WO2022073508A1 - 语音信息录入方法、装置、电子设备及存储介质 - Google Patents
语音信息录入方法、装置、电子设备及存储介质 Download PDFInfo
- Publication number
- WO2022073508A1 WO2022073508A1 PCT/CN2021/122836 CN2021122836W WO2022073508A1 WO 2022073508 A1 WO2022073508 A1 WO 2022073508A1 CN 2021122836 W CN2021122836 W CN 2021122836W WO 2022073508 A1 WO2022073508 A1 WO 2022073508A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- natural language
- language text
- voice information
- voice
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000004044 response Effects 0.000 claims abstract description 21
- 230000004048 modification Effects 0.000 claims description 12
- 238000012986 modification Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 13
- 238000004891 communication Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 230000002596 correlated effect Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000036528 appetite Effects 0.000 description 2
- 235000019789 appetite Nutrition 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000002715 modification method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
Definitions
- the present application relates to voice processing technology, and in particular, to a voice information input method, device, electronic device and storage medium.
- financial advisors of financial institutions can understand the relevant information of customers through one-to-one communication with customers offline, and then through reasonable and systematic customer analysis, they can know the financial needs of different customers.
- users' financial plans can be optimally planned.
- the medical insurance business personnel of financial institutions communicate with customers offline one-on-one to answer customers' questions about medical insurance or reimbursement procedures.
- a voice information input method applied to electronic equipment, the method comprising:
- Receive the real-time voice information input by the user convert the real-time voice information into natural language text, match the natural language text with one or more preset tags one by one, and output the natural language text and the Match results for one or more tags;
- a voice information input device applied to electronic equipment, the device comprises:
- Login module used to collect the voice unlocking instruction sent by the user to the electronic device, match the voiceprint of the voice unlocking instruction with the voiceprint of the preset login voice instruction, and when the voiceprint matches successfully, search for the voiceprint that matches the login voice Account information corresponding to the voice command, log in to the APP corresponding to the account information;
- Conversion module for receiving the real-time voice information input by the user, converting the real-time voice information into natural language text, and matching the natural language text with one or more preset tags one by one, and outputting the natural language text. the matching result of the language text with the one or more tags;
- Storage module used to respond to the instruction for storing the matching result issued by the user, and save the natural language text and the successfully matched label to a preset storage address;
- Update module for judging whether a historical label associated with the natural language text is stored in the preset storage address, and when the judgment result is yes, calculating the similarity between the historical label and the successfully matched label , when the similarity is greater than a preset value, update the historical label to the successfully matched label.
- An electronic device comprising:
- the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of:
- Receive the real-time voice information input by the user convert the real-time voice information into natural language text, match the natural language text with one or more preset tags one by one, and output the natural language text and the Match results for one or more tags;
- a computer-readable storage medium comprising a storage data area and a storage program area
- the storage data area stores data created according to the use of a blockchain node
- the storage program area stores a voice information input program , when the voice information input program is executed by the processor, the following steps are implemented:
- Receive the real-time voice information input by the user convert the real-time voice information into natural language text, match the natural language text with one or more preset tags one by one, and output the natural language text and the Match results for one or more tags;
- This application can improve the efficiency of information entry.
- FIG. 1 is a schematic diagram of a preferred embodiment of the electronic device of the application.
- Fig. 2 is the module schematic diagram of the preferred embodiment of the voice information input device of the application
- FIG. 3 is a flowchart of a preferred embodiment of the voice information input method of the application.
- AI artificial intelligence
- digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
- the basic technologies of artificial intelligence generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics.
- Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning/deep learning.
- FIG. 1 it is a schematic diagram of a preferred embodiment of an electronic device 1 of the present application.
- the electronic device 1 includes but is not limited to: a memory 11 , a processor 12 , a display 13 and a network interface 14 .
- the electronic device 1 is connected to the network through the network interface 14 to obtain original data.
- the network may be an intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth (Bluetooth), Wi-Fi, call network and other wireless or wired networks.
- the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), Magnetic Memory, Magnetic Disk, Optical Disk, etc.
- the memory 11 may be an internal storage unit of the electronic device 1 , such as a hard disk or a memory of the electronic device 1 .
- the memory 11 may also be an external storage device of the electronic device 1, for example, a plug-in hard disk equipped with the electronic device 1, a smart memory card (Smart Media Card, SMC), Secure Digital (SD) card, Flash Card (Flash Card), etc.
- the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device thereof.
- the memory 11 is generally used to store the operating system and various application software installed in the electronic device 1 , such as the program code of the voice information input program 10 and the like.
- the memory 11 can also be used to temporarily store various types of data that have been output or will be output.
- the processor 12 may be a central processing unit (Central Processing Unit) in some embodiments. Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip.
- the processor 12 is generally used to control the overall operation of the electronic device 1, such as performing data interaction or communication-related control and processing.
- the processor 12 is configured to run the program code or process data stored in the memory 11 , for example, run the program code of the voice information input program 10 and the like.
- the display 13 may be referred to as a display screen or a display unit.
- the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an organic light emitting diode (Organic Light Emitting Diode). Light-Emitting Diode, OLED) touch device, etc.
- the display 13 is used for displaying information processed in the electronic device 1 and for displaying a visual working interface, for example, displaying the results of data statistics.
- the network interface 14 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and the network interface 14 is generally used to establish a communication connection between the electronic device 1 and other electronic devices 1 .
- a wireless interface such as a WI-FI interface
- FIG. 1 only shows the electronic device 1 and the cloud database 2 having the components 11-14 and the voice information input program 10, but it should be understood that it is not required to implement all the shown components, and more or more components may be implemented instead. fewer components.
- the electronic device 1 may further include a user interface, and the user interface may include a display (Display), an input unit such as a keyboard (Keyboard), and an optional user interface may further include a standard wired interface and a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an organic light-emitting diode (Organic Light-Emitting Diode, OLED) touch device, and the like.
- the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
- the electronic device 1 may also include a radio frequency (Radio Frequency, RF) circuits, sensors and audio circuits, etc., and will not be repeated here.
- RF Radio Frequency
- Receive the real-time voice information input by the user convert the real-time voice information into natural language text, match the natural language text with one or more preset tags one by one, and output the natural language text and the Match results for one or more tags;
- FIG. 2 For a detailed introduction of the above steps, please refer to the following description of FIG. 2 about the functional block diagram of the embodiment of the voice information input apparatus 100 and the description of the flowchart of the embodiment of the voice information input method in FIG. 3 .
- FIG. 2 is a functional block diagram of the voice information input device 100 of the present application.
- the voice information input device 100 described in this application may be installed in the electronic device 1 .
- the voice information input device 100 may include a login module 110 , a conversion module 120 , a storage module 130 and an update module 140 .
- the modules described in this application may also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device 1 and can perform fixed functions, and are stored in the memory of the electronic device 1 .
- each module/unit is as follows:
- the login module 110 is used to collect the voice unlocking instruction issued by the user to the electronic device 1, and match the voiceprint of the voice unlocking instruction with the voiceprint of the preset login voice instruction.
- the account information corresponding to the login voice command is logged in to the application APP corresponding to the account information.
- the electronic device 1 collects the voice unlock instruction issued by the user to the electronic device 1, recognizes the voice print of the voice unlock command, and determines whether the voice print of the voice unlock command matches the preset voice print of the login voice command .
- the login voice instruction is recorded by the user when registering an account, and the login voice instruction is a specific word, such as "login account”.
- the voiceprint of each person's voice is different, and the user's identity can be determined by using the voiceprint.
- the electronic device 1 determines that the voiceprint of the voice unlocking instruction matches the voiceprint of the preset login voice instruction successfully, the electronic device 1 searches for the account information corresponding to the login voice instruction, thereby logging in the application corresponding to the account information APP, such as logging in to a financial management APP.
