CN117956082B - Electric marketing method combined with AI voice - Google Patents
Electric marketing method combined with AI voice Download PDFInfo
- Publication number
- CN117956082B CN117956082B CN202410358749.7A CN202410358749A CN117956082B CN 117956082 B CN117956082 B CN 117956082B CN 202410358749 A CN202410358749 A CN 202410358749A CN 117956082 B CN117956082 B CN 117956082B
- Authority
- CN
- China
- Prior art keywords
- voice
- communication
- user
- observation
- customer service
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004891 communication Methods 0.000 claims abstract description 142
- 238000001356 surgical procedure Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 abstract 1
- 230000003993 interaction Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003287 optical effect Effects 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
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Manipulator (AREA)
- Toys (AREA)
Abstract
The invention provides an electric marketing method combined with AI voice, which comprises the following steps: acquiring user problems related to user voice content, judging whether the user problems are objective problems, if so, carrying out voice communication by an AI voice robot, otherwise, marking the user problems as observation problems when manual customer service is in an idle state, and switching to the manual customer service to carry out voice communication of the observation problems; the AI voice robot performs simulated communication of the observation problem at the same time to obtain a first answering operation adopted by the simulated communication, and records a second answering operation performed by the artificial customer service and a corresponding observation communication result; and respectively obtaining corresponding communication results obtained when the manual customer service and the AI voice robot use corresponding answering operation of the same type of observation problem, and correcting the answering operation of the AI voice robot according to the communication results of the manual customer service and the AI voice robot. The invention can enable the answer phone operation of the AI voice robot to be more in line with the interactive logic so as to improve the communication result of the electric marketing.
Description
Technical Field
The invention relates to the technical field of voice recognition, in particular to an electric marketing method combining AI (analog to digital) voice.
Background
At present, the application of AI voice robots on telephone pins is becoming more and more popular. Although the AI voice has the problems of easy recognition, difficult communication and the like, the AI voice can reduce the operation cost of enterprises to a certain extent, and can carry out primary screening on users in a large range. Therefore, AI speech is critical to the confirmation of the user's purchase intent, as it allows a good initial screening result to be provided to the human customer service for further promotion.
In practice, AI speech often follows the dialogs for which the technician is designing and is therefore prone to error in handling some of the questions that need to be considered and analyzed, which in turn reduces the user's intent to purchase. Therefore, the existing AI speech also has the problem of lower communication results.
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides an electric pin method combined with AI voice to improve the communication result of electric pins.
In order to achieve the above purpose, the invention adopts the following technical scheme:
In a first aspect, the present invention provides an electrical pinning method in combination with AI speech, comprising the steps of:
Acquiring user problems related to user voice content, judging whether the user problems are objective problems, if so, carrying out voice communication by an AI voice robot, otherwise, marking the user problems as observation problems when manual customer service is in an idle state, and switching the user problems into the manual customer service to carry out voice communication of the observation problems;
When the artificial customer service carries out voice communication of the observation problem, the AI voice robot carries out simulated communication of the observation problem at the same time, a first answering operation adopted by the simulated communication is obtained, a second answering operation that whether the artificial customer service has a tendency to the voice communication of the observation problem or not is judged, and if yes, the second answering operation and a corresponding observation communication result are recorded;
and respectively summarizing observation communication results of the same type of observation questions on different answer surgeries to obtain first communication results of each type of observation questions on different answer surgeries, obtaining second communication results corresponding to the first answer surgeries used by the same type of observation questions by the AI voice robot in the same promotion product, and correcting the answer surgeries of the AI voice robot according to the first communication results and the second communication results.
The invention has the beneficial effects that: when the user questions are subjective questions, the voice communication of the subjective questions is carried out through the manual customer service in an idle state, the second answering operation and the corresponding observation communication results which are prone to the communication are recorded, then the first communication results of each type of observation questions on different answering operations are obtained through summarization, the first communication results are used for comparing with the second communication results corresponding to the first answering operation used by the AI voice robot for the same type of observation questions, and finally the answering operation of the AI voice robot is corrected according to the first communication results and the second communication results, so that the answer of some subjective questions is carried out through the manual customer service, the problem that the AI voice robot is prone to making mistakes when the questions needing to be considered and analyzed are processed is solved, meanwhile, the answering operation of the AI voice robot is corrected by means of the processing effects of the manual customer service, so that the answering operation of the AI voice robot is more in accordance with the interaction logic, and the communication results of an electronic pin are improved.
