CN106709804A - Interactive wealth planning consulting robot system - Google Patents

Interactive wealth planning consulting robot system Download PDF

Info

Publication number
CN106709804A
CN106709804A CN201510779046.2A CN201510779046A CN106709804A CN 106709804 A CN106709804 A CN 106709804A CN 201510779046 A CN201510779046 A CN 201510779046A CN 106709804 A CN106709804 A CN 106709804A
Authority
CN
China
Prior art keywords
operator
information
wealth
recognition
live body
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
CN201510779046.2A
Other languages
Chinese (zh)
Inventor
邓庆平
许方
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.)
Shanghai Yihui Information Technology Co ltd
Original Assignee
Optimization Technology (suzhou) Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Optimization Technology (suzhou) Co Ltd filed Critical Optimization Technology (suzhou) Co Ltd
Priority to CN201510779046.2A priority Critical patent/CN106709804A/en
Publication of CN106709804A publication Critical patent/CN106709804A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06Asset management; Financial planning or analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31User authentication
    • G06F21/32User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • Computer Security & Cryptography (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention discloses an interactive wealth planning consultation robot system. After the identity information of a customer is validated, a human living body identity authentication module is started, a wealth planning consultation system is started after identity authentication is successful, the wealth planning consultation system provides a set of complete and detailed wealth planning investment proposals for the customer, the web link of the completed wealth planning investment proposals is sent to the mobile phone terminal of the customer through SMS, WeChat or e-mail, and the investment can be directly completed after the customer clicks the web link of the SMS, WeChat or e-mail. Compared with the prior art, a variety of biological characteristics are integrated in the human living body identity authentication, the customer and intelligent living body identity and emotion states are verified at the same, the system is safe and reliable, wealth planning consultation service is provided for the customer, a lot of manpower and resources are saved, and the system is convenient for popularization and application.

Description

A kind of interactive wealth Planning consultation robot system
Technical field
The present invention relates to a kind of interactive wealth Planning consultation robot system, more particularly to wealth Planning consultation robot system.
Background technology
Since reforming and opening up to the outside world more than 30 years, based on powerful, the lasting economic growth of China, Chinese national wealth realizes Rapid Accumulation, Chinese affluence population ratio is continuously increased, current middle class number is up to 1.09 hundred million, the hat in the whole world is occupied, in addition continuous lifting of the society to financial investment knowledge and theory, made wealth planning management market scale with 25% annual average compound growth rate rapid growth.Arise at the historic moment in the one Wealth management market for shooting up.At present, China exceedes Japan finally, and as the second-biggest-in-the-world economy being only second to after the U.S., Chinese private wealth alreadys exceed 120 trillion yuans.Greatly develop individual wealth management business, the need for national wealth management is met, the need for being also operation core competitiveness, transformation banking structure and the profit model for lifting private bank and other wealth planning management units, even more make full use of private bank's asset management service platform circulation social funds, correct guidance social capital, immense amount of treasure is imported into real economy, the need for promoting real economy to develop.From for State-level, wealth planning management business is included the huge non-governmental capital outside national Financial Management channel in national Financial Management channel by this finance activities;In case country's finance order is upset in the irrational flowing of a large amount of non-governmental capitals.Therefore, when country is quite rich(Possess a large amount of wealthy families and a large amount of wealth among the people)When, carry out this business relations of wealth planning management to national interests.
The wealth that low net value personage of the China more than 93% is possessed with the family of largely common middle net value personages is close to 40%, and domestic low net value personage is with the crowd that commonly middle net value personage is covered widely, and number is especially huge.But, their demand for services is less, it is desirable to not high, and the degree of product standardization is higher.The wealth planning management business in this market should be well worth doing.But, due to their crowds, widely number is especially huge, if being all impossible on manpower or material resources by the business personnel of bank for they directly provide service.Therefore, it is necessary to develop a set of interactive wealth Planning consultation robot system of design,It is that vast low net value personage and a large amount of common middle net value personages provide self-service wealth planning management service.
The content of the invention
The purpose of the present invention is to overcome the deficiencies in the prior art, there is provided a kind of wealth Planning consultation robot system.
To achieve these goals, the technical solution adopted in the present invention is as follows:
A kind of interactive wealth Planning consultation robot system, including bank card card interface, identity card radio frequency reader, true man's live body authentication module, voice interaction module, wealth Planning consultation subsystem, secondary module, it is characterised in that:If new client, identity card is placed in identity card radio frequency reader, identity information online checking is carried out by bank interface, verification starts true man's live body authentication module after passing through;If frequent customer, insertion bank card places identity card in identity card radio frequency reader, robot reads identity card or bank card chip information, after identity information checking effectively, start true man's live body authentication module, authentication starts wealth Planning consultation subsystem after passing through, wealth Planning consultation subsystem provides complete set detailed wealth planning suggestion for investment book for client, after the completion of wealth planning suggestion for investment book web page interlinkage be sent on the mobile phone terminal of client by short message or wechat or Email, after client clicks on the link of short message or wechat or Email, investment can be done directly to place an order purchase, then transaction record is exported, transaction record gives client by short message or wechat or Email.
After starting wealth Planning consultation subsystem, customer data is read according to customer information by data platform, improve the essential information and financial investment information of client, investment survey is carried out to client, judge the investment types and risk partiality of client, according to the financial information of client, investment types and risk partiality, for lead referral optimization of investment is combined, replacement investment product and its ratio, and with the simulation of science, use model's Monte Carlo Simulation of Ions Inside, confidence index is analyzed, effective frontal line analysis, and test analysis backward, simulate the expected asset transition and expected value of planning, according to data analysis for client provides complete set detailed Asset Allocation report.
