CN112988948B - Service processing method and device - Google Patents
Service processing method and device Download PDFInfo
- Publication number
- CN112988948B CN112988948B CN202110160323.7A CN202110160323A CN112988948B CN 112988948 B CN112988948 B CN 112988948B CN 202110160323 A CN202110160323 A CN 202110160323A CN 112988948 B CN112988948 B CN 112988948B
- Authority
- CN
- China
- Prior art keywords
- text
- target
- information
- service
- dialogue
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
Abstract
The embodiment of the specification provides a service processing method and a device, wherein the service processing method comprises the following steps: acquiring historical multimedia service data containing at least two dialogue roles in a target service, converting the historical multimedia service data into text information, dividing the text information into text fragments, dividing the text fragments into dialogue roles according to semantic information of the text fragments, determining a target dialogue role according to dialogue role division results and the semantic information, acquiring association relations among problem texts of the target dialogue roles in the text fragments, screening target problem texts of the target dialogue roles in the text fragments according to the association relations, and constructing a dialogue knowledge base of the target service based on the target problem texts.
Description
Technical Field
The embodiment of the specification relates to the technical field of computers, in particular to a business processing method. One or more embodiments of the present specification relate to a business processing apparatus, a computing device, and a computer-readable storage medium.
Background
Along with the increase of the attention of the user group to the health care project, the number of people joining the project is increased, so that in order to enable the user to more quickly and conveniently experience or enjoy the service provided by the project, different from the traditional offline service mode, a plurality of online service platforms are generated. The user can join in the health care project through the offline or online service platform, and under the condition that the user joins in the project and the project initiator is required to provide health care for the user when the health problem occurs, the project initiator of the health care project is required to collect the visit certificates and other relevant proving materials of the user, and audit the visit certificates and other proving materials to judge whether the user meets the condition of enjoying the health care.
At present, a business initiator mostly adopts a pre-constructed knowledge base to generate a collection proof material, but the construction of the current knowledge base is completely dependent on manual work or assisted by mining high-frequency client information, so that the initial labor cost is very high, and the knowledge base is updated and maintained continuously by manual work, so that the problem of high maintenance cost is caused, and therefore, an effective method is needed to solve the problem.
Disclosure of Invention
In view of this, the embodiments of the present disclosure provide a service processing method. One or more embodiments of the present specification also relate to a business processing apparatus, a computing device, and a computer-readable storage medium that solve the technical drawbacks of the prior art.
According to a first aspect of embodiments of the present disclosure, there is provided a service processing method, including:
acquiring historical multimedia service data containing at least two dialogue roles in a target service, and converting the historical multimedia service data into text information;
dividing the text information into text fragments, dividing the text fragments into dialogue roles according to semantic information of the text fragments, and determining target dialogue roles according to dialogue role division results and the semantic information;
acquiring an association relation between the problem texts of the target dialogue roles in the text fragments;
and screening target question texts of the target dialogue roles in the text fragments according to the association relation, and constructing a dialogue knowledge base of the target business based on the target question texts.
Optionally, the converting the historical multimedia service data into text information includes:
And carrying out voice recognition on the historical multimedia service data to obtain text information generated by recognition.
Optionally, the dividing the text information into text segments includes:
and determining a semantic matching result of at least one service information acquisition item and the text information in a service processing template of the target service, and dividing the text information into at least one text segment according to the semantic matching result.
Optionally, in the determining the service processing template of the target service, the semantic matching result between at least one service information acquisition item and the text information includes:
determining information to be acquired corresponding to at least one service information acquisition item based on the at least one service information acquisition item in the service processing template of the target service;
carrying out semantic similarity calculation on the information to be acquired and the text information;
and determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
Optionally, in the determining the service processing template of the target service, the semantic matching result between at least one service information acquisition item and the text information includes:
Determining information to be acquired corresponding to at least one service information acquisition item based on the at least one service information acquisition item in the service processing template of the target service;
inputting the information to be acquired and the text information into a pre-trained semantic matching model for similarity calculation;
and determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
Optionally, the acquiring the association relationship between the question texts of the target dialogue roles in the text segment includes:
inputting the text segment into a natural language processing model for relevance calculation, and generating a relevance calculation result between the problem texts of the target dialogue roles in the text segment;
and determining the association relation between the question texts of the target dialogue roles in the text fragments according to the association degree calculation result.
Optionally, the acquiring the association relationship between the question texts of the target dialogue roles in the text segment includes:
acquiring semantic information of an ith question text, an answer text of the ith question text and an (i+1) th question text of the target dialogue character in the text segment;
And determining the association relation between the ith question text and the (i+1) th question text based on the semantic information, wherein i epsilon [1, n-1], n is the number of question texts of the target dialogue roles in the text fragments, and n is a positive integer.
Optionally, the screening the target question text of the target dialogue role in the text segment according to the association relation includes:
determining the text length of the problem text with the association relationship and/or the text quantity of the problem text with the association relationship;
and screening target question text of the target dialogue role according to the text length and/or the text quantity.
Optionally, the screening the target question text of the target dialogue role in the text segment according to the association relation includes:
combining the question text with the association relationship and the answer text corresponding to the question text into text pairs, and calculating the information entropy of the text pairs;
and screening target question text of the target dialogue role in the text segment according to the information entropy.
Optionally, the service processing method further includes:
collecting voice data of a user, and carrying out semantic analysis on the voice data;
And screening the voice recommendation information matched with the voice data in the voice knowledge base according to the semantic analysis result, and recommending the voice recommendation information to the user.
According to a second aspect of embodiments of the present specification, there is provided a service processing apparatus, comprising:
the acquisition module is configured to acquire historical multimedia service data containing at least two dialogue roles in the target service and convert the historical multimedia service data into text information;
the dividing module is configured to divide the text information into text fragments, divide the text fragments into dialogue roles according to semantic information of the text fragments, and determine target dialogue roles according to dialogue role division results and the semantic information;
the acquisition module is configured to acquire the association relation between the question texts of the target dialogue roles in the text fragments;
and the construction module is configured to screen target question text of the target dialogue roles in the text fragments according to the association relation and construct a dialogue knowledge base of the target business based on the target question text.
According to a third aspect of embodiments of the present specification, there is provided a computing device comprising:
A memory and a processor;
the memory is configured to store computer-executable instructions and the processor is configured to execute the computer-executable instructions to implement the steps of the business processing method.
According to a fourth aspect of embodiments of the present description, there is provided a computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the business processing method.
According to one embodiment of the specification, historical multimedia service data containing at least two dialogue roles in a target service are obtained, the historical multimedia service data are converted into text information, the text information is divided into text fragments, dialogue roles are divided according to semantic information of the text fragments, target dialogue roles are determined according to dialogue role division results and the semantic information, association relations among problem texts of the target dialogue roles in the text fragments are obtained, target problem texts of the target dialogue roles in the text fragments are screened according to the association relations, and a dialogue knowledge base of the target service is constructed based on the target problem texts.
The voice operation knowledge base is built through the historical multimedia service data of the target service, so that the complexity of the construction of the voice operation knowledge base and the difficulty of the maintenance of the knowledge base are reduced, and the construction efficiency is improved; in addition, text information of the historical multimedia service data is divided into text fragments, and a speaking operation knowledge base of the target service is constructed according to different text fragments, so that the coverage rate of the speaking operation knowledge base is improved, and the accuracy of speaking operations contained in the constructed speaking operation knowledge base is further ensured.
Drawings
FIG. 1 is a process flow diagram of a business processing method provided in one embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a business process provided in one embodiment of the present disclosure;
FIG. 3 is a flowchart of a business processing method according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a service processing apparatus according to an embodiment of the present disclosure;
FIG. 5 is a block diagram of a computing device provided in one embodiment of the present description.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many other forms than described herein and similarly generalized by those skilled in the art to whom this disclosure pertains without departing from the spirit of the disclosure and, therefore, this disclosure is not limited by the specific implementations disclosed below.
The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
In the present specification, a business processing method is provided, and the present specification relates to a business processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.
Fig. 1 shows a process flow diagram of a service processing method according to an embodiment of the present disclosure, including steps 102 to 108.
Step 102, acquiring historical multimedia service data containing at least two dialogue roles in a target service, and converting the historical multimedia service data into text information.
Specifically, the historical multimedia service data includes, but is not limited to, video data or audio data, and the target service refers to a to-be-checked service, including, but not limited to, a to-be-checked claim service, a to-be-checked loan service, a to-be-checked investment service, and the like, and in this embodiment of the specification, the to-be-checked claim service is described as an example, and the specific implementation of the to-be-checked loan service and the to-be-checked investment service is similar to the specific implementation of the to-be-checked claim service, and only needs to refer to the specific implementation of the to-be-checked claim service, and is not repeated here.
If the target service is the service to be claiming, after the user participates in and goes out the insurance, the service initiator is sent a claiming application, the service initiator collects the visit certificates and other relevant proving materials of the user through interviews or surveys and the like, and the visit certificates and other proving materials are initially checked to prepare for the subsequent judgment of whether the user meets the claiming condition. The historical multimedia service data is video data or audio data formed by recording the interview process in a video or audio mode in the process of collecting related materials by the service initiator in an interview mode, wherein the video data or the audio data comprises at least two dialogue roles, and the at least two dialogue roles can comprise the service initiator, a user and the like.
When the method is implemented, after the historical multimedia service data is obtained, the historical multimedia service data is required to be converted into text information, a speaking knowledge base is built based on the text information, the historical multimedia service data is converted into the text information, and particularly, voice recognition is carried out on the historical multimedia service data, so that the text information generated by recognition is obtained.
In practice, voice recognition techniques (Automatic Speech Recognition, ASR) may be used to convert voice information in the historical multimedia service data to textual information.
And 104, dividing the text information into text fragments, dividing the dialogue roles of the text fragments according to the semantic information of the text fragments, and determining a target dialogue role according to the dialogue role division result and the semantic information.
Specifically, the target service is a service to be checked, in the process of checking the service to be checked, in order to ensure the accuracy of the checking result, a plurality of service information items are generally checked, the final checking result is comprehensively obtained, and the correlation between any two or more service information items in the possibly checked service information items is low, so if the text information item is used as a whole for performing the correlation analysis of the problem text, the accuracy of the obtained analysis result is not high, and therefore, in the process of constructing a speech knowledge base, the text information item can be divided according to the matching relation between the service information acquisition item and the text information item in the service processing template, so that the speech knowledge base corresponding to each service information acquisition item can be respectively constructed according to each text segment generated by division.
As described above, the historical multimedia service data is video data or audio data formed by recording the interview process in the form of video or audio, and the video data or audio data includes at least two conversational roles of the service initiator and the user.
The objective of the embodiments of the present disclosure is to construct a session knowledge base for a target service according to historical multimedia service data, and use the session knowledge base to recommend a session link for a service initiator, so as to mine more effective audit material information through session information in the session link.
In specific implementation, the text information is divided into text fragments, namely, the semantic matching result of at least one service information acquisition item and the text information in the service processing template of the target service is determined, and the text information is divided into at least one text fragment according to the semantic matching result.
Further, determining a semantic matching result between at least one service information acquisition item and the text information in the service processing template of the target service can be realized in the following manner:
determining information to be acquired corresponding to at least one service information acquisition item based on the at least one service information acquisition item in the service processing template of the target service;
carrying out semantic similarity calculation on the information to be acquired and the text information;
and determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
Specifically, because the target service is a service to be checked, in the process of collecting the audit data in the interview mode, the service initiator of the target service can collect the audit data in the mode of asking a question to a user based on the service processing template, and because the collected information contained in the historical multimedia service data obtained by recording the interview process generally corresponds to each information collection item in the service processing template, the text fragment can be divided according to the semantic matching result by determining the semantic matching result of each service information collection item in the service processing template and the text information. And constructing a conversation knowledge base corresponding to each information acquisition item through text information in each text segment.
Still taking the target service as an example of the claim service to be checked, in the interview process, the service initiator can ask a question to the user based on a service processing template (a claim information acquisition template of the claim service) so as to acquire claim material based on reply information of the user. Since the service information collection items in the information collection template generally comprise user basic information (name, age, etc.), business insurance, social insurance, physical examination, hypertension/diabetes/hepatitis, etc., text fragments of the text information can be divided according to the semantic matching result by determining the semantic matching result of each service information collection item and the text information.
In practical application, the information to be collected corresponding to each business information collection item can be determined based on the business information collection items in the business processing template, and the semantic similarity between the information to be collected and the text information is calculated, so that the text information is divided into text fragments according to the calculation result of the semantic similarity.
For example, if the converted text information contains 10 lines of data, it is determined that the 1 st to 4 th lines of text are related to the user basic information, the 5 th to 7 th lines are related to social security, and the 8 th to 10 th lines are related to physical examination, the text information is divided into 3 text segments (1-4 lines are divided into one text segment, 5 to 7 lines are divided into one text segment, and 8 to 10 lines are divided into one text segment).
In the embodiment of the specification, in the process of constructing the conversation knowledge base, the text information is divided according to the matching relation between the business information acquisition items and the text information in the business processing template, so that the conversation knowledge base corresponding to each business information acquisition item is respectively constructed according to each text segment generated by division, and the validity and the accuracy of the conversation knowledge base of each constructed business information acquisition item are guaranteed.
In addition, determining the semantic matching result of at least one service information acquisition item and the text information in the service processing template of the target service can be realized by the following ways:
determining information to be acquired corresponding to at least one service information acquisition item based on the at least one service information acquisition item in the service processing template of the target service;
inputting the information to be acquired and the text information into a pre-trained semantic matching model for similarity calculation;
and determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
Specifically, similarity calculation can be performed on the information to be collected and the text information through a semantic matching model (Enhanced Sequential Inference Model, ESIM).
According to the embodiment of the specification, the similarity calculation is carried out on the information to be acquired and the text information by means of the semantic matching model, so that the accuracy of a calculation result is guaranteed, and the efficiency of a calculation process is improved.
In addition, in practical application, in the interview process, the service initiation Fang Duo collects the audit information of the user by asking questions to the user, so that the target dialogue roles can be determined by determining text sentence patterns, and in the text of each dialogue role, the dialogue roles with more question sentence patterns can be specifically determined as the target dialogue roles.
And 106, acquiring the association relation between the question texts of the target dialogue roles in the text fragments.
Specifically, in the embodiment of the present disclosure, a speaking knowledge base of a target service needs to be constructed through historical multimedia service data of the target service, so that in an actual application process, a speaking link that can be used in a interview process is recommended to a user according to an association relationship between each speaking in the speaking knowledge base, so that more effective audit material information is mined through speaking information in the speaking link.
Therefore, in the construction process of the conversation knowledge base, the association relation between the question texts of the target conversation roles in the text fragments needs to be constructed, so that the conversation link is generated according to the association relation.
