CN114650329A - Computer artificial intelligent information screening system - Google Patents

Computer artificial intelligent information screening system Download PDF

Info

Publication number
CN114650329A
CN114650329A CN202210238453.2A CN202210238453A CN114650329A CN 114650329 A CN114650329 A CN 114650329A CN 202210238453 A CN202210238453 A CN 202210238453A CN 114650329 A CN114650329 A CN 114650329A
Authority
CN
China
Prior art keywords
user
voice
module
app
call
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
CN202210238453.2A
Other languages
Chinese (zh)
Inventor
刘夏飞
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN202210238453.2A priority Critical patent/CN114650329A/en
Publication of CN114650329A publication Critical patent/CN114650329A/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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/436—Arrangements for screening incoming calls, i.e. evaluating the characteristics of a call before deciding whether to answer it
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/12—Detection or prevention of fraud

Abstract

The invention discloses a computer artificial intelligent information screening system, which judges a product to be promoted by automatically answering an advertising promotion telephone and judges whether a user answers the advertising promotion telephone or not by combining the actual demand of the user, thereby filtering a large number of invalid telephones for the user and saving time for the user; when the actual demand of a user is obtained, a plurality of aspects such as voice, purchase and trip of the user are combined, corresponding weights are set according to the demand categories where the various aspects are located, the total demand of the user is obtained and serves as the actual demand of the user, the accuracy of demand judgment is improved, when answering, answer response is carried out according to the ordinary language habits of the user, when the ordinary language habits of the user are obtained, the language of the user is converted into numbers to carry out digital model processing, the models are trained, so that when answering, the sales call can not be perceived as AI answering, and the dialing experience of sales promotion personnel is improved.

Description

Computer artificial intelligent information screening system
Technical Field
The invention relates to the field of information processing, in particular to a computer artificial intelligent information screening system.
Background
In daily life, people often receive calls of advertising promotion, and partial user groups of the calls can dial at will, so that people hear topics which do not dare to be interested when receiving the calls, and a dysphoric mind is generated over time. However, each user has own requirements, and boring emotions cannot be generated for some advertisement promotion telephones which just meet the requirements of the user, so that the living and working efficiency of the user is improved, and the user has better living experience.
Disclosure of Invention
The invention aims to overcome the problems in the prior art and provide a computer artificial intelligent information screening system, which judges the product to be promoted by automatically answering the advertising promotion telephone and judges whether the user answers the advertising promotion telephone according to the actual requirements of the user, thereby filtering a large number of invalid telephones for the user and saving time for the user.
Therefore, the invention provides a computer artificial intelligent information screening system, which comprises:
the telephone answering module is used for answering the voice call of the user;
the telephone switching module is used for prompting the user to answer the voice call by using a ring tone;
the telephone rejection module is used for hanging up the voice incoming call;
the telephone answering module is used for answering the voice call of the user by using AI voice, converting the generated voice conversation into characters in real time and storing the characters in the cache region;
the promotion detection module is used for analyzing the characters in the cache region in real time, accessing the telephone switching module when the characters contain the name in the address book of the user, otherwise obtaining the name of a promotion product, and obtaining the corresponding category of the promotion product according to the name of the promotion product;
the user requirement acquisition module is used for collecting user requirements after acquiring user authorization and acquiring corresponding categories according to the user requirements;
the requirement judging module compares the corresponding category of the promotion product obtained in the promotion detecting module with the category corresponding to the user requirement in the user requirement obtaining module, and when the categories are consistent, the telephone switching module is accessed, otherwise, the telephone refusing module is accessed;
and the database is used for storing the categories, the names of the sales promotion products corresponding to the categories and the user requirements and providing the calls of the sales promotion detection module and the user requirement acquisition module.
Further, when the telephone answering module answers the incoming call by using AI voice, the method comprises the following steps:
step 1: receiving the language of the voice incoming call, converting the language into characters which are sequentially arranged, and segmenting each segment according to punctuation marks, wherein the segment consists of at least one character;
step 2: expressing each character by using a hexadecimal numerical value respectively;
and step 3: representing each segment by using a character array, wherein the character array is composed of hexadecimal numerical values corresponding to characters arranged in sequence in the segment, and each character array is longitudinally tiled and arranged with a vacancy of 0 to obtain a language matrix;
and 4, step 4: sending the language matrix into a trained learning model, and outputting to obtain a reply matrix;
and 5: decomposing the reply matrix to obtain each reply segment, and decoding the reply segments to obtain each reply character and an arrangement sequence;
step 6: and outputting and playing the reply characters according to the arrangement sequence of the reply characters.
Further, in step 4, the learning model, when being trained, includes the following steps:
step (1): acquiring a call record of a user, and dividing the call record into a user voice and a visiting voice;
step (2): dividing the user voice and the visiting voice into a plurality of groups respectively, wherein each group comprises the adjacent user voice and the visiting voice;
and (3): respectively carrying out text conversion on the user voice and the visiting voice of each group;
and (4): respectively processing the language matrix corresponding to the obtained user voice and the language matrix corresponding to the visiting voice;
and (5): respectively taking the language matrix corresponding to the visiting voice of each group as input and the language matrix corresponding to the user voice as output, and training the learning model;
and (6): and traversing all the groups of all the call records of the user to obtain the trained learning model.
Further, in the step (1), the method of dividing the call recording into the user voice and the visiting voice is a tone color division method or a pause time division method.
Further, the user requirement obtaining module, when collecting the user requirement, includes:
the user monitoring module is used for acquiring the life content of the user;
the content decomposition module is used for decomposing the acquired life content according to categories to obtain sub-content;
the frequency acquisition module is used for corresponding the different sub-contents to the APP generating the sub-contents and acquiring the frequency used by the corresponding APP;
the type judgment module is used for obtaining the sub-content corresponding to the APP with the highest use frequency according to the frequency of the APP and determining the user requirement according to the sub-content;
the database is also used for storing user requirements and corresponding sub-contents.
Furthermore, when obtaining the APP with the highest use frequency, the type determination module obtains a weight corresponding to each APP according to the type of the APP, multiplies the weight corresponding to the APP by the frequency corresponding to the APP to obtain a frequency value, and screens the APP with the highest frequency value as the APP with the highest use frequency.
Further, the cache region clears data when the voice incoming call is hung up.
The invention provides a computer artificial intelligent information screening system, which has the following beneficial effects:
the invention judges the product to be promoted by automatically answering the advertising promotion telephone and judges whether the user answers the advertising promotion telephone according to the actual requirement of the user, thereby filtering a large amount of invalid telephones for the user and saving time for the user;
when the sales promotion telephone is answered, answering response is carried out according to the usual language habit of the user, when the usual language habit of the user is obtained, the language of the user is converted into numbers to carry out digital model processing, and the models are trained, so that the sales promotion telephone cannot perceive that AI is answered when answering, and the dialing experience of sales promotion personnel is improved;
when the actual demand of the user is obtained, the total demand of the user is obtained as the actual demand of the user by combining a plurality of aspects of voice, purchase, trip and the like of the user and setting corresponding weights according to the demand categories of the aspects, so that the accuracy of demand judgment is improved.
Drawings
FIG. 1 is a schematic block diagram of the overall system connection of the present invention;
FIG. 2 is a schematic block diagram illustrating a process of answering a voice call using AI voice according to the present invention;
FIG. 3 is a schematic block diagram of a training process of the learning model of the present invention;
FIG. 4 is a schematic block diagram of the system connection for the user requirement acquisition module to collect the user requirement according to the present invention.
Detailed Description
An embodiment of the present invention will be described in detail below with reference to the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the embodiment.
Specifically, as shown in fig. 1 to 4, an embodiment of the present invention provides a computer artificial intelligence information screening system, including: the system comprises a telephone answering module, a telephone switching module, a telephone refusing module, a telephone answering module, a promotion detection module, a user demand acquisition module, a demand judgment module and a database. The functions of the respective modules will be described in detail below.
The telephone answering module is used for answering the voice call of the user; the module answers the language call when the call exists after acquiring the equipment authority of the user.
The telephone switching module is used for prompting the user to answer the voice call by using a ring tone; the module prompts a user to send a prompt, and prompts the user to answer a voice call in a ring mode, which is equivalent to the ring of the current mobile phone ringing and indicates the call prompt.
The telephone rejection module is used for hanging up the voice incoming call; the module hangs up the voice incoming call by acquiring the operation authority of the equipment.
The telephone answering module is used for answering the voice call of the user by using AI voice, converting the generated voice conversation into characters in real time and storing the characters in the cache region; the module converts voice into words in real time by using a voice-word conversion technology, and stores the words in a cache for subsequent use in word processing of conversation.
The promotion detection module is used for analyzing the characters in the cache region in real time, accessing the telephone switching module when the characters contain the names in the address list of the user, otherwise obtaining the names of the promotion products, and obtaining the corresponding categories according to the names of the promotion products; the module is the content of conversation, namely processes the characters in the cache region, thereby judging the caller's intention according to the key information in the characters, generally, if the personnel stored in the address book are the caller, the name of the caller can be spoken, at the moment, the corresponding caller can be matched according to pronunciation, then switching is carried out, so that the owner of the equipment answers, and when the caller is a stranger, the name of the product to be promoted can be obtained according to the content of the conversation. In the invention, the dialogue mode of the AI can be set in advance through a setting mode, and the voice reply of the AI can also be carried out according to the conversation characteristics of the user.
The user requirement acquisition module is used for collecting user requirements after acquiring user authorization and acquiring corresponding categories according to the user requirements; the module is to collect the current demand of the user, that is, the goods or services that the user wants to obtain, and during the collection, the module can analyze the current voice of the user, and can also use the application with higher frequency accessed by the user at present, and the like.
The requirement judging module compares the corresponding category of the promotion product obtained in the promotion detecting module with the category corresponding to the user requirement in the user requirement obtaining module, and when the categories are consistent, the telephone switching module is accessed, otherwise, the telephone refusing module is accessed; the module matches the sales promotion products to be promoted by the caller with the current requirements of the user, when the matching is consistent, the user answers the call, and when the matching is inconsistent, the user refuses the call, namely, the call is hung up. Therefore, the user can avoid wasting time by answering unnecessary sales promotion calls, and sales promotion personnel (namely the caller) can also carry out conversation with the AI instead of carrying out possible emotion waste with invalid clients, so that the experience is improved in two ways.
And the database is used for storing the categories, the names of the sales promotion products corresponding to the categories and the user requirements and providing the calls of the sales promotion detection module and the user requirement acquisition module.
In the invention, through the mutual coordination of the work of the modules, when the user equipment calls, the AI is used for helping the client to answer the call, so that the waiting time of the caller can be avoided, the experience of the caller is improved, meanwhile, the identity of the caller is judged through the first layer of customs control of the AI on the call, so that whether the user answers the call is judged, when the identity of the caller is a sales promotion person, the AI is continuously conversed with the sales promotion person, so that sales promotion products required by the caller are obtained, whether the user answers the call is judged according to the type of the sales promotion products, and the second layer of customs control is carried out on the user. The invention provides a good communication environment for users through multi-layer customs clearance, so that some sales promotion which do not meet requirements are filtered, thereby improving the communication experience of the users, effectively improving the communication efficiency of the users, simultaneously, for sales promotion personnel, when AI communication is carried out, the experience can be explained in a concise and brief way, and the sales promotion personnel can not be simply and roughly hung up by the users due to the fact that the sales promotion products do not meet the requirements of the users, thereby improving the experience of the sales promotion personnel.
In an embodiment of the present invention, when the telephone answering module answers the incoming call by using AI voice, the telephone answering module includes the following steps:
step 1: receiving the language of the voice incoming call, converting the language into characters which are sequentially arranged, and segmenting each segment according to punctuation marks, wherein the segment consists of at least one character;
and 2, step: expressing each character by using a hexadecimal numerical value respectively;
and step 3: representing each segment by using a character array, wherein the character array is composed of hexadecimal numerical values corresponding to characters arranged in sequence in the segment, and each character array is longitudinally tiled and arranged with a vacancy of 0 to obtain a language matrix;
and 4, step 4: sending the language matrix into a trained learning model, and outputting to obtain a reply matrix;
and 5: decomposing the reply matrix to obtain each reply segment, and decoding the reply segments to obtain each reply character and an arrangement sequence;
step 6: and outputting and playing the reply characters according to the arrangement sequence of the reply characters.
In the steps 1-6, the words are sequentially represented according to the sequence, the method uses a digital array matrix mode to replace the expression words, and compresses a large number of words, so that a machine learning mode is used, the answer is given to the caller according to the usual language habit of the user, a salesperson can know the language speaking mode of the user from the beginning, a proper chatting mode is found to communicate with the user, and unpleasant feelings cannot be generated due to the improper speaking mode when the user answers the phone.
Meanwhile, the invention uses the mode of the digital array matrix to express the character segment, thus reducing the storage space of the character, and compared with the character processing, the invention has small operation memory and higher processing speed when processing the array matrix.
In the present invention, the correspondence between characters and numbers may be a sequential numbering system, a phonetic numbering system, or a numbering system of character-type structure components. So long as each letter corresponds to a number one to one.
Preferably, in step 4, the learning model of the present invention includes the following steps during training:
step (1): acquiring a call record of a user, and dividing the call record into a user voice and a visiting voice;
step (2): dividing the user voice and the visiting voice into a plurality of groups respectively, wherein each group comprises the adjacent user voice and the visiting voice;
and (3): respectively carrying out text conversion on the user voice and the visiting voice of each group;
and (4): respectively processing the language matrix corresponding to the obtained user voice and the language matrix corresponding to the visiting voice;
and (5): respectively taking the language matrix corresponding to the visiting voice of each group as input and the language matrix corresponding to the user voice as output, and training the learning model;
and (6): and traversing all the groups of all the call records of the user to obtain the trained learning model.
The steps (1) to (6) are sequentially carried out according to a logical relationship, the technical scheme is that a learning model is trained, materials selected during training are based on usual communication and conversation of a user, the user voice of the user and the voice of a visitor who has a conversation with the user are distinguished during conversation, and the user voice and the voice of the visitor are expressed in an array matrix mode, so that training of the learning model is completed, and the learning model is uniquely corresponding to the user.
Preferably, in step (1), the method for dividing the call recording into the user voice and the visiting voice is a tone color division method or a pause time division method. The tone segmentation method is to divide the sound with similar tone into one person according to the whole call record and different tones, so as to separate the user voice from the visiting voice, and meanwhile, the user voice and the visiting voice are adjacent to each other in sequence; the pause time division method is to judge the user voice and the visiting voice according to the pause time between utterances, generally, the interval time is longer, generally exceeding 1.5 seconds, the user voice and the visiting voice are considered to be adjacent, conversely, the user voice or the visiting voice is considered to be adjacent, and meanwhile, the user voice and the visiting voice are combined to be adjacent in sequence, and the user voice and the visiting voice are obtained in sequence.
In an embodiment of the present invention, when acquiring a user requirement, the user requirement acquiring module, when collecting the user requirement, includes: the device comprises a user monitoring module, a content decomposition module, a frequency acquisition module and a type judgment module. The following is a detailed description of the various functional modules.
The user monitoring module is used for acquiring the life content of the user; the module is used for recording user operations at ordinary times, such as content browsed by a user when using a mobile phone, products ordered by the user when shopping, or services purchased by the user.
The content decomposition module is used for decomposing the acquired life content according to categories to obtain sub-content; the module classifies the life content to obtain sub-content of multiple aspects, and can have multiple sub-content under one category.
The frequency acquisition module is used for corresponding the different sub-contents to the APP which generates the sub-contents and acquiring the frequency used by the corresponding APP; the module is used for counting the using frequency of the APP corresponding to the sub-content, so that the frequency of the sub-content accessed and browsed by a user is obtained, the interest degree of the user on the sub-content is judged, and the higher the frequency of the APP corresponding to the general sub-content is, the greater the interest degree of the user on the sub-content is.
The type judgment module is used for obtaining the sub-content corresponding to the APP with the highest use frequency according to the frequency of the APP and determining the user requirement according to the sub-content; the module determines the sub-content corresponding to the APP with the highest frequency of use as the user's requirement, which is obtained according to the above inference.
The database is also used for storing user requirements and corresponding sub-contents.
When the user needs are determined, the user browsing at ordinary times is obtained according to the ordinary life content of the user, namely after the permission of the user is obtained, and the access trace records obtained by directly jumping to the APP in the mobile phone are directly extracted, so that the system operation workload is reduced. Therefore, the method and the device obtain the requirements of the user in a mode of comprehensively obtaining the living content of the user, the adopted data is multivariate instead of the data resource of a single APP, the obtained requirements are more comprehensive, and meanwhile, compared with the method and the device which only extract data from shopping APPs, the method and the device have the characteristic that the extracted data is more advanced in time.
As an optimization of the above scheme, when obtaining the APP with the highest use frequency, the type determination module obtains the weight corresponding to each APP according to the type of the APP, multiplies the weight corresponding to the APP by the frequency corresponding to the APP to obtain a frequency value, and screens the APP with the highest frequency value as the APP with the highest use frequency. For some APP with higher professional degree, higher weight can be given, and for APP with higher comprehensive degree, lower weight can be given, so that when the final frequency is obtained, the obtained accuracy is higher, and the obtained user requirement is matched with the actual requirement of the user.
In the embodiment of the present invention, the buffer area clears data when the voice incoming call is hung up. The memory space of the cache space of the system can be reduced by clearing the data at every time, the operation efficiency of the system is improved, for voice calls which are not answered by some users, the intention of the incoming call of the caller can be obtained by browsing the voices of the AI and the caller, whether the call is disconnected or not is determined according to the self condition, and the use experience of the users is improved.
The above disclosure is only for a few specific embodiments of the present invention, however, the present invention is not limited to the above embodiments, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present invention.

Claims (7)

1. A computer artificial intelligent information screening system is characterized by comprising:
the telephone answering module is used for answering the voice call of the user;
the telephone switching module is used for prompting the user to answer the voice call by using a ring tone;
the telephone rejection module is used for hanging up the voice incoming call;
the telephone answering module is used for answering the voice call of the user by using AI voice, converting the generated voice conversation into characters in real time and storing the characters in the cache region;
the promotion detection module is used for analyzing the characters in the cache region in real time, accessing the telephone switching module when the characters contain the names in the address list of the user, otherwise obtaining the names of the promotion products, and obtaining the corresponding categories according to the names of the promotion products;
the user requirement acquisition module is used for collecting user requirements after acquiring user authorization and acquiring corresponding categories according to the user requirements;
the requirement judging module compares the corresponding category of the promotion product obtained from the promotion detecting module with the category corresponding to the user requirement in the user requirement obtaining module, and when the categories are consistent, the telephone switching module is accessed, otherwise, the telephone refusing module is accessed;
and the database is used for storing the categories, the names of the sales promotion products corresponding to the categories and the user demands, and providing the call of the sales promotion detection module and the user demand acquisition module.
2. The computer artificial intelligence information screening system of claim 1, wherein said telephone answering module, when answering said incoming call using AI voice, comprises the steps of:
step 1: receiving the language of the voice incoming call, converting the language into characters which are sequentially arranged, and segmenting each segment according to punctuation marks, wherein the segment consists of at least one character;
step 2: expressing each character by using a hexadecimal numerical value respectively;
and step 3: representing each segment by using a character array, wherein the character array is composed of hexadecimal numerical values corresponding to characters arranged in sequence in the segment, and each character array is longitudinally tiled and arranged with a vacancy of 0 to obtain a language matrix;
and 4, step 4: the language matrix is sent into a trained learning model, and a reply matrix is obtained through output;
and 5: decomposing the reply matrix to obtain each reply segment, and decoding the reply segments to obtain each reply character and an arrangement sequence;
step 6: and outputting and playing the reply characters according to the arrangement sequence of the reply characters.
3. The computer artificial intelligence information screening system of claim 2, wherein in step 4, the learning model, when trained, comprises the steps of:
step (1): acquiring a call record of a user, and dividing the call record into a user voice and a visiting voice;
step (2): dividing the user voice and the visiting voice into a plurality of groups respectively, wherein each group comprises the adjacent user voice and the visiting voice;
and (3): respectively carrying out text conversion on the user voice and the visiting voice of each group;
and (4): respectively processing the language matrix corresponding to the obtained user voice and the language matrix corresponding to the visiting voice;
and (5): respectively taking the language matrix corresponding to the visiting voice of each group as input and the language matrix corresponding to the user voice as output, and training the learning model;
and (6): and traversing all the groups of all the call records of the user to obtain the trained learning model.
4. The computer artificial intelligence information screening system of claim 3, wherein in the step (1), the method of dividing the call recording into the user voice and the visiting voice is a tone division method or a pause time division method.
5. The computer artificial intelligence information screening system of claim 1, wherein the user requirement acquisition module, when collecting the user requirements, comprises:
the user monitoring module is used for acquiring the life content of the user;
the content decomposition module is used for decomposing the acquired life content according to categories to obtain sub-content;
the frequency acquisition module is used for corresponding the different sub-contents to the APP generating the sub-contents and acquiring the frequency used by the corresponding APP;
the type judgment module is used for obtaining the sub-content corresponding to the APP with the highest use frequency according to the frequency of the APP and determining the user requirement according to the sub-content;
the database is also used for storing user requirements and corresponding sub-contents.
6. The computer artificial intelligence information screening system of claim 5, wherein when obtaining the APP with the highest use frequency, the type determination module obtains the weight corresponding to each APP according to the type of the APP, multiplies the weight corresponding to the APP by the frequency corresponding to the APP to obtain a frequency value, and screens the APP with the highest frequency value as the APP with the highest use frequency.
7. The computer artificial intelligence information screening system of claim 1, wherein said buffer clears data when said incoming voice call is hung up.
CN202210238453.2A 2022-03-10 2022-03-10 Computer artificial intelligent information screening system Pending CN114650329A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210238453.2A CN114650329A (en) 2022-03-10 2022-03-10 Computer artificial intelligent information screening system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210238453.2A CN114650329A (en) 2022-03-10 2022-03-10 Computer artificial intelligent information screening system

Publications (1)

Publication Number Publication Date
CN114650329A true CN114650329A (en) 2022-06-21

Family

ID=81992744

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210238453.2A Pending CN114650329A (en) 2022-03-10 2022-03-10 Computer artificial intelligent information screening system

Country Status (1)

Country Link
CN (1) CN114650329A (en)

Similar Documents

Publication Publication Date Title
CN101460995B (en) Monitoring device, evaluation data selection device, reception person evaluation device, and reception person evaluation system
CN111294463B (en) Intelligent response method and system
CN111683175B (en) Method, device, equipment and storage medium for automatically answering incoming call
JP2010113167A (en) Harmful customer detection system, its method and harmful customer detection program
CN109858702A (en) Client upgrades prediction technique, device, equipment and the readable storage medium storing program for executing complained
CN112188017A (en) Information interaction method, information interaction system, processing equipment and storage medium
US20130253932A1 (en) Conversation supporting device, conversation supporting method and conversation supporting program
CN106407393A (en) An information processing method and device for intelligent apparatuses
CN109859032A (en) Funds on account collection method, apparatus, equipment and storage medium based on intelligent sound
CN106936971B (en) A kind of incoming person's information presentation system and reminding method
CN101485188A (en) Method and system for providing voice analysis service, and apparatus therefor
CN108364638A (en) A kind of voice data processing method, device, electronic equipment and storage medium
CN103546613A (en) Contact person recording method, contact person recording device and mobile terminal
CN111787168A (en) Voice recognition quality inspection allocation method based on artificial intelligence technology
CN107995368A (en) Method, apparatus, the terminal and server of intelligent control Stranger Calls alerting pattern
CN106791097A (en) Method of speech processing and device, mobile phone
JP7304627B2 (en) Answering machine judgment device, method and program
WO2023090380A1 (en) Program, information processing system, and information processing method
CN114650329A (en) Computer artificial intelligent information screening system
CN110602334A (en) Intelligent outbound method and system based on man-machine cooperation
CN103067579A (en) Method and device assisting in on-line voice chat
CN111901488B (en) Method for improving outbound efficiency of voice robot based on number state
JP2005192024A (en) Communication voice data management system in call center and operator terminal using the same
CN114328867A (en) Intelligent interruption method and device in man-machine conversation
CN113890949A (en) Intelligent voice outbound method and device for intention recognition

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