CN107800900B - Call data processing method and device, storage medium and computer equipment - Google Patents
Call data processing method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN107800900B CN107800900B CN201710612991.2A CN201710612991A CN107800900B CN 107800900 B CN107800900 B CN 107800900B CN 201710612991 A CN201710612991 A CN 201710612991A CN 107800900 B CN107800900 B CN 107800900B
- Authority
- CN
- China
- Prior art keywords
- words
- word
- feature
- feature word
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/523—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
- H04M3/5232—Call distribution algorithms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention relates to a call data processing method, a device, a storage medium and computer equipment, wherein the method comprises the following steps: acquiring user voice data in historical voice conversation according to a time period; segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set; acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word; determining the difference value between the ratio acquired by each feature word in the current time period and the ratio acquired in the historical time period before the current time period; selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words; and distributing corresponding special communication channels for the selected feature words. The scheme provided by the application improves the efficiency of telephone interaction.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for processing call data, a storage medium, and a computer device.
Background
With the development of computer technology, it is more and more common to use telephone to interact with telephone service staff and to implement various types of business handling and consultation through remote conversation. However, in the conventional manual interaction, after the user needs to communicate with the telephone service staff, the user actively informs the telephone service staff of the own needs, and the service staff passively handles the relevant services for the user according to the voice content of the user, so that the efficiency of the telephone interaction is low.
Disclosure of Invention
Based on this, it is necessary to provide a call data processing method, device, storage medium and computer equipment for solving the problem of low efficiency of telephone interaction in the conventional manual interaction.
A method of call data processing, the method comprising:
acquiring user voice data in historical voice conversation according to a time period;
segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set;
acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word;
determining the difference value between the ratio acquired by each feature word in the current time period and the ratio acquired in the historical time period before the current time period;
selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words;
and distributing corresponding special communication channels for the selected feature words.
In one embodiment, the segmenting the conversation text obtained by recognizing the user voice data into the feature word set includes:
segmenting words of a conversation text obtained by recognizing the user voice data to obtain single words;
classifying the individual words according to the semantics of the individual words to obtain individual word subsets;
selecting the individual word with the highest occurrence frequency in each individual word subset as a feature word to obtain a feature word set;
the obtaining of the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word includes:
for each feature word in the feature word set, acquiring the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word;
and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
In one embodiment, the method further comprises:
collecting historical service data corresponding to each agent identifier;
determining the correlation between the historical service data of each agent identifier and the selected feature words;
sorting the corresponding agent identifications in a descending order according to the correlation degree;
selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers;
and associating the seat terminal corresponding to the selected seat identifier to the special communication channel.
In one embodiment, the method further comprises:
after establishing communication connection with a user terminal, sending voice guide information to the user terminal;
receiving a special communication channel selected by the user terminal according to the guide information in real time;
and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
In one embodiment, the method further comprises:
determining the service type of the selected feature word;
acquiring service knowledge information from a service database corresponding to the service type;
generating a response template corresponding to the service type according to the service knowledge information;
and sending the response template to the seat terminal corresponding to the selected seat identifier.
A call data processing apparatus, the apparatus comprising:
the first acquisition module is used for acquiring user voice data in historical voice conversation according to a time period;
the word segmentation module is used for segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set;
the second acquisition module is used for acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word;
the determining module is used for determining the difference value between the proportion of each feature word acquired in the current time period and the proportion of each feature word acquired in the historical time period before the current time period;
the selecting module is used for selecting the feature words of which the corresponding determined difference values are larger than the preset difference values and are inconsistent with the preset words;
and the distribution module is used for distributing corresponding special communication channels for the selected feature words.
In one embodiment, the word segmentation module is further configured to segment a conversation text obtained by recognizing the user voice data to obtain an individual word; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; selecting the individual word with the highest occurrence frequency in each individual word subset as a feature word to obtain a feature word set;
the second obtaining module is further used for obtaining the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word for each feature word in the feature word set; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
In one embodiment, the apparatus further comprises:
the correlation module is used for collecting historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; and associating the seat terminal corresponding to the selected seat identifier to the special communication channel.
A computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a processor, cause the processor to perform the steps of:
acquiring user voice data in historical voice conversation according to a time period;
segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set;
acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word;
determining the difference value between the ratio acquired by each feature word in the current time period and the ratio acquired in the historical time period before the current time period;
selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words;
and distributing corresponding special communication channels for the selected feature words.
A computer device comprising a memory and a processor, the memory having stored therein computer-executable instructions that, when executed by the processor, cause the processor to perform the steps of:
acquiring user voice data in historical voice conversation according to a time period;
segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set;
acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word;
determining the difference value between the ratio acquired by each feature word in the current time period and the ratio acquired in the historical time period before the current time period;
selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words;
and distributing corresponding special communication channels for the selected feature words.
According to the call data processing method, the call data processing device, the storage medium and the computer equipment, the feature words representing the user requirements are extracted from the user voice data of the user in the historical voice conversation according to the time period, the ratio of the occurrence times of the feature words to the sum of the occurrence times of the feature words is obtained, and the difference value between the ratio obtained by the feature words in the current time period and the ratio obtained in the historical time period before the current time period is determined. When the corresponding difference value of the feature word is larger than the preset difference value and is inconsistent with the preset word, the fact that the traffic related to the feature word is increased obviously in the near term is judged, and the special communication channel is automatically allocated to the feature word, so that the information of the service related to the feature word can be actively provided for the user through the allocated special communication channel, and the efficiency of telephone interaction is improved.
Drawings
FIG. 1 is a diagram of an exemplary application environment for a method for call data processing;
FIG. 2 is a schematic diagram showing an internal configuration of a computer device according to an embodiment;
FIG. 3 is a flow diagram illustrating a method for call data processing according to one embodiment;
FIG. 4 is a flow chart illustrating a method for processing call data according to another embodiment;
FIG. 5 is a block diagram showing the structure of a call data processing apparatus according to an embodiment;
fig. 6 is a block diagram showing a structure of a call data processing apparatus according to another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 is a diagram of an application environment of a call data processing method according to an embodiment. Referring to fig. 1, the call data processing method is applied to a call data processing system. The call data processing system comprises a user terminal 110, a server 120 and an agent terminal 130, wherein both the user terminal 110 and the agent terminal 130 can communicate with the server 120 through a network. The user terminal 110 may be a mobile terminal used by a user or a fixed call terminal. The server 120 may be an independent physical server or a server cluster including a plurality of physical servers. The agent terminals 130 are fixed call terminals, and each agent terminal corresponds to a fixed artificial agent. The plurality of seat terminals correspond to one special communication channel. The server 120 extracts feature words representing user requirements from user voice data of a user in a historical voice conversation according to a time period, obtains the ratio of the occurrence times of the feature words to the sum of the occurrence times of the feature words, and allocates a special call channel for the feature words of which the difference between the ratio obtained in the current time period and the ratio obtained in the historical time period before the current time period is greater than a preset difference and is inconsistent with the preset word, so that the user can enjoy services such as consultation, service handling and the like provided by a staff member.
FIG. 2 is a diagram showing an internal configuration of a computer device according to an embodiment. The computer device may be the server 120 of fig. 1. As shown in fig. 2, the computer apparatus includes a processor, a nonvolatile storage medium, an internal memory, and a network interface, which are connected by a system bus. Wherein the non-volatile storage medium of the computer device may store an operating system and computer-executable instructions that, when executed, may cause the processor to perform a call data processing method. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole computer device. The internal memory may store computer-executable instructions, which when executed by the processor, are configured to implement a call data processing method provided in the following embodiments. The computer equipment can also be connected with the user terminal and/or the seat terminal through a network to receive voice data sent by the user terminal and/or the seat terminal. Those skilled in the art will appreciate that the configuration shown in fig. 2 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation on the terminal to which the present application is applied, and that a particular terminal may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
As shown in fig. 3, in one embodiment, a call data processing method is provided. The embodiment is mainly illustrated by applying the method to the server 120 in fig. 1. Referring to fig. 3, the call data processing method specifically includes the following steps:
s302, acquiring user voice data in historical voice conversation according to a time period.
The voice conversation is a conversation of voice answering between the agent personnel and the user. The user voice data is voice data of the user generated during a voice conversation. A historical voice session is a voice session that has occurred. A time period refers to a period during which data acquisition is performed, such as one or more days, weeks, or months.
Specifically, after the server makes a time period, it determines whether the current time reaches a periodic time point corresponding to the time period. Periodic time points such as a preset time of day or a preset day of the month. The server acquires user voice data in the historical voice conversation when the server judges that the next time reaches the periodic time point. The user voice data is stored in a database, a file or a cache of the server.
In one embodiment, the user terminal can establish a voice session with the server through a telephone network by dialing the service number, collect voice data generated by the user in the voice session, and send the collected voice data of the user to the server through the telephone network. The server may store the received user voice data in a database, cache, or file for reading when needed.
In one embodiment, the user terminal may also establish an internet connection with the server by a network request for initiating a voice session, thereby establishing an internet-based voice session, collect voice data generated by the user in the voice session, and send the collected voice data of the user to the server through the internet. The server may store the received user voice data in a database, cache, or file for reading when needed.
S304, segmenting the conversation text obtained by recognizing the voice data of the user to obtain a feature word set.
Where word segmentation refers to the segmentation of a continuous sequence of characters into individual characters or character sequences. The characteristic word refers to a character or a character sequence with a semantic expression function.
Specifically, the server can perform feature extraction on user voice data to obtain user voice feature data to be recognized, then perform voice framing processing on the user voice feature data to be recognized based on an acoustic model to obtain a plurality of phonemes, convert the plurality of phonemes obtained through processing into character sequences according to the corresponding relation between candidate words and phonemes in the candidate word library, and then adjust the converted character sequences by using a language model, so as to obtain a conversation text conforming to a natural language mode.
Further, the server may perform word segmentation processing on the session text by using a preset word segmentation mode to obtain a plurality of characters or character sequences, and screen out characters or character sequences with actual semantics from the obtained character sequences as feature words to form a feature word set. The feature word set may include one or more feature words. The preset word segmentation mode can be a word segmentation mode based on character matching, semantic understanding or statistics.
Furthermore, when the server screens out characters or character sequences with actual semantics from the obtained characters or character sequences as the feature words, the server can specifically filter out stop words from the obtained characters or character sequences. The stop word refers to a functional character or a character sequence included in a natural language, and such functional character or character sequence has no actual semantics, and includes a tone character or a character sequence representing a tone, a connection character or a character sequence representing a certain logical relationship, and the like. Specifically, a mood character such as "Dome" or "West", etc., a connection character such as "what" or "on", etc., a mood character sequence such as "what" or "what" etc., a connection character sequence such as "to" or "then", etc.
S306, obtaining the ratio of the occurrence times of all the characteristic words in the characteristic word set to the sum of the occurrence times of all the characteristic words.
Wherein the occurrence frequency of the feature words is the occurrence frequency of the feature words in the conversation text recognized by the user voice data. Specifically, after segmenting words of a session text obtained by recognizing user voice data to obtain a feature word set, the server can count the occurrence times of each feature word in the feature word set in the session text obtained by recognizing the user voice data to obtain the occurrence times of each feature word, and then calculate to obtain the ratio of the occurrence times of each feature word to the sum of the occurrence times of each feature word.
For example, the feature word set includes three feature words, namely "health risk", "one-card" and "medical insurance". The number of occurrences of the feature word "health risk" in the session text recognized by the user voice data obtained in the current time period is 185 times, the number of occurrences of the feature word "one-card" in the session text recognized by the user voice data obtained in the current time period is 260 times, and the number of occurrences of the feature word "medical insurance" in the session text recognized by the user voice data obtained in the current time period is 97 times. 185/(185+160+97) ═ 41.86%.
S308, determining the difference value between the proportion of each feature word obtained in the current time period and the proportion of each feature word obtained in the historical time period before the current time period.
Specifically, the server may obtain, for each feature word in the feature word set obtained in the current time period, a ratio of the occurrence number to the sum of the occurrence numbers of the feature words in the current time period, and a ratio of the occurrence number to the sum of the occurrence numbers of the feature words in a historical time period before the current time period, and then calculate a difference between the two ratios. The historical time period before the current time period may be a previous time period adjacent to the current time period, or may be any time period before the current time period.
S310, selecting the feature words of which the corresponding determined difference values are larger than the preset difference values and are inconsistent with the preset words.
The preset difference is a difference between a preset ratio acquired by the feature words in the current time period and a ratio acquired in a historical time period before the current time period. The preset difference is configured as a condition for selecting a feature word for allocating the dedicated call channel. And when the difference value between the occupation ratio acquired by the characteristic word in the current time period and the occupation ratio acquired in the historical time period before the current time period is greater than a preset difference value, judging that the characteristic word meets the condition of being allocated with the special call channel. The preset words are preset feature words, and the server allocates corresponding special communication channels for the preset words.
Specifically, the server may determine, for each feature word in the feature word set obtained in the current time period, a difference between an occupation ratio of the feature word obtained in the current time period and an occupation ratio obtained in a historical time period before the current time period, compare the determined differences with a preset difference one by one, and screen out the feature words of which the corresponding determined differences are greater than the preset difference. The server can compare the screened feature words with the preset words and select the feature words inconsistent with the preset words.
And S312, distributing corresponding special communication channels for the selected feature words.
Wherein, the dedicated communication channel is a communication channel dedicated to a specific service. Such as a talk channel dedicated to health insurance or a talk channel dedicated to medical insurance. Specifically, the feature words selected by the server represent the important points recently focused by the user, and the server can allocate corresponding channels to the feature words after the feature words are selected, so that corresponding dedicated services are provided.
The call data processing method extracts the characteristic words representing the user requirements from the user voice data of the user in the historical voice conversation according to the time period, obtains the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words, and determines the difference value between the ratio of the characteristic words obtained in the current time period and the ratio obtained in the historical time period before the current time period. When the corresponding difference value of the feature word is larger than the preset difference value and is inconsistent with the preset word, the fact that the traffic related to the feature word is increased obviously in the near term is judged, and the special communication channel is automatically allocated to the feature word, so that the information of the service related to the feature word can be actively provided for the user through the allocated special communication channel, and the efficiency of telephone interaction is improved.
In one embodiment, step S304 includes: segmenting a conversation text obtained by recognizing user voice data to obtain an individual word; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; and selecting the individual word with the highest occurrence frequency in each individual word subset as the feature word to obtain the feature word set. Step S306 includes: for each feature word in the feature word set, acquiring the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
Where an individual word is a character or sequence of characters that represents a single semantic meaning.
In one embodiment, the server may perform word segmentation based on character matching, segment the session text one by one according to a sequence from front to back or from back to front, and match the single character with the standard lexicon. If the matching is successful, acquiring the character as a single word; and if the matching fails, continuing to match by adding one character until all characters included in the session text are matched.
In one embodiment, the server may also perform forward matching segmentation and reverse matching segmentation on the conversation text at the same time. And when the word segmentation results of the two word segmentation modes are the same, taking a plurality of independent characters or character sequences obtained by word segmentation as independent words. When the word segmentation results of the two word segmentation modes are different, the number of the independent characters or the character sequences obtained by the two word segmentation modes is calculated respectively, and the independent characters or the character sequences obtained by the word segmentation mode with the small calculated number are selected as the independent words.
Further, the server can determine the obtained semantics of each single word, divide the single words with the same semantics into the same class, and obtain a plurality of single word subsets. For each obtained individual word subset, the server can select the individual word with the highest occurrence frequency from the individual words as the feature word to represent the corresponding individual word subset, so as to obtain the feature word set. For each feature word in the feature word set, the server can select the sum of the occurrence times of each individual word in the individual word subset selected by each feature word as the occurrence times of each feature word because the individual words in each individual word subset belong to the same semantic; and calculating the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
In the embodiment, the individual words belonging to the same semantic meaning are divided into the same class, the individual word with the highest occurrence frequency is selected as a representative, then the characteristic words serving as the representative are selected from the individual word subset, and the sum of the occurrence frequencies of the individual words is used as the occurrence frequency of the characteristic word, so that the statistics of the occurrence frequency of the characteristic words is more reasonable, and the selected characteristic words can reflect the focus of recent attention of the user.
In one embodiment, the call data processing method further includes: collecting historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; and associating the agent terminal corresponding to the selected agent identifier to a special communication channel.
The seat identification is used for uniquely identifying one seat person. The agent identification may be a character string including at least one character of a number, a letter, and a symbol. The historical service data refers to online call records of online business consultation and business handling provided for the user by the seat personnel in historical time. The historical service data comprises the number of connected online calls, call records corresponding to each online call, user feedback and other data.
Specifically, the server may obtain historical service data corresponding to each agent identifier, and calculate a degree of correlation between the historical service data of each agent identifier and the selected feature word, so as to sort the corresponding agent identifiers according to the degree of correlation. And during sorting, sorting is performed according to descending order of the correlation degree, wherein the correlation degree is higher and the correlation degree is lower and higher. The server can select the seat identification from the sequenced seat identifications according to the preset percentage of the total amount of the sequenced seat identifications from the seat identification with the highest correlation. For example, if there are X seat identifiers in total, then the seat identifiers with X × 10% of the top rank are taken, and the preset proportion may be 10%. The server can associate the seat terminal corresponding to the selected seat identifier with the special communication channel corresponding to the selected feature word.
In this embodiment, based on the correlation between the historical service data of the agent identifier and the selected feature words, the agent terminal is associated with the dedicated communication channel allocated to the selected feature words, and the familiar agent personnel provide services for the user, thereby improving the efficiency of telephone interaction.
In one embodiment, the call data processing method further includes: after establishing communication connection with the user terminal, sending voice guide information to the user terminal; receiving a special call channel selected by the user terminal according to the guide information in real time; and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
The voice guidance information is information for guiding a user to select a service. For example, a health insurance consultation request performs XX, a universal insurance account inquiry request performs XX, and so on.
Specifically, the server may invoke the IVR system to send voice guidance information to the user terminal, the voice guidance information including voice prompt information for selection of the service type. The user terminal can play the voice prompt message and send the acquired operation information of the user to the server. After receiving the operation information sent by the user terminal, the server determines the corresponding characteristic words according to the corresponding relation between the preset operation information and the characteristic words, and establishes communication connection between the user terminal and the seat terminal corresponding to the special communication channel corresponding to the determined characteristic words.
In this embodiment, the server obtains the dedicated call channel selected by the user through the voice guidance information, and establishes a communication connection between the user terminal and the corresponding seat terminal of the dedicated call channel in real time, so as to connect to a professional seat person allocated to the dedicated call channel in real time to perform telephone interaction with the user, thereby improving the telephone interaction efficiency.
In one embodiment, the call data processing method further includes: determining the service type of the selected feature word; acquiring service knowledge information from a service database corresponding to the service type; generating a response template corresponding to the service type according to the service knowledge information; and sending the response template to the seat terminal corresponding to the selected seat identifier.
The service types comprise various credit card service types, banking service types, security service types, insurance service types and the like. The insurance business type can also comprise sub business types such as a life insurance business type, a health insurance business type, a continuous insurance business type and the like.
Specifically, the agent service database stores feature words of a plurality of service types. And setting the corresponding relation between each service type and one or more feature words, wherein the feature words having the corresponding relation with the service types are the feature words belonging to the service types. After determining the feature words selected by the user terminal, the server can determine the service types of the feature words according to the corresponding relation of the corresponding service types of the feature words.
Furthermore, the server also sets calling interfaces corresponding to the service database aiming at different service types, and allocates interface calling resources corresponding to the same or different quantities for different service types. After the service type is determined, the server can establish connection with the service database corresponding to the service type according to calling the interface corresponding to the service type.
Furthermore, the service database stores service knowledge information of the service type corresponding to the service database. The business knowledge information includes business related knowledge and knowledge information of questions and answers. The knowledge information comprises information such as a certain professional noun explanation, a calculation formula, a business process and the like. And after establishing connection with the service database corresponding to the service type, the server acquires service knowledge information from the service database. The server can generate a response template corresponding to the service type according to the service knowledge information and send the response template to the seat terminal corresponding to the selected seat identification.
In this embodiment, the service knowledge information and the response template related to the feature words are further automatically provided to the agent terminal, so that the agent personnel can improve the efficiency of obtaining answers to questions when needing to retrieve the related service knowledge information to answer the questions consulted by the user.
As shown in fig. 4, in a specific embodiment, the call data processing method includes the following steps:
s402, acquiring user voice data in the historical voice conversation according to the time period.
S404, segmenting words of a conversation text obtained by recognizing the voice data of the user to obtain single words; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; and selecting the individual word with the highest occurrence frequency in each individual word subset as the feature word to obtain the feature word set.
S406, for each feature word in the feature word set, obtaining the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
S408, determining the difference value between the proportion of each feature word obtained in the current time period and the proportion of each feature word obtained in the historical time period before the current time period.
S410, selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words; and distributing corresponding special communication channels for the selected feature words.
S412, collecting historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; and associating the agent terminal corresponding to the selected agent identifier to a special communication channel.
S414, determining the service type of the selected feature word; acquiring service knowledge information from a service database corresponding to the service type; generating a response template corresponding to the service type according to the service knowledge information; and sending the response template to the seat terminal corresponding to the selected seat identifier.
S416, after establishing communication connection with the user terminal, sending voice guide information to the user terminal; receiving a special call channel selected by the user terminal according to the guide information in real time; and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
In the embodiment, the characteristic words representing the user requirements are extracted from the user voice data of the user in the historical voice conversation according to the time period, the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words is obtained, and the difference value between the ratio of the characteristic words obtained in the current time period and the ratio of the characteristic words obtained in the historical time period before the current time period is determined. When the corresponding difference value of the feature word is larger than the preset difference value and is inconsistent with the preset word, the fact that the traffic related to the feature word is increased obviously in the near term is judged, and the special communication channel is automatically allocated to the feature word, so that the information of the service related to the feature word can be actively provided for the user through the allocated special communication channel, and the efficiency of telephone interaction is improved.
Secondly, the special communication channel allocated for the feature word is associated with the seat terminal corresponding to the seat personnel with high familiarity, and provides the inquired service knowledge information and the response template related to the feature word, so that when the seat personnel need to search the related service knowledge information to answer the question consulted by the user, the obtaining efficiency of the answer to the question is improved, and the efficiency of telephone interaction is further improved.
As shown in fig. 5, in one embodiment, a call data processing apparatus 500 is provided, the call data processing apparatus 500 including: the system comprises a first acquisition module 501, a word segmentation module 502, a second acquisition module 503, a determination module 504, a selection module 505 and an allocation module 506.
A first obtaining module 501, configured to obtain user voice data in a historical voice session according to a time period.
The word segmentation module 502 is configured to segment words of a session text obtained by recognizing voice data of a user to obtain a feature word set.
The second obtaining module 503 is configured to obtain a ratio of the occurrence number of each feature word in the feature word set to the sum of the occurrence number of each feature word.
A determining module 504, configured to determine a difference between the obtained proportion of each feature word in the current time period and the obtained proportion in the historical time period before the current time period.
And a selecting module 505, configured to select a feature word whose corresponding determined difference is greater than the preset difference and is inconsistent with the preset word.
And an allocating module 506, configured to allocate a corresponding dedicated communication channel to the selected feature word.
The call data processing apparatus 500 extracts feature words representing user requirements from user voice data of a user in a historical voice conversation according to a time period, obtains a ratio of the occurrence times of the feature words to the sum of the occurrence times of the feature words, and determines a difference between the ratio of the feature words obtained in the current time period and the ratio of the feature words obtained in the historical time period before the current time period. When the corresponding difference value of the feature word is larger than the preset difference value and is inconsistent with the preset word, the fact that the traffic related to the feature word is increased obviously in the near term is judged, and the special communication channel is automatically allocated to the feature word, so that the information of the service related to the feature word can be actively provided for the user through the allocated special communication channel, and the efficiency of telephone interaction is improved.
In one embodiment, the word segmentation module 502 is further configured to segment a conversation text obtained by recognizing the user voice data to obtain an individual word; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; and selecting the individual word with the highest occurrence frequency in each individual word subset as the feature word to obtain the feature word set. The second obtaining module 503 is further configured to obtain, for each feature word in the feature word set, a sum of occurrence times of each individual word in the subset of individual words selected by the current feature word as an occurrence time of the current feature word; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
In this embodiment, the individual words belonging to the same semantic meaning are divided into the same category, the individual word with the highest occurrence frequency is selected as a representative, then the characteristic words serving as the representative are selected from the individual word subset, and the sum of the occurrence frequencies of the individual words is used as the occurrence frequency of the characteristic word, so that the statistics of the occurrence frequencies of the characteristic words is more reasonable, and the selected characteristic words can reflect the focus of recent attention of the user.
As shown in fig. 6, in one embodiment, the call data processing apparatus 500 further includes: and an association module 507.
The association module 507 is configured to collect historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; and associating the agent terminal corresponding to the selected agent identifier to a special communication channel.
In this embodiment, based on the correlation between the historical service data of the agent identifier and the selected feature words, the agent terminal is associated with the dedicated communication channel allocated to the selected feature words, and the familiar agent personnel provide services for the user, thereby improving the efficiency of telephone interaction.
In one embodiment, the association module 507 is further configured to send voice guidance information to the user terminal after establishing a communication connection with the user terminal; receiving a special call channel selected by the user terminal according to the guide information in real time; and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
In this embodiment, the server obtains the dedicated call channel selected by the user through the voice guidance information, and establishes a communication connection between the user terminal and the corresponding seat terminal of the dedicated call channel in real time, so as to connect to a professional seat person allocated to the dedicated call channel in real time to perform telephone interaction with the user, thereby improving the telephone interaction efficiency.
In one embodiment, the association module 507 is further configured to determine a service type to which the selected feature word belongs; acquiring service knowledge information from a service database corresponding to the service type; generating a response template corresponding to the service type according to the service knowledge information; and sending the response template to the seat terminal corresponding to the selected seat identifier.
In this embodiment, the service knowledge information and the response template related to the feature words are further automatically provided to the agent terminal, so that the agent personnel can improve the efficiency of obtaining answers to questions when needing to retrieve the related service knowledge information to answer the questions consulted by the user.
In one embodiment, a computer-readable storage medium having computer-executable instructions stored thereon that, when executed by a processor, cause the processor to perform the steps of: acquiring user voice data in historical voice conversation according to a time period; segmenting words of a session text obtained by recognizing user voice data to obtain a feature word set; acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word; determining the difference value between the proportion of each feature word obtained in the current time period and the proportion of each feature word obtained in the historical time period before the current time period; selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words; and distributing corresponding special communication channels for the selected feature words.
In one embodiment, segmenting a conversational text obtained by recognizing speech data of a user to obtain a feature word set comprises: segmenting a conversation text obtained by recognizing user voice data to obtain an individual word; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; and selecting the individual word with the highest occurrence frequency in each individual word subset as the feature word to obtain the feature word set. Obtaining the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word, wherein the ratio comprises the following steps: for each feature word in the feature word set, acquiring the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
In one embodiment, the computer executable instructions, when executed by the processor, further cause the processor to perform the steps of: collecting historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; and associating the agent terminal corresponding to the selected agent identifier to a special communication channel.
In one embodiment, the computer executable instructions, when executed by the processor, further cause the processor to perform the steps of: after establishing communication connection with the user terminal, sending voice guide information to the user terminal; receiving a special call channel selected by the user terminal according to the guide information in real time; and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
In one embodiment, the computer executable instructions, when executed by the processor, further cause the processor to perform the steps of: determining the service type of the selected feature word; acquiring service knowledge information from a service database corresponding to the service type; generating a response template corresponding to the service type according to the service knowledge information; and sending the response template to the seat terminal corresponding to the selected seat identifier.
The storage medium extracts feature words representing user requirements from user voice data of a user in a historical voice conversation according to a time period, obtains the proportion of the occurrence times of the feature words to the sum of the occurrence times of the feature words, and determines the difference value between the proportion of the feature words obtained in the current time period and the proportion of the feature words obtained in the historical time period before the current time period. When the corresponding difference value of the feature word is larger than the preset difference value and is inconsistent with the preset word, the fact that the traffic related to the feature word is increased obviously in the near term is judged, and the special communication channel is automatically allocated to the feature word, so that the information of the service related to the feature word can be actively provided for the user through the allocated special communication channel, and the efficiency of telephone interaction is improved.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein computer-executable instructions that, when executed by the processor, cause the processor to perform the steps of: acquiring user voice data in historical voice conversation according to a time period; segmenting words of a session text obtained by recognizing user voice data to obtain a feature word set; acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word; determining the difference value between the proportion of each feature word obtained in the current time period and the proportion of each feature word obtained in the historical time period before the current time period; selecting feature words of which the corresponding determined difference values are larger than a preset difference value and are inconsistent with the preset words; and distributing corresponding special communication channels for the selected feature words.
In one embodiment, segmenting a conversational text obtained by recognizing speech data of a user to obtain a feature word set comprises: segmenting a conversation text obtained by recognizing user voice data to obtain an individual word; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; and selecting the individual word with the highest occurrence frequency in each individual word subset as the feature word to obtain the feature word set. Obtaining the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word, wherein the ratio comprises the following steps: for each feature word in the feature word set, acquiring the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
In one embodiment, the computer executable instructions, when executed by the processor, further cause the processor to perform the steps of: collecting historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; and associating the agent terminal corresponding to the selected agent identifier to a special communication channel.
In one embodiment, the computer executable instructions, when executed by the processor, further cause the processor to perform the steps of: after establishing communication connection with the user terminal, sending voice guide information to the user terminal; receiving a special call channel selected by the user terminal according to the guide information in real time; and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
In one embodiment, the computer executable instructions, when executed by the processor, further cause the processor to perform the steps of: determining the service type of the selected feature word; acquiring service knowledge information from a service database corresponding to the service type; generating a response template corresponding to the service type according to the service knowledge information; and sending the response template to the seat terminal corresponding to the selected seat identifier.
The computer device extracts the characteristic words representing the user requirements from the user voice data of the user in the historical voice conversation according to the time period, obtains the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words, and determines the difference value between the ratio of the characteristic words obtained in the current time period and the ratio of the characteristic words obtained in the historical time period before the current time period. When the corresponding difference value of the feature word is larger than the preset difference value and is inconsistent with the preset word, the fact that the traffic related to the feature word is increased obviously in the near term is judged, and the special communication channel is automatically allocated to the feature word, so that the information of the service related to the feature word can be actively provided for the user through the allocated special communication channel, and the efficiency of telephone interaction is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), or the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method of call data processing, the method comprising:
acquiring user voice data in historical voice conversation according to a time period;
segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set;
acquiring the ratio of the occurrence times of each feature word in the feature word set to the sum of the occurrence times of each feature word in each time period;
determining the difference value between the ratio acquired by each feature word in the current time period and the ratio acquired in the historical time period before the current time period;
selecting a feature word of which the corresponding determined difference is greater than a preset difference and is inconsistent with a preset word, wherein the preset word is a preset feature word, and the server allocates a corresponding special communication channel for the preset word;
distributing corresponding special communication channels for the selected feature words;
the method further comprises the following steps:
collecting historical service data corresponding to each agent identifier;
determining the correlation between the historical service data of each agent identifier and the selected feature words;
sorting the corresponding agent identifications in a descending order according to the correlation degree;
selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers;
associating the agent terminal corresponding to the selected agent identifier to the special communication channel, wherein each agent terminal corresponds to a fixed artificial agent;
the segmenting of the conversation text obtained by recognizing the user voice data to obtain a feature word set comprises the following steps:
segmenting words of a conversation text obtained by recognizing the user voice data to obtain single words;
classifying the individual words according to the semantics of the individual words to obtain individual word subsets;
selecting the individual word with the highest occurrence frequency in each individual word subset as a feature word to obtain a feature word set;
the obtaining of the ratio of the occurrence times of the characteristic words in the characteristic word set to the sum of the occurrence times of the characteristic words in each time period includes:
for each feature word in the feature word set, acquiring the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word;
and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
2. The method of claim 1, further comprising:
after establishing communication connection with a user terminal, sending voice guide information to the user terminal;
receiving a special communication channel selected by the user terminal according to the guide information in real time;
and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
3. The method of claim 1, further comprising:
determining the service type of the selected feature word;
acquiring service knowledge information from a service database corresponding to the service type;
generating a response template corresponding to the service type according to the service knowledge information;
and sending the response template to the seat terminal corresponding to the selected seat identifier.
4. A call data processing apparatus, the apparatus comprising:
the first acquisition module is used for acquiring user voice data in historical voice conversation according to a time period;
the word segmentation module is used for segmenting words of a session text obtained by recognizing the user voice data to obtain a feature word set;
the second acquisition module is used for acquiring the ratio of the occurrence times of all the characteristic words in the characteristic word set to the sum of the occurrence times of all the characteristic words in all the time periods;
the determining module is used for determining the difference value between the proportion of each feature word acquired in the current time period and the proportion of each feature word acquired in the historical time period before the current time period;
the selecting module is used for selecting the feature words of which the corresponding determined difference values are larger than the preset difference values and are inconsistent with the preset words, the preset words are preset feature words, and the server allocates corresponding special communication channels for the preset words;
the distribution module is used for distributing corresponding special communication channels for the selected feature words;
the correlation module is used for collecting historical service data corresponding to each agent identifier; determining the correlation between the historical service data of each agent identifier and the selected feature words; sorting the corresponding agent identifications in a descending order according to the correlation degree; selecting seat identifiers with a preset proportion from the head of the sequenced seat identifiers; associating the agent terminal corresponding to the selected agent identifier to the special communication channel, wherein each agent terminal corresponds to a fixed artificial agent;
the word segmentation module is also used for segmenting a conversation text obtained by recognizing the user voice data to obtain an individual word; classifying the individual words according to the semantics of the individual words to obtain individual word subsets; selecting the individual word with the highest occurrence frequency in each individual word subset as a feature word to obtain a feature word set;
the second obtaining module is further used for obtaining the sum of the occurrence times of each individual word in the individual word subset selected by the current feature word as the occurrence times of the current feature word for each feature word in the feature word set; and determining the ratio of the occurrence times of the characteristic words to the sum of the occurrence times of the characteristic words.
5. The device for processing call data according to claim 4, wherein the association module is further configured to send voice guidance information to the user terminal after establishing a communication connection with the user terminal; receiving a special communication channel selected by the user terminal according to the guide information in real time; and establishing communication connection between the user terminal and the seat terminal corresponding to the selected special communication channel.
6. The call data processing apparatus according to claim 4, wherein the association module is further configured to determine a service type to which the selected feature word belongs; acquiring service knowledge information from a service database corresponding to the service type; generating a response template corresponding to the service type according to the service knowledge information; and sending the response template to the seat terminal corresponding to the selected seat identifier.
7. A computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a processor, cause the processor to perform the steps of the method of any one of claims 1 to 3.
8. A computer device comprising a memory and a processor, the memory having stored therein computer-executable instructions that, when executed by the processor, cause the processor to perform the steps of the method of any one of claims 1 to 3.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612991.2A CN107800900B (en) | 2017-07-25 | 2017-07-25 | Call data processing method and device, storage medium and computer equipment |
| PCT/CN2018/087327 WO2019019778A1 (en) | 2017-07-25 | 2018-05-17 | Method and apparatus for processing call data, storage medium and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612991.2A CN107800900B (en) | 2017-07-25 | 2017-07-25 | Call data processing method and device, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107800900A CN107800900A (en) | 2018-03-13 |
| CN107800900B true CN107800900B (en) | 2020-08-28 |
Family
ID=61531124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710612991.2A Active CN107800900B (en) | 2017-07-25 | 2017-07-25 | Call data processing method and device, storage medium and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107800900B (en) |
| WO (1) | WO2019019778A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107800900B (en) * | 2017-07-25 | 2020-08-28 | 平安科技（深圳）有限公司 | Call data processing method and device, storage medium and computer equipment |
| CN109543177B (en) * | 2018-10-19 | 2022-04-12 | 中国平安人寿保险股份有限公司 | Message data processing method and device, computer equipment and storage medium |
| CN111901554B (en) * | 2020-07-27 | 2022-11-11 | 中国平安人寿保险股份有限公司 | Call channel construction method and device based on semantic clustering and computer equipment |
| CN113129866B (en) * | 2021-04-13 | 2022-08-02 | 重庆度小满优扬科技有限公司 | Voice processing method, device, storage medium and computer equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015047272A1 (en) * | 2013-09-26 | 2015-04-02 | Interactive Intelligence, Inc. | System and method for context based knowledge retrieval |
| US9036806B1 (en) * | 2014-08-27 | 2015-05-19 | Xerox Corporation | Predicting the class of future customer calls in a call center |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101094271A (en) * | 2007-07-20 | 2007-12-26 | 华为技术有限公司 | Method and device for creating menu of automatic voice responsion system |
| CN104375847B (en) * | 2013-08-14 | 2017-12-05 | 华为技术有限公司 | Identify the method and device of type of service |
| CN104598632B (en) * | 2015-02-05 | 2017-12-01 | 北京航空航天大学 | Focus incident detection method and device |
| CN107800900B (en) * | 2017-07-25 | 2020-08-28 | 平安科技（深圳）有限公司 | Call data processing method and device, storage medium and computer equipment |
-
2017
- 2017-07-25 CN CN201710612991.2A patent/CN107800900B/en active Active
-
2018
- 2018-05-17 WO PCT/CN2018/087327 patent/WO2019019778A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015047272A1 (en) * | 2013-09-26 | 2015-04-02 | Interactive Intelligence, Inc. | System and method for context based knowledge retrieval |
| US9036806B1 (en) * | 2014-08-27 | 2015-05-19 | Xerox Corporation | Predicting the class of future customer calls in a call center |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107800900A (en) | 2018-03-13 |
| WO2019019778A1 (en) | 2019-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107800900B (en) | Call data processing method and device, storage medium and computer equipment | |
| US10057419B2 (en) | Intelligent call screening | |
| CN107798032B (en) | Method and device for processing response message in self-service voice conversation | |
| RU2383938C2 (en) | Improved calling subscriber identification based on speech recognition | |
| CN110751943A (en) | Voice emotion recognition method and device and related equipment | |
| CN110610705B (en) | Voice interaction prompter based on artificial intelligence | |
| CN104185868A (en) | Voice authentication and speech recognition system and method | |
| CN111833871A (en) | Intelligent outbound system based on intention recognition and method thereof | |
| CN109254669A (en) | A kind of expression picture input method, device, electronic equipment and system | |
| CN111212191B (en) | Customer incoming call seat distribution method | |
| CN103514165A (en) | Method and device for identifying persons mentioned in conversation | |
| CN110516057B (en) | Petition question answering method and device | |
| CN109145050B (en) | Computing device | |
| CN110570295A (en) | Resource collection method and device, computer equipment and storage medium | |
| CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
| CN111626061A (en) | Conference record generation method, device, equipment and readable storage medium | |
| CN112291428B (en) | Intelligent calling method and device of voice assistant | |
| CN112291430B (en) | Intelligent response method and device based on identity confirmation | |
| CN107844562B (en) | Intelligent consultation service method | |
| CN113779217A (en) | Intelligent voice outbound service method and system based on human-computer interaction | |
| CN113573029B (en) | Multi-party audio and video interaction method and system based on IOT | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| CN110765242A (en) | Method, device and system for providing customer service information | |
| CN109146737B (en) | Intelligent interaction method and device based on examination platform | |
| CN113284497A (en) | Method and device for urging collection of customers and intelligent collection urging system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |