CN109510904B - Method and system for detecting call center outbound record - Google Patents
Method and system for detecting call center outbound record Download PDFInfo
- Publication number
- CN109510904B CN109510904B CN201811591872.4A CN201811591872A CN109510904B CN 109510904 B CN109510904 B CN 109510904B CN 201811591872 A CN201811591872 A CN 201811591872A CN 109510904 B CN109510904 B CN 109510904B
- Authority
- CN
- China
- Prior art keywords
- keyword
- target user
- optimal
- text
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5175—Call or contact centers supervision arrangements
Landscapes
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for detecting an outbound record of a call center, wherein the detection method comprises the following steps: s1, constructing a keyword library, wherein the keyword library stores a plurality of keywords corresponding to a plurality of users; s2, obtaining the call-out record of a target user, and converting the call-out record into a text to be detected; s3, acquiring at least one target keyword corresponding to the target user from the keyword library, and extracting the target keyword with the longest word length as an optimal keyword; s4, detecting whether the text to be detected contains the optimal keyword, if so, determining that the telephone of the target user is matched with the target user. According to the method, the text content of the outbound record is subjected to semantic analysis, the matched longest word keyword is preferentially identified, the optimal result is accurately matched, and the efficiency and accuracy of text information verification are improved.
Description
Technical Field
The invention belongs to the field of voice detection, and particularly relates to a method and a system for detecting an outbound call record of a call center.
Background
With the rapid development of internet platforms, more and more B-end (Business end or enterprise end) merchants access each large internet platform, and the change of the telephone numbers of the merchants can cause the information sources not to match with the actual mastery conditions of the platform, which causes inconvenience to the platform.
Disclosure of Invention
The invention aims to overcome the defect of low keyword matching precision in voice call verification in the prior art and provides a method and a system for detecting call center outbound record.
The invention solves the technical problems through the following technical scheme:
a detection method for call center outbound recording comprises the following steps:
s1, constructing a keyword library, wherein the keyword library stores a plurality of keywords corresponding to a plurality of users;
s2, obtaining the call-out record of a target user, and converting the call-out record into a text to be detected;
s3, acquiring at least one target keyword corresponding to the target user from the keyword library, and extracting the target keyword with the longest word length as an optimal keyword;
s4, detecting whether the text to be detected contains the optimal keyword, if so, determining that the telephone of the target user is matched with the target user.
Preferably, step S4 specifically includes:
s41, acquiring the word length of the optimal keyword of the target user;
s42, taking the word length of the optimal keyword as an intercepting length, and intercepting the text to be detected in a forward direction to obtain a first substring;
s43, matching the first substring with the optimal keyword of the target user, and if the matching is successful, executing the step S44;
s44, stopping matching, and determining that the target user' S phone is a match with the target user.
Preferably, in step S43, if the matching is not successful, step S45 is executed;
s45, cutting off the first character of the text to be detected;
s46, detecting whether the length of the cut text to be detected is smaller than the word length of the optimal keyword, if not, executing a step S47;
and S47, continuously intercepting the removed text to be detected to obtain a new first substring, and then returning to the step S43 to match the new first substring.
Preferably, in step S4, if the detection result is no, step S5 is executed;
s5, removing the optimal keywords;
s6, extracting the target keyword with the longest word length from the removed target keywords as a new optimal keyword;
s7, detecting whether the text to be detected contains the new optimal keyword, if so, marking an uncertain label for the target user, wherein the uncertain label is used for representing whether the telephone of the target user is matched with the target user and needs to be manually verified.
Preferably, in step S7, if the detection result is no, step S8 is executed;
s8, detecting whether all the target keywords are extracted, if so, executing a step S9, and if not, returning to the step S5 to remove the new optimal keywords;
s9, determining that the target user' S phone is not matched with the target user.
A detection system for an outbound record of a call center comprises a word stock construction module, a record acquisition module, a keyword extraction module and a first detection module;
the word stock construction module is used for constructing a keyword stock, and the keyword stock stores a plurality of keywords corresponding to a plurality of users;
the recording acquisition module is used for acquiring the outgoing call recording of a call of a target user and converting the outgoing call recording into a text to be detected;
the keyword extraction module is used for acquiring at least one target keyword corresponding to the target user from the keyword library and extracting the target keyword with the longest word length as an optimal keyword;
the first detection module is used for detecting whether the text to be detected contains the optimal keyword, and if yes, the telephone of the target user is determined to be matched with the target user.
Preferably, the keyword extraction module comprises a word length obtaining unit, an intercepting unit and a matching unit;
the word length obtaining unit is used for obtaining the word length of the optimal keyword of the target user;
the intercepting unit is used for positively intercepting the text to be detected by taking the word length of the optimal keyword as an intercepting length to obtain a first substring;
and the matching unit is used for matching the first substring with the optimal keyword of the target user, stopping matching if the matching is successful, and determining that the telephone of the target user is matched with the target user.
Preferably, the keyword extraction module further comprises a cutting unit and a detection unit;
the matching unit is also used for calling the cutting-out unit when the first substring is unsuccessfully matched with the optimal keyword of the target user; (ii) a
The cutting-off unit is used for cutting off the first character of the text to be detected;
the detection unit is used for detecting whether the length of the cut text to be detected is smaller than the word length of the optimal keyword or not, and if not, the interception unit is called; (ii) a
The intercepting unit is further used for continuously intercepting the cut text to be detected to obtain a new first sub-string, and then the matching unit is called to match the new first sub-string.
Preferably, the detection system further comprises a rejection module;
the first detection module is further used for calling the eliminating module when the text to be detected does not contain the optimal keyword;
the removing module is used for removing the optimal keywords;
the keyword extraction module is also used for extracting a target keyword with the longest word length from the removed target keywords as a new optimal keyword;
the first detection module is further configured to detect whether the text to be detected contains the new optimal keyword, and if so, mark an uncertain tag to the target user, where the uncertain tag is used to represent whether a phone of the target user matches the target user and needs manual verification.
Preferably, the detection system further comprises a second detection module;
the first detection module is further used for calling the second detection module when the text to be detected does not contain the new optimal keyword;
the second detection module is used for detecting whether the target keywords are extracted completely, if so, determining that the telephone of the target user is unmatched with the target user, and if not, calling the rejection module to reject the new optimal keywords.
The positive progress effects of the invention are as follows: according to the method, the text content of the outbound record is subjected to semantic analysis, the matched longest word keyword is preferentially identified, the optimal result is accurately matched, and the efficiency and accuracy of text information verification are improved.
Drawings
Fig. 1 is a flowchart of a method for detecting an outgoing call record of a call center according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of step 40 of the method for detecting an outgoing call record in a call center according to embodiment 1 of the present invention.
Fig. 3 is a flowchart of a method for detecting an outbound record of a call center according to embodiment 2 of the present invention.
Fig. 4 is a block diagram of a system for detecting an outgoing call record in a call center according to embodiment 3 of the present invention.
Fig. 5 is a schematic block diagram of a keyword extraction module in a system for detecting an outgoing call record in a call center according to embodiment 3 of the present invention.
Fig. 6 is a block diagram of a system for detecting an outgoing call record in a call center according to embodiment 4 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
A method for detecting an outbound record of a call center, as shown in fig. 1, the method includes:
In this embodiment, as shown in fig. 2, step 40 specifically includes:
step 404 stops the match and determines that the target user's phone is a match with the target user.
and 407, continuously intercepting the removed text to be detected to obtain a new first sub-string, and returning to the 403 to match the new first sub-string.
Taking a specific example for explanation, assuming that the outgoing call record of a target user is detected, a plurality of keywords AB, BC, ABB and ABBC corresponding to the target user are obtained according to a keyword library;
if the content of the out-of-segment call recording is AAAABBCCC, extracting a keyword ABBC for matching, taking 4 as an intercepting length, intercepting to obtain an AAAA, and if the AAAA is not matched with the ABBC, cutting off the first character to obtain AAABBCCC, continuing intercepting and matching, finally intercepting to obtain the ABBC which is matched with the ABBC, and further determining that the telephone of the target user is matched with the target user.
In the embodiment, the text content of the outbound record is subjected to semantic analysis, the matched longest word keyword is preferentially identified, the optimal result is accurately matched, and the efficiency and the accuracy of text information verification are improved.
Example 2
The method for detecting the outgoing call record of the call center of the present embodiment is further improved on the basis of embodiment 1, as shown in fig. 3, in step 40, if the detection result is no, step 60 is executed;
It should be noted that, when a new optimal keyword is matched in this embodiment, the matching manner is the same as the matching scheme for the optimal keyword in embodiment 1, and the matching is performed by intercepting substrings.
Further explanation based on the example in example 1:
supposing that the content of the out-of-segment call record is AAAABBACC, when matching is carried out by using a keyword ABBC, if the matching is not successful, selecting the keyword ABB with the next length for matching, and matching is successful, marking an uncertain label for the target user, wherein the uncertain label is used for representing whether the telephone of the target user is matched with the target user or not and needs manual verification, and further confirmation is needed because similar users possibly exist;
assuming that the content of the out-of-segment call recording is ACACACACCCACC, all the keywords AB, BC, ABB and ABBC are not successfully matched, and at this time, it is determined that the telephone of the target user is not matched with the target user.
In this embodiment, when all the keywords are not successfully matched, it is indicated that the phone of the target user is not matched with the target user, but when other keywords except the optimal keyword are successfully matched, an uncertain tag is marked on the target user, where the uncertain tag is used to characterize whether the phone of the target user is matched with the target user or not, and manual verification is required.
Example 3
A detection system for call center outbound record is disclosed, as shown in FIG. 3, the detection system comprises a word stock construction module 1, a record acquisition module 2, a keyword extraction module 3 and a first detection module 4;
the word stock building module 1 is used for building a keyword stock, and the keyword stock stores a plurality of keywords corresponding to a plurality of users;
the recording acquisition module 2 is used for acquiring the outgoing call recording of a call of a target user and converting the outgoing call recording into a text to be detected;
the keyword extraction module 3 is configured to obtain at least one target keyword corresponding to the target user from the keyword library, and extract a target keyword with a longest word length as an optimal keyword;
the first detecting module 4 is configured to detect whether the text to be detected includes the optimal keyword, and if so, determine that the phone of the target user is matched with the target user.
In this embodiment, as shown in fig. 4, the keyword extraction module 3 includes a word length obtaining unit 31, an intercepting unit 32, and a matching unit 33;
the word length acquiring unit 31 is configured to acquire a word length of an optimal keyword of the target user;
the intercepting unit 32 is configured to intercept the text to be detected in the forward direction by using the word length of the optimal keyword as an intercepting length to obtain a first substring;
the matching unit 33 is configured to match the first sub-string with the optimal keyword of the target user, stop matching if matching is successful, and determine that the phone of the target user is matched with the target user.
With reference to fig. 4, the keyword extraction module 3 further includes a cutting unit 34 and a detection unit 35;
the matching unit 33 is further configured to invoke the cutting unit 34 when the first sub-string is unsuccessfully matched with the optimal keyword of the target user; (ii) a
The cutting unit 34 is used for cutting off the first character of the text to be detected;
the detecting unit 35 is configured to detect whether the length of the cut text to be detected is smaller than the word length of the optimal keyword, and if not, invoke the intercepting unit 32; (ii) a
The intercepting unit 32 is further configured to continue intercepting the cut text to be detected to obtain a new first sub-string, and then call the matching unit 33 to match the new first sub-string.
Taking a specific example for explanation, assuming that the outgoing call record of a target user is detected, a plurality of keywords AB, BC, ABB and ABBC corresponding to the target user are obtained according to a keyword library;
if the content of the out-of-segment call recording is AAAABBCCC, extracting a keyword ABBC for matching, taking 4 as an intercepting length, intercepting to obtain an AAAA, and if the AAAA is not matched with the ABBC, cutting off the first character to obtain AAABBCCC, continuing intercepting and matching, finally intercepting to obtain the ABBC which is matched with the ABBC, and further determining that the telephone of the target user is matched with the target user.
In the embodiment, the text content of the outbound record is subjected to semantic analysis, the matched longest word keyword is preferentially identified, the optimal result is accurately matched, and the efficiency and the accuracy of text information verification are improved.
Example 4
The detection system of the outgoing call recording of the call center of the present embodiment is further improved on the basis of embodiment 3, as shown in fig. 5, the detection system further includes a rejecting module 5 and a second detecting module 6;
the first detection module 4 is further configured to invoke the eliminating module 5 when the text to be detected does not include the optimal keyword;
the eliminating module 5 is used for eliminating the optimal keywords;
the keyword extraction module 3 is further configured to extract a target keyword with the longest word length from the removed target keywords as a new optimal keyword;
the first detection module 4 is further configured to detect whether the text to be detected includes the new optimal keyword, and if so, mark an uncertain tag to the target user, where the uncertain tag is used to represent whether a phone of the target user matches the target user and needs to be manually verified.
The first detection module 4 is further configured to invoke the second detection module 6 when the text to be detected does not include the new optimal keyword;
the second detection module 6 is configured to detect whether all the target keywords are extracted, determine that the phone call of the target user is unmatched with the target user if the target keywords are extracted, and call the rejecting module 5 to reject the new optimal keyword if the target keywords are not extracted.
It should be noted that, in the embodiment, when a new optimal keyword is matched, the matching mode is the same as the matching scheme of the optimal keyword, and the matching is performed by intercepting the substrings.
Further explanation based on the example in example 3:
supposing that the content of the out-of-segment call record is AAAABBACC, when matching is carried out by using a keyword ABBC, if the matching is not successful, selecting the keyword ABB with the next length for matching, and matching is successful, marking an uncertain label for the target user, wherein the uncertain label is used for representing whether the telephone of the target user is matched with the target user or not and needs manual verification, and further confirmation is needed because similar users possibly exist;
assuming that the content of the out-of-segment call recording is ACACACACCCACC, all the keywords AB, BC, ABB and ABBC are not successfully matched, and at this time, it is determined that the telephone of the target user is not matched with the target user.
In this embodiment, when all the keywords are not successfully matched, it is indicated that the phone of the target user is not matched with the target user, but when other keywords except the optimal keyword are successfully matched, an uncertain tag is marked on the target user, where the uncertain tag is used to characterize whether the phone of the target user is matched with the target user or not, and manual verification is required.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (10)
1. A detection method for an outbound record of a call center is characterized by comprising the following steps:
s1, constructing a keyword library, wherein the keyword library stores a plurality of keywords corresponding to a plurality of users;
s2, obtaining the call-out record of a target user, and converting the call-out record into a text to be detected;
s3, acquiring a plurality of target keywords corresponding to the target user from the keyword library, and extracting the target keyword with the longest word length as an optimal keyword;
s4, detecting whether the text to be detected contains the optimal keyword, if so, determining that the telephone of the target user is matched with the target user.
2. The method for detecting the outgoing call record of the call center according to claim 1, wherein the step S4 specifically includes:
s41, acquiring the word length of the optimal keyword of the target user;
s42, taking the word length of the optimal keyword as an intercepting length, and intercepting the text to be detected in a forward direction to obtain a first substring;
s43, matching the first substring with the optimal keyword of the target user, and if the matching is successful, executing the step S44;
s44, stopping matching, and determining that the target user' S phone is a match with the target user.
3. The method as claimed in claim 2, wherein in step S43, if the matching is not successful, step S45 is executed;
s45, cutting off the first character of the text to be detected;
s46, detecting whether the length of the cut text to be detected is smaller than the word length of the optimal keyword, if not, executing a step S47;
and S47, continuously intercepting the removed text to be detected to obtain a new first substring, and then returning to the step S43 to match the new first substring.
4. The method as claimed in claim 1, wherein in step S4, if the detection result is negative, step S5 is executed;
s5, removing the optimal keywords;
s6, extracting the target keyword with the longest word length from the removed target keywords as a new optimal keyword;
s7, detecting whether the text to be detected contains the new optimal keyword, if so, marking an uncertain label for the target user, wherein the uncertain label is used for representing whether the telephone of the target user is matched with the target user and needs to be manually verified.
5. The method as claimed in claim 4, wherein in step S7, if the detection result is negative, executing step S8;
s8, detecting whether all the target keywords are extracted, if so, executing a step S9, and if not, returning to the step S5 to remove the new optimal keywords;
s9, determining that the target user' S phone is not matched with the target user.
6. A detection system for an outbound record of a call center is characterized by comprising a word stock construction module, a record acquisition module, a keyword extraction module and a first detection module;
the word stock construction module is used for constructing a keyword stock, and the keyword stock stores a plurality of keywords corresponding to a plurality of users;
the recording acquisition module is used for acquiring the outgoing call recording of a call of a target user and converting the outgoing call recording into a text to be detected;
the keyword extraction module is used for acquiring a plurality of target keywords corresponding to the target user from the keyword library and extracting the target keyword with the longest word length as an optimal keyword;
the first detection module is used for detecting whether the text to be detected contains the optimal keyword, and if yes, the telephone of the target user is determined to be matched with the target user.
7. The system for detecting an outgoing call record of a call center of claim 6, wherein the keyword extraction module comprises a word length acquisition unit, an interception unit and a matching unit;
the word length obtaining unit is used for obtaining the word length of the optimal keyword of the target user;
the intercepting unit is used for positively intercepting the text to be detected by taking the word length of the optimal keyword as an intercepting length to obtain a first substring;
and the matching unit is used for matching the first substring with the optimal keyword of the target user, stopping matching if the matching is successful, and determining that the telephone of the target user is matched with the target user.
8. The system for detecting a call center outgoing call recording of claim 7, wherein said keyword extraction module further comprises a cutting unit and a detection unit;
the matching unit is also used for calling the cutting-out unit when the first substring is unsuccessfully matched with the optimal keyword of the target user;
the cutting-off unit is used for cutting off the first character of the text to be detected;
the detection unit is used for detecting whether the length of the cut text to be detected is smaller than the word length of the optimal keyword or not, and if not, the interception unit is called;
the intercepting unit is further used for continuously intercepting the cut text to be detected to obtain a new first sub-string, and then the matching unit is called to match the new first sub-string.
9. The system for detecting a call center outgoing call recording of claim 6, wherein said detection system further comprises a culling module;
the first detection module is further used for calling the eliminating module when the text to be detected does not contain the optimal keyword;
the removing module is used for removing the optimal keywords;
the keyword extraction module is also used for extracting a target keyword with the longest word length from the removed target keywords as a new optimal keyword;
the first detection module is further configured to detect whether the text to be detected contains the new optimal keyword, and if so, mark an uncertain tag to the target user, where the uncertain tag is used to represent whether a phone of the target user matches the target user and needs manual verification.
10. The system for detecting a call center outgoing call recording of claim 9, wherein said detection system further comprises a second detection module;
the first detection module is further used for calling the second detection module when the text to be detected does not contain the new optimal keyword;
the second detection module is used for detecting whether the target keywords are extracted completely, if so, determining that the telephone of the target user is unmatched with the target user, and if not, calling the rejection module to reject the new optimal keywords.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811591872.4A CN109510904B (en) | 2018-12-25 | 2018-12-25 | Method and system for detecting call center outbound record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811591872.4A CN109510904B (en) | 2018-12-25 | 2018-12-25 | Method and system for detecting call center outbound record |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109510904A CN109510904A (en) | 2019-03-22 |
| CN109510904B true CN109510904B (en) | 2020-10-27 |
Family
ID=65754652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811591872.4A Active CN109510904B (en) | 2018-12-25 | 2018-12-25 | Method and system for detecting call center outbound record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109510904B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111601002B (en) * | 2020-04-10 | 2021-07-30 | 北京捷通华声科技股份有限公司 | Client number state matching method and device, electronic equipment and storage medium |
| CN112015884A (en) * | 2020-08-28 | 2020-12-01 | 欧冶云商股份有限公司 | Method and device for extracting keywords of user visiting data and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10177582A (en) * | 1996-12-18 | 1998-06-30 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for retrieving longest match |
| CN102298585A (en) * | 2010-06-24 | 2011-12-28 | 高德软件有限公司 | Address splitting and level marking method and device |
| CN103577548A (en) * | 2013-10-12 | 2014-02-12 | 优视科技有限公司 | Method and device for matching characters with close pronunciation |
| CN103914533A (en) * | 2014-03-31 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Promotion search result display method and device |
| CN108536667A (en) * | 2017-03-06 | 2018-09-14 | 中国移动通信集团广东有限公司 | Chinese text recognition methods and device |
| CN108848276A (en) * | 2018-07-30 | 2018-11-20 | 携程旅游信息技术（上海）有限公司 | Telephone number method for detecting availability, system, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103873601B (en) * | 2012-12-11 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | A kind of method for digging and system addressing class query word |
| CN104077320B (en) * | 2013-03-29 | 2019-12-17 | 北京百度网讯科技有限公司 | method and device for generating information to be issued |
-
2018
- 2018-12-25 CN CN201811591872.4A patent/CN109510904B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10177582A (en) * | 1996-12-18 | 1998-06-30 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for retrieving longest match |
| CN102298585A (en) * | 2010-06-24 | 2011-12-28 | 高德软件有限公司 | Address splitting and level marking method and device |
| CN103577548A (en) * | 2013-10-12 | 2014-02-12 | 优视科技有限公司 | Method and device for matching characters with close pronunciation |
| CN103914533A (en) * | 2014-03-31 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Promotion search result display method and device |
| CN108536667A (en) * | 2017-03-06 | 2018-09-14 | 中国移动通信集团广东有限公司 | Chinese text recognition methods and device |
| CN108848276A (en) * | 2018-07-30 | 2018-11-20 | 携程旅游信息技术（上海）有限公司 | Telephone number method for detecting availability, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109510904A (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106033416B (en) | Character string processing method and device | |
| US6711542B2 (en) | Method of identifying a language and of controlling a speech synthesis unit and a communication device | |
| CN109145095B (en) | Place name information matching method, information matching device and computer equipment | |
| CN103916513A (en) | Method and device for recording communication message at communication terminal | |
| CN104462105B (en) | Chinese word cutting method, device and server | |
| CN109510904B (en) | Method and system for detecting call center outbound record | |
| CN111881297A (en) | Method and device for correcting voice recognition text | |
| CN111782892B (en) | Similar character recognition method, device, apparatus and storage medium based on prefix tree | |
| CN110909123A (en) | Data extraction method and device, terminal equipment and storage medium | |
| CN111079410A (en) | Text recognition method and device, electronic equipment and storage medium | |
| EP1058446A2 (en) | Key segment spotting in voice messages | |
| CN111737424A (en) | Question matching method, device, equipment and storage medium | |
| CN111401012A (en) | Text error correction method, electronic device and computer readable storage medium | |
| CN113761137B (en) | Method and device for extracting address information | |
| CN116501844A (en) | Voice keyword retrieval method and system | |
| CN108038124B (en) | PDF document acquisition and processing method, system and device based on big data | |
| CN115691503A (en) | Voice recognition method and device, electronic equipment and storage medium | |
| CN110634480A (en) | Voice dialogue system, model creation device, and method thereof | |
| CN115331675A (en) | Method and device for processing user voice | |
| CN110955771B (en) | Customer service method and system, computer equipment and computer readable storage medium | |
| CN113822029A (en) | Customer service assistance method, device and system | |
| CN112183097B (en) | Entity recall method and related device | |
| CN115329756B (en) | Execution body extraction method and device, storage medium and electronic equipment | |
| CN116523478B (en) | Policy data management method, system, equipment and storage medium | |
| CN114462364B (en) | Method and device for inputting information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |