CN111901473A - Incoming call processing method, device, equipment and storage medium - Google Patents

Incoming call processing method, device, equipment and storage medium Download PDF

Info

Publication number
CN111901473A
CN111901473A CN202010921691.4A CN202010921691A CN111901473A CN 111901473 A CN111901473 A CN 111901473A CN 202010921691 A CN202010921691 A CN 202010921691A CN 111901473 A CN111901473 A CN 111901473A
Authority
CN
China
Prior art keywords
incoming call
harassment
call
promotion
marked
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010921691.4A
Other languages
Chinese (zh)
Inventor
邹芳
李俊蓉
袁思明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Life Insurance Company of China Ltd
Original Assignee
Ping An Life Insurance Company of China Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Life Insurance Company of China Ltd filed Critical Ping An Life Insurance Company of China Ltd
Priority to CN202010921691.4A priority Critical patent/CN111901473A/en
Publication of CN111901473A publication Critical patent/CN111901473A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/66—Substation equipment, e.g. for use by subscribers with means for preventing unauthorised or fraudulent calling
    • H04M1/663—Preventing unauthorised calls to a telephone set
    • 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
    • G06F16/23—Updating

Abstract

The invention relates to artificial intelligence, and provides an incoming call processing method, an incoming call processing device, incoming call processing equipment and a storage medium, wherein the method comprises the steps of determining whether the incoming call number of an incoming call is a pre-marked harassment number according to a harassment identification library, automatically rejecting the incoming call if the incoming call number is the pre-marked harassment number, automatically switching over the incoming call if the incoming call number is not the pre-marked harassment number, answering the incoming call according to a preset dialogue script and voice information of the incoming call and acquiring call content, marking the incoming call number according to the call content, and updating the harassment identification; in the invention, the marked harassment numbers can be directly intercepted, the harassment numbers which are not marked as harassment numbers are marked, and then the harassment identification library is timely updated according to the marking structure, so that the harassment identification can be automatically refused when the incoming call comes next time, the problem that the harassment call cannot be timely refused to cause user trouble due to poor update effect of the harassment number library in the prior art is solved, and the harassment of strange harassment numbers to the user is reduced. The invention also relates to a block chain technology, and the disturbance identification database is stored in the block chain network.

Description

Incoming call processing method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an incoming call processing method, an incoming call processing device, incoming call processing equipment and a medium.
Background
At present, mobile communication technology is more and more mature, terminals like mobile phones and the like become indispensable tools in life and work of people, but with the development of the mobile communication technology, telephone disturbance aiming at promotion or fraud is often prohibited, and troubles are brought to life of people.
In the prior art, a harassment number library containing a promotion number and a fraud number is generally designed, when a user receives an unfamiliar call, a terminal firstly performs call reminding (such as screen lighting, ring playing and the like), and if the number of the unfamiliar call is detected to be a number in the harassment number library, harassment prompting is performed on the user, so that when the user receives the unfamiliar call, the user can determine to answer the unfamiliar call or hang up the unfamiliar call according to the harassment prompting, and the following problems exist in the harassment prevention method that: even if the number of the strange incoming call is detected to be a number in a harassment number library, the incoming call reminding is required instead of directly intercepting to reduce harassment to the user; the harassment prompting effect depends on the number of the marked numbers in the harassment number library, if the strange incoming call number is not in the harassment number library, strange promotion numbers and fraud numbers cannot be prompted, but now many promotion or fraud harassment calls can frequently change numbers, the harassment number library can be updated only through harassment call reporting platforms provided by various large operators, so that the harassment number library is poor in updating effect, and a user cannot timely know that the incoming call is a harassment incoming call, thereby causing troubles in answering the incoming call.
Disclosure of Invention
The invention provides an incoming call processing method, an incoming call processing device, incoming call processing equipment and a storage medium, and aims to solve the problems that in the prior art, a harassing number bank is poor in updating effect, and harassment users are caused by the fact that harassment incoming calls cannot be rejected in time.
The invention provides an incoming call processing method, which comprises the following steps:
determining whether the incoming call number of the incoming call is a pre-marked harassment number or not according to a harassment identification library, wherein the harassment identification library is a pre-marked harassment number library;
if the incoming call number is determined to be the pre-marked harassment number, automatically rejecting the incoming call;
if the incoming call number is determined not to be the pre-marked harassment number, answering the incoming call according to a preset dialog script and the voice information of the incoming call, and acquiring conversation contents, wherein the preset dialog script is a dialog script which is designed in advance according to the intention of the incoming call;
and marking the incoming call number according to the call content, and updating the harassment identification library according to a marking result.
The present invention provides an incoming call processing apparatus, including:
the determining module is used for determining whether the incoming call number of the incoming call is a pre-marked harassment number according to the harassment identification library, wherein the harassment identification library is a pre-marked harassment number library;
the rejecting module is used for automatically rejecting the incoming call if the incoming call number is determined to be the pre-marked harassment number;
the answer module is used for answering the incoming call according to a preset dialogue script and voice information of the incoming call and acquiring conversation contents if the incoming call number is determined not to be the pre-marked harassment number, wherein the preset dialogue script is a dialogue script which is designed according to incoming call intentions in advance;
and the updating module is used for marking the incoming call number according to the call content and updating the harassment identification library according to a marking result.
The invention provides computer equipment which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of the incoming call processing method when executing the computer program.
The invention provides a readable storage medium, which stores a computer program, wherein the computer program is used for realizing the steps of the incoming call processing method when being executed by a processor.
In one scheme provided by the incoming call processing method, the incoming call processing device, the incoming call processing equipment and the storage medium, whether the incoming call number of the incoming call is a pre-marked harassment number is determined according to a harassment identification library, the harassment identification library is a pre-marked harassment number library, if the incoming call number is determined to be the pre-marked harassment number, the incoming call is automatically rejected, if the incoming call number is determined not to be the pre-marked harassment number, the incoming call is answered according to a preset dialogue script and voice information of the incoming call, call content is acquired, the preset dialogue script is a dialogue script designed according to the intention of the incoming call, the incoming call number is marked according to call content, and the harassment identification library is updated according to a marking result, so that the incoming call is automatically rejected in the next time; in the invention, whether the incoming call number is a marked harassment number is determined, the marked harassment number is directly intercepted, the incoming call number which is not marked as the harassment number is automatically switched, the incoming call number is marked according to the call content, and the harassment identification library is updated according to the marking result, so that the incoming call is automatically refused when coming next time, the harassment identification library is updated in time, the problem that the harassment number library in the prior art is poor in updating effect, the harassment incoming call cannot be refused in time, and the harassment of strange harassment numbers to users is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a diagram illustrating an application environment of an incoming call processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating an incoming call processing method according to an embodiment of the invention;
FIG. 3 is a flowchart illustrating an implementation of step S30 in FIG. 2;
FIG. 4 is a flowchart illustrating an implementation of step S31 in FIG. 3;
FIG. 5 is a flowchart illustrating an implementation of step S33 in FIG. 3;
FIG. 6 is a schematic flow chart of an implementation after step S30 in FIG. 2;
FIG. 7 is a schematic flow chart of another implementation after step S30 in FIG. 2;
FIG. 8 is a flowchart illustrating an implementation of step S40 in FIG. 2;
FIG. 9 is a schematic diagram of an incoming call processing apparatus according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making an invasive task, are within the scope of the present invention.
The incoming call processing method provided by the embodiment of the invention can be applied to the application environment shown in figure 1, wherein the client communicates with the server through the network. The client determines whether the incoming call number is a pre-marked harassment number or not according to a harassment identification library in the server, automatically refuses the incoming call if the incoming call number is determined to be the pre-marked harassment number, answers the incoming call according to a preset dialogue script and the voice information of the incoming call in the server and acquires the call content if the incoming call number is determined not to be the pre-marked harassment number, marks the incoming call number according to the call content and updates the harassment identification library according to the marking result, wherein the preset dialogue script is a dialogue script designed according to the incoming call intention in advance.
Among other things, the client may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers.
In an embodiment, as shown in fig. 2, an incoming call processing method is provided, which is described by taking the application of the method to the client in fig. 1 as an example, and specifically includes the following steps:
s10: and determining whether the incoming call number of the incoming call is a pre-marked harassment number according to a harassment identification library, wherein the harassment identification library is a pre-marked harassment number library.
When a client of a user receives an incoming call, whether the incoming call number of the incoming call is a pre-marked harassment number is determined according to the harassment identification library, and different processing strategies are carried out on the incoming call according to a judgment result. Wherein the harassment identification library is a harassment number library marked in advance.
The harassment identification library is a harassment number library which marks harassment numbers output by the harassment identification model according to the harassment identification model and the big data analysis technology. When the client receives an incoming call, the harassment identification library can identify the incoming call number according to the harassment numbers marked in advance, wherein the harassment numbers marked in advance comprise fraud numbers and promotion numbers.
For example, a harassment identification model is constructed based on harassment numbers provided in a universal telephone number library, and harassment numbers output by the harassment identification model are marked according to the harassment identification model and a big data analysis technology, namely different harassment marks such as fraud marks, promotion marks and the like are marked on the harassment numbers, wherein the promotion marks comprise house property promotion, insurance promotion and the like. And storing the harassment number and the corresponding label in a harassment identification library so as to automatically reject the incoming call of the harassment number according to the identification result of the harassment identification library on the incoming call number when the incoming call of the strange number is received.
In this embodiment, the harassment mark is only an exemplary illustration, and in other embodiments, the harassment mark further includes other types of labels, and the promotion further includes other types of promotions, which are not described herein again.
In an embodiment, before determining whether the unfamiliar number is a premarked harassment number according to the harassment identification library, a harassment identification model needs to be constructed in advance, so that the harassment identification library is obtained according to the harassment identification model, and whether the unfamiliar number is a premarked harassment number is determined according to the harassment identification library after the unfamiliar number is answered.
The method comprises the steps that a harassment identification model is built, all numbers in a general telephone number library need to be acquired, and the general telephone number library is a telephone number library which is acquired in advance through a big data technology and contains harassment numbers. After all numbers in the general telephone number library are obtained, all numbers are judged and marked, the marked numbers comprise harassment numbers, and a two-classification model is constructed by taking the harassment numbers as samples to obtain a harassment identification model.
In the embodiment, all numbers in a universal telephone number library are acquired, the universal telephone number library is a telephone number library which is acquired in advance through a big data technology and contains harassment numbers, then all the numbers are judged and marked, the marked numbers comprise the harassment numbers, a two-classification model is established by taking the harassment numbers as samples so as to acquire a harassment identification model, the process of acquiring the harassment identification model is clarified, the harassment identification library is acquired according to the harassment identification model in the following process, and a basis is provided for determining whether an incoming call number is the harassment number which is marked in advance according to the harassment identification library.
In this embodiment, the disturbance identifier is stored in the blockchain network. The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, which is used for verifying the validity (anti-counterfeiting) of the information and generating a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like. The preset database is deployed in the block chain, so that the safety of data storage can be improved.
In one embodiment, before determining whether the incoming call number is a pre-marked harassment number according to a harassment identification library, judging whether the incoming call number is a strange number, and if the local address list contact number of the incoming call number client is the local address list contact number, prompting a user to answer the call; and if the incoming number is an unfamiliar number, determining whether the unfamiliar number is a pre-marked harassment number according to the harassment identification library.
In the embodiment, when a client of a user receives an incoming call, if the incoming call number of the incoming call is judged to be the local address book contact number of the client, the user is prompted to answer the call without automatically forwarding the incoming call, if the incoming call number is not the local address book contact number of the client, the incoming call number is judged to be a strange number, and then whether the strange number is a harassing number is further judged, so that different countermeasures are taken for the incoming call of the strange number, and therefore user troubles are reduced.
S20: and if the incoming call number is determined to be the pre-marked harassment number, automatically rejecting the incoming call.
After whether the unfamiliar number is the premarked harassment number or not is determined according to the harassment identification library, if the unfamiliar number is the premarked harassment number, the incoming call is determined to be a promotion or a fraud call, and the incoming call is directly and automatically rejected, so that the harassment to a user is reduced.
S30: and if the incoming call number is determined not to be the pre-marked harassment number, answering the incoming call according to a preset dialogue script and the voice information of the incoming call, and acquiring the conversation content, wherein the preset dialogue script is a dialogue script which is designed in advance according to the intention of the incoming call.
After determining whether the unfamiliar number is a premarked harassment number according to the harassment identification library, if the unfamiliar number is determined not to be the premarked harassment number and represents a possible normal number of an incoming call or an unmarked harassment call, at the moment, the incoming call is answered according to a preset dialog script and voice information of the incoming call and conversation content is obtained, so that whether the incoming call is a harassment call is further determined according to the conversation content, and the preset dialog script is a dialog script which is designed in advance according to the intention of the incoming call.
In the process of answering an incoming call according to a preset dialog script and voice information of the incoming call, namely in the process of automatic answering, the incoming call can be converted into character output through voice input, feature vector coding, acoustics and voice model processing by a voice recognition technology (ASR), the character output is used as the input of a natural language processing model (such as an NLP model), the voice intention of the voice information of the incoming call is recognized by the natural language processing model, a proper dialog script is matched based on the intention recognition result of the voice intention, and the text in the dialog script is synthesized into voice by a voice synthesis technology (TTS) through a splicing method or a parameter method to answer the incoming call.
The preset dialogue script is a dialogue script designed in advance according to the incoming call intention, for example, different dialogue scripts are designed aiming at the promotion and fraud intentions, and the promotion telephone skills are designed aiming at the promotion intentions to know the details and pricing of products; aiming at fraud intentions, anti-fraud techniques are designed to acquire fraud source information, such as affiliated units, unit addresses, bank cards, contacts and the like, so as to provide reference information for reporting time.
In this embodiment, the promotional item design is only an exemplary illustration, and in other embodiments, other contents can be known for the promotional item design, which is not described herein again.
In this embodiment, the fraud source information obtained by the anti-fraud speaker is designed for the fraud intention only for illustration, and in other embodiments, other contents can be known for the speaker designed for the fraud intention, which is not described herein again.
S40: and marking the incoming call number according to the call content, and updating the harassment identification library according to the marking result.
In the process of answering an incoming call and acquiring call content according to preset dialogue script and voice information of the incoming call, determining incoming call intention according to the call content, judging whether the incoming call number is a harassment number according to the incoming call intention, marking the incoming call number according to a judgment result, and updating a harassment identification library according to a marking result. For example, if the incoming call intention is determined to be a promotion product according to the call content, the incoming call is determined to be a harassing call, the incoming call number is marked as a harassing number, and the marked number is updated to a harassment recognition library as the harassment number, so that automatic denial is performed when the incoming call of the number is detected next time, the update timeliness of the harassment recognition library is improved, a user does not need to report to a reporting platform, and the user trouble is reduced.
In the embodiment, whether the incoming call number is a pre-marked harassment number is determined according to a harassment identification library, the harassment identification library is a pre-marked harassment number library, if the incoming call number is determined to be the pre-marked harassment number, the incoming call is automatically rejected, if the incoming call number is determined not to be the pre-marked harassment number, the incoming call is answered according to a preset dialogue script and the voice information of the incoming call, call content is obtained, the preset dialogue script is a dialogue script designed according to the incoming call intention in advance, the incoming call number is marked according to the call content, and the harassment identification library is updated according to a marking result; in the invention, whether the incoming call number is a marked harassment number is determined, the marked harassment number is directly intercepted, the incoming call number which is not marked as the harassment number is automatically switched, the incoming call number is marked according to the call content, and the harassment identification library is updated according to the marking result, so that the incoming call is automatically rejected next time, the harassment identification library is updated in time, the problem that the harassment number library in the prior art is poor in updating effect, the harassment incoming call cannot be rejected in time and the harassment of a strange harassment number to a user is reduced.
In an embodiment, as shown in fig. 3, the step S30 of answering the incoming call according to the preset dialog script and the voice message of the incoming call specifically includes the following steps:
s31: and determining the intention of the incoming call according to the voice information of the incoming call.
And after the unfamiliar number is determined not to be the premarked harassing number, determining the intention of the incoming call according to the voice information of the incoming call.
In this embodiment, the speech recognition technology (ASR) may be used to convert the speech input, the feature vector encoding, the acoustics, and the speech model processing into text output, the text output is used as the input of the natural language processing model (such as the NLP model), and the natural language processing model is used to recognize the speech meaning of the incoming call speech information.
S32: and determining whether the incoming call is a harassing call according to the intention of the incoming call.
After the intention of the incoming call is determined according to the voice information of the incoming call, whether the incoming call is a harassing call is determined according to the intention of the incoming call, so that different coping strategies are adopted according to the determination.
For example, the voice message of the incoming call is: and if the XX product is interested, determining that the intention of the incoming call is to promote the XX product, and further determining that the incoming call is a harassing call.
S33: and if the incoming call is determined to be a harassing call, matching a corresponding preset dialogue script according to the harassing call intention.
After whether the incoming call is a harassing call is determined according to the voice information of the incoming call, if the incoming call is determined to be a harassing call, matching a corresponding preset dialogue script according to the intention of the harassing call.
In the process, the type of the harassing call is determined according to the intention of the harassing call, so that the corresponding preset dialogue script is determined according to the type of the harassing call, and the preset dialogue scripts matched with different types of harassing calls are different.
S34: and adjusting the telephone operation according to the voice information of the harassing call and the corresponding preset dialogue script to answer the harassing call.
After the corresponding preset dialogue script is matched according to the intention of the harassing call, adjusting the phone call according to the voice information of the harassing call and the corresponding preset dialogue script to answer the harassing call so as to obtain the call content of the harassing call, identifying and marking the number of the harassing call according to the call content of the harassing call, and updating the harassment identification library according to the marking result.
For example, the types of the harassing calls comprise promotional calls and fraudulent calls, and after the intention of the harassing calls is determined according to the voice information of the harassing calls, whether the harassing calls are promotional calls or fraudulent calls is further determined according to the intention of the harassing calls. If the harassing call is a promotion call, matching a promotion answering in a preset dialogue script according to the voice information of the promotion call to answer the promotion call; if the harassing call is a fraud call, the anti-fraud telephone operation in the preset dialogue script is matched according to the voice information of the fraud call so as to answer the fraud call.
In this embodiment, the types of harassing calls including promotional calls and fraudulent calls are merely exemplary, and in other embodiments, the harassing calls include others, which are not described herein again.
S35: and if the incoming call is determined not to be a harassing call, prompting the user to answer the incoming call.
After whether the incoming call is a harassing call is determined according to the intention of the incoming call, if the incoming call is determined not to be a harassing call, the number of the incoming call is possibly a normal number, and when the incoming call number is found to be the normal number, the user is reminded to answer the incoming call, so that the user can answer the incoming call in time, the situation of wrong interception is avoided, and the accuracy of call interception is improved.
In the embodiment, whether the incoming call is a harassing call is determined according to the voice information of the incoming call, if the incoming call is determined to be a harassing call, the corresponding preset dialogue script is matched according to the intention of the harassing call, and the call is adjusted according to the voice information of the harassing call and the corresponding preset dialogue script to answer the harassing call; if the incoming call is determined not to be a harassing call, the user is prompted to answer the incoming call, the situation of wrong interception is avoided, and the accuracy of call interception is improved.
In an embodiment, as shown in fig. 4, in step S31, the method for determining the intention of the incoming call according to the voice information of the incoming call specifically includes the following steps:
s311: and inputting the voice information of the incoming call into the voice recognition model for natural language processing to generate a text corresponding to the voice information of the harassing incoming call.
After the strange number is determined not to be the pre-marked harassment number, the voice information of the incoming call is input into the voice recognition model to be processed by natural language, and a text corresponding to the voice information of the incoming call is generated.
The speech recognition model is an artificial intelligence model which is established in advance according to a speech recognition technology (ASR) and a natural language processing technology (NLP), can convert the speech information of the incoming call into text information, and extracts the intention expressed by the text information according to the text information.
S312: corresponding text is input into the intention recognition model to recognize the intention of the incoming call.
After the voice information of the incoming call is input into the voice recognition model to be subjected to natural language processing, and the text corresponding to the voice information of the incoming call is generated, the corresponding text is input into the intention recognition model to recognize the intention of the incoming call.
The method comprises the steps of recognizing the intention of an incoming call according to an intention recognition model and a corresponding text, matching corresponding phone art texts according to the intention of the incoming call and a preset dialogue script (for example, matching a promotion answering phone text in the preset dialogue script if the intention of the incoming call is a promotion product, and matching an anti-fraud phone art text in the preset dialogue script if the intention of the incoming call is a fraud), converting the corresponding phone art texts into phone term tones to answer harassing calls, achieving artificial intelligent answering, and reducing the trouble of the harassing incoming calls to users.
In the embodiment, the voice information of the incoming call is input into the voice recognition model to perform natural language processing, a text corresponding to the voice information of the incoming call is generated, the corresponding text is input into the intention recognition model to recognize the intention of the incoming call, the intention of the incoming call is determined according to the voice information of the incoming call is explained in detail, so that the corresponding phonetics text is matched with the preset dialogue script according to the intention of the incoming call, the corresponding phonetics text is converted into phonetics terminology tones to answer the harassing call, artificial intelligent answering is realized, the trouble of the harassing call to a user is reduced, and a technical basis is provided for obtaining the corresponding call content subsequently.
The embodiment provides an incoming call processing method based on an artificial intelligence technology, which combines a speech recognition technology (ASR), a speech synthesis technology (TTS), a natural language processing technology (NLP) and a big data technology to realize a closed-loop harassment recognition library automatically upgraded. On one hand, the method can effectively intercept fraud calls and effectively prevent telecommunication fraud; and on the other hand effectively prevents telephone nuisance while allowing the user to mark promotional content of interest. The problems of mistaken interception and missed interception of the traditional anti-harassment interception are solved, the harassment identification library is updated in real time, and accurate anti-harassment is realized.
In an embodiment, as shown in fig. 5, in step S33, matching the corresponding preset dialog script according to the intention of the harassing call specifically includes the following steps:
s331: and determining the type of the harassing call according to the harassing call intention.
After the incoming call is determined to be a harassing call according to the intention of the incoming call, the type of the harassing call is further determined according to the intention of the harassing call, wherein the type of the harassing call comprises a promotional incoming call and a fraud incoming call.
S332: and if the harassing incoming call is determined to be a promotion incoming call according to the harassing incoming call intention, matching a promotion answering call in the preset dialogue script.
After the type of the harassing call is determined according to the intention of the harassing call, if the harassing call is a promotion call, matching a promotion answer in a preset dialogue script to answer the promotion call and acquire the call content of the promotion call so as to record and process the promotion call and the corresponding content thereof according to the call content of the promotion call, so that a user can know the promotion call and inquire according to the record condition so as to know the product details, pricing and the like of the promotion product.
S333: and if the harassing call is determined to be a fraud call according to the harassing call intention, matching anti-fraud telephone operation in the preset dialogue script.
After the type of the harassing call is determined according to the intention of the harassing call, if the harassing call is a fraud call, the anti-fraud telephone operation in the preset dialogue script is matched to answer the fraud call and acquire the conversation content with the fraud call, so that the fraud call and the corresponding content thereof are recorded and processed according to the conversation content with the fraud call, and a user can know the fraud call and inquire according to the recording condition.
In the embodiment, the type of the harassing call is determined according to the intention of the harassing call, if the harassing call is determined to be a promotion call according to the intention of the harassing call, a promotion answer phone in the preset dialogue script is matched, if the harassing call is determined to be a fraud call according to the intention of the harassing call, an anti-fraud phone in the preset dialogue script is matched, the step of matching the corresponding preset dialogue script according to the intention of the harassing call is further refined, different phones are executed according to the type of the harassing call, different call contents are obtained according to the different phone skills, and a subsequent user can process different call contents according to the different types of calls conveniently.
In an embodiment, as shown in fig. 6, after the step S30, that is, after the call content is acquired, the method further includes the following steps:
s301: and acquiring the promotion information of the promotion incoming call according to the call content of the promotion incoming call, and pushing the promotion information to the user.
After answering according to the promotion answering answer in the preset dialogue script and acquiring the call content of the promotion incoming call, acquiring the promotion information of the promotion incoming call according to the call content of the promotion incoming call and pushing the promotion information to the user, so that the subsequent user can acquire the promotion information of the promotion incoming call and mark the promotion information of the promotion incoming call.
S302: and receiving a marking instruction of the promotion information, and marking the promotion incoming call based on the marking instruction.
After pushing promotion information of a promotion incoming call to a user, receiving a marking instruction of the user to the promotion information, and marking the promotion incoming call based on the marking instruction.
S303: and confirming whether the mark is a shielding mark or not, and if so, marking the number of the push-to-sell incoming call as a push-to-sell number and updating the push-to-sell incoming call number to a harassment identification library.
After receiving the marking instruction of the promotion information, if the marking is confirmed to be the shielding type marking, the number of the promotion incoming call is marked as a promotion number and is updated to a harassment identification library.
For example, the shielding class mark is not interesting, namely if the user is confirmed to mark the promotion information as not interesting, the number of the promotion incoming call is marked as a promotion number and is updated to a harassment identification library, so that the next incoming call is automatically rejected; if the mark for confirming the promotion information is not a shielding type mark, namely the mark for confirming the promotion information is interested, the promotion number is not updated to the harassment identification library, and the user is prompted to answer the call when the promotion number next calls.
In the embodiment, the method comprises the steps of obtaining promotion information of a promotion incoming call according to call content, pushing the promotion information to a user, receiving a marking instruction of the promotion information, marking the promotion incoming call based on the marking instruction, marking the number of the promotion incoming call as a promotion number and updating the promotion number to a harassment identification library if the marking is confirmed to be a shielding type mark, so that the promotion incoming call can be automatically rejected next time, and processing the promotion number according to the interest of the user after the call content of the promotion incoming call is obtained, so that the call processing is more suitable for the actual needs of the user, and is more intelligent and humanized.
In an embodiment, as shown in fig. 7, after the step S30, that is, after the call content is acquired, the method further includes the following steps:
s304: and acquiring relevant information corresponding to the fraud incoming call according to the call content, and reporting the fraud incoming call according to the relevant information corresponding to the fraud incoming call.
After the call content is acquired, the related information corresponding to the fraud call is acquired according to the call content of the fraud call, and the fraud call is reported according to the related information corresponding to the fraud call.
The related information includes personal information of a fraud incoming call corresponding to a fraud person, the personal information includes a affiliated unit, a unit address, a bank card and a contact person, and in other embodiments, the personal information further includes other information, which is not described herein again.
For example, after the related information corresponding to the fraud incoming call is acquired according to the call content of the fraud incoming call, the reporting information for the corresponding fraud person can be sent to the number operation platform according to the personal information of the corresponding fraud person in the related information so as to report the corresponding fraud person.
In this embodiment, the relevant information corresponding to the fraud incoming call is acquired according to the call content, and the fraud incoming call is reported according to the relevant information corresponding to the fraud incoming call. The safety of the user and other people is protected, the incoming call processing can be more suitable for actual requirements, and the intelligent and humanized effects are achieved.
In an embodiment, as shown in fig. 8, in step S40, the method includes steps of marking an incoming call number according to call content, and updating a harassment identification library according to a marking result:
s41: and determining the type of the incoming call according to the call content.
After answering an incoming call and acquiring call content according to the preset dialogue script and the voice information of the incoming call, determining the type of the incoming call according to the call content, and updating a harassment recognition library according to a determination result.
The types of the incoming calls comprise a promotion incoming call, a fraud incoming call and a normal incoming call.
After the type of the incoming call is determined according to the call content, if the incoming call is determined to be a normal incoming call according to the call content, prompting a user to answer the incoming call.
In this embodiment, the types of the incoming call include a promotional incoming call, a fraud incoming call, and a normal incoming call, which are only exemplary illustrations, and in other embodiments, the types of the incoming call include others, and are not described herein again.
S42: and if the incoming call is determined to be a promotion incoming call according to the call content, marking the number of the promotion incoming call as a promotion number, and updating the number of the promotion incoming call as the promotion number to a harassment identification library.
After answering an incoming call and acquiring call content according to a preset dialogue script and voice information of the incoming call, if the incoming call is determined to be a promotion incoming call according to the call content, the number of the promotion incoming call is marked as a promotion number, and the number of the promotion incoming call is updated to a harassment recognition library as the promotion number.
S43: and if the incoming call is determined to be a fraud incoming call according to the call content, marking the number of the fraud incoming call as a fraud number, and updating the number of the fraud incoming call as the fraud number to the harassment identification library.
After answering an incoming call and acquiring call content according to preset dialogue script and voice information of the incoming call, if the incoming call is determined to be a fraud incoming call according to the call content, marking the number of the fraud incoming call as a fraud number, and updating the number of the fraud incoming call as the fraud number to a harassment identification library.
In the embodiment, after answering an incoming call according to a preset dialogue script and voice information of the incoming call and acquiring call contents, determining the type of the incoming call according to the call contents, if the incoming call is determined to be a promotion incoming call according to the call contents, marking the number of the promotion incoming call as a promotion number, updating the number of the promotion incoming call as the promotion number to a harassment recognition library, and if the incoming call is determined to be the promotion incoming call according to the call contents, marking the number of the promotion incoming call as the promotion number, and updating the number of the promotion incoming call as the promotion number to the harassment recognition library; the types of the harassing calls are further refined according to the call content, so that different coping strategies are adopted according to different harassing call types in the following, the harassment recognition library is updated in an iterative mode automatically in the intercepting process, and the anti-harassment effect is continuously improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, an incoming call processing apparatus is provided, and the incoming call processing apparatus corresponds to the incoming call processing method in the above embodiment one to one. As shown in fig. 9, the incoming call processing apparatus includes a determination module 901, a rejection module 902, an answer module 903, and an update module 904. The functional modules are explained in detail as follows:
a determining module 901, configured to determine whether an incoming call number is a pre-marked harassment number according to a harassment identification library, where the harassment identification library is a pre-marked harassment number library;
a rejecting module 902, configured to automatically reject the incoming call if it is determined that the incoming call number is the pre-marked harassment number;
an answering module 903, configured to answer the incoming call according to a preset dialog script and voice information of the incoming call and acquire call content if it is determined that the incoming call number is not the pre-marked harassment number, where the preset dialog script is a dialog script designed according to an incoming call intention in advance;
and the updating module 904 is configured to mark the incoming call number according to the call content, and update the harassment identification library according to a marking result.
Further, the update module 904 is specifically configured to:
if the incoming call is determined to be a promotion incoming call according to the call content, marking the number of the promotion incoming call as a promotion number, and updating the number of the promotion incoming call as the promotion number to the harassment identification library;
and if the incoming call is determined to be a fraud incoming call according to the call content, marking the number of the fraud incoming call as a fraud number, and updating the number of the fraud incoming call as a fraud number to the harassment identification library.
Further, the response module 903 is specifically configured to:
determining the intention of the incoming call according to the voice information of the incoming call;
determining whether the incoming call is a harassing call according to the intention of the incoming call;
if the incoming call is determined to be a harassing call, matching a corresponding preset dialogue script according to the harassment incoming call intention;
adjusting a telephone operation according to the voice information of the harassing call and the preset dialogue script to answer the incoming call;
and if the incoming call is determined not to be a harassing call, prompting a user to answer the incoming call.
Further, the response module 903 is further specifically configured to:
inputting the voice information of the incoming call into a voice recognition model for natural language processing to generate a text corresponding to the voice information of the incoming call;
inputting the corresponding text into an intention recognition model to recognize the intention of the incoming call.
Further, after the call content is acquired, the response module 903 is specifically configured to:
acquiring promotion information of promoting incoming calls according to the call content, and pushing the promotion information to a user;
receiving a marking instruction of the promotion information, and marking the promotion incoming call based on the marking instruction;
and if the mark is confirmed to be a shielding mark, marking the number of the promotion incoming call as a promotion number and updating the promotion number to the harassment identification library.
Further, after the call content is acquired, the response module 903 is further specifically configured to:
and acquiring relevant information corresponding to a fraud call according to the call content, and reporting the fraud call according to the relevant information corresponding to the fraud call.
For specific limitations of the incoming call processing device, reference may be made to the above limitations on the incoming call processing method, which is not described herein again. The modules in the call processing device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a client, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external server through a network connection. The computer program is executed by a processor to implement an incoming call processing method.
In one embodiment, there is provided a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
determining whether the incoming call number of the incoming call is a pre-marked harassment number or not according to a harassment identification library, wherein the harassment identification library is a pre-marked harassment number library;
if the incoming call number is determined to be the pre-marked harassment number, automatically rejecting the incoming call;
if the incoming call number is determined not to be the pre-marked harassment number, answering the incoming call according to a preset dialog script and the voice information of the incoming call, and acquiring conversation contents, wherein the preset dialog script is a dialog script which is designed in advance according to the intention of the incoming call;
and marking the incoming call number according to the call content, and updating the harassment identification library according to a marking result.
In one embodiment, a readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, performs the steps of:
determining whether the incoming call number of the incoming call is a pre-marked harassment number or not according to a harassment identification library, wherein the harassment identification library is a pre-marked harassment number library;
if the incoming call number is determined to be the pre-marked harassment number, automatically rejecting the incoming call;
if the incoming call number is determined not to be the pre-marked harassment number, answering the incoming call according to a preset dialog script and the voice information of the incoming call, and acquiring conversation contents, wherein the preset dialog script is a dialog script which is designed in advance according to the intention of the incoming call;
and marking the incoming call number according to the call content, and updating the harassment identification library according to a marking result.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which is stored in a non-volatile computer readable storage medium and can include the processes of the embodiments of the methods when executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. The volatile memory may include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and simplicity of description, the foregoing functional units and modules are merely illustrated in terms of division, and in practical applications, the foregoing functional allocation may be performed by different functional units and modules as needed, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above described functions.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims (10)

1. An incoming call processing method, comprising:
determining whether the incoming call number of the incoming call is a pre-marked harassment number or not according to a harassment identification library, wherein the harassment identification library is a pre-marked harassment number library;
if the incoming call number is determined to be the pre-marked harassment number, automatically rejecting the incoming call;
if the incoming call number is determined not to be the pre-marked harassment number, answering the incoming call according to a preset dialogue script and the voice information of the incoming call, and acquiring conversation contents, wherein the preset dialogue script is a dialogue script designed in advance according to the incoming call intention;
and marking the incoming call number according to the call content, and updating the harassment identification library according to a marking result.
2. The incoming call processing method according to claim 1, wherein the marking the incoming call number according to the call content and updating the harassment identification library according to the marking result comprises:
if the incoming call is determined to be a promotion incoming call according to the call content, the number of the promotion incoming call is marked as a promotion number, and the number of the promotion incoming call is used as the promotion number and is updated to the harassment identification library;
and if the incoming call is determined to be a fraud incoming call according to the call content, marking the number of the fraud incoming call as a fraud number, and updating the number of the fraud incoming call as a fraud number to the harassment identification library.
3. The incoming call processing method according to claim 1, wherein said answering the incoming call based on a preset dialog script and a voice message of the incoming call, comprises:
determining the intention of the incoming call according to the voice information of the incoming call;
determining whether the incoming call is a harassing call according to the intention of the incoming call;
if the incoming call is determined to be a harassing call, matching a corresponding preset dialogue script according to the harassment incoming call intention;
adjusting a telephone operation according to the voice information of the harassing call and the corresponding preset dialogue script to answer the incoming call;
and if the incoming call is determined not to be a harassing call, prompting a user to answer the incoming call.
4. The incoming call processing method according to claim 3, wherein the determining the intention of the incoming call according to the voice information of the incoming call comprises:
inputting the voice information of the incoming call into a voice recognition model for natural language processing to generate a text corresponding to the voice information of the incoming call;
inputting the corresponding text into an intention recognition model to recognize the intention of the incoming call.
5. The incoming call processing method according to any of claims 1 to 4, wherein after the call content is acquired, the method further comprises:
acquiring promotion information of promoting incoming calls according to the call content, and pushing the promotion information to a user;
receiving a marking instruction of the promotion information, and marking the promotion incoming call based on the marking instruction;
and if the mark is confirmed to be the shielding mark, marking the number of the promotion incoming call as a promotion number and updating the promotion number to the harassment identification library.
6. The incoming call processing method according to any of claims 1 to 4, wherein after the call content is acquired, the method further comprises:
and acquiring relevant information corresponding to a fraud incoming call according to the call content, and reporting the fraud incoming call according to the relevant information corresponding to the fraud incoming call.
7. An incoming call processing apparatus, comprising:
the determining module is used for determining whether the incoming call number of the incoming call is a pre-marked harassment number according to the harassment identification library, wherein the harassment identification library is a pre-marked harassment number library;
the rejecting module is used for automatically rejecting the incoming call if the incoming call number is determined to be the pre-marked harassment number;
the answer module is used for answering the incoming call according to a preset dialogue script and voice information of the incoming call and acquiring conversation contents if the incoming call number is determined not to be the pre-marked harassment number, wherein the preset dialogue script is a dialogue script which is designed according to incoming call intentions in advance;
and the updating module is used for marking the incoming call number according to the call content and updating the harassment identification library according to a marking result.
8. The incoming call processing apparatus according to claim 7, wherein the answering module is specifically configured to:
if the incoming call is determined to be a promotion incoming call according to the call content, the number of the promotion incoming call is marked as a promotion number, and the number of the promotion incoming call is used as the promotion number and is updated to the harassment identification library;
and if the incoming call is determined to be a fraud incoming call according to the call content, marking the number of the fraud incoming call as a fraud number, and updating the number of the fraud incoming call as a fraud number to the harassment identification library.
9. Computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor realizes the steps of the method for handling incoming calls according to any of claims 1 to 6 when executing the computer program.
10. A readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the incoming call processing method according to any one of claims 1 to 6.
CN202010921691.4A 2020-09-04 2020-09-04 Incoming call processing method, device, equipment and storage medium Pending CN111901473A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010921691.4A CN111901473A (en) 2020-09-04 2020-09-04 Incoming call processing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010921691.4A CN111901473A (en) 2020-09-04 2020-09-04 Incoming call processing method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN111901473A true CN111901473A (en) 2020-11-06

Family

ID=73224965

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010921691.4A Pending CN111901473A (en) 2020-09-04 2020-09-04 Incoming call processing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111901473A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112651223A (en) * 2020-12-01 2021-04-13 浙江百应科技有限公司 Disturbance information judgment method and system based on NER and NLU
CN113055523A (en) * 2021-03-08 2021-06-29 北京百度网讯科技有限公司 Crank call interception method and device, electronic equipment and storage medium
CN114172995A (en) * 2021-11-11 2022-03-11 微位（深圳）网络科技有限公司 Incoming call processing method and device, electronic equipment and readable storage medium
CN115396548A (en) * 2022-07-25 2022-11-25 歌尔科技有限公司 Incoming call interception method and device, wearable device and computer readable storage medium
WO2023011024A1 (en) * 2021-08-05 2023-02-09 中兴通讯股份有限公司 Method for reporting malicious call, terminal, electronic device, and storage medium
CN117119104A (en) * 2023-10-25 2023-11-24 南京治煜信息科技有限公司 Telecom fraud active detection processing method based on virtual character orientation training

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109348037A (en) * 2018-11-28 2019-02-15 东南大学 A kind of anti-harassing and wrecking fixed telephone of anti-swindle based on intelligent answer
CN111343638A (en) * 2020-02-26 2020-06-26 中国联合网络通信集团有限公司 Crank call processing method, server and terminal

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109348037A (en) * 2018-11-28 2019-02-15 东南大学 A kind of anti-harassing and wrecking fixed telephone of anti-swindle based on intelligent answer
CN111343638A (en) * 2020-02-26 2020-06-26 中国联合网络通信集团有限公司 Crank call processing method, server and terminal

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112651223A (en) * 2020-12-01 2021-04-13 浙江百应科技有限公司 Disturbance information judgment method and system based on NER and NLU
CN112651223B (en) * 2020-12-01 2023-03-24 浙江百应科技有限公司 Disturbance information judgment method and system based on NER and NLU
CN113055523A (en) * 2021-03-08 2021-06-29 北京百度网讯科技有限公司 Crank call interception method and device, electronic equipment and storage medium
CN113055523B (en) * 2021-03-08 2022-12-30 北京百度网讯科技有限公司 Crank call interception method and device, electronic equipment and storage medium
WO2023011024A1 (en) * 2021-08-05 2023-02-09 中兴通讯股份有限公司 Method for reporting malicious call, terminal, electronic device, and storage medium
CN114172995A (en) * 2021-11-11 2022-03-11 微位（深圳）网络科技有限公司 Incoming call processing method and device, electronic equipment and readable storage medium
CN115396548A (en) * 2022-07-25 2022-11-25 歌尔科技有限公司 Incoming call interception method and device, wearable device and computer readable storage medium
CN115396548B (en) * 2022-07-25 2024-03-22 歌尔科技有限公司 Incoming call interception method and device, wearable equipment and computer readable storage medium
CN117119104A (en) * 2023-10-25 2023-11-24 南京治煜信息科技有限公司 Telecom fraud active detection processing method based on virtual character orientation training
CN117119104B (en) * 2023-10-25 2024-01-30 南京治煜信息科技有限公司 Telecom fraud active detection processing method based on virtual character orientation training

Similar Documents

Publication Publication Date Title
CN111901473A (en) Incoming call processing method, device, equipment and storage medium
EP2747389B1 (en) Mobile terminal having auto answering function and auto answering method for use in the mobile terminal
CN110381221B (en) Call processing method, device, system, equipment and computer storage medium
US9542074B2 (en) Method and apparatus for enhancing an interactive voice response (IVR) system
CN107944258A (en) Start control method, device, storage medium and the terminal of application with method of service
US20100119046A1 (en) Caller identification using voice recognition
CN104183238B (en) A kind of the elderly's method for recognizing sound-groove based on enquirement response
CN107944257A (en) Start control method, device, storage medium and the terminal of application with method of service
US20220279025A1 (en) Network service system, computer storage medium for communication, and network service method
CN106850931A (en) The method and mobile intelligent terminal of Barassment preventing telephone
CN111063355A (en) Conference record generation method and recording terminal
CN110766442A (en) Client information verification method, device, computer equipment and storage medium
CN110769425A (en) Method and device for judging abnormal call object, computer equipment and storage medium
KR20080038873A (en) Portable terminal with function for reporting lost of credit card and method thereof
CN111224865A (en) User identification method based on payment session, electronic device and storage medium
US20230162741A1 (en) Voice verification and restriction method of voice terminal
CN107018502A (en) Short message recognition methods and device
US20220238114A1 (en) System and method for managing an automated voicemail
CN110798576A (en) Incoming call identity recognition method and device and related equipment
CN110221874A (en) The method, device and equipment of quick start application
CN114257688A (en) Telephone fraud identification method and related device
CN116418915A (en) Abnormal number identification method, device, server and storage medium
WO2020171040A1 (en) Voice authentication apparatus, voice authentication method and recording medium
CN112615967A (en) Method, device and equipment for prompting fraud call
CN110473522B (en) Method for accurately analyzing short voice fragments

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20201106