WO2020207025A1 - 基于语音交互的语音外呼方法、装置及终端 - Google Patents

基于语音交互的语音外呼方法、装置及终端 Download PDF

Info

Publication number
WO2020207025A1
WO2020207025A1 PCT/CN2019/120613 CN2019120613W WO2020207025A1 WO 2020207025 A1 WO2020207025 A1 WO 2020207025A1 CN 2019120613 W CN2019120613 W CN 2019120613W WO 2020207025 A1 WO2020207025 A1 WO 2020207025A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
outbound
terminal device
text information
communication
Prior art date
Application number
PCT/CN2019/120613
Other languages
English (en)
French (fr)
Inventor
姬小玉
郑如刚
徐志成
Original Assignee
深圳壹账通智能科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2020207025A1 publication Critical patent/WO2020207025A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/22—Arrangements for supervision, monitoring or testing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/42136—Administration or customisation of services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
    • H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
    • H04M3/4936—Speech interaction details

Definitions

  • This application relates to the field of computer technology, and in particular to a voice outbound call method, device and terminal based on voice interaction.
  • automatic voice outbound calls have realized the characteristics of fast, convenient, and efficient.
  • many enterprise users have established their own telemarketing system platforms. Used to expand and maintain customers and increase corporate efficiency.
  • there are more and more application scenarios for automatic voice outbound calls including telemarketing, market research, and collection of debts.
  • the content of automatic voice outbound calls is fixed voice, and the content of outbound voice cannot be changed according to the information returned by the user's terminal device, and the intelligence of voice outbound calls is low.
  • the embodiments of the present application provide a voice outbound call method, device, and terminal based on voice interaction, which can adjust the content of the output voice according to the acquired environmental volume, thereby improving the intelligence of the voice outbound call.
  • an embodiment of the present application provides a voice outbound call method based on voice interaction, and the method includes:
  • the system environment information including system time and/or system load
  • the system environment information When it is detected that the system environment information satisfies a preset voice outbound call condition, acquiring an outbound call plan corresponding to the voice outbound call condition, where the outbound call plan includes an outbound call number and at least one outbound voice;
  • the communication connection is successfully established with the terminal device, acquiring the environmental volume value of the terminal device, and determining the target outbound voice from the at least one outbound voice according to the environmental volume value;
  • an embodiment of the present application provides a voice outbound call device based on voice interaction, and the device includes:
  • the detection module is configured to detect whether the system environment information meets preset voice outgoing call conditions, and the system environment information includes system time and/or system load;
  • the acquiring module is further configured to, when it is detected that the system environment information meets a preset voice outbound condition, obtain an outbound call plan corresponding to the voice outbound condition, and the outbound call plan includes an outbound number and At least one outgoing voice;
  • a sending module configured to send a communication request to the terminal device corresponding to the outbound number
  • the acquiring module is further configured to acquire the environmental volume value of the terminal device if the communication connection with the terminal device is successfully established;
  • a determining module configured to determine a target outbound voice from the at least one outbound voice according to the environmental volume value
  • the sending module is also used to send the target outbound voice to the terminal device.
  • an embodiment of the present application provides a terminal, including a processor, an input device, an output device, and a memory.
  • the processor, input device, output device, and memory are connected to each other, wherein the memory is used to store a computer A program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method described in the first aspect.
  • an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the program instructions are When executing, the processor is caused to execute the method described in the first aspect.
  • the terminal can adjust the content of the output voice according to the acquired environmental volume, which improves the intelligence of voice outbound calls.
  • FIG. 1 is a schematic flowchart of a voice outbound call method based on voice interaction in an embodiment of the present application
  • FIG. 2 is a schematic flowchart of another voice outbound call method based on voice interaction in an embodiment of the present application
  • FIG. 3 is a schematic structural diagram of a voice outbound call device based on voice interaction in an embodiment of the present application
  • Fig. 4 is a schematic structural diagram of a terminal in an embodiment of the present application.
  • the voice outbound method provided by the embodiments of the present application is implemented in a terminal, and the terminal includes electronic devices such as a smart phone, a tablet computer, a digital audio and video player, an electronic reader, a handheld game console, or a vehicle-mounted electronic device.
  • the terminal includes electronic devices such as a smart phone, a tablet computer, a digital audio and video player, an electronic reader, a handheld game console, or a vehicle-mounted electronic device.
  • FIG. 1 is a schematic flowchart of a voice outbound call method based on voice interaction in an embodiment of the present application. As shown in Figure 1, the process of the voice outbound call method based on voice interaction in this embodiment may include:
  • the terminal obtains system environment information, and detects whether the system environment information meets preset voice outbound conditions.
  • the system environment information includes system time and system load, where the system time is the current time recorded by the terminal, and the system load includes the number of outbound tasks currently processed by the system.
  • the system load can also be the ratio of the number of outbound tasks currently processed by the terminal to the maximum number of outbound calls that the terminal can handle at the same time.
  • the terminal includes electronic devices such as mobile phones, computers, and tablets. After obtaining the system environment information, the terminal will detect whether the system environment information meets the preset voice outgoing call conditions. In specific implementation, the voice outbound call conditions can be preset by the user corresponding to the terminal.
  • the system environment information is determined Meet the preset outbound conditions.
  • the user uses the preset time point and the load threshold as the voice outbound call condition, that is, when the terminal detects that the time reaches the preset time point and the load is less than the load threshold, the terminal determines that the system environment information meets the voice outbound call condition.
  • the terminal When the terminal detects that the system environment information meets the preset voice outbound call condition, acquire an outbound call plan corresponding to the voice outbound call condition, where the outbound call plan includes an outbound call number and at least one outbound voice.
  • the terminal when the terminal detects that the system environment information meets the preset outbound call conditions, it will obtain the outbound call plan corresponding to the voice outbound call condition, wherein each voice outbound call condition corresponds to one or more outbound call plans , Where the outbound call plan includes an outbound call number and at least one outbound voice. It should be noted that at least one outbound voice in the same outbound call plan is used to express the same semantics, but in terms of speech rate and voice volume. Or there are differences in the duration of the voice and the conciseness of the content, which can be preset by the user corresponding to the terminal.
  • S103 The terminal sends a communication request to the terminal device corresponding to the outbound number.
  • the terminal After the terminal determines the outbound call plan corresponding to the voice outbound condition, it sends a communication request to the terminal device corresponding to the outbound number in the outbound call plan, where the outbound number can be one or multiple , Which can be preset by the user corresponding to the terminal.
  • S104 If the communication connection with the terminal device corresponding to the outbound number is successfully established, obtain the environmental volume value of the terminal device, and determine the target outbound voice from at least one outbound voice according to the environmental volume value.
  • the terminal after the terminal sends a communication request to the terminal device corresponding to the outbound number, if the called user outputs a corresponding receiving operation on the terminal device, the terminal establishes a communication connection with the terminal device corresponding to the outbound number, Then the terminal obtains the environmental volume value (ie, the noise volume value) of the terminal device, where the called user is the user of the terminal device corresponding to the outbound number.
  • the environmental volume value sent by the terminal device corresponding to the outbound number can be obtained, where the environmental volume value may specifically be the terminal device corresponding to the outbound number The volume value of the noise in the environment.
  • the terminal After the terminal obtains the environmental volume value of the terminal device corresponding to the outbound number, it will determine the target outbound voice from at least one outbound voice according to the obtained environmental volume value.
  • the at least one outbound voice in the outbound call solution includes a first outbound voice and a second outbound voice, wherein the duration of the first outbound voice is greater than the duration of the second outbound voice, and the first The output volume value of the outbound voice is smaller than the output volume value of the second outbound voice.
  • the semantics of the first outbound voice and the second outbound voice are the introduction to car insurance, and the specific content of the first outbound voice is "Hello, vehicle insurance, that is, motor vehicle insurance, referred to as car insurance, also called car insurance. It refers to a kind of commercial insurance that compensates for personal injury or property damage caused by natural disasters or accidents.
  • Auto insurance is a type of property insurance. In the field of property insurance, auto insurance belongs to a relative Young insurance, this is because car insurance is produced and developed with the appearance and popularization of cars. "The duration of the first outbound voice is 30 seconds, and the output volume is 30 decibels.
  • the specific content of the second outbound voice is "Hello, vehicle insurance, namely motor vehicle insurance, referred to as car insurance, also known as car insurance. It refers to the loss of life or property caused by natural disasters or accidents of motor vehicles.
  • a kind of commercial insurance for liability the duration of the second outbound voice is 15 seconds, and the output volume value is 60 decibels.
  • the preset volume value is 40 decibels.
  • the at least one outbound voice included in the outbound call plan includes outbound voice 1, outbound voice 2... outbound voice N, where N is a positive integer, which can be specifically configured by the user corresponding to the terminal It is preset during outbound call plan.
  • the outbound voice configured in the outbound call plan is shown in Table 1:
  • Outbound voice 1 60 seconds 30 dB 0-10 dB
  • Outbound voice 2 50 seconds 40 dB 11-20 dB
  • Outbound voice 3 40 seconds 50 dB 21-30 dB ... ... ... ...
  • Outbound voice N 20 seconds 70 dB >60 dB
  • Outbound Voice 1, Outbound Voice 2...Outbound Voice N can have different text content for each outbound voice, but they are all used to represent the same semantics, such as for debt collection, business Introduction, market research, etc. As the number of outbound voices increases, the text content corresponding to outbound voices can be more and more concise, the output time is shorter, and the output volume value becomes larger. It can be seen from Table 1 that when the terminal detects that the environmental volume value is between 0-10 decibels, the outbound voice 1 is determined as the target outbound voice. When the terminal detects that the environmental volume value is between 10-20 decibels, Then the outbound voice 2 is determined as the target outbound voice.
  • S105 The terminal sends the target outbound voice to the terminal device corresponding to the outbound number.
  • the terminal device corresponding to the outbound number sends the target outbound voice.
  • the terminal after the terminal establishes a communication connection with the terminal device corresponding to the outgoing call number, it will obtain the environmental volume value sent by the terminal device.
  • the terminal determines the voice content that needs to be output for the device corresponding to the outgoing call number according to the received environmental volume value. If the environmental volume value obtained by the terminal is large, it will output a simple voice solution and use a large volume value for voice output , So that the called user can hear the voice content sent by the terminal clearly. If the environmental volume value acquired by the terminal is small, the terminal can output a detailed voice plan and use a moderate volume value for voice output.
  • Fig. 2 is a schematic flowchart of another voice outbound call method based on voice interaction in an embodiment of the present application. As shown in Figure 2, the process of the voice outbound method based on voice interaction in this embodiment may include:
  • the terminal obtains system environment information, and detects whether the system environment information meets preset voice outbound conditions.
  • the terminal system environment information includes system time and system load, where the system load can be the ratio of the number of outbound tasks currently processed by the terminal to the maximum number of outbound tasks that the terminal can process simultaneously, and the preset voice outbound calls
  • the specific conditions can be preset time point and preset load.
  • each voice outbound call condition can correspond to multiple outbound call plans, and further Yes, each outbound call plan contains one or more outbound numbers, and at least one voice that needs to be output for the outbound number.
  • S203 The terminal sends a communication request to the terminal device corresponding to the outbound number.
  • the terminal when the terminal detects that the system environment information meets the preset voice outbound conditions, it will determine the outbound number in the outbound call plan corresponding to the outbound condition, and send it to the terminal device corresponding to the outbound number Communication request.
  • the terminal detects whether the call duration of the communication request is greater than the third preset duration, where the call duration can be the outbound number
  • the duration of the corresponding terminal device ringing, the third preset duration may be 15 seconds, 20 seconds, etc., which may be preset by the user corresponding to the terminal. If the terminal detects that the call duration is greater than the third preset duration, the terminal detects the number of communication requests sent to the terminal device corresponding to the outbound number within the preset time period, where the preset time period may be 2 times before the current time node.
  • the terminal determines that the number of calls is less than the preset number, the terminal sends a communication request to the terminal device corresponding to the outbound number.
  • the third preset duration can be determined as the longest ringing duration of the terminal device, that is, the terminal device will automatically disconnect the communication request when the ringing duration exceeds the maximum ringing duration, and the terminal will determine whether the call duration is greater than the third preset duration. Set the duration. If yes, the terminal determines that the called user may have failed the communication connection due to the absence of the terminal device. The terminal continues to detect that the number of communication requests sent to the called user is less than the preset number of times. After time, the communication request is sent to the terminal device again. If the call duration is less than the third preset duration, the terminal determines that the called user refuses to receive the communication request, and the terminal may no longer send the communication request with the called terminal device for a period of time.
  • step S204 is executed.
  • the terminal after the terminal sends a communication request to the terminal device corresponding to the outgoing call number, if the called user outputs a corresponding receiving operation on the terminal device, so that the terminal establishes a communication connection with the terminal device corresponding to the outgoing call number, then The terminal obtains the environmental volume value (ie, noise volume value) of the terminal device. Specifically, after the terminal establishes a communication connection with the terminal device corresponding to the outbound number, it can obtain the environmental volume value sent by the terminal device corresponding to the outbound number.
  • the environmental volume value may specifically be the volume value of noise in the environment where the terminal device corresponding to the outbound number is located. After the terminal obtains the environmental volume value of the terminal device corresponding to the outbound number, it will determine the target outbound voice from at least one outbound voice according to the obtained environmental volume value.
  • S205 The terminal sends the target outbound voice to the terminal device corresponding to the outbound number.
  • S206 If the terminal receives the voice information returned by the terminal device, it determines the target voice response for the terminal device according to the voice information and the environmental volume value, and outputs the target voice response.
  • the terminal After the terminal sends the target outbound voice to the terminal device corresponding to the outbound number, if it receives the voice information returned by the terminal device, it will determine the target voice response for the terminal device based on the voice information and the environmental volume value.
  • the terminal converts the received voice information into text information, and calculates the similarity between the text information and at least one reference text information pre-stored in the database.
  • the specific calculation method of similarity includes that the terminal separately performs word segmentation processing on each reference text information in the text information and at least one pre-stored reference text information, to obtain the first phrase set corresponding to the text information and the corresponding reference text information.
  • the terminal detects the number of identical phrases contained in the first phrase set and each second phrase set, and compares the number of the same phrase corresponding to each second phrase set to the total number of phrases in each second phrase set The ratio is determined as the similarity between the text information and each reference text information.
  • the content obtained after the terminal converts the received voice information into text information is "vehicle insurance amount”
  • the reference text information pre-stored in the database includes “vehicle insurance type, vehicle insurance amount, medical insurance amount”
  • each The word segmentation results of the reference text information and the similarity with the text information are shown in Table 2:
  • Vehicle insurance amount Vehicle insurance, amount To Reference text information 1 Vehicle insurance type Vehicle, insurance, type 66.7% Reference text information 2 Vehicle insurance amount Vehicle, insurance, amount 100% Reference text information 3 Medical insurance amount Medical care, insurance, amount 66.7%
  • reference text information 2 has the highest similarity to the text information.
  • the terminal determines the similarity of each reference text information to the text information, it will also determine at least one reference text in the reference text information with the highest similarity to the text information.
  • Information and obtain preset at least one voice response corresponding to the reference text information with the highest similarity to the text information, and the terminal determines the target voice response from the at least one voice response according to the environmental volume value. Further, the terminal determines the target voice response from at least one voice response according to the environmental volume value.
  • reference text information 2 has the highest similarity with text information, and the terminal obtains at least one voice response corresponding to reference text information 2, as shown in Table 3:
  • the voice reply 1, voice reply 2 in Table 3 the voice reply 1, voice reply 2 in Table 3...
  • the text content of each voice reply in voice reply N can be preset by the user corresponding to the terminal. As the number of the voice reply increases, the text content corresponding to the voice reply can be changed. The more concise, the shorter the output time, and the larger the output volume value. It can be seen from Table 3 that when the terminal detects that the environmental volume value is between 0-10 decibels, it will determine voice response 1 as the target voice response, and when the terminal detects that the environmental volume value is between 10-20 decibels, it will Voice response 2 is determined as the target voice response.
  • the terminal after the terminal detects that the communication of the terminal device corresponding to the outbound number is disconnected, it will acquire the communication content of this communication, where the communication content includes the duration of the communication and the type of target outbound voice.
  • the target outbound voice types include collection type, business recommendation type, etc.
  • the collection target outbound voice is used to collect arrears, and the business recommendation target outbound voice is used to recommend different types of services.
  • the type of target outbound voice may also include market research type, telemarketing type, etc., which is not limited in the embodiment of the application.
  • the terminal determines the next outbound call plan of the terminal device corresponding to the outbound number according to the communication content of the communication.
  • the terminal detects whether the duration of this communication is less than the first preset. Set the duration. If the terminal detects that the duration of this communication is less than the first preset duration, the terminal needs to send a communication request to the terminal device again, and send the target outbound voice to the terminal device after the terminal device establishes a communication connection .
  • the first preset duration may be 10 seconds, 15 seconds, etc., which may be preset by the research and development personnel.
  • the terminal after the terminal detects that the communication with the terminal device corresponding to the outgoing call number is disconnected, it determines from the communication content that the target outgoing voice type is a service recommendation type, and the terminal detects whether the duration of this communication is greater than the first 2.
  • the preset duration if the duration of this communication is greater than the second preset duration, the terminal sends a communication request to the terminal device again after the preset time interval, and sends the target to the terminal device after establishing a communication connection with the terminal device Outbound voice.
  • the first preset time length may be 30 seconds, 60 seconds, etc.
  • the preset time interval may be 10 days, 15 days, etc., which can be preset by the R&D personnel.
  • the called user s interest in the recommended service can be determined according to the communication time. If the communication time is longer, it means that the called user is interested in the recommended service.
  • the terminal can be called again after a period of time. Users make business recommendations. Further, the terminal may also store the outbound number in a priority area. When a new service needs to be recommended, the terminal may preferentially call the terminal device corresponding to the outbound number stored in the priority area to improve the accuracy of service recommendation.
  • the terminal after the terminal establishes a communication connection with the terminal device corresponding to the outgoing call number, it will obtain the environmental volume value sent by the terminal device.
  • the terminal determines the voice content that needs to be output for the device corresponding to the outgoing call number according to the received environmental volume value. If the environmental volume value obtained by the terminal is large, it will output a simple voice solution and use a large volume value for voice output , So that the called user can hear the voice content sent by the terminal clearly. If the environmental volume value acquired by the terminal is small, the terminal can output a detailed voice plan and use a moderate volume value for voice output.
  • the voice response to the voice can be determined according to the similarity algorithm and the environmental volume value, which is that after the communication of the called user ends, the voice response is determined according to the duration of the call.
  • the next call plan of the called user improves the intelligence of voice outbound calls.
  • the voice outbound call device based on voice interaction provided by the embodiment of the present application will be described in detail below with reference to FIG. 3. It should be noted that the voice interaction-based voice outbound device shown in FIG. 3 is used to implement the method of the embodiment shown in FIG. 1 to FIG. 2 of the present application. For ease of description, only the same as the embodiment of the present application is shown. For the relevant parts, the specific technical details are not disclosed, please refer to the embodiments shown in Figures 1 to 2 of this application.
  • FIG. 3 is a schematic structural diagram of a voice outbound device based on voice interaction provided by this application.
  • the voice outbound device 30 based on voice interaction may include: an acquisition module 301, a detection module 302, a sending module 303, and a determination Module 304, conversion module 305, calculation module 306.
  • the obtaining module 301 is used to obtain system environment information
  • the detection module 302 is configured to detect whether the system environment information meets preset voice outbound conditions, and the system environment information includes system time and/or system load;
  • the acquiring module 301 is further configured to, when it is detected that the system environment information satisfies a preset voice outbound condition, obtain an outbound call plan corresponding to the voice outbound condition, and the outbound call plan includes an outbound number And at least one outgoing voice;
  • the sending module 303 is configured to send a communication request to the terminal device corresponding to the outbound number
  • the obtaining module 301 is further configured to obtain the environmental volume value of the terminal device if the communication connection with the terminal device is successfully established;
  • the determining module 304 is configured to determine a target outbound voice from the at least one outbound voice according to the environmental volume value
  • the sending module 303 is further configured to send the target outbound voice to the terminal device.
  • the at least one outbound voice includes a first outbound voice and a second outbound voice, and the duration of the first outbound voice is greater than the duration of the second outbound voice, and The output volume value of the first outbound voice is less than the output volume value of the second outbound voice, and the determining module 304 is specifically configured to:
  • the conversion module 305 is configured to convert the voice information into text information if the voice information returned by the terminal device is received;
  • the calculation module 306 is configured to calculate the similarity between the text information and each reference text information in at least one reference text information pre-stored in the database;
  • the determining module 304 is configured to determine the reference text information with the highest similarity to the text information in the at least one reference text information, and obtain the preset reference text information corresponding to the highest similarity with the text information.
  • the determining module 304 is configured to determine a target voice response from the at least one voice response according to the environmental volume value
  • the sending module 303 is configured to send the target voice response to the terminal device.
  • calculation module 306 is specifically configured to:
  • the ratio of the number of identical phrases corresponding to each second phrase set to the total number of phrases in each second phrase set is determined as the similarity between the text information and each of the reference text information.
  • the acquiring module 301 is further configured to acquire the communication content of the communication if it is detected that the communication with the terminal device is disconnected, and the communication content includes the duration of the communication and The type of the target outbound voice;
  • the detection module 302 is further configured to detect whether the duration of the communication is less than a first preset duration if the type of the target outbound voice is a collection type, and the collection-type target outbound voice is used for debt collection Payment collection;
  • the sending module 303 is further configured to send a communication request to the terminal device if the duration of the communication is less than the first preset duration, and to the terminal device after establishing a communication connection with the terminal device The device sends the target outbound voice.
  • the detection module 302 is further configured to detect whether the duration of the communication is greater than a second preset duration if the target outbound voice type is a service recommendation type, and the service recommendation Target outbound voice is used to recommend different types of services;
  • the sending module 303 is further configured to, if the duration of the communication is greater than the second preset duration, send a communication request to the terminal device after the preset time interval, and establish communication with the terminal device. After connecting, send the target outbound voice to the terminal device.
  • the detection module 302 is further configured to detect whether the call duration of the communication request is greater than a third preset duration if the communication connection with the terminal device fails to be established;
  • the detection module 302 is further configured to detect the number of communication requests sent to the terminal device within a preset time period if the call duration is greater than the third preset duration;
  • the sending module 303 is further configured to send a communication request to the terminal device if the number of times is less than the preset number of times.
  • the acquisition module 301 acquires system environment information; the detection module 302 detects whether the system environment information meets the preset voice outbound conditions, and when it is detected that the system environment information meets the preset voice outbound conditions , The acquiring module 301 acquires an outbound call plan corresponding to the voice outbound condition, the outbound plan including an outbound number and at least one outbound voice; the sending module 303 sends a communication to the terminal device corresponding to the outbound number Request; if the communication connection is successfully established with the terminal device, the obtaining module 301 obtains the environmental volume value of the terminal device; the determining module 304 determines the target outbound call from the at least one outbound voice according to the environmental volume value Voice; the sending module sends the target outgoing voice to the terminal device.
  • the terminal includes: at least one processor 401, an input device 403, an output device 404, a memory 405, and at least one communication bus 402.
  • the communication bus 402 is used to implement connection and communication between these components.
  • the input device 403 may be a control panel or a microphone
  • the output device 404 may be a display screen or the like.
  • the memory 405 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory.
  • the memory 405 may also be at least one storage device located far away from the foregoing processor 401.
  • the processor 401 may be combined with the device described in FIG. 3, the memory 405 stores a set of program codes, and the processor 401, the input device 403, and the output device 404 call the program codes stored in the memory 405 to perform the following operations:
  • the processor 401 is configured to obtain system environment information and detect whether the system environment information meets preset voice outbound conditions, and the system environment information includes system time and/or system load;
  • the processor 401 is configured to, when it is detected that the system environment information meets a preset voice outbound condition, obtain an outbound call plan corresponding to the voice outbound condition, where the outbound call plan includes an outbound number and at least one Kind of outgoing voice;
  • the output device 404 is configured to send a communication request to the terminal device corresponding to the outbound number
  • the input device 403 is configured to obtain the environmental volume value of the terminal device if the communication connection with the terminal device is successfully established;
  • the processor 401 is configured to determine a target outbound voice from the at least one outbound voice according to the environmental volume value
  • the output device 404 is configured to send the target outbound voice to the terminal device.
  • the at least one outbound voice includes a first outbound voice and a second outbound voice, and the duration of the first outbound voice is greater than the duration of the second outbound voice, and The output volume value of the first outbound voice is less than the output volume value of the second outbound voice, and the processor 401 is specifically configured to:
  • the processor 401 is specifically configured to:
  • the processor 401 is specifically configured to:
  • the ratio of the number of identical phrases corresponding to each second phrase set to the total number of phrases in each second phrase set is determined as the similarity between the text information and each of the reference text information.
  • the processor 401 is specifically configured to:
  • the communication content of the communication including the duration of the communication and the type of the target outbound voice
  • the type of the target outbound voice is a collection type, detecting whether the duration of the communication is less than a first preset duration, and the collection-type target outbound voice is used to collect arrears;
  • the output device 404 is further configured to send a communication request to the terminal device if the duration of the communication is less than the first preset duration, and send to the terminal device after establishing a communication connection with the terminal device The target outbound voice.
  • the processor 401 is further configured to detect whether the duration of the communication is greater than a second preset duration if the target outbound voice type is a service recommendation type, and the service recommendation type target Outbound voice is used to recommend different types of services;
  • the output device 404 is further configured to, if the duration of the communication is greater than the second preset duration, send a communication request to the terminal device after a preset time interval, and after establishing a communication connection with the terminal device Sending the target outbound voice to the terminal device.
  • the processor 401 is specifically configured to:
  • the output device 404 is further configured to send a communication request to the terminal device if the number of times is less than the preset number of times.
  • the processor 401 obtains system environment information, and detects whether the system environment information meets preset voice outgoing call conditions, and the system environment information includes system time and/or system load; When the system environment information satisfies the preset voice outgoing call condition, the processor 401 obtains an outgoing call plan corresponding to the voice outgoing call condition, and the outgoing call plan includes the outgoing call number and at least one outgoing call voice; the output device 404 Send a communication request to the terminal device corresponding to the outbound number; if the communication connection is successfully established with the terminal device, the input device 403 obtains the environmental volume value of the terminal device; the processor 401 obtains the environmental volume value of the terminal device according to the environmental volume value.
  • the target outbound voice is determined among the at least one outbound voice; the output device 404 sends the target outbound voice to the terminal device.
  • the content of the output voice can be adjusted according to the acquired environmental volume, which improves the intelligence of voice outbound calls.
  • the modules in the embodiments of the present application may be implemented by general integrated circuits, such as CPU (Central Processing Unit, central processing unit), or by ASIC (Application Specific Integrated Circuit, application specific integrated circuit).
  • CPU Central Processing Unit, central processing unit
  • ASIC Application Specific Integrated Circuit, application specific integrated circuit
  • the processor 401 may be a central processing unit (CPU), and the processor may also be other general-purpose processors or digital signal processors (DSP). , Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the bus 402 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component
  • EISA Extended Industry Standard Architecture
  • the bus 402 can be divided into The address bus, data bus, control bus, etc., for ease of presentation, FIG. 4 is only represented by a thick line, but it does not mean that there is only one bus or one type of bus.
  • the program can be stored in a computer-readable storage medium. At this time, it may include the procedures of the above-mentioned method embodiments.
  • the computer-readable storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请实施例公开了一种基于语音交互的语音外呼方法、装置及终端，其中，终端对应的用户可以预先设置语音外呼条件，当终端检测到当前满足语音外呼条件时，终端获取语音外呼条件对应的外呼号码，并向该外呼号码对应的终端设备发送通信请求，在与该终端设备建立通信连接之后，获取外呼号码对应的终端设备当前所处环境的环境音量值，并根据获取到的环境音量值确定需要向该终端设备发送的语音内容。通过实施上述方法，可以根据获取到的环境音量调整发送语音的内容，提升了语音外呼的智能性。