Optionally, the step of acquiring the user questions involved in the user voice content includes:
And monitoring the overall communication result of the current promotion product in real time, judging whether the overall communication result is lower than expected, if yes, acquiring user problems related to user voice contents, otherwise, carrying out voice communication on the user voice contents by an AI voice robot.
According to the description, the AI voice robot performs voice communication when the overall communication result meets the expectation, and the artificial customer service performs intervention assistance when the overall communication result does not meet the expectation, so that the marketing effect is improved and the demand pressure of the artificial customer service is reduced.
Optionally, when the overall communication result is lower than expected, determining a subjective problem to be manually involved, and otherwise, in step S1, when the manual customer service is in an idle state, specifically:
otherwise, judging whether the user problem is a subjective problem to be manually intervened, if so, and if the manual customer service is in an idle state.
Optionally, the correcting the answer operation of the AI voice robot according to the first communication result and the second communication result includes the steps of:
when the first communication result exceeds the first threshold value of the second communication result, directly correcting the user problem of the type from the adopted first answering operation to the second answering operation;
When the first communication result exceeds the second communication result but is lower than the first threshold, the weight value of the second answering operation in the user problems of the type is increased, and the weight value of the first answering operation is correspondingly reduced;
and when the first communication result is lower than the second communication result, maintaining the answer phone operation of the AI voice robot.
Optionally, the first threshold is between 10% and 25% of expected.
Optionally, the method further comprises the steps of:
If the voice communication of the artificial customer service to the observation problem does not accord with all preset answering methods, an alternative answering method is added.
According to the above description, when the manual customer service has a difference between the answer of the current subjective question of the user and all answer calls, an alternative answer call is added to enrich the answer call of the AI voice robot.
Optionally, the method further comprises the steps of:
When the manual customer service is busy, the AI voice robot performs voice communication of subjective questions.
Optionally, the communication result in the first communication result and the second communication result is a user intention result or a user singleness result.
Optionally, the AI voice robot generates pronunciation for training based on the corresponding manual customer service.
From the above description, the machine and the human are the same pronunciation as much as possible to reduce the voice switching threshold.
Drawings
Fig. 1 is a main flow chart of an electrical marketing method combined with AI speech according to an embodiment of the invention.
Detailed Description
In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Example 1
The embodiment is applied to a scene of popularizing products, after receiving the telephone marketing of a client to a certain product, the user is automatically dialed by an AI voice robot, the user intention result is obtained according to the automatic voice communication with the user, and the client carries out the next product popularizing to the user with the intention result as the intended result, so that a user order result is obtained. In this process, there is a case that the outbound user loses interest because the automatic reply effect of the AI voice robot is poor, so in this embodiment, the reasonability of the interaction logic is improved by intervention of the manual customer service and automatic correction of the answer call after the intervention, so as to avoid the above-mentioned case, thereby improving the communication result of this portion. Reference is made in particular to the following description.
Referring to fig. 1, the electric pinning method combined with AI voice includes the steps of:
In a first aspect, the present invention provides an electrical pinning method in combination with AI speech, comprising the steps of:
S1, acquiring user problems related to user voice content, judging whether the user problems are objective problems, if so, carrying out voice communication by an AI voice robot, otherwise, marking the user problems as observation problems when manual customer service is in an idle state, and switching the user problems into the manual customer service to carry out voice communication of the observation problems;
The AI voice robot may use an existing voice interaction model based on deep learning and natural language data, such as a voice interaction model based on a convolutional neural network, and when using the existing voice interaction model, receives user voice content, then performs feature extraction on the user voice content to identify the content to be expressed by the user, then generates a corresponding response, namely a answer speech, according to the content to be expressed, and then converts the response to voice output through a voice synthesis technology to complete the interaction with the user. In the voice synthesis technology, the AI voice robot generates pronunciation for training based on the corresponding manual customer service, so that the voice switching gap feeling is reduced.
Wherein subjective questions and objective questions refer to whether the user's question is an explicit answer content or no explicit answer content, such as "what money is the product? "," which express can be sent "and the like. Is the user question "is this something good? "," can be cheaper? "the price is so low that the product is not good", and the like can be replied according to the situation, and the subjective problem is solved.
In this embodiment, the step of acquiring the user questions related to the user voice content includes the steps of:
S11, monitoring the overall communication result of the current marketing product in real time, judging whether the overall communication result is lower than expected, if yes, acquiring user problems related to user voice contents, otherwise, carrying out voice communication on the user voice contents by an AI voice robot.
The AI voice robot obtains a communication result each time the number is dialed, and the communication result is generally divided into intentional and unintentional, and the final overall communication is the intentional duty ratio. In this embodiment, the overall communication result of the current promoted product is monitored in real time, for example, the intended clients account for 5% of the overall communication result, only 3% of the intended clients are needed for manual intervention, and if the intended clients account for 6%, no manual intervention is needed.
Therefore, when the overall communication result is lower than expected, intervention of manual service is needed, and the method further comprises determining subjective questions to be manually intervened, and specifically comprises the following steps:
S12, filtering the communicated voice content of the current promotion product with the overall communication result lower than the expected one, wherein the voice content with the communication frequency lower than twice or before hang-up does not belong to subjective problems, so as to obtain filtered voice content;
That is, the communication frequency is less than twice, and the communication voice content which is not subject to subjective problem is filtered, so that the voice content which is likely to be hung up due to the communication of the AI voice robot is reserved.
S13, carrying out type division on subjective questions before hanging-up in the filtered voice content to obtain the number of the subjective questions of different types in the filtered voice content, namely a first number, counting the number of the subjective questions of different types in the communication result which is intentional communication voice content, namely a second number, sorting all types of subjective questions from low to high according to the proportional relation between the first number and the second number, and determining the subjective questions with the highest sorting among the subjective questions with the first number larger than a quantity threshold as the subjective questions needing manual intervention.
Among these, different subjective questions are of different types, such as "do this matter get good? "is a problem of product type," can be cheaper a little? "belonging to the price type problem". Then, the subjective questions before hanging up in the filtered voice content are judged, and the type of the subjective questions is judged, so that the number of the subjective questions of each type in the filtered voice content can be obtained, for example, the number of the subjective questions of the type A in the filtered voice content is 176, and the subjective questions of the type B and the subjective questions of the type C are 94 and 37 respectively, namely the first number. At this time, the number statistics is performed on each type of subjective questions from the intentional communicated voice content, for example, the number of subjective questions of type A, B, C in the intentional communicated voice content is 6, 4 and 1, that is, the second number, at this time, the proportional relationship between the first number of subjective questions of type A, B, C and the second number is 29.3, 23.5 and 37, respectively, at this time, the number threshold is 50, only the first number of subjective questions of type a and type B is greater than the number threshold, and the highest ranking of the two subjective questions is type a, and the type a is determined to be the subjective question requiring manual intervention.
In other embodiments, subjective questions about what was last determined to require human intervention may also include: the first quantity and the proportion relation are subjected to weight conversion to obtain the maximum value; or the first number is the largest in the proportion relation being greater than the proportion threshold; or the proportion relation is smaller than the first quantity in the whole communication result of the current promoted product; or the highest, largest, and highest of the preceding are replaced with the order before the preset number of times, such as the first two and the first three.
Thus, when the human service intervenes and determines the problem type of the subjective problem to be intervened, in step S1, otherwise, when the human service is in the idle state, it is specifically:
otherwise, judging whether the user problem is a subjective problem to be manually intervened, if so, and if the manual customer service is in an idle state.
Whether the subjective problem of human intervention is needed or not is judged first, and if not, the AI voice robot is used for voice communication.
Thus, the present embodiment further includes the steps of:
When the manual customer service is busy, the AI voice robot performs voice communication of subjective questions.
Therefore, the embodiment distributes the artificial customer service according to the current situation of the artificial customer service and the influence of the user problem on the final communication result, so that the benefit improvement generated by the subjective problem processed by the artificial customer service on the result of the whole product promotion is maximized.
S2, when the artificial customer service carries out voice communication of the observation problem, the AI voice robot carries out simulated communication of the observation problem at the same time, a first answering operation adopted by the simulated communication is obtained, whether the artificial customer service has a second answering operation prone to voice communication of the observation problem or not is judged, and if yes, the second answering operation and a corresponding observation communication result are recorded;
in this embodiment, the method further includes the steps of:
if the voice communication of the manual customer service on the observation problem does not accord with all preset answering procedures, an alternative answering procedure is added.
The answer phone operation is preset for the AI voice robot to carry out matching reply, in the process, the voice speech of the manual customer service does not necessarily follow the answer phone operation of the AI voice robot, so that the answer phone operation needs to be matched firstly, the expression content is different but the expression meaning is consistent, the same trend is considered, the expression meaning is inconsistent with all preset answer phone operations, an alternative answer phone operation needs to be newly added, and the alternative answer phone operation is used for firstly carrying out effective matching in the subsequent steps and then considering whether the answer phone operation is newly added into the answer phone operation of the AI voice robot.
Therefore, the manual customer service has a corresponding relation with the answer phone operation of the AI voice robot for the voice communication of the observation problem, and is convenient for subsequent matching processing.
S3, respectively summarizing the observation communication results of the same type of observation questions on different answer phones to obtain the first communication results of each type of observation questions on different answer phones, obtaining the second communication results corresponding to the first answer phones used by the same type of observation questions in the same promotion product by the AI voice robot, and correcting the answer phones of the AI voice robot according to the first communication results and the second communication results.
In this embodiment, the communication result in the first communication result and the second communication result is a user intention result or a user single result. Also, the statistics is performed by the human customer service after the number of voice communication times for observing the problem reaches a certain number, for example, 36 times.
At this time, if only one type of subjective questions is to be manually inserted, i.e., the type a described above, 36 answers all belong to the observation questions of the type a, and the subjective questions of the type are all prone to the second answer operation. In this embodiment, by summarizing the 36 observed communication results of the artificial customer service, a first communication result, for example, intentionally 3 and not intentionally 33, is obtained, so that the first communication result is intentionally 8.33% and the second communication result is 3.30% if the previous AI voice robot has the intentional and unintentional numbers of 6 and 176, respectively.
At this time, correcting the answer operation of the AI voice robot according to the first communication result and the second communication result includes the steps of:
s31, when the first communication result exceeds a first threshold value of the second communication result, directly correcting the user problem of the type from the adopted first answering operation to the second answering operation;
S32, when the first communication result exceeds the second communication result but is lower than a first threshold value, increasing the weight value of the second answering operation in the user problem of the type, and correspondingly decreasing the weight value of the first answering operation;
s33, when the first communication result is lower than the second communication result, the answer phone operation of the AI voice robot is maintained.
Wherein the first threshold is between 10% and 25% of expected. In this embodiment, 17% is expected, as described above, to be 5%, if the first threshold is 0.85%, if the first communication result is 8.33% greater than the second communication result by 3.30% and if the first communication result is 5.03%, then the first threshold is 0.85%, so that the type a answer phone operation is directly modified from the first answer phone operation to the second answer phone operation.
If the first communication result is 3.50%, only exceeds 0.2%, at this time, the weight value of the second answer is increased, and the increasing portion may refer to the exceeding value, for example, the weight value difference between the first answer and the second answer is set to a, the first threshold is set to b, the current exceeding value is c, the value h= (a×c)/(2*b) is adjusted, at this time, the difference a between the weight value 0.6 of the first answer and the weight value 0.3 of the second answer is 0.3, the adjusted value h= (0.3×0.2%)/(2×0.85%) = 0.035), the adjusted weight value of the first answer is reduced to 0565, and the weight value of the second answer is increased to 0.335.
In this embodiment, if the manual service has no tendency, the second answering method is replaced by the alternative answering method. At this time, the communication record of the AI voice robot has no corresponding second communication result, so the second communication result is set as the overall communication result of the current promotion product, such as 3% as described above, otherwise the same as described above.
In summary, through the intervention of the manual customer service, the benefit improvement generated by the intervention of the manual customer service on the result of the sales promotion of the whole product is ensured to be maximized, and meanwhile, the answer operation of the AI voice robot is automatically corrected and supplemented, so that the answer operation of the AI voice robot is more in accordance with the interaction logic, and the communication result of the electric sales is improved.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third, etc. are for convenience of description only and do not denote any order. These terms may be understood as part of the component name.
Furthermore, it should be noted that in the description of the present specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with the embodiment or example being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art upon learning the basic inventive concepts. Therefore, the appended claims should be construed to include preferred embodiments and all such variations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, the present invention should also include such modifications and variations provided that they come within the scope of the following claims and their equivalents.
Claims (9)
1. An electrical pinning method in combination with AI speech, comprising the steps of:
Acquiring user problems related to user voice content, judging whether the user problems are objective problems, if so, carrying out voice communication by an AI voice robot, otherwise, marking the user problems as observation problems when manual customer service is in an idle state, and switching the user problems into the manual customer service to carry out voice communication of the observation problems;
When the artificial customer service carries out voice communication of the observation problem, the AI voice robot carries out simulated communication of the observation problem at the same time, a first answering operation adopted by the simulated communication is obtained, a second answering operation that whether the artificial customer service has a tendency to the voice communication of the observation problem or not is judged, and if yes, the second answering operation and a corresponding observation communication result are recorded;
And respectively summarizing observation communication results of the same type of observation questions on different answer surgeries by the artificial customer service to obtain first communication results of each type of observation questions on different answer surgeries by the artificial customer service, obtaining second communication results corresponding to the first answer surgeries used by the same type of observation questions by the AI voice robot in the same promotion product, and correcting the answer surgeries of the AI voice robot according to the first communication results and the second communication results.
2. The AI-voice-combined electric marketing method of claim 1, wherein the acquiring the user questions related to the user voice content comprises the steps of:
And monitoring the overall communication result of the current promotion product in real time, judging whether the overall communication result is lower than expected, if yes, acquiring user problems related to user voice contents, otherwise, carrying out voice communication on the user voice contents by an AI voice robot.
3. The method for electric marketing in combination with AI speech according to claim 2, further comprising determining a subjective question to be manually interposed when the overall communication result is lower than expected, wherein in step S1, otherwise, when the manual service is in an idle state, specifically:
otherwise, judging whether the user problem is a subjective problem to be manually intervened, if so, and if the manual customer service is in an idle state.
4. The AI-voice-combined electric marketing method of claim 1, wherein the correcting the answer sheet of the AI-voice robot based on the first communication result and the second communication result comprises the steps of:
when the first communication result exceeds the first threshold value of the second communication result, directly correcting the user problem of the type from the adopted first answering operation to the second answering operation;
When the first communication result exceeds the second communication result but is lower than the first threshold, the weight value of the second answering operation in the user problems of the type is increased, and the weight value of the first answering operation is correspondingly reduced;
and when the first communication result is lower than the second communication result, maintaining the answer phone operation of the AI voice robot.
5. The AI speech-combined electrical pinning method of claim 4, wherein the first threshold is from 10% to 25% of expected.
6. The AI-voice-incorporated electric pinning method of claim 1, further comprising the step of:
If the voice communication of the artificial customer service to the observation problem does not accord with all preset answering methods, an alternative answering method is added.
7. The AI speech-combined electric pinning method according to any one of claims 1 to 6, characterized by further comprising the step of:
When the manual customer service is busy, the AI voice robot performs voice communication of subjective questions.
8. The AI-voice-combined electric marketing method of any of claims 1 to 6, wherein the communication result of the first communication result and the second communication result is a user intent result or a user singleness result.
9. The AI speech-combined electric pinning method of any of claims 1-6, wherein the AI speech robot generates a pronunciation for training based on a corresponding human customer service.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410358749.7A CN117956082B (en) | 2024-03-27 | 2024-03-27 | Electric marketing method combined with AI voice |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410358749.7A CN117956082B (en) | 2024-03-27 | 2024-03-27 | Electric marketing method combined with AI voice |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117956082A CN117956082A (en) | 2024-04-30 |
CN117956082B true CN117956082B (en) | 2024-06-07 |
Family
ID=90804103
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410358749.7A Active CN117956082B (en) | 2024-03-27 | 2024-03-27 | Electric marketing method combined with AI voice |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117956082B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019098409A1 (en) * | 2017-11-15 | 2019-05-23 | (주)페르소나시스템 | Machine learning based data adding device for chatbot |
CN111428023A (en) * | 2020-03-26 | 2020-07-17 | 支付宝(杭州)信息技术有限公司 | Method and device for recommending dialect and electronic equipment |
CN111881254A (en) * | 2020-06-10 | 2020-11-03 | 百度在线网络技术(北京)有限公司 | Method and device for generating dialogs, electronic equipment and storage medium |
CN112685297A (en) * | 2020-12-25 | 2021-04-20 | 科讯嘉联信息技术有限公司 | Automatic testing method for telephone service robot dialect process |
CN114297365A (en) * | 2022-03-04 | 2022-04-08 | 广东联讯科技发展股份有限公司 | Intelligent customer service system and method based on Internet |
CN114554018A (en) * | 2022-02-24 | 2022-05-27 | 南通安米信息科技有限公司 | Intelligent cloud call management center system |
CN115525750A (en) * | 2022-10-13 | 2022-12-27 | 深圳壹账通智能科技有限公司 | Robot phonetics detection visualization method and device, electronic equipment and storage medium |
CN117221451A (en) * | 2023-09-27 | 2023-12-12 | 杭州龙席网络科技股份有限公司 | Customer service response system and method based on artificial intelligence |
CN117333277A (en) * | 2023-10-25 | 2024-01-02 | 中信银行股份有限公司 | Service processing method, device, equipment and storage medium |
-
2024
- 2024-03-27 CN CN202410358749.7A patent/CN117956082B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019098409A1 (en) * | 2017-11-15 | 2019-05-23 | (주)페르소나시스템 | Machine learning based data adding device for chatbot |
CN111428023A (en) * | 2020-03-26 | 2020-07-17 | 支付宝(杭州)信息技术有限公司 | Method and device for recommending dialect and electronic equipment |
CN111881254A (en) * | 2020-06-10 | 2020-11-03 | 百度在线网络技术(北京)有限公司 | Method and device for generating dialogs, electronic equipment and storage medium |
CN112685297A (en) * | 2020-12-25 | 2021-04-20 | 科讯嘉联信息技术有限公司 | Automatic testing method for telephone service robot dialect process |
CN114554018A (en) * | 2022-02-24 | 2022-05-27 | 南通安米信息科技有限公司 | Intelligent cloud call management center system |
CN114297365A (en) * | 2022-03-04 | 2022-04-08 | 广东联讯科技发展股份有限公司 | Intelligent customer service system and method based on Internet |
CN115525750A (en) * | 2022-10-13 | 2022-12-27 | 深圳壹账通智能科技有限公司 | Robot phonetics detection visualization method and device, electronic equipment and storage medium |
CN117221451A (en) * | 2023-09-27 | 2023-12-12 | 杭州龙席网络科技股份有限公司 | Customer service response system and method based on artificial intelligence |
CN117333277A (en) * | 2023-10-25 | 2024-01-02 | 中信银行股份有限公司 | Service processing method, device, equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
基于人工智能的电网调度操作智能防误***建设及实践;蔡新雷;齐颖;;电力大数据;20200421(04);全文 * |
电力客服聊天机器人知识库快速更新方法研究;应君裕;李凡;温兵兵;廖玉坤;刘奕;;计算机产品与流通;20200519(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117956082A (en) | 2024-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9571650B2 (en) | Method and system for generating a responsive communication based on behavioral assessment data | |
CN107343077A (en) | Identify malicious call and establish the method, apparatus of identification model, equipment | |
CN107886949A (en) | A kind of content recommendation method and device | |
CN105206269A (en) | Voice processing method and device | |
RU2007108794A (en) | MACHINE TRAINING | |
US7783027B2 (en) | Computer-readable recording medium having recorded therein agent training support program, and agent training support method and agent training support apparatus | |
CN107784033A (en) | A kind of dialogue-based method and apparatus recommended | |
CN110401780A (en) | A kind of method and device identifying fraudulent call | |
CN103366760A (en) | Method, device and system for data processing | |
CN108257600B (en) | Voice processing method and device | |
JP2015186018A (en) | Communication apparatus, operator selection method and program | |
CN117956082B (en) | Electric marketing method combined with AI voice | |
CN106356056B (en) | Audio recognition method and device | |
CN117240964B (en) | Voice recognition method in call process | |
CN110781340A (en) | Offline evaluation method, system and device for recall strategy of recommendation system and storage medium | |
CN116303978B (en) | Potential user mining method based on voice analysis | |
CN113408880A (en) | Test paper generation method and device and intelligent examination system | |
CN113572903A (en) | Call center man-machine coupling coordination method, device, equipment and storage medium | |
CN116030788B (en) | Intelligent voice interaction method and device | |
CN106911832A (en) | A kind of method and device of voice record | |
CN109773806A (en) | A kind of electricity Xiao AI robot based on artificial intelligence | |
CN114363467A (en) | Method for dynamically correcting silent time in robot outbound call | |
CN112422756A (en) | Automatic intelligent dialing method and device and computer readable storage medium | |
CN110415015A (en) | Product degree of recognition analysis method, device, terminal and computer readable storage medium | |
CN112714217A (en) | Telephone traffic quality inspection method, device, storage medium and server |
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 |