CN110298682A - Intelligent Decision-making Method, device, equipment and medium based on user information analysis - Google Patents
Intelligent Decision-making Method, device, equipment and medium based on user information analysis Download PDFInfo
- Publication number
- CN110298682A CN110298682A CN201910429738.2A CN201910429738A CN110298682A CN 110298682 A CN110298682 A CN 110298682A CN 201910429738 A CN201910429738 A CN 201910429738A CN 110298682 A CN110298682 A CN 110298682A
- Authority
- CN
- China
- Prior art keywords
- user
- intention
- decision
- project
- call object
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention discloses a kind of Intelligent Decision-making Method, device, equipment and media based on user information analysis.The described method includes: obtaining the user tag for corresponding to call object in user list;It obtains corresponding with user tag to decision project;Start outgoing call component and calls call object corresponding with user tag;When setting up communication connection, according to calling, art template is by project information of the voice assistant to the introduction of call object voice to decision project, and obtains the voice data of call object feedback corresponding with problem each in words art template;The intention keyword in voice data is extracted, and judges whether the quantity of intention keyword is greater than or equal to preset quantity threshold value;If more than, it is determined that call object is intention user, and switches over the voice communication currently carried out with intention user according to preset rules.The Intelligent Decision-making Method based on user information analysis provided through the invention, can be improved the recommendation probability of success for treating decision project.
Description
Technical field
The present invention relates to data analysis field more particularly to a kind of Intelligent Decision-making Methods based on user information analysis, dress
It sets, equipment and medium.
Background technique
It is all based on artificial customer service using more telemarketing method on the market at present to carry out, this method not only needs
More artificial customer service is recruited, and to carry out the training of certain time to artificial customer service, it is also desirable to put into a large amount of cost and go
Purchase of equipment, the artificial customer service salary of payment and rental place etc.;Since user information of the artificial customer service to user can not analyse position,
Artificial customer service cannot accurately hold marketing objectives, i.e., cannot be for the marketing decision-making that marketing objectives (to decision project) has made
(such as the marketing objectives for not providing entirely appropriate user), whole marketing success rate is low.Therefore, finding one kind can be reduced certainly
The intelligent decision scheme based on user information analysis of plan cost and the recommendation probability of success of raising product becomes art technology
The problem of personnel's urgent need to resolve.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide it is a kind of based on user information analysis Intelligent Decision-making Method,
Device, equipment and medium, for reducing cost of decision making, improving and treat decision by being carried out after precisely analyzing to user information
The probability of success (such as the probability of success precisely promoted to user) of project progress decision.
A kind of Intelligent Decision-making Method based on user information analysis, comprising:
It determines that a user is call object from user list, and obtains and correspond to the calling in the user list
The user tag of object, the user tag are generated according to the user information of the call object;
Acquisition is corresponding with the user tag to decision project, each is described to the corresponding a project letter of decision project
Breath and a words art template;
When receiving call instruction, starting outgoing call component calls the call object corresponding with the user tag;
When setting up communication connection by the outgoing call component and the call object, call and the user tag pair
The words art template answered, and voice assistant is passed through to call object voice place of matchmakers according to the words art template of calling
The corresponding project information to decision project of user tag is stated, and is obtained and each problem pair in the words art template
The problem of voice data for the call object feedback answered, the words art template includes at least more than one;
The intention keyword in the voice data is extracted, and judges whether the quantity of the intention keyword is greater than or waits
In preset quantity threshold value;
If the quantity of the intention keyword is greater than or equal to the preset quantity threshold value, it is determined that the call object is
Intention user, and switched over current with the ongoing voice communication of intention user according to preset rules.
A kind of intelligent decision device based on user information analysis, comprising:
First obtains module, for determining that a user is call object from user list, and obtains the user name
Correspond to the user tag of the call object in list, the user tag is generated according to the user information of the call object;
Second obtains module, and corresponding with the user tag to decision project for obtaining, each is described to decision
The corresponding a project information of project and a words art template;
Calling module, for when receiving call instruction, starting outgoing call component to call institute corresponding with the user tag
State call object;
Calling module, for when setting up communication connection by the outgoing call component and the call object, call with
The corresponding words art template of the user tag, and according to the words art template of calling by voice assistant to the calling
Object voice introduces the corresponding project information to decision project of the user tag, and obtains and the words art mould
The voice data of the corresponding call object feedback of each problem in plate, the words art template includes asking at least more than one
Topic;
Judgment module for extracting the intention keyword in the voice data, and judges the number of the intention keyword
Whether amount is greater than or equal to preset quantity threshold value;
Determining module, if the quantity for the intention keyword is greater than or equal to the preset quantity threshold value, it is determined that
The call object be intention user, and according to preset rules will currently with the ongoing voice communication of intention user into
Row switching.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realized when executing the computer program it is above-mentioned based on user information analysis
Intelligent Decision-making Method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes the above-mentioned Intelligent Decision-making Method based on user information analysis when being executed by processor.
Above-mentioned Intelligent Decision-making Method, device, equipment and medium based on user information analysis, determines one from user list
A user is call object, and obtains the user tag for corresponding to the call object in the user list, user's mark
Label are generated according to the user information of the call object;It obtains corresponding with the user tag to decision project, each institute
It states to the corresponding a project information of decision project and a words art template;When receiving call instruction, starting outgoing call component calling
The call object corresponding with the user tag;When setting up communication link by the outgoing call component and the call object
When connecing, the words art template corresponding with the user tag is called, and help by voice according to the words art template of calling
Hand introduces the corresponding project information to decision project of the user tag to the call object voice, and obtains
The voice data of the call object feedback corresponding with problem each in the words art template, the words art template includes at least
More than one the problem of;Extract the intention keyword in the voice data, and judge the intention keyword quantity whether
More than or equal to preset quantity threshold value;If the quantity of the intention keyword is greater than or equal to the preset quantity threshold value, really
The fixed call object is intention user, and according to preset rules will currently with the ongoing voice communication of intention user
It switches over.The present invention extracts call object according to the intention keyword in the voice data of words art template feedback, when intention is closed
When the quantity of keyword is greater than or equal to preset quantity threshold value, it is determined that call object is intention user, and will according to preset rules
Artificial customer service currently is switched to the ongoing voice communication of intention user, so as to accurate by carrying out to user information
After analysis, reduces cost of decision making and improve and treat the probability of success that decision project carries out decision.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment signal of the Intelligent Decision-making Method based on user information analysis in one embodiment of the invention
Figure;
Fig. 2 is a flow chart of the Intelligent Decision-making Method based on user information analysis in one embodiment of the invention;
Fig. 3 be in one embodiment of the invention based on user information analysis Intelligent Decision-making Method step in an application environment
Under pre-establish words art template flow diagram;
Fig. 4 be in one embodiment of the invention based on user information analysis Intelligent Decision-making Method step in an application environment
The lower flow diagram for excluding inactive phone number;
Fig. 5 be in one embodiment of the invention based on user information analysis Intelligent Decision-making Method step in an application environment
The flow diagram of lower confirmation call object mood;
Fig. 6 be in one embodiment of the invention based on user information analysis Intelligent Decision-making Method step in an application environment
The flow diagram of lower extraction intention keyword;
Fig. 7 is the structural schematic diagram of the intelligent decision device based on user information analysis in one embodiment of the invention;
Fig. 8 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Intelligent Decision-making Method provided by the invention based on user information analysis, can be applicable in the application environment such as Fig. 1,
Wherein, client is communicated by network with server.Wherein, client can be, but not limited to various personal computers, pen
Remember this computer, smart phone, tablet computer and portable wearable device.Server can be either more with independent server
The server cluster of a server composition is realized.
In one embodiment, as shown in Fig. 2, a kind of Intelligent Decision-making Method based on user information analysis is provided, with the party
Method is illustrated for applying the server in Fig. 1, is included the following steps:
S10 determines that a user is call object from user list, and obtains in the user list corresponding to described
The user tag of call object, the user tag are generated according to the user information of the call object.
It is understood that user list includes the user information of at least one user;Correspondence can be generated in user information
User tag, user information includes but is not limited to that consumer products hobby, customer consumption be horizontal, user's income level, Yong Hulian
It is mode, user's occupation and address name, gender etc., generating corresponding user tag includes but is not limited to consumer products hobby class
Type, customer consumption grade, user's Income Classes and user calling pattern, user's occupation attribute are (for example, belong to high development spatial row
Industry) and user's address mode etc.;Specifically, from user list can according to default selection rule (can be randomly select or
Person is according to putting in order in list) determine that a user is call object.
S20, acquisition is corresponding with the user tag to decision project, each is described to the corresponding a item of decision project
Mesh information and a words art template.
It is understood that being the marketing decision-making marketed to user to decision project;Project information is marketing decision-making
Relevant information;Due to the presence of user tag, server can be generated corresponding with user tag (co-pending to decision project
Plan project can be the product for recommending a kind of suitable user to user), to can more be directed to call object to decision project
(i.e. call object can be more satisfied with to decision project, improve the decision success rate to decision project), and to decision project pair
The project information (product information that can correspond to above-mentioned recommended products) and words art template answered also can more be directed to call object.
Further, shown in Fig. 3, it is described to the corresponding words art template of decision project, institute that each need to be pre-configured with
Before stating step S20, further includes:
S201 establishes the first words art template.
It is understood that first words art template include but is not limited to be question formulation, project information introduce mode,
Address mode of user etc..
S202, obtains the project information to decision project from presetting database, and by the project information
It is input to and the predeterminated position in the first words art template, generation at least one described user tag of the call object
Second words art template.
In this step, due to store in advance in the preset database to the corresponding project information of decision project (such as to
Decision project is loan product, and project information includes the clause etc. of loan), and the first words art template has preset blank position,
At this point, server can obtain project information to decision project from presetting database, and by project information and call object
(possible certain customers' label is simultaneously not necessarily to input, such as consumer products preference type, customer consumption grade at least one user tag
With user's Income Classes etc.) it is input to the preset blank position in the first words art template, the second words art both can be generated
Template.
S203 sends default auditor for the second words art template and checks.
It is understood that at least one of project information and call object user tag are inputted in above-mentioned steps S202
To with the predeterminated position in the first words art template, project information and call object may be caused due to server problem extremely
A few user tag has no in the predeterminated position being input in the first specified words art template, to also result in generation error
Second words art template carries out at this point, default auditor need to be sent in the form of language or text by the second words art template
Further verification confirmation.
S204 determines that the second words art template is described to decision item when default auditor's confirmation
The corresponding words art template of mesh.
In this step, when default auditor's confirmation, illustrate that mistake does not occur in the second words art template.
S205, when the default auditor checks wrong, then in the default auditor to the second words art
After template is modified, determine that the modified second words art template is described to the corresponding words art mould of decision project
Plate.
In this step, when default auditor verification is wrong, illustrate that mistake occurs in the second words art template.
S30, when receiving call instruction, the starting outgoing call component calling calling pair corresponding with the user tag
As.
In this step, there are telephone numbers for the user calling pattern in user tag, when receiving call instruction, starting
Outgoing call component makes a phone call number and removes calling call object corresponding with user tag.
Further, as shown in figure 4, in order to exclude the interference of inactive phone number, in order to save the time, the step
Before S30, further includes:
S301, obtains the telephone number of the user calling pattern in the user tag, and judges that the telephone number is
The no significant number for belonging to international regulations.
It is understood that the telephone number of each country has certain international regulations, for example, mobile phone as defined in China
Telephone number number of significant digit is 11, is fewer of more than 11, can think that the cell-phone telephone number is invalid mobile portable phone
Number.
S302 generates the call instruction if belonging to the significant number of international regulations.
It is understood that if belonging to the significant number of international regulations, it can be said that bright telephone number can be got through.This
When, the call instruction comprising telephone number can be generated, after server receives call instruction at this time, can star outgoing call component
Call call object corresponding with user tag.
S303, if the significant number of international regulations is not belonging to, by the call object from the user list
It removes.
It is understood that illustrate that telephone number is not turned on if being not belonging to the significant number of international regulations, at this time without
It need to go to call the call object, which can also be considered as inactive users, therefore can be by call object from user name
It is removed in list.
S40 is called and is marked with the user when setting up communication connection by the outgoing call component and the call object
The corresponding words art template is signed, and is situated between by voice assistant to the call object voice according to the words art template of calling
The corresponding project information to decision project of the user tag that continues, and obtain and each problem pair in the words art template
The problem of voice data for the call object feedback answered, the words art template includes at least more than one.
It is understood that voice assistant can be artificial intelligent telephone set device people.Specifically, according to invocation step S201
It is corresponding to decision project by voice assistant to introduce user tag to call object voice for art template if generating to S204
When project information, and the voice data of call object feedback corresponding with problem each in words art template is obtained, that is, passes through voice
As soon as assistant is using problem in words art template, the voice data of the corresponding feedback of the problem is obtained in real time, thus
Server can make further analysis according to the voice data that call object is fed back, including call object intention and mood
Confirmation.
Further, as shown in figure 5, in order to understand the mood of the call object, after the step S40, further includes:
S401 carries out feature extraction to the voice data of call object feedback, obtains each phonetic feature.
It is understood that phonetic feature includes but is not limited to prosodic features, sound quality feature, spectrum signature, lexical feature
And vocal print feature.Specifically, the process for carrying out feature extraction to voice data, which specifically includes, carries out at preemphasis voice data
Reason, to treated, voice data carries out framing, multiplying window, is then handled by Fast Fourier Transform (FFT) and logarithm operation,
Above-mentioned phonetic feature is most obtained through discrete cosine transform afterwards.Above-mentioned phonetic feature is spliced into feature vector again, by feature
Vector carries out Emotion identification as input Emotion identification model.
S402 respectively identifies each phonetic feature using Emotion identification model, obtains Emotion identification result.
Wherein, Emotion identification model is trained in advance for carrying out the model of authentication;Emotion identification result packet
Include but be not limited to identify that the happiness having when the corresponding call object of phonetic feature is spoken, indignation, sadness, irritated peace wait quietly
Mood.Specifically, phonetic feature is identified using preparatory trained Emotion identification model, is spoken with obtaining call object
When carry happiness, indignation, sadness, irritated peaceful wait Emotion identification result quietly.In the present embodiment, using Emotion identification model pair
Phonetic feature carries out intelligent recognition, to obtain Emotion identification as a result, its identification process treatment effeciency height is, it can be achieved that call object
Corresponding voice data inspect by random samples in time and comprehensively, is not necessarily to manual intervention, is conducive to save labour turnover.
The training process of Emotion identification model neural network based is as follows: firstly, obtaining training voice data, and to instruction
Practice voice data and carry out mood mark, so that training voice data carries mood label.Wherein, training voice data is for instructing
Practice the voice data of Emotion identification model.The corresponding trained voice data of every kind of mood label choose preset quantity (such as
500) item so that glad, indignation, it is sad, irritated it is peaceful wait the corresponding trained voice data equal proportion of mood quietly, avoid mood from knowing
Occurs over-fitting during other model training.Then, feature extraction is carried out to the training voice data for carrying mood label,
The training phonetic feature for carrying mood label is obtained, specific to be indicated with training phonetic feature x and corresponding mood label y, such as (instruction
It is practice phonetic feature 1, glad), (training phonetic feature 2, indignation) ... (training phonetic feature x, mood y).Again using nerve
Logistic regression algorithm in network model is iterated calculating to all trained phonetic features, will be glad, angry, sad, tired
The hot-tempered peaceful corresponding feature of mood that waits quietly is extracted from training phonetic feature.After successive ignition, the damage of trained model
Mistake restrains, then deconditioning, obtains final trained Emotion identification model neural network based, so that should be based on mind
Emotion identification model through network have stronger nonlinear fitting ability, can mapping complex non-linear relation, and have compared with
Strong robustness and memory capability.Further, the neural network of the present embodiment is specially deep neural network (Deep
Neural Networks, i.e. DNN).
S50 extracts the intention keyword in the voice data, and judges whether the quantity of the intention keyword is greater than
Or it is equal to preset quantity threshold value.
In this step, the intention keyword and intention in voice data can be obtained by following step S501 to S503
The quantity of keyword.
Further, as shown in fig. 6, the intention keyword extracted in the voice data, comprising:
S501 identifies the voice data by preset speech recognition modeling, and obtains the speech recognition
The target text of model output.
Further, before the step S501, it is also necessary to training speech recognition modeling, so that after training is completed
Speech recognition modeling target text can be identified from voice data.Understandably, the training process tool of speech recognition modeling
Body are as follows: choose the different history voice data of multiple and different call object typings as identification sample, and each identification sample
This, which is corresponding with a speech recognition modeling to be trained, will train the speech text identified, by being equipped with initial parameter
Speech recognition modeling to identification sample identify after, according to the target text of identification of output and with the identification sample
Degree of deviation micro-adjustment initial parameter between corresponding speech text, until finally getting the speech recognition that a training finishes
Model inputs after an identification sample among the speech recognition modeling, the target text of identification that it is exported and with
The degree of deviation between the corresponding speech text of identification sample can control within preset threshold, know at this point, representing to voice
Other model is trained successfully, and trained speech recognition modeling is above-mentioned preset speech recognition modeling.
S502 carries out word segmentation processing to the target text, obtains multiple words.
S503 from the words chosen in default dictionary in the multiple words as the intention keyword, and counts institute
State the quantity of the intention keyword in target text.
Default dictionary refers to dictionary (dictionary composed by the preset words that can be selected as intention keyword
For call object answer words art in problem when it is possible that intention keyword).It include multiple words in default dictionary, for
The words is chosen for intention key if the words is present in default dictionary by the words segmented in target text
Word;If the words is not present in default dictionary, it is determined that the words is not intention keyword, finally determines intention keyword
Quantity.By the above-mentioned means, whether being opinion keyword without each of discrimination objective text words, but directly will
Words is compared with the words in default dictionary, helps to reduce calculation amount, improves the efficiency of intention keyword extraction, more square
Just the quantity of intention keyword is determined.
S60, if the quantity of the intention keyword is greater than or equal to the preset quantity threshold value, it is determined that the calling pair
As for intention user, and switched over current with the ongoing voice communication of intention user according to preset rules.
In this step, when the quantity of intention keyword is greater than or equal to preset quantity threshold value, it can be said that bright calling
Object goes purchase to decision project in the presence of very high intention.In order to improve the marketing success rate to decision project, at this point, server can
With according to preset rules, (preset rules can according to need to be arranged in advance, wherein a kind of preset rules can be to take notice of to pass
The quantity of keyword is greater than or equal under the precondition of preset quantity threshold value, and the quantity of opinion keyword reaches another present count
When measuring threshold value, if preset quantity threshold value can be 10, another preset quantity threshold value can be 18, but opinion keyword reaches
To 20, then voice communication can be switched over to highest priority and not in the artificial customer service of working condition, and opinion
Keyword can be then randomly assigned to each not in the staff of working condition at 10 to 18) switch voice communication to people
Work customer service, and artificial customer service can further be introduced with intention user to decision project.
In one embodiment, the Emotion identification result of call object can be sent to artificial customer service by server, artificial visitor
Clothes, which can shift to an earlier date, makes counter-measure according to the Emotion identification result of call object.
Further, after the step S50, further includes:
If the quantity of the intention keyword is less than the preset quantity threshold value, it is determined that the user is unintended user
And intention deciding grade and level is carried out to the unintended user according to the quantity of the intention keyword, intention deciding grade and level is obtained as a result, and will
The intention deciding grade and level result of the unintended user and the user tag associated storage of the unintended user are in preset data
Library.
In this step, when the quantity of intention keyword is less than preset quantity threshold value, it can be said that bright call object is anticipated
A possibility that purchase to decision project, is very low.At this point, according to the Emotion identification of the quantity of intention keyword and unintended user
As a result intention deciding grade and level is carried out to unintended user, is to improve the marketing to decision project to further excavate unintended user
Success rate.
Further, if the quantity of the intention keyword is less than the preset quantity threshold value, it is determined that the use
Family is unintended user and carries out intention deciding grade and level to the unintended user according to the quantity of the intention keyword, obtains intention
Deciding grade and level result, comprising:
Obtain the Emotion identification result of the unintended user.
Step S401 to S402, the available Emotion identification result to unintended user.
It is given a mark according to the Emotion identification result of the unintended user to the unintended user, obtains the non-meaning
To the first score of user.
In this step, the Emotion identification result of unintended user can wait quietly for glad, indignation, sad, irritated peace
Mood, and Emotion identification result has preset a corresponding score, for example happiness is 10 points, indignation is 1 point, sadness 4
Point, it is irritated be 2 points and calmness is 6 points etc., so that server can be according to the corresponding score of Emotion identification result to unintended use
It gives a mark at family.
It is given a mark, is obtained to the unintended user according to the quantity of the intention keyword of the unintended user
The second score of the unintended user.
In this step, the quantity of each intention keyword has preset a corresponding score, for example, preset quantity
Threshold value is 10, and 0 to 3 is 2 points for 1 point, 3 to 7, and 8 to 9 are 3 points etc., so that server can be according to intention
The corresponding score of the quantity of keyword gives a mark to unintended user.
The intention deciding grade and level score of the unintended user is determined according to the following formula:
S=M*a+N*b
Wherein:
S is the intention deciding grade and level score of the unintended user;
M is the first score of the unintended user;
A is the weight coefficient of the first score of the unintended user, the weight coefficient of first score be set [0,
1] any value between;
N is the second score of the unintended user;
B is the weight coefficient of the second score of the unintended user, the weight coefficient b=1-a of second score.
Unintended user described in the presetting database is determined according to the intention of unintended user deciding grade and level score
The intention deciding grade and level result.
It is understood that the intention deciding grade and level score of unintended user is higher, in the intention deciding grade and level result of unintended user
A possibility that corresponding unintended user is further excavated is very big.
In conclusion above provide a kind of Intelligent Decision-making Methods based on user information analysis, from user list really
A fixed user is call object, and obtains the user tag for corresponding to the call object in the user list, the use
Family label is generated according to the user information of the call object;Acquisition is corresponding with the user tag to decision project, each
It is a described to the corresponding a project information of decision project and a words art template;When receiving call instruction, start outgoing call component
Call the call object corresponding with the user tag;It is logical when being set up by the outgoing call component with the call object
When letter connection, the words art template corresponding with the user tag is called, and language is passed through according to the words art template of calling
Sound assistant introduces the corresponding project information to decision project of the user tag to the call object voice, and
The voice data of the call object feedback corresponding with problem each in the words art template is obtained, the words art template includes
At least more than one the problem of;The intention keyword in the voice data is extracted, and judges the quantity of the intention keyword
Whether preset quantity threshold value is greater than or equal to;If the quantity of the intention keyword is greater than or equal to the preset quantity threshold value,
Then determine the call object be intention user, and according to preset rules will currently with the ongoing voice of intention user
Communication switches over.The present invention extracts call object according to the intention keyword in the voice data of words art template feedback, works as meaning
Preset quantity threshold value is greater than or equal to the quantity of keyword, it is determined that call object is intention user, and according to default rule
Then artificial customer service currently will be switched to the ongoing voice communication of intention user, so as to by carrying out to user information
Precisely after analysis, reduces cost of decision making and improve and treat the probability of success that decision project carries out decision.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of intelligent decision device based on user information analysis is provided, it should be based on user information point
Intelligent Decision-making Method based on user information analysis in the intelligent decision device and above-described embodiment of analysis corresponds.Such as Fig. 7 institute
Show, should include that the first acquisition module 11, second obtains module 12, C module and D based on the intelligent decision device that user information is analyzed
Module.Detailed description are as follows for each functional module:
First obtains module 11, for determining that a user is call object from user list, and obtains the user
Correspond to the user tag of the call object in list, the user tag is raw according to the user information of the call object
At;
Second obtains module 12, and corresponding with the user tag to decision project for obtaining, each is described co-pending
The corresponding a project information of plan project and a words art template;
Calling module 13, for when receiving call instruction, starting outgoing call component calling to be corresponding with the user tag
The call object;
Calling module 14, for calling when setting up communication connection by the outgoing call component and the call object
The words art template corresponding with the user tag, and exhaled by voice assistant to described according to the words art template of calling
It makes object voice introduce the corresponding project information to decision project of the user tag, and obtains and the words art
The voice data of the corresponding call object feedback of each problem in template, the words art template includes at least more than one
Problem;
Judgment module 15 for extracting the intention keyword in the voice data, and judges the intention keyword
Whether quantity is greater than or equal to preset quantity threshold value;
Determining module 16, if the quantity for the intention keyword is greater than or equal to the preset quantity threshold value, really
The fixed call object is intention user, and according to preset rules will currently with the ongoing voice communication of intention user
It switches over.
Further, the intelligent decision device based on user information analysis further include:
Module is established, for establishing the first words art template;
Third obtains module, for obtaining the project information to decision project from presetting database, and will
At least one of the project information and the call object user tag are input to be talked about in art template with described first
Predeterminated position generates the second words art template;
Sending module is checked for sending default auditor for the second words art template;
Second determining module is used for when default auditor's confirmation, determines that the second words art template is
It is described to the corresponding words art template of decision project;
Third determining module is used for when the default auditor checks wrong, then in the default auditor couple
After the second words art template is modified, determine that the modified second words art template is described corresponding to decision project
The words art template.
Further, the intelligent decision device based on user information analysis further include:
4th obtains module, for obtaining the telephone number of the user calling pattern in the user tag, and judges institute
State the significant number whether telephone number belongs to international regulations;
Generation module, if the significant number for belonging to international regulations, generates the call instruction;
Module is removed, if the significant number for being not belonging to international regulations, by the call object from the use
It is removed in name in an account book list.
Further, the telemarketing device further include:
5th obtains module, and the voice data for feeding back to the call object carries out feature extraction, obtains each
Phonetic feature;
6th obtains module, for identifying respectively to each phonetic feature using Emotion identification model, obtains feelings
Thread recognition result.
Further, the judgment module includes:
Acquisition submodule for identifying by preset speech recognition modeling to the voice data, and obtains institute
State the target text of speech recognition modeling output;
Submodule is handled, for carrying out word segmentation processing to the target text, obtains multiple words;
Statistic submodule, for crucial as the intention from the words chosen in the multiple words in default dictionary
Word, and count the quantity of the intention keyword in the target text.
Further, the intelligent decision device based on user information analysis further include:
4th determining module, if the quantity for the intention keyword is less than the preset quantity threshold value, it is determined that institute
It states user to be unintended user and carry out intention deciding grade and level to the unintended user according to the quantity of the intention keyword, obtain
Intention deciding grade and level is as a result, and close the user tag of the intention of unintended user deciding grade and level result and the unintended user
Connection is stored in presetting database.
Further, the 4th determining module includes:
Second acquisition submodule, for obtaining the Emotion identification result of the unintended user;
First marking submodule, for according to the Emotion identification result of the unintended user to the unintended user into
Row marking, obtains the first score of the unintended user;
Second marking submodule, for the quantity according to the intention keyword of the unintended user to the non-meaning
It gives a mark to user, obtains the second score of the unintended user
First determines submodule, for determining the intention deciding grade and level score of the unintended user according to the following formula:
S=M*a+N*b
Wherein:
S is the intention deciding grade and level score of the unintended user;
M is the first score of the unintended user;
A is the weight coefficient of the first score of the unintended user, the weight coefficient of first score be set [0,
1] any value between;
N is the second score of the unintended user;
B is the weight coefficient of the second score of the unintended user, the weight coefficient b=1-a of second score;
Second determines submodule, for determining the presetting database according to the intention of unintended user deciding grade and level score
Described in unintended user the intention define the level result.
Specific restriction about the intelligent decision device analyzed based on user information may refer to above for based on use
The restriction of the Intelligent Decision-making Method of family information analysis, details are not described herein.The above-mentioned intelligent decision dress based on user information analysis
Modules in setting can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be in the form of hardware
It is embedded in or independently of the storage that in the processor in computer equipment, can also be stored in a software form in computer equipment
In device, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 8.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the data being related in the Intelligent Decision-making Method based on user information analysis.The computer is set
Standby network interface is used to communicate with external terminal by network connection.To realize when the computer program is executed by processor
A kind of Intelligent Decision-making Method based on user information analysis.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor are realized in above-described embodiment when executing computer program based on user
The step of Intelligent Decision-making Method of information analysis, such as step S10 shown in Fig. 2 to step S60.Alternatively, processor executes meter
The function of each module/unit of the intelligent decision device based on user information analysis in above-described embodiment is realized when calculation machine program,
Such as module 11 shown in Fig. 7 is to the function of module 16.To avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of Intelligent Decision-making Method based on user information analysis in above-described embodiment when being executed by processor, such as
Step S10 shown in Fig. 2 to step S60.Alternatively, being realized when computer program is executed by processor in above-described embodiment based on use
The function of each module/unit of the intelligent decision device of family information analysis, such as module 11 shown in Fig. 7 is to the function of module 16.
To avoid repeating, which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided by the present invention,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of Intelligent Decision-making Method based on user information analysis characterized by comprising
It determines that a user is call object from user list, and obtains and correspond to the call object in the user list
User tag, the user tag according to the user information of the call object generate;
Obtain it is corresponding with the user tag to decision project, each it is described to the corresponding a project information of decision project with
One words art template;
When receiving call instruction, starting outgoing call component calls the call object corresponding with the user tag;
When setting up communication connection by the outgoing call component and the call object, call corresponding with the user tag
The words art template, and the use is introduced to the call object voice by voice assistant according to the words art template of calling
The corresponding project information to decision project of family label, and obtain corresponding with each problem in the words art template
The problem of voice data of the call object feedback, the words art template includes at least more than one;
The intention keyword in the voice data is extracted, and it is pre- to judge whether the quantity of the intention keyword is greater than or equal to
If amount threshold;
If the quantity of the intention keyword is greater than or equal to the preset quantity threshold value, it is determined that the call object is intention
User, and switched over current with the ongoing voice communication of intention user according to preset rules.
2. it is according to claim 1 based on user information analysis Intelligent Decision-making Method, which is characterized in that it is described acquisition with
Before the corresponding project to decision of the user tag, further includes:
Establish the first words art template;
Obtain the project information to decision project from presetting database, and by the project information and the calling
At least one of object user tag is input to and the predeterminated position in the first words art template, generation the second words art mould
Plate;
Default auditor is sent by the second words art template to check;
When default auditor's confirmation, determine the second words art template to be described to the corresponding institute of decision project
State words art template;
When the default auditor checks wrong, then the second words art template is repaired in the default auditor
After changing, determine that the modified second words art template is described to the corresponding words art template of decision project.
3. the Intelligent Decision-making Method according to claim 1 based on user information analysis, which is characterized in that described to receive
When call instruction, starting outgoing call component is called before the call object corresponding with the user tag, further includes:
The telephone number of the user calling pattern in the user tag is obtained, and judges whether the telephone number belongs to the world
Defined significant number;
If belonging to the significant number of international regulations, the call instruction is generated;
If being not belonging to the significant number of international regulations, the call object is removed from the user list.
4. the Intelligent Decision-making Method according to claim 1 based on user information analysis, which is characterized in that described to pass through
When the outgoing call component and the call object set up communication connection, the words art mould corresponding with the user tag is called
Plate, and the user tag is introduced to the call object voice by voice assistant according to the words art template of calling and is corresponded to
The project information to decision project, and it is anti-to obtain corresponding with problem each in the words art template call object
After the voice data of feedback, further includes:
Feature extraction is carried out to the voice data of call object feedback, obtains each phonetic feature;
Each phonetic feature is identified respectively using Emotion identification model, obtains Emotion identification result.
5. the Intelligent Decision-making Method according to claim 1 based on user information analysis, which is characterized in that the extraction institute
State the intention keyword in voice data, comprising:
The voice data is identified by preset speech recognition modeling, and obtains the speech recognition modeling output
Target text;
Word segmentation processing is carried out to the target text, obtains multiple words;
From the words chosen in default dictionary in the multiple words as the intention keyword, and count the target text
In the intention keyword quantity.
6. the Intelligent Decision-making Method according to claim 1 based on user information analysis, which is characterized in that the judgement institute
Whether the quantity for stating intention keyword is greater than or equal to after preset quantity threshold value, further includes:
If the quantity of the intention keyword is less than the preset quantity threshold value, it is determined that the user is unintended user and root
Intention deciding grade and level is carried out to the unintended user according to the quantity of the intention keyword, obtains intention deciding grade and level as a result, and will be described
The intention deciding grade and level result of unintended user and the user tag associated storage of the unintended user are in presetting database.
7. the Intelligent Decision-making Method according to claim 6 based on user information analysis, which is characterized in that if described
The quantity of intention keyword is less than the preset quantity threshold value, it is determined that the user is for unintended user and according to the intention
The quantity of keyword carries out intention deciding grade and level to the unintended user, obtains intention deciding grade and level result, comprising:
Obtain the Emotion identification result of the unintended user;
It is given a mark according to the Emotion identification result of the unintended user to the unintended user, obtains the unintended use
First score at family;
It is given a mark, is obtained described to the unintended user according to the quantity of the intention keyword of the unintended user
The second score of unintended user;
The intention deciding grade and level score of the unintended user is determined according to the following formula:
S=M*a+N*b
Wherein:
S is the intention deciding grade and level score of the unintended user;
M is the first score of the unintended user;
A is the weight coefficient of the first score of the unintended user, the weight coefficient of first score be set [0,1] it
Between any value;
N is the second score of the unintended user;
B is the weight coefficient of the second score of the unintended user, the weight coefficient b=1-a of second score;
It is determined described in unintended user described in the presetting database according to the intention of unintended user deciding grade and level score
Intention deciding grade and level result.
8. a kind of intelligent decision device based on user information analysis characterized by comprising
First obtains module, for determining that a user is call object from user list, and obtains in the user list
Corresponding to the user tag of the call object, the user tag is generated according to the user information of the call object;
Second obtains module, and corresponding with the user tag to decision project for obtaining, each is described to decision project
Corresponding portion project information and a words art template;
Calling module is exhaled for when receiving call instruction, described in starting outgoing call component calling is corresponding with the user tag
It is object;
Calling module, for when setting up communication connection by the outgoing call component and the call object, call with it is described
The corresponding words art template of user tag, and voice assistant is passed through to the call object according to the words art template of calling
Voice introduces the corresponding project information to decision project of the user tag, and in acquisition and the words art template
The problem of voice data of the corresponding call object feedback of each problem, the words art template includes at least more than one;
Judgment module for extracting the intention keyword in the voice data, and judges that the quantity of the intention keyword is
It is no to be greater than or equal to preset quantity threshold value;
Determining module, if the quantity for the intention keyword is greater than or equal to the preset quantity threshold value, it is determined that described
Call object is intention user, and communicate cutting with the ongoing voice of intention user by current according to preset rules
It changes.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
Intelligent Decision-making Method based on user information analysis described in any one of 7.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization is analyzed as described in any one of claims 1 to 7 based on user information when the computer program is executed by processor
Intelligent Decision-making Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910429738.2A CN110298682A (en) | 2019-05-22 | 2019-05-22 | Intelligent Decision-making Method, device, equipment and medium based on user information analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910429738.2A CN110298682A (en) | 2019-05-22 | 2019-05-22 | Intelligent Decision-making Method, device, equipment and medium based on user information analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110298682A true CN110298682A (en) | 2019-10-01 |
Family
ID=68027088
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910429738.2A Pending CN110298682A (en) | 2019-05-22 | 2019-05-22 | Intelligent Decision-making Method, device, equipment and medium based on user information analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110298682A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110852799A (en) * | 2019-11-07 | 2020-02-28 | 北京集奥聚合科技有限公司 | User screening method and device based on intention label, electronic equipment and medium |
CN111091832A (en) * | 2019-11-28 | 2020-05-01 | 秒针信息技术有限公司 | Intention assessment method and system based on voice recognition |
CN111371959A (en) * | 2020-03-17 | 2020-07-03 | 集奥聚合(北京)人工智能科技有限公司 | Intelligent voice data processing method and device |
CN111539221A (en) * | 2020-05-13 | 2020-08-14 | 北京焦点新干线信息技术有限公司 | Data processing method and system |
CN111653262A (en) * | 2020-08-06 | 2020-09-11 | 上海荣数信息技术有限公司 | Intelligent voice interaction system and method |
CN111709864A (en) * | 2020-06-11 | 2020-09-25 | 湖北美和易思教育科技有限公司 | Automatic classification analysis method and device based on student intention |
CN111916111A (en) * | 2020-07-20 | 2020-11-10 | 中国建设银行股份有限公司 | Intelligent voice outbound method and device with emotion, server and storage medium |
CN112435047A (en) * | 2020-10-30 | 2021-03-02 | 四川新网银行股份有限公司 | Marketing outbound data recommendation method based on buried point data |
CN113420140A (en) * | 2021-08-24 | 2021-09-21 | 北京明略软件系统有限公司 | User emotion prediction method and device, electronic equipment and readable storage medium |
CN114860912A (en) * | 2022-05-20 | 2022-08-05 | 马上消费金融股份有限公司 | Data processing method and device, electronic equipment and storage medium |
CN115499547A (en) * | 2022-10-20 | 2022-12-20 | 深圳市八度云计算信息技术有限公司 | Cloud call management system |
CN115914468A (en) * | 2023-03-09 | 2023-04-04 | 成都秦川物联网科技股份有限公司 | Feedback management method, internet of things system and medium for intelligent gas call center |
CN115905502A (en) * | 2022-07-19 | 2023-04-04 | 北京中关村科金技术有限公司 | Method, device and storage medium for mining and recommending dialect |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109033257A (en) * | 2018-07-06 | 2018-12-18 | 中国平安人寿保险股份有限公司 | Talk about art recommended method, device, computer equipment and storage medium |
CN109120804A (en) * | 2017-06-26 | 2019-01-01 | 浙江金讯网络技术股份有限公司 | A kind of outer paging system based on response message identification |
CN109462707A (en) * | 2018-11-13 | 2019-03-12 | 平安科技(深圳)有限公司 | Method of speech processing, device and computer equipment based on automatic outer call system |
CN109767765A (en) * | 2019-01-17 | 2019-05-17 | 平安科技(深圳)有限公司 | Talk about art matching process and device, storage medium, computer equipment |
CN109767791A (en) * | 2019-03-21 | 2019-05-17 | 中国—东盟信息港股份有限公司 | A kind of voice mood identification and application system conversed for call center |
-
2019
- 2019-05-22 CN CN201910429738.2A patent/CN110298682A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109120804A (en) * | 2017-06-26 | 2019-01-01 | 浙江金讯网络技术股份有限公司 | A kind of outer paging system based on response message identification |
CN109033257A (en) * | 2018-07-06 | 2018-12-18 | 中国平安人寿保险股份有限公司 | Talk about art recommended method, device, computer equipment and storage medium |
CN109462707A (en) * | 2018-11-13 | 2019-03-12 | 平安科技(深圳)有限公司 | Method of speech processing, device and computer equipment based on automatic outer call system |
CN109767765A (en) * | 2019-01-17 | 2019-05-17 | 平安科技(深圳)有限公司 | Talk about art matching process and device, storage medium, computer equipment |
CN109767791A (en) * | 2019-03-21 | 2019-05-17 | 中国—东盟信息港股份有限公司 | A kind of voice mood identification and application system conversed for call center |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110852799A (en) * | 2019-11-07 | 2020-02-28 | 北京集奥聚合科技有限公司 | User screening method and device based on intention label, electronic equipment and medium |
CN111091832B (en) * | 2019-11-28 | 2022-12-30 | 秒针信息技术有限公司 | Intention assessment method and system based on voice recognition |
CN111091832A (en) * | 2019-11-28 | 2020-05-01 | 秒针信息技术有限公司 | Intention assessment method and system based on voice recognition |
CN111371959A (en) * | 2020-03-17 | 2020-07-03 | 集奥聚合(北京)人工智能科技有限公司 | Intelligent voice data processing method and device |
CN111539221A (en) * | 2020-05-13 | 2020-08-14 | 北京焦点新干线信息技术有限公司 | Data processing method and system |
CN111539221B (en) * | 2020-05-13 | 2023-09-12 | 北京焦点新干线信息技术有限公司 | Data processing method and system |
CN111709864A (en) * | 2020-06-11 | 2020-09-25 | 湖北美和易思教育科技有限公司 | Automatic classification analysis method and device based on student intention |
CN111916111A (en) * | 2020-07-20 | 2020-11-10 | 中国建设银行股份有限公司 | Intelligent voice outbound method and device with emotion, server and storage medium |
CN111653262A (en) * | 2020-08-06 | 2020-09-11 | 上海荣数信息技术有限公司 | Intelligent voice interaction system and method |
CN112435047A (en) * | 2020-10-30 | 2021-03-02 | 四川新网银行股份有限公司 | Marketing outbound data recommendation method based on buried point data |
CN113420140B (en) * | 2021-08-24 | 2021-12-28 | 北京明略软件系统有限公司 | User emotion prediction method and device, electronic equipment and readable storage medium |
CN113420140A (en) * | 2021-08-24 | 2021-09-21 | 北京明略软件系统有限公司 | User emotion prediction method and device, electronic equipment and readable storage medium |
CN114860912A (en) * | 2022-05-20 | 2022-08-05 | 马上消费金融股份有限公司 | Data processing method and device, electronic equipment and storage medium |
CN114860912B (en) * | 2022-05-20 | 2023-08-29 | 马上消费金融股份有限公司 | Data processing method, device, electronic equipment and storage medium |
CN115905502A (en) * | 2022-07-19 | 2023-04-04 | 北京中关村科金技术有限公司 | Method, device and storage medium for mining and recommending dialect |
CN115905502B (en) * | 2022-07-19 | 2024-01-05 | 北京中关村科金技术有限公司 | Speaking skill mining and recommending method, device and storage medium |
CN115499547A (en) * | 2022-10-20 | 2022-12-20 | 深圳市八度云计算信息技术有限公司 | Cloud call management system |
CN115914468A (en) * | 2023-03-09 | 2023-04-04 | 成都秦川物联网科技股份有限公司 | Feedback management method, internet of things system and medium for intelligent gas call center |
US11870937B2 (en) | 2023-03-09 | 2024-01-09 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods for smart gas call center feedback management and Internet of things (IoT) systems thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110298682A (en) | Intelligent Decision-making Method, device, equipment and medium based on user information analysis | |
CN110472224B (en) | Quality of service detection method, apparatus, computer device and storage medium | |
CN108509596B (en) | Text classification method and device, computer equipment and storage medium | |
CN110084636A (en) | Improve telemarketing efficiency method, device, computer equipment and storage medium | |
CN110493019B (en) | Automatic generation method, device, equipment and storage medium of conference summary | |
CN111309887B (en) | Method and system for training text key content extraction model | |
CN112468659B (en) | Quality evaluation method, device, equipment and storage medium applied to telephone customer service | |
CN109885828A (en) | Word error correction method, device, computer equipment and medium based on language model | |
CN110569356A (en) | interviewing method and device based on intelligent interviewing interaction system and computer equipment | |
CN109344823B (en) | OCR deep learning method based on block chain mechanism and storage medium | |
CN109766419A (en) | Products Show method, apparatus, equipment and storage medium based on speech analysis | |
CN111597818A (en) | Call quality inspection method, call quality inspection device, computer equipment and computer readable storage medium | |
CN112434501A (en) | Work order intelligent generation method and device, electronic equipment and medium | |
CN110288192A (en) | Quality detecting method, device, equipment and storage medium based on multiple Checking models | |
CN112699923A (en) | Document classification prediction method and device, computer equipment and storage medium | |
CN110728182A (en) | Interviewing method and device based on AI interviewing system and computer equipment | |
CN111444677A (en) | Reading model optimization method, device, equipment and medium based on big data | |
CN113343677B (en) | Intention identification method and device, electronic equipment and storage medium | |
CN115034886A (en) | Default risk prediction method and device | |
CN113591463A (en) | Intention recognition method and device, electronic equipment and storage medium | |
CN112288584A (en) | Insurance application processing method and device, computer readable medium and electronic equipment | |
CN117093682A (en) | Intention recognition method, device, computer equipment and storage medium | |
CN115393077B (en) | Data processing method based on loan transaction man-machine conversation system and related device | |
CN117237479A (en) | Product style automatic generation method, device and equipment based on diffusion model | |
CN116150319A (en) | Auxiliary answering method, device, electronic equipment and storage medium |
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 |