In the implementation, the association relation between the problem texts of the target dialogue roles in the text fragments is obtained, the text fragments can be input into a natural language processing model to perform association degree calculation, an association degree calculation result between the problem texts of the target dialogue roles in the text fragments is generated, and the association relation between the problem texts of the target dialogue roles in the text fragments is determined according to the association degree calculation result.
Specifically, relevance calculation can be performed on the problem texts in the text fragments through a data natural language processing model (Natural Language Processing, NLP), and a relevance calculation result between the problem texts of the target dialogue roles in the text fragments is generated, so that the relevance between the problem texts is determined according to the relevance calculation result.
In addition, the association relation between any two adjacent problem texts in the text segment can be determined, so that the association relation between all the problem texts of the target dialogue role in the whole text segment can be determined, and the method can be realized specifically by the following steps:
acquiring semantic information of an ith question text, an answer text of the ith question text and an (i+1) th question text of the target dialogue character in the text segment;
And determining the association relation between the ith question text and the (i+1) th question text based on the semantic information, wherein i epsilon [1, n-1], n is the number of question texts of the target dialogue roles in the text fragments, and n is a positive integer.
Specifically, the text segment contains n question texts of the target dialogue role, and whether the association relationship exists between any two adjacent question texts can be determined, so that the association relationship between the question texts of the target dialogue role in the whole text segment can be determined.
For example, if the text segment includes 5 question texts of the target dialogue character, and if it is determined whether there is an association between the 2 nd question text and the 3 rd question text of the target dialogue character, the association is determined according to the 2 nd question text, the 3 rd question text and the answer text corresponding to the 2 nd question text of the target dialogue character.
In the actual interview process, in order to ensure the validity of the audit information obtained by interview, the service initiator needs to adjust the next interview question information in real time according to the reply information of the user, and a specific adjustment strategy needs to be given by a conversation knowledge base, so that in the process of constructing the conversation knowledge base, the association relation between the question texts of the target conversation roles in the text fragments needs to be determined, and a foundation is laid for generating a conversation link for the service initiator to refer according to the association relation.
And step 108, screening target question text of the target dialogue roles in the text fragments according to the association relation, and constructing a dialogue knowledge base of the target business based on the target question text.
Specifically, after the association relation between the problem texts of the target dialogue roles in the text fragments is determined, the target texts can be further screened according to the association relation to construct a dialogue knowledge base.
In the implementation, the target problem text of the target dialogue role in the text segment is screened according to the association relation, and the implementation can be realized in the following way:
determining the text length of the problem text with the association relationship and/or the text quantity of the problem text with the association relationship;
and screening target question text of the target dialogue role according to the text length and/or the text quantity.
In addition, the target question text of the target dialogue role in the text segment is screened according to the association relation, and the method can be realized by the following steps:
combining the question text with the association relationship and the answer text corresponding to the question text into text pairs, and calculating the information entropy of the text pairs;
And screening target question text of the target dialogue role in the text segment according to the information entropy.
Specifically, the embodiment of the specification can evaluate the quality of the target question text from three dimensions of text length, number of question texts and information entropy;
the length of the answer can intuitively reflect the length of the answer of the user, and in general, the longer the answer of the user is, the more effective information the answer may contain, so that the target question text can be screened by combining the question text and the text length of the corresponding answer text, and the question text with the association relation, in which the sum of the text lengths of the question text and the answer text is greater than the preset length threshold, can be taken as the target question text.
In addition, as the number of question texts can be used for reflecting the number of question-answer interactions between the service initiator and the user, the more the number of question texts is, the more the number of question-answer interactions between the service initiator and the user is, the deeper the depth of the question texts can be further indicated, and the more effective the information contained in the corresponding answer texts is, therefore, one, two or more sets of question texts with the number of texts being greater than the preset number threshold can be used as target question texts in a plurality of sets of question texts with association relations.
In addition, because the information entropy is a measure of event uncertainty, if the question text and the answer text are combined into text pairs, the information entropy of the text pairs can be used for representing the accuracy of the answer text relative to the question text, and the smaller the information entropy is, the more accurate the answer is, and the more effective the question is, so that the question text with an association relationship and the text pairs formed by the corresponding answer text can be used as target question text.
Or if the problem text is screened from the three dimensions of the text length, the text quantity and the information entropy at the same time, weighting calculation can be carried out according to weights respectively corresponding to the three dimensions so as to screen the target problem text.
And screening the target problem text from three dimensions of text length, text quantity and information entropy, thereby being beneficial to improving the effectiveness of the target problem text obtained by screening.
In addition, after the target problem text is obtained through screening, the target problem text is required to be audited to determine whether the target problem text is matched with a conversation in an initial conversation scenario constructed manually in advance, and the initial conversation scenario is updated according to a matching result.
For example, the initial script does not include a node for inquiring whether you have hypertension, but by processing the historical multimedia service data, the finally screened target question text includes whether you have hypertension, and the semantic matching degree of the target question text and an inquiry module about hypertension in the initial script is higher, so that the target question text of whether you have hypertension can be added into the inquiry module about hypertension in the initial script to update the initial script.
After the initial conversation scenario is updated to generate a conversation knowledge base, the conversation knowledge base can be stored in a service platform for a service initiator to use, and the conversation knowledge base can be further iteratively updated in the later period.
In addition, the voice recommendation can be performed for the service initiator based on the voice knowledge base, voice data of the user are collected, semantic analysis is performed on the voice data, voice recommendation information matched with the voice data is screened from the voice knowledge base according to semantic analysis results, and the voice recommendation information is recommended to the user.
By the method, the call operation is recommended to the service initiator, so that the service initiator can recommend the call operation with better quality in real time in the interview process of the service initiator, and the service initiator can acquire more effective audit material information.
The schematic diagram of the service processing procedure provided in the embodiment of the present disclosure is shown in fig. 2, where first, historical multimedia service data (audio file) of a target service is obtained, the audio file is converted into text information (voice-to-text), and then the text information is cut according to semantic information of each information acquisition item in a service processing template, so as to generate a plurality of text fragments; then, screening high-quality vocabularies from each text segment, grading the high-quality vocabularies in the screening result, determining a target vocabularies according to the grading result, checking the target vocabularies, and updating an initial vocabularies by using the target vocabularies under the condition that the checking is passed (the initial vocabularies are constructed by manually based on information acquisition items such as user basic information, business insurance/social insurance, physical examination, past medical history and the like); and storing the updated speech operation, and performing evaluation on the stored speech operation at a later stage to continuously perform iterative optimization on the speech operation so as to construct a closed loop for speech operation generation, speech operation storage and speech operation evaluation optimization.
The voice operation knowledge base is built through the historical multimedia service data of the target service, so that the complexity of the construction of the voice operation knowledge base and the difficulty of the maintenance of the knowledge base are reduced, and the construction efficiency is improved; in addition, text information of the historical multimedia service data is divided into text fragments, and a speaking operation knowledge base of the target service is constructed according to different text fragments, so that the coverage rate of the speaking operation knowledge base is improved, and the accuracy of speaking operations contained in the constructed speaking operation knowledge base is further ensured.
The following describes, with reference to fig. 3, an application of the service processing method provided in the present specification in a claim scene as an example. Fig. 3 is a flowchart of a processing procedure of a service processing method according to an embodiment of the present disclosure, and specific steps include steps 302 to 322.
Step 302, obtaining historical interview video data containing at least two dialogue roles in the claim settlement business.
And 304, performing voice recognition on the historical interview video data to obtain text information generated by recognition.
Step 306, determining information to be collected corresponding to at least one service information collection item based on at least one service information collection item in the service processing template of the claim settlement service.
And 308, inputting the information to be acquired and the text information into a pre-trained semantic matching model to perform similarity calculation.
And step 310, determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
And step 312, dividing the text information into at least one text segment according to the semantic matching result.
And 314, performing dialogue role division on the text fragments according to the semantic information of the text fragments, and determining a target dialogue role according to dialogue role division results and the semantic information.
And step 316, inputting the text segment into a natural language processing model for relevance calculation, and generating a relevance calculation result between the problem texts of the target dialogue roles in the text segment.
And step 318, determining the association relation between the question texts of the target dialogue roles in the text fragments according to the association degree calculation result.
And 320, screening target question text of the target dialogue roles in the text fragments according to the association relation.
And step 322, constructing a speaking knowledge base of the claim settlement business based on the target question text.
According to the embodiment of the specification, the speaking knowledge base is built through the historical interview video data of the claim settlement business, so that the complexity of building the speaking knowledge base and the difficulty of maintaining the knowledge base are reduced, and the building efficiency is improved; in addition, text segment division is carried out on text information of the historical interview video data, and a conversation knowledge base corresponding to different service information acquisition items is constructed according to different text segments, so that the coverage rate of the conversation knowledge base is improved, and the accuracy of a conversation contained in the constructed conversation knowledge base is further ensured.
Corresponding to the above method embodiments, the present disclosure further provides an embodiment of a service processing apparatus, and fig. 4 shows a schematic diagram of a service processing apparatus provided in one embodiment of the present disclosure. As shown in fig. 4, the apparatus includes:
A conversion module 402, configured to obtain historical multimedia service data including at least two dialogue roles in a target service, and convert the historical multimedia service data into text information;
the dividing module 404 is configured to divide the text information into text segments, divide the text segments into dialogue roles according to semantic information of the text segments, and determine a target dialogue role according to dialogue role division results and the semantic information;
an obtaining module 406, configured to obtain an association relationship between the question texts of the target dialogue roles in the text segment;
and a construction module 408, configured to filter target question text of the target dialogue role in the text segment according to the association relation, and construct a dialogue knowledge base of the target business based on the target question text.
Optionally, the conversion module 402 includes:
and the voice recognition sub-module is configured to perform voice recognition on the historical multimedia service data to obtain text information generated by recognition.
Optionally, the dividing module 404 includes:
and the dividing sub-module is configured to determine a semantic matching result of at least one service information acquisition item and the text information in the service processing template of the target service, and divide the text information into at least one text segment according to the semantic matching result.
Optionally, the dividing submodule includes:
a first determining unit configured to determine information to be collected corresponding to at least one service information collection item based on the at least one service information collection item in a service processing template of the target service;
the first computing unit is configured to perform semantic similarity computation on the information to be acquired and the text information;
and the second determining unit is configured to determine a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
Optionally, the dividing submodule includes:
a third determining unit configured to determine information to be collected corresponding to at least one service information collection item based on the at least one service information collection item in the service processing template of the target service;
the second computing unit is configured to input the information to be acquired and the text information into a pre-trained semantic matching model for similarity computation;
and the fourth determining unit is configured to determine a semantic matching result of the at least one service information acquisition item and the text information according to the calculation result.
Optionally, the acquiring module 406 includes:
The relevance calculating submodule is configured to input the text fragments into a natural language processing model to calculate relevance and generate a relevance calculating result between the problem texts of the target dialogue roles in the text fragments;
and the first acquisition sub-module is configured to determine the association relation between the question texts of the target dialogue roles in the text fragments according to the association degree calculation result.
Optionally, the acquiring module 406 includes:
the second acquisition submodule is configured to acquire semantic information of an ith question text, an answer text of the ith question text and an (i+1) th question text of the target dialogue character in the text segment;
and a third determining submodule configured to determine an association relationship between the ith question text and the (i+1) th question text based on the semantic information, wherein i epsilon [1, n-1], n is the number of question texts of the target dialogue character in the text segment, and n is a positive integer.
Optionally, the building module 408 includes:
a text information determining sub-module configured to determine a text length of a question text having an association relationship and/or a text number of the question text having an association relationship;
And the first screening submodule is configured to screen target question texts of the target dialogue roles according to the text length and/or the text quantity.
Optionally, the building module 408 includes:
the information entropy calculation sub-module is configured to form text pairs from question texts with association relations and answer texts corresponding to the question texts, and calculates information entropy of the text pairs;
and the second screening submodule is configured to screen target problem text of the target dialogue role in the text segment according to the information entropy.
Optionally, the service processing device further includes:
the acquisition module is configured to acquire voice data of a user and perform semantic analysis on the voice data;
and the recommending module is configured to screen the voice recommendation information matched with the voice data from the voice knowledge base according to the semantic analysis result and recommend the voice recommendation information to the user.
The above is a schematic scheme of a service processing apparatus of this embodiment. It should be noted that, the technical solution of the service processing apparatus and the technical solution of the service processing method belong to the same concept, and details of the technical solution of the service processing apparatus, which are not described in detail, can be referred to the description of the technical solution of the service processing method.
Fig. 5 illustrates a block diagram of a computing device 500 provided in accordance with one embodiment of the present description. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. Processor 520 is coupled to memory 510 via bus 530 and database 550 is used to hold data.
Computing device 500 also includes access device 540, access device 540 enabling computing device 500 to communicate via one or more networks 560. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 540 may include one or more of any type of network interface, wired or wireless (e.g., a Network Interface Card (NIC)), such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present description, the above-described components of computing device 500, as well as other components not shown in FIG. 5, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device shown in FIG. 5 is for exemplary purposes only and is not intended to limit the scope of the present description. Those skilled in the art may add or replace other components as desired.
Computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 500 may also be a mobile or stationary server.
Wherein the memory 510 is configured to store computer executable instructions and the processor 520 is configured to execute the computer executable instructions for implementing the steps of the business processing method.
The foregoing is a schematic illustration of a computing device of this embodiment. It should be noted that, the technical solution of the computing device and the technical solution of the service processing method belong to the same concept, and details of the technical solution of the computing device, which are not described in detail, can be referred to the description of the technical solution of the service processing method.
An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, are configured to implement the steps of the business processing method.
The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the service processing method belong to the same concept, and details of the technical solution of the storage medium which are not described in detail can be referred to the description of the technical solution of the service processing method.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the embodiments are not limited by the order of actions described, as some steps may be performed in other order or simultaneously according to the embodiments of the present disclosure. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all required for the embodiments described in the specification.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
The preferred embodiments of the present specification disclosed above are merely used to help clarify the present specification. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the teaching of the embodiments. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. This specification is to be limited only by the claims and the full scope and equivalents thereof.
Claims (12)
1. A business processing method, comprising:
acquiring historical multimedia service data containing at least two dialogue roles in a target service, and converting the historical multimedia service data into text information, wherein the at least two dialogue roles comprise a service initiator and a user;
dividing the text information into text fragments, performing dialogue role division on the text fragments according to semantic information of the text fragments, and determining a target dialogue role according to dialogue role division results and the semantic information, wherein the target dialogue role is the target service initiator;
acquiring the association relation between the question texts of the target dialogue roles in the text fragments, wherein the acquiring the association relation between the question texts of the target dialogue roles in the text fragments comprises the following steps: determining the association relation between any two adjacent problem texts in the text fragment;
and screening target problem texts of the target dialogue roles in the text fragments according to the association relations, and constructing a dialogue knowledge base of the target service based on the target problem texts, wherein the dialogue knowledge base recommends a dialogue link for the target dialogue roles based on the association relations.
2. The service processing method of claim 1, the converting the historical multimedia service data into text information, comprising:
and carrying out voice recognition on the historical multimedia service data to obtain text information generated by recognition.
3. The service processing method according to claim 1 or 2, the dividing the text information into text segments, comprising:
and determining a semantic matching result of at least one service information acquisition item and the text information in a service processing template of the target service, and dividing the text information into at least one text segment according to the semantic matching result.
4. The service processing method according to claim 3, wherein determining a semantic matching result between at least one service information acquisition item and the text information in the service processing template of the target service includes:
determining information to be acquired corresponding to at least one service information acquisition item based on the at least one service information acquisition item in the service processing template of the target service;
carrying out semantic similarity calculation on the information to be acquired and the text information;
and determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
5. The service processing method according to claim 3, wherein determining a semantic matching result between at least one service information acquisition item and the text information in the service processing template of the target service includes:
determining information to be acquired corresponding to at least one service information acquisition item based on the at least one service information acquisition item in the service processing template of the target service;
inputting the information to be acquired and the text information into a pre-trained semantic matching model for similarity calculation;
and determining a semantic matching result of the at least one business information acquisition item and the text information according to the calculation result.
6. The service processing method according to claim 1 or 2, wherein the determining the association relationship between any two adjacent problem texts in the text segment includes:
acquiring semantic information of an ith question text, an answer text of the ith question text and an (i+1) th question text of the target dialogue character in the text segment;
and determining the association relation between the ith question text and the (i+1) th question text based on the semantic information, wherein i epsilon [1, n-1], n is the number of question texts of the target dialogue roles in the text fragments, and n is a positive integer.
7. The service processing method according to claim 1, wherein the screening the target question text of the target dialogue character in the text segment according to the association relation includes:
determining the text length of the problem text with the association relationship and/or the text quantity of the problem text with the association relationship;
and screening target question text of the target dialogue role according to the text length and/or the text quantity.
8. The service processing method according to claim 1 or 7, wherein the screening the target question text of the target dialogue character in the text segment according to the association relation includes:
combining the question text with the association relationship and the answer text corresponding to the question text into text pairs, and calculating the information entropy of the text pairs;
and screening target question text of the target dialogue role in the text segment according to the information entropy.
9. The traffic processing method according to claim 1, further comprising:
collecting voice data of a user, and carrying out semantic analysis on the voice data;
and screening the voice recommendation information matched with the voice data in the voice knowledge base according to the semantic analysis result, and recommending the voice recommendation information to the user.
10. A traffic processing apparatus comprising:
the conversion module is configured to acquire historical multimedia service data containing at least two dialogue roles in a target service and convert the historical multimedia service data into text information, wherein the at least two dialogue roles comprise a service initiator and a user;
the dividing module is configured to divide the text information into text fragments, divide the text fragments into dialogue roles according to semantic information of the text fragments, and determine target dialogue roles according to dialogue role division results and the semantic information, wherein the target dialogue roles are the target service sponsors;
the obtaining module is configured to obtain an association relationship between the question texts of the target dialogue roles in the text segment, wherein the obtaining of the association relationship between the question texts of the target dialogue roles in the text segment includes: determining the association relation between any two adjacent problem texts in the text fragment;
the construction module is configured to screen target problem texts of the target dialogue roles in the text fragments according to the association relations, and construct a dialogue knowledge base of the target service based on the target problem texts, wherein the dialogue knowledge base recommends a dialogue link for the target dialogue roles based on the association relations.
11. A computing device, comprising:
a memory and a processor;
the memory is configured to store computer executable instructions and the processor is configured to execute the computer executable instructions to implement the steps of the business processing method of any of claims 1 to 9.
12. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the business processing method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110160323.7A CN112988948B (en) | 2021-02-05 | 2021-02-05 | Service processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110160323.7A CN112988948B (en) | 2021-02-05 | 2021-02-05 | Service processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112988948A CN112988948A (en) | 2021-06-18 |
| CN112988948B true CN112988948B (en) | 2023-09-19 |
Family
ID=76347646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110160323.7A Active CN112988948B (en) | 2021-02-05 | 2021-02-05 | Service processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112988948B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113626573B (en) * | 2021-08-11 | 2022-09-27 | 北京深维智信科技有限公司 | Sales session objection and response extraction method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018223992A1 (en) * | 2017-06-07 | 2018-12-13 | 阿里巴巴集团控股有限公司 | Dialogue generation method and apparatus, and electronic device |
| CN109033270A (en) * | 2018-07-09 | 2018-12-18 | 深圳追科技有限公司 | A method of service knowledge base is constructed based on artificial customer service log automatically |
| CN110019149A (en) * | 2019-01-30 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of method for building up of service knowledge base, device and equipment |
| CN110727764A (en) * | 2019-10-10 | 2020-01-24 | 珠海格力电器股份有限公司 | Phone operation generation method and device and phone operation generation equipment |
| CN110765776A (en) * | 2019-10-11 | 2020-02-07 | 阳光财产保险股份有限公司 | Method and device for generating return visit labeling sample data |
| CN111061847A (en) * | 2019-11-22 | 2020-04-24 | 中国南方电网有限责任公司 | Dialogue generation and corpus expansion method and device, computer equipment and storage medium |
| CN111177350A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Method, device and system for forming dialect of intelligent voice robot |
| CN111309889A (en) * | 2020-02-27 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
| CN111324704A (en) * | 2018-12-14 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Method and device for constructing dialect knowledge base and customer service robot |
| CN111339283A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111611382A (en) * | 2020-05-22 | 2020-09-01 | 贝壳技术有限公司 | Dialect model training method, dialog information generation method, device and system |
| CN111782792A (en) * | 2020-08-05 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for information processing |
| CN111984779A (en) * | 2020-09-10 | 2020-11-24 | 支付宝(杭州)信息技术有限公司 | Dialog text analysis method, device, equipment and readable medium |
-
2021
- 2021-02-05 CN CN202110160323.7A patent/CN112988948B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018223992A1 (en) * | 2017-06-07 | 2018-12-13 | 阿里巴巴集团控股有限公司 | Dialogue generation method and apparatus, and electronic device |
| CN109033270A (en) * | 2018-07-09 | 2018-12-18 | 深圳追科技有限公司 | A method of service knowledge base is constructed based on artificial customer service log automatically |
| CN111324704A (en) * | 2018-12-14 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Method and device for constructing dialect knowledge base and customer service robot |
| CN110019149A (en) * | 2019-01-30 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of method for building up of service knowledge base, device and equipment |
| CN110727764A (en) * | 2019-10-10 | 2020-01-24 | 珠海格力电器股份有限公司 | Phone operation generation method and device and phone operation generation equipment |
| CN110765776A (en) * | 2019-10-11 | 2020-02-07 | 阳光财产保险股份有限公司 | Method and device for generating return visit labeling sample data |
| CN111061847A (en) * | 2019-11-22 | 2020-04-24 | 中国南方电网有限责任公司 | Dialogue generation and corpus expansion method and device, computer equipment and storage medium |
| CN111177350A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Method, device and system for forming dialect of intelligent voice robot |
| CN111309889A (en) * | 2020-02-27 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
| CN111339283A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111611382A (en) * | 2020-05-22 | 2020-09-01 | 贝壳技术有限公司 | Dialect model training method, dialog information generation method, device and system |
| CN111782792A (en) * | 2020-08-05 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for information processing |
| CN111984779A (en) * | 2020-09-10 | 2020-11-24 | 支付宝(杭州)信息技术有限公司 | Dialog text analysis method, device, equipment and readable medium |
Non-Patent Citations (2)
| Title |
|---|
| Yunqi Qiu.et al.Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision.WSDM '20: Proceedings of the 13th International Conference on Web Search and Data Mining.2020,第474–482页. * |
| 融合神经网络与电力领域知识的智能客服对话系统研究;吕诗宁等;浙江电力;第76-82页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112988948A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108877839B (en) | Voice quality perception evaluation method and system based on voice semantic recognition technology | |
| CN110046230B (en) | Method for generating recommended speaking collection, and recommended speaking method and device | |
| CN107222865A (en) | The communication swindle real-time detection method and system recognized based on suspicious actions | |
| CN111966800B (en) | Emotion dialogue generation method and device and emotion dialogue model training method and device | |
| CN111625632A (en) | Question-answer pair recommendation method, device, equipment and storage medium | |
| CN108132952A (en) | A kind of active searching method and device based on speech recognition | |
| CN110472008B (en) | Intelligent interaction method and device | |
| CN112988948B (en) | Service processing method and device | |
| CN113468891A (en) | Text processing method and device | |
| CN115269836A (en) | Intention identification method and device | |
| CN108053826A (en) | For the method, apparatus of human-computer interaction, electronic equipment and storage medium | |
| CN110570208A (en) | Complaint preprocessing method and device | |
| CN113918712A (en) | Data processing method and device | |
| CN117150338A (en) | Task processing, automatic question and answer and multimedia data identification model training method | |
| CN110209804B (en) | Target corpus determining method and device, storage medium and electronic device | |
| CN116108858A (en) | Text processing method and device | |
| CN110765242A (en) | Method, device and system for providing customer service information | |
| CN113886560A (en) | Recommendation method and device for court trial problems | |
| CN112989046A (en) | Real-time speech technology prejudging method, device, computer equipment and storage medium | |
| CN112163075A (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN117332072B (en) | Dialogue processing, voice abstract extraction and target dialogue model training method | |
| CN113918690A (en) | Conversation method and device | |
| Le et al. | Building Filters for Vietnamese Chatbot Responses | |
| CN117350304B (en) | Multi-round dialogue context vector enhancement method and system | |
| CN116186225A (en) | Text updating 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211216 Address after: Room 610, floor 6, No. 618, Wai Road, Huangpu District, Shanghai 200010 Applicant after: Ant Shengxin (Shanghai) Information Technology Co.,Ltd. Address before: 801-11, Section B, 8th floor, 556 Xixi Road, Xihu District, Hangzhou City, Zhejiang Province, 310013 Applicant before: Alipay (Hangzhou) Information Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |