CN109472608A - Business confirmation method and terminal device based on Emotion identification - Google Patents
Business confirmation method and terminal device based on Emotion identification Download PDFInfo
- Publication number
- CN109472608A CN109472608A CN201811203293.8A CN201811203293A CN109472608A CN 109472608 A CN109472608 A CN 109472608A CN 201811203293 A CN201811203293 A CN 201811203293A CN 109472608 A CN109472608 A CN 109472608A
- Authority
- CN
- China
- Prior art keywords
- transaction event
- safety detection
- password
- emotional state
- image
- 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
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention is suitable for technical field of data processing, provide business confirmation method, terminal device and computer readable storage medium based on Emotion identification, it include: after transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera, if including facial image in primary scene image, facial image is analyzed to obtain the first emotional state;Based on preset mapping relationship searching mood grade corresponding with the first emotional state, if mood grade is more than that grade threshold freezes transaction event, and execute safety detection after receiving trading password relevant to transaction event;If the result for executing safety detection is safety, thaw to transaction event, and transaction event is executed based on trading password;If execute safety detection result be it is dangerous, based on transaction event generate and outputting alarm information.The present invention improves the safety of transaction by setting Emotion identification mechanism and safety detection mechanism.
Description
Technical field
The invention belongs to technical field of data processing, more particularly to the business confirmation method based on Emotion identification, terminal are set
Standby and computer readable storage medium.
Background technique
Transaction refers to exchange of the both sides with currency and service for the value of medium, with the development of information technology, counterparty
Formula also develops towards the direction of diversification, more convenient and fast network trading occurs, such as transfers accounts online and cash dispenser withdrawal.
Before the transaction event of network trading specifically executes, need to verify the identity of user, to guarantee the safety of transaction.
In the prior art, the identity of dealer is usually verified by way of examining password or recognition of face,
And trade after being proved to be successful, but in practical application scene, user may be defeated by threat or stress
Enter password or carry out recognition of face and causes the loss of user if transaction event remains to execute using the prior art.
To sum up, the case where can not being threatened in the prior art user, is effectively identified that the safety traded is low.
Summary of the invention
In view of this, the embodiment of the invention provides by the business confirmation method of Emotion identification, terminal device and based on
Calculation machine readable storage medium storing program for executing is identified, the safety of transaction with solving the case where can not being threatened in the prior art user
Low problem.
The first aspect of the embodiment of the present invention provides a kind of business confirmation method based on Emotion identification, comprising:
After transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera, if described the
Include facial image in one live image, then the facial image is analyzed to obtain the first emotional state;
The mapping relations between preset multiple emotional states and mood grade are obtained, and are based on the mapping relationship searching
The mood grade corresponding with first emotional state, if the mood grade be more than grade threshold, receive with
After the relevant trading password of the transaction event, the transaction event is freezed, and execute safety detection, described mood etc.
Grade is used to indicate the severity of the emotional state;
If the result for executing safety detection is safety, thaw to the transaction event, and close based on the transaction
Code executes the transaction event;
If execute safety detection result be it is dangerous, based on the transaction event generate and outputting alarm information.
The second aspect of the embodiment of the present invention provides a kind of terminal device, and the terminal device includes memory, processing
Device and storage in the memory and the computer program that can run on the processor, described in the processor execution
Following steps are realized when computer program:
After transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera, if described the
Include facial image in one live image, then the facial image is analyzed to obtain the first emotional state;
The mapping relations between preset multiple emotional states and mood grade are obtained, and are based on the mapping relationship searching
The mood grade corresponding with first emotional state, if the mood grade be more than grade threshold, receive with
After the relevant trading password of the transaction event, the transaction event is freezed, and execute safety detection, described mood etc.
Grade is used to indicate the severity of the emotional state;
If the result for executing safety detection is safety, thaw to the transaction event, and close based on the transaction
Code executes the transaction event;
If execute safety detection result be it is dangerous, based on the transaction event generate and outputting alarm information.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor:
After transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera, if described the
Include facial image in one live image, then the facial image is analyzed to obtain the first emotional state;
The mapping relations between preset multiple emotional states and mood grade are obtained, and are based on the mapping relationship searching
The mood grade corresponding with first emotional state, if the mood grade be more than grade threshold, receive with
After the relevant trading password of the transaction event, the transaction event is freezed, and execute safety detection, described mood etc.
