CN114338921B - Home service-based incoming call processing method, device and medium - Google Patents
Home service-based incoming call processing method, device and medium Download PDFInfo
- Publication number
- CN114338921B CN114338921B CN202111676614.8A CN202111676614A CN114338921B CN 114338921 B CN114338921 B CN 114338921B CN 202111676614 A CN202111676614 A CN 202111676614A CN 114338921 B CN114338921 B CN 114338921B
- Authority
- CN
- China
- Prior art keywords
- incoming call
- type
- call
- feature words
- user
- 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
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The application discloses an incoming call processing method, equipment and a medium based on housekeeping service, which are used for solving the technical problem that the content of the existing housekeeping service incoming call is not easy to record. The method comprises the following steps: accessing an incoming call request of a user; converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template; determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords; and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method, device, and medium for processing an incoming call based on a housekeeping service.
Background
In recent years, home services companies have achieved an integrated service demand for reservation, consultation, complaint, and the like of home services by comprehensively using various informatization means. However, when receiving an incoming call from a user, a worker of the home services company needs to manually record incoming call information during a call, which results in low information recording efficiency, and a large amount of invalid information is generated during the call.
Disclosure of Invention
The embodiment of the application provides an incoming call processing method, equipment and a medium based on an housekeeping service, and aims to solve the technical problem that the content of an incoming call of the traditional housekeeping service is not easy to record.
In order to solve the above problem, the present application provides an incoming call processing method based on a home service, including: accessing an incoming call request of a user; converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template; determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords; and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
In an implementation manner of the application, the incoming call type feature library comprises standard type feature words respectively corresponding to different types of home services; determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords, wherein the method specifically comprises the following steps: matching the type feature words in the call keywords with the standard type feature words to screen out a plurality of standard type feature words corresponding to the call request from the call type feature library, and taking the plurality of standard type feature words as the type feature words to be selected; respectively determining a first weight and a second weight corresponding to a plurality of to-be-selected type feature words according to the frequency of the to-be-selected type feature words in the target call content; the first weight corresponds to a user, and the second weight corresponds to a called party who communicates with the user; respectively arranging the feature words of the type to be selected according to the sequence of the first weight and the second weight to obtain a corresponding first type sequence and a corresponding second type sequence; and determining a corresponding first incoming call type and a second incoming call type according to the first type sequence and the second type sequence, and taking the second incoming call type as the incoming call type corresponding to the incoming call request.
In an implementation manner of the present application, before accessing an incoming call request of a user, the method further includes: acquiring a historical call record of a user, and generating a corresponding relationship network according to an association relationship between another calling party and the user in the historical call record; determining the communication credit level of a user, and predicting an incoming call intention type corresponding to an incoming call request according to the relationship network and the communication credit level; and determining whether the incoming call request is an effective incoming call according to the incoming call intention type, and accessing the incoming call request of the user if the incoming call request is the effective incoming call.
In one implementation of the present application, the second incoming call type includes a plurality of sub incoming call types; after the second incoming call type is used as the incoming call type corresponding to the incoming call request, the method further comprises the following steps: determining a corresponding call stage in the target call content for the type of the incoming call; performing emotion analysis on the conversation stage to obtain corresponding emotion words, and performing tone analysis on key conversation points in the conversation stage to obtain corresponding tone words; and determining the emotion type of the user according to the combination feature words obtained after the emotion words and the tone words are combined and a preset emotion vocabulary library, so as to determine the priority of the sub-call type corresponding to the call stage through the emotion type.
In an implementation manner of the present application, generating a corresponding relationship network according to an association relationship between another party and a user in a historical call record specifically includes: determining the association degree between the other party and the user according to the conversation frequency and the conversation duration of the other party and the user within a preset time period; taking the user and the other party as nodes, taking the association relationship between the user and the other party as an edge, and taking the association degree as the weight of the edge to generate a relationship network; wherein the weight is updated according to the call record of the user.
In an implementation manner of the present application, predicting an incoming call intention corresponding to an incoming call request according to a relationship network and a communication credit level specifically includes: determining whether a called party and a user who have a call with the user are associated or not according to the relationship network; if not, determining that the incoming call intention type corresponding to the incoming call request with the communication credit level reaching the preset level is an answering type, and accessing the incoming call request through an automatic answering mode; based on the automatic answering mode, acquiring initial call content corresponding to the incoming call request, and converting the initial call content into a corresponding initial call text; performing word segmentation on the initial call text, matching word segmentation results with feature words in a domestic vocabulary feature library, and calculating the matching degree between the word segmentation results and the feature words; and controlling the incoming call request to be switched into a manual answering mode under the condition that the matching degree is greater than a first preset threshold value.
In an implementation manner of the present application, before obtaining a call keyword in a target call text, the method further includes: obtaining historical incoming call request information of a plurality of users, and determining user types, requirement types and service fields corresponding to the historical incoming call requests; respectively determining a primary type division index, a secondary type division index and a tertiary type division index which a type feature word corresponding to a historical incoming call request belongs to according to the user type, the demand type and the service field so as to construct a corresponding incoming call type feature library; and determining corresponding description feature words and frequency of the description feature words in the historical incoming call request according to the three-level type division indexes, and taking the description feature words with the frequency greater than a second preset threshold value as default feature words to generate corresponding incoming call templates.
In one implementation of the present application, the method further comprises: and under the condition that the type feature words in the call keywords cannot be matched with the incoming call type feature library, adding the type feature words serving as auxiliary type feature words into the incoming call type feature library to assist in determining the incoming call type corresponding to the incoming call request.
An incoming call processing device based on housekeeping service provided by an embodiment of the application comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
An embodiment of the present application provides a non-volatile computer storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are set to:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
The method, the device and the medium for processing the incoming call based on the housekeeping service have the following beneficial effects at least:
the call type and the call template corresponding to the call request can be determined by identifying the call keywords in the call text and matching the call keywords with the standard feature words in the household vocabulary feature library, so that the call template is filled in real time in the call process with the user to generate a complete call record, the call content does not need to be recorded again after the call is finished, the recording efficiency is improved, and the accuracy of the call record is also improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flowchart of an incoming call processing method based on a housekeeping service according to an embodiment of the present disclosure;
fig. 2 is an architecture diagram of an incoming call processing method based on a housekeeping service according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an incoming call processing device based on a housekeeping service according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, an incoming call processing method based on a home administration service provided in an embodiment of the present application includes:
s101: and accessing an incoming call request of a user.
The home service company is provided with a call center, and the call center is provided with a large display screen or terminal equipment for displaying the incoming call request of the user. After the staff accesses the incoming call request of the user, the background server can record the incoming call record information in the call process and display the incoming call record information according to the display interface of the equipment after the call process is finished.
Before accessing an incoming call request, the server can acquire historical incoming call request information of a plurality of users and determine a user type, a demand type and a service field corresponding to the historical incoming call request. And then respectively determining a primary type division index, a secondary type division index and a tertiary type division index to which the type feature words corresponding to the historical incoming call request belong according to the user type, the demand type and the service field, and accordingly constructing a corresponding incoming call type feature library. The client types are divided into a contracted user and a new user, the first-level type division index can be correspondingly set into a contract type and a consultation type, and certainly, if the contracted user has new requirements, the contracted user can be listed under the consultation type. The secondary type division index mainly aims at the use category of the housekeeping service and is divided into two categories of consultation and complaint. The three-level type division index aims at the application field of the housekeeping services, including the categories of the month-to-law, the child care, the old care, the housekeeping, the medical care, the hour, the sanitation, the kitchen-to-law and the like. The above categories are merely examples and are not intended to be limiting in this application.
The first-level type division indexes, the second-level type division indexes and the third-level type division indexes have hierarchical relations, wherein the first-level type division indexes are highest in level, each first-level type division index can divide each second-level type division index downwards, and each second-level type division index can also continue to divide the third-level type division indexes downwards. And summarizing the type division indexes to obtain a corresponding incoming call type feature library, wherein standard type representation words of different levels of consultation, child care and the like are stored in the incoming call type feature library and are used for determining the incoming call type corresponding to the incoming call request.
The three-level type division indexes are obtained by dividing specific household service fields, and the server can select the description feature words with the frequency larger than a second preset threshold value from the description feature words as default feature words according to the corresponding description feature words and the frequency of the description feature words in the historical incoming call requests aiming at each three-level type division index, so that corresponding incoming call templates are generated. For example, assuming that the second preset threshold is 10, for the three-level type division index of the month-old man, the description feature words include a user name, a service address, a due date, a service date, an 8-hour/full-day system, a service star level, remarks, and the like, and the frequency of occurrence of the description feature words in the historical incoming call request is greater than 10 times, so that the description feature words can be used as default feature words to generate an incoming call template corresponding to the three-level type division index corresponding to the month-old man. In the process of communication with a user, the server can directly obtain the incoming call template corresponding to a certain three-level type division index, so that the template only needs to be filled according to the communication content, all communication information does not need to be recorded, and the efficiency is higher. Each three-level type division index corresponds to an incoming call template, and an incoming call type template library in which a plurality of incoming call templates are stored can be obtained by summarizing the incoming call templates, so that after an incoming call request is accessed, a corresponding incoming call template can be selected from the incoming call templates to record incoming call contents.
When the call center detects that the incoming call request exists, the staff does not answer the incoming call at the first time, but judges whether the incoming call request is a harassing call. If the incoming call request is an effective incoming call with actual requirements, the incoming call request is converted into manual processing, so that the working time of workers is greatly saved, and the working efficiency is improved.
Specifically, the server may determine whether the incoming call request is valid through an association relationship between the user and the home service company and a communication credit level of the user.
Firstly, obtaining a historical call record of a user, and generating a corresponding relationship network according to the association relationship between another calling party and the user in the historical call record. The association relationship can be determined by the call frequency and the call duration between the user and the other party, where the call frequency refers to the frequency of answering the incoming call. The higher the call frequency is, the longer the call duration is, which shows that the trust value of both parties is higher, and the degree of association between the two parties is higher. After determining the degree of association between two parties, the two parties, i.e. the user and the other party, are used as nodes, the association relationship between the user and the other party is used as an edge, and the degree of association is used as the weight of the edge. Of course, with the continuous update of the call records of the user, the weights between the user and other parties will be updated correspondingly, and the relationship network will be updated accordingly.
However, it is impossible to accurately determine whether the call request is valid or not only by the association relationship between the user and the other parties. When a new user places an order or consults the home administration service, the user does not have a call with the home administration service company before, and if the judgment is only carried out according to the association relationship, the user can not receive the incoming call request of the new user any more. Therefore, in order to guarantee the normal incoming call of the new user, the identification result of the incoming call request needs to be further calibrated by combining the communication credit of the user.
The server can predict the type of the incoming call intention corresponding to the incoming call request through the communication credit level of the user and the corresponding relationship network. First, according to the relationship network, it is determined whether there is an association between a called party, which is referred to as a call center of a home service company, and a user, who makes a call with the user. If the association exists, whether the incoming call request can access the call center can be determined directly through the degree of the association between the two. If the association does not exist, the user is a new user, at this time, whether the communication credit level of the user reaches a preset level needs to be determined, if the communication credit level reaches the preset level, the credit of the user is good, and the user can be temporarily listed under the receivable category. However, in order to ensure the accuracy of the recognition result, once the communication credit level of the user meets the preset condition, the user needs to be firstly accessed into the automatic answering mode, and then converses with the caller according to the standard dialogues template set in the automatic answering mode, so as to obtain the corresponding initial call content and initial call text. Then, performing word segmentation processing on the initial call text, matching word segmentation results with feature words in a housekeeping vocabulary feature library, calculating the matching degree between the word segmentation results and the feature words, and when the matching degree is greater than a first preset threshold value, indicating that a conversation performed by a user in an automatic answering mode has an actual service requirement, determining that an incoming call request corresponding to the user is an effective incoming call, and switching the incoming call request into a manual answering mode so as to provide deeper and comprehensive services. It should be noted that the matching degree can be obtained by calculating a ratio between the matching number of the word segmentation result and the feature words and the number of the feature words.
S102: converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template.
After the incoming call request of the user is accessed to the manual answering mode, the staff can be communicated with the user by combining the standard dialect template of the home service. For example, the standard dialogs template may include "your maiden name", "prenatal period +", "which hospital", "what the waiter called", "you want to complain +", and so on. The server can convert the target call content between the user and the staff into a corresponding target call text, and then call keywords in the target call text are obtained according to a preset call template and a preset household vocabulary feature library. The household vocabulary feature library comprises an incoming call type feature library and an incoming call template which are pre-constructed in S101, the call keywords comprise words such as language words, emotion words and feature words, the feature words comprise type feature words and description feature words, the type feature words are words used for representing incoming call request types such as consultations, baby nurses and signed clients, and the description feature words are attribute information under three-level type division indexes, for example, the attribute is 'service star level' under the application type of the baby nurses: and 5 stars, wherein the service star level is the default feature words in the incoming call template, and 5 stars are the description feature words obtained according to the call content. It should be noted that, if the content between the user and the staff can be accurately matched to the standard dialect template, the corresponding call keyword can be determined only according to the standard dialect template, and then the screening according to the housekeeping vocabulary feature library is not needed.
S103: and determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords.
After the keywords are obtained, if the incoming call record corresponding to the incoming call request needs to be quickly recorded according to the call keywords, the incoming call type of the incoming call request needs to be judged first, and only after the incoming call type is obtained, the corresponding incoming call template can be obtained. The determination of the incoming call type corresponding to the incoming call request can be realized by the following steps:
firstly, a user may cover a plurality of type feature words when describing requirements, therefore, the server needs to match the type feature words in the call keywords with the standard type feature words, so as to screen a plurality of standard type feature words corresponding to the call request from the call type feature library, and the screened plurality of standard type feature words are used as the type feature words to be selected. It can be understood that, when the feature words of the types to be selected are screened, the server sequentially screens according to the grades of the classification indexes of the types of each grade in the incoming call type feature library, and finally the determined classification indexes of the types of the three grades are determined.
Then, because the weights of the feature words of each type between the user and the called party are different, the server can respectively determine a first weight and a second weight corresponding to the feature words of the plurality of types to be selected according to the frequency of the feature words of the types to be selected in the target call content; the first weight corresponds to a user, the second weight corresponds to a called party who communicates with the user, and the higher the frequency is, the larger the first weight and the second weight are.
And finally, arranging the feature words of the type to be selected according to the sequence of the first weight and the second weight respectively to obtain a corresponding first type sequence and a corresponding second type sequence. The server can select the feature words of the types to be selected with the largest weight from the first type sequence and the second type sequence as the first incoming call type and the second incoming call type. And when the first incoming call type is not matched with the second incoming call type, taking the second incoming call type corresponding to the called party as a standard, and taking the second incoming call type as the finally identified incoming call type. This is because the willingness of the staff is dominant in the consultation process of the home services, and the recognition result of the called party should be used as the criterion for recognizing the type of the incoming call.
In one embodiment, if the user has multiple events during the call, the finally obtained second incoming call type may include multiple sub-incoming call types, and the events performed by the user need to be confirmed with corresponding priorities according to the actual requirements of the user.
Specifically, for the type of the incoming call, the corresponding call stage in the target call content is determined. The call stage refers to which sentence in the target call content the sub-incoming call type corresponds to, and these sentences refer to the call stage. And then carrying out emotion analysis on the conversation stage to obtain corresponding emotion words, and carrying out tone analysis on key conversation points in the conversation stage to obtain corresponding tone words. The key call points referred to herein refer to the beginning, end or pause of a sentence. Further, the emotion type of the user is determined according to a combined feature word obtained by combining the emotion words and the tone words and a preset emotion word library, so that the priority of the sub-incoming call type corresponding to the call stage is determined according to the emotion type. The emotion vocabulary is stored with a plurality of combined feature words formed by combining emotion words and tone words, different emotion types correspond to different combined feature words, and when the emotion types are worried, urgent and feared, the priority of the sub-incoming call type corresponding to the call stage can be improved, so that when the user needs to be processed, the urgent need can be processed preferentially, the user experience is improved, and the user needs are met.
S104: and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
After the server determines the incoming call type, the server can acquire the incoming call template matched with the incoming call type from the incoming call type template library, and the attribute filling is carried out on the incoming call template according to the call keyword, so that the filled incoming call template is a complete incoming call record. The staff need not to record corresponding conversation content in the conversation process, just can obtain the conversation information automatically and accomplish the record of conversation content, and efficiency is higher, has also improved the rate of accuracy of record.
When the server cannot accurately judge the call type according to the type feature words in the call keywords, the standard feature words stored in the current call type feature library do not include the feature words of the type corresponding to the current call request, and the call type feature library needs to be updated. However, since the incoming call feature library is a word library created by a large number of previous samplings, a single call instance cannot have a great influence on the whole vocabulary architecture, and therefore, the server can add the type feature words corresponding to the current incoming call request as auxiliary type feature words to the incoming call feature library so as to assist in determining the type of the incoming call. Similarly, when the incoming call type template base cannot provide an accurate incoming call template, the server can regenerate a new incoming call template according to the current incoming call requirement, and the newly generated incoming call template is used as an auxiliary template to be added to the original incoming call type template base.
Fig. 2 is an architecture diagram of an incoming call processing method according to an embodiment of the present application. As shown in fig. 2, the family vocabulary feature library includes an incoming call type feature library and an incoming call type template library. After the call center accesses the incoming call request, the staff converses with the user according to the standard conversational template of the housekeeping service, and performs voice recognition in real time in the conversation process to obtain a corresponding target conversation text. And extracting the call keywords matched with the target call text from the target call text by combining the household vocabulary feature library and the standard dialect template, and displaying the call keywords on a working interface of a worker. With the call, when the number of the call keywords reaches a certain degree, the call type corresponding to the current call request can be judged through the call type feature library and the type feature words in the call keywords. And then according to the incoming call type, selecting an incoming call template matched with the attributes from the incoming call type template library. After the incoming call template is obtained, the server can fill the template by itself, so that a complete incoming call record is obtained when the call is finished and is displayed on an interface of a staff end. In the process of executing the flow, if the housekeeping vocabulary feature library cannot provide accurate incoming call type and incoming call template judgment results, the judgment and the adjustment can be carried out by the staff according to the judgment and the adjustment, and corresponding data updating is carried out in the original library.
The above is a method embodiment proposed in the present application. Based on the same idea, some embodiments of the present application further provide a device and a non-volatile computer storage medium corresponding to the above method.
Fig. 3 is a schematic structural diagram of an incoming call processing device based on a housekeeping service according to an embodiment of the present application. As shown in fig. 3, includes:
at least one processor; and the number of the first and second groups,
at least one processor communicatively coupled memory; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to cause the at least one processor to:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a household vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
A non-volatile computer storage medium provided in an embodiment of the present application stores computer-executable instructions, and the computer-executable instructions are configured to:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
and acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (9)
1. An incoming call processing method based on home services is characterized by comprising the following steps:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request;
the incoming call type feature library comprises standard type feature words respectively corresponding to different types of home services;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords, wherein the determining specifically comprises the following steps:
matching the type feature words in the call keywords with the standard type feature words to screen a plurality of standard type feature words corresponding to the call request from the call type feature library, and taking the plurality of standard type feature words as to-be-selected type feature words;
respectively determining a first weight and a second weight corresponding to a plurality of to-be-selected type feature words according to the frequency of the to-be-selected type feature words in the target call content; the first weight corresponds to the user, and the second weight corresponds to a called party who communicates with the user;
respectively arranging the feature words of the type to be selected according to the sequence of the first weight and the second weight to obtain a corresponding first type sequence and a corresponding second type sequence;
and determining a corresponding first incoming call type and a second incoming call type according to the first type sequence and the second type sequence, and taking the second incoming call type as the incoming call type corresponding to the incoming call request.
2. The method for processing an incoming call based on an housekeeping service of claim 1, wherein before accessing the incoming call request of the user, the method further comprises:
acquiring a historical call record of the user, and generating a corresponding relationship network according to the association relationship between the other party and the user in the historical call record;
determining the communication credit level of the user, and predicting the incoming call intention type corresponding to the incoming call request according to the relationship network and the communication credit level;
and determining whether the incoming call request is an effective incoming call according to the incoming call intention type, and accessing the incoming call request of the user if the incoming call request is the effective incoming call.
3. The method according to claim 1, wherein the second incoming call type comprises a plurality of incoming sub-call types;
after the second incoming call type is used as the incoming call type corresponding to the incoming call request, the method further includes:
determining a corresponding call stage of the sub-incoming call in the target call content aiming at the sub-incoming call type;
performing emotion analysis on the conversation stage to obtain corresponding emotion words, and performing tone analysis on key conversation points in the conversation stage to obtain corresponding tone words;
and determining the emotion type of the user according to a combined feature word obtained by combining the emotion word and the tone word and a preset emotion word library, so as to determine the priority of the sub-incoming call type corresponding to the conversation stage through the emotion type.
4. The method according to claim 2, wherein a corresponding relationship network is generated according to an association relationship between another caller in the historical call records and the user, and specifically comprises:
determining the association degree between the other calling party and the user according to the calling frequency and the calling duration of the other calling party and the user within a preset time period;
taking the user and the other party as nodes, taking the association relationship between the user and the other party as an edge, and taking the association degree as the weight of the edge to generate the relationship network; and updating the weight according to the call record of the user.
5. The method according to claim 2, wherein predicting the incoming call intention corresponding to the incoming call request according to the relationship network and the communication credit level comprises:
determining whether a called party in communication with the user is associated with the user or not according to the relationship network;
if not, determining that the incoming call intention type corresponding to the incoming call request with the communication credit level reaching the preset level is an answering type, and accessing the incoming call request through an automatic answering mode;
based on the automatic answering mode, acquiring initial call content corresponding to the incoming call request, and converting the initial call content into a corresponding initial call text;
performing word segmentation processing on the initial call text, matching word segmentation results with feature words in the housekeeping vocabulary feature library, and calculating the matching degree between the word segmentation results and the feature words;
and controlling the incoming call request to be switched into a manual answering mode under the condition that the matching degree is greater than a first preset threshold value.
6. The method according to claim 1, wherein before obtaining the call keywords in the target call text, the method further comprises:
obtaining historical incoming call request information of a plurality of users, and determining user types, requirement types and service fields corresponding to the historical incoming call requests;
respectively determining a primary type division index, a secondary type division index and a tertiary type division index to which a type feature word corresponding to the historical incoming call request belongs according to the user type, the demand type and the service field so as to construct a corresponding incoming call type feature library;
and determining corresponding description feature words and the frequency of the description feature words in the historical incoming call request aiming at the three-level type division indexes, and taking the description feature words with the frequency larger than a second preset threshold value as default feature words to generate a corresponding incoming call template.
7. The method for processing an incoming call based on an housekeeping service according to claim 1, further comprising:
and under the condition that the type feature words in the call keywords cannot be matched with the incoming call type feature library, adding the type feature words serving as auxiliary type feature words into the incoming call type feature library to assist in determining the incoming call type corresponding to the incoming call request.
8. An incoming call processing device based on a housekeeping service, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request;
the incoming call type feature library comprises standard type feature words respectively corresponding to different types of home services;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords, wherein the method specifically comprises the following steps:
matching the type feature words in the call keywords with the standard type feature words to screen out a plurality of standard type feature words corresponding to the call request from the call type feature library, and taking the plurality of standard type feature words as to-be-selected type feature words;
respectively determining a first weight and a second weight corresponding to a plurality of to-be-selected type feature words according to the frequency of the to-be-selected type feature words in the target call content; the first weight corresponds to the user, and the second weight corresponds to a called party who communicates with the user;
respectively arranging the feature words of the type to be selected according to the sequence of the first weight and the second weight to obtain a corresponding first type sequence and a corresponding second type sequence;
and determining a corresponding first incoming call type and a second incoming call type according to the first type sequence and the second type sequence, and taking the second incoming call type as the incoming call type corresponding to the incoming call request.
9. A non-transitory computer storage medium storing computer-executable instructions, the computer-executable instructions configured to:
accessing an incoming call request of a user;
converting target call content in the incoming call request into a target call text, and acquiring call keywords in the target call text according to a preset call technology template and a home administration vocabulary feature library; the household vocabulary feature library consists of a call type feature library and a call template;
determining an incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords;
acquiring an incoming call template corresponding to the incoming call type, and filling the incoming call template according to the description feature words in the call keywords to obtain an incoming call record corresponding to the incoming call request;
the incoming call type feature library comprises standard type feature words respectively corresponding to different types of home services;
determining the incoming call type corresponding to the incoming call request according to the incoming call type feature library and the type feature words in the call keywords, wherein the method specifically comprises the following steps:
matching the type feature words in the call keywords with the standard type feature words to screen out a plurality of standard type feature words corresponding to the call request from the call type feature library, and taking the plurality of standard type feature words as to-be-selected type feature words;
respectively determining a first weight and a second weight corresponding to a plurality of feature words of the types to be selected according to the frequency of the feature words of the types to be selected in the target call content; the first weight corresponds to the user, and the second weight corresponds to a called party who communicates with the user;
respectively arranging the feature words of the type to be selected according to the sequence of the first weight and the second weight to obtain a corresponding first type sequence and a corresponding second type sequence;
and determining a corresponding first incoming call type and a second incoming call type according to the first type sequence and the second type sequence, and taking the second incoming call type as the incoming call type corresponding to the incoming call request.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111676614.8A CN114338921B (en) | 2021-12-31 | 2021-12-31 | Home service-based incoming call processing method, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111676614.8A CN114338921B (en) | 2021-12-31 | 2021-12-31 | Home service-based incoming call processing method, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114338921A CN114338921A (en) | 2022-04-12 |
| CN114338921B true CN114338921B (en) | 2022-10-18 |
Family
ID=81022427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111676614.8A Active CN114338921B (en) | 2021-12-31 | 2021-12-31 | Home service-based incoming call processing method, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114338921B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116070875B (en) * | 2023-03-06 | 2023-08-22 | 济南丽阳神州智能科技有限公司 | User demand analysis method, device and medium based on household service |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112235470A (en) * | 2020-09-16 | 2021-01-15 | 重庆锐云科技有限公司 | Incoming call client follow-up method, device and equipment based on voice recognition |
| CN113507541A (en) * | 2021-07-02 | 2021-10-15 | 马上消费金融股份有限公司 | Incoming call intention display method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764649B (en) * | 2018-04-28 | 2022-04-26 | 平安科技（深圳）有限公司 | Insurance sales real-time monitoring method, device, equipment and storage medium |
| CN111340323B (en) * | 2018-12-19 | 2023-09-05 | 中国移动通信集团湖南有限公司 | Automatic dispatch method and system for complaint service request |
| CN110223695B (en) * | 2019-06-27 | 2021-08-27 | 维沃移动通信有限公司 | Task creation method and mobile terminal |
| CN110798578A (en) * | 2019-11-07 | 2020-02-14 | 浙江同花顺智能科技有限公司 | Incoming call transaction management method and device and related equipment |
| CN112199498A (en) * | 2020-09-27 | 2021-01-08 | 中国建设银行股份有限公司 | Man-machine conversation method, device, medium and electronic equipment for endowment service |
-
2021
- 2021-12-31 CN CN202111676614.8A patent/CN114338921B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112235470A (en) * | 2020-09-16 | 2021-01-15 | 重庆锐云科技有限公司 | Incoming call client follow-up method, device and equipment based on voice recognition |
| CN113507541A (en) * | 2021-07-02 | 2021-10-15 | 马上消费金融股份有限公司 | Incoming call intention display method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114338921A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9536266B2 (en) | Fact checker engine | |
| US9210263B2 (en) | Audio archive generation and presentation | |
| CN106548788B (en) | Intelligent emotion determining method and system | |
| US8767927B2 (en) | System and method for servicing a call | |
| TW201818734A (en) | Method and device for processing incoming call, and terminal | |
| US8767928B2 (en) | System and method for servicing a call | |
| US20130156171A1 (en) | System and method for servicing a call | |
| US11769509B2 (en) | Speech-based contextual delivery of content | |
| JP2017519443A (en) | Audio display | |
| KR101645992B1 (en) | Apparatus for monitering customer complaint and computer-readable medium thereof | |
| US20100056100A1 (en) | Rules-based association of a phone number with one or more destination locations | |
| US20090049006A1 (en) | Method and system for processing knowledge | |
| CN114338921B (en) | Home service-based incoming call processing method, device and medium | |
| US11095601B1 (en) | Connection tier structure defining for control of multi-tier propagation of social network content | |
| CN108920543A (en) | The method and device of inquiry and interaction, computer installation, storage medium | |
| CN101710927B (en) | Method and system for providing information service based on voice platform | |
| WO2019103727A1 (en) | Improved onboarding of entity data | |
| CN109065045A (en) | Audio recognition method, device, electronic equipment and computer readable storage medium | |
| CN106488050B (en) | Interactive voice answering method and system | |
| US10924611B2 (en) | Voice recognition system and call evaluation setting method | |
| CN113194210B (en) | Voice call access method and device | |
| US20220198138A1 (en) | Consent to content template mapping | |
| CN110955760B (en) | Evaluation method of judgment result and related device | |
| CN110096653A (en) | Construction method, device, equipment and the storage medium of space time information service architecture | |
| CN111355849A (en) | Telephone traffic work order processing method and device |
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 |