RFID tag in handheld terminal | |
| CN107591155A (en) | Audio recognition method and device, terminal and computer-readable recording medium | |
| CN1316707A (en) | Data compaction and search method and data retieval equipment and recording medium | |
| CN107077510A (en) | A kind of information output method and device | |
| CN107680588A (en) | Intelligent sound air navigation aid, device and storage medium | |
| CN108268637A (en) | A kind of intelligent sound correction recognition methods, device and user terminal | |
| WO2022134110A1 (en) | Speech comprehension method and device | |
| US7319394B2 (en) | Techniques to configure a remote control | |
| CN117351956A (en) | Freight track generation and query method | |
| CN106934918A (en) | The method and apparatus for carrying out bill character recognition using basic corpus auxiliary | |
| CN116153338B (en) | Tuning parameter loading method, device, equipment and storage medium | |
| CN111554329A (en) | Audio editing method, server and storage medium | |
| CN107180027A (en) | Voice command business sorting technique and device | |
| CN104484426A (en) | Multi-mode music searching method and system | |
| JP2004021677A (en) | Information providing system, information providing method, information providing program and computer-readable recording medium recorded with its program | |
| US20090271395A1 (en) | Media file searching system and method for a mobile phone | |
| CN106294567B (en) | Audio sorting method and device | |
| CN117520552B (en) | Policy text processing method, device, equipment and storage medium |
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 |