Grade is used to indicate the severity of the emotional state;
If the result for executing safety detection is safety, thaw to the transaction event, and close based on the transaction
Code executes the transaction event;
If execute safety detection result be it is dangerous, based on the transaction event generate and outputting alarm information.
Existing beneficial effect is the embodiment of the present invention compared with prior art:
The embodiment of the present invention analyze to the collected primary scene image of camera after transaction event is triggered
To the first emotional state, it is then based on preset mapping relations and determines mood grade corresponding with the first emotional state, if the feelings
Thread grade freezes transaction event then after receiving trading password more than grade threshold, and executes safety detection, if
Safety detection passes through, then thaws to transaction event, and executes transaction event based on trading password;If safety detection is not led to
It crosses, then warning information is generated based on transaction event and alerted, the embodiment of the present invention executes safety in the expression exception of user
Detection, and transaction is alerted or is continued to execute according to the selection of the result of safety detection, improve the safety of transaction.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation flow chart for the business confirmation method based on Emotion identification that the embodiment of the present invention one provides;
Fig. 2 is the implementation flow chart of the business confirmation method provided by Embodiment 2 of the present invention based on Emotion identification;
Fig. 3 is the implementation flow chart for the business confirmation method based on Emotion identification that the embodiment of the present invention three provides;
Fig. 4 is the implementation flow chart for the business confirmation method based on Emotion identification that the embodiment of the present invention four provides;
Fig. 5 is the implementation flow chart for the business confirmation method based on Emotion identification that the embodiment of the present invention five provides;
Fig. 6 is the structural block diagram for the terminal device that the embodiment of the present invention six provides;
Fig. 7 is the schematic diagram for the terminal device that the embodiment of the present invention seven provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 shows the implementation process of the business confirmation method provided in an embodiment of the present invention based on Emotion identification, is described in detail
It is as follows:
In S101, after transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera,
If including facial image in the primary scene image, the facial image is analyzed to obtain the first emotional state.
In embodiments of the present invention, executing subject is terminal device, for example, smart phone, computer, tablet computer or from
Dynamic cash dispenser (Automatic Teller Machine, ATM) etc..Transaction event refers to that is occurred on terminal device hands over virtual
Easily or reality is traded relevant event, for example, transaction event can be transfer accounts, stock exchange or loan etc..In the embodiment of the present invention
In, whether the transaction event first on detection terminal device is triggered, and whether detection transaction event is triggered can be by existing in advance
Setting control (such as javascript control) is realized in the bottom code of transaction event, wherein the trigger condition of transaction event
It can be configured according to practical application scene, be to transfer accounts for example with transaction event, trigger condition may be configured as user and fill in
Transfer amounts are completed, and click button of transferring accounts, i.e., just assert that transaction event is opened after user clicks button of transferring accounts, certainly, this
The restriction to the embodiment of the present invention is not constituted, for example can also set trigger condition to user and open software of transferring accounts.It is detecting
To after transaction event triggering, terminal device starts the camera (camera or external that the camera can carry for terminal device
Camera), and acquisition camera image within the vision is as primary scene image.
After getting primary scene image, terminal device carries out recognition of face to primary scene image, if identifying the
Do not include facial image in one live image, then terminates transaction event;If identifying to include facial image in primary scene image,
Then facial image is analyzed, obtains the first emotional state corresponding with facial image.The mistake that facial image is analyzed
Journey is broadly divided into two parts, i.e. feature extraction and Expression analysis, specifically, in characteristic extraction procedure, in primary scene figure
Region where being partitioned into facial image as in, and feature extraction is carried out to facial image, the region for carrying out feature extraction can be with
Pre-establish, for example, can ocular to facial image, nasal region and mouth region carry out feature extraction;In Expression analysis
In the process, terminal device is based on the multiple features extracted, calculating and the immediate emotional state of facial image, as the first table
Situation state.It is noted that in embodiments of the present invention, terminal device is in advance to multiple with the existing of different emotional states
Facial image (existing facial image can be obtained from the picture library such as jaffe picture library of open source) is trained, in order to promote table
The accuracy of mutual affection analysis, terminal device can divide multiple emotional states, such as " fear ", " happiness " and " sadness " in advance, then right
Multiple existing facial images are classified according to different emotional states, for example are the existing face figure of " fear " by emotional state
As individually being classified, the existing facial image that emotional state is " happiness " is individually classified, then again to sorted
Multiple existing facial images are trained, and training process and the analysis of subsequent facial image can be based on artificial neural network
The models such as (Artificial Neural Network, ANN) or support vector machines (Support Vector Machine, SVM)
It realizes.Certainly, in practical application scene, terminal device can also call open source Expression Recognition interface such as Azure interface or
Face++ interface etc., to analyze the first emotional state.
Optionally, it if terminal device includes multiple cameras, (for the ease of illustrating, is ordered in the image of camera acquisition
Entitled camera image) in, the camera image comprising facial image is chosen as primary scene image.In practical application scene
In, terminal device may include multiple cameras, for example smart phone may include front camera and rear camera, then exists
Transaction event is triggered, and when enabling camera acquisition primary scene image, can apply following two mode: first way is same
All cameras of Shi Qiyong terminal device carry out Image Acquisition, and carry out face knowledge to collected all camera images
Not, using the camera image comprising facial image as primary scene image, the efficiency of which is higher;The second way be by
Camera is enabled according to preset acquisition order and carries out Image Acquisition, after collecting camera image, if identifying the camera
It include facial image in image, then using the camera image as primary scene image, if identifying in the camera image not
Comprising facial image, then next camera is enabled according to acquisition order and carry out Image Acquisition, the resource which expends is less,
For example, if smart phone include front camera and rear camera, first enable smart phone front camera into
Row Image Acquisition if not occurring facial image in collected camera image, then enables rear camera progress image and adopts
Collection.Certainly, according to the needs of practical application scene, the camera for carrying out Image Acquisition can also be pre-assigned by the user.By upper
Method is stated, the acquisition of primary scene image is realized when terminal device includes multiple cameras, improves the suitable of Image Acquisition
The property used.
Optionally, multiple primary scene images are acquired, analysis obtains emotional state corresponding with each primary scene image,
Using the highest emotional state of the frequency of occurrences as the first emotional state.In embodiments of the present invention, it can also be acquired by camera
Multiple primary scene images, such as setting frequency acquisition are after transaction event is triggered, once every acquisition in 1 second, until adopting
Collect until 6 primary scene images.Then, terminal device to obtained each primary scene image carry out recognition of face and
Analysis, obtains multiple emotional states corresponding with multiple primary scene images, determines the frequency of occurrences most from multiple emotional states
High emotional state, using the emotional state as the first emotional state.The first expression determined is improved by the above method
The accuracy of state prevents Emotion identification inaccuracy caused by being mutated because of user emotion.
In S102, the mapping relations between preset multiple emotional states and mood grade are obtained, and reflect based on described
It penetrates relationship and searches the mood grade corresponding with first emotional state, if the mood grade is more than grade threshold,
After receiving trading password relevant to the transaction event, the transaction event is freezed, and execute safety detection,
The mood grade is used to indicate the severity of the emotional state.
In embodiments of the present invention, the mapping relations between multiple emotional states and mood grade are preset, and at end
Stored in end equipment Local or Remote database, the mood grade be used to indicate emotional state severity (mood
Severity), for example mood grade can be indicated with specific number, if emotional state is more serious, the number of mood grade
It is bigger.In this step, mapping relations are obtained, and are based on mapping relationship searching mood grade corresponding with the first emotional state,
If the mood grade is more than preset grade threshold, right after the password relevant to transaction event for receiving user's input
Transaction event is freezed and (does not execute transaction event), and executes safety detection;If the mood grade is less than grade threshold,
Transaction event is then continued to execute based on trading password.For example, setting emotional state includes " fear ", " happiness " and " sorrow
Wound ", there are mapping relations between emotional state " fear " and mood grade 3, deposit between emotional state " sadness " and mood grade 2
There are mapping relations between mapping relations, emotional state " happiness " and mood grade 1, then can set grade threshold as 2, work as touching
The mood grade for sending out the user of transaction event is more than grade threshold, i.e., when user is in " fear " emotional state, executes to transaction
The operation that event is freezed.
In S103, if the result for executing safety detection is safety, thaw to the transaction event, and be based on institute
It states trading password and executes the transaction event.
In embodiments of the present invention, in order to detect whether user triggers in voluntary situation and execute transaction event, in feelings
Thread grade executes safety detection when being more than grade threshold, and different operations, safety detection are executed according to the result of safety detection
Mechanism can be set according to practical application scene, such as may be set to when detect user press terminal device some or
Certain several key, or detect that user carries out after rapidly blinking, the result that output executes safety detection is safety.If executing peace
The result that full inspection is surveyed is safety, assert that user triggers transaction event in voluntary situation, then thaws to transaction event, and base
Transaction event is executed in trading password.It is noted that in order to promote the confidentiality of safety detection, while adapting to user and being coerced
Urgent scene, execute safety detection process in terminal device running background, i.e., can not issue the prompt of safety detection (or hair
The prompt of trading password is being verified out), safety detection whole process is recessive progress for a user, prevents stress people from learning
When carrying out safety detection, stress user carries out safety detection.
In S104, if the result for executing safety detection be it is dangerous, generate and export announcement based on the transaction event
Alert information.
If execute safety detection result be it is dangerous, terminal device be based on transaction event generate warning information, and to
Alarm center exports the warning information, to realize alarm.In addition to this, scene ground when transaction event is triggered can also be obtained
Position, situ time and primary scene image are managed, and based on transaction event, live geographical location, situ time and primary scene
Image generate warning information alerted, convenient for alarm center personnel after receiving warning information, quickly understand live feelings
It is efficient to promote alarm for condition.The way of output of warning information includes but is not limited to short message, mail and phone.
By embodiment illustrated in fig. 1 it is found that in embodiments of the present invention, terminal device is right after transaction event is triggered
The collected primary scene image of camera is analyzed to obtain the first emotional state, then obtains preset multiple emotional states
With the mapping relations between mood grade, and be based on mapping relationship searching mood grade corresponding with the first emotional state, if looking into
The mood grade found out be more than grade threshold, then after receiving trading password relevant to transaction event, to transaction event into
Row freezes, and executes safety detection, if the result for executing safety detection is safety, thaws to transaction event, and be based on
Trading password executes transaction event;If the result for executing safety detection be it is dangerous, generate and export announcement based on transaction event
Alert information, the embodiment of the present invention execute safety detection in user's expression exception by identification user's expression, are examined according to safety
The result selection of survey is alerted or continues to trade, and the safety of transaction is improved.
It is that there are preset phases on the basis of the embodiment of the present invention one, and between different emotional states shown in Fig. 2
On the basis of value, a kind of obtained method after being refined to the process for executing safety detection.The embodiment of the invention provides
The implementation flow chart of business confirmation method based on Emotion identification, as shown in Fig. 2, the business confirmation method may include following step
It is rapid:
In S201, after preset interval duration, people is carried out to the collected secondary scene image of the camera
Face identification analyzes the facial image to obtain the second expression if including facial image in the secondary scene image
State.
There are preset similar value between the embodiment of the present invention, different emotional states, similar value is used to indicate difference
Two emotional states between similarity degree, for the ease of illustrate, it is assumed that similar value is bigger, then similarity degree is higher, but this
The restriction to the embodiment of the present invention is not constituted.For example, the phase between emotional state " severe is frightened " and " slight frightened "
It is higher like degree, then similar value between the two can be set as to 1, and it is similar between emotional state " severe is frightened " and " calmness "
Degree is lower, then similar value between the two can be set as 0.1.Transaction event is freezed, and through super-interval duration
After (such as 10 seconds), current image is acquired as secondary scene image by camera, and face is carried out to secondary scene image
Identification analyzes the facial image to obtain the second emotional state if including facial image in the image of the secondary scene;If the
Two live images do not include facial image, then export Face normalization prompt, until camera acquired image includes face figure
Until picture.
In S202, if the corresponding mood grade of second emotional state is more than the grade threshold, export
It is dangerous for executing the result of safety detection.
If the corresponding mood grade of the second obtained emotional state also more than grade threshold, assert that user emotion more swashs
Strong, user is that the result for triggering transaction event in unwilled situation, therefore exporting execution safety detection is dangerous.
In S203, if the corresponding mood grade of second emotional state is less than the grade threshold, and institute
Stating the similar value between the first emotional state and second emotional state is more than preset similar value threshold value, then output is held
The result of row safety detection is safety.
If the corresponding mood grade of the second obtained emotional state is less than grade threshold, and the first emotional state and
Similar value between two emotional states is more than preset similar value threshold value, assert that user emotion fluctuation is larger, and be by user
It is gentle actively to have carried out mood, and has been not to be in the case where being coerced, therefore the result that output executes safety detection is safety,
Middle similar value threshold value customized can be arranged, the phase that can also be set similar value threshold value between specified two emotional states
Like value, such as the similar value that similar value threshold value can be set between emotional state " severe is frightened " and " calmness ";If obtaining
The corresponding mood grade of second emotional state is less than grade threshold, and between the first emotional state and the second emotional state
Similar value is less than preset similar value threshold value, assert that user emotion fluctuation is smaller, assert that user is in by stress state (in reality
In the application scenarios of border, it is gentle that user may carry out mood under the requirement of stress people, therefore there are the moods of the second emotional state
Grade is less than the possibility of grade threshold), the result that output executes safety detection is dangerous.
By embodiment illustrated in fig. 2 it is found that in embodiments of the present invention, after preset interval duration, to camera
Collected secondary scene image is analyzed to obtain the second emotional state, if the corresponding mood grade of the second emotional state is more than
Grade threshold, then it is dangerous for exporting and executing the result of safety detection;If the corresponding mood grade of the second emotional state is less than
Grade threshold, and the similar value between the first emotional state and the second emotional state is more than preset similar value threshold value, then exports
The result for executing safety detection is safety.The embodiment of the present invention passes through the expression of analysis different time points, to judge that user is
It is no in the state coerced, improve the accuracy of judgement.
Shown in Fig. 3, be on the basis of the embodiment of the present invention one, to receive trading password relevant to transaction event it
A kind of method that process afterwards obtains after being refined.The embodiment of the invention provides the business confirmation methods based on Emotion identification
Implementation flow chart, as shown in figure 3, the business confirmation method may comprise steps of:
In S301, obtains and examine password, and judge whether the trading password is identical as the inspection password, the inspection
Password is tested for examining whether the transaction event is voluntarily triggered by user.
In practical application scene, when the mood grade of user is more than grade threshold, user may also be not to be coerced
Transaction event is triggered in the case where compeling.For example, user may be to be influenced by other events, cause to have intense feelings, thus into
When row Emotion identification, mood grade is more than grade threshold, but user is to trigger transaction event in voluntary situation.For above-mentioned feelings
Condition, fault alarm, the embodiment of the present invention increase inspection mechanism in order to prevent, and specifically, terminal device, which obtains, examines password, sentence
Whether the trading password that disconnecting receives is identical as password is examined, and different operations is executed according to the result of judgement.Examine password
It can be preset, and be stored in terminal device local, can also be generated at random in the form of handset token, i.e., every fixed generation
It is spaced (such as 1 minute) inspection password new in terminal device generation synchronous in the equipment that user is held.
In S302, if the trading password is identical as the inspection password, exports and input the trading password again
Prompt the transaction event is executed based on the trading password and after receiving the trading password inputted again.
If trading password is identical as password is examined, assert that user voluntarily triggers transaction event and (coerced if user is in
State, since stress people to inspection mechanism and may be unaware of, then user can deliberately input trading password by mistake), then terminal is set
The standby prompt for inputting trading password again to user's output, and after receiving the trading password that user inputs again, being based on should
Trading password executes transaction event.
In S303, if the trading password and the inspection password be not identical, execute described to the transaction event
The operation freezed.
If trading password and inspection password be not identical, assert that user is not voluntarily to trade, then execute to transaction event
The operation freezed is convenient for subsequent execution safety detection, and is alerted after safety detection failure, to promote transaction
Safety.
By embodiment illustrated in fig. 3 it is found that in embodiments of the present invention, examining password by obtaining, and it is close to judge to trade
Whether code is identical as password is examined, if trading password is identical as password is examined, exports the prompt for inputting trading password again, and
After receiving the trading password inputted again, transaction event is executed based on trading password;If trading password and inspection password are not
It is identical, then execute the operation freezed to transaction event.The embodiment of the present invention is provided a user by setting inspection mechanism
Without safety detection, the channel of transaction event is directly executed, the convenience of transaction is improved.