In true man's live body authentication module, face recognition database, Application on Voiceprint Recognition database, lipreading recognition database, speech recognition database, micro- Expression Recognition database and emotion recognition database are set;Video information and audio-frequency information during acquisition operations person's random preset content of reading;Human face image information is extracted according to the video information compared with the data in face recognition database pair or/and right compared with the data in Application on Voiceprint Recognition database according to the audio information voiceprint, if comparing successfully, operator is me, and otherwise operator is not me;Continuous lip image information is extracted according to the video information right compared with the data in lip reading database, identify that lip is semantic and is compared or/and right compared with the data in speech recognition database according to the audio information voice messaging with random preset content, that identifies is semantic right compared with random preset content, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body;Continuous facial image is extracted according to described video information, the expression shape change of operator is recognized by algorithm, judge whether it is live body;According to described audio-frequency information, audio frequency characteristics are extracted, according to affection data storehouse, the emotion of identification operator, emotion recognition is divided into happiness, excited, normal, indignation and fear, when the emotion recognition of operator is glad or normal, is verified;When the emotion recognition of operator is other three kinds of states, checking is jumped out;If operator is I and intelligent live body and during for normal emotion, authentication success, the i.e. operator are strictly the true man's intelligence live body with normal emotion, otherwise authentication failure.
The face recognition database includes face template storehouse, the face template storehouse includes true man's human face image information, true man's human face image information in the face template storehouse carries out recognition of face and compares with the human face image information of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
The recognition of face is mainly included the following steps that:Face datection, face tracking, image quality analysis, facial image pretreatment, face characteristic are extracted and face alignment identification.
The Application on Voiceprint Recognition database includes my voiceprint, and the true man's voiceprint in the Application on Voiceprint Recognition database carries out Application on Voiceprint Recognition and compares with the voiceprint of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
The Application on Voiceprint Recognition is mainly included the following steps that:Voice is pre-processed, extracted the characteristic parameter of each frame voice signal and the parameter extracted is classified using grader, identifies speaker.
The lipreading recognition database includes standard lip image information, standard lip image information in the lipreading recognition database carries out lipreading recognition and compares with the continuous lip image information of the operator for extracting, identify the semanteme of lip image, contrasted with random default semantic content, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body.
The lipreading recognition is mainly included the following steps that:Image preprocessing, lip positioning, lip outline extraction, the extraction of lip Contour extraction, lip contour feature, tagsort and lip matching identification.
The speech recognition database includes received pronunciation information, received pronunciation information in the speech recognition database carries out speech recognition identification with the voice messaging of the operator for extracting, the semanteme for identifying is compared with semanteme is randomly generated, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body.
The speech recognition is mainly included the following steps that:Voice pretreatment, speech feature extraction, feature mode identification and output voice identification result.
The preset content includes voice messaging or text information, and the text information includes any one character or any combination character in word, letter and number.
Compared with prior art, the beneficial effect of interactive wealth Planning consultation robot system of the invention is:Old and new customers is after true man's live body authentication system verifies identity, after being interacted with robot system, after improving customer information, the detailed wealth planning suggestion for investment book of robot system generation complete set, after the completion of wealth planning suggestion for investment book web page interlinkage be sent on the mobile phone terminal of client by short message or wechat or Email, after client clicks on the link of short message or wechat or Email, investment can be done directly to place an order purchase, then transaction record is exported, transaction record gives client by short message or wechat or Email, this greatlys save manpower and materials.
Brief description of the drawings
Fig. 1 is wealth Planning consultation robot system architecture's block diagram of the invention;
Fig. 2 is wealth Planning consultation robot system flow chart of the invention;
Fig. 3 is wealth Planning consultation subsystem flow chart of the invention;
Fig. 4 is the FB(flow block) of face recognition module of the present invention;
Fig. 5 is the FB(flow block) of voiceprint identification module of the present invention;
Fig. 6 is the FB(flow block) of lipreading recognition of the present invention;
Fig. 7 is the FB(flow block) of speech recognition of the present invention;
Fig. 8 is the FB(flow block) of emotion recognition of the present invention.
Specific embodiment
With reference to specific accompanying drawing and embodiment, the present invention is described further.
As shown in figure 1, wealth Planning consultation robot system of the invention includes bank card card interface, identity card radio frequency reader, true man's live body authentication module, voice interaction module, wealth Planning consultation subsystem, secondary module.
As Figure 2-3, if new client is placing identity card in identity card radio frequency reader, identity information online checking is carried out by bank interface, verification starts true man's live body authentication module after passing through;If frequent customer, insertion bank card places identity card in identity card radio frequency reader, robot reads identity card or bank card chip information, after identity information checking effectively, start true man's live body authentication module, then being he or she is made whether to client, whether be intelligent live body authentication, and verify the current affective state of client, confirming the clear-headed reason of client, on the premise of free will, robot automatic wealth Planning consultation subsystem, and be displayed on the touch-screen of robot, voice guide client completes wealth Planning consultation content.First it is that robot reads customer data by data platform according to customer information, improve the essential information and financial investment information of client, during improving, client can be by phonetic entry, by after system voice identification, as input content, it is also possible to which selection is input on the touch-screen beside robot;After client confirms, investment survey is carried out to client, judge the investment types and risk partiality of client;Financial information, investment types and risk partiality according to client, for lead referral optimization of investment is combined, replacement investment product and its ratio, and with the simulation of science, use model's Monte Carlo Simulation of Ions Inside, confidence index analysis, effective frontal line analysis, and test analysis etc. backward, the expected asset transition and expected value of planning are simulated, robot can be reported according to data analysis for client provides the detailed Asset Allocation of complete set.In the process, the step of client both can complete wealth Planning consultation with voice, it is also possible to which information input is completed by touch-screen.After the completion of wealth planning suggestion for investment book web page interlinkage be sent on the mobile phone terminal of client by short message or wechat or Email, after client clicks on the link of short message or wechat or Email, investment can be done directly to place an order purchase, then transaction record is exported, transaction record gives client by short message or wechat or Email.
In true man's live body authentication module, using based on figure as true man's live body auth method of feature, face recognition database, Application on Voiceprint Recognition database, lipreading recognition database and speech recognition database are set, true man's live body checking of new client is main using sound identification module, micro- Expression Recognition module, lip reading identification module, emotion recognition module and face recognition module, and new face characteristic, the vocal print feature for opening client of training study in the process.True man's live body checking of old user uses sound identification module, voiceprint identification module, micro- Expression Recognition module, lip reading identification module, emotion recognition module and face recognition module.When operator is when newly opening client, video information and audio-frequency information during acquisition operations person's reading preset content, the preset content includes voice messaging or text information, and the text information includes any one character or any combination character in word, letter and number;Right compared with the data in face recognition database according to video information extraction human face image information, if comparing successfully, operator is me, and otherwise operator is not me;Lip image information is extracted according to the video information right compared with the data in lip reading identification database, identify the semanteme of lip reading, and it is compared with the semanteme for randomly generating pair or/and right compared with the data in speech recognition database according to the audio information voice messaging, identify the semantic and right compared with the semanteme for randomly generating of voice, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body;Continuous facial image is extracted according to described video information, the expression shape change of operator is recognized by algorithm, judge whether it is live body;According to described audio-frequency information, audio frequency characteristics are extracted, according to affection data storehouse, the emotion of identification operator, emotion recognition is divided into happiness, excited, normal, indignation and fear, when the emotion recognition of operator is glad or normal, is verified;When the emotion recognition of operator is other three kinds of states, checking is jumped out;If operator is I and intelligent live body and during for normal emotion, authentication success, the i.e. operator are strictly the true man's intelligence live body with normal emotion;Otherwise authentication failure.When operator is frequent customer, video information and audio-frequency information during acquisition operations person's reading preset content, the preset content includes voice messaging or text information, and the text information includes any one character or any combination character in word, letter and number;Human face image information is extracted according to the video information compared with the data in face recognition database pair or/and right compared with the data in Application on Voiceprint Recognition database according to the audio information voiceprint, if comparing successfully, operator is me, and otherwise operator is not me;Lip image information is extracted according to the video information right compared with the data in lip reading identification database, identify the semanteme of lip reading, and it is compared with the semanteme for randomly generating pair or/and right compared with the data in speech recognition database according to the audio information voice messaging, identify the semantic and right compared with the semanteme for randomly generating of voice, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body;Continuous facial image is extracted according to described video information, the expression shape change of operator is recognized by algorithm, judge whether it is live body;According to described audio-frequency information, audio frequency characteristics are extracted, according to affection data storehouse, the emotion of identification operator, emotion recognition is divided into happiness, excited, normal, indignation and fear, when the emotion recognition of operator is glad or normal, is verified;When the emotion recognition of operator is other three kinds of states, checking is jumped out;If operator is I and intelligent live body and during for normal emotion, authentication success, the i.e. operator are strictly the true man's intelligence live body with normal emotion;Otherwise authentication failure.
In an embodiment of the present invention, the true man's human face image information in the face template storehouse carries out recognition of face and compares with the human face image information of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
In an embodiment of the present invention, the true man's human face image information in the face template storehouse carries out recognition of face and compares with the human face image information of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
Refer to shown in Fig. 4, face recognition module is mainly included the following steps that:Face datection, face tracking, image quality analysis, facial image pretreatment, face characteristic are extracted and face alignment identification.Facial image is done the methods such as color range, contrast, color balance, sharpening, noise reduction, deblurring, histogram equalization, super resolution by facial image pretreatment to be strengthened.Face datection algorithm extracts the feature of face, it is classified using adboost cascade classifiers afterwards, the face position of face is extracted, the face to extracting uses image tracking algorithm, and face is tracked, ensure it is same people, and preferred several high-quality pictures, the feature for recognition of face is extracted from human face photo, and dimension-reduction treatment is carried out to data with principal component analysis algorithm, face feature vector is formed, face identity is identified using sorting algorithm.
In an alternative embodiment of the invention, the true man's voiceprint in the Application on Voiceprint Recognition database carries out Application on Voiceprint Recognition and compares with the voiceprint of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
Refer to shown in Fig. 5, voiceprint identification module is mainly included the following steps that:Voice is pre-processed, extracted the characteristic parameter of each frame voice signal and the parameter extracted is classified using grader, identifies speaker.Voice pretreatment is the speech-sound data sequence to being input into(PCM code streams)Carry out framing, calculate the cumlative energy of each frame speech data, extract the speech data with information, speech data with information is processed by high-pass filter preemphasis, voice signal after treatment is divided into short time interval one by one, then window function will be multiplied by per frame again, to increase the continuity of every frame left end and right-hand member, each frame signal after to framing adding window enters the frequency spectrum that line translation obtains each frame, the characteristic vector of every section of voice is extracted according to frequency spectrum, has characteristic vector according to deep neural network or other graders and ATL identification vocal print identity.
The standard lip image information in the lipreading recognition database carries out lipreading recognition and compares with the lip image information of the operator for extracting in an embodiment of the present invention, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body.
Refer to shown in Fig. 6, lipreading recognition module is mainly included the following steps that:Image preprocessing, lip positioning, lip outline extraction, the extraction of lip Contour extraction, lip contour feature, tagsort and lip matching identification.Lip positioning is in the facial image region that above-mentioned Face datection is positioned, priori according to lip site color distinguishes lip and the colour of skin, and strengthen lip region color, and the coarse positioning of lip is completed using binary image, realize lip fine positioning in conjunction with lip color model.It is initial curve that lip is extracted by morphology processing that lip outline is extracted, then by extracting the contour curve of lip based on contour extraction method.Lip Contour extraction is tracked using optical flow method or meanshift to sequence image, and next frame initial profile is predicted, the feature point set vector of lip profile is extracted, according to characteristic vector and training ATL, the identification of lip reading is carried out using artificial intelligence sorting algorithm.
In an alternative embodiment of the invention, the received pronunciation information in the speech recognition database carries out speech recognition and compares with the voice messaging of the operator for extracting, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body.
Refer to shown in Fig. 7, sound identification module is mainly included the following steps that:Voice pretreatment, speech feature extraction, feature mode identification and output voice identification result.The characteristic parameter of each frame voice signal is extracted, the parameter extracted is classified using grader, identify speaker.Voice pretreatment is to carry out framing to the voice being input into, calculate the cumlative energy of each frame speech data, extract the speech data with information, a state network is built using hidden Markov model, the path that searching is most matched with sound from state network, construction word level network, is launched into phoneme network and state network.Then an optimal path, the maximum probability between this paths and voice are searched in state network.Using the searching algorithm for calculating Dynamic Programming beta pruning, for finding global optimum path, current speech content is identified according to state transfer.
Refer to shown in Fig. 8, emotion recognition module is mainly included the following steps that:Voice pretreatment, characteristic parameter extraction, characteristic parameter and five kinds of emotion parameters compare, grader is classified, the output of affective state recognition result.First-selection is pre-processed to voice signal, then characteristic parameter is extracted to pretreated voice signal, characteristic parameter and five kinds of basic emotion parameters after extraction compare, then characteristic parameter is classified by grader, determine the corresponding affective state parameter of characteristic parameter, finally export affective state recognition result.
Schematical above that the present invention and embodiments thereof are described, the description does not have restricted, and shown in accompanying drawing is also one of embodiments of the present invention, and actual structure is not limited thereto.So, if one of ordinary skill in the art is enlightened by it, in the case where the invention objective is not departed from, frame mode and the embodiment similar to the technical scheme is designed without creative, protection scope of the present invention all should be belonged to.

Claims (12)

1. a kind of interactive wealth Planning consultation robot system, including bank card card interface, identity card radio frequency reader, true man's live body authentication module, voice interaction module, wealth Planning consultation subsystem, secondary module, it is characterised in that:If new client, identity card is placed in identity card radio frequency reader, identity information online checking is carried out by bank interface, verification starts true man's live body authentication module after passing through;If frequent customer, insertion bank card places identity card in identity card radio frequency reader, robot reads identity card or bank card chip information, after identity information checking effectively, start true man's live body authentication module, authentication starts wealth Planning consultation subsystem after passing through, wealth Planning consultation subsystem provides complete set detailed wealth planning suggestion for investment book for client, after the completion of wealth planning suggestion for investment book web page interlinkage be sent on the mobile phone terminal of client by short message or wechat or Email, after client clicks on the link of short message or wechat or Email, investment can be done directly to place an order purchase, then transaction record is exported, transaction record gives client by short message or wechat or Email.
2. a kind of interactive wealth Planning consultation robot system as claimed in claim 1, it is characterised in that:After starting wealth Planning consultation subsystem, customer data is read according to customer information by data platform, improve the essential information and financial investment information of client, investment survey is carried out to client, judge the investment types and risk partiality of client, according to the financial information of client, investment types and risk partiality, for lead referral optimization of investment is combined, replacement investment product and its ratio, and with the simulation of science, use model's Monte Carlo Simulation of Ions Inside, confidence index is analyzed, effective frontal line analysis, and test analysis backward, simulate the expected asset transition and expected value of planning, according to data analysis for client provides complete set detailed Asset Allocation report.
3. a kind of interactive wealth Planning consultation robot system as claimed in claim 1, it is characterised in that:In true man's live body authentication module, face recognition database, Application on Voiceprint Recognition database, lipreading recognition database, speech recognition database, micro- Expression Recognition database and emotion recognition database are set;Video information and audio-frequency information during acquisition operations person's random preset content of reading;Human face image information is extracted according to the video information compared with the data in face recognition database pair or/and right compared with the data in Application on Voiceprint Recognition database according to the audio information voiceprint, if comparing successfully, operator is me, and otherwise operator is not me;Continuous lip image information is extracted according to the video information right compared with the data in lip reading database, identify that lip is semantic and is compared or/and right compared with the data in speech recognition database according to the audio information voice messaging with random preset content, that identifies is semantic right compared with random preset content, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body;Continuous facial image is extracted according to described video information, the expression shape change of operator is recognized by algorithm, judge whether it is live body;According to described audio-frequency information, audio frequency characteristics are extracted, according to affection data storehouse, the emotion of identification operator, emotion recognition is divided into happiness, excited, normal, indignation and fear, when the emotion recognition of operator is glad or normal, is verified;When the emotion recognition of operator is other three kinds of states, checking is jumped out;If operator is I and intelligent live body and during for normal emotion, authentication success, the i.e. operator are strictly the true man's intelligence live body with normal emotion, otherwise authentication failure.
4. a kind of interactive wealth Planning consultation robot system as claimed in claim 3, it is characterized in that, the face recognition database includes face template storehouse, the face template storehouse includes true man's human face image information, true man's human face image information in the face template storehouse carries out recognition of face and compares with the human face image information of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
5. a kind of interactive wealth Planning consultation robot system as claimed in claim 3, it is characterised in that the recognition of face is mainly included the following steps that:Face datection, face tracking, image quality analysis, facial image pretreatment, face characteristic are extracted and face alignment identification.
6. a kind of interactive wealth Planning consultation robot system as claimed in claim 3, it is characterized in that, the Application on Voiceprint Recognition database includes my voiceprint, true man's voiceprint in the Application on Voiceprint Recognition database carries out Application on Voiceprint Recognition and compares with the voiceprint of the operator for extracting, if comparing successfully, operator is me, and otherwise operator is not me.
7. a kind of interactive wealth Planning consultation robot system as claimed in claim 3, it is characterised in that the Application on Voiceprint Recognition is mainly included the following steps that:Voice is pre-processed, extracted the characteristic parameter of each frame voice signal and the parameter extracted is classified using grader, identifies speaker.
8. a kind of interactive wealth Planning consultation robot system as claimed in claim 3, it is characterized in that, the lipreading recognition database includes standard lip image information, standard lip image information in the lipreading recognition database carries out lipreading recognition and compares with the continuous lip image information of the operator for extracting, the semanteme of lip image is identified, is contrasted with random default semantic content, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body.
9. a kind of interactive wealth Planning consultation robot system as claimed in claim 8, it is characterised in that the lipreading recognition is mainly included the following steps that:Image preprocessing, lip positioning, lip outline extraction, the extraction of lip Contour extraction, lip contour feature, tagsort and lip matching identification.
10. a kind of interactive wealth Planning consultation robot system as claimed in claim 3, it is characterized in that, the speech recognition database includes received pronunciation information, received pronunciation information in the speech recognition database carries out speech recognition identification with the voice messaging of the operator for extracting, the semanteme for identifying is compared with semanteme is randomly generated, if comparing successfully, operator is intelligent live body, and otherwise operator is not intelligent live body.
11. a kind of interactive wealth Planning consultation robot systems as claimed in claim 10, it is characterised in that the speech recognition is mainly included the following steps that:Voice pretreatment, speech feature extraction, feature mode identification and output voice identification result.
A kind of 12. interactive wealth Planning consultation robot systems as claimed in claim 3, it is characterized in that, the preset content includes voice messaging or text information, and the text information includes any one character or any combination character in word, letter and number.
CN201510779046.2A 2015-11-16 2015-11-16 Interactive wealth planning consulting robot system Pending CN106709804A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510779046.2A CN106709804A (en) 2015-11-16 2015-11-16 Interactive wealth planning consulting robot system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510779046.2A CN106709804A (en) 2015-11-16 2015-11-16 Interactive wealth planning consulting robot system

Publications (1)

Publication Number Publication Date
CN106709804A true CN106709804A (en) 2017-05-24

Family

ID=58931398

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510779046.2A Pending CN106709804A (en) 2015-11-16 2015-11-16 Interactive wealth planning consulting robot system

Country Status (1)

Country Link
CN (1) CN106709804A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107315409A (en) * 2017-05-27 2017-11-03 芜湖星途机器人科技有限公司 The hardware platform of system for tracking is dispatched by bank service robot
CN107798607A (en) * 2017-07-25 2018-03-13 上海壹账通金融科技有限公司 Asset Allocation strategy acquisition methods, device, computer equipment and storage medium
CN108335198A (en) * 2018-02-07 2018-07-27 平安科技(深圳)有限公司 Customer risk assessment method, device, equipment and computer readable storage medium
CN108509619A (en) * 2018-04-04 2018-09-07 科大讯飞股份有限公司 A kind of voice interactive method and equipment
US20180330152A1 (en) * 2017-05-11 2018-11-15 Kodak Alaris Inc. Method for identifying, ordering, and presenting images according to expressions
CN109079813A (en) * 2018-08-14 2018-12-25 重庆四通都成科技发展有限公司 Automobile Marketing service robot system and its application method
CN109785140A (en) * 2018-12-05 2019-05-21 上海拍拍贷金融信息服务有限公司 A kind of financing investment planning method and device based on intelligent sound
CN109840406A (en) * 2017-11-29 2019-06-04 百度在线网络技术(北京)有限公司 Living body verification method, device and computer equipment
CN110263653A (en) * 2019-05-23 2019-09-20 广东鼎义互联科技股份有限公司 A kind of scene analysis system and method based on depth learning technology
CN110599187A (en) * 2019-08-30 2019-12-20 广东智慧电子信息产业股份有限公司 Payment method and device based on face recognition, computer equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102236869A (en) * 2010-04-20 2011-11-09 中国工商银行股份有限公司 Real-time risk monitoring system for bank entrusted assets
CN102236870A (en) * 2010-04-26 2011-11-09 上海无花果信息科技有限公司 Control method of quantified multiple-factor investment portfolio for obtaining stable payback
CN102298694A (en) * 2011-06-21 2011-12-28 广东爱科数字科技有限公司 Man-machine interaction identification system applied to remote information service
CN102622707A (en) * 2012-02-15 2012-08-01 孙大利 Self-service account opening system and self-service account opening method thereof
CN104376250A (en) * 2014-12-03 2015-02-25 优化科技(苏州)有限公司 Real person living body identity verification method based on sound-type image feature
US20150206533A1 (en) * 2014-01-20 2015-07-23 Huawei Technologies Co., Ltd. Speech interaction method and apparatus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102236869A (en) * 2010-04-20 2011-11-09 中国工商银行股份有限公司 Real-time risk monitoring system for bank entrusted assets
CN102236870A (en) * 2010-04-26 2011-11-09 上海无花果信息科技有限公司 Control method of quantified multiple-factor investment portfolio for obtaining stable payback
CN102298694A (en) * 2011-06-21 2011-12-28 广东爱科数字科技有限公司 Man-machine interaction identification system applied to remote information service
CN102622707A (en) * 2012-02-15 2012-08-01 孙大利 Self-service account opening system and self-service account opening method thereof
US20150206533A1 (en) * 2014-01-20 2015-07-23 Huawei Technologies Co., Ltd. Speech interaction method and apparatus
CN104376250A (en) * 2014-12-03 2015-02-25 优化科技(苏州)有限公司 Real person living body identity verification method based on sound-type image feature

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180330152A1 (en) * 2017-05-11 2018-11-15 Kodak Alaris Inc. Method for identifying, ordering, and presenting images according to expressions
CN107315409A (en) * 2017-05-27 2017-11-03 芜湖星途机器人科技有限公司 The hardware platform of system for tracking is dispatched by bank service robot
CN107798607A (en) * 2017-07-25 2018-03-13 上海壹账通金融科技有限公司 Asset Allocation strategy acquisition methods, device, computer equipment and storage medium
CN109840406A (en) * 2017-11-29 2019-06-04 百度在线网络技术(北京)有限公司 Living body verification method, device and computer equipment
CN109840406B (en) * 2017-11-29 2022-05-17 百度在线网络技术(北京)有限公司 Living body verification method and device and computer equipment
CN108335198A (en) * 2018-02-07 2018-07-27 平安科技(深圳)有限公司 Customer risk assessment method, device, equipment and computer readable storage medium
CN108509619A (en) * 2018-04-04 2018-09-07 科大讯飞股份有限公司 A kind of voice interactive method and equipment
CN109079813A (en) * 2018-08-14 2018-12-25 重庆四通都成科技发展有限公司 Automobile Marketing service robot system and its application method
CN109785140A (en) * 2018-12-05 2019-05-21 上海拍拍贷金融信息服务有限公司 A kind of financing investment planning method and device based on intelligent sound
CN110263653A (en) * 2019-05-23 2019-09-20 广东鼎义互联科技股份有限公司 A kind of scene analysis system and method based on depth learning technology
CN110599187A (en) * 2019-08-30 2019-12-20 广东智慧电子信息产业股份有限公司 Payment method and device based on face recognition, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
CN106709804A (en) Interactive wealth planning consulting robot system
EP3109858B1 (en) Voiceprint authentication method and apparatus
CN106373575B (en) User voiceprint model construction method, device and system
CN110473566A (en) Audio separation method, device, electronic equipment and computer readable storage medium
CN107886957A (en) The voice awakening method and device of a kind of combination Application on Voiceprint Recognition
CN103325037A (en) Mobile payment safety verification method based on voice recognition
CN107492382A (en) Voiceprint extracting method and device based on neutral net
CN104376250A (en) Real person living body identity verification method based on sound-type image feature
CN107886943A (en) A kind of method for recognizing sound-groove and device
CN111243602A (en) Voiceprint recognition method based on gender, nationality and emotional information
CN107767263A (en) A kind of measures and procedures for the examination and approval of consumptive credit, device and server
CN109214914A (en) A kind of loan information checking method and device based on communication open platform
CN204667465U (en) Pay true man's live body authentication system by mails
CN110704618B (en) Method and device for determining standard problem corresponding to dialogue data
CN109462603A (en) Voiceprint authentication method, equipment, storage medium and device based on blind Detecting
CN108985776A (en) Credit card security monitoring method based on multiple Information Authentication
CN107274905A (en) A kind of method for recognizing sound-groove and system
CN109766419A (en) Products Show method, apparatus, equipment and storage medium based on speech analysis
CN106991312A (en) Internet based on Application on Voiceprint Recognition is counter to cheat authentication method
CN107346568A (en) The authentication method and device of a kind of gate control system
CN110517696A (en) A kind of offline Voiceprint Recognition System of implantable
CN109308578A (en) A kind of enterprise's big data analysis system and method
CN111062834A (en) Dispute case entity identification method and device, computer equipment and storage medium
CN114549241A (en) Contract examination method, device, system and computer readable storage medium
CN113191787A (en) Telecommunication data processing method, device electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
TA01 Transfer of patent application right

Effective date of registration: 20170814

Address after: 200333 Shanghai city Putuo District the same way 1225 Lane 13 Building 3 layer

Applicant after: SHANGHAI YIHUI INFORMATION TECHNOLOGY CO.,LTD.

Address before: Suzhou City, Jiangsu province 215300 Kunshan Qiandeng Park No. 1 Building 2 floor

Applicant before: YOUHUA SCIENCE & TECHNOLOGY (SUZHOU) CO.,LTD.

TA01 Transfer of patent application right
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170524

RJ01 Rejection of invention patent application after publication