- the electronic device 1 collects the voice unlocking instruction issued by the user to the electronic device 1, recognizes the voiceprint and content of the voice unlocking command, and determines whether the voiceprint and content of the voice unlocking command match the preset login voice command. Whether the voiceprint and the content match; when the electronic device 1 determines that the voiceprint and content of the voice unlocking command match the voiceprint and content of the preset login voice command successfully, then the electronic device 1 searches for the account information corresponding to the login voice command , so as to log in to the application APP corresponding to the account information. Use the voice content to determine whether the user wants to log in to the APP to avoid misoperation.
- the voice content of the login voice command can be customized, and the voiceprint is used to confirm the user's identity.
- the voiceprint verification and content verification are combined to ensure the security of user account information.
- the conversion module 120 is configured to receive the real-time voice information input by the user, convert the real-time voice information into natural language text, and match the natural language text with one or more preset tags one by one, and output the Matching results of natural language text to the one or more tags.
- the real-time voice information input by the user may be the information that the user reads out the relevant information of the customer by speaking after the user completes the visit to the customer.
- the memory of the customer's relevant information is relatively clear and complete, and the timely sorting through the voice information has high accuracy and completeness.
- the real-time voice information input by the user may also be information generated by playing a voice file pre-saved by the user.
- the electronic device 1 transcodes the real-time voice information into an audio format file, and uses the NLP model to convert the audio format file into natural language text.
- the electronic device 1 matches the natural language text with one or more preset tags one by one, obtains a matching result between the natural language text and the one or more tags, and outputs the matching result. It can be understood that the matching results include: matching success and matching failure.
- the labels include a basic information label and a financial investment information label.
- the basic information label includes the customer's gender, age, marital status, education, children, work, income, parents, hobbies, real estate information, car, permanent residence, etc.
- Financial investment information labels include: investable assets, investment experience, investment channels, risk appetite, financial knowledge, investment purpose, liquidity needs, etc.
- the natural language text is matched with one or more preset tags one by one, and the matching degree between the preset one or more tags and the natural language text is calculated.
- the matching degree is greater than the threshold, If the matching result is obtained, the matching is successful; when it is judged that the matching degree is less than or equal to the threshold value, the matching result is obtained as the matching failure.
- the natural language text is "the customer has a son”, and the matching degree between each preset label and "the customer has a son” is calculated, and it is determined that "children's gender - male” and "the customer has a son”.
- the matching degree of "one son” is greater than the threshold, and the matching result between "children's gender-male” and “customer has a son” is output as a successful match, and "children's gender-male” is used as a label for successful matching;
- the matching degree between "customer has a son” and “customer has a son” is less than the threshold, and the matching result between "children's gender-female” and “customer has a son” is output as a matching failure, and "children's gender-female” is used as the label for matching failure.
- Outputting the matching result between the natural language text and the one or more tags includes: displaying the tags that are successfully matched with the natural language text in the first display state, displaying the tags that fail to match in the second display state, and displaying the tags that fail to match in the second display state.
- the natural language text is displayed in a third display state, and the first display state, the second display state and the third display state are different.
- the first display state is the first brightness
- the second display state is the second brightness
- the third display state is the third brightness
- the first brightness is greater than the third brightness
- the third brightness is greater than the second brightness. That is, the brightness of the tags that fail to match is smaller than the brightness of tags that match successfully, which is helpful for the user to distinguish the tags that match successfully from those that fail to match.
- receiving the real-time voice information input by the user may be receiving multiple pieces of real-time voice information intermittently input by the user, that is, the electronic device 1 may receive multiple pieces of real-time voice information input by the user in sections.
- the electronic device 1 sends the recording prompt information corresponding to the first label type to the user, and after receiving the real-time voice information corresponding to the first label type input by the user, sends out to the user corresponding to the second label type. and receive the real-time voice information corresponding to the second tag type input by the user.
- the first label type is different from the second label type.
- the first label type and the second label type are basic information and financial investment information, respectively.
- the electronic device 1 first displays the text information of "Please enter the customer's basic information", and then displays the text information of "Please enter the customer's financial investment information” after receiving the real-time voice information corresponding to the "customer's basic information” input by the user. Receive real-time voice information corresponding to "financial investment information”. In this way, the user is restrained, which is helpful for the user to sort out the customer information, and the input information is more standardized and complete.
- the electronic device 1 can first receive the real-time voice information corresponding to the remembered part of the customer information input by the user, respond to the user's instruction to pause the recording, and stop. Receiving voice information, when the user remembers the previously forgotten customer information, the user sends an instruction to continue recording to the electronic device 1; in response to the user's instruction to continue recording, continue to receive real-time voice information corresponding to the customer information just remembered by the user.
- the storage module 130 is configured to save the natural language text and the successfully matched tags to a preset storage address in response to an instruction issued by the user to store the matching result.
- Storing the natural language text and the successfully matched label to a preset storage address may also include: judging whether there is a corresponding preset storage address, and when there is a corresponding preset storage address, storing the successfully matched label and all the stored addresses.
- the natural language text is stored in the corresponding preset storage address. When the corresponding preset storage address does not exist, a corresponding preset storage address is newly created, and the successfully matched label and the natural language text are stored in the newly created preset storage address.
- a preset storage address can be set to correspond to a customer.
- the voice information input method further includes: in response to the user's modification instruction, deleting and/or adding text in the natural language text;
- the natural language text is matched with the preset one or more tags one by one, and a new matching result is output.
- modification methods include deletion and addition.
- the electronic device 1 modifies the natural language text in response to the user's modification instruction. For example, the user finds that the customer name in the natural language text is "Li Dacheng", but the customer name is actually “Li Dacheng", and sends a modification instruction to the electronic device 1 to change "cheng” to "cheng”.
- the electronic device 1 deletes "cheng” at the corresponding position in the natural language text, and adds "cheng”. Match the modified natural language text with one or more preset tags one by one, and output a new matching result.
- the update module 140 is used for judging whether a historical label associated with the natural language text is stored in the preset storage address, and when the judgment result is yes, calculating the similarity between the historical label and the successfully matched label When the similarity is greater than a preset value, the historical label is updated to the successfully matched label.
- the electronic device 1 determines whether the preset storage address stores a history tag associated with the natural language text stored in the preset storage address, and determines whether the preset storage address stores a history tag associated with the natural language text. In the case of a historical tag associated with the natural language text, calculate the similarity between the associated historical tag and the successfully matched tag, and when judging that the similarity is greater than a preset value, update the historical tag to the successful matching Tag of.
- the successfully matched tags and natural language texts saved to the preset storage address are "marriage status - married” and "customer just got married last week", and the electronic device 1 recognizes the preset storage address.
- the storage address stores the historical label "marriage status-unmarried” associated with “customer just got married last week”, calculates the similarity between "marriage status-unmarried” and “marriage status-married”, and judges the similarity If it is greater than the preset value, delete the history label of "marital status-unmarried”.
- the voice information input device 100 proposed in the present application collects the voice unlocking command issued by the user, matches the voiceprint of the voice unlocking command with the voiceprint of the preset login voice command, and when the voiceprint is successfully matched, searches for the voiceprint corresponding to the login voice For account information corresponding to the voice command, log in to the application APP corresponding to the account information to log in to the account, so as to ensure the security of the user account information.
- Receive the real-time voice information input by the user generate the corresponding natural language text according to the real-time voice information, match the natural language text and each preset tag one by one, output the matching result between the natural language text and the tag, and match the successful Labels and natural language texts are stored in preset storage addresses, which improves the efficiency of information entry.
- the similarity between the historical tags and the successfully matched tags is further calculated, and when the similarity is greater than the preset value, the corresponding historical tags Update the tags that match successfully, and realize the tag update in the preset address.
- the present application also provides a voice information input method, which is applied to the electronic device 1 .
- FIG. 3 it is a schematic flowchart of an embodiment of a voice information input method of the present application.
- the processor 12 of the electronic device 1 executes the voice information input program 10 stored in the memory 11, the following steps are implemented in the voice information input method:
- Step S10 Collect the voice unlocking instruction issued by the user to the electronic device 1, match the voiceprint of the voice unlocking instruction with the voiceprint of the preset login voice instruction, and when the voiceprint is successfully matched, search for the voiceprint that matches the login voice.
- the account information corresponding to the instruction is used to log in to the application APP corresponding to the account information.
- the electronic device 1 collects the voice unlock instruction issued by the user to the electronic device 1, recognizes the voice print of the voice unlock command, and determines whether the voice print of the voice unlock command matches the preset voice print of the login voice command .
- the login voice instruction is recorded by the user when registering an account, and the login voice instruction is a specific word, such as "login account”.
- the voiceprint of each person's voice is different, and the user's identity can be determined by using the voiceprint.
- the electronic device 1 determines that the voiceprint of the voice unlocking instruction matches the voiceprint of the preset login voice instruction successfully, the electronic device 1 searches for the account information corresponding to the login voice instruction, thereby logging in the application corresponding to the account information APP, such as logging in to a financial management APP.
- the electronic device 1 collects the voice unlocking instruction issued by the user to the electronic device 1, recognizes the voiceprint and content of the voice unlocking command, and determines whether the voiceprint and content of the voice unlocking command match the preset login voice command. Whether the voiceprint and the content match; when the electronic device 1 determines that the voiceprint and content of the voice unlocking command match the voiceprint and content of the preset login voice command successfully, then the electronic device 1 searches for the account information corresponding to the login voice command , so as to log in to the application APP corresponding to the account information. Use the voice content to determine whether the user wants to log in to the APP to avoid misoperation.
- the voice content of the login voice command can be customized, and the voiceprint is used to confirm the user's identity.
- the voiceprint verification and content verification are combined to ensure the security of user account information.
- Step S20 Receive the real-time voice information input by the user, convert the real-time voice information into natural language text, match the natural language text with one or more preset tags one by one, and output the natural language text Matches to the one or more tags.
- the real-time voice information input by the user may be the information that the user reads out the relevant information of the customer by speaking after the user completes the visit to the customer.
- the memory of the customer's relevant information is relatively clear and complete, and the timely sorting through the voice information has high accuracy and completeness.
- the real-time voice information input by the user may also be information generated by playing a voice file pre-saved by the user.
- the electronic device 1 transcodes the real-time voice information into an audio format file, and uses the NLP model to convert the audio format file into natural language text.
- the electronic device 1 matches the natural language text with one or more preset tags one by one, obtains a matching result between the natural language text and the one or more tags, and outputs the matching result. It can be understood that the matching results include: matching success and matching failure.
- the labels include a basic information label and a financial investment information label.
- the basic information label includes the customer's gender, age, marital status, education, children, work, income, parents, hobbies, real estate information, car, permanent residence, etc.
- Financial investment information labels include: investable assets, investment experience, investment channels, risk appetite, financial knowledge, investment purpose, liquidity needs, etc.
- the natural language text is matched with one or more preset tags one by one, and the matching degree between the preset one or more tags and the natural language text is calculated.
- the matching degree is greater than the threshold, If the matching result is obtained, the matching is successful; when it is judged that the matching degree is less than or equal to the threshold value, the matching result is obtained as the matching failure.
- the natural language text is "the customer has a son”, and the matching degree between each preset label and "the customer has a son” is calculated, and it is determined that "children's gender - male” and "the customer has a son”.
- the matching degree of "one son” is greater than the threshold, and the matching result between "children's gender-male” and “customer has a son” is output as a successful match, and "children's gender-male” is used as a label for successful matching;
- the matching degree between "customer has a son” and “customer has a son” is less than the threshold, and the matching result between "children's gender-female” and “customer has a son” is output as a matching failure, and "children's gender-female” is used as the label for matching failure.
- Outputting the matching result between the natural language text and the one or more tags includes: displaying the tags that are successfully matched with the natural language text in the first display state, displaying the tags that fail to match in the second display state, and displaying the tags that fail to match in the second display state.
- the natural language text is displayed in a third display state, and the first display state, the second display state and the third display state are different.
- the first display state is the first brightness
- the second display state is the second brightness
- the third display state is the third brightness
- the first brightness is greater than the third brightness
- the third brightness is greater than the second brightness. That is, the brightness of the tags that fail to match is smaller than the brightness of tags that match successfully, which is helpful for the user to distinguish the tags that match successfully from those that fail to match.
- receiving the real-time voice information input by the user may be receiving multiple pieces of real-time voice information intermittently input by the user, that is, the electronic device 1 may receive multiple pieces of real-time voice information input by the user in sections.
- the electronic device 1 sends the recording prompt information corresponding to the first label type to the user, and after receiving the real-time voice information corresponding to the first label type input by the user, sends out to the user corresponding to the second label type. and receive the real-time voice information corresponding to the second tag type input by the user.
- the first label type is different from the second label type.
- the first label type and the second label type are basic information and financial investment information, respectively.
- the electronic device 1 first displays the text information of "Please enter the customer's basic information", and then displays the text information of "Please enter the customer's financial investment information” after receiving the real-time voice information corresponding to the "customer's basic information” input by the user. Receive real-time voice information corresponding to "financial investment information”. In this way, the user is restrained, which is helpful for the user to sort out the customer information, and the input information is more standardized and complete.
- the electronic device 1 can first receive the real-time voice information corresponding to the remembered part of the customer information input by the user, respond to the user's instruction to pause the recording, and stop.
- the user After receiving the voice information, when the user remembers the previously forgotten customer information, the user sends an instruction to continue recording to the electronic device 1; in response to the user's instruction to continue recording, the user continues to receive the real-time voice information corresponding to the client information just remembered by the user.
- Step S30 Responding to an instruction issued by the user to store the matching result, save the natural language text and the successfully matched label to a preset storage address.
- Storing the natural language text and the successfully matched label to a preset storage address may also include: judging whether there is a corresponding preset storage address, and when there is a corresponding preset storage address, storing the successfully matched label and all the stored addresses.
- the natural language text is stored in the corresponding preset storage address. When the corresponding preset storage address does not exist, a corresponding preset storage address is newly created, and the successfully matched label and the natural language text are stored in the newly created preset storage address.
- a preset storage address can be set to correspond to a customer.
- the voice information input method further includes: in response to the user's modification instruction, deleting and/or adding text in the natural language text;
- the natural language text is matched with the preset one or more tags one by one, and a new matching result is output.
- modification methods include deletion and addition.
- the electronic device 1 modifies the natural language text in response to the user's modification instruction. For example, the user finds that the customer name in the natural language text is "Li Dacheng", but the customer name is actually “Li Dacheng", and sends a modification instruction to the electronic device 1 to change "cheng” to "cheng”.
- the electronic device 1 deletes "cheng” at the corresponding position in the natural language text, and adds "cheng”. Match the modified natural language text with one or more preset tags one by one, and output a new matching result.
- Step S40 judging whether a historical tag associated with the natural language text is stored in the preset storage address, when the judgment result is yes, calculate the similarity between the historical tag and the successfully matched tag, when When the similarity is greater than a preset value, the historical tag is updated to the successfully matched tag.
- the electronic device 1 determines whether the preset storage address stores a history tag associated with the natural language text stored in the preset storage address, and determines whether the preset storage address stores a history tag associated with the natural language text. In the case of a historical tag associated with the natural language text, calculate the similarity between the associated historical tag and the successfully matched tag, and when judging that the similarity is greater than a preset value, update the historical tag to the successful matching Tag of.
- the successfully matched tags and natural language texts saved to the preset storage address are "marriage status - married” and "customer just got married last week", and the electronic device 1 recognizes the preset storage address.
- the storage address stores the historical label "marriage status-unmarried” associated with “customer just got married last week”, calculates the similarity between "marriage status-unmarried” and “marriage status-married”, and judges the similarity If it is greater than the preset value, delete the history label of "marital status-unmarried”.
- the voice information input method proposed in the present application collects the voice unlocking command issued by the user, matches the voiceprint of the voice unlocking command with the voiceprint of the preset login voice command, and when the voiceprint is successfully matched, searches for the voiceprint that matches the login voice.
- the account information corresponding to the instruction is logged in to the application APP corresponding to the account information to log in the account, so as to ensure the security of the user account information.
- Receive the real-time voice information input by the user generate the corresponding natural language text according to the real-time voice information, match the natural language text and each preset tag one by one, output the matching result between the natural language text and the tag, and match the successful Labels and natural language texts are stored in preset storage addresses, which improves the efficiency of information entry.
- the similarity between the historical tags and the successfully matched tags is further calculated, and when the similarity is greater than the preset value, the corresponding historical tags Update the tags that match successfully, and realize the tag update in the preset address.
- the embodiments of the present application can be applied to relevant communication scenarios of financial institutions, such as a consultation scenario of medical insurance reimbursement.
- an embodiment of the present application also proposes a computer-readable storage medium, which may be volatile or non-volatile, and the computer-readable storage medium may be a hard disk, a multimedia card, a Any of SD Card, Flash Card, SMC, Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), Portable Compact Disc Read Only Memory (CD-ROM), USB memory, etc. or any combination of several.
- the computer-readable storage medium includes a storage data area and a storage program area, the storage data area stores data created according to the use of the blockchain node, and the storage program area stores a voice information input program 10, and the voice information input program 10 performs the following operations when executed by the processor:
- Receive the real-time voice information input by the user convert the real-time voice information into natural language text, match the natural language text with one or more preset tags one by one, and output the natural language text and the Match results for one or more tags;
- all the above-mentioned data can also be stored in a node of a blockchain.
- a node of a blockchain For example, knowledge graph, text to be recognized, etc., these data can be stored in blockchain nodes.
- Blockchain is essentially a decentralized database, which is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
一种语音信息录入方法、装置、电子设备及介质，涉及人工智能技术。其中，该方法包括：采集用户对电子设备发出的语音解锁指令，匹配语音解锁指令的声纹与预先设置的登录语音指令的声纹，当匹配成功，查找对应的账号信息，登录应用APP（S10）；接收用户输入的实时语音信息，将实时语音信息转换为自然语言文本，并与预先设置的标签匹配，输出匹配结果（S20）；响应用户发出的存储匹配结果的指令，保存自然语言文本及匹配成功的标签至预设存储地址（S30）；判断是否存储有与自然语言文本相关联的历史标签，若是，计算历史标签与匹配成功的标签的相似度，当大于预设值时，更新历史标签（S40）。该方案可应用于金融机构的相关沟通场景，比如医疗保险报销的咨询场景，提升了信息录入效率。
Description
本申请要求于2020年10月09日提交中国专利局、申请号为CN202011075452.8，发明名称为“语音信息录入方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请涉及语音处理技术，尤其涉及一种语音信息录入方法、装置、电子设备及存储介质。
目前，金融机构的理财顾问通过跟客户线下一对一沟通，了解客户的相关信息，进而通过合理、系统的客户分析，可以知道不同的客户的理财需求。通过分析客户理财需求与机构产品与服务的商务效益的关系，可以使用户的理财计划得到最优的规划。或者金融机构的医疗保险业务人员跟客户线下一对一沟通，来解答客户对于医疗保险方面的问题或者报销流程等问题。
发明人意识到理财顾问或者医疗保险业务人员通过跟客户线下一对一沟通后，手工记录客户信息，存在信息录入效率较低的问题。
一种语音信息录入方法，应用于电子设备，该方法包括：
采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；
接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；
响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；
判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
一种语音信息录入装置，应用于电子设备，所述装置包括：
登录模块：用于采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；
转换模块：用于接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；
存储模块：用于响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；
更新模块：用于判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
一种电子设备，所述电子设备包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如下步骤：
采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；
接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；
响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；
判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
一种计算机可读存储介质，所述计算机可读存储介质中包括存储数据区和存储程序区，存储数据区存储根据区块链节点的使用所创建的数据，存储程序区存储有语音信息录入程序，所述语音信息录入程序被处理器执行时，实现如下步骤：
采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；
接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；
响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；
判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
本申请可以提升信息的录入效率。
图1为本申请电子设备较佳实施例的示意图；
图2为本申请语音信息录入装置较佳实施例的模块示意图；
图3为本申请语音信息录入方法较佳实施例的流程图；
本申请目的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请实施例可以基于人工智能技术对相关的数据进行获取和处理。其中，人工智能（Artificial Intelligence，AI）是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。
人工智能基础技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理技术、操作/交互系统、机电一体化等技术。人工智能软件技术主要包括计算机视觉技术、机器人技术、生物识别技术、语音处理技术、自然语言处理技术以及机器学习/深度学习等几大方向。
参照图1所示，为本申请电子设备1较佳实施例的示意图。
该电子设备1包括但不限于：存储器11、处理器12、显示器13及网络接口14。所述电子设备1通过网络接口14连接网络，获取原始数据。其中，所述网络可以是企业内部网（Intranet）、互联网（Internet）、全球移动通讯系统（Global
System of Mobile communication，GSM）、宽带码分多址（Wideband Code Division Multiple Access，WCDMA）、4G网络、5G网络、蓝牙（Bluetooth）、Wi-Fi、通话网络等无线或有线网络。其中，存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器（例如，SD或DX存储器等）、随机访问存储器（RAM）、静态随机访问存储器（SRAM）、只读存储器（ROM）、电可擦除可编程只读存储器（EEPROM）、可编程只读存储器（PROM）、磁性存储器、磁盘、光盘等。在一些实施例中，所述存储器11可以是所述电子设备1的内部存储单元，例如该电子设备1的硬盘或内存。在另一些实施例中，所述存储器11也可以是所述电子设备1的外部存储设备，例如该电子设备1配备的插接式硬盘，智能存储卡（Smart Media
Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。当然，所述存储器11还可以既包括所述电子设备1的内部存储单元也包括其外部存储设备。本实施例中，存储器11通常用于存储安装于所述电子设备1的操作系统和各类应用软件，例如语音信息录入程序10的程序代码等。此外，存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器12在一些实施例中可以是中央处理器（Central
Processing Unit，CPU）、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器12通常用于控制所述电子设备1的总体操作，例如执行数据交互或者通信相关的控制和处理等。本实施例中，所述处理器12用于运行所述存储器11中存储的程序代码或者处理数据，例如运行语音信息录入程序10的程序代码等。
显示器13可以称为显示屏或显示单元。在一些实施例中显示器13可以是LED显示器、液晶显示器、触控式液晶显示器以及有机发光二极管（Organic
Light-Emitting Diode，OLED）触摸器等。显示器13用于显示在电子设备1中处理的信息以及用于显示可视化的工作界面，例如显示数据统计的结果。
网络接口14可选地可以包括标准的有线接口、无线接口（如WI-FI接口），该网络接口14通常用于在所述电子设备1与其它电子设备1之间建立通信连接。
图1仅示出了具有组件11-14以及语音信息录入程序10的电子设备1和云端数据库2，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
可选地，所述电子设备1还可以包括用户接口，用户接口可以包括显示器（Display）、输入单元比如键盘（Keyboard），可选的用户接口还可以包括标准的有线接口、无线接口。可选地，在一些实施例中，显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及有机发光二极管（Organic Light-Emitting Diode，OLED）触摸器等。其中，显示器也可以适当的称为显示屏或显示单元，用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
该电子设备1还可以包括射频（Radio
Frequency，RF）电路、传感器和音频电路等等，在此不再赘述。
在上述实施例中，处理器12执行存储器11中存储的语音信息录入程序10时可以实现如下步骤：
采集用户对电子设备1发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；
接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；
响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；
判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
关于上述步骤的详细介绍，请参照下述图2关于语音信息录入装置100实施例的功能模块图以及图3关于语音信息录入方法实施例的流程图的说明。
参照图2所示，为本申请语音信息录入装置100的功能模块图。
本申请所述语音信息录入装置100可以安装于电子设备1中。根据实现的功能，所述语音信息录入装置100可以包括登录模块110、转换模块120、存储模块130及更新模块140。本申请中所述模块也可以称之为单元，是指一种能够被电子设备1处理器所执行，并且能够完成固定功能的一系列计算机程序段，其存储在电子设备1的存储器中。
在本实施例中，关于各模块/单元的功能如下：
登录模块110，用于采集用户对所述电子设备1发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP。
在本实施例中，电子设备1采集用户对所述电子设备1发出的语音解锁指令，识别语音解锁指令的声纹，判断语音解锁指令的声纹与预先设置的登录语音指令的声纹是否匹配。其中，登录语音指令是用户在注册账号时录制得到的，登录语音指令为一段特定的话，例如“登录账号”。每个人声音的声纹不同，利用声纹可确定用户身份。当电子设备1判断语音解锁指令的声纹与预先设置的登录语音指令的声纹匹配成功时，则电子设备1查找与登录语音指令相对应的账号信息，从而登录与所述账号信息对应的应用APP，例如登录某款理财APP。
在其他实施例中，电子设备1采集用户对所述电子设备1发出的语音解锁指令，识别语音解锁指令的声纹和内容，判断语音解锁指令的声纹和内容与预先设置的登录语音指令的声纹和内容是否匹配；当电子设备1判断语音解锁指令的声纹和内容与预先设置的登录语音指令的声纹和内容匹配成功时，则电子设备1查找与登录语音指令相对应的账号信息，从而登录与所述账号信息对应的应用APP。利用语音内容判断用户是否想要登录应用APP，避免误操作。登录语音指令的语音内容可自定义，并且利用声纹确认用户身份，声纹验证和内容验证相配合，保证用户账号信息的安全性。
转换模块120，用于接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果。
在本实施例中，以应用APP为理财APP为例，用户输入的实时语音信息可以为用户完成拜访客户后将客户的相关信息用说话的方式读出的信息。用户刚拜访完客户时，对客户的相关信息的记忆较为清楚完整，及时通过语音信息的方式进行梳理具有较高的准确性和完整性。当然，用户输入的实时语音信息也可以为播放用户预先保存的语音文件所产生的信息。
具体地，在登录应用APP后，电子设备1将实时语音信息转码为音频格式文件，利用NLP模型将音频格式文件转为自然语言文本。电子设备1将自然语言文本与预先设置的一个或多个标签一一进行匹配，得到所述自然语言文本与所述一个或多个标签的匹配结果，输出所述匹配结果。可以理解的是，匹配结果包括：匹配成功和匹配失败。
以应用APP为理财APP为例，所述标签包括基本信息标签和金融投资信息标签。基本信息标签包括客户的性别、年龄、婚姻状态、教育情况、子女情况、工作情况、收入情况、父母、兴趣爱好、房产信息、车、常住地等。金融投资信息标签包括：可投资产、投资经验、投资渠道、风险偏好、金融知识、投资目的、流动性需求等。
具体地，将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，计算预先设置的一个或多个标签与所述自然语言文本的匹配度，当判断匹配度大于阈值时，得到匹配结果为匹配成功；判断匹配度小于或等于阈值时，得到匹配结果为匹配失败。
以应用APP为理财APP为例，自然语言文本为“客户有一个儿子”，计算预先设置的每个标签与“客户有一个儿子”的匹配度，判断出“子女性别-男”与“客户有一个儿子”的匹配度大于阈值，输出“子女性别-男”与“客户有一个儿子”的匹配结果为匹配成功，将“子女性别-男”作为匹配成功的标签；识别出“子女性别-女”与“客户有一个儿子”的匹配度小于阈值，输出“子女性别-女”与“客户有一个儿子”的匹配结果为匹配失败，将“子女性别-女”作为匹配失败的标签。
输出所述自然语言文本与所述一个或多个标签的匹配结果包括：将与所述自然语言文本匹配成功的标签以第一显示状态展示，将匹配失败的标签以第二显示状态展示，将自然语言文本以第三显示状态展示，第一显示状态、第二显示状态及第三显示状态不同。例如，第一显示状态为第一亮度，第二显示状态为第二亮度，第三显示状态为第三亮度，第一亮度大于第三亮度，且第三亮度大于第二亮度。即匹配失败的标签的亮度小于匹配成功的标签的亮度，利于用户区分匹配成功的标签和匹配失败的标签。
在其他实施例中，接收用户输入的实时语音信息，可以为接收用户间断输入的多段实时语音信息，即电子设备1可分段接收用户输入的多段实时语音信息。
具体地，电子设备1向用户发出对应于第一标签类型的录音提示信息，当接收到用户输入的对应于第一标签类型的所述实时语音信息后，向用户发出对应于第二个标签类型的录音提示信息，接收用户输入的对应于该第二标签类型的所述实时语音信息。第一标签类型与第二标签类型不同，以应用APP为理财APP为例，第一标签类型与第二标签类型分别为基本信息和金融投资信息。例如，电子设备1先显示“请录入客户基本信息”的文字信息，接收到用户输入的对应于“客户基本信息”的实时语音信息后，再显示“请录入客户金融投资信息”的文字信息，接收对应于“金融投资信息”的实时语音信息。如此，约束用户，利于用户理清客户信息，输入的信息更为规范完整。
或者，接收用户输入的实时语音信息，接收完成后，响应用户暂停录音的指令，停止接收语音信息，停止接收语音信息后响应用户继续录音的指令，继续接收用户输入的实时语音信息。可不按标签的类型分段接收用户输入的实时语音信息。以应用APP为理财APP为例，用户有时会想不起部分客户信息，此时电子设备1可先接收用户输入的记得起来的部分客户信息对应的实时语音信息，响应用户暂停录音的指令，停止接收语音信息，等用户想起之前忘记的客户信息时，用户对电子设备1发出继续录音指令；响应用户的继续录音指令，继续接收用户输入的刚想起来的客户信息对应的实时语音信息。
存储模块130，用于响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址。
在本实施例中，以应用APP为理财APP为例，用户对匹配结果和自然语言文本确认无误之后，发出确认存储的指令。电子设备1响应用户的确认存储的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址。存储所述自然语言文本及匹配成功的标签至预设存储地址，还可以包括：判断是否存在对应的预设存储地址，当存在对应的预设存储地址时，将所述匹配成功的标签和所述自然语言文本存储至对应的预设存储地址中。当不存在对应的预设存储地址时，新建一个对应的预设存储地址，将所述匹配成功的标签和所述自然语言文本存储至新建的所述预设存储地址中。可以设置一个预设存储地址对应一个客户。
进一步地，在所述响应用户的确认存储的指令之前，所述语音信息录入方法还包括：响应用户的修改指令，在所述自然语言文本中删除和/或新增文字；将修改后的所述自然语言文本与所述预先设置的一个或多个标签一一进行匹配，输出新的匹配结果。
用户可以检查输出的自然语言文本的文字信息是否准确，在文字信息不准确的情况下，向电子设备1发出修改指令。一般来说，修改方式包括删除和新增。电子设备1响应于用户的修改指令，修改自然语言文本。例如，用户发现自然语言文本中的客户名称为“李大成”，客户名称实际为“李大程”，向电子设备1发出将“成”改为“程”的修改指令。电子设备1响应修改指令，在自然语言文本中相应的位置删除“成”，并新增“程”。将修改后的自然语言文本与预先设置的一个或多个标签一一进行匹配，输出新的匹配结果。
更新模块140，用于判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
在本实施例中，电子设备1判断所述预设存储地址中是否存储有与保存至预设存储地址中的所述自然语言文本相关联的历史标签，在判断出预设存储地址中保存有与所述自然语言文本相关联的历史标签的情况下，计算相关联的历史标签与匹配成功的标签的相似度，判断相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
以应用APP为理财APP为例，保存至预设存储地址中的匹配成功的标签和自然语言文本分别为“婚姻状态-已婚”和“客户上周刚结婚”，电子设备1识别出预设存储地址中存储有与“客户上周刚结婚”相关联的“婚姻状态-未婚”这一历史标签，计算出“婚姻状态-未婚”与“婚姻状态-已婚”的相似度，判断相似度大于预设值，删除“婚姻状态-未婚”这一历史标签。
可以理解的是，在判断所述预设存储地址中未存储有与自然语言文本相关联的历史标签，或者相似度小于或等于预设值的情况下，则不更新历史标签，换言之，保留历史标签。
本申请提出的语音信息录入装置100，采集用户发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP以登录账号，保证用户账号信息的安全性。接收用户发出输入的实时语音信息，根据实时语音信息生成相应的自然语言文本，将自然语言文本和预先设置的每个标签一一进行匹配，输出自然语言文本与标签的匹配结果，将匹配成功的标签和自然语言文本存储到预设存储地址，提升了信息的录入效率。在预设存储地址中保存有与所述自然语言文本相关联的历史标签的情况下，进一步计算历史标签与匹配成功的标签的相似度，当相似度大于预设值时，将对应的历史标签更新为匹配成功的标签，实现了预设地址中的标签更新。
此外，本申请还提供一种语音信息录入方法，该方法应用于电子设备1。参照图3所示，为本申请语音信息录入方法的实施例的方法流程示意图。电子设备1的处理器12执行存储器11中存储的语音信息录入程序10时实现语音信息录入方法的如下步骤：
步骤S10：采集用户对所述电子设备1发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP。
在本实施例中，电子设备1采集用户对所述电子设备1发出的语音解锁指令，识别语音解锁指令的声纹，判断语音解锁指令的声纹与预先设置的登录语音指令的声纹是否匹配。其中，登录语音指令是用户在注册账号时录制得到的，登录语音指令为一段特定的话，例如“登录账号”。每个人声音的声纹不同，利用声纹可确定用户身份。当电子设备1判断语音解锁指令的声纹与预先设置的登录语音指令的声纹匹配成功时，则电子设备1查找与登录语音指令相对应的账号信息，从而登录与所述账号信息对应的应用APP，例如登录某款理财APP。
在其他实施例中，电子设备1采集用户对所述电子设备1发出的语音解锁指令，识别语音解锁指令的声纹和内容，判断语音解锁指令的声纹和内容与预先设置的登录语音指令的声纹和内容是否匹配；当电子设备1判断语音解锁指令的声纹和内容与预先设置的登录语音指令的声纹和内容匹配成功时，则电子设备1查找与登录语音指令相对应的账号信息，从而登录与所述账号信息对应的应用APP。利用语音内容判断用户是否想要登录应用APP，避免误操作。登录语音指令的语音内容可自定义，并且利用声纹确认用户身份，声纹验证和内容验证相配合，保证用户账号信息的安全性。
步骤S20：接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果。
在本实施例中，以应用APP为理财APP为例，用户输入的实时语音信息可以为用户完成拜访客户后将客户的相关信息用说话的方式读出的信息。用户刚拜访完客户时，对客户的相关信息的记忆较为清楚完整，及时通过语音信息的方式进行梳理具有较高的准确性和完整性。当然，用户输入的实时语音信息也可以为播放用户预先保存的语音文件所产生的信息。
具体地，在登录应用APP后，电子设备1将实时语音信息转码为音频格式文件，利用NLP模型将音频格式文件转为自然语言文本。电子设备1将自然语言文本与预先设置的一个或多个标签一一进行匹配，得到所述自然语言文本与所述一个或多个标签的匹配结果，输出所述匹配结果。可以理解的是，匹配结果包括：匹配成功和匹配失败。
以应用APP为理财APP为例，所述标签包括基本信息标签和金融投资信息标签。基本信息标签包括客户的性别、年龄、婚姻状态、教育情况、子女情况、工作情况、收入情况、父母、兴趣爱好、房产信息、车、常住地等。金融投资信息标签包括：可投资产、投资经验、投资渠道、风险偏好、金融知识、投资目的、流动性需求等。
具体地，将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，计算预先设置的一个或多个标签与所述自然语言文本的匹配度，当判断匹配度大于阈值时，得到匹配结果为匹配成功；判断匹配度小于或等于阈值时，得到匹配结果为匹配失败。
以应用APP为理财APP为例，自然语言文本为“客户有一个儿子”，计算预先设置的每个标签与“客户有一个儿子”的匹配度，判断出“子女性别-男”与“客户有一个儿子”的匹配度大于阈值，输出“子女性别-男”与“客户有一个儿子”的匹配结果为匹配成功，将“子女性别-男”作为匹配成功的标签；识别出“子女性别-女”与“客户有一个儿子”的匹配度小于阈值，输出“子女性别-女”与“客户有一个儿子”的匹配结果为匹配失败，将“子女性别-女”作为匹配失败的标签。
输出所述自然语言文本与所述一个或多个标签的匹配结果包括：将与所述自然语言文本匹配成功的标签以第一显示状态展示，将匹配失败的标签以第二显示状态展示，将自然语言文本以第三显示状态展示，第一显示状态、第二显示状态及第三显示状态不同。例如，第一显示状态为第一亮度，第二显示状态为第二亮度，第三显示状态为第三亮度，第一亮度大于第三亮度，且第三亮度大于第二亮度。即匹配失败的标签的亮度小于匹配成功的标签的亮度，利于用户区分匹配成功的标签和匹配失败的标签。
在其他实施例中，接收用户输入的实时语音信息，可以为接收用户间断输入的多段实时语音信息，即电子设备1可分段接收用户输入的多段实时语音信息。
具体地，电子设备1向用户发出对应于第一标签类型的录音提示信息，当接收到用户输入的对应于第一标签类型的所述实时语音信息后，向用户发出对应于第二个标签类型的录音提示信息，接收用户输入的对应于该第二标签类型的所述实时语音信息。第一标签类型与第二标签类型不同，以应用APP为理财APP为例，第一标签类型与第二标签类型分别为基本信息和金融投资信息。例如，电子设备1先显示“请录入客户基本信息”的文字信息，接收到用户输入的对应于“客户基本信息”的实时语音信息后，再显示“请录入客户金融投资信息”的文字信息，接收对应于“金融投资信息”的实时语音信息。如此，约束用户，利于用户理清客户信息，输入的信息更为规范完整。
或者，接收用户输入的实时语音信息，接收完成后，响应用户暂停录音的指令，停止接收语音信息，停止接收语音信息后响应用户的继续录音指令，继续接收用户输入的实时语音信息。可不按标签的类型分段接收用户输入的实时语音信息。以应用APP为理财APP为例，用户有时会想不起部分客户信息，此时电子设备1可先接收用户输入的记得起来的部分客户信息对应的实时语音信息，响应用户暂停录音的指令，停止接收语音信息，等用户想起之前忘记的客户信息时，用户对电子设备1发出继续录音指令；响应用户的继续录音指令，继续接收用户输入的刚想起来的客户信息对应的实时语音信息。
步骤S30：响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址。
在本实施例中，以应用APP为理财APP为例，用户对匹配结果和自然语言文本确认无误之后，发出确认存储的指令。电子设备1响应用户的确认存储的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址。存储所述自然语言文本及匹配成功的标签至预设存储地址，还可以包括：判断是否存在对应的预设存储地址，当存在对应的预设存储地址时，将所述匹配成功的标签和所述自然语言文本存储至对应的预设存储地址中。当不存在对应的预设存储地址时，新建一个对应的预设存储地址，将所述匹配成功的标签和所述自然语言文本存储至新建的所述预设存储地址中。可以设置一个预设存储地址对应一个客户。
进一步地，在所述响应用户的确认存储的指令之前，所述语音信息录入方法还包括：响应用户的修改指令，在所述自然语言文本中删除和/或新增文字；将修改后的所述自然语言文本与所述预先设置的一个或多个标签一一进行匹配，输出新的匹配结果。
用户可以检查输出的自然语言文本的文字信息是否准确，在文字信息不准确的情况下，向电子设备1发出修改指令。一般来说，修改方式包括删除和新增。电子设备1响应于用户的修改指令，修改自然语言文本。例如，用户发现自然语言文本中的客户名称为“李大成”，客户名称实际为“李大程”，向电子设备1发出将“成”改为“程”的修改指令。电子设备1响应修改指令，在自然语言文本中相应的位置删除“成”，并新增“程”。将修改后的自然语言文本与预先设置的一个或多个标签一一进行匹配，输出新的匹配结果。
步骤S40：判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
在本实施例中，电子设备1判断所述预设存储地址中是否存储有与保存至预设存储地址中的所述自然语言文本相关联的历史标签，在判断出预设存储地址中保存有与所述自然语言文本相关联的历史标签的情况下，计算相关联的历史标签与匹配成功的标签的相似度，判断相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
以应用APP为理财APP为例，保存至预设存储地址中的匹配成功的标签和自然语言文本分别为“婚姻状态-已婚”和“客户上周刚结婚”，电子设备1识别出预设存储地址中存储有与“客户上周刚结婚”相关联的“婚姻状态-未婚”这一历史标签，计算出“婚姻状态-未婚”与“婚姻状态-已婚”的相似度，判断相似度大于预设值，删除“婚姻状态-未婚”这一历史标签。
可以理解的是，在判断所述预设存储地址中未存储有与自然语言文本相关联的历史标签，或者相似度小于或等于预设值的情况下，则不更新历史标签，换言之，保留历史标签。
本申请提出的语音信息录入方法，采集用户发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP以登录账号，保证用户账号信息的安全性。接收用户发出输入的实时语音信息，根据实时语音信息生成相应的自然语言文本，将自然语言文本和预先设置的每个标签一一进行匹配，输出自然语言文本与标签的匹配结果，将匹配成功的标签和自然语言文本存储到预设存储地址，提升了信息的录入效率。在预设存储地址中保存有与所述自然语言文本相关联的历史标签的情况下，进一步计算历史标签与匹配成功的标签的相似度，当相似度大于预设值时，将对应的历史标签更新为匹配成功的标签，实现了预设地址中的标签更新。本申请实施例可应用于金融机构的相关沟通场景，比如医疗保险报销的咨询场景。
此外，本申请实施例还提出一种计算机可读存储介质，该计算机可读存储介质可以是易失性的，也可以是非易失性的，该计算机可读存储介质可以是硬盘、多媒体卡、SD卡、闪存卡、SMC、只读存储器（ROM）、可擦除可编程只读存储器（EPROM）、便携式紧致盘只读存储器（CD-ROM）、USB存储器等等中的任意一种或者几种的任意组合。所述计算机可读存储介质中包括存储数据区和存储程序区，存储数据区存储根据区块链节点的使用所创建的数据，存储程序区存储有语音信息录入程序10，所述语音信息录入程序10被处理器执行时实现如下操作：
采集用户对所述电子设备1发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；
接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；
响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；
判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
需要强调的是，本申请之计算机可读存储介质的具体实施方式与上述语音信息录入方法的具体实施方式大致相同，在此不再赘述。
在另一个实施例中，本申请所提供的语音信息录入方法，为进一步保证上述所有出现的数据的私密和安全性，上述所有数据还可以存储于一区块链的节点中。例如知识图谱、待识别文本等等，这些数据均可存储在区块链节点中。
需要说明的是，本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串使用密码学方法相关联产生的数据块，每个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
本申请之计算机可读存储介质的具体实施方式与上述语音信息录入方法的具体实施方式大致相同，在此不再赘述。
需要说明的是，上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。并且本文中的术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、装置、物品或者方法不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、装置、物品或者方法所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、装置、物品或者方法中还存在另外的相同要素。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，电子设备，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种语音信息录入方法，应用于电子设备，其中，所述方法包括：采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
- 如权利要求1所述的语音信息录入方法，其中，所述接收用户输入的实时语音信息，包括：接收用户间断输入的多段实时语音信息。
- 如权利要求2所述的语音信息录入方法，其中，所述接收用户间断输入的多段实时语音信息，包括：向用户发送对应于第一标签类型的录音提示信息，当接收到用户输入的与所述第一标签类型对应的实时语音信息后，向用户发送对应于第二标签类型的录音提示信息，并接收用户输入的与所述第二标签类型对应的实时语音信息。
- 如权利要求2所述的语音信息录入方法，其中，所述接收用户间断输入的多段实时语音信息，包括：接收用户输入的实时语音信息；响应用户暂停录音的指令，停止接收语音信息；响应用户继续录音的指令，继续接收用户输入的实时语音信息。
- 如权利要求1所述的语音信息录入方法，其中，所述将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果，包括：将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，计算所述一个或多个标签与所述自然语言文本的匹配度，当判断匹配度大于阈值时，匹配成功；当判断所述匹配度小于或等于所述阈值时，匹配失败。
- 如权利要求5所述的语音信息录入方法，其中，所述输出所述自然语言文本与所述一个或多个标签的匹配结果，包括：将匹配成功的标签以第一显示状态展示，将匹配失败的标签以第二显示状态展示，将所述自然语言文本以第三显示状态展示，所述第一显示状态、所述第二显示状态及所述第三显示状态不同。
- 如权利要求1所述的语音信息录入方法，其中，在所述响应用户发出的存储匹配结果的指令之前，所述方法还包括：响应用户的修改指令，在所述自然语言文本中删除和/或新增文字；将修改后的自然语言文本与所述预先设置的一个或多个标签一一进行匹配，输出新的匹配结果。
- 一种语音信息录入装置，应用于电子设备，其中，所述语音信息录入装置包括：登录模块：用于采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；转换模块：用于接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；存储模块：用于响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；更新模块：用于判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
- 一种电子设备，其中，所述电子设备包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如下步骤：采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP;接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果;响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
- 如权利要求9所述的电子设备，其中，所述接收用户输入的实时语音信息，包括：接收用户间断输入的多段实时语音信息。
- 如权利要求10所述的电子设备，其中，所述接收用户间断输入的多段实时语音信息，包括：向用户发送对应于第一标签类型的录音提示信息，当接收到用户输入的与所述第一标签类型对应的实时语音信息后，向用户发送对应于第二标签类型的录音提示信息，并接收用户输入的与所述第二标签类型对应的实时语音信息。
- 如权利要求10所述的电子设备，其中，所述接收用户间断输入的多段实时语音信息，包括：接收用户输入的实时语音信息；响应用户暂停录音的指令，停止接收语音信息；响应用户继续录音的指令，继续接收用户输入的实时语音信息。
- 如权利要求9所述的电子设备，其中，所述将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果，包括：将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，计算所述一个或多个标签与所述自然语言文本的匹配度，当判断匹配度大于阈值时，匹配成功；当判断所述匹配度小于或等于所述阈值时，匹配失败。
- 如权利要求13所述的电子设备，其中，所述输出所述自然语言文本与所述一个或多个标签的匹配结果，包括：将匹配成功的标签以第一显示状态展示，将匹配失败的标签以第二显示状态展示，将所述自然语言文本以第三显示状态展示，所述第一显示状态、所述第二显示状态及所述第三显示状态不同。
- 如权利要求9所述的电子设备，其中，在所述响应用户发出的存储匹配结果的指令之前，所述至少一个处理器还执行以下步骤：响应用户的修改指令，在所述自然语言文本中删除和/或新增文字；将修改后的自然语言文本与所述预先设置的一个或多个标签一一进行匹配，输出新的匹配结果。
- 一种计算机可读存储介质，其中，所述计算机可读存储介质中包括存储数据区和存储程序区，存储数据区存储根据区块链节点的使用所创建的数据，存储程序区存储有语音信息录入程序，所述语音信息录入程序被处理器执行时，实现如下步骤：采集用户对所述电子设备发出的语音解锁指令，匹配所述语音解锁指令的声纹与预先设置的登录语音指令的声纹，当声纹匹配成功时，查找与所述登录语音指令对应的账号信息，登录与所述账号信息对应的应用APP；接收用户输入的实时语音信息，将所述实时语音信息转换为自然语言文本，并将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果；响应用户发出的存储匹配结果的指令，保存所述自然语言文本及匹配成功的标签至预设存储地址；判断所述预设存储地址中是否存储有与所述自然语言文本相关联的历史标签，当判断结果为是时，计算所述历史标签与所述匹配成功的标签的相似度，当相似度大于预设值时，将所述历史标签更新为所述匹配成功的标签。
- 如权利要求16所述的计算机可读存储介质，其中，所述接收用户输入的实时语音信息，包括：接收用户间断输入的多段实时语音信息。
- 如权利要求17所述的计算机可读存储介质，其中，所述接收用户间断输入的多段实时语音信息，包括：向用户发送对应于第一标签类型的录音提示信息，当接收到用户输入的与所述第一标签类型对应的实时语音信息后，向用户发送对应于第二标签类型的录音提示信息，并接收用户输入的与所述第二标签类型对应的实时语音信息。
- 如权利要求17所述的计算机可读存储介质，其中，所述接收用户间断输入的多段实时语音信息，包括：接收用户输入的实时语音信息；响应用户暂停录音的指令，停止接收语音信息；响应用户继续录音的指令，继续接收用户输入的实时语音信息。
- 如权利要求16所述的计算机可读存储介质，其中，所述将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，输出所述自然语言文本与所述一个或多个标签的匹配结果，包括：将所述自然语言文本与预先设置的一个或多个标签一一进行匹配，计算所述一个或多个标签与所述自然语言文本的匹配度，当判断匹配度大于阈值时，匹配成功；当判断所述匹配度小于或等于所述阈值时，匹配失败。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011075452.8 | 2020-10-09 | ||
| CN202011075452.8A CN112214997A (zh) | 2020-10-09 | 2020-10-09 | 语音信息录入方法、装置、电子设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022073508A1 true WO2022073508A1 (zh) | 2022-04-14 |
Family
ID=74054332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/122836 WO2022073508A1 (zh) | 2020-10-09 | 2021-10-09 | 语音信息录入方法、装置、电子设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112214997A (zh) |
| WO (1) | WO2022073508A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112214997A (zh) * | 2020-10-09 | 2021-01-12 | 深圳壹账通智能科技有限公司 | 语音信息录入方法、装置、电子设备及存储介质 |
| CN113221990B (zh) * | 2021-04-30 | 2024-02-23 | 平安科技（深圳）有限公司 | 信息录入方法、装置及相关设备 |
| CN116663534A (zh) * | 2023-08-02 | 2023-08-29 | 中国标准化研究院 | 一种基于自然语言处理的文本数据统计分析系统及方法 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105827581A (zh) * | 2015-06-30 | 2016-08-03 | 维沃移动通信有限公司 | 一种登陆账号的方法和终端 |
| CN107785021A (zh) * | 2017-08-02 | 2018-03-09 | 上海壹账通金融科技有限公司 | 语音输入方法、装置、计算机设备和介质 |
| CN108287815A (zh) * | 2017-12-29 | 2018-07-17 | 重庆小雨点小额贷款有限公司 | 信息录入方法、装置、终端及计算机可读存储介质 |
| WO2019142976A1 (ko) * | 2018-01-16 | 2019-07-25 | 주식회사 머니브레인 | 사용자 발화 입력에 대한 대화 응답 후보를 표시하도록 하는 디스플레이 제어 방법, 컴퓨터 판독가능 기록 매체 및 컴퓨터 장치 |
| CN111274351A (zh) * | 2020-01-13 | 2020-06-12 | 深圳壹账通智能科技有限公司 | 自动调整用户优先级的方法、装置、电子设备及存储介质 |
| CN112214997A (zh) * | 2020-10-09 | 2021-01-12 | 深圳壹账通智能科技有限公司 | 语音信息录入方法、装置、电子设备及存储介质 |
-
2020
- 2020-10-09 CN CN202011075452.8A patent/CN112214997A/zh active Pending
-
2021
- 2021-10-09 WO PCT/CN2021/122836 patent/WO2022073508A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105827581A (zh) * | 2015-06-30 | 2016-08-03 | 维沃移动通信有限公司 | 一种登陆账号的方法和终端 |
| CN107785021A (zh) * | 2017-08-02 | 2018-03-09 | 上海壹账通金融科技有限公司 | 语音输入方法、装置、计算机设备和介质 |
| CN108287815A (zh) * | 2017-12-29 | 2018-07-17 | 重庆小雨点小额贷款有限公司 | 信息录入方法、装置、终端及计算机可读存储介质 |
| WO2019142976A1 (ko) * | 2018-01-16 | 2019-07-25 | 주식회사 머니브레인 | 사용자 발화 입력에 대한 대화 응답 후보를 표시하도록 하는 디스플레이 제어 방법, 컴퓨터 판독가능 기록 매체 및 컴퓨터 장치 |
| CN111274351A (zh) * | 2020-01-13 | 2020-06-12 | 深圳壹账通智能科技有限公司 | 自动调整用户优先级的方法、装置、电子设备及存储介质 |
| CN112214997A (zh) * | 2020-10-09 | 2021-01-12 | 深圳壹账通智能科技有限公司 | 语音信息录入方法、装置、电子设备及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112214997A (zh) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022073508A1 (zh) | 语音信息录入方法、装置、电子设备及存储介质 | |
| WO2019091103A1 (zh) | 简历筛选方法、电子装置及可读存储介质 | |
| WO2021151270A1 (zh) | 图像结构化数据提取方法、装置、设备及存储介质 | |
| US20240320526A1 (en) | Computerized System and Method of Open Account Processing | |
| CN112507125A (zh) | 三元组信息提取方法、装置、设备及计算机可读存储介质 | |
| CN111861768B (zh) | 基于人工智能的业务处理方法、装置、计算机设备及介质 | |
| CN106485261B (zh) | 一种图像识别的方法和装置 | |
| US20170344948A1 (en) | Coordinated mobile access to electronic medical records | |
| CN112632278A (zh) | 一种基于多标签分类的标注方法、装置、设备及存储介质 | |
| CN113761577B (zh) | 一种大数据脱敏的方法、装置、计算机设备及存储介质 | |
| CN113868419B (zh) | 基于人工智能的文本分类方法、装置、设备及介质 | |
| CN112836521A (zh) | 问答匹配方法、装置、计算机设备及存储介质 | |
| CN112395401B (zh) | 自适应负样本对采样方法、装置、电子设备及存储介质 | |
| CN110428342B (zh) | 数据修复方法、服务器、客服端及存储介质 | |
| CN116681045A (zh) | 报表生成方法、装置、计算机设备及存储介质 | |
| CN116704528A (zh) | 票据识别核验方法、装置、计算机设备及存储介质 | |
| CN114626352B (zh) | 报表自动化生成方法、装置、计算机设备及存储介质 | |
| CN114968725A (zh) | 任务依赖关系校正方法、装置、计算机设备及存储介质 | |
| CN116166858A (zh) | 基于人工智能的信息推荐方法、装置、设备及存储介质 | |
| CN112685439B (zh) | 针对风控系统的造数方法、系统、装置及存储介质 | |
| US20220197898A1 (en) | System and method for implementing intelligent service request remedy | |
| CN113806372B (zh) | 新数据信息构建方法、装置、计算机设备及存储介质 | |
| CN114637823A (zh) | 一种指标口径确定方法、装置、计算机设备及存储介质 | |
| CN115827047A (zh) | 请求处理方法、装置、计算机设备及存储介质 | |
| CN115731057A (zh) | 信息生成方法、装置、计算机设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21877025 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 01.09.2023) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21877025 Country of ref document: EP Kind code of ref document: A1 |