WO2018000659A1 - Method and apparatus for extracting key content of call - Google Patents

Method and apparatus for extracting key content of call Download PDF

Info

Publication number
WO2018000659A1
WO2018000659A1 PCT/CN2016/102041 CN2016102041W WO2018000659A1 WO 2018000659 A1 WO2018000659 A1 WO 2018000659A1 CN 2016102041 W CN2016102041 W CN 2016102041W WO 2018000659 A1 WO2018000659 A1 WO 2018000659A1
Authority
WO
WIPO (PCT)
Prior art keywords
call
key content
keywords
extracted
preset
Prior art date
Application number
PCT/CN2016/102041
Other languages
French (fr)
Chinese (zh)
Inventor
卢丽君
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2018000659A1 publication Critical patent/WO2018000659A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W8/00Network data management
    • H04W8/22Processing or transfer of terminal data, e.g. status or physical capabilities
    • H04W8/24Transfer of terminal data

Definitions

  • the embodiments of the present invention relate to the field of communications technologies, and in particular, to a call key content extraction method and apparatus.
  • Communication terminals such as mobile phones are indispensable tools for communication between people in today's society. Many things that cannot be done face to face need to be completed by telephone. However, during the call, some key words mentioned by the two parties, such as time, place, people, and processing objects, are often ignored because the listener is distracted, or because the surrounding environment is too noisy, or This information was not recorded in time after the phone was hanged, and the key information was omitted or misjudged afterwards. Calling again to ask the other person's information is often very inappropriate, especially during work, interviews, and business meetings.
  • the owner can open the recording button on the call interface during the call, and after the call ends, find the recorded content of the call at the time in the corresponding recording storage file, and play back to obtain The information you need.
  • a key content extraction method is extremely inconvenient for the user, and the following problems mainly exist:
  • the embodiment of the invention provides a method and a device for extracting key content of a call, which aims to solve the technical problem that the related key content extraction method is extremely inconvenient, wastes time and effort, and is prone to error.
  • an embodiment of the present invention provides a call key content extraction method, where the call key content extraction method includes:
  • the key content of the call is extracted from the recorded content of the call.
  • the call key content extraction method further includes:
  • the saving the extracted call key content includes:
  • a corresponding reminder item is established according to the call key content to issue a reminder to the user at a specified time;
  • the call key content When the call key content does not include a date and/or time, the call key content is stored in a text type application for the user to view the call key content of the call at any time.
  • the determining, according to the acquired information related to the call, and the preset keyword determining mechanism, determining a group of keywords related to the call includes:
  • the keywords are extracted from one or more histories according to the keyword determination mechanism in descending order of creation time of the history.
  • the determining, according to the acquired information related to the call, and the preset keyword determining mechanism, determining a group of keywords related to the call includes:
  • the keyword intelligent association is expanded, and the keyword is extracted.
  • the determining, according to the obtained information related to the call, and the preset keyword determining mechanism, determining a group of keywords related to the call further includes:
  • the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
  • the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  • the call key content extraction method further includes:
  • an embodiment of the present invention further provides a call key content extracting apparatus, where the call key content extracting apparatus includes:
  • a timing module configured to count the duration of the call when a call establishment is detected
  • a recording module configured to record the call when a call establishment is detected
  • the first extraction module is configured to extract the call key content from the recorded content of the call according to the determined set of keywords.
  • the call key content extracting apparatus further includes:
  • a storage module configured to save the extracted key content of the call
  • the storage module includes:
  • a first storage unit configured to establish a corresponding reminding item according to the key content of the call when the call key content includes a date and/or a time, to issue a reminder to the user at a specified time;
  • the second storage unit is configured to store the call key content into a text type application when the call key content does not include a date and/or time, so that the user can view the call key content of the call at any time.
  • the determining module includes:
  • a search unit configured to search for a history related to the counterpart number in the call from the specified application
  • the first extracting unit is configured to extract keywords from the one or more history records according to the keyword determining mechanism in an order of the history creation time from large to small.
  • the determining module includes:
  • the second extracting unit is configured to expand the keyword intelligent association according to the address book contact details corresponding to the counterpart number in the call, and the keyword determining mechanism, and extract keywords.
  • the determining module further includes:
  • a third extracting unit configured to: when the total number of extracted keywords is less than a preset first threshold, continue to extract keywords according to the massive vocabulary in the keyword determining mechanism, so that the extracted one is obtained
  • the total number of group keywords is greater than or equal to a preset first threshold and less than or equal to a preset second threshold;
  • a screening unit configured to: when the total number of extracted keywords is greater than a preset second threshold, select a keyword from the extracted keywords according to the keyword determining mechanism, so as to obtain a set of key selected by the screening
  • the total number of words is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  • the call key content extracting apparatus further includes:
  • the second extraction module is configured to extract a word of the specified part of speech from the text content corresponding to the recorded content as a key content of the call of the call.
  • a computer storage medium is also provided, and the computer storage medium is provided.
  • the quality may be stored with an execution instruction for executing the call key content extraction method in the above embodiment.
  • the call key content extraction method and device collects the duration of the call and records the call when the call is established, and obtains when the duration of the call is greater than or equal to the preset duration. Obtaining information related to the call, and a preset keyword determining mechanism, determining a set of keywords, and extracting key content of the call from the recorded content of the call according to the obtained set of keywords, The automatic extraction of the important information in the call content, thereby obtaining the call key content of the call, and facilitating the subsequent convenient service for the user to provide various uses based on the extracted call key content.
  • FIG. 1 is a schematic flowchart of a first embodiment of a method for extracting key content of a call according to the present invention
  • FIG. 2 is a schematic diagram of a refinement process of step S20 in FIG. 1;
  • FIG. 3 is a schematic flowchart of a second embodiment of a call key content extraction method according to the present invention.
  • FIG. 4 is a schematic diagram of functional modules of a first embodiment of a call key content extracting apparatus according to the present invention.
  • FIG. 5 is a schematic diagram of a refinement function module of the determining module in FIG. 4;
  • FIG. 5 is a schematic diagram of a refinement function module of the determining module in FIG. 4;
  • FIG. 6 is a schematic diagram of functional modules of a second embodiment of a call key content extracting apparatus according to the present invention.
  • FIG. 7 is a schematic diagram of a refinement function module of the storage module in FIG. 6;
  • FIG. 8 is a schematic diagram of a refinement function module of a determining module in a third embodiment of the call key content extracting apparatus of the present invention.
  • FIG. 9 is a schematic diagram of functional modules of a fourth embodiment of a call key content extracting apparatus according to the present invention.
  • An embodiment of the present invention provides a method for extracting key content of a call. As shown in FIG. 1 , a schematic flowchart of a method for extracting a key content of a call according to the present invention is shown.
  • the call key content extraction method can be implemented on any terminal having a call function, for example, a smart phone.
  • a call function for example, a smart phone.
  • the call connection is successfully established between the terminal used by the user and the terminal used by the other party.
  • the terminal used by the user detects that a call is established, the real time duration of the call may be counted by a timer set on the terminal, and the call is recorded by a recording device set on the terminal, where The recorded content obtained by the call recording can be stored in the buffer first.
  • the total duration of the call and the size of the preset duration obtained by comparing statistics may be performed after the total duration of the call is greater than or equal to the preset duration;
  • a subsequent operation may be performed.
  • the preset duration is a preset duration value, for example, 1 minute or 30 seconds, which can be set by the user or set by the terminal as a default value; the duration of each call obtained by the statistics can be accurate to minutes and seconds. .
  • some unimportant calls can be filtered out, the call key content is not extracted, and the calls are recorded in the buffer when the calls are over. The recorded content is deleted to save mobile phone storage space and reduce the running pressure and power consumption of the background system.
  • Unimportant calls usually a few seconds, ten seconds of phone calls, such as some courier calls, advertising marketing, harassing calls, wrong calls, etc. that people often receive, these calls are usually a few seconds after being connected.
  • the left and right will be hung up, and there is basically no need to save the key content of the call. If you do not filter beforehand, The recording and extraction of all the call recordings will inevitably bring great pressure to the running speed and power consumption of the mobile phone. Therefore, by using the preset duration to limit, it is necessary to filter out these unnecessary calls in advance, and to alleviate the running pressure in the background and the memory consumption of the buffer.
  • the terminal may obtain some history information related to the call by querying various applications installed in the installed application or the storage file, thereby obtaining a history related to the call, and then according to the preset keywords.
  • the determining mechanism extracts a set of keywords related to the call from the obtained history.
  • the keyword determining mechanism is configured to specify, according to information related to the call in different applications or stored files, keywords related to the call, where the keyword determining mechanism is preset.
  • step S20 specifically includes:
  • the specified application may be any application installed on the terminal.
  • the specified application is preferably a common tool application such as a calendar, an alarm clock, a memo, or a notepad installed on various terminals.
  • the terminal can obtain a history related to the counterpart number in the call by querying. For example, suppose that the alarm application stores a reminder related to the other party number in the call, such as the cooperation with the general manager at 9:00 am on March 15, 2016 (where the terminal address book stores Wang Zong)
  • the notebook application stores two records related to Wang Zong.
  • the company’s main production communication equipment, Wang’s company address is Nanshan District, Shenzhen. In the Science and Technology Park, the terminal can obtain 3 historical records in the two applications through inquiry.
  • the first threshold and the second threshold are preset in the keyword determining mechanism, where the first threshold and the second threshold are two fixed values, wherein the second threshold is greater than the first threshold, where The value can be set by the user or the terminal according to the actual demand.
  • the two thresholds are set to protect The number of keywords extracted by the certificate is not too small or too much, and the key content of the call that is subsequently extracted is less or more.
  • the history record in the alarm is the latest information.
  • the terminal follows the history.
  • the order of creation of records is from the largest to the smallest, first extracting keywords from the history record in the alarm application, and assuming that the keywords extracted according to the keyword determination mechanism are "March 15, 2016” "Morning" 9:00" “Wang total” “negotiation” "cooperation", a total of 5 keywords. If the first threshold is greater than 5, it means that the number of keywords extracted according to the history record in the alarm application is small.
  • the history may be created from a history record with a larger time in the two history records of the notebook.
  • Extracting assuming that another keyword is extracted, if the total number of keywords extracted at this time satisfies the condition that is greater than or equal to the preset first threshold and less than or equal to the preset second threshold, no extraction is required.
  • the six keywords obtained at this time are a set of keywords to be extracted; if the first threshold is also greater than 6, it means that the number of keywords extracted according to the two historical records is still insufficient, and at this time, it is necessary to The third history record continues to extract keywords until the condition that the total number of extracted keywords is greater than or equal to the first threshold and less than or equal to the second threshold is satisfied.
  • step S20 further includes:
  • the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
  • the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  • the appropriate number of the keywords may be determined from the keyword vocabulary of the keywords according to the keyword determining mechanism.
  • the keyword is added; if the total number of extracted keywords is greater than the second threshold, then according to the keyword determining mechanism, an appropriate number of keywords may be removed. It should be noted that among the extracted keywords, each keyword is different.
  • the terminal After extracting a set of keywords, gradually converts all or part of the recorded content of the call into text content, and then performs fuzzy matching or similar matching of the obtained set of keywords with the text content, thereby The call key content of the call is extracted.
  • the recorded content of the call stored in the buffer may be stored in a designated storage area of the terminal, so that the user can retrieve the call recording of the call afterwards.
  • the method for extracting the key content of the call provided by the embodiment of the present invention, when the call is established, the duration of the call is counted and the call is recorded, and when the duration of the call is greater than or equal to the preset duration, the obtained call is obtained.
  • the second embodiment of the call key content extraction method of the present invention is proposed based on the first embodiment.
  • the call key content extraction method further includes:
  • the terminal may save the call key content in a designated storage location or a designated application of the terminal, so that the user can view it at any time. It can be understood that the terminal can also convert the obtained call key content into a file in a voice format for storage, and when the user views the key content of the call, the call key content is delivered to the user by means of voice broadcast.
  • the call key content is stored, so that the user can view at any time, so that the user can receive the call intently during the call without recording the key content while answering the phone, thereby saving the user's operation. And the energy consumed, it also facilitates users to get key content of the call.
  • step S40 includes:
  • a corresponding reminder item is established according to the call key content to issue a reminder to the user at a specified time;
  • the call key content When the call key content does not include a date and/or time, the call key content is stored in a text type application for the user to view the call key content of the call at any time.
  • the terminal may use an application with a reminder function (for example, a calendar or an alarm clock) to establish a reminder, and then call the call
  • a reminder function for example, a calendar or an alarm clock
  • the key content is added to the reminder in accordance with the reminder, for example, the date of the key content of the call "May 1, 2016, 6:00, Xiao Wang, KFC, and dinner", "May 1, 2016” , set to the date of the new reminder of the specified application calendar, set the "6 o'clock” in the key content of the call to the time of the reminder, the "key king, KFC, eat” of the key content of the call, Set to the title or note of the reminder.
  • the terminal can provide the setting page to the user, and the user can add or modify the setting according to individual needs, and the user can also set how long to advance the reminder.
  • the terminal will remind the user of the item according to the setting of how long to remind the reminder before the time corresponding to the set date and time.
  • the designated time is a time when the reminder is issued in advance with respect to the set date and time
  • the specified time is the set date and time corresponding to the set time Moment.
  • the terminal may use the text type application to store the call key content, for example, the call key content may be stored in a memo or a notebook, so that the user can View.
  • the call key content extraction method is provided in the embodiment of the present invention, and the extracted call key content is separately stored according to whether the date and/or time is included, so as to include the date and/or time of the call key content in the form of a reminder item.
  • Storage easy to remind users of the corresponding matters, to avoid the handling of important things, and to store the key content of the call without date and / or time in the text type of application, so that users can view at any time, eliminating the need to remember The trouble makes the user more worry-free during the call.
  • the third embodiment of the call key content extraction method of the present invention is proposed based on the foregoing second embodiment.
  • the foregoing step S20 specifically includes:
  • the keyword intelligent association is expanded, and the keyword is extracted.
  • the terminal can obtain the contact details of the other party's number in the address book according to the other party's number of the call, and some important information may be stored in the contact details, and the information may be extracted as a keyword.
  • step S20 further includes:
  • the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
  • the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  • the method for extracting key content of the call provided by the embodiment of the present invention extracts a keyword from the contact details of the address book corresponding to the other party number in the call, and the method can obtain a more accurate keyword, which is beneficial to the call from the call.
  • the recorded content extracts more accurate call key content.
  • the keyword is extracted by using the extraction method of the first embodiment, and the total number of keywords extracted is less than
  • the keyword is extracted by using the extraction method of the third embodiment, and if the total number of keywords extracted in the two extraction modes meets the first threshold and is less than or equal to
  • all the keywords extracted are the set of keywords to be obtained; if the total number of keywords extracted in the two extraction modes does not satisfy the first threshold and If the condition is less than or equal to the second threshold, then the appropriate number of keywords are supplemented or screened according to the keyword determining mechanism.
  • the keyword is extracted by using the extraction method of the third embodiment, and when the total number of extracted keywords is less than the first threshold, the extraction method of the first embodiment is used. Extracting a keyword, if the total number of keywords extracted in the two extraction modes satisfies a condition greater than or equal to the first threshold and less than or equal to the second threshold, all the extracted keywords are a set of keywords obtained; if the total number of keywords extracted in the two extraction modes does not satisfy a condition greater than or equal to the first threshold and less than or equal to the second threshold, then according to the key
  • the word determination mechanism supplements or screens the appropriate number of keywords.
  • the combination of the two extraction methods can extract the appropriate and more accurate keywords, and extract the key content of the call according to the extracted keywords, and make the data foundation, which is most accurate and useful for extracting to the call. Information.
  • the call key content extraction method of the present invention when the extracted call key content is empty, the call key content extraction method further includes:
  • the keyword extracted from the information related to the call, or the keyword extracted from the mass vocabulary in the keyword determining mechanism sometimes the text content corresponding to the recorded content of the call is irrelevant In this case, the key content of the call extracted at this time may be air.
  • words specifying the part of speech such as nouns, quantifiers, verbs, etc., may be extracted from the text content corresponding to the recorded content as the key content of the call.
  • the call key content extraction method when the extracted key content is empty according to the information related to the call and the keyword determination mechanism, The words corresponding to the part of speech are extracted from the text content corresponding to the recorded content, thereby ensuring that the extracted key content of the call is not empty, and providing the user with certain useful information.
  • the embodiment of the present invention further provides a call key content extracting apparatus.
  • a schematic diagram of a function module of the first embodiment of the call key content extracting apparatus of the present invention is shown.
  • the call key content extracting apparatus includes:
  • the timing module 100 is configured to count the duration of the call when a call establishment is detected
  • the recording module 200 is configured to record the call when a call establishment is detected
  • the call key content extraction device may be disposed on any terminal having a call function, such as a smart phone.
  • a call function such as a smart phone.
  • the timing module 100 can count the real-time duration of the call by using a timer set on the terminal, and the recording module 200 records the call by using a recording device set on the terminal.
  • the recorded content obtained by recording the call may be stored in a buffer first.
  • the determining module 300 is configured to: when the duration of the call is greater than or equal to a preset duration, determine a group related to the call according to the acquired information related to the call and a preset keyword determining mechanism Key words;
  • the total duration of the call and the size of the preset duration obtained by comparing statistics may be performed after the total duration of the call is greater than or equal to the preset duration;
  • a subsequent operation may be performed.
  • the preset duration is a preset duration value, for example, 1 minute or 30 seconds, which can be set by the user or set by the terminal as a default value; the duration of each call obtained by the statistics can be accurate to minutes and seconds. .
  • some unimportant calls can be filtered out, the call key content is not extracted, and the calls are recorded in the buffer when the calls are over. The recorded content is deleted to save mobile phone storage space and reduce the running pressure and power consumption of the background system.
  • Unimportant calls usually a few seconds, ten seconds of phone calls, such as some courier calls, advertising marketing, harassing calls, wrong calls, etc. that people often receive, these calls are usually a few seconds after being connected.
  • the left and right will be hung up, and there is basically no need to save the key content of the call. If you do not perform filtering and filtering beforehand, all the recordings of all calls will be cached and extracted, which will inevitably put a lot of pressure on the running speed and power consumption of the mobile phone. Therefore, by using the preset duration to limit, it is necessary to filter out these unnecessary calls in advance, and to alleviate the running pressure in the background and the memory consumption of the buffer.
  • the determining module 300 of the terminal may obtain some history information related to the call by querying various applications or storage files installed in the terminal, thereby obtaining a history related to the call, and then according to the pre-
  • the keyword determining mechanism extracts a set of keywords related to the call from the obtained history record.
  • the keyword determining mechanism is configured to specify, according to information related to the call in different applications or stored files, keywords related to the call, where the keyword determining mechanism is preset A variety of extraction rules, which stipulate the extraction range of keywords, and also provide a massive vocabulary of keywords.
  • the determining module 300 includes:
  • the searching unit 301 is configured to search for a history related to the counterpart number in the call from the specified application;
  • the specified application may be any application installed on the terminal.
  • the specified application is preferably a common tool application such as a calendar, an alarm clock, a memo, or a notepad installed on various terminals.
  • the search unit 301 of the terminal can obtain a history related to the counterpart number in the call by querying. For example, assume that the pair in the call is stored in the alarm application. A reminder related to the party number, such as 9:00 am on March 15, 2016, to discuss cooperation with Wang. (The terminal address book stores the telephone number of Wang, that is, the number of the other party in the call)
  • the Notepad application stores two records related to Wang Zong. For example, the company's main production communication equipment, Wang's company address is Shenzhen Nanshan District Science and Technology Park, the terminal's search unit 301 can be obtained through inquiry. 3 historical records in both applications.
  • the first extracting unit 302 is configured to extract keywords from one or more historical records according to the keyword determining mechanism in descending order of creation time of the history.
  • the first threshold and the second threshold are preset in the keyword determining mechanism, where the first threshold and the second threshold are two fixed values, wherein the second threshold is greater than the first threshold, where The value can be set by the user or the terminal according to the actual demand.
  • the two thresholds are set to ensure that the number of keywords to be extracted is not too small or too much, and the key content of the subsequent extraction is less or more.
  • the history record in the alarm is the latest information, and at this time, the terminal An extracting unit 302 first extracts keywords from the history record in the alarm clock application in descending order of the creation time of the history record, and assumes that the keyword extracted according to the keyword determining mechanism is “2016 3 On the 15th of the month, "9:00 am” "Wang Zong", “Consultation” and “Cooperation”, a total of 5 keywords. If the first threshold is greater than 5, it indicates that the number of keywords extracted according to the history in the alarm application is small.
  • the first extracting unit 302 can create a larger time from the two historical records of the notebook. Continue to extract from a history record, assuming that another keyword is extracted, if the total number of keywords extracted at this time satisfies a condition that is greater than or equal to the preset first threshold and less than or equal to the preset second threshold. , the need to extract again, the six keywords obtained at this time is a set of keywords to be extracted; if the first threshold is also greater than 6, it means that the number of keywords extracted according to the two historical records is still insufficient. At this time, the first extracting unit 302 needs to continue to extract keywords from the third history record until the total number of keywords that are extracted is greater than or equal to the first threshold and less than or equal to the second threshold. The conditions are up.
  • the determining module 300 further includes:
  • the third extracting unit 304 is configured to: when the total number of extracted keywords is less than the preset number
  • a threshold is used, according to the massive vocabulary in the keyword determining mechanism, the keyword is continuously extracted, so that the total number of the extracted set of keywords is greater than or equal to the preset first threshold and less than or equal to the preset.
  • the screening unit 305 is configured to: when the total number of extracted keywords is greater than a preset second threshold, filter keywords from the extracted keywords according to the keyword determining mechanism, so as to obtain a selected group
  • the total number of keywords is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  • the third extracting unit 304 may determine the mechanism according to the keyword, from the massive vocabulary of the keywords therein. The appropriate number of keywords is determined as a supplement; if the total number of extracted keywords is greater than the second threshold, the screening unit 305 may remove an appropriate number of keywords according to the keyword determining mechanism. It should be noted that among the extracted keywords, each keyword is different.
  • the first extraction module 400 is configured to extract the call key content from the recorded content of the call according to the determined set of keywords.
  • the first extraction module 400 of the terminal After extracting a set of keywords, gradually converts all or part of the recorded content of the call into text content, and then performs fuzzy matching on the obtained set of keywords with the text content. Or the meanings are similarly matched, so that the key content of the call of the call is extracted.
  • the recorded content of the call stored in the buffer may be stored in a designated storage area of the terminal, so that the user can retrieve the call recording of the call afterwards.
  • the call key content extracting apparatus of the embodiment of the present invention collects the duration of the call and records the call when the call is established, and obtains the obtained time when the duration of the call is greater than or equal to the preset duration.
  • the second embodiment of the call key content extracting apparatus of the present invention is proposed based on the first embodiment of the call key content extracting apparatus.
  • the call key content extracting apparatus further include:
  • the storage module 500 is configured to save the extracted call key content.
  • the storage module 500 of the terminal may save the call key content in a specified storage location or a designated application of the terminal, so that the user can view it at any time. It can be understood that the storage module 500 of the terminal can further convert the obtained call key content into a file in a voice format, and when the user views the key content of the call, the key content of the call is broadcasted by means of voice broadcast. Passed to the user.
  • the call key content is stored, so that the user can view at any time, so that the user can receive the call intently during the call without recording the key content while answering the phone, thereby saving the user's operation. And the energy consumed, it also facilitates users to get key content of the call.
  • the storage module 500 includes:
  • the first storage unit 501 is configured to establish a corresponding reminding item according to the call key content when the call key content includes a date and/or a time, so as to issue a reminder to the user at a specified time;
  • the first storage unit 501 of the terminal may establish a reminder using an application (eg, a calendar or an alarm) having a remind function. And then adding the key content of the call to the reminder according to the provisions of the reminder item, for example, the date of the call key content "May 1, 2016, 6 pm, Xiao Wang, KFC, eating" "May 1st of the year”, set the date to the new reminder of the specified application calendar, set "6 o'clock” in the key content of the call to the time of the reminder, and the "key king" of the key content of the call , KFC, dinner", set to the title or remarks of the reminder.
  • an application eg, a calendar or an alarm
  • the terminal can provide the setting page to the user, and the user can add or modify the setting according to individual needs, and the user can also set how long to advance the reminder.
  • the terminal will remind the user of the item according to the setting of how long to remind the reminder before the time corresponding to the set date and time.
  • the designated time is a time when the reminder is issued in advance with respect to the set date and time
  • the specified time is the set date and time corresponding to the set time Moment.
  • the second storage unit 502 is configured to store the call key content into a text type application when the call key content does not include a date and/or time, so that the user can view the call key content of the call at any time. .
  • the second storage unit 502 of the terminal may store the call key content using a text type application, for example, the call key content may be stored in a memo or a note. This is for users to view at any time.
  • the call key content extracting device of the embodiment of the present invention stores the extracted call key content separately according to whether the date and/or time is included, so as to include the date and/or time of the call key content in the form of a reminder item. Storage, easy to remind users of the corresponding matters, to avoid the handling of important things, and to store the key content of the call without date and / or time in the text type of application, so that users can view at any time, eliminating the need to remember The trouble makes the user more worry-free during the call.
  • the determining module 300 includes:
  • the second extracting unit 303 is configured to expand keyword keyword association and extract keywords according to the address book contact details corresponding to the counterpart number in the call and the keyword determining mechanism.
  • the terminal can obtain the contact details of the other party's number in the address book according to the other party's number of the call, and some important information may be stored in the contact details, and the information may be extracted as a keyword.
  • the determining module 300 further includes:
  • the third extracting unit 304 is configured to: when the total number of extracted keywords is less than a preset first threshold, continue to extract keywords according to the massive vocabulary in the keyword determining mechanism, so as to obtain the extracted
  • the total number of keywords in a group is greater than or equal to a preset first threshold and less than or equal to a preset second threshold;
  • the screening unit 305 is configured to: when the total number of extracted keywords is greater than a preset second threshold, filter keywords from the extracted keywords according to the keyword determining mechanism, so as to obtain a selected group
  • the total number of keywords is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  • the second extraction unit 303 can be "small” Li “chain home”, “housing agency”, “degree room” and “primary school” as keywords and launch intelligent association, so as to get more relevant keywords.
  • the third extracting unit 304 may select an appropriate number of related keywords from the mass vocabulary of the keyword of the keyword determining mechanism, thereby The total number of sets of keywords is greater than or equal to the first threshold and less than or equal to the second threshold.
  • the filtering unit 305 may remove an appropriate number of keywords according to the keyword determining mechanism. It should be noted that among the extracted keywords, each keyword is different.
  • the call key content extracting device of the embodiment of the present invention extracts a keyword from the address book contact details corresponding to the counterpart number in the call, and can obtain a more accurate keyword by using the method, which is beneficial to the call from the call.
  • the recorded content extracts more accurate call key content.
  • the keyword is extracted by using the extraction method of the first embodiment of the call key content extracting device. If the total number of keywords is less than the first threshold, the keyword is extracted by using the extraction method of the third embodiment of the call key content extraction device, and if the total number of keywords extracted by the two extraction modes is greater than Or a condition equal to the first threshold and less than or equal to the second threshold, then all keywords extracted are obtained a set of keywords; if the total number of keywords extracted in the two extraction modes does not satisfy the condition that is greater than or equal to the first threshold and less than or equal to the second threshold, then determining according to the keyword
  • the mechanism supplements or screens the appropriate number of keywords.
  • the keyword is extracted by using the extraction method of the third embodiment of the call key content extraction device, and when the total number of extracted keywords is less than the first threshold, the above-mentioned threshold is used.
  • the extraction method of the first embodiment of the call key content extraction device extracts keywords, if the total number of keywords extracted in the two extraction modes meets the first threshold and is less than or equal to the second threshold.
  • the condition, the all keywords extracted are the set of keywords to be obtained; if the total number of keywords extracted in the two extraction modes does not satisfy the first threshold and is less than or equal to the said
  • the condition of the second threshold is then supplemented or screened by an appropriate amount of keywords according to the keyword determination mechanism.
  • the combination of the two extraction methods can extract the appropriate and more accurate keywords, and extract the key content of the call according to the extracted keywords, and make the data foundation, which is most accurate and useful for extracting to the call. Information.
  • the fourth embodiment of the call key content extracting apparatus of the present invention is proposed based on the third embodiment of the call key content extracting apparatus.
  • the call key content is extracted.
  • the method also includes:
  • the second extraction module 600 is configured to extract a word of the specified part of speech from the text content corresponding to the recorded content as the key content of the call.
  • the keyword extracted from the information related to the call, or the keyword extracted from the mass vocabulary in the keyword determining mechanism sometimes the text content corresponding to the recorded content of the call is irrelevant In this case, the key content of the call extracted at this time may be empty.
  • the second extraction module 600 may extract words specifying the part of speech, such as nouns, quantifiers, verbs, etc., from the text content corresponding to the recorded content, as the key of the call of the call. content.
  • the call key content extracting apparatus extracts the key content of the call according to the keyword determined by the information related to the call and the keyword determining mechanism.
  • the words of the specified part of speech are extracted from the text content corresponding to the recorded content of the call, thereby ensuring that the extracted key content of the call is not empty, and providing the user with certain useful information.
  • Embodiments of the present invention also provide a storage medium.
  • the foregoing storage medium may be configured to store program code for performing the following steps:
  • the storage medium is further configured to store program code for performing the following steps: S1, after extracting the call key content, saving the extracted call key content; wherein, saving the extracted call key content includes: When the key content of the call includes date and/or time, a corresponding reminder is established according to the key content of the call to send a reminder to the user at a specified time; or, when the key content of the call does not include a date and/or time, the call is made
  • the key content is stored in a text-type application for users to view the key content of the call at any time.
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • the duration of the call is counted and the Recording, and when the duration of the call is greater than or equal to the preset duration, the obtained information related to the call and the preset keyword determining mechanism determine a set of keywords, and according to the obtained a set of keywords, extracting key content of the call from the recorded content of the call, realizing automatic extraction of important information in the call content, thereby obtaining the key content of the call, facilitating subsequent call key based on the extraction
  • the content provides users with convenient services for various purposes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Telephone Function (AREA)
  • Telephonic Communication Services (AREA)

Abstract

Disclosed in the embodiments of the present invention is a method for extracting key content of a call, comprising: upon detecting a call has been established, compiling statistics about duration of the call and recording the call; when the duration of the call is greater than or equal to a preset duration, determining a group of keywords related to the call according to acquired information relating to the call and a preset keyword determination mechanism; according to the determined group of keywords, extracting key content of the call from recorded content of the call. Further disclosed by the embodiments of the present invention is an apparatus for extracting key content of a call. The embodiments of the present invention may automatically extract key content of an important call.

Description

通话关键内容提取方法及装置Call key content extraction method and device 技术领域Technical field
本发明实施例涉及通信技术领域,尤其涉及一种通话关键内容提取方法及装置。The embodiments of the present invention relate to the field of communications technologies, and in particular, to a call key content extraction method and apparatus.
背景技术Background technique
手机等通信终端,是当今社会中人与人之间沟通交流所不可缺少的工具,很多无法面对面完成的事情,都需要通过打电话来完成。然而在通话过程中,双方提到的一些关键词语,例如时间、地点、人物、处理对象等重要信息,往往会因为接听者一时走神,没注意倾听,或者是因为周围环境太嘈杂,又或是挂电话后未及时记录这些信息,而事后把这些关键信息遗漏或者记错。再次打电话去追问对方这些信息,往往是非常不合适的事情,尤其是在工作、面试以及商务会谈中的电话。Communication terminals such as mobile phones are indispensable tools for communication between people in today's society. Many things that cannot be done face to face need to be completed by telephone. However, during the call, some key words mentioned by the two parties, such as time, place, people, and processing objects, are often ignored because the listener is distracted, or because the surrounding environment is too noisy, or This information was not recorded in time after the phone was hanged, and the key information was omitted or misjudged afterwards. Calling again to ask the other person's information is often very inappropriate, especially during work, interviews, and business meetings.
虽然目前的手机普遍具有通话录音功能,机主在通话时可以在通话界面将录音按键打开,在通话结束后,再在对应的录音存储文件中找到当时那通电话的录音内容,进行回放以获取自己需要的信息。然而,这样的通话关键内容提取方式对于用户来说是极为不便的,主要存在以下几个问题:Although the current mobile phone generally has a call recording function, the owner can open the recording button on the call interface during the call, and after the call ends, find the recorded content of the call at the time in the corresponding recording storage file, and play back to obtain The information you need. However, such a key content extraction method is extremely inconvenient for the user, and the following problems mainly exist:
(1)需要花时间去查找指定通话的录音内容,且需要将录音内容进行全部回放,或者花时间去前进或者后退录音内容,才能将需要的关键内容提取出来;(1) It takes time to find the recording content of the specified call, and it is necessary to play back all the recorded content, or take the time to go forward or back the recorded content, in order to extract the key content needed;
(2)在回放录音的同时,还需要手动记录需要的关键内容,在记录关键内容的过程中也可能出现听错或者记错的情况;(2) While playing back the recording, it is also necessary to manually record the key content required, and in the process of recording the key content, errors or errors may occur;
(3)如果手机中保存了多条通话的录音内容,在查找并回放以确认是否为需要的录音内容时,很有可能混淆或者搞错。(3) If the recording content of multiple calls is saved in the mobile phone, it may be confused or mistaken when searching and playing back to confirm whether it is the desired recording content.
因而,有必要提出一种针对重要通话的关键内容提取方案,以简化用户操作,节省用户时间和精力,为用户获取通话的关键内容提供便利。 Therefore, it is necessary to propose a key content extraction scheme for important calls, to simplify user operations, save user time and effort, and facilitate the user to obtain key content of the call.
发明内容Summary of the invention
本发明实施例提供一种通话关键内容提取方法及装置,旨在解决相关通话关键内容提取方式极为不便,浪费时间和精力,且容易出错的技术问题。The embodiment of the invention provides a method and a device for extracting key content of a call, which aims to solve the technical problem that the related key content extraction method is extremely inconvenient, wastes time and effort, and is prone to error.
为实现上述目的,本发明实施例提供一种通话关键内容提取方法,所述通话关键内容提取方法包括:To achieve the above objective, an embodiment of the present invention provides a call key content extraction method, where the call key content extraction method includes:
在检测到有通话建立时,统计所述通话的时长,并对所述通话进行录音;When it is detected that a call is established, the duration of the call is counted, and the call is recorded;
在所述通话的时长大于或等于预置时长时,根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词;When the duration of the call is greater than or equal to the preset duration, determining a set of keywords related to the call according to the acquired information related to the call and a preset keyword determining mechanism;
根据确定出的一组关键词,从所述通话的录音内容中提取通话关键内容。According to the determined set of keywords, the key content of the call is extracted from the recorded content of the call.
可选地,在提取出通话关键内容后,所述通话关键内容提取方法还包括:Optionally, after the call key content is extracted, the call key content extraction method further includes:
保存提取出的所述通话关键内容;Saving the extracted call key content;
其中,所述保存提取出的所述通话关键内容包括:The saving the extracted call key content includes:
在所述通话关键内容包含有日期和/或时间时,根据所述通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;或者,When the call key content includes a date and/or a time, a corresponding reminder item is established according to the call key content to issue a reminder to the user at a specified time; or
在所述通话关键内容未包含有日期和/或时间时,将所述通话关键内容存储到文本类型的应用中,以供用户随时查看所述通话的通话关键内容。When the call key content does not include a date and/or time, the call key content is stored in a text type application for the user to view the call key content of the call at any time.
可选地,所述根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词包括:Optionally, the determining, according to the acquired information related to the call, and the preset keyword determining mechanism, determining a group of keywords related to the call includes:
从指定应用中查找与所述通话中的对方号码相关的历史记录;Finding a history related to the counterpart number in the call from the specified application;
按照历史记录的创建时间从大到小的顺序,根据所述关键词确定机制从一个或多个历史记录中提取关键词。The keywords are extracted from one or more histories according to the keyword determination mechanism in descending order of creation time of the history.
可选地,所述根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词包括: Optionally, the determining, according to the acquired information related to the call, and the preset keyword determining mechanism, determining a group of keywords related to the call includes:
根据所述通话中的对方号码对应的通讯录联系人详情,以及所述关键词确定机制,展开关键词智能联想,并提取关键词。And according to the address book contact details corresponding to the counterpart number in the call, and the keyword determining mechanism, the keyword intelligent association is expanded, and the keyword is extracted.
可选地,所述根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词还包括:Optionally, the determining, according to the obtained information related to the call, and the preset keyword determining mechanism, determining a group of keywords related to the call further includes:
当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;When the total number of extracted keywords is less than the preset first threshold, according to the massive vocabulary in the keyword determining mechanism, the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。When the total number of extracted keywords is greater than a preset second threshold, the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
可选地,当提取的通话关键内容为空时,所述通话关键内容提取方法还包括:Optionally, when the extracted call key content is empty, the call key content extraction method further includes:
从所述录音内容对应的文本内容中提取指定词性的词语,作为所述通话的通话关键内容。Extracting a word of the specified part of speech from the text content corresponding to the recorded content as a key content of the call of the call.
为实现上述目的,本发明实施例还提供一种通话关键内容提取装置,所述通话关键内容提取装置包括:In order to achieve the above object, an embodiment of the present invention further provides a call key content extracting apparatus, where the call key content extracting apparatus includes:
计时模块,设置为在检测到有通话建立时,统计所述通话的时长;a timing module, configured to count the duration of the call when a call establishment is detected;
录音模块,设置为在检测到有通话建立时,对所述通话进行录音;a recording module, configured to record the call when a call establishment is detected;
确定模块,设置为在所述通话的时长大于或等于预置时长时,根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词;Determining, when the duration of the call is greater than or equal to a preset duration, determining a set of keys related to the call according to the acquired information related to the call and a preset keyword determining mechanism word;
第一提取模块,设置为根据确定出的一组关键词,从所述通话的录音内容中提取通话关键内容。The first extraction module is configured to extract the call key content from the recorded content of the call according to the determined set of keywords.
可选地,在提取出通话关键内容后,所述通话关键内容提取装置还包括:Optionally, after the call key content is extracted, the call key content extracting apparatus further includes:
存储模块,设置为保存提取出的所述通话关键内容;a storage module, configured to save the extracted key content of the call;
其中,所述存储模块包括: The storage module includes:
第一存储单元,设置为在所述通话关键内容包含有日期和/或时间时,根据所述通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;a first storage unit, configured to establish a corresponding reminding item according to the key content of the call when the call key content includes a date and/or a time, to issue a reminder to the user at a specified time;
第二存储单元,设置为在所述通话关键内容未包含有日期和/或时间时,将所述通话关键内容存储到文本类型的应用中,以供用户随时查看所述通话的通话关键内容。The second storage unit is configured to store the call key content into a text type application when the call key content does not include a date and/or time, so that the user can view the call key content of the call at any time.
可选地,所述确定模块包括:Optionally, the determining module includes:
查找单元,设置为从指定应用中查找与所述通话中的对方号码相关的历史记录;a search unit configured to search for a history related to the counterpart number in the call from the specified application;
第一提取单元,设置为按照历史记录的创建时间从大到小的顺序,根据所述关键词确定机制从一个或多个历史记录中提取关键词。The first extracting unit is configured to extract keywords from the one or more history records according to the keyword determining mechanism in an order of the history creation time from large to small.
可选地,所述确定模块包括:Optionally, the determining module includes:
第二提取单元,设置为根据所述通话中的对方号码对应的通讯录联系人详情,以及所述关键词确定机制,展开关键词智能联想,并提取关键词。The second extracting unit is configured to expand the keyword intelligent association according to the address book contact details corresponding to the counterpart number in the call, and the keyword determining mechanism, and extract keywords.
可选地,所述确定模块还包括:Optionally, the determining module further includes:
第三提取单元,设置为当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;a third extracting unit, configured to: when the total number of extracted keywords is less than a preset first threshold, continue to extract keywords according to the massive vocabulary in the keyword determining mechanism, so that the extracted one is obtained The total number of group keywords is greater than or equal to a preset first threshold and less than or equal to a preset second threshold;
筛选单元,设置为当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。a screening unit, configured to: when the total number of extracted keywords is greater than a preset second threshold, select a keyword from the extracted keywords according to the keyword determining mechanism, so as to obtain a set of key selected by the screening The total number of words is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
可选地,当提取的通话关键内容为空时,所述通话关键内容提取装置还包括:Optionally, when the extracted call key content is empty, the call key content extracting apparatus further includes:
第二提取模块,设置为从所述录音内容对应的文本内容中提取指定词性的词语,作为所述通话的通话关键内容。The second extraction module is configured to extract a word of the specified part of speech from the text content corresponding to the recorded content as a key content of the call of the call.
在本发明实施例中,还提供了一种计算机存储介质,该计算机存储介 质可以存储有执行指令,该执行指令用于执行上述实施例中的通话关键内容提取方法。In the embodiment of the present invention, a computer storage medium is also provided, and the computer storage medium is provided. The quality may be stored with an execution instruction for executing the call key content extraction method in the above embodiment.
本发明实施例提出的通话关键内容提取方法及装置,在通话建立时,统计所述通话的时长并对所述通话进行录音,且在所述通话的时长大于或等于预置时长时,通过获取得到的与所述通话相关的信息,以及预置的关键词确定机制,确定出一组关键词,并根据得到的一组关键词,从所述通话的录音内容中提取通话关键内容,实现了对通话内容中的重要信息的自动提取,从而得到所述通话的通话关键内容,便于后续基于提取得到的通话关键内容为用户提供各种用途的便捷服务。The call key content extraction method and device provided by the embodiment of the present invention collects the duration of the call and records the call when the call is established, and obtains when the duration of the call is greater than or equal to the preset duration. Obtaining information related to the call, and a preset keyword determining mechanism, determining a set of keywords, and extracting key content of the call from the recorded content of the call according to the obtained set of keywords, The automatic extraction of the important information in the call content, thereby obtaining the call key content of the call, and facilitating the subsequent convenient service for the user to provide various uses based on the extracted call key content.
附图说明DRAWINGS
图1为本发明通话关键内容提取方法第一实施例的流程示意图;1 is a schematic flowchart of a first embodiment of a method for extracting key content of a call according to the present invention;
图2为图1中步骤S20的细化流程示意图;2 is a schematic diagram of a refinement process of step S20 in FIG. 1;
图3为本发明通话关键内容提取方法第二实施例的流程示意图;3 is a schematic flowchart of a second embodiment of a call key content extraction method according to the present invention;
图4为本发明通话关键内容提取装置第一实施例的功能模块示意图;4 is a schematic diagram of functional modules of a first embodiment of a call key content extracting apparatus according to the present invention;
图5为图4中确定模块的细化功能模块示意图;FIG. 5 is a schematic diagram of a refinement function module of the determining module in FIG. 4; FIG.
图6为本发明通话关键内容提取装置第二实施例的功能模块示意图;6 is a schematic diagram of functional modules of a second embodiment of a call key content extracting apparatus according to the present invention;
图7为图6中存储模块的细化功能模块示意图;7 is a schematic diagram of a refinement function module of the storage module in FIG. 6;
图8为本发明通话关键内容提取装置第三实施例中确定模块的细化功能模块示意图;8 is a schematic diagram of a refinement function module of a determining module in a third embodiment of the call key content extracting apparatus of the present invention;
图9为本发明通话关键内容提取装置第四实施例的功能模块示意图。FIG. 9 is a schematic diagram of functional modules of a fourth embodiment of a call key content extracting apparatus according to the present invention.
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments.
具体实施方式detailed description
应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。 It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
本发明实施例提供一种通话关键内容提取方法,如图1所示,示出了本发明通话关键内容提取方法第一实施例的流程示意图,所述通话关键内容提取方法包括:An embodiment of the present invention provides a method for extracting key content of a call. As shown in FIG. 1 , a schematic flowchart of a method for extracting a key content of a call according to the present invention is shown.
S10、在检测到有通话建立时,统计所述通话的时长,并对所述通话进行录音;S10. When it is detected that a call is established, the duration of the call is counted, and the call is recorded;
所述通话关键内容提取方法可在任意的具有通话功能的终端上进行实施,例如,智能手机。当用户接到来电并接听电话,或是用户呼出电话且对方接听电话,则在用户所使用终端及对方所使用终端之间成功建立了通话连接。当用户所使用终端检测到有通话建立时,可通过设置在终端上的计时器统计所述通话的实时时长,并通过设置在终端上的录音设备对所述通话进行录音,其中,对所述通话进行录音得到的录音内容,可先存储在缓冲区中。The call key content extraction method can be implemented on any terminal having a call function, for example, a smart phone. When the user receives an incoming call and answers the call, or the user calls out and the other party answers the call, the call connection is successfully established between the terminal used by the user and the terminal used by the other party. When the terminal used by the user detects that a call is established, the real time duration of the call may be counted by a timer set on the terminal, and the call is recorded by a recording device set on the terminal, where The recorded content obtained by the call recording can be stored in the buffer first.
S20、在所述通话的时长大于或等于预置时长时,根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词;S20. When the duration of the call is greater than or equal to the preset duration, determine a set of keywords related to the call according to the acquired information related to the call and a preset keyword determining mechanism.
可在所述通话结束时,通过比较统计得到的所述通话的总时长与所述预置时长的大小,在所述通话的总时长大于或等于所述预置时长时,进行后续操作;也可在所述通话进行的过程中,当统计得到的所述通话的实时时长大于或等于所述预置时长时,进行后续操作。At the end of the call, the total duration of the call and the size of the preset duration obtained by comparing statistics may be performed after the total duration of the call is greater than or equal to the preset duration; During the process of the call, when the calculated real-time duration of the call is greater than or equal to the preset duration, a subsequent operation may be performed.
其中,所述预置时长为预先设置的一个时长值,例如,1分钟或30秒,可由用户自己设置,也可由终端设置为默认值;统计得到的每个通话的时长,可精确到分秒。通过比较每个通话的时长与所述预置时长的大小,可将一些不重要的通话过滤掉,不对其进行通话关键内容提取,且在这些通话结束通话时,将这些通话的录音在缓冲区的录音内容删除掉,以节约手机存储空间,减少后台系统的运行压力和耗电量。不重要的通话,一般为几秒、十几秒的电话,例如人们经常接到的一些快递电话、广告营销、骚扰电话、打错的陌生来电等,这些通话一般在接通后的几秒钟左右就会被挂断,基本没有保存通话关键内容的必要。如果事先不进行筛选过滤, 而将所有通话的录音内容都进行缓存和提取,这样必然会给手机的运行速度和功耗带来很大的压力。因而,通过使用预置时长进行限制,能将这些不必要的通话提前过滤掉,减轻后台的运行压力和缓冲区的内存消耗,是非常有必要的。The preset duration is a preset duration value, for example, 1 minute or 30 seconds, which can be set by the user or set by the terminal as a default value; the duration of each call obtained by the statistics can be accurate to minutes and seconds. . By comparing the duration of each call with the preset duration, some unimportant calls can be filtered out, the call key content is not extracted, and the calls are recorded in the buffer when the calls are over. The recorded content is deleted to save mobile phone storage space and reduce the running pressure and power consumption of the background system. Unimportant calls, usually a few seconds, ten seconds of phone calls, such as some courier calls, advertising marketing, harassing calls, wrong calls, etc. that people often receive, these calls are usually a few seconds after being connected. The left and right will be hung up, and there is basically no need to save the key content of the call. If you do not filter beforehand, The recording and extraction of all the call recordings will inevitably bring great pressure to the running speed and power consumption of the mobile phone. Therefore, by using the preset duration to limit, it is necessary to filter out these unnecessary calls in advance, and to alleviate the running pressure in the background and the memory consumption of the buffer.
在进行后续操作时,终端可通过查询其安装的各种应用或存储文件中存储的、与所述通话相关的一些信息,从而得到与所述通话相关的历史记录,进而根据预置的关键词确定机制,从得到的历史记录中提取出与所述通话相关的一组关键词。其中,所述关键词确定机制用于规定,如何根据不同的应用或存储文件中与所述通话相关的信息,来提取与所述通话相关的关键词;所述关键词确定机制中预先设置有多种提取规则,规定了关键词的提取范围,还提供了关键词的海量词库。When performing the subsequent operations, the terminal may obtain some history information related to the call by querying various applications installed in the installed application or the storage file, thereby obtaining a history related to the call, and then according to the preset keywords. The determining mechanism extracts a set of keywords related to the call from the obtained history. The keyword determining mechanism is configured to specify, according to information related to the call in different applications or stored files, keywords related to the call, where the keyword determining mechanism is preset A variety of extraction rules, which stipulate the extraction range of keywords, and also provide a massive vocabulary of keywords.
进一步地,参照图2,上述步骤S20具体包括:Further, referring to FIG. 2, the foregoing step S20 specifically includes:
S21、从指定应用中查找与所述通话中的对方号码相关的历史记录;S21. Search for a history related to the counterpart number in the call from the specified application.
所述指定应用可以为终端上安装的任意应用,本实施例中,所述指定应用优选为各种终端均安装有的日历、闹钟、备忘录、记事本等常用工具性应用。在这些指定应用中,如果存储有与所述通话中的对方号码相关的事项或记录,则终端通过查询即可得到与所述通话中的对方号码相关的历史记录。例如,假设闹钟应用中存储了与所述通话中的对方号码相关的一个提醒事项,如2016年3月15日上午9:00与王总洽谈合作事宜(其中,终端通讯录中存储有王总的电话号码,也即所述通话中的对方号码),记事本应用中存储有与王总相关的两条记录,如王总的公司主要生产通信设备、王总的公司地址是深圳市南山区科技园,则终端通过查询,可得到这两个应用中的3条历史记录。The specified application may be any application installed on the terminal. In this embodiment, the specified application is preferably a common tool application such as a calendar, an alarm clock, a memo, or a notepad installed on various terminals. In these designated applications, if an item or record related to the counterpart number in the call is stored, the terminal can obtain a history related to the counterpart number in the call by querying. For example, suppose that the alarm application stores a reminder related to the other party number in the call, such as the cooperation with the general manager at 9:00 am on March 15, 2016 (where the terminal address book stores Wang Zong) The phone number, that is, the other party number in the call), the notebook application stores two records related to Wang Zong. For example, the company’s main production communication equipment, Wang’s company address is Nanshan District, Shenzhen. In the Science and Technology Park, the terminal can obtain 3 historical records in the two applications through inquiry.
S22、按照历史记录的创建时间从大到小的顺序,根据所述关键词确定机制从一个或多个历史记录中提取关键词。S22. Extract keywords from one or more historical records according to the keyword determining mechanism according to an order in which the creation time of the history records is from large to small.
所述关键词确定机制中预先设置有第一阈值和第二阈值,所述第一阈值和所述第二阈值为两个固定值,其中所述第二阈值大于所述第一阈值,其取值可根据实际需求由用户或终端来设定,这两个阈值的设置是为了保 证提取的关键词的个数不过于少也不过于多,避免后续提取的通话关键内容较少或繁多。The first threshold and the second threshold are preset in the keyword determining mechanism, where the first threshold and the second threshold are two fixed values, wherein the second threshold is greater than the first threshold, where The value can be set by the user or the terminal according to the actual demand. The two thresholds are set to protect The number of keywords extracted by the certificate is not too small or too much, and the key content of the call that is subsequently extracted is less or more.
假设闹钟应用中查到的历史记录的创建时间晚于(即大于)记事本中的两条历史记录的创建时间,则闹钟中的该条历史记录是当前最新的信息,此时,终端按照历史记录的创建时间从大到小的顺序,先从闹钟应用中的该条历史记录中提取关键词,假设根据所述关键词确定机制提取得到的关键词为“2016年3月15日”“上午9:00”“王总”“洽谈”“合作”,共5个关键词。如果所述第一阈值大于5,则说明根据闹钟应用中的历史记录提取的关键词个数较少,此时,可从记事本的两条历史记录中创建时间较大的一条历史记录中继续提取,假设又提取出1个关键词,如果此时提取出的关键词的总个数满足大于或等于预置的第一阈值且小于或等于预置的第二阈值的条件,则无需再提取,此时得到的6个关键词即为要提取的一组关键词;如果所述第一阈值也大于6,则说明根据两条历史记录提取的关键词个数仍不够,此时,需从第三条历史记录中继续提取关键词,直到满足提取出的关键词的总个数大于或等于所述第一阈值且小于或等于所述第二阈值的条件为止。Assuming that the history recorded in the alarm application is created later than (ie, greater than) the creation time of the two history records in the notebook, the history record in the alarm is the latest information. At this time, the terminal follows the history. The order of creation of records is from the largest to the smallest, first extracting keywords from the history record in the alarm application, and assuming that the keywords extracted according to the keyword determination mechanism are "March 15, 2016" "Morning" 9:00" "Wang total" "negotiation" "cooperation", a total of 5 keywords. If the first threshold is greater than 5, it means that the number of keywords extracted according to the history record in the alarm application is small. In this case, the history may be created from a history record with a larger time in the two history records of the notebook. Extracting, assuming that another keyword is extracted, if the total number of keywords extracted at this time satisfies the condition that is greater than or equal to the preset first threshold and less than or equal to the preset second threshold, no extraction is required. The six keywords obtained at this time are a set of keywords to be extracted; if the first threshold is also greater than 6, it means that the number of keywords extracted according to the two historical records is still insufficient, and at this time, it is necessary to The third history record continues to extract keywords until the condition that the total number of extracted keywords is greater than or equal to the first threshold and less than or equal to the second threshold is satisfied.
进一步地,上述步骤S20还包括:Further, the above step S20 further includes:
当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;When the total number of extracted keywords is less than the preset first threshold, according to the massive vocabulary in the keyword determining mechanism, the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。When the total number of extracted keywords is greater than a preset second threshold, the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
如果从已有的三条历史记录中提取的关键词的总个数仍小于所述第一阈值,则可根据所述关键词确定机制,从其中的关键词的海量词库中确定出适量个数的关键词作为补充;如果提取的关键词的总个数大于所述第二阈值,则根据所述关键词确定机制,去掉适量个数的关键词即可。需要说明的是,提取得到的一组关键词中,各个关键词均不相同。 If the total number of keywords extracted from the existing three historical records is still less than the first threshold, the appropriate number of the keywords may be determined from the keyword vocabulary of the keywords according to the keyword determining mechanism. The keyword is added; if the total number of extracted keywords is greater than the second threshold, then according to the keyword determining mechanism, an appropriate number of keywords may be removed. It should be noted that among the extracted keywords, each keyword is different.
S30、根据确定出的一组关键词,从所述通话的录音内容中提取通话关键内容。S30. Extract call content from the recorded content of the call according to the determined set of keywords.
在提取得到一组关键词后,终端将所述通话的录音内容全部或分段逐步转为文本内容,然后通过将得到的一组关键词与所述文本内容进行模糊匹配或含义相近匹配,从而提取得到所述通话的通话关键内容。After extracting a set of keywords, the terminal gradually converts all or part of the recorded content of the call into text content, and then performs fuzzy matching or similar matching of the obtained set of keywords with the text content, thereby The call key content of the call is extracted.
在所述通话结束通话时,可将存储在缓冲区的所述通话的录音内容存储到终端的指定存储区域,以便用户事后调取所述通话的通话录音。When the call ends the call, the recorded content of the call stored in the buffer may be stored in a designated storage area of the terminal, so that the user can retrieve the call recording of the call afterwards.
本发明实施例提出的通话关键内容提取方法,在通话建立时,统计所述通话的时长并对所述通话进行录音,且在所述通话的时长大于或等于预置时长时,通过获取得到的与所述通话相关的信息,以及预置的关键词确定机制,确定出一组关键词,并根据得到的一组关键词,从所述通话的录音内容中提取通话关键内容,实现了对通话内容中的重要信息的自动提取,从而得到所述通话的通话关键内容,便于后续基于提取得到的通话关键内容为用户提供各种用途的便捷服务。The method for extracting the key content of the call provided by the embodiment of the present invention, when the call is established, the duration of the call is counted and the call is recorded, and when the duration of the call is greater than or equal to the preset duration, the obtained call is obtained. Information related to the call, and a preset keyword determining mechanism, determining a set of keywords, and extracting key content of the call from the recorded content of the call according to the obtained set of keywords, and realizing the call The automatic extraction of the important information in the content, thereby obtaining the key content of the call of the call, and facilitating the subsequent convenient service for the user to provide various uses based on the extracted key content of the call.
基于上述第一实施例提出本发明通话关键内容提取方法第二实施例,在本实施例中,参照图3,在提取出通话关键内容后,所述通话关键内容提取方法还包括:The second embodiment of the call key content extraction method of the present invention is proposed based on the first embodiment. In this embodiment, referring to FIG. 3, after the call key content is extracted, the call key content extraction method further includes:
S40、保存提取出的所述通话关键内容。S40. Save the extracted call key content.
在提取得到所述通话的通话关键内容后,终端可将所述通话关键内容保存在终端的指定存储位置或指定应用中,以便用户随时查看。可以理解,终端还可将得到的所述通话关键内容转为语音格式的文件进行存储,在用户查看所述通话的通话关键内容时,通过语音播报的方式将所述通话关键内容传递给用户。After extracting the call key content of the call, the terminal may save the call key content in a designated storage location or a designated application of the terminal, so that the user can view it at any time. It can be understood that the terminal can also convert the obtained call key content into a file in a voice format for storage, and when the user views the key content of the call, the call key content is delivered to the user by means of voice broadcast.
在提取得到所述通话的通话关键内容后,存储所述通话关键内容,以便用户随时查看,使得用户在通话时能够专注地接听电话,而无需一边接听电话一边记录关键内容,节省了用户的操作和消耗的精力,也为用户获得通话关键内容提供了便利。 After extracting the call key content of the call, the call key content is stored, so that the user can view at any time, so that the user can receive the call intently during the call without recording the key content while answering the phone, thereby saving the user's operation. And the energy consumed, it also facilitates users to get key content of the call.
其中,上述步骤S40包括:Wherein, the above step S40 includes:
在所述通话关键内容包含有日期和/或时间时,根据所述通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;或者,When the call key content includes a date and/or a time, a corresponding reminder item is established according to the call key content to issue a reminder to the user at a specified time; or
在所述通话关键内容未包含有日期和/或时间时,将所述通话关键内容存储到文本类型的应用中,以供用户随时查看所述通话的通话关键内容。When the call key content does not include a date and/or time, the call key content is stored in a text type application for the user to view the call key content of the call at any time.
在保存所述通话的通话关键内容时,如果所述通话关键内容中包含日期和/或时间,则终端可使用具有提醒功能的应用(例如,日历或闹钟)建立提醒事项,然后将所述通话关键内容按照提醒事项的规定添加到该提醒事项中,例如,将通话关键内容“2016年5月1日、晚上6点、小王、肯德基、吃饭”中的日期“2016年5月1日”,设置到指定应用日历的新建提醒事项的日期中,将该通话关键内容中的“晚上6点”设置到该提醒事项的时间中,将该通话关键内容的“小王、肯德基、吃饭”,设置到该提醒事项的标题或备注中。提醒事项自动设置完成后,终端可将设置页面提供给用户,由用户根据个人需求进行添加或修改设置,用户还可设置提前多久进行提醒等。用户设置完成并保存后,终端将根据提起多久进行提醒的设置,在设置的日期和时间对应的时刻到来之前,提醒用户该事项。其中,在设置有提前多久提醒时,所述指定时间为相对于设置的日期和时间提前发出提醒时的时间,在未设置有提前多久提醒时,所述指定时间即为设置的日期和时间对应的时刻。When saving the call key content of the call, if the call key content includes a date and/or time, the terminal may use an application with a reminder function (for example, a calendar or an alarm clock) to establish a reminder, and then call the call The key content is added to the reminder in accordance with the reminder, for example, the date of the key content of the call "May 1, 2016, 6:00, Xiao Wang, KFC, and dinner", "May 1, 2016" , set to the date of the new reminder of the specified application calendar, set the "6 o'clock" in the key content of the call to the time of the reminder, the "key king, KFC, eat" of the key content of the call, Set to the title or note of the reminder. After the automatic setting of the reminder is completed, the terminal can provide the setting page to the user, and the user can add or modify the setting according to individual needs, and the user can also set how long to advance the reminder. After the user setting is completed and saved, the terminal will remind the user of the item according to the setting of how long to remind the reminder before the time corresponding to the set date and time. Wherein, when the reminder is set in advance, the designated time is a time when the reminder is issued in advance with respect to the set date and time, and when the reminder is not set in advance, the specified time is the set date and time corresponding to the set time Moment.
如果所述通话关键内容中未包含日期和/或时间,则终端可使用文本类型的应用存储所述通话关键内容,例如,可将所述通话关键内容存储在备忘录或记事本中,以便用户随时查看。If the date and/or time is not included in the call key content, the terminal may use the text type application to store the call key content, for example, the call key content may be stored in a memo or a notebook, so that the user can View.
本发明实施例提出的通话关键内容提取方法,将提取得到的通话关键内容根据是否包含有日期和/或时间进行区分存储,以将包含有日期和/或时间的通话关键内容以提醒事项的形式存储,便于提醒用户相应事项,避免遗忘重要事情的处理,以及将未包含有日期和/或时间的通话关键内容以文本形式存储在文本类型的应用中,便于用户随时查看,省去了需要记忆的麻烦,使得用户在通话过程中更为省心省力。 The call key content extraction method is provided in the embodiment of the present invention, and the extracted call key content is separately stored according to whether the date and/or time is included, so as to include the date and/or time of the call key content in the form of a reminder item. Storage, easy to remind users of the corresponding matters, to avoid the handling of important things, and to store the key content of the call without date and / or time in the text type of application, so that users can view at any time, eliminating the need to remember The trouble makes the user more worry-free during the call.
基于上述第二实施例提出本发明通话关键内容提取方法第三实施例,在本实施例中,上述步骤S20具体包括:The third embodiment of the call key content extraction method of the present invention is proposed based on the foregoing second embodiment. In this embodiment, the foregoing step S20 specifically includes:
根据所述通话中的对方号码对应的通讯录联系人详情,以及所述关键词确定机制,展开关键词智能联想,并提取关键词。And according to the address book contact details corresponding to the counterpart number in the call, and the keyword determining mechanism, the keyword intelligent association is expanded, and the keyword is extracted.
终端根据所述通话的对方号码,即可获取得到对方号码在通讯录中的联系人详情,在所述联系人详情中可能存储有一些重要的信息,这些信息即可被提取作为关键词。The terminal can obtain the contact details of the other party's number in the address book according to the other party's number of the call, and some important information may be stored in the contact details, and the information may be extracted as a keyword.
进一步地,上述步骤S20还包括:Further, the above step S20 further includes:
当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;When the total number of extracted keywords is less than the preset first threshold, according to the massive vocabulary in the keyword determining mechanism, the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。When the total number of extracted keywords is greater than a preset second threshold, the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
假设根据所述通话的对方号码获得的联系人详情为,“姓名:小李,公司:链家房屋中介,职业:房屋中介,备注:学位房、小学”,则可将“小李”“链家”“房屋中介”“学位房”“小学”作为关键词并展开智能联想,从而得到更多相关的关键词。如果得到的关键词的总个数小于所述第一阈值,则可从所述关键词确定机制的关键词的海量词库中选取适量个数的相关关键词,从而使得到的一组关键词的总个数大于或等于所述第一阈值且小于或等于所述第二阈值。如果得到的关键词的总个数大于所述第二阈值,则根据所述关键词确定机制,去掉适量个数的关键词即可。需要说明的是,提取得到的一组关键词中,各个关键词均不相同。Assume that the contact details obtained according to the other party number of the call are: "Name: Xiao Li, company: chain home agency, occupation: housing agency, remarks: degree room, primary school", then "Xiao Li" "chain home" "House agency", "degree room" and "primary school" as keywords and develop intelligent associations to get more relevant keywords. If the total number of keywords obtained is less than the first threshold, an appropriate number of related keywords may be selected from the mass vocabulary of the keyword determining mechanism keyword, thereby causing a set of keywords The total number of times is greater than or equal to the first threshold and less than or equal to the second threshold. If the total number of keywords obtained is greater than the second threshold, then according to the keyword determining mechanism, an appropriate number of keywords may be removed. It should be noted that among the extracted keywords, each keyword is different.
本发明实施例提出的通话关键内容提取方法,从与所述通话中的对方号码对应的通讯录联系人详情中提取关键词,通过该方式能够获得较为精确的关键词,有利于从所述通话的录音内容中提取较为准确的通话关键内容。 The method for extracting key content of the call provided by the embodiment of the present invention extracts a keyword from the contact details of the address book corresponding to the other party number in the call, and the method can obtain a more accurate keyword, which is beneficial to the call from the call. The recorded content extracts more accurate call key content.
可以理解,还存在这样的两个通话关键内容提取方法实施例:(1)、在上述步骤S20中,先采用上述第一实施例的提取方式提取关键词,在提取的关键词总个数小于所述第一阈值时,再采用上述第三实施例的提取方式提取关键词,如果两种提取方式下提取得到的关键词的总个数满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则提取出的所有关键词即为要得到的一组关键词;如果两种提取方式下提取得到的关键词的总个数不满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则再根据所述关键词确定机制补充或筛选适量个数的关键词。It can be understood that there are two embodiments of the method for extracting the key content of the call. (1) In the above step S20, the keyword is extracted by using the extraction method of the first embodiment, and the total number of keywords extracted is less than When the first threshold is used, the keyword is extracted by using the extraction method of the third embodiment, and if the total number of keywords extracted in the two extraction modes meets the first threshold and is less than or equal to When the condition of the second threshold is described, all the keywords extracted are the set of keywords to be obtained; if the total number of keywords extracted in the two extraction modes does not satisfy the first threshold and If the condition is less than or equal to the second threshold, then the appropriate number of keywords are supplemented or screened according to the keyword determining mechanism.
(2)、在上述步骤S20中,先采用上述第三实施例的提取方式提取关键词,在提取的关键词总个数小于所述第一阈值时,再采用上述第一实施例的提取方式提取关键词,如果两种提取方式下提取得到的关键词的总个数满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则提取出的所有关键词即为要得到的一组关键词;如果两种提取方式下提取得到的关键词的总个数不满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则再根据所述关键词确定机制补充或筛选适量个数的关键词。(2) In the above step S20, the keyword is extracted by using the extraction method of the third embodiment, and when the total number of extracted keywords is less than the first threshold, the extraction method of the first embodiment is used. Extracting a keyword, if the total number of keywords extracted in the two extraction modes satisfies a condition greater than or equal to the first threshold and less than or equal to the second threshold, all the extracted keywords are a set of keywords obtained; if the total number of keywords extracted in the two extraction modes does not satisfy a condition greater than or equal to the first threshold and less than or equal to the second threshold, then according to the key The word determination mechanism supplements or screens the appropriate number of keywords.
两种提取方式的结合,能够提取得到数量合适且较为准确的关键词,为后续根据提取得到的关键词进行通话关键内容的提取,做好了数据基础,有利于提取到通话中最为准确且有用的信息。The combination of the two extraction methods can extract the appropriate and more accurate keywords, and extract the key content of the call according to the extracted keywords, and make the data foundation, which is most accurate and useful for extracting to the call. Information.
基于上述第三实施例提出本发明通话关键内容提取方法第四实施例,在本实施例中,当提取的通话关键内容为空时,所述通话关键内容提取方法还包括:The fourth embodiment of the call key content extraction method of the present invention is proposed based on the foregoing third embodiment. In this embodiment, when the extracted call key content is empty, the call key content extraction method further includes:
从所述录音内容对应的文本内容中提取指定词性的词语,作为所述通话的通话关键内容。Extracting a word of the specified part of speech from the text content corresponding to the recorded content as a key content of the call of the call.
从与所述通话相关的信息中提取的关键词,或者是根据所述关键词确定机制中的海量词库中提取的关键词,有时会存在与所述通话的录音内容对应的文本内容不相关的情况,这个时候提取得到的通话关键内容可能为 空。为了使提供给用户的通话关键内容不为空,可从所述录音内容对应的文本内容中提取指定词性的词语,例如名词、数量词、动词等,作为所述通话的通话关键内容。The keyword extracted from the information related to the call, or the keyword extracted from the mass vocabulary in the keyword determining mechanism, sometimes the text content corresponding to the recorded content of the call is irrelevant In this case, the key content of the call extracted at this time may be air. In order to make the key content of the call provided to the user not empty, words specifying the part of speech, such as nouns, quantifiers, verbs, etc., may be extracted from the text content corresponding to the recorded content as the key content of the call.
本发明实施例提出的通话关键内容提取方法,在根据与所述通话相关的信息和所述关键词确定机制确定出的关键词,提取得到的通话关键内容为空时,通过从所述通话的录音内容对应的文本内容中提取指定词性的词语,从而保证提取得到的通话关键内容不为空,为用户提供一定的有用信息。The call key content extraction method according to the embodiment of the present invention, when the extracted key content is empty according to the information related to the call and the keyword determination mechanism, The words corresponding to the part of speech are extracted from the text content corresponding to the recorded content, thereby ensuring that the extracted key content of the call is not empty, and providing the user with certain useful information.
本发明实施例还提供一种通话关键内容提取装置,如图4所示,示出了本发明通话关键内容提取装置第一实施例的功能模块示意图,所述通话关键内容提取装置包括:The embodiment of the present invention further provides a call key content extracting apparatus. As shown in FIG. 4, a schematic diagram of a function module of the first embodiment of the call key content extracting apparatus of the present invention is shown. The call key content extracting apparatus includes:
计时模块100,设置为在检测到有通话建立时,统计所述通话的时长;The timing module 100 is configured to count the duration of the call when a call establishment is detected;
录音模块200,设置为在检测到有通话建立时,对所述通话进行录音;The recording module 200 is configured to record the call when a call establishment is detected;
所述通话关键内容提取装置可设置在任意的具有通话功能的终端上,例如,智能手机。当用户接到来电并接听电话,或是用户呼出电话且对方接听电话,则在用户所使用终端及对方所使用终端之间成功建立了通话连接。当用户所使用终端检测到有通话建立时,计时模块100可通过设置在终端上的计时器统计所述通话的实时时长,录音模块200通过设置在终端上的录音设备对所述通话进行录音,其中,对所述通话进行录音得到的录音内容,可先存储在缓冲区中。The call key content extraction device may be disposed on any terminal having a call function, such as a smart phone. When the user receives an incoming call and answers the call, or the user calls out and the other party answers the call, the call connection is successfully established between the terminal used by the user and the terminal used by the other party. When the terminal used by the user detects that a call is established, the timing module 100 can count the real-time duration of the call by using a timer set on the terminal, and the recording module 200 records the call by using a recording device set on the terminal. The recorded content obtained by recording the call may be stored in a buffer first.
确定模块300,设置为在所述通话的时长大于或等于预置时长时,根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词;The determining module 300 is configured to: when the duration of the call is greater than or equal to a preset duration, determine a group related to the call according to the acquired information related to the call and a preset keyword determining mechanism Key words;
可在所述通话结束时,通过比较统计得到的所述通话的总时长与所述预置时长的大小,在所述通话的总时长大于或等于所述预置时长时,进行后续操作;也可在所述通话进行的过程中,当统计得到的所述通话的实时时长大于或等于所述预置时长时,进行后续操作。 At the end of the call, the total duration of the call and the size of the preset duration obtained by comparing statistics may be performed after the total duration of the call is greater than or equal to the preset duration; During the process of the call, when the calculated real-time duration of the call is greater than or equal to the preset duration, a subsequent operation may be performed.
其中,所述预置时长为预先设置的一个时长值,例如,1分钟或30秒,可由用户自己设置,也可由终端设置为默认值;统计得到的每个通话的时长,可精确到分秒。通过比较每个通话的时长与所述预置时长的大小,可将一些不重要的通话过滤掉,不对其进行通话关键内容提取,且在这些通话结束通话时,将这些通话的录音在缓冲区的录音内容删除掉,以节约手机存储空间,减少后台系统的运行压力和耗电量。不重要的通话,一般为几秒、十几秒的电话,例如人们经常接到的一些快递电话、广告营销、骚扰电话、打错的陌生来电等,这些通话一般在接通后的几秒钟左右就会被挂断,基本没有保存通话关键内容的必要。如果事先不进行筛选过滤,而将所有通话的录音内容都进行缓存和提取,这样必然会给手机的运行速度和功耗带来很大的压力。因而,通过使用预置时长进行限制,能将这些不必要的通话提前过滤掉,减轻后台的运行压力和缓冲区的内存消耗,是非常有必要的。The preset duration is a preset duration value, for example, 1 minute or 30 seconds, which can be set by the user or set by the terminal as a default value; the duration of each call obtained by the statistics can be accurate to minutes and seconds. . By comparing the duration of each call with the preset duration, some unimportant calls can be filtered out, the call key content is not extracted, and the calls are recorded in the buffer when the calls are over. The recorded content is deleted to save mobile phone storage space and reduce the running pressure and power consumption of the background system. Unimportant calls, usually a few seconds, ten seconds of phone calls, such as some courier calls, advertising marketing, harassing calls, wrong calls, etc. that people often receive, these calls are usually a few seconds after being connected. The left and right will be hung up, and there is basically no need to save the key content of the call. If you do not perform filtering and filtering beforehand, all the recordings of all calls will be cached and extracted, which will inevitably put a lot of pressure on the running speed and power consumption of the mobile phone. Therefore, by using the preset duration to limit, it is necessary to filter out these unnecessary calls in advance, and to alleviate the running pressure in the background and the memory consumption of the buffer.
在进行后续操作时,终端的确定模块300可通过查询其安装的各种应用或存储文件中存储的、与所述通话相关的一些信息,从而得到与所述通话相关的历史记录,进而根据预置的关键词确定机制,从得到的历史记录中提取出与所述通话相关的一组关键词。其中,所述关键词确定机制用于规定,如何根据不同的应用或存储文件中与所述通话相关的信息,来提取与所述通话相关的关键词;所述关键词确定机制中预先设置有多种提取规则,规定了关键词的提取范围,还提供了关键词的海量词库。When the subsequent operations are performed, the determining module 300 of the terminal may obtain some history information related to the call by querying various applications or storage files installed in the terminal, thereby obtaining a history related to the call, and then according to the pre- The keyword determining mechanism extracts a set of keywords related to the call from the obtained history record. The keyword determining mechanism is configured to specify, according to information related to the call in different applications or stored files, keywords related to the call, where the keyword determining mechanism is preset A variety of extraction rules, which stipulate the extraction range of keywords, and also provide a massive vocabulary of keywords.
进一步地,参照图5,所述确定模块300包括:Further, referring to FIG. 5, the determining module 300 includes:
查找单元301,设置为从指定应用中查找与所述通话中的对方号码相关的历史记录;The searching unit 301 is configured to search for a history related to the counterpart number in the call from the specified application;
所述指定应用可以为终端上安装的任意应用,本实施例中,所述指定应用优选为各种终端均安装有的日历、闹钟、备忘录、记事本等常用工具性应用。在这些指定应用中,如果存储有与所述通话中的对方号码相关的事项或记录,则终端的查找单元301通过查询即可得到与所述通话中的对方号码相关的历史记录。例如,假设闹钟应用中存储了与所述通话中的对 方号码相关的一个提醒事项,如2016年3月15日上午9:00与王总洽谈合作事宜(其中,终端通讯录中存储有王总的电话号码,也即所述通话中的对方号码),记事本应用中存储有与王总相关的两条记录,如王总的公司主要生产通信设备、王总的公司地址是深圳市南山区科技园,则终端的查找单元301通过查询,可得到这两个应用中的3条历史记录。The specified application may be any application installed on the terminal. In this embodiment, the specified application is preferably a common tool application such as a calendar, an alarm clock, a memo, or a notepad installed on various terminals. In these designated applications, if an item or record related to the counterpart number in the call is stored, the search unit 301 of the terminal can obtain a history related to the counterpart number in the call by querying. For example, assume that the pair in the call is stored in the alarm application. A reminder related to the party number, such as 9:00 am on March 15, 2016, to discuss cooperation with Wang. (The terminal address book stores the telephone number of Wang, that is, the number of the other party in the call) The Notepad application stores two records related to Wang Zong. For example, the company's main production communication equipment, Wang's company address is Shenzhen Nanshan District Science and Technology Park, the terminal's search unit 301 can be obtained through inquiry. 3 historical records in both applications.
第一提取单元302,设置为按照历史记录的创建时间从大到小的顺序,根据所述关键词确定机制从一个或多个历史记录中提取关键词。The first extracting unit 302 is configured to extract keywords from one or more historical records according to the keyword determining mechanism in descending order of creation time of the history.
所述关键词确定机制中预先设置有第一阈值和第二阈值,所述第一阈值和所述第二阈值为两个固定值,其中所述第二阈值大于所述第一阈值,其取值可根据实际需求由用户或终端来设定,这两个阈值的设置是为了保证提取的关键词的个数不过于少也不过于多,避免后续提取的通话关键内容较少或繁多。The first threshold and the second threshold are preset in the keyword determining mechanism, where the first threshold and the second threshold are two fixed values, wherein the second threshold is greater than the first threshold, where The value can be set by the user or the terminal according to the actual demand. The two thresholds are set to ensure that the number of keywords to be extracted is not too small or too much, and the key content of the subsequent extraction is less or more.
假设闹钟应用中查到的历史记录的创建时间晚于(即大于)记事本中的两条历史记录的创建时间,则闹钟中的该条历史记录是当前最新的信息,此时,终端的第一提取单元302按照历史记录的创建时间从大到小的顺序,先从闹钟应用中的该条历史记录中提取关键词,假设根据所述关键词确定机制提取得到的关键词为“2016年3月15日”“上午9:00”“王总”“洽谈”“合作”,共5个关键词。如果所述第一阈值大于5,则说明根据闹钟应用中的历史记录提取的关键词个数较少,此时,第一提取单元302可从记事本的两条历史记录中创建时间较大的一条历史记录中继续提取,假设又提取出1个关键词,如果此时提取出的关键词的总个数满足大于或等于预置的第一阈值且小于或等于预置的第二阈值的条件,则无需再提取,此时得到的6个关键词即为要提取的一组关键词;如果所述第一阈值也大于6,则说明根据两条历史记录提取的关键词个数仍不够,此时,第一提取单元302需从第三条历史记录中继续提取关键词,直到满足提取出的关键词的总个数大于或等于所述第一阈值且小于或等于所述第二阈值的条件为止。Assuming that the history recorded in the alarm application is created later than (ie, greater than) the creation time of the two history records in the notebook, the history record in the alarm is the latest information, and at this time, the terminal An extracting unit 302 first extracts keywords from the history record in the alarm clock application in descending order of the creation time of the history record, and assumes that the keyword extracted according to the keyword determining mechanism is “2016 3 On the 15th of the month, "9:00 am" "Wang Zong", "Consultation" and "Cooperation", a total of 5 keywords. If the first threshold is greater than 5, it indicates that the number of keywords extracted according to the history in the alarm application is small. At this time, the first extracting unit 302 can create a larger time from the two historical records of the notebook. Continue to extract from a history record, assuming that another keyword is extracted, if the total number of keywords extracted at this time satisfies a condition that is greater than or equal to the preset first threshold and less than or equal to the preset second threshold. , the need to extract again, the six keywords obtained at this time is a set of keywords to be extracted; if the first threshold is also greater than 6, it means that the number of keywords extracted according to the two historical records is still insufficient. At this time, the first extracting unit 302 needs to continue to extract keywords from the third history record until the total number of keywords that are extracted is greater than or equal to the first threshold and less than or equal to the second threshold. The conditions are up.
进一步地,所述确定模块300还包括:Further, the determining module 300 further includes:
第三提取单元304,设置为当提取出的关键词的总个数小于预置的第 一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;The third extracting unit 304 is configured to: when the total number of extracted keywords is less than the preset number When a threshold is used, according to the massive vocabulary in the keyword determining mechanism, the keyword is continuously extracted, so that the total number of the extracted set of keywords is greater than or equal to the preset first threshold and less than or equal to the preset. Second threshold
筛选单元305,设置为当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。The screening unit 305 is configured to: when the total number of extracted keywords is greater than a preset second threshold, filter keywords from the extracted keywords according to the keyword determining mechanism, so as to obtain a selected group The total number of keywords is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
如果从已有的三条历史记录中提取的关键词的总个数仍小于所述第一阈值,则第三提取单元304可根据所述关键词确定机制,从其中的关键词的海量词库中确定出适量个数的关键词作为补充;如果提取的关键词的总个数大于所述第二阈值,则筛选单元305根据所述关键词确定机制,去掉适量个数的关键词即可。需要说明的是,提取得到的一组关键词中,各个关键词均不相同。If the total number of keywords extracted from the existing three history records is still less than the first threshold, the third extracting unit 304 may determine the mechanism according to the keyword, from the massive vocabulary of the keywords therein. The appropriate number of keywords is determined as a supplement; if the total number of extracted keywords is greater than the second threshold, the screening unit 305 may remove an appropriate number of keywords according to the keyword determining mechanism. It should be noted that among the extracted keywords, each keyword is different.
第一提取模块400,设置为根据确定出的一组关键词,从所述通话的录音内容中提取通话关键内容。The first extraction module 400 is configured to extract the call key content from the recorded content of the call according to the determined set of keywords.
在提取得到一组关键词后,终端的第一提取模块400将所述通话的录音内容全部或分段逐步转为文本内容,然后通过将得到的一组关键词与所述文本内容进行模糊匹配或含义相近匹配,从而提取得到所述通话的通话关键内容。After extracting a set of keywords, the first extraction module 400 of the terminal gradually converts all or part of the recorded content of the call into text content, and then performs fuzzy matching on the obtained set of keywords with the text content. Or the meanings are similarly matched, so that the key content of the call of the call is extracted.
在所述通话结束通话时,可将存储在缓冲区的所述通话的录音内容存储到终端的指定存储区域,以便用户事后调取所述通话的通话录音。When the call ends the call, the recorded content of the call stored in the buffer may be stored in a designated storage area of the terminal, so that the user can retrieve the call recording of the call afterwards.
本发明实施例提出的通话关键内容提取装置,在通话建立时,统计所述通话的时长并对所述通话进行录音,且在所述通话的时长大于或等于预置时长时,通过获取得到的与所述通话相关的信息,以及预置的关键词确定机制,确定出一组关键词,并根据得到的一组关键词,从所述通话的录音内容中提取通话关键内容,实现了对通话内容中的重要信息的自动提取,从而得到所述通话的通话关键内容,便于后续基于提取得到的通话关键内容为用户提供各种用途的便捷服务。 The call key content extracting apparatus of the embodiment of the present invention collects the duration of the call and records the call when the call is established, and obtains the obtained time when the duration of the call is greater than or equal to the preset duration. Information related to the call, and a preset keyword determining mechanism, determining a set of keywords, and extracting key content of the call from the recorded content of the call according to the obtained set of keywords, and realizing the call The automatic extraction of the important information in the content, thereby obtaining the key content of the call of the call, and facilitating the subsequent convenient service for the user to provide various uses based on the extracted key content of the call.
基于上述通话关键内容提取装置第一实施例提出本发明通话关键内容提取装置第二实施例,在本实施例中,参照图6,在提取出通话关键内容后,所述通话关键内容提取装置还包括:The second embodiment of the call key content extracting apparatus of the present invention is proposed based on the first embodiment of the call key content extracting apparatus. In this embodiment, referring to FIG. 6, after the call key content is extracted, the call key content extracting apparatus further include:
存储模块500,设置为保存提取出的所述通话关键内容。The storage module 500 is configured to save the extracted call key content.
在提取得到所述通话的通话关键内容后,终端的存储模块500可将所述通话关键内容保存在终端的指定存储位置或指定应用中,以便用户随时查看。可以理解,终端的存储模块500还可将得到的所述通话关键内容转为语音格式的文件进行存储,在用户查看所述通话的通话关键内容时,通过语音播报的方式将所述通话关键内容传递给用户。After the call key content of the call is extracted, the storage module 500 of the terminal may save the call key content in a specified storage location or a designated application of the terminal, so that the user can view it at any time. It can be understood that the storage module 500 of the terminal can further convert the obtained call key content into a file in a voice format, and when the user views the key content of the call, the key content of the call is broadcasted by means of voice broadcast. Passed to the user.
在提取得到所述通话的通话关键内容后,存储所述通话关键内容,以便用户随时查看,使得用户在通话时能够专注地接听电话,而无需一边接听电话一边记录关键内容,节省了用户的操作和消耗的精力,也为用户获得通话关键内容提供了便利。After extracting the call key content of the call, the call key content is stored, so that the user can view at any time, so that the user can receive the call intently during the call without recording the key content while answering the phone, thereby saving the user's operation. And the energy consumed, it also facilitates users to get key content of the call.
参照图7,所述存储模块500包括:Referring to FIG. 7, the storage module 500 includes:
第一存储单元501,设置为在所述通话关键内容包含有日期和/或时间时,根据所述通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;The first storage unit 501 is configured to establish a corresponding reminding item according to the call key content when the call key content includes a date and/or a time, so as to issue a reminder to the user at a specified time;
在保存所述通话的通话关键内容时,如果所述通话关键内容中包含日期和/或时间,则终端的第一存储单元501可使用具有提醒功能的应用(例如,日历或闹钟)建立提醒事项,然后将所述通话关键内容按照提醒事项的规定添加到该提醒事项中,例如,将通话关键内容“2016年5月1日、晚上6点、小王、肯德基、吃饭”中的日期“2016年5月1日”,设置到指定应用日历的新建提醒事项的日期中,将该通话关键内容中的“晚上6点”设置到该提醒事项的时间中,将该通话关键内容的“小王、肯德基、吃饭”,设置到该提醒事项的标题或备注中。When saving the call key content of the call, if the call key content includes a date and/or time, the first storage unit 501 of the terminal may establish a reminder using an application (eg, a calendar or an alarm) having a remind function. And then adding the key content of the call to the reminder according to the provisions of the reminder item, for example, the date of the call key content "May 1, 2016, 6 pm, Xiao Wang, KFC, eating" "May 1st of the year", set the date to the new reminder of the specified application calendar, set "6 o'clock" in the key content of the call to the time of the reminder, and the "key king" of the key content of the call , KFC, dinner", set to the title or remarks of the reminder.
提醒事项自动设置完成后,终端可将设置页面提供给用户,由用户根据个人需求进行添加或修改设置,用户还可设置提前多久进行提醒等。用 户设置完成并保存后,终端将根据提起多久进行提醒的设置,在设置的日期和时间对应的时刻到来之前,提醒用户该事项。其中,在设置有提前多久提醒时,所述指定时间为相对于设置的日期和时间提前发出提醒时的时间,在未设置有提前多久提醒时,所述指定时间即为设置的日期和时间对应的时刻。After the automatic setting of the reminder is completed, the terminal can provide the setting page to the user, and the user can add or modify the setting according to individual needs, and the user can also set how long to advance the reminder. use After the user setting is completed and saved, the terminal will remind the user of the item according to the setting of how long to remind the reminder before the time corresponding to the set date and time. Wherein, when the reminder is set in advance, the designated time is a time when the reminder is issued in advance with respect to the set date and time, and when the reminder is not set in advance, the specified time is the set date and time corresponding to the set time Moment.
第二存储单元502,设置为在所述通话关键内容未包含有日期和/或时间时,将所述通话关键内容存储到文本类型的应用中,以供用户随时查看所述通话的通话关键内容。The second storage unit 502 is configured to store the call key content into a text type application when the call key content does not include a date and/or time, so that the user can view the call key content of the call at any time. .
如果所述通话关键内容中未包含日期和/或时间,则终端的第二存储单元502可使用文本类型的应用存储所述通话关键内容,例如,可将所述通话关键内容存储在备忘录或记事本中,以便用户随时查看。If the date and/or time is not included in the call key content, the second storage unit 502 of the terminal may store the call key content using a text type application, for example, the call key content may be stored in a memo or a note. This is for users to view at any time.
本发明实施例提出的通话关键内容提取装置,将提取得到的通话关键内容根据是否包含有日期和/或时间进行区分存储,以将包含有日期和/或时间的通话关键内容以提醒事项的形式存储,便于提醒用户相应事项,避免遗忘重要事情的处理,以及将未包含有日期和/或时间的通话关键内容以文本形式存储在文本类型的应用中,便于用户随时查看,省去了需要记忆的麻烦,使得用户在通话过程中更为省心省力。The call key content extracting device of the embodiment of the present invention stores the extracted call key content separately according to whether the date and/or time is included, so as to include the date and/or time of the call key content in the form of a reminder item. Storage, easy to remind users of the corresponding matters, to avoid the handling of important things, and to store the key content of the call without date and / or time in the text type of application, so that users can view at any time, eliminating the need to remember The trouble makes the user more worry-free during the call.
基于上述通话关键内容提取装置第二实施例提出本发明通话关键内容提取装置第三实施例,在本实施例中,参照图8,所述确定模块300包括:The third embodiment of the call key content extracting apparatus of the present invention is proposed based on the second embodiment of the call key content extracting apparatus. In this embodiment, referring to FIG. 8, the determining module 300 includes:
第二提取单元303,设置为根据所述通话中的对方号码对应的通讯录联系人详情,以及所述关键词确定机制,展开关键词智能联想,并提取关键词。The second extracting unit 303 is configured to expand keyword keyword association and extract keywords according to the address book contact details corresponding to the counterpart number in the call and the keyword determining mechanism.
终端根据所述通话的对方号码,即可获取得到对方号码在通讯录中的联系人详情,在所述联系人详情中可能存储有一些重要的信息,这些信息即可被提取作为关键词。The terminal can obtain the contact details of the other party's number in the address book according to the other party's number of the call, and some important information may be stored in the contact details, and the information may be extracted as a keyword.
进一步地,所述确定模块300还包括: Further, the determining module 300 further includes:
第三提取单元304,设置为当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;The third extracting unit 304 is configured to: when the total number of extracted keywords is less than a preset first threshold, continue to extract keywords according to the massive vocabulary in the keyword determining mechanism, so as to obtain the extracted The total number of keywords in a group is greater than or equal to a preset first threshold and less than or equal to a preset second threshold;
筛选单元305,设置为当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。The screening unit 305 is configured to: when the total number of extracted keywords is greater than a preset second threshold, filter keywords from the extracted keywords according to the keyword determining mechanism, so as to obtain a selected group The total number of keywords is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
假设根据所述通话的对方号码获得的联系人详情为,“姓名:小李,公司:链家房屋中介,职业:房屋中介,备注:学位房、小学”,则第二提取单元303可将“小李”“链家”“房屋中介”“学位房”“小学”作为关键词并展开智能联想,从而得到更多相关的关键词。如果得到的关键词的总个数小于所述第一阈值,则第三提取单元304可从所述关键词确定机制的关键词的海量词库中选取适量个数的相关关键词,从而使得到的一组关键词的总个数大于或等于所述第一阈值且小于或等于所述第二阈值。如果得到的关键词的总个数大于所述第二阈值,则筛选单元305根据所述关键词确定机制,去掉适量个数的关键词即可。需要说明的是,提取得到的一组关键词中,各个关键词均不相同。Assume that the contact details obtained according to the counterpart number of the call are, "Name: Xiao Li, company: chain home agency, occupation: housing agency, remarks: degree room, primary school", then the second extraction unit 303 can be "small" Li "chain home", "housing agency", "degree room" and "primary school" as keywords and launch intelligent association, so as to get more relevant keywords. If the total number of the obtained keywords is less than the first threshold, the third extracting unit 304 may select an appropriate number of related keywords from the mass vocabulary of the keyword of the keyword determining mechanism, thereby The total number of sets of keywords is greater than or equal to the first threshold and less than or equal to the second threshold. If the total number of keywords obtained is greater than the second threshold, the filtering unit 305 may remove an appropriate number of keywords according to the keyword determining mechanism. It should be noted that among the extracted keywords, each keyword is different.
本发明实施例提出的通话关键内容提取装置,从与所述通话中的对方号码对应的通讯录联系人详情中提取关键词,通过该方式能够获得较为精确的关键词,有利于从所述通话的录音内容中提取较为准确的通话关键内容。The call key content extracting device of the embodiment of the present invention extracts a keyword from the address book contact details corresponding to the counterpart number in the call, and can obtain a more accurate keyword by using the method, which is beneficial to the call from the call. The recorded content extracts more accurate call key content.
可以理解,还存在这样的两个通话关键内容提取装置实施例:(1)、在所述确定模块300中,先采用上述通话关键内容提取装置第一实施例的提取方式提取关键词,在提取的关键词总个数小于所述第一阈值时,再采用上述通话关键内容提取装置第三实施例的提取方式提取关键词,如果两种提取方式下提取得到的关键词的总个数满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则提取出的所有关键词即为要得到的 一组关键词;如果两种提取方式下提取得到的关键词的总个数不满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则再根据所述关键词确定机制补充或筛选适量个数的关键词。It is to be understood that there are also two embodiments of the call key content extracting device. (1) In the determining module 300, the keyword is extracted by using the extraction method of the first embodiment of the call key content extracting device. If the total number of keywords is less than the first threshold, the keyword is extracted by using the extraction method of the third embodiment of the call key content extraction device, and if the total number of keywords extracted by the two extraction modes is greater than Or a condition equal to the first threshold and less than or equal to the second threshold, then all keywords extracted are obtained a set of keywords; if the total number of keywords extracted in the two extraction modes does not satisfy the condition that is greater than or equal to the first threshold and less than or equal to the second threshold, then determining according to the keyword The mechanism supplements or screens the appropriate number of keywords.
(2)、在所述确定模块300中,先采用上述通话关键内容提取装置第三实施例的提取方式提取关键词,在提取的关键词总个数小于所述第一阈值时,再采用上述通话关键内容提取装置第一实施例的提取方式提取关键词,如果两种提取方式下提取得到的关键词的总个数满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则提取出的所有关键词即为要得到的一组关键词;如果两种提取方式下提取得到的关键词的总个数不满足大于或等于所述第一阈值且小于或等于所述第二阈值的条件,则再根据所述关键词确定机制补充或筛选适量个数的关键词。(2) In the determining module 300, the keyword is extracted by using the extraction method of the third embodiment of the call key content extraction device, and when the total number of extracted keywords is less than the first threshold, the above-mentioned threshold is used. The extraction method of the first embodiment of the call key content extraction device extracts keywords, if the total number of keywords extracted in the two extraction modes meets the first threshold and is less than or equal to the second threshold The condition, the all keywords extracted are the set of keywords to be obtained; if the total number of keywords extracted in the two extraction modes does not satisfy the first threshold and is less than or equal to the said The condition of the second threshold is then supplemented or screened by an appropriate amount of keywords according to the keyword determination mechanism.
两种提取方式的结合,能够提取得到数量合适且较为准确的关键词,为后续根据提取得到的关键词进行通话关键内容的提取,做好了数据基础,有利于提取到通话中最为准确且有用的信息。The combination of the two extraction methods can extract the appropriate and more accurate keywords, and extract the key content of the call according to the extracted keywords, and make the data foundation, which is most accurate and useful for extracting to the call. Information.
基于上述通话关键内容提取装置第三实施例提出本发明通话关键内容提取装置第四实施例,在本实施例中,参照图9,当提取的通话关键内容为空时,所述通话关键内容提取方法还包括:The fourth embodiment of the call key content extracting apparatus of the present invention is proposed based on the third embodiment of the call key content extracting apparatus. In this embodiment, referring to FIG. 9, when the extracted call key content is empty, the call key content is extracted. The method also includes:
第二提取模块600,设置为从所述录音内容对应的文本内容中提取指定词性的词语,作为所述通话的通话关键内容。The second extraction module 600 is configured to extract a word of the specified part of speech from the text content corresponding to the recorded content as the key content of the call.
从与所述通话相关的信息中提取的关键词,或者是根据所述关键词确定机制中的海量词库中提取的关键词,有时会存在与所述通话的录音内容对应的文本内容不相关的情况,这个时候提取得到的通话关键内容可能为空。为了使提供给用户的通话关键内容不为空,第二提取模块600可从所述录音内容对应的文本内容中提取指定词性的词语,例如名词、数量词、动词等,作为所述通话的通话关键内容。The keyword extracted from the information related to the call, or the keyword extracted from the mass vocabulary in the keyword determining mechanism, sometimes the text content corresponding to the recorded content of the call is irrelevant In this case, the key content of the call extracted at this time may be empty. In order to make the call key content provided to the user not empty, the second extraction module 600 may extract words specifying the part of speech, such as nouns, quantifiers, verbs, etc., from the text content corresponding to the recorded content, as the key of the call of the call. content.
本发明实施例提出的通话关键内容提取装置,在根据与所述通话相关的信息和所述关键词确定机制确定出的关键词,提取得到的通话关键内容 为空时,通过从所述通话的录音内容对应的文本内容中提取指定词性的词语,从而保证提取得到的通话关键内容不为空,为用户提供一定的有用信息。The call key content extracting apparatus according to the embodiment of the present invention extracts the key content of the call according to the keyword determined by the information related to the call and the keyword determining mechanism. When it is empty, the words of the specified part of speech are extracted from the text content corresponding to the recorded content of the call, thereby ensuring that the extracted key content of the call is not empty, and providing the user with certain useful information.
本发明的实施例还提供了一种存储介质。可选地,在本实施例中,上述存储介质可以被设置为存储用于执行以下步骤的程序代码:Embodiments of the present invention also provide a storage medium. Optionally, in the embodiment, the foregoing storage medium may be configured to store program code for performing the following steps:
S1,在检测到有通话建立时,统计通话的时长,并对通话进行录音;S1, when detecting the establishment of a call, counting the duration of the call, and recording the call;
S2,在通话的时长大于或等于预置时长时,根据获取的与通话相关的信息,以及预置的关键词确定机制,确定出与通话相关的一组关键词;S2, when the duration of the call is greater than or equal to the preset duration, determining a set of keywords related to the call according to the acquired information related to the call and the preset keyword determining mechanism;
S3,根据确定出的一组关键词,从通话的录音内容中提取通话关键内容。S3, according to the determined set of keywords, extract the key content of the call from the recorded content of the call.
可选地,存储介质还被设置为存储用于执行以下步骤的程序代码:S1,在提取出通话关键内容后,保存提取出的通话关键内容;其中,保存提取出的通话关键内容包括:在通话关键内容包含有日期和/或时间时,根据通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;或者,在通话关键内容未包含有日期和/或时间时,将通话关键内容存储到文本类型的应用中,以供用户随时查看通话的通话关键内容。Optionally, the storage medium is further configured to store program code for performing the following steps: S1, after extracting the call key content, saving the extracted call key content; wherein, saving the extracted call key content includes: When the key content of the call includes date and/or time, a corresponding reminder is established according to the key content of the call to send a reminder to the user at a specified time; or, when the key content of the call does not include a date and/or time, the call is made The key content is stored in a text-type application for users to view the key content of the call at any time.
可选地,在本实施例中,上述存储介质可以包括但不限于:U盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。Optionally, in this embodiment, the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory. A variety of media that can store program code, such as a disc or a disc.
以上仅为本发明的优选实施例,并非因此限制本发明的专利范围,凡是利用本发明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,均同理包括在本发明的专利保护范围内。The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the present invention and the drawings are directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.
工业实用性Industrial applicability
在本发明实施例中,在通话建立时,统计所述通话的时长并对所述通 话进行录音,且在所述通话的时长大于或等于预置时长时,通过获取得到的与所述通话相关的信息,以及预置的关键词确定机制,确定出一组关键词,并根据得到的一组关键词,从所述通话的录音内容中提取通话关键内容,实现了对通话内容中的重要信息的自动提取,从而得到所述通话的通话关键内容,便于后续基于提取得到的通话关键内容为用户提供各种用途的便捷服务。 In the embodiment of the present invention, when the call is established, the duration of the call is counted and the Recording, and when the duration of the call is greater than or equal to the preset duration, the obtained information related to the call and the preset keyword determining mechanism determine a set of keywords, and according to the obtained a set of keywords, extracting key content of the call from the recorded content of the call, realizing automatic extraction of important information in the call content, thereby obtaining the key content of the call, facilitating subsequent call key based on the extraction The content provides users with convenient services for various purposes.

Claims (12)

  1. 一种通话关键内容提取方法,所述通话关键内容提取方法包括:A call key content extraction method, the call key content extraction method includes:
    在检测到有通话建立时,统计所述通话的时长,并对所述通话进行录音;When it is detected that a call is established, the duration of the call is counted, and the call is recorded;
    在所述通话的时长大于或等于预置时长时,根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词;When the duration of the call is greater than or equal to the preset duration, determining a set of keywords related to the call according to the acquired information related to the call and a preset keyword determining mechanism;
    根据确定出的一组关键词,从所述通话的录音内容中提取通话关键内容。According to the determined set of keywords, the key content of the call is extracted from the recorded content of the call.
  2. 如权利要求1所述的通话关键内容提取方法,其中,在提取出通话关键内容后,所述通话关键内容提取方法还包括:The call key content extraction method of claim 1 , wherein after the call key content is extracted, the call key content extraction method further comprises:
    保存提取出的所述通话关键内容;Saving the extracted call key content;
    其中,所述保存提取出的所述通话关键内容包括:The saving the extracted call key content includes:
    在所述通话关键内容包含有日期和/或时间时,根据所述通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;或者,When the call key content includes a date and/or a time, a corresponding reminder item is established according to the call key content to issue a reminder to the user at a specified time; or
    在所述通话关键内容未包含有日期和/或时间时,将所述通话关键内容存储到文本类型的应用中,以供用户随时查看所述通话的通话关键内容。When the call key content does not include a date and/or time, the call key content is stored in a text type application for the user to view the call key content of the call at any time.
  3. 如权利要求1所述的通话关键内容提取方法,其中,所述根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词包括:The call key content extraction method according to claim 1, wherein said determining, according to the acquired information related to the call, and a preset keyword determining mechanism, a set of keywords related to the call includes :
    从指定应用中查找与所述通话中的对方号码相关的历史记录;Finding a history related to the counterpart number in the call from the specified application;
    按照历史记录的创建时间从大到小的顺序,根据所述关键词确定机制从一个或多个历史记录中提取关键词。The keywords are extracted from one or more histories according to the keyword determination mechanism in descending order of creation time of the history.
  4. 如权利要求1所述的通话关键内容提取方法,其中,所述根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词包括: The call key content extraction method according to claim 1, wherein said determining, according to the acquired information related to the call, and a preset keyword determining mechanism, a set of keywords related to the call includes :
    根据所述通话中的对方号码对应的通讯录联系人详情,以及所述关键词确定机制,展开关键词智能联想,并提取关键词。And according to the address book contact details corresponding to the counterpart number in the call, and the keyword determining mechanism, the keyword intelligent association is expanded, and the keyword is extracted.
  5. 如权利要求3或4所述的通话关键内容提取方法,其中,所述根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词还包括:The call key content extraction method according to claim 3 or 4, wherein the determining a set of keys related to the call according to the acquired information related to the call and a preset keyword determining mechanism The words also include:
    当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值;When the total number of extracted keywords is less than the preset first threshold, according to the massive vocabulary in the keyword determining mechanism, the keywords are continuously extracted, so that the total number of extracted keywords is obtained. Greater than or equal to the preset first threshold and less than or equal to the preset second threshold;
    当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。When the total number of extracted keywords is greater than a preset second threshold, the keywords are selected according to the keyword determining mechanism to filter keywords from the extracted keywords, so as to obtain a total number of selected keywords. It is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  6. 如权利要求1所述的通话关键内容提取方法,其中,当提取的通话关键内容为空时,所述通话关键内容提取方法还包括:The call key content extraction method of claim 1 , wherein when the extracted call key content is empty, the call key content extraction method further comprises:
    从所述录音内容对应的文本内容中提取指定词性的词语,作为所述通话的通话关键内容。Extracting a word of the specified part of speech from the text content corresponding to the recorded content as a key content of the call of the call.
  7. 一种通话关键内容提取装置,所述通话关键内容提取装置包括:A call key content extracting apparatus, the call key content extracting apparatus includes:
    计时模块,设置为在检测到有通话建立时,统计所述通话的时长;a timing module, configured to count the duration of the call when a call establishment is detected;
    录音模块,设置为在检测到有通话建立时,对所述通话进行录音;a recording module, configured to record the call when a call establishment is detected;
    确定模块,设置为在所述通话的时长大于或等于预置时长时,根据获取的与所述通话相关的信息,以及预置的关键词确定机制,确定出与所述通话相关的一组关键词;Determining, when the duration of the call is greater than or equal to a preset duration, determining a set of keys related to the call according to the acquired information related to the call and a preset keyword determining mechanism word;
    第一提取模块,设置为根据确定出的一组关键词,从所述通话的录音内容中提取通话关键内容。The first extraction module is configured to extract the call key content from the recorded content of the call according to the determined set of keywords.
  8. 如权利要求7所述的通话关键内容提取装置,其中,在提取出通 话关键内容后,所述通话关键内容提取装置还包括:The call key content extracting apparatus according to claim 7, wherein the extracting pass is performed After the key content, the call key content extracting device further includes:
    存储模块,设置为保存提取出的所述通话关键内容;a storage module, configured to save the extracted key content of the call;
    其中,所述存储模块包括:The storage module includes:
    第一存储单元,设置为在所述通话关键内容包含有日期和/或时间时,根据所述通话关键内容建立相应的提醒事项,以在指定时间向用户发出事项提醒;a first storage unit, configured to establish a corresponding reminding item according to the key content of the call when the call key content includes a date and/or a time, to issue a reminder to the user at a specified time;
    第二存储单元,设置为在所述通话关键内容未包含有日期和/或时间时,将所述通话关键内容存储到文本类型的应用中,以供用户随时查看所述通话的通话关键内容。The second storage unit is configured to store the call key content into a text type application when the call key content does not include a date and/or time, so that the user can view the call key content of the call at any time.
  9. 如权利要求7所述的通话关键内容提取装置,其中,所述确定模块包括:The call key content extracting apparatus according to claim 7, wherein the determining module comprises:
    查找单元,设置为从指定应用中查找与所述通话中的对方号码相关的历史记录;a search unit configured to search for a history related to the counterpart number in the call from the specified application;
    第一提取单元,设置为按照历史记录的创建时间从大到小的顺序,根据所述关键词确定机制从一个或多个历史记录中提取关键词。The first extracting unit is configured to extract keywords from the one or more history records according to the keyword determining mechanism in an order of the history creation time from large to small.
  10. 如权利要求7所述的通话关键内容提取装置,其中,所述确定模块包括:The call key content extracting apparatus according to claim 7, wherein the determining module comprises:
    第二提取单元,设置为根据所述通话中的对方号码对应的通讯录联系人详情,以及所述关键词确定机制,展开关键词智能联想,并提取关键词。The second extracting unit is configured to expand the keyword intelligent association according to the address book contact details corresponding to the counterpart number in the call, and the keyword determining mechanism, and extract keywords.
  11. 如权利要求9或10所述的通话关键内容提取装置,其中,所述确定模块还包括:The call key content extracting apparatus according to claim 9 or 10, wherein the determining module further comprises:
    第三提取单元,设置为当提取出的关键词的总个数小于预置的第一阈值时,根据所述关键词确定机制中的海量词库,继续提取关键词,以使提取得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值; a third extracting unit, configured to: when the total number of extracted keywords is less than a preset first threshold, continue to extract keywords according to the massive vocabulary in the keyword determining mechanism, so that the extracted one is obtained The total number of group keywords is greater than or equal to a preset first threshold and less than or equal to a preset second threshold;
    筛选单元,设置为当提取出的关键词的总个数大于预置的第二阈值时,根据所述关键词确定机制从提取出的关键词中筛选关键词,以使筛选得到的一组关键词的总个数大于或等于预置的第一阈值且小于或等于预置的第二阈值。a screening unit, configured to: when the total number of extracted keywords is greater than a preset second threshold, select a keyword from the extracted keywords according to the keyword determining mechanism, so as to obtain a set of key selected by the screening The total number of words is greater than or equal to the preset first threshold and less than or equal to the preset second threshold.
  12. 如权利要求7所述的通话关键内容提取装置,其中,当提取的通话关键内容为空时,所述通话关键内容提取装置还包括:The call key content extracting apparatus according to claim 7, wherein when the extracted call key content is empty, the call key content extracting apparatus further comprises:
    第二提取模块,设置为从所述录音内容对应的文本内容中提取指定词性的词语,作为所述通话的通话关键内容。 The second extraction module is configured to extract a word of the specified part of speech from the text content corresponding to the recorded content as a key content of the call of the call.
PCT/CN2016/102041 2016-06-28 2016-10-13 Method and apparatus for extracting key content of call WO2018000659A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610486894.9A CN107547728B (en) 2016-06-28 2016-06-28 Call key content extraction method and device
CN201610486894.9 2016-06-28

Publications (1)

Publication Number Publication Date
WO2018000659A1 true WO2018000659A1 (en) 2018-01-04

Family

ID=60785083

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/102041 WO2018000659A1 (en) 2016-06-28 2016-10-13 Method and apparatus for extracting key content of call

Country Status (2)

Country Link
CN (1) CN107547728B (en)
WO (1) WO2018000659A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111918293A (en) * 2020-07-29 2020-11-10 北京宏达隆和科技有限公司 Multi-dimensional association detection method for communication information fraud
CN112291423A (en) * 2020-10-23 2021-01-29 腾讯科技(深圳)有限公司 Intelligent response processing method and device for communication call, electronic equipment and storage medium

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109040444B (en) * 2018-07-27 2020-08-14 维沃移动通信有限公司 Call recording method, terminal and computer readable storage medium
CN111126553B (en) * 2019-12-25 2024-04-30 平安银行股份有限公司 Intelligent robot interview method, equipment, storage medium and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7953751B2 (en) * 2005-03-24 2011-05-31 The Mitre Corporation System and method for audio hot spotting
CN103249034A (en) * 2013-05-21 2013-08-14 北京小米科技有限责任公司 Method and device for acquiring contact information
CN103607512A (en) * 2013-11-25 2014-02-26 深圳市金立通信设备有限公司 Memo reminding method and terminal

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103871401B (en) * 2012-12-10 2016-12-28 联想(北京)有限公司 A kind of method of speech recognition and electronic equipment
CN104394271A (en) * 2014-11-21 2015-03-04 无锡科思电子科技有限公司 Method for generating digital voice file of special contact person based on keywords
CN105516472A (en) * 2015-11-30 2016-04-20 联想(北京)有限公司 Information processing method and electronic apparatus

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7953751B2 (en) * 2005-03-24 2011-05-31 The Mitre Corporation System and method for audio hot spotting
CN103249034A (en) * 2013-05-21 2013-08-14 北京小米科技有限责任公司 Method and device for acquiring contact information
CN103607512A (en) * 2013-11-25 2014-02-26 深圳市金立通信设备有限公司 Memo reminding method and terminal

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111918293A (en) * 2020-07-29 2020-11-10 北京宏达隆和科技有限公司 Multi-dimensional association detection method for communication information fraud
CN112291423A (en) * 2020-10-23 2021-01-29 腾讯科技(深圳)有限公司 Intelligent response processing method and device for communication call, electronic equipment and storage medium
CN112291423B (en) * 2020-10-23 2023-09-26 腾讯科技(深圳)有限公司 Communication call intelligent response processing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN107547728B (en) 2020-09-22
CN107547728A (en) 2018-01-05

Similar Documents

Publication Publication Date Title
WO2018000659A1 (en) Method and apparatus for extracting key content of call
CN103929539B (en) A kind of mobile terminal notepad processing method based on speech recognition and system
US7684552B2 (en) Phone batch calling task management system
CN103577965B (en) A kind of affairs prompt method and apparatus
CN103000175A (en) Voice recognition method and mobile terminal
CN101931701A (en) Method, system and mobile terminal for prompting contact information in communication process
CN102316227B (en) Data processing method for voice call process
CN106302933B (en) Voice information processing method and terminal
CN104125340A (en) Generating managing method and system for call sound recording files
CN104038630A (en) Speech processing method and device
CN103888581A (en) Communication terminal and method for recording communication information thereof
CN103856602A (en) System and method for duplicating call
CN102542436A (en) Method, system and mobile terminal for reminding user of needing to communicate with contact persons
CN104394271A (en) Method for generating digital voice file of special contact person based on keywords
CN104796546A (en) Bluetooth communication processing method and Bluetooth communication processing system based on mobile terminals
CN103227870A (en) Method of saving contact information
CN102143264A (en) Method for storing memo in call and mobile terminal
CN106327151A (en) Note recording method and system based on voice recognition
WO2012062079A1 (en) Method and device for processing information
US20080270761A1 (en) Techniques to generate event contexts for recurring events
CN106686182A (en) Method and device for grouping contact persons
WO2011150881A2 (en) Contact card management method and device used for mobile terminal
CN101257691A (en) Mobile terminal with voice prompting function and voice prompting method
CN108512984A (en) Information displaying method and device, information-pushing method, terminal and storage medium
CN103258564A (en) Method for automatic recording of memo events

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: 16907055

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16907055

Country of ref document: EP

Kind code of ref document: A1