CN117354422A - Service auxiliary processing method, device, computer equipment and storage medium - Google Patents
Service auxiliary processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117354422A CN117354422A CN202311303721.5A CN202311303721A CN117354422A CN 117354422 A CN117354422 A CN 117354422A CN 202311303721 A CN202311303721 A CN 202311303721A CN 117354422 A CN117354422 A CN 117354422A
- Authority
- CN
- China
- Prior art keywords
- service
- call
- text
- current call
- summary information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 99
- 230000008451 emotion Effects 0.000 claims abstract description 92
- 238000004891 communication Methods 0.000 claims abstract description 78
- 238000000034 method Methods 0.000 claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 230000000875 corresponding effect Effects 0.000 claims description 105
- 238000004590 computer program Methods 0.000 claims description 37
- 238000003058 natural language processing Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000012795 verification Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Marketing (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Hospice & Palliative Care (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application relates to a service auxiliary processing method, a device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved; if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service; generating service summary information according to the communication result, the user demand and the user emotion of the current call service; and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information. By adopting the method, the problem to be solved can be automatically analyzed and sent, the working efficiency is improved, meanwhile, the analysis of the emotion of the user is introduced, and the service summary information containing the problem to be solved can be more accurately analyzed and obtained.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a service auxiliary processing method, apparatus, computer device, and storage medium.
Background
With the development of artificial intelligence technology, the artificial intelligence technology is gradually applied to service call scenes, that is, received service calls are distributed to staff through artificial intelligence, and then the staff solves service problems for users.
However, in the process of solving the service problem for the user by the staff, the staff is usually required to record the service problem of the user in the process of answering the service call, which affects the working efficiency of the staff, meanwhile, for the service problem which cannot be solved, the staff can analyze the service problem to be solved based on the user requirement and the communication result, determine the service type of the service problem to be solved and distribute the service type to the corresponding service department.
Although the method can finish the processing of the service problem to be solved, the method has the problems of low working efficiency and low accuracy of recording and analyzing the service problem to be solved because the repeated workload of the method is large and the process of recording and analyzing the service problem to be solved is complicated and the staff has strong subjectivity.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a service assistance processing method, apparatus, computer device, and storage medium, which can improve the working efficiency and improve the accuracy of the recording analysis process of the service problem to be solved.
In a first aspect, the present application provides a service-assisted processing method. The method comprises the following steps:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In one embodiment, determining whether a current call service has a pending problem includes:
detecting whether a delay reply sentence exists in call audio of the current call service;
if so, determining that the current call service has a problem to be solved.
In one embodiment, according to the call audio of the current call service, analyzing the communication result, the user demand and the user emotion of the current call service includes:
based on the switching time of the audio source in the current conversation service process, the conversation audio of the current conversation service is segmented into at least two sub-audio segments;
Performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment;
according to the audio source, the call time and the text content corresponding to each sub-text segment, generating a call text of the current call service;
and analyzing the communication result, the user demand and the user emotion of the current call service according to the call text.
In one embodiment, according to the call text, analyzing the communication result, the user demand and the user emotion of the current call service includes:
identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text;
analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service;
and carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
In one embodiment, the method further comprises:
generating a call identifier of the current call service according to the call party information and the call time of the current call service; the calling party information comprises information of both calling parties;
Determining a service label corresponding to the service summary information according to the user demand;
and storing the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service in a preset storage space in a correlated manner.
In one embodiment, the sending the service summary information to the special service processing end includes:
if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to the service label corresponding to each service summary information stored in a preset storage space;
and sending the service summary information to the corresponding special service processing end.
In a second aspect, the present application further provides a service auxiliary processing device. The device comprises:
the problem determining module is used for determining whether the current call service has a problem to be solved or not if the call state of the current call service is detected to be finished;
the call analysis module is used for analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service if the call request exists;
the information generation module is used for generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
And the information sending module is used for sending the service summary information to the special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
If the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
When determining that the current call service which is finished has the problem to be solved, the service auxiliary processing method, the device, the computer equipment and the storage medium generate service summary information according to the communication result, the user demand and the user emotion which are analyzed by the call audio of the current call service, and send the service summary information to the special service processing end so that the special service processing end can process the problem to be solved based on the service summary information. According to the method, when the problem to be solved exists in the finished current call service, service summary information is automatically generated according to the communication result of call audio, the user demand and the user emotion, and the service summary information is sent to the special service processing end, so that the working efficiency is improved while the cost is reduced.
Drawings
Fig. 1 is an application environment diagram of a service auxiliary processing method provided in this embodiment;
fig. 2 is a flow chart of a first service auxiliary processing method according to the present embodiment;
fig. 3 is a schematic flow chart of resolving a call text according to the present embodiment;
fig. 4 is a schematic flow chart of storing service information according to the present embodiment;
fig. 5 is a flowchart of a second service assistance processing method according to the present embodiment;
fig. 6 is a block diagram of a first service support processing apparatus according to the present embodiment;
fig. 7 is a block diagram of a second service support processing apparatus according to the present embodiment;
fig. 8 is a block diagram of a third service support processing apparatus according to the present embodiment;
fig. 9 is a block diagram of a fourth service support processing apparatus according to the present embodiment;
fig. 10 is a block diagram of a fifth service support processing apparatus according to the present embodiment;
fig. 11 is an internal structure diagram of a computer device according to the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The service auxiliary processing method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein, the server 101 communicates with the special service processing end 102 through a network. If the server 101 detects that the current call service is finished, determining whether the current call service has a problem to be solved, if so, the server 101 analyzes the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service, generates service summary information according to the communication result, the user demand and the user emotion of the current call service, and finally sends the service summary information to the special service processing end 102 for the special service processing end 102 to process the problem to be solved based on the service summary information. The special service processing end 102 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a service assistance processing method is provided, and the method is applied to the server 101 in fig. 1 for illustration, and includes the following steps:
s201, detecting the call state of the current call service.
The current call service may be a call that provides a service to the user at the current time. The call state of the current call service call may include in-call and end.
Optionally, after the current service dialed by the user is communicated, the server records the current call service, detects the call state of the current call service in real time, if the call state of the current call service is in call, continues to detect the current call service state until the current call service state becomes finished, then proves that the current call service is finished, and continues to execute step S202.
S202, if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved.
The to-be-solved problem may be a service problem that a worker does not help a user to solve in the current call service.
Optionally, if the call state of the current call service is detected to be finished, the manner of determining whether the current call service has the problem to be solved may be various, which is not limited in the present application.
One of the alternative ways may be that when the server detects that the current call service is finished, query information is output through the terminal, the query information is used for querying whether the staff member has all solved the problem of the user, and according to the options input on the terminal by the staff member based on the query information, whether the current call service has the problem to be solved is determined, that is, if the staff member selects the problem of the user to be solved, the current call service is proved that the problem to be solved does not exist; if the staff chooses not to solve the problem of the user completely, the current call service is proved to have the problem to be solved.
Alternatively, whether a deferred reply sentence exists in the call audio of the current call service is detected; if so, determining that the current call service has a problem to be solved. The call audio may be audio obtained by recording the current call service. The deferred answer sentence may be a standard conversation that is preset for applying a deferred answer to the user, for example, an answer will be made N days later for the question to be solved by the user. Specifically, it may be to detect the call audio of the current call service and determine whether there is a deferred reply sentence in the call audio; it is also possible to convert the call audio of the current call service into a call text and detect whether there is a deferred reply sentence in the call text. If yes, proving that the current call service has a problem to be solved; if the call service does not exist, determining that the current call service does not exist the problem to be solved.
And S203, if the communication result, the user demand and the user emotion of the current call service are analyzed according to the call audio of the current call service.
The communication result may be a solution of the problem to be solved, such as delaying a response for several days, whether the problem to be solved is solved, etc. The user demand may be the content of the problem to be solved, such as the existence of an advance payback demand, etc. The user emotion may be the emotion of the user in the process of communicating the problem to be solved, such as peace, eager, active, etc.
Optionally, according to the call audio of the current call service, there may be various ways of analyzing the communication result, the user demand and the user emotion of the current call service, which is not limited in this application.
One of the alternative implementation manners may be that the call audio of the current call service is converted into a call text, and the call text is parsed by a natural language processing algorithm (such as Natural Language Processing, NLP) to obtain the communication result and the user requirement of the current call service; and analyzing the call text through an emotion perception algorithm to obtain the emotion of the user of the current call service.
Another alternative implementation manner may be that the call audio of the current call service is converted into a call text, the call text is input into a natural language processing model, and the natural language processing analysis model performs semantic analysis on the call text, so as to obtain the communication result and the user requirement of the current call service; and inputting the call text into the emotion perception model to carry out emotion perception processing on the call text, so as to obtain the emotion of the user of the current call service.
S204, generating service summary information according to the communication result, the user demand and the user emotion of the current call service.
The service summary information may be information for summarizing key contents in the current call service.
Optionally, the communication result, the user demand and the user emotion of the current call service are spliced through a preset service summary template to generate service summary information.
Exemplary, if the communication result is: the problem to be solved is not solved, and the staff promises to answer after 3 days; the user demand is an advanced repayment demand; the emotion of the user is urgency. The service summary information obtained by the preset service summary template is determined to be: the user has the demand of repayment in advance, the staff does not solve the demand, and the answer is given within 3 days, so that the emotion of the user is urgent.
S205, the service summary information is sent to the special service processing end, so that the special service processing end processes the problem to be solved based on the service summary information.
The special service processing end may be a server for performing special service processing, and optionally, the special service processing end includes a lending service processor, a financial service processor, and the like.
Optionally, the obtained service summary information is sent to a special service processing end, and the special service processing end processes the problem to be solved based on the service summary information.
S206, if not, ending.
According to the service auxiliary processing method, when the problem to be solved exists in the finished current call service, service summary information is generated according to the communication result, the user demand and the user emotion analyzed by the call audio of the current call service, and the service summary information is sent to the special service processing end so that the special service processing end can process the problem to be solved based on the service summary information. According to the method, when the problem to be solved exists in the finished current call service, service summary information is automatically generated according to the communication result of call audio, the user demand and the user emotion, and the service summary information is sent to the special service processing end, so that the working efficiency is improved while the cost is reduced.
It should be noted that in the technology of the above embodiment, the present embodiment may further set a self-checking method, that is, a sample audio for self-checking is preset, the sample audio is parsed, a verification communication result, a verification user requirement, and a verification user emotion corresponding to the sample audio are determined, the verification communication result, the verification user requirement, and the verification user emotion are compared, and a real communication result, a real user requirement, and a real user emotion corresponding to the sample audio are compared to determine accuracy of an audio parsing function; if the accuracy verification of the audio analysis function is not passed, determining that the audio analysis function is abnormal, notifying a related department to adjust the audio analysis function, if the accuracy verification of the audio analysis function is passed, generating verification summary information based on a verification communication result, a verification user requirement and a verification user emotion, simultaneously determining the similarity between the verification summary information and the real summary information corresponding to the sample audio, if the similarity is lower than a preset similarity threshold, determining that the summary information generation function is abnormal, and notifying the related department to adjust the verification summary information generation function; if the similarity is not lower than a preset similarity threshold, the verification summary information is sent to a special service processing end, whether the special service processing end receives the verification summary information or not is determined, if the verification summary information is not received, the abnormality of the summary information sending function is determined, and a related department is informed to adjust the verification summary information sending function; and if the verification summary information is received, the self-checking is passed.
FIG. 3 is a flow diagram of parsing call text in one embodiment. In order to more accurately determine the communication result, the user demand and the user emotion of the user, the present embodiment may convert the call audio into a call text, and determine the communication result, the user demand and the user emotion of the user based on the call text, and specifically, the present embodiment provides an alternative manner of analyzing the call text, which includes the following steps:
s301, based on the switching time of the audio source in the current conversation service process, the conversation audio of the current conversation service is segmented into at least two sub-audio segments.
The audio source may be a source for acquiring audio, alternatively, the audio source may be internal audio, i.e. audio generated by a user, or may be a microphone, i.e. audio generated by a staff member.
Optionally, determining each audio source in the current call service process, and simultaneously determining a switching time of the audio source in the current call service process, and dividing the call audio of the current call service into at least two sub-audio segments by taking the switching time as a dividing point.
S302, performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment.
Alternatively, text conversion processing may be performed on each sub-audio segment based on a voice-to-text conversion algorithm (such as Whisper algorithm) or a neural network model, to determine a corresponding sub-text segment for each sub-audio segment.
S303, according to the audio source, the communication time and the text content corresponding to each sub-text segment, generating the communication text of the current communication service.
Optionally, determining the arrangement sequence of the sub-text segments according to the call time corresponding to the sub-text segments, and sequencing the sub-text segments. Determining a calling party corresponding to each sub-text segment according to the audio source of the corresponding sub-audio segment of each sub-text segment, namely if the audio source corresponding to the sub-audio segment is a microphone, the calling party corresponding to the sub-audio segment is a staff; if the audio source corresponding to the sub-audio segment is internal audio, the corresponding calling party of the sub-audio segment is the user. And aiming at each sub-text segment which is determined with the identity information and sequenced, acquiring text content corresponding to each sub-text segment, and splicing the text content with the identity information of each sub-text segment to generate a call text of the current call service.
S304, analyzing the communication result, the user demand and the user emotion of the current call service according to the call text.
Optionally, identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text; analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service; and carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
The invalid information may be information having no actual meaning in the call text, such as a mood word or the like.
Optionally, identifying and obtaining invalid information from the call text by presetting an invalid information template, deleting the invalid information in the call text, and completing simplified processing of the call text to obtain a simplified text corresponding to the call text; the simplified text is input into a natural language processing model, the natural language processing model analyzes the simplified text, and a communication result and a user requirement of the current call service are extracted from the simplified text. Text content corresponding to the user audio source in the call text is extracted, emotion analysis is carried out on the text content corresponding to the user audio source through an emotion analysis algorithm, and therefore emotion of the user is determined.
And analyzing the call text, determining a sub-text segment corresponding to each sub-audio segment by carrying out segmentation processing on the call text, generating a call text of the current call service according to an audio source, a call time and text content corresponding to each sub-text segment, and finally analyzing according to the call text to obtain a communication result, a user demand and a user emotion of the current call service. According to the method, identity information corresponding to each sub-audio segment can be accurately identified through the audio source, the arrangement sequence and the identity information of each sub-text segment of the call text can be more accurately determined according to the audio source, the call time and the text content corresponding to the sub-text segment, the call text of the current call service can be more reasonably generated, and finally, the accurate communication result, the user requirement and the user emotion of the current call service can be further obtained based on the accurate call text.
FIG. 4 is a flow diagram of storing service information in one embodiment. On the basis of the above embodiment, the present embodiment may further store service summary information, so as to be invoked when the service summary information is subsequently sent to a specific service processing end, and in particular, the present embodiment provides an alternative way of storing service information, which includes the following steps:
S401, according to the calling party information and the calling time of the current calling service, generating the calling identification of the current calling service.
The calling party information comprises information of both calling parties. Alternatively, the calling party information may include a calling number of the user, and a job number of the staff member. The call identifier may be a unique identifier that characterizes the current call service.
Optionally, obtaining the calling party information of the current calling service and the calling time of the current calling service, and performing splicing processing on the calling party information and the calling time of the current calling service to obtain the calling identifier of the current calling service.
S402, determining a service label corresponding to the service summary information according to the user requirements.
Optionally, determining a service type corresponding to the user requirement in the service summary information, determining a service tag corresponding to the service type, and taking the service tag as the service tag corresponding to the service summary information.
S403, the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service are stored in a preset storage space in an associated mode.
Optionally, the service summary information, the service tag corresponding to the service summary information, and the call identifier of the current call service are stored in a preset record document (such as a table document), and the record document is stored in a preset storage space in an associated manner.
According to the method for storing the service information, the call identifier of the current call service is generated according to the call party information and the call time of the previous call service, meanwhile, the service label is determined according to the user requirement, and the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service are stored in the preset storage space in a correlated mode. The method is based on the determined service summary information, the call identifier corresponding to the service summary information and the service label for associated storage, so that when each service summary information is conveniently and subsequently sent to a special service processing end, the service summary information can be directly called from a preset storage space, and based on the service label corresponding to the service summary information, the service summary information is directly sent to the special service processing end corresponding to the service label.
It should be noted that, in this embodiment, the summary information sending condition may be set, and when the summary information sending condition is met at the current time, the summary information is sent, so that the problem of information loss caused by too high sending frequency of the summary information is avoided. Optionally, if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to a service label corresponding to each service summary information stored in a preset storage space; and sending the service summary information to the corresponding special service processing end. The summary information sending condition may be a preset condition for sending the summary information, such as reaching a preset period and having a summary information sending requirement. Specifically, if the current moment meets the summary information sending condition, determining a service tag corresponding to each service summary information stored in a preset storage space, determining a special service processing end corresponding to the service tag, and sending the service summary information to the special service processing end corresponding to the service tag of the service summary information. The service label based on the service summary information can more accurately and rapidly determine the special service processing end corresponding to the service summary information, and the service summary information is sent to the special service processing end, so that the working efficiency is improved.
In one embodiment, this embodiment provides an alternative way of service assistance processing, and the method is applied to a server for example. As shown in fig. 5, the method comprises the steps of:
s501, detecting the call state of the current call service.
S502, if the conversation state of the current conversation service is detected to be the end, detecting whether a delay reply sentence exists in the conversation audio of the current conversation service.
S503, if yes, determining that the current call service has a problem to be solved, and dividing the call audio of the current call service into at least two sub-audio segments based on the switching time of the audio source in the current call service process.
S504, performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment.
S505, according to the audio source, the communication time and the text content corresponding to each sub-text segment, generating the communication text of the current communication service.
S506, identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text.
S507, analyzing the simplified text through a natural language processing model to obtain the communication result and the user requirement of the current call service.
S508, carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
S509, generating service summary information according to the communication result, the user demand and the user emotion of the current call service.
S510, according to the calling party information and the calling time of the current calling service, generating the calling identification of the current calling service.
The calling party information comprises information of both calling parties.
S511, determining the service label corresponding to the service summary information according to the user requirement.
S512, the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service are stored in a preset storage space in an associated mode.
S513, if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to the service label corresponding to each service summary information stored in the preset storage space.
And S514, sending the service summary information to a corresponding special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
And S515, if the call service does not exist, determining that the current call service does not exist the problem to be solved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a service assistance processing device for implementing the service assistance processing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the one or more service assistance processing devices provided below may be referred to the limitation of the service assistance processing method hereinabove, and will not be described herein.
In one embodiment, as shown in fig. 6, there is provided a service-assisted processing apparatus 1 including: a problem determination module 10, a call analysis module 11, an information generation module 12, and an information transmission module 13, wherein:
the problem determining module 10 is configured to determine whether a problem to be solved exists in the current call service if the call state of the current call service is detected to be finished;
the call analysis module 11 is configured to analyze, if any, a communication result, a user requirement and a user emotion of the current call service according to a call audio of the current call service;
the information generating module 12 is configured to generate service summary information according to a communication result, a user demand and a user emotion of a current call service;
the information sending module 13 is configured to send the service summary information to the special service processing end, so that the special service processing end processes the problem to be solved based on the service summary information.
In one embodiment, as shown in fig. 7, the problem determination module 10 in fig. 6 includes:
a sentence detection unit 100, configured to detect whether a deferred reply sentence exists in a call audio of a current call service;
a problem determining unit 101, configured to determine that the current call service has a problem to be solved if the problem exists.
In one embodiment, as shown in fig. 8, the call parsing module 11 in fig. 6 includes:
an audio slicing unit 110, configured to slice the call audio of the current call service into at least two sub-audio segments based on the switching time of the audio source in the current call service process;
a sub-segment determining unit 111, configured to perform text conversion processing on each sub-audio segment, so as to obtain a sub-text segment corresponding to each sub-audio segment;
a text generation unit 112, configured to generate a call text of the current call service according to the audio source, the call time and the text content corresponding to each sub-text segment;
the text parsing unit 113 is configured to parse the communication result, the user requirement and the user emotion of the current call service according to the call text.
In one embodiment, the text parsing unit 113 in fig. 8 includes:
the text simplifying subunit is used for identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text;
the text analysis subunit is used for analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service;
And the emotion perception subunit is used for carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
In one embodiment, as shown in fig. 9, the service support processing apparatus 1 in fig. 6 includes:
the identifier generating module 14 is configured to generate a call identifier of the current call service according to the call party information and the call time of the current call service; the calling party information comprises information of both calling parties;
the tag determining module 15 is configured to determine a service tag corresponding to the service summary information according to a user requirement;
the information storage module 16 is configured to store the service summary information, the service tag corresponding to the service summary information, and the call identifier of the current call service in a preset storage space in an associated manner.
In one embodiment, as shown in fig. 10, the information sending module 13 in fig. 6 includes:
the processing end determining unit 130 is configured to determine, if the current time meets the summary information sending condition, a specific service processing end corresponding to each service summary information according to a service tag corresponding to each service summary information stored in a preset storage space;
the information sending unit 131 is configured to send each service summary information to a corresponding dedicated service processing end.
The respective modules in the service-assistance processing apparatus described above may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a service-assisted processing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In one embodiment, the processor when executing the computer program further performs the steps of:
Detecting whether a delay reply sentence exists in call audio of the current call service;
if so, determining that the current call service has a problem to be solved.
In one embodiment, the processor when executing the computer program further performs the steps of:
based on the switching time of the audio source in the current conversation service process, the conversation audio of the current conversation service is segmented into at least two sub-audio segments;
performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment;
according to the audio source, the call time and the text content corresponding to each sub-text segment, generating a call text of the current call service;
and analyzing the communication result, the user demand and the user emotion of the current call service according to the call text.
In one embodiment, the processor when executing the computer program further performs the steps of:
identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text;
analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service;
and carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
In one embodiment, the processor when executing the computer program further performs the steps of:
generating a call identifier of the current call service according to the call party information and the call time of the current call service; the calling party information comprises information of both calling parties;
determining a service label corresponding to the service summary information according to the user demand;
and storing the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service in a preset storage space in a correlated manner.
In one embodiment, the processor when executing the computer program further performs the steps of:
if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to the service label corresponding to each service summary information stored in a preset storage space;
and sending the service summary information to the corresponding special service processing end.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
If so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In one embodiment, the computer program when executed by the processor further performs the steps of:
detecting whether a delay reply sentence exists in call audio of the current call service;
if so, determining that the current call service has a problem to be solved.
In one embodiment, the computer program when executed by the processor further performs the steps of:
based on the switching time of the audio source in the current conversation service process, the conversation audio of the current conversation service is segmented into at least two sub-audio segments;
performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment;
according to the audio source, the call time and the text content corresponding to each sub-text segment, generating a call text of the current call service;
and analyzing the communication result, the user demand and the user emotion of the current call service according to the call text.
In one embodiment, the computer program when executed by the processor further performs the steps of:
identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text;
analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service;
and carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
generating a call identifier of the current call service according to the call party information and the call time of the current call service; the calling party information comprises information of both calling parties;
determining a service label corresponding to the service summary information according to the user demand;
and storing the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service in a preset storage space in a correlated manner.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to the service label corresponding to each service summary information stored in a preset storage space;
And sending the service summary information to the corresponding special service processing end.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
In one embodiment, the computer program when executed by the processor further performs the steps of:
detecting whether a delay reply sentence exists in call audio of the current call service;
if so, determining that the current call service has a problem to be solved.
In one embodiment, the computer program when executed by the processor further performs the steps of:
based on the switching time of the audio source in the current conversation service process, the conversation audio of the current conversation service is segmented into at least two sub-audio segments;
Performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment;
according to the audio source, the call time and the text content corresponding to each sub-text segment, generating a call text of the current call service;
and analyzing the communication result, the user demand and the user emotion of the current call service according to the call text.
In one embodiment, the computer program when executed by the processor further performs the steps of:
identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text;
analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service;
and carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
generating a call identifier of the current call service according to the call party information and the call time of the current call service; the calling party information comprises information of both calling parties;
determining a service label corresponding to the service summary information according to the user demand;
And storing the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service in a preset storage space in a correlated manner.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to the service label corresponding to each service summary information stored in a preset storage space;
and sending the service summary information to the corresponding special service processing end.
The data (including, but not limited to, data for analysis, data stored, data displayed, etc.) referred to in this application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A service-assisted processing method, the method comprising:
if the call state of the current call service is detected to be finished, determining whether the current call service has a problem to be solved;
if so, analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service;
Generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
and sending the service summary information to a special service processing end so that the special service processing end can process the problem to be solved based on the service summary information.
2. The method of claim 1, wherein the determining whether the current call service has a pending problem comprises:
detecting whether a delay reply sentence exists in the call audio of the current call service;
if so, determining that the current call service has a problem to be solved.
3. The method according to claim 1, wherein the parsing the communication result, the user demand, and the user emotion of the current call service according to the call audio of the current call service includes:
dividing the call audio of the current call service into at least two sub-audio segments based on the switching time of the audio source in the current call service process;
performing text conversion processing on each sub-audio segment to obtain a sub-text segment corresponding to each sub-audio segment;
according to the audio source, the call time and the text content corresponding to each sub-text segment, generating a call text of the current call service;
And analyzing the communication result, the user demand and the user emotion of the current call service according to the call text.