Description

基于语音交互的语音外呼方法、装置及终端
本申请要求于2019年4月12日提交中国专利局、申请号为2019103015548、申请名称为“基于语音交互的语音外呼方法、装置及终端”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。
技术领域
本申请涉及计算机技术领域，尤其涉及一种基于语音交互的语音外呼方法、装置及终端。
背景技术
随着技术的发展，自动语音外呼已经实现了快捷、方便、高效的特征，同时因其拥有省时、省力、低成本等天然的优点，很多企业用户都建立起自己的电话营销系统平台，用以扩大和维护客户，增加企业效益。同时，自动语音外呼的应用场景越来越多，包括电话营销、市场调查、欠款催收等场景。
目前，自动语音外呼的内容固定语音，无法根据用户的终端设备返回的信息而改变呼出语音的内容，语音外呼的智能性较低。
发明内容
本申请实施例提供一种基于语音交互的语音外呼方法、装置及终端，可以为根据获取到的环境音量调整输出语音的内容，提升了语音外呼的智能性。
第一方面，本申请实施例提供了一种基于语音交互的语音外呼方法，所述方法包括：
获取系统环境信息，并检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
向所述外呼号码对应的终端设备发送通信请求；
若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值，并根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
向所述终端设备发送所述目标外呼语音。
第二方面，本申请实施例提供了一种基于语音交互的语音外呼装置，所述装置包括：
获取模块，用于获取系统环境信息；
检测模块，用于检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
所述获取模块，还用于当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
发送模块，用于向所述外呼号码对应的终端设备发送通信请求；
所述获取模块，还用于若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值；
确定模块，用于根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
所述发送模块，还用于向所述终端设备发送所述目标外呼语音。
第三方面，本申请实施例提供了一种终端，包括处理器、输入设备、输出设备和存储器，所述处理器、输入设备、输出设备和存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令，执行第一方面所述的方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行第一方面所述的方法。
本申请实施例中，终端可以根据获取到的环境音量调整输出语音的内容，提升了语音外呼的智能性。
附图说明
为了更清楚地说明本申请实施例技术方案，下面将对实施例描述中所需要使用的附图进行说明。
图1是本申请实施例中的一种基于语音交互的语音外呼方法的流程示意图；
图2是本申请实施例中的另一种基于语音交互的语音外呼方法的流程示意图；
图3是本申请实施例中的一种基于语音交互的语音外呼装置的结构示意图；
图4是本申请实施例中的一种终端的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。
本申请实施例提供的语音外呼方法实现于终端，所述终端包括智能手机、平板电脑、数字音视频播放器、电子阅读器、手持游戏机或车载电子设备等电子设备。
图1是本申请实施例中一种基于语音交互的语音外呼方法的流程示意图。如图1所示，本实施例中的基于语音交互的语音外呼方法的流程可以包括：
S101、终端获取系统环境信息，并检测系统环境信息是否满足预设的语音外呼条件。
本申请实施例中，系统环境信息包括系统时间、系统负载，其中，系统时间为终端记录的当前的时间，系统负载包括系统当前处理的外呼任务的数量等。或者，系统负载也可以为终端当前处理的外呼任务数量与终端能同时处理的最大外呼数量的比值，终端包括手机、电脑、平板电脑等电子设备。终端获取到系统环境信息之后，将检测该系统环境信息是否满足预设的语音外呼条件。具体实现中，语音外呼条件可以由该终端对应的用户预先设定，如用户将预设时间点作为语音外呼条件，则当终端检测到时间到达该预设时间点时，确定系统环境信息满足预设的外呼条件。或者，用户将预设时间点以及负载量阈值作为语音外呼条件，即当终端检测当时间到达预设时间点，且负载量小于负载量阈值时，终端确定系统环境信息满足语音外呼条件。
S102、当终端检测到系统环境信息满足预设的语音外呼条件时，获取与语音外呼条件对应的外呼方案，外呼方案包括外呼号码以及至少一种外呼语音。
本申请实施例中，终端检测到系统环境信息满足预设的外呼条件时，将获取该语音外呼条件对应的外呼方案，其中，每个语音外呼条件对应一个或多个外呼方案，其中，外呼方案包括外呼号码以及至少一种外呼语音，需要说明的是，同一外呼方案中的至少一种外呼语音用于表达相同的语义，但在语速、语音音量值或语音的时长、内容的简洁程度上存在差异，具体可以由终端对应的用户预先设置。
S103、终端向外呼号码对应的终端设备发送通信请求。
本申请实施例中，终端确定了语音外呼条件对应的外呼方案之后，将向外呼方案中外呼号码对应的终端设备发送通信请求，其中，外呼号码可以为一个，也可以是多个，具体可以由终端对应的用户预先设置。
S104、若成功与外呼号码对应的终端设备建立通信连接，则获取终端设备的环境音量值，并根据环境音量值从至少一种外呼语音中确定目标外呼语音。
本申请实施例中，终端向外呼号码对应的终端设备发送通信请求之后，若被呼叫用户在终端设备上输出了相应的接收操作，使得终端与外呼号码对应的终端设备建立了通信连接，则终端获取终端设备的环境音量值(即噪音音量值)，其中，被呼叫用户为外呼号码对应的终端设备的用户。具体的，当终端与外呼号码对应的终端设备建立了通信连接之后，可以获取到外呼号码对应的终端设备发送的环境音量值，其中，环境音量值具体可以为外呼号码对应的终端设备所处环境中噪声的音量值。终端获取到外呼号码对应的终端设备的环境音量值之后，将根据获取到的环境音量值从至少一种外呼语音中确定目标外呼语音。
在一种实现方式中，外呼方案中至少一种外呼语音包括第一外呼语音和第二外呼语音，其中，第一外呼语音的时长大于第二外呼语音的时长，第一外呼语音的输出音量值小于第二外呼语音的输出音量值。终端获取到外呼号码对应的终端设备发送的环境音量值之后，将检测该环境音量值是否小于预设音量值，若该环境音量值小于预设音量值，则将第一外呼语音确定为目标外呼语音，若环境音量值大于或等于预设音量值，则将第二外呼语音确定为目标外呼语音。
举例说明，第一外呼语音和第二外呼语音的语义都为车险简介，第一外呼语音的具体内容为“您好，车辆保险，即机动车辆保险，简称车险，也称作汽车保险。它是指对机动车辆由于自然灾害或意外事故所造成的人身伤亡或财产损失负赔偿责任的一种商业保险。汽车保险是财产保险的一种，在财产保险领域中，汽车保险属于一个相对年轻的险种，这是由于汽车保险是伴随着汽车的出现和普及而产生和发展的。”第一外呼语音的时长为30秒，且输出音量值为30分贝。第二外呼语音的具体内容为“您好，车辆保险，即机动车辆保险，简称车险，也称作汽车保险它是指对机动车辆由于自然灾害或意外事故所造成的人身伤亡或财产损失负赔偿责任的一种商业保险”，第二外呼语音的时长为15秒，且输出音量值为60分贝。预设音量值为40分贝，当终端检测到外呼号码对应的终端设备发送的环境音量值小于40分贝时，则确定第一外呼语音作为目标外呼语音，当终端检测到外呼号码对应的终端设备返回的音量值大于或等于40分贝时，则确定第二外呼语音作为目标外呼语音。
在一种实现方式中，外呼方案包括的至少一种外呼语音包括外呼语音1、外呼语音2…外呼语音N，其中，N为正整数，具体可以由终端对应的用户在配置外呼方案时预先设置。 其中，外呼方案中配置的外呼语音具体如表1所示：
表1
编号 时长 输出音量值 环境音量值
外呼语音1 60秒 30分贝 0-10分贝
外呼语音2 50秒 40分贝 11-20分贝
外呼语音3 40秒 50分贝 21-30分贝
… … … …
外呼语音N 20秒 70分贝 >60分贝
需要说明的是，表1中外呼语音1、外呼语音2…外呼语音N中每种外呼语音的文字内容可以不同，但都用于表示相同的语义，如用于欠款催收、业务介绍、市场调查等，随着外呼语音的编号的增加，外呼语音对应的文字内容可以越来越简洁，输出时长越短，且输出音量值越来越大。由表1可知，当终端检测到环境音量值在0-10分贝之间时，则将外呼语音1确定为目标外呼语音，当终端检测到环境音量值在10-20分贝之间时，则将外呼语音2确定为目标外呼语音。
S105、终端向外呼号码对应的终端设备发送目标外呼语音。
本申请实施例中，终端确定了目标外呼语音之后，将向外呼号码对应的终端设备发送该目标外呼语音。
本申请实施例中，终端在与外呼号码对应的终端设备建立通信连接之后，将获取到该终端设备发送的环境音量值。终端根据接收到的环境音量值确定需要针对外呼号码对应的设备输出的语音内容，若终端获取到的环境音量值较大，则输出简洁的语音方案，并采用较大的音量值进行语音输出，使得被呼叫用户可以听清终端发送的语音内容。若终端获取到的环境音量值较小，则终端可以输出详细的语音方案，并采用适中的音量值进行语音输出。通过上述方式，可以保证被呼叫用户即使处于噪音较大的环境中也能听清终端发送的语音内容，在噪音较小的环境中可以接收到详细的语音介绍，提升了用户体验以及语音外呼的智能性。
图2是本申请实施例中另一种基于语音交互的语音外呼方法的流程示意图。如图2所示，本实施例中的基于语音交互的语音外呼方法的流程可以包括：
S201、终端获取系统环境信息，并检测系统环境信息是否满足预设的语音外呼条件。
本申请实施例中，终端系统环境信息包括系统时间和系统负载，其中，系统负载可以为终端当前处理的外呼任务数量与终端能同时处理的最大外呼任务数量的比值，预设语音外呼条件具体可以预设时间点和预设负载。当终端检测到当前系统时间到达预设时间点且当前负载小于预设负载率时，则确定系统环境信息满足预设外呼条件。
S202、当终端检测到系统环境信息满足预设的语音外呼条件时，获取与语音外呼条件对应的外呼方案，外呼方案包括外呼号码以及至少一种外呼语音。
本申请实施例中，终端检测到系统环境信息满足预设的外呼条件时，将获取语音外呼条件对应的外呼方案，其中，每个语音外呼条件可以对应多个外呼方案，进一步的，每个外呼方案中包含一个或多个外呼号码，以及针对该外呼号码需要输出的至少一种语音。
S203、终端向外呼号码对应的终端设备发送通信请求。
本申请实施例中，终端检测到系统环境信息满足预设的语音外呼条件时，将确定该外呼条件对应的外呼方案中的外呼号码，并向该外呼号码对应的终端设备发送通信请求。
若与外呼号码对应的终端设备建立通信连接失败，即被呼叫用户未接听该通信请求，则终端检测该通信请求的呼叫时长是否大于第三预设时长，其中，呼叫时长可以为外呼号码对应的终端设备响铃的时长，第三预设时长可以为15秒、20秒等，具体可以由终端对应的用户预先设置。若终端检测到呼叫时长大于第三预设时长，则终端检测预设时间段内向该外呼号码对应的终端设备发送通信请求的次数，其中，预设时间段可以是当前时间节点的之前的2小时、1小时等，若终端确定呼叫次数小于预设次数，则终端向该外呼号码对应的终端设备发送通信请求。通过上述方式，可以将第三预设时长确定为终端设备的最长响铃时长，即终端设备响铃超过最长响铃时长时会自动断开通信请求，终端判断呼叫时长是否大于第三预设时长，若是，则终端判定被呼叫用户可能是因终端设备不在身边而导致通信连接失败，终端继续检测到之前向该被呼叫用户发送通信请求的次数小于预设次数，则终端可以在间隔一段时间后向该终端设备再次发送通信请求。若呼叫时长小于第三预设时长，则终端判定被呼叫用户拒绝接收该通信请求，终端可以在一段时间内不再与该被呼叫终端设备发送通信请求。
若成功与所述终端设备建立通信连接，则执行步骤S204。
S204、若成功与外呼号码对应的终端设备建立通信连接，则获取终端设备的环境音量值，并根据环境音量值从至少一种外呼语音中确定目标外呼语音。
本申请实施中，终端向外呼号码对应的终端设备发送通信请求之后，若被呼叫用户在终端设备上输出了相应的接收操作，使得终端与外呼号码对应的终端设备建立了通信连接，则终端获取终端设备的环境音量值(即噪音音量值)，具体的，当终端与外呼号码对应的终端设备建立了通信连接之后，可以获取到外呼号码对应的终端设备发送的环境音量值，其中，环境音量值具体可以为外呼号码对应的终端设备所处环境中噪声的音量值。终端获取到外呼号码对应的终端设备的环境音量值之后，将根据获取到的环境音量值从至少一种外呼语音中确定目标外呼语音。
S205、终端向外呼号码对应的终端设备发送目标外呼语音。
S206、若终端接收到终端设备返回的语音信息，则根据语音信息以及环境音量值确定针对终端设备的目标语音答复，并输出该目标语音答复。
本申请实施例中，终端向外呼号码对应的终端设备发送目标外呼语音之后，若接收到终端设备返回的语音信息，则将根据语音信息以及环境音量值确定针对终端设备的目标语音答复。具体实现中，终端将接收到的语音信息转化为文本信息，并计算该文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度。其中，相似度的具体计算方式包括终端分别对文本信息以及预先存储的至少一个参考文本信息中每个参考文本信息进行分词处理，得到文本信息对应的第一词组集以及每个参考文本信息对应的第二词组集，终端检测第一词组集以及每个第二词组集中包含的相同词组的数量，并将每个第二词组集对应的相同词组的数量与每个第二词组集中词组总数量的比值确定为文本信息与每个参考文本信息的相似度。
举例说明，终端将接收到的语音信息转化为文本信息后得到的内容为“车辆保险金额”，数据库中预先存储参考文本信息包括“车辆保险类型、车辆保险金额、医疗保险金额”，则每个参考文本信息的分词结果以及与文本信息的相似度如表2所示：
表2
名称 内容 分词结果 相似度
文本信息 车辆保险金额 车辆、保险、金额  
参考文本信息1 车辆保险类型 车辆、保险、类型 66.7％
参考文本信息2 车辆保险金额 车辆、保险、金额 100％
参考文本信息3 医疗保险金额 医疗、保险、金额 66.7％
由表2可知，参考文本信息2与文本信息的相似度最高，终端确定每个参考文本信息与文本信息的相似度之后，还将确定至少一个参考文本信息中与文本信息相似度最高的参考文本信息，并获取预设的与文本信息相似度最高的参考文本信息对应的至少一种语音答复，终端根据环境音量值从至少一种语音答复中确定目标语音答复。进一步的，终端根据环境音量值从至少一种语音答复中确定目标语音答复。例如，参考文本信息2与文本信息的相似度最高，终端获取到参考文本信息2对应的至少一种语音答复如表3所示：
表3
编号 时长 输出音量值 环境音量值
语音答复1 60秒 30分贝 0-10分贝
语音答复2 50秒 40分贝 11-20分贝
语音答复3 40秒 50分贝 21-30分贝
… … … …
语音答复N 20秒 70分贝 >60分贝
其中，表3中语音答复1、语音答复2…语音答复N中每种语音答复的文字内容可以由终端对应的用户预先设置，随着语音答复的编号的增加，语音答复对应的文字内容可以越来越简洁，输出时长越短，且输出音量值越来越大。由表3可知，当终端检测到环境音量值在0-10分贝之间时，则将语音答复1确定为目标语音答复，当终端检测到环境音量值在10-20分贝之间时，则将语音答复2确定为目标语音答复。
S207、若终端检测到与外呼号码对应的终端设备的通信断开，则获取此次通信的通信内容。
本申请实施例中，终端检测到与外呼号码对应的终端设备的通信断开之后，将获取此次通信的通信内容，其中，通信内容包括通信的持续时长和目标外呼语音的类型。目标外呼语音的类型包括催收型、业务推荐型等，催收型目标外呼语音用于对欠款进行催收，业务推荐型目标外呼语音用于对不同类型的业务进行推荐。需要说明的是，目标外呼语音的类型还可以包括市场调查型、电话营销型等，本申请实施例不做限定。
S208、终端根据通信的通信内容确定外呼号码对应的终端设备的下一次外呼方案。
在一种实现方式中，终端检测到与外呼号码对应的终端设备通信断开之后，从通信内容中目标外呼语音的类型为催收型，则终端检测此次通信的时长是否小于第一预设时长，若终端检测到此次通信的持续时长小于第一预设时长，则终端需要再次向该终端设备发送 通信请求，并在于该终端设备建立通信连接后向该终端设备发送目标外呼语音。其中，第一预设时长可以为10秒、15秒等，具体可以由研发人员预先设置。通过上述方式，可以确保被呼叫用户接收到目标外呼语音中的核心内容，达到电话催收的目的。
在一种实现方式中，终端检测到与外呼号码对应的终端设备通信断开之后，从通信内容中确定目标外呼语音的类型为业务推荐型，终端检测此次通信的持续时长是否大于第二预设时长，若此次通信的持续时长大于第二预设时长，则终端在预设时间间隔后再次向该终端设备发送通信请求，并在与终端设备建立通信连接后向终端设备发送目标外呼语音。其中，第一预设时长可以为30秒、60秒等，预设时间间隔可以为10天、15天等，具体可以由研发人员预先设置。通过上述方式，可以根据通信时长确定出被呼叫用户对于推荐业务的兴趣度，若通信时长较长，则说明被呼叫用户对推荐的业务感兴趣，终端在可以间隔一段时间后再次对该被呼叫用户进行业务推荐。进一步的，终端还可以将该外呼号码存储于优先区域，当有新业务需要进行推荐时，终端可以优先对优先区域存储的外呼号码对应的终端设备进行呼叫，提升业务推荐的精准性。
本申请实施例中，终端在与外呼号码对应的终端设备建立通信连接之后，将获取到该终端设备发送的环境音量值。终端根据接收到的环境音量值确定需要针对外呼号码对应的设备输出的语音内容，若终端获取到的环境音量值较大，则输出简洁的语音方案，并采用较大的音量值进行语音输出，使得被呼叫用户可以听清终端发送的语音内容。若终端获取到的环境音量值较小，则终端可以输出详细的语音方案，并采用适中的音量值进行语音输出。进一步的，当终端接收到被呼叫用户输出的语音时，可以根据相似度算法以及环境音量值确定针对该语音的语音答复，在于该被呼叫用户的通信结束后，根据此次通话的时长确定针对该被呼叫用户的下一次呼叫方案，提升了语音外呼的智能性。
下面将结合附图3对本申请实施例提供的基于语音交互的语音外呼装置进行详细介绍。需要说明的是，附图3所示的基于语音交互的语音外呼装置，用于执行本申请图1-图2所示实施例的方法，为了便于说明，仅示出了与本申请实施例相关的部分，具体技术细节未揭示的，经参照本申请图1-图2所示的实施例。
请参见图3，为本申请提供的一种基于语音交互的语音外呼装置的结构示意图，该基于语音交互的语音外呼装置30可包括：获取模块301、检测模块302、发送模块303、确定模块304、转化模块305、计算模块306。
获取模块301，用于获取系统环境信息；
检测模块302，用于检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
所述获取模块301，还用于当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
发送模块303，用于向所述外呼号码对应的终端设备发送通信请求；
所述获取模块301，还用于若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值；
确定模块304，用于根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
所述发送模块303，还用于向所述终端设备发送所述目标外呼语音。
在一种实现方式中，所述至少一种外呼语音包括第一外呼语音和第二外呼语音，所述第一外呼语音的时长大于所述第二外呼语音的时长，所述第一外呼语音的输出音量值小于所述第二外呼语音的输出音量值，所述确定模块304具体用于：
检测所述环境音量值是否小于预设音量值；
若所述环境音量值小于所述预设音量值，则将所述第一外呼语音确定为目标外呼语音；
若所述环境音量值大于或等于所述预设音量值，则将所述第二外呼语音确定为目标外呼语音。
在一种实现方式中，所述转换模块305，用于若接收到所述终端设备返回的语音信息，则将所述语音信息转化为文本信息；
所述计算模块306，用于计算所述文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度；
所述确定模块304，用于确定所述至少一个参考文本信息中与所述文本信息相似度最高的参考文本信息，并获取预设的与所述文本信息相似度最高的参考文本信息对应的至少一种语音答复；
所述确定模块304，用于根据所述环境音量值从所述至少一种语音答复中确定目标语音答复；
所述发送模块303，用于向所述终端设备发送所述目标语音答复。
在一种实现方式中，所述计算模块306，具体用于：
分别对所述文本信息以及预先存储的至少一个参考文本信息中每个参考文本信息进行分词处理，得到所述文本信息对应的第一词组集以及每个所述参考文本信息对应的第二词组集；
检测所述第一词组集以及每个所述第二词组集中包含的相同词组的数量；
将每个所述第二词组集对应的相同词组的数量与每个所述第二词组集中词组总数量的比值确定为所述文本信息与每个所述参考文本信息的相似度。
在一种实现方式中，所述获取模块301，还用于若检测到与所述终端设备的通信断开，则获取所述通信的通信内容，所述通信内容包括所述通信的持续时长和所述目标外呼语音的类型；
所述检测模块302，还用于若所述目标外呼语音的类型为催收型，则检测所述通信的持续时长是否小于第一预设时长，所述催收型目标外呼语音用于对欠款进行催收；
所述发送模块303，还用于若所述通信的持续时长小于所述第一预设时长，则向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
在一种实现方式中，所述检测模块302，还用于若所述目标外呼语音的类型为业务推荐型，则检测所述通信的持续时长是否大于第二预设时长，所述业务推荐型目标外呼语音用于对不同种类的业务进行推荐；
所述发送模块303，还用于若所述通信的持续时长大于所述第二预设时长，则在预设时间间隔后向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
在一种实现方式中，所述检测模块302，还用于若与所述终端设备建立通信连接失败，则检测所述通信请求的呼叫时长是否大于第三预设时长；
所述检测模块302，还用于若所述呼叫时长大于所述第三预设时长，则检测预设时间段内向所述终端设备发送通信请求的次数；
所述发送模块303，还用于若所述次数小于预设次数，则向所述终端设备发送通信请求。
本申请实施例中，获取模块301获取系统环境信息；检测模块302检测所述系统环境信息是否满足预设的语音外呼条件，当检测到所述系统环境信息满足预设的语音外呼条件时，获取模块301获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；发送模块303向所述外呼号码对应的终端设备发送通信请求；若成功与所述终端设备建立通信连接，则获取模块301获取所述终端设备的环境音量值；确定模块304根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；发送模块向所述终端设备发送所述目标外呼语音。通过上述方式，可以保证被呼叫用户即使处于噪音较大的环境中也能听清终端发送的语音内容，在噪音较小的环境中可以接收到详细的语音介绍，提升了用户体验以及语音外呼的智能性。
请参见图4，为本申请实施例提供了一种终端的结构示意图。如图4所示，该终端包括：至少一个处理器401，输入设备403，输出设备404，存储器405，至少一个通信总线402。其中，通信总线402用于实现这些组件之间的连接通信。其中，输入设备403可以是控制面板或者麦克风等，输出设备404可以是显示屏等。其中，存储器405可以是高速RAM存储器，也可以是非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。存储器405可选的还可以是至少一个位于远离前述处理器401的存储装置。其中处理器401可以结合图3所描述的装置，存储器405中存储一组程序代码，且处理器401，输入设备403，输出设备404调用存储器405中存储的程序代码，用于执行以下操作：
处理器401，用于获取系统环境信息，并检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
处理器401，用于当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
输出设备404，用于向所述外呼号码对应的终端设备发送通信请求；
输入设备403，用于若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值；
处理器401，用于根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
输出设备404，用于向所述终端设备发送所述目标外呼语音。
在一种实现方式中，所述至少一种外呼语音包括第一外呼语音和第二外呼语音，所述第一外呼语音的时长大于所述第二外呼语音的时长，所述第一外呼语音的输出音量值小于 所述第二外呼语音的输出音量值，处理器401，具体用于：
检测所述环境音量值是否小于预设音量值；
若所述环境音量值小于所述预设音量值，则将所述第一外呼语音确定为目标外呼语音；
若所述环境音量值大于或等于所述预设音量值，则将所述第二外呼语音确定为目标外呼语音。
在一种实现方式中，处理器401，具体用于：
若接收到所述终端设备返回的语音信息，则将所述语音信息转化为文本信息；
计算所述文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度；
确定所述至少一个参考文本信息中与所述文本信息相似度最高的参考文本信息，并获取预设的与所述文本信息相似度最高的参考文本信息对应的至少一种语音答复；
根据所述环境音量值从所述至少一种语音答复中确定目标语音答复，并向所述终端设备发送所述目标语音答复。
在一种实现方式中，处理器401，具体用于：
分别对所述文本信息以及预先存储的至少一个参考文本信息中每个参考文本信息进行分词处理，得到所述文本信息对应的第一词组集以及每个所述参考文本信息对应的第二词组集；
检测所述第一词组集以及每个所述第二词组集中包含的相同词组的数量；
将每个所述第二词组集对应的相同词组的数量与每个所述第二词组集中词组总数量的比值确定为所述文本信息与每个所述参考文本信息的相似度。
在一种实现方式中，处理器401，具体用于：
若检测到与所述终端设备的通信断开，则获取所述通信的通信内容，所述通信内容包括所述通信的持续时长和所述目标外呼语音的类型；
若所述目标外呼语音的类型为催收型，则检测所述通信的持续时长是否小于第一预设时长，所述催收型目标外呼语音用于对欠款进行催收；
输出设备404，还用于若所述通信的持续时长小于所述第一预设时长，则向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
在一种实现方式中，处理器401，还用于若所述目标外呼语音的类型为业务推荐型，则检测所述通信的持续时长是否大于第二预设时长，所述业务推荐型目标外呼语音用于对不同种类的业务进行推荐；
输出设备404，还用于若所述通信的持续时长大于所述第二预设时长，则在预设时间间隔后向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
在一种实现方式中，处理器401，具体用于：
若与所述终端设备建立通信连接失败，则检测所述通信请求的呼叫时长是否大于第三预设时长；
若所述呼叫时长大于所述第三预设时长，则检测预设时间段内向所述终端设备发送通 信请求的次数；
输出设备404，还用于若所述次数小于预设次数，则向所述终端设备发送通信请求。
本申请实施例中，处理器401获取系统环境信息，并检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；当检测到所述系统环境信息满足预设的语音外呼条件时，处理器401获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；输出设备404向所述外呼号码对应的终端设备发送通信请求；若成功与所述终端设备建立通信连接，则输入设备403获取所述终端设备的环境音量值；处理器401根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；输出设备404向所述终端设备发送所述目标外呼语音。通过实施上述方法，可以根据获取到的环境音量调整输出语音的内容，提升了语音外呼的智能性。
本申请实施例中所述模块，可以通过通用集成电路，例如CPU(Central Processing Unit，中央处理器)，或通过ASIC(Application Specific Integrated Circuit，专用集成电路)来实现。
应当理解，在本申请实施例中，所称处理器401可以是中央处理模块(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
总线402可以是工业标准体系结构(Industry Standard Architecture，ISA)总线、外部设备互联(Peripheral Component，PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture，EISA)总线等，该总线402可以分为地址总线、数据总线、控制总线等，为便于表示，图4仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于计算机可读存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的计算机可读存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (20)

  1. 一种基于语音交互的语音外呼方法，其特征在于，所述方法包括：
    获取系统环境信息，并检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
    当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
    向所述外呼号码对应的终端设备发送通信请求；
    若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值，并根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
    向所述终端设备发送所述目标外呼语音。
  2. 根据权利要求1所述的方法，其特征在于，所述至少一种外呼语音包括第一外呼语音和第二外呼语音，所述第一外呼语音的时长大于所述第二外呼语音的时长，所述第一外呼语音的输出音量值小于所述第二外呼语音的输出音量值；所述根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音，包括：
    检测所述环境音量值是否小于预设音量值；
    若所述环境音量值小于所述预设音量值，则将所述第一外呼语音确定为目标外呼语音；
    若所述环境音量值大于或等于所述预设音量值，则将所述第二外呼语音确定为目标外呼语音。
  3. 根据权利要求1所述的方法，其特征在于，所述向所述终端设备发送所述目标外呼语音之后，所述方法还包括：
    若接收到所述终端设备返回的语音信息，则将所述语音信息转化为文本信息；
    计算所述文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度；
    确定所述至少一个参考文本信息中与所述文本信息相似度最高的参考文本信息，并获取预设的与所述文本信息相似度最高的参考文本信息对应的至少一种语音答复；
    根据所述环境音量值从所述至少一种语音答复中确定目标语音答复，并向所述终端设备发送所述目标语音答复。
  4. 根据权利要求3所述的方法，其特征在于，所述计算所述文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度，包括：
    分别对所述文本信息以及预先存储的至少一个参考文本信息中每个参考文本信息进行分词处理，得到所述文本信息对应的第一词组集以及每个所述参考文本信息对应的第二词组集；
    检测所述第一词组集以及每个所述第二词组集中包含的相同词组的数量；
    将每个所述第二词组集对应的相同词组的数量与每个所述第二词组集中词组总数量的比值确定为所述文本信息与每个所述参考文本信息的相似度。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    若检测到与所述终端设备的通信断开，则获取所述通信的通信内容，所述通信内容包 括所述通信的持续时长和所述目标外呼语音的类型；
    若所述目标外呼语音的类型为催收型，则检测所述通信的持续时长是否小于第一预设时长，所述催收型目标外呼语音用于对欠款进行催收；
    若所述通信的持续时长小于所述第一预设时长，则向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
  6. 根据权利要求5所述的方法，其特征在于，所述获取所述通信的通信内容之后，所述方法还包括：
    若所述目标外呼语音的类型为业务推荐型，则检测所述通信的持续时长是否大于第二预设时长，所述业务推荐型目标外呼语音用于对不同种类的业务进行推荐；
    若所述通信的持续时长大于所述第二预设时长，则在预设时间间隔后向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
  7. 根据权利要求1所述的方法，其特征在于，所述向所述外呼号码对应的终端设备发送通信请求之后，所述方法还包括：
    若与所述终端设备建立通信连接失败，则检测所述通信请求的呼叫时长是否大于第三预设时长；
    若所述呼叫时长大于所述第三预设时长，则检测预设时间段内向所述终端设备发送通信请求的次数；
    若所述次数小于预设次数，则向所述终端设备发送通信请求。
  8. 一种基于语音交互的语音外呼装置，其特征在于，所述装置包括：
    获取模块，用于获取系统环境信息；
    检测模块，用于检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
    所述获取模块，还用于当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
    发送模块，用于向所述外呼号码对应的终端设备发送通信请求；
    所述获取模块，还用于若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值；
    确定模块，用于根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
    所述发送模块，还用于向所述终端设备发送所述目标外呼语音。
  9. 根据权利要求8所述的装置，其特征在于，所述至少一种外呼语音包括第一外呼语音和第二外呼语音，所述第一外呼语音的时长大于所述第二外呼语音的时长，所述第一外呼语音的输出音量值小于所述第二外呼语音的输出音量值，所述确定模块具体用于：
    检测所述环境音量值是否小于预设音量值；
    若所述环境音量值小于所述预设音量值，则将所述第一外呼语音确定为目标外呼语音；
    若所述环境音量值大于或等于所述预设音量值，则将所述第二外呼语音确定为目标外呼语音。
  10. 根据权利要求8所述的装置，其特征在于，所述装置还包括转换模块和计算模块，
    所述转换模块，用于若接收到所述终端设备返回的语音信息，则将所述语音信息转化为文本信息；
    所述计算模块，用于计算所述文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度；
    所述确定模块，用于确定所述至少一个参考文本信息中与所述文本信息相似度最高的参考文本信息，并获取预设的与所述文本信息相似度最高的参考文本信息对应的至少一种语音答复；
    所述确定模块，用于根据所述环境音量值从所述至少一种语音答复中确定目标语音答复；
    所述发送模块，用于向所述终端设备发送所述目标语音答复。
  11. 根据权利要求10所述的装置，其特征在于，所述计算模块，具体用于：
    分别对所述文本信息以及预先存储的至少一个参考文本信息中每个参考文本信息进行分词处理，得到所述文本信息对应的第一词组集以及每个所述参考文本信息对应的第二词组集；
    检测所述第一词组集以及每个所述第二词组集中包含的相同词组的数量；
    将每个所述第二词组集对应的相同词组的数量与每个所述第二词组集中词组总数量的比值确定为所述文本信息与每个所述参考文本信息的相似度。
  12. 根据权利要求8-11任一项所述的装置，其特征在于，
    所述获取模块，还用于若检测到与所述终端设备的通信断开，则获取所述通信的通信内容，所述通信内容包括所述通信的持续时长和所述目标外呼语音的类型；
    所述检测模块，还用于若所述目标外呼语音的类型为催收型，则检测所述通信的持续时长是否小于第一预设时长，所述催收型目标外呼语音用于对欠款进行催收；
    所述发送模块，还用于若所述通信的持续时长小于所述第一预设时长，则向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
  13. 根据权利要求12所述的装置，其特征在于，
    所述检测模块，还用于若所述目标外呼语音的类型为业务推荐型，则检测所述通信的持续时长是否大于第二预设时长，所述业务推荐型目标外呼语音用于对不同种类的业务进行推荐；
    所述发送模块，还用于若所述通信的持续时长大于所述第二预设时长，则在预设时间间隔后向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
  14. 根据权利要求8所述的装置，其特征在于，
    所述检测模块，还用于若与所述终端设备建立通信连接失败，则检测所述通信请求的呼叫时长是否大于第三预设时长；
    所述检测模块，还用于若所述呼叫时长大于所述第三预设时长，则检测预设时间段内向所述终端设备发送通信请求的次数；
    所述发送模块，还用于若所述次数小于预设次数，则向所述终端设备发送通信请求。
  15. 一种终端，其特征在于，包括处理器、输入设备、输出设备和存储器，所述处理器、输入设备、输出设备和存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令，执行以下步骤：
    获取系统环境信息，并检测所述系统环境信息是否满足预设的语音外呼条件，所述系统环境信息包括系统时间和/或系统负载；
    当检测到所述系统环境信息满足预设的语音外呼条件时，获取与所述语音外呼条件对应的外呼方案，所述外呼方案包括外呼号码以及至少一种外呼语音；
    向所述外呼号码对应的终端设备发送通信请求；
    若成功与所述终端设备建立通信连接，则获取所述终端设备的环境音量值，并根据所述环境音量值从所述至少一种外呼语音中确定目标外呼语音；
    向所述终端设备发送所述目标外呼语音。
  16. 根据权利要求15所述的终端，其特征在于，所述至少一种外呼语音包括第一外呼语音和第二外呼语音，所述第一外呼语音的时长大于所述第二外呼语音的时长，所述第一外呼语音的输出音量值小于所述第二外呼语音的输出音量值；所述处理器还用于调用所述程序指令执行以下步骤：
    检测所述环境音量值是否小于预设音量值；
    若所述环境音量值小于所述预设音量值，则将所述第一外呼语音确定为目标外呼语音；
    若所述环境音量值大于或等于所述预设音量值，则将所述第二外呼语音确定为目标外呼语音。
  17. 根据权利要求15所述的终端，其特征在于，所述处理器还用于调用所述程序指令执行以下步骤：
    若接收到所述终端设备返回的语音信息，则将所述语音信息转化为文本信息；
    计算所述文本信息与数据库中预先存储的至少一个参考文本信息中每个参考文本信息的相似度；
    确定所述至少一个参考文本信息中与所述文本信息相似度最高的参考文本信息，并获取预设的与所述文本信息相似度最高的参考文本信息对应的至少一种语音答复；
    根据所述环境音量值从所述至少一种语音答复中确定目标语音答复，并向所述终端设备发送所述目标语音答复。
  18. 根据权利要求17所述的终端，其特征在于，所述处理器还用于调用所述程序指令执行以下步骤：
    分别对所述文本信息以及预先存储的至少一个参考文本信息中每个参考文本信息进行分词处理，得到所述文本信息对应的第一词组集以及每个所述参考文本信息对应的第二词组集；
    检测所述第一词组集以及每个所述第二词组集中包含的相同词组的数量；
    将每个所述第二词组集对应的相同词组的数量与每个所述第二词组集中词组总数量的比值确定为所述文本信息与每个所述参考文本信息的相似度。
  19. 根据权利要求15-18任一项所述的终端，其特征在于，所述处理器还用于调用所述程序指令执行以下步骤：
    若检测到与所述终端设备的通信断开，则获取所述通信的通信内容，所述通信内容包括所述通信的持续时长和所述目标外呼语音的类型；
    若所述目标外呼语音的类型为催收型，则检测所述通信的持续时长是否小于第一预设时长，所述催收型目标外呼语音用于对欠款进行催收；
    若所述通信的持续时长小于所述第一预设时长，则向所述终端设备发送通信请求，并在与所述终端设备建立通信连接后向所述终端设备发送所述目标外呼语音。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如权利要求1-7任一项所述的方法。
PCT/CN2019/120613 2019-04-12 2019-11-25 基于语音交互的语音外呼方法、装置及终端 WO2020207025A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910301554.8 2019-04-12
CN201910301554.8A CN110113497B (zh) 2019-04-12 2019-04-12 基于语音交互的语音外呼方法、装置、终端及存储介质

Publications (1)

Publication Number Publication Date
WO2020207025A1 true WO2020207025A1 (zh) 2020-10-15

Family

ID=67484078

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/120613 WO2020207025A1 (zh) 2019-04-12 2019-11-25 基于语音交互的语音外呼方法、装置及终端

Country Status (2)

Country Link
CN (1) CN110113497B (zh)
WO (1) WO2020207025A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113448871A (zh) * 2021-07-22 2021-09-28 深圳追一科技有限公司 会话调试方法、装置、计算机设备和计算机可读存储介质
CN113572900A (zh) * 2021-07-22 2021-10-29 深圳追一科技有限公司 外呼测试方法、装置、计算机设备和计算机可读存储介质
CN113784007A (zh) * 2021-09-29 2021-12-10 深圳追一科技有限公司 外呼通话方法、装置、设备及存储介质
CN113992806A (zh) * 2021-10-25 2022-01-28 百融至信(北京)征信有限公司 一种智能语音rpa机器人外呼方法及装置
CN115329206A (zh) * 2022-10-13 2022-11-11 深圳市人马互动科技有限公司 语音外呼处理方法及相关装置
CN117316191A (zh) * 2023-11-30 2023-12-29 天津科立尔科技有限公司 一种情绪监测分析方法及系统

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110113497B (zh) * 2019-04-12 2022-01-11 深圳壹账通智能科技有限公司 基于语音交互的语音外呼方法、装置、终端及存储介质
CN112839137A (zh) * 2020-12-30 2021-05-25 平安普惠企业管理有限公司 基于背景环境的呼叫处理方法、装置、设备及存储介质
CN112687293B (zh) * 2021-03-22 2021-06-22 北京孵家科技股份有限公司 一种基于机器学习及数据挖掘的智能坐席训练方法和系统
KR102369263B1 (ko) * 2021-12-08 2022-03-04 주식회사 세븐포인트원 인공지능 기반 대상자의 치매 검사를 위한 아웃바운드 콜의 음량 제어 방법, 장치 및 시스템

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105656726A (zh) * 2016-02-22 2016-06-08 国家电网公司 语音数据的发布方法和装置及系统
CN107274882A (zh) * 2017-08-08 2017-10-20 腾讯科技（深圳）有限公司 数据传输方法及装置
CN108369805A (zh) * 2017-12-27 2018-08-03 深圳前海达闼云端智能科技有限公司 一种语音交互方法、装置和智能终端
CN108733341A (zh) * 2018-05-18 2018-11-02 出门问问信息科技有限公司 一种语音交互方法及装置
CN110113497A (zh) * 2019-04-12 2019-08-09 深圳壹账通智能科技有限公司 基于语音交互的语音外呼方法、装置及终端

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100488353B1 (ko) * 2001-12-27 2005-05-10 주식회사 케이티 전화망의 사용자 터미널의 데이터통신 중에음성호출신호를 표시하는 방법 및 장치
JP2010141806A (ja) * 2008-12-15 2010-06-24 Hitachi Ltd 通話中に送話音量を調整できる通話端末装置および通話端末装置における送話音量増大方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105656726A (zh) * 2016-02-22 2016-06-08 国家电网公司 语音数据的发布方法和装置及系统
CN107274882A (zh) * 2017-08-08 2017-10-20 腾讯科技（深圳）有限公司 数据传输方法及装置
CN108369805A (zh) * 2017-12-27 2018-08-03 深圳前海达闼云端智能科技有限公司 一种语音交互方法、装置和智能终端
CN108733341A (zh) * 2018-05-18 2018-11-02 出门问问信息科技有限公司 一种语音交互方法及装置
CN110113497A (zh) * 2019-04-12 2019-08-09 深圳壹账通智能科技有限公司 基于语音交互的语音外呼方法、装置及终端

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113448871A (zh) * 2021-07-22 2021-09-28 深圳追一科技有限公司 会话调试方法、装置、计算机设备和计算机可读存储介质
CN113572900A (zh) * 2021-07-22 2021-10-29 深圳追一科技有限公司 外呼测试方法、装置、计算机设备和计算机可读存储介质
CN113784007A (zh) * 2021-09-29 2021-12-10 深圳追一科技有限公司 外呼通话方法、装置、设备及存储介质
CN113992806A (zh) * 2021-10-25 2022-01-28 百融至信(北京)征信有限公司 一种智能语音rpa机器人外呼方法及装置
CN115329206A (zh) * 2022-10-13 2022-11-11 深圳市人马互动科技有限公司 语音外呼处理方法及相关装置
CN115329206B (zh) * 2022-10-13 2022-12-20 深圳市人马互动科技有限公司 语音外呼处理方法及相关装置
CN117316191A (zh) * 2023-11-30 2023-12-29 天津科立尔科技有限公司 一种情绪监测分析方法及系统

Also Published As

Publication number Publication date
CN110113497B (zh) 2022-01-11
CN110113497A (zh) 2019-08-09

Similar Documents

Publication Publication Date Title
WO2020207025A1 (zh) 基于语音交互的语音外呼方法、装置及终端
US9525767B2 (en) System and method for answering a communication notification
US10057413B2 (en) System and method for spoken caller identification in a cellular telephone headset
US20120109655A1 (en) Wireless server based text to speech email
US8358753B2 (en) Interactive voice response (IVR) cloud user interface
US10257350B2 (en) Playing back portions of a recorded conversation based on keywords
EP3229504A1 (en) Method and apparatus for analyzing state of receiving terminal, and program for implementing same
CN107920154A (zh) 陌生来电的处理方法及终端
WO2020124453A1 (zh) 信息自动回复的方法及相关装置
US10789954B2 (en) Transcription presentation
WO2012065509A1 (zh) 一种网络设备、被叫终端及处理第三方呼叫的方法
TWM565346U (zh) 智能客服平台
CN110309284B (zh) 一种基于贝叶斯网络推理的自动对答方法及装置
TWM590333U (zh) 自動呼叫分配系統
US20130196642A1 (en) Communication device, recording medium, and communication method
US9514750B1 (en) Voice call content supression
CN114157763A (zh) 交互过程中的信息处理方法、装置、终端及存储介质
CN108769363A (zh) 通话方法及装置、计算机装置和计算机可读存储介质
US20140051390A1 (en) Automatically connecting to a best available calling device based on resource strength
CN118264750A (zh) 呼叫处理方法、装置、设备和介质
CN117373164A (zh) 业务办理的声音控制方法、装置、电子设备及存储介质
CN113327582A (zh) 语音交互方法、装置、电子设备及存储介质
CN111835920A (zh) 通话处理方法、装置、设备及存储介质
CN115834769A (zh) 智能外呼方法、装置、设备及计算机可读存储介质
CN113314152A (zh) 判断通话是否有效拨出的方法及设备

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: 19924353

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 02/02/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19924353

Country of ref document: EP

Kind code of ref document: A1