CN109213971A - The generation method and device of court's trial notes - Google Patents
The generation method and device of court's trial notes Download PDFInfo
- Publication number
- CN109213971A CN109213971A CN201710527103.7A CN201710527103A CN109213971A CN 109213971 A CN109213971 A CN 109213971A CN 201710527103 A CN201710527103 A CN 201710527103A CN 109213971 A CN109213971 A CN 109213971A
- Authority
- CN
- China
- Prior art keywords
- court
- trial
- text information
- notes
- software interface
- 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 120
- 238000004458 analytical method Methods 0.000 claims abstract description 51
- 230000008569 process Effects 0.000 claims abstract description 41
- 238000003860 storage Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Technology Law (AREA)
- Acoustics & Sound (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Telephonic Communication Services (AREA)
Abstract
This application discloses the generation methods and device of a kind of court's trial notes.This method comprises: in court trial process, sound collection is carried out by multichannel sound card, obtains multiple voice signals, wherein, the corresponding sound collector of each sound channel on multichannel sound card, each sound collector are used to acquire the voice signal of corresponding court's trial object speech；Each voice signal is sent to speech analysis server, wherein speech analysis server parses the corresponding text information of each voice signal for parsing to each voice signal；Receive the text information that speech analysis server returns；Court's trial notes are generated according to text information in the target area of software interface.By the application, solve the relevant technologies during court trial, the lower problem of record court's trial notes efficiency.
Description
Technical field
This application involves technical field of information processing, in particular to the generation method and device of a kind of court's trial notes.
Background technique
Currently, need the speech information by each role such as judge and party to record during court trial,
It is organized into a court's trial notes after court's trial, is achieved after party signs confirmation.In traditional court trial process, can all it match
One speed clerk, speed clerk records each role speech in entire court trial process, needs after the completion of record according to fixed grating
Formula is organized into court's trial notes.Whole process has certain requirement to the typewriting level of speed clerk, while also needing the case to court's trial
Certain understanding is had in part, has a degree of professional depth to laws and regulations.In the process, due to speed clerk's typewriting speed
It is degree, different to the case degree of understanding, the problems such as it is lower often to will appear record efficiency, misregister, error of omission.The recording at scene
Video recording equipment records video and voice content in real time, retains to data, looked into after facilitating in case of need
It askes and traces.However, although the video and audio recording file of court has recorded the real processes at court's trial scene, but data volume is big, subsequent
It searches and retrospect is compared the cost time, and these data files cannot be directly used to improve the writing speed of court's trial notes, ginseng
It examines and has little significance.
For the relevant technologies during court trial, the lower problem of record court's trial notes efficiency not yet proposes at present
Effective solution scheme.
Summary of the invention
The main purpose of the application is to provide the generation method and device of a kind of court's trial notes, be existed with solving the relevant technologies
During court trial, the lower problem of record court's trial notes efficiency.
To achieve the goals above, according to the one aspect of the application, a kind of generation method of court's trial notes is provided.It should
Method includes: to carry out sound collection in court trial process by multichannel sound card, obtain multiple voice signals, wherein described more
The corresponding sound collector of each sound channel on sound channel sound card, each sound collector is for acquiring corresponding court's trial object hair
The voice signal of speech；Each voice signal is sent to speech analysis server, wherein the speech analysis server is used
It is parsed in each voice signal, parses the corresponding text information of each voice signal；Receive institute's predicate
The text information that sound resolution server returns；Court's trial is generated according to the text information in the target area of software interface
Notes.
Further, generating court's trial notes according to the text information in the target area of the software interface includes:
Case based on court's trial case in the target area of the software interface is by carrying out correction process to the text information；Based on entangling
It is wrong that treated that text information generates the court's trial notes.
Further, the method also includes: receive mark instructions, wherein the mark instructions are used to indicate to described
Target text in the target area of software interface is marked；Based on the mark instructions to the target area of the software interface
Target text in domain is marked.
Further, the method also includes: receive and delete instruction, wherein deletions is instructed and be used to indicate to described
Target text in the target area of software interface is deleted；Instruction is deleted to the target area of the software interface based on described
Target text in domain is deleted.
Further, in court trial process, sound collection is carried out by the sound card of multichannel, obtain multiple voice signals it
Before, the method also includes: obtain text associated with court's trial case；From Text Feature Extraction word associated with court's trial case
It converges, obtains multiple target vocabularies；The multiple target vocabulary is learnt.
Further, described after generating court's trial notes according to the text information in the target area of software interface
Method further include: put down the court's trial that court's trial notes are converted to object format type；Export the object format type
Court's trial notes, alternatively, printing the court's trial notes of the object format type.
Further, after receiving the text information that the speech analysis server returns, in software interface
Before generating court's trial notes according to the text information in target area, the method also includes: the speech analysis is serviced
The text information that device returns is shown in the first area of space of the software interface, wherein first area of space
It is located at the different location of the software interface with the target area；Detect the state of target interface, wherein connect in the target
When the state of mouth is open state, the text information in the first area of space for entering the software interface is sent to described soft
The target area at part interface；Generating court's trial notes according to the text information in the target area of software interface includes: to examine
In the case where the state of the target interface is measured as open state, it will enter in the first area of space of the software interface
Text information is sent to the target area of the software interface；The target area is sent to based on first area of space
Text information generates court's trial notes.
To achieve the goals above, according to the another aspect of the application, a kind of generating means of court's trial notes are provided.It should
Device includes: acquisition unit, for carrying out sound collection by multichannel sound card in court trial process, obtains multiple sound letters
Number, wherein the corresponding sound collector of each sound channel on the multichannel sound card, each sound collector is for acquisition pair
The voice signal for the court's trial object speech answered；Transmission unit, for each voice signal to be sent to speech analysis service
Device, wherein the speech analysis server, which is used to indicate, parses each voice signal, parses each sound
The corresponding text information of sound signal；Receiving unit, the text information returned for receiving the speech analysis server；It is raw
At unit, for generating court's trial notes according to the text information in the target area of software interface.
To achieve the goals above, according to the another aspect of the application, a kind of storage medium, the storage medium are provided
Program including storage, wherein described program executes the generation method of the notes of court's trial described in above-mentioned any one.
To achieve the goals above, according to the another aspect of the application, a kind of processor is provided, the processor is used for
Run program, wherein described program executes the generation method of the notes of court's trial described in above-mentioned any one when running.
By the application, using following steps: in court trial process, carrying out sound collection by multichannel sound card, obtain
Multiple voice signals, wherein the corresponding sound collector of each sound channel on multichannel sound card, each sound collector are used for
Acquire the voice signal of corresponding court's trial object speech；Each voice signal is sent to speech analysis server, wherein voice
Resolution server parses the corresponding text information of each voice signal for parsing to each voice signal；Receive language
The text information that sound resolution server returns；Court's trial notes, solution are generated according to text information in the target area of software interface
The relevant technologies determined during court trial, the lower problem of record court's trial notes efficiency.By the way that collected sound is believed
Number corresponding text information is converted to, notes are generated based on text information, and then has reached the efficiency for promoting record court's trial notes
Effect.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present application, the schematic reality of the application
Example and its explanation are applied for explaining the application, is not constituted an undue limitation on the present application.In the accompanying drawings:
Fig. 1 is the flow chart according to the generation method of court's trial provided by the embodiments of the present application notes；
Fig. 2 is the schematic diagram according to each character location distribution in court scene in the embodiment of the present application；
Fig. 3 is the schematic diagram of sound card in the generation method according to court's trial provided by the embodiments of the present application notes；
Fig. 4 is the schematic diagram of voice signal in the generation method according to court's trial provided by the embodiments of the present application notes；
Fig. 5 is the schematic diagram according to the generation method of optional court's trial notes provided by the embodiments of the present application；And
Fig. 6 is the schematic diagram according to the generating means of court's trial provided by the embodiments of the present application notes.
Specific embodiment
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
For ease of description, below to the invention relates to part noun or term be illustrated:
Court's trial notes are also known as courtroom record or trial record, are law court's judge's indispensable written materials of case, it is
During court trial, by the literature record of the synchronous truth for reflecting whole trial procedures of clerk's production, court's trial
What notes reflected is the whole process of case trial, is the important evidence that law court makes a ruling in accordance with the law, and tried in the future
The important materials of supervision, important function and meaning are apparent.Court's trial notes should reflect objective, true, accurately and in time
The whole show of court's trial.