4. The method of claim 3, wherein the parsing the communication result, the user demand, and the user emotion of the current call service according to the call text comprises:
identifying invalid information in the call text, and simplifying the call text based on the invalid information to obtain a simplified text corresponding to the call text;
analyzing the simplified text through a natural language processing model to obtain a communication result and user requirements of the current call service;
and carrying out emotion analysis on text content corresponding to the user audio source in the call text through an emotion analysis algorithm to obtain the emotion of the user.
5. The method according to claim 1, wherein the method further comprises:
generating a call identifier of the current call service according to the call party information and the call time of the current call service; wherein the calling party information comprises information of both calling parties;
determining a service label corresponding to the service summary information according to the user demand;
And storing the service summary information, the service label corresponding to the service summary information and the call identifier of the current call service in a preset storage space in a correlated manner.
6. The method of claim 5, wherein sending the service summary information to a dedicated service processing end comprises:
if the current moment meets the summary information sending condition, determining a special service processing end corresponding to each service summary information according to the service label corresponding to each service summary information stored in a preset storage space;
and sending the service summary information to a corresponding special service processing end.
7. A service-assisted processing apparatus, the apparatus comprising:
the problem determining module is used for determining whether a problem to be solved exists in the current call service or not if the call state of the current call service is detected to be finished;
the call analysis module is used for analyzing the communication result, the user demand and the user emotion of the current call service according to the call audio of the current call service if the call audio exists;
the information generation module is used for generating service summary information according to the communication result, the user demand and the user emotion of the current call service;
And the information sending module is used for sending the service summary information to a special service processing end so that the special service processing end can process the to-be-solved problem based on the service summary information.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311303721.5A CN117354422A (en) | 2023-10-10 | 2023-10-10 | Service auxiliary processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311303721.5A CN117354422A (en) | 2023-10-10 | 2023-10-10 | Service auxiliary processing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117354422A true CN117354422A (en) | 2024-01-05 |
Family
ID=89364441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311303721.5A Pending CN117354422A (en) | 2023-10-10 | 2023-10-10 | Service auxiliary processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117354422A (en) |
-
2023
- 2023-10-10 CN CN202311303721.5A patent/CN117354422A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111027295B (en) | Data processing method, device, computer equipment and storage medium | |
| CN110135888B (en) | Product information pushing method, device, computer equipment and storage medium | |
| WO2020125463A1 (en) | Report generation method and apparatus, computer device, and computer readable storage medium | |
| CN110908778B (en) | Task deployment method, system and storage medium | |
| WO2019019645A1 (en) | Method and apparatus for executing information pushing task, and computer device and storage medium | |
| CN103870528B (en) | Depth problem answers the method and system of intersystem problem classification and Feature Mapping | |
| US20240203407A1 (en) | Automatic generation of a contextual meeting summary | |
| US20180365319A1 (en) | Identifying relationships from communication content | |
| CN110737655A (en) | Method and device for reporting data | |
| CN110609618A (en) | Man-machine conversation method and device, computer equipment and storage medium | |
| CN110442439B (en) | Task process processing method and device and computer equipment | |
| CN117354422A (en) | Service auxiliary processing method, device, computer equipment and storage medium | |
| CN115544050A (en) | Operation log recording method, device, equipment and storage medium | |
| CN111859191A (en) | GIS service aggregation method, device, computer equipment and storage medium | |
| CN114297380A (en) | Data processing method, device, equipment and storage medium | |
| US11941358B2 (en) | Identifying messages entered into an incorrect conversation | |
| CN116681408B (en) | System management method, device, computer equipment and storage medium | |
| CN117436057A (en) | Security verification method, security verification device, computer equipment and storage medium | |
| CN117409806A (en) | Service processing method, device, computer equipment and storage medium | |
| CN118071101A (en) | Problem reporting method, device, computer equipment, storage medium and program product | |
| CN117495191A (en) | Quality of service evaluation method, device, computer equipment and storage medium | |
| CN116962335A (en) | Prompt message sending method and device, computer equipment and storage medium | |
| CN117950778A (en) | System interaction method, device, computer equipment and storage medium | |
| CN117131066A (en) | Query statement generation method, device, computer equipment and storage medium | |
| CN114898739A (en) | Voice call response processing method and device, computer equipment and storage medium |
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 |