According to an embodiment of the present application, a kind of generation method of court's trial notes is provided.
Fig. 1 is the flow chart according to the generation method of the court's trial of the embodiment of the present application notes.As shown in Figure 1, this method packet
Include following steps:
Step S101 carries out sound collection by multichannel sound card, obtains multiple voice signals in court trial process,
In, the corresponding sound collector of each sound channel on multichannel sound card, each sound collector is for acquiring corresponding court's trial
The voice signal of object speech.
In this application, it is illustrated by for law court carries out sound collection, the approximate location of each role in court scene
As shown in Figure 2.There is multichannel sound card in court, and sound card is connected on speed clerk's computer, the corresponding microphone of each sound channel on sound card
(corresponding above-mentioned sound collector), sound channel is corresponding with court's trial role relation, and will be if each role according to this corresponded manner
Cylinder is connected to sound card, as shown in Figure 3.When carrying out court's trial, pass through the multiple roles' using microphone of the sound DAQ of multichannel
Sound obtains voice signal, and collected voice signal is one section of Wave data, for example, as shown in Figure 4.
In order to guarantee the sound DAQ by multichannel to voice signal, given birth in notes provided by the embodiments of the present application
At in method, sound collection, before obtaining multiple voice signals, this method are being carried out by multichannel sound card further include: configuration
Corresponding relationship on multichannel sound card between each sound channel and each court's trial object role；According to corresponding relationship, by each court's trial
The corresponding sound collector of object role is attached with each sound channel.
Alternatively, by configuring the corresponding relationship between each court's trial object role and each sound collector；Then according to
Each sound collector sound channel corresponding with each court's trial object role is attached by corresponding relationship.
It should be noted that the notes generation method by the embodiment of the present application can be applied in court's trial software, that is,
The notes generation method of the embodiment of the present application is embedded in court's trial software.Before starting court's trial, which is installed, and
Further this court's trial case can also be arranged in the corresponding relationship that role's sound channel is arranged in software in court's trial software before opening a court session
The information such as part type, notes type, level of trial.It can be with reference to the information being arranged in court's trial software when being subsequently generated notes.
Each voice signal is sent to speech analysis server by step S102, wherein speech analysis server for pair
Each voice signal is parsed, and the corresponding text information of each voice signal is parsed.
Voice signal is parsed in step S102, obtaining the corresponding text information of voice signal can be in sound card end reality
It is existing, voice signal can also be sent to speech analysis server, parse voice signal in speech analysis server end,
Return to the text information parsed.
Before parsing to voice signal, resolution server is needed by the training of a large amount of corpus, optionally, in this Shen
In court trial process, sound collection please be carried out by the sound card of multichannel in the generation method of court's trial notes that provides of embodiment,
Before obtaining multiple voice signals, this method further include: obtain text associated with court's trial case；From related to court's trial case
The Text Feature Extraction vocabulary of connection, obtains multiple target vocabularies；Multiple target vocabularies are learnt.
By being trained study to text associated with court's trial case, it can be promoted and voice signal is parsed
Accuracy.
Step S103 receives the text information that speech analysis server returns.
Step S104 generates court's trial notes according to text information in the target area of software interface.
Through the above steps, the text returned in the target area of software interface according to the speech analysis server received
This information generates court's trial notes.It should be noted that the court's trial notes referred in the embodiment of the present application can also be according to voice solution
The text information that analysis server returns continues growing content, is dynamic change, after court's trial, can sort out a final pen
Record, the literature record as the truth for reflecting whole trial procedures.The relevant technologies are solved during court trial, are remembered
Record the lower problem of court's trial notes efficiency.By sound device and speech recognition technology, the writing speed of court's trial notes is improved
And accuracy, court time is further decreased, efficiency of opening a court session is improved.
Due to parsing to obtain text information by voice signal, it is understood that there may be some literal mistakes will lead to generation
Court's trial notes there is also mistake, in order to guarantee the accuracy of court's trial notes, according to text in the target area of software interface
It includes: case based on court's trial case in the target area of software interface by entangling to text information that information, which generates court's trial notes,
Fault reason；Court's trial notes are generated based on the text information after correction process.
By to the case based on court's trial case by text information carry out correction process；Based on the text envelope after correction process
Breath generates court's trial notes, to guarantee the accuracy of the court's trial generated notes.Before being parsed to voice signal, by right
Text associated with court's trial case is trained study, after generating court's trial notes, can according to the case of court's trial case by
Correction process is carried out to the court's trial notes of generation, to further promote the accuracy of court's trial notes.
Optionally, in the generation method of court's trial provided by the embodiments of the present application notes, this method further include: receive label
Instruction, wherein mark instructions are used to indicate the target text in the target area to software interface and are marked；Referred to based on label
The target text in the target area of software interface is marked in order.
Optionally, in the generation method of court's trial provided by the embodiments of the present application notes, this method further include: receive and delete
Instruction, wherein delete the target text that instruction is used to indicate in the target area to software interface and delete；Referred to based on deletion
The target text in the target area of software interface is deleted in order.
Above-mentioned target text information is the text information for needing to delete, and when receiving deletion instruction, is referred to based on deletion
The target text in the target area of software interface is deleted in order.
Optionally, in the generation method of court's trial provided by the embodiments of the present application notes, in the target area of software interface
After the interior generation court's trial notes according to text information, this method further include: court's trial notes are converted to the front yard of object format type
Examine notes；The court's trial notes of object format type are exported, alternatively, the court's trial notes of printing object format type.
For example, being word format by the Content Transformation of court's trial notes, court's trial notes or the printing of word format are exported as
The court's trial of word format is put down.
Optionally, in the generation method of court's trial provided by the embodiments of the present application notes, speech analysis server is being received
After the text information of return, before generating court's trial notes according to text information in the target area of software interface, this method
Further include: the text information that speech analysis server returns is shown in the first area of space of software interface, wherein first
Area of space and target area are located at the different location of software interface；Detect the state of target interface, wherein in target interface
When state is open state, the text information in the first area of space for entering software interface is sent to the target of software interface
Region；Generating court's trial notes according to text information in the target area of software interface includes: in the shape for detecting target interface
In the case that state is open state, the text information in the first area of space for entering software interface is sent to software interface
Target area；Court's trial notes are generated based on the text information that the first area of space is sent to target area.It is opened in target interface
When, the new text information into the first area of space is also conveyed directly in target area, new to enter when target interface is closed
The text information of first area of space stops transmitting to target area.It should be noted that newly entering the text of the first area of space
This information that is to say the text information of the newest return of speech analysis server.
Specifically, as shown in figure 5, in such a way that hardware and software combines, the sound of spokesman is converted to text,
It is edited using the modification of clerk, is organized into complete notes file.Spokesman against microphone make a speech, sound by microphone into
Row acquisition connects multiple microphones simultaneously by sound card, the sound of different spokesman is distinguish according to sound channel, is being transferred to language
When sound engine, different microphone sources is marked, to carry out the matching of role and text, when guaranteeing multiple roles pronunciation, sound
Orderly is collected, saves and identifies, and is embodied on court's trial notes edit page.By the way that speech analysis server is returned
Text information be shown in the first area of space of software interface, wherein the first area of space and target area are located at software
The different location at interface；It is provided with target interface between first area of space and target area, is to open in the state of target interface
In the case where opening state, the text information in the first area of space for entering software interface is sent to the target area of software interface
Domain；That is, clerk can control the target area whether text information that speech analysis server returns is sent to software interface
Domain, clerk can also on the target area of software interface edit text message.
It should be noted that the text envelope of each court's trial role speech is shown in the first area of space sequentially in time
Breath, in the case where the state of target interface is in off state, can be sent to target area for single text information, that is,
Each single text information is provided with the corresponding switch for importing target area and clicks the switch, i.e., in case of need
Corresponding text information will be switched and be sent to target area.Clerk can also be in suitable position editor's text in target area
This information, for example, the suitable position in target area is inserted into content of text relevant to court's trial case.
In conclusion the generation method of court's trial provided by the embodiments of the present application notes, by court trial process, by more
Sound channel sound card carries out sound collection, obtains multiple voice signals, wherein the corresponding sound of each sound channel on multichannel sound card
Collector, each sound collector are used to acquire the voice signal of corresponding court's trial object speech；Each voice signal is sent
To speech analysis server, wherein speech analysis server parses each sound for parsing to each voice signal
The corresponding text information of signal；Receive the text information that speech analysis server returns；The root in the target area of software interface
Court's trial notes are generated according to text information, solve the relevant technologies during court trial, record court's trial notes efficiency is lower
Problem.By the way that collected voice signal is converted to corresponding text information, notes are generated based on text information, and then reach
Promote the effect of the efficiency of record court's trial notes.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
The embodiment of the present application also provides a kind of generating means of court's trial notes, it should be noted that the embodiment of the present application
The generating means of court's trial notes can be used for executing the generation method provided by the embodiment of the present application for court's trial notes.With
Under to court's trial provided by the embodiments of the present application notes generating means be introduced.
Fig. 6 is the schematic diagram according to the generating means of the court's trial of the embodiment of the present application notes.As shown in fig. 6, the device packet
It includes: acquisition unit 10, transmission unit 20, receiving unit 30 and generation unit 40.
Specifically, acquisition unit 10, for carrying out sound collection by multichannel sound card, obtaining more in court trial process
A voice signal, wherein the corresponding sound collector of each sound channel on multichannel sound card, each sound collector is for adopting
Collect the voice signal of corresponding court's trial object speech.
Transmission unit 20, for each voice signal to be sent to speech analysis server, wherein speech analysis server
It is used to indicate and each voice signal is parsed, parse the corresponding text information of each voice signal.
Receiving unit 30, for receiving the text information of speech analysis server return.
Generation unit 40, for generating court's trial notes according to text information in the target area of software interface.
The generating means of court's trial notes provided by the embodiments of the present application pass through through acquisition unit 10 in court trial process
Multichannel sound card carries out sound collection, obtains multiple voice signals, wherein the corresponding sound of each sound channel on multichannel sound card
Sound collector, each sound collector are used to acquire the voice signal of corresponding court's trial object speech；Transmission unit 20 will be each
Voice signal is sent to speech analysis server, wherein speech analysis server, which is used to indicate, solves each voice signal
Analysis, parses the corresponding text information of each voice signal；Receiving unit 30 receives the text envelope that speech analysis server returns
Breath；Generation unit 40 generates court's trial notes according to text information in the target area of software interface, solves the relevant technologies and exists
During court trial, the lower problem of record court's trial notes efficiency is corresponding by being converted to collected voice signal
Text information generates notes based on text information, and then has achieved the effect that the efficiency for promoting record court's trial notes.
The generating means of court's trial notes include processor and memory, above-mentioned acquisition unit 10, and transmission unit 20 connects
It receives unit 30 and generation unit 40 etc. to store in memory as program unit, storage is executed in memory by processor
Above procedure unit realize corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, it is put down by adjusting kernel parameter to generate court's trial.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
The embodiment of the invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The generation method of the existing court's trial notes.
The embodiment of the invention provides a kind of processor, the processor is for running program, wherein described program operation
The generation method of the notes of court's trial described in Shi Zhihang.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor perform the steps of in court trial process when executing program, pass through multichannel sound card
Sound collection is carried out, multiple voice signals are obtained, wherein the corresponding sound collector of each sound channel on multichannel sound card,
Each sound collector is used to acquire the voice signal of corresponding court's trial object speech；Each voice signal is sent to voice solution
Analyse server, wherein it is corresponding to parse each voice signal for parsing to each voice signal for speech analysis server
Text information；Receive the text information that speech analysis server returns；According to text envelope in the target area of software interface
Breath generates court's trial notes.
Generating court's trial notes according to text information in the target area of software interface includes: in the target area of software interface
Case based on court's trial case in domain is by carrying out correction process to text information；Court's trial is generated based on the text information after correction process
Notes.
This method further include: receive mark instructions, wherein mark instructions are used to indicate in the target area to software interface
Target text be marked；The target text in the target area of software interface is marked based on mark instructions.
This method further include: receive and delete instruction, wherein delete instruction and be used to indicate in the target area to software interface
Target text deleted；The target text in the target area of software interface is deleted based on instruction is deleted.
In court trial process, sound collection, before obtaining multiple voice signals, this method are carried out by the sound card of multichannel
Further include: obtain text associated with court's trial case；From Text Feature Extraction vocabulary associated with court's trial case, multiple mesh are obtained
Mark vocabulary；Multiple target vocabularies are learnt.
After generating court's trial notes according to text information in the target area of software interface, this method further include: by front yard
It is careful to put down the court's trial notes for being converted to object format type；The court's trial notes of object format type are exported, alternatively, printing target lattice
The court's trial of formula type is put down.
After receiving the text information that speech analysis server returns, according to text in the target area of software interface
Before information generates court's trial notes, this method further include: show the text information that speech analysis server returns in software circle
In first area of space in face, wherein the first area of space is located at the different location of software interface with target area；Detect target
The state of interface, wherein when the state of target interface is open state, will enter in the first area of space of software interface
Text information is sent to the target area of software interface；Court's trial pen is generated according to text information in the target area of software interface
Record includes: that will enter the first area of space of software interface in the case where detecting the state of target interface is open state
Interior text information is sent to the target area of software interface；The text information of target area is sent to based on the first area of space
Generate court's trial notes.Equipment herein can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step: in court trial process, sound collection is carried out by multichannel sound card, obtains multiple sound
Signal, wherein the corresponding sound collector of each sound channel on multichannel sound card, each sound collector is for acquiring correspondence
Court's trial object speech voice signal；Each voice signal is sent to speech analysis server, wherein speech analysis service
Device parses the corresponding text information of each voice signal for parsing to each voice signal；Receive speech analysis clothes
The text information that business device returns；Court's trial notes are generated according to text information in the target area of software interface.
Generating court's trial notes according to text information in the target area of software interface includes: in the target area of software interface
Case based on court's trial case in domain is by carrying out correction process to text information；Court's trial is generated based on the text information after correction process
Notes.
This method further include: receive mark instructions, wherein mark instructions are used to indicate in the target area to software interface
Target text be marked；The target text in the target area of software interface is marked based on mark instructions.
This method further include: receive and delete instruction, wherein delete instruction and be used to indicate in the target area to software interface
Target text deleted；The target text in the target area of software interface is deleted based on instruction is deleted.
In court trial process, sound collection, before obtaining multiple voice signals, this method are carried out by the sound card of multichannel
Further include: obtain text associated with court's trial case；From Text Feature Extraction vocabulary associated with court's trial case, multiple mesh are obtained
Mark vocabulary；Multiple target vocabularies are learnt.
After generating court's trial notes according to text information in the target area of software interface, this method further include: by front yard
It is careful to put down the court's trial notes for being converted to object format type；The court's trial notes of object format type are exported, alternatively, printing target lattice
The court's trial of formula type is put down.
After receiving the text information that speech analysis server returns, according to text in the target area of software interface
Before information generates court's trial notes, this method further include: show the text information that speech analysis server returns in software circle
In first area of space in face, wherein the first area of space is located at the different location of software interface with target area；Detect target
The state of interface, wherein when the state of target interface is open state, will enter in the first area of space of software interface
Text information is sent to the target area of software interface；Court's trial pen is generated according to text information in the target area of software interface
Record includes: that will enter the first area of space of software interface in the case where detecting the state of target interface is open state
Interior text information is sent to the target area of software interface；The text information of target area is sent to based on the first area of space
Generate court's trial notes.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of generation method of court's trial notes characterized by comprising
In court trial process, sound collection is carried out by multichannel sound card, obtains multiple voice signals, wherein the multichannel
The corresponding sound collector of each sound channel on sound card, each sound collector are used to acquire corresponding court's trial object speech
Voice signal；
Each voice signal is sent to speech analysis server, wherein the speech analysis server is used for each
The voice signal is parsed, and the corresponding text information of each voice signal is parsed；
Receive the text information that the speech analysis server returns；
Court's trial notes are generated according to the text information in the target area of software interface.
2. the method according to claim 1, wherein according to the text in the target area of the software interface
This information generates court's trial notes
Case based on court's trial case in the target area of the software interface is by carrying out correction process to the text information；
The court's trial notes are generated based on the text information after correction process.
3. the method according to claim 1, wherein the method also includes:
Receive mark instructions, wherein the mark instructions are used to indicate the text of the target in the target area to the software interface
Originally it is marked；
The target text in the target area of the software interface is marked based on the mark instructions.
4. the method according to claim 1, wherein the method also includes:
It receives and deletes instruction, wherein the target text deleting instruction and being used to indicate in the target area to the software interface
This is deleted；
The target text in the target area of the software interface is deleted based on deletion instruction.
5. the method according to claim 1, wherein passing through the sound card carry out sound of multichannel in court trial process
Sound acquisition, before obtaining multiple voice signals, the method also includes:
Obtain text associated with court's trial case；
From Text Feature Extraction vocabulary associated with court's trial case, multiple target vocabularies are obtained；
The multiple target vocabulary is learnt.
6. the method according to claim 1, wherein according to the text envelope in the target area of software interface
After breath generates court's trial notes, the method also includes:
Court's trial notes are converted to the court's trial notes of object format type；
The court's trial notes of the object format type are exported, alternatively, printing the court's trial notes of the object format type.
7. the method according to claim 1, wherein
After receiving the text information that the speech analysis server returns, the basis in the target area of software interface
Before the text information generates court's trial notes, the method also includes:
The text information that the speech analysis server returns is shown in the first area of space of the software interface,
Wherein, first area of space and the target area are located at the different location of the software interface；
Detect the state of target interface, wherein when the state of the target interface is open state, software circle will be entered
Text information in first area of space in face is sent to the target area of the software interface；
Generating court's trial notes according to the text information in the target area of software interface includes: to detect that the target connects
In the case that the state of mouth is open state, the text information entered in the first area of space of the software interface is sent to
The target area of the software interface；
Court's trial notes are generated based on the text information that first area of space is sent to the target area.
8. a kind of generating means of court's trial notes characterized by comprising
Acquisition unit, for carrying out sound collection by multichannel sound card, obtaining multiple voice signals in court trial process,
In, the corresponding sound collector of each sound channel on the multichannel sound card, each sound collector is used to acquire corresponding
The voice signal of court's trial object speech；
Transmission unit, for each voice signal to be sent to speech analysis server, wherein the speech analysis service
Device, which is used to indicate, parses each voice signal, parses the corresponding text information of each voice signal；
Receiving unit, the text information returned for receiving the speech analysis server；
Generation unit, for generating court's trial notes according to the text information in the target area of software interface.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 7 described in court's trial notes generation method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 7 described in court's trial notes generation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710527103.7A CN109213971A (en) | 2017-06-30 | 2017-06-30 | The generation method and device of court's trial notes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710527103.7A CN109213971A (en) | 2017-06-30 | 2017-06-30 | The generation method and device of court's trial notes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109213971A true CN109213971A (en) | 2019-01-15 |
Family
ID=64991556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710527103.7A Pending CN109213971A (en) | 2017-06-30 | 2017-06-30 | The generation method and device of court's trial notes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109213971A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110660395A (en) * | 2019-08-26 | 2020-01-07 | 天津开心生活科技有限公司 | Safety report generation method and device based on voice recognition |
| CN114255760A (en) * | 2021-12-15 | 2022-03-29 | 江苏税软软件科技有限公司 | Inquiry recording system and method |
| CN114462376A (en) * | 2022-02-16 | 2022-05-10 | 来也科技(北京)有限公司 | RPA and AI-based court trial record generation method, device, equipment and medium |
| CN115662437A (en) * | 2022-12-28 | 2023-01-31 | 广州市保伦电子有限公司 | Voice transcription method under scene of simultaneous use of multiple microphones |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5369704A (en) * | 1993-03-24 | 1994-11-29 | Engate Incorporated | Down-line transcription system for manipulating real-time testimony |
| CN1585018A (en) * | 2004-06-15 | 2005-02-23 | 梁国雄 | Comptuer recoding information system for court |
| CN101206673A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Intelligent error correcting system and method in network searching process |
| CN101803214A (en) * | 2007-09-12 | 2010-08-11 | 微软公司 | The speech-to-text transcription that is used for the personal communication devices |
| CN105575402A (en) * | 2015-12-18 | 2016-05-11 | 合肥寰景信息技术有限公司 | Network teaching real time voice analysis method |
| CN106782551A (en) * | 2016-12-06 | 2017-05-31 | 北京华夏电通科技有限公司 | A kind of speech recognition system and method |
-
2017
- 2017-06-30 CN CN201710527103.7A patent/CN109213971A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5369704A (en) * | 1993-03-24 | 1994-11-29 | Engate Incorporated | Down-line transcription system for manipulating real-time testimony |
| CN1585018A (en) * | 2004-06-15 | 2005-02-23 | 梁国雄 | Comptuer recoding information system for court |
| CN101803214A (en) * | 2007-09-12 | 2010-08-11 | 微软公司 | The speech-to-text transcription that is used for the personal communication devices |
| CN101206673A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Intelligent error correcting system and method in network searching process |
| CN105575402A (en) * | 2015-12-18 | 2016-05-11 | 合肥寰景信息技术有限公司 | Network teaching real time voice analysis method |
| CN106782551A (en) * | 2016-12-06 | 2017-05-31 | 北京华夏电通科技有限公司 | A kind of speech recognition system and method |
Non-Patent Citations (1)
| Title |
|---|
| 史忠植 编著: "《认知科学》", 30 September 2008, 合肥：中国科技大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110660395A (en) * | 2019-08-26 | 2020-01-07 | 天津开心生活科技有限公司 | Safety report generation method and device based on voice recognition |
| CN110660395B (en) * | 2019-08-26 | 2022-04-29 | 天津开心生活科技有限公司 | Safety report generation method and device based on voice recognition |
| CN114255760A (en) * | 2021-12-15 | 2022-03-29 | 江苏税软软件科技有限公司 | Inquiry recording system and method |
| CN114462376A (en) * | 2022-02-16 | 2022-05-10 | 来也科技(北京)有限公司 | RPA and AI-based court trial record generation method, device, equipment and medium |
| CN115662437A (en) * | 2022-12-28 | 2023-01-31 | 广州市保伦电子有限公司 | Voice transcription method under scene of simultaneous use of multiple microphones |
| CN115662437B (en) * | 2022-12-28 | 2023-04-18 | 广东保伦电子股份有限公司 | Voice transcription method under scene of simultaneous use of multiple microphones |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523993B (en) | Voice language classification method based on CNN and GRU fusion deep neural network | |
| CN109086199B (en) | Method, terminal and storage medium for automatically generating test script | |
| CN103440201B (en) | Dynamically stain analytical equipment and the application in file format resolving inversely thereof | |
| CN107968959B (en) | Knowledge point segmentation method for teaching video | |
| CN109213971A (en) | The generation method and device of court's trial notes | |
| EP3262634B1 (en) | Obfuscating training data | |
| CN109871326A (en) | A kind of method and apparatus that script is recorded | |
| CN103198828A (en) | Method and system of construction of voice corpus | |
| CN109213977A (en) | The generation system of court's trial notes | |
| US8682678B2 (en) | Automatic realtime speech impairment correction | |
| CN110379410A (en) | Voice response speed automatic analysis method and system | |
| CN110650250B (en) | Method, system, device and storage medium for processing voice conversation | |
| CN110262965A (en) | A kind of test method and equipment of application program | |
| CN109215659A (en) | Processing method, the device and system of voice data | |
| CN109213970B (en) | Method and device for generating notes | |
| CN110019923A (en) | The lookup method and device of speech message | |
| CN109559752B (en) | Speech recognition method and device | |
| CN113327576B (en) | Speech synthesis method, device, equipment and storage medium | |
| CN110312161B (en) | Video dubbing method and device and terminal equipment | |
| CN106528715A (en) | Audio content checking method and device | |
| CN111462760B (en) | Voiceprint recognition system, voiceprint recognition method, voiceprint recognition device and electronic equipment | |
| CN109213466B (en) | Court trial information display method and device | |
| CN111246026A (en) | Recording processing method based on convolutional neural network and connectivity time sequence classification | |
| CN114999464A (en) | Voice data processing method and device | |
| CN115719073A (en) | Translation method, device and medium for multilingual resources |
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 | ||
| CB02 | Change of applicant information |
Address after: 100083 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. Address before: 100086 Cuigong Hotel, 76 Zhichun Road, Shuangyushu District, Haidian District, Beijing Applicant before: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |
|
| RJ01 | Rejection of invention patent application after publication |