It is that transaction event will be freezed on the basis of the embodiment of the present invention one, and execute safe inspection shown in Fig. 4
A kind of method that the process of survey obtains after being refined.The embodiment of the invention provides the business confirmation methods based on Emotion identification
Implementation flow chart, as shown in figure 4, the business confirmation method may comprise steps of:
In S401, pond is freezed into transaction event merging, and records the transaction event and freezes pond positioned at described
There are durations.
In embodiments of the present invention, the concrete operations freezed to transaction event are that transaction event is placed in preset jelly
Pond is tied, which can be that database or task queue etc. are freezed in pond after pond is freezed in transaction event merging
What transaction event was inaccessible by for terminal device, only corresponding with transaction event defrosting order is issued to freezing pond
Afterwards, transaction event could be taken out.For example, freezing pond is oracle database, will all numbers relevant to transaction event
It is the additional attribute field of above-mentioned data creation (life in oracle database when being freezed according to deposit oracle database
It is entitled to freeze field), and will freeze field be assigned a value of frozen value (frozen value instruction cannot be taken out from oracle database it is above-mentioned
Data, such as frozen value can will freeze the value update of field 0), to order when terminal device issues to thaw to oracle database
For (instruction of non-freezing value can take out above-mentioned data from oracle database, for example non-freezing value can be complete for 1) after non-freezing value
The defrosting of pairs of above-mentioned data.After pond is freezed in transaction event merging, record transaction event, which is located at, in real time freezes depositing in pond
In duration, wherein the counter that can be zero by presetting initial value, when detect freeze in pond be stored in transaction event when touching
Hair counter starts counting, so that there are durations for record, the journal file that record freezes pond operation can also be obtained, from journal file
In analyze that there are durations.
It there are duration is more than preset alarm duration if described, to camera collected third scene in S402
Image carries out recognition of face, if facial image is not present in the third live image, exports the result for executing safety detection
It is dangerous.
Due in actual stress scene, user may be coerced by stress people and leave transaction scene, if therefore record deposit
It is more than preset alarm duration (such as 5 minutes) in duration, then again by camera collection image, as third live image,
And recognition of face is carried out to third live image, if facial image is not present in third live image, export execution safety inspection
The result of survey is dangerous;If exporting and executing the result of safety detection is safety there are facial image in third live image
(in third live image there are on the basis of facial image, further safety detection, the present invention can be carried out to the facial image
Embodiment does not limit this).In addition, if record there are durations to be less than alarm duration, continue record there are durations.
Optionally, if facial image is not present in third live image, and transaction event is in progress, then exports execution
The result of safety detection is dangerous.On the basis of facial image is not present in third live image, terminal device is to transaction
The state of event is detected, defeated if transaction event is still underway (frozen transaction event, which is also considered as, to be carried out)
It is dangerous for executing the result of safety detection out.The above method is suitable for the scenes such as ATM, for example bank card is inserted by user
ATM, and left withdrawing the money to be kidnapped by stress people on the way, then it can effectively be alerted by the above method, improve safety detection
Accuracy.
By embodiment illustrated in fig. 4 it is found that in embodiments of the present invention, by the way that pond is freezed in transaction event merging, and remembering
Record transaction event be located at freeze pond there are duration, duration is more than preset alarm duration if it exists, then collects to camera
Third live image carry out recognition of face, if in third live image be not present facial image, export execution safety detection
Result be it is dangerous, the embodiment of the present invention be suitable for user by stress people seize on both sides by the arms leave transaction scene scene, by timely
Alarm, improves the safety of user.
It shown in Fig. 5, is obtained after being refined to the process for executing safety detection on the basis of the embodiment of the present invention one
A kind of method.The embodiment of the invention provides the implementation flow charts of the business confirmation method based on Emotion identification, such as Fig. 5 institute
Show, which may comprise steps of:
In S501, if identifying in the primary scene image comprising multiple facial images, collection site language
The field speech is converted to live text, and carries out lexical analysis to the live text by sound.
When executing safety detection, if identified in primary scene image comprising multiple facial images, terminal is enabled
The microphone of equipment, with collection site voice.Terminal device calls voice to turn text (Speech after collecting field speech
To Text, STT) service creation live text corresponding with field speech, and live text is segmented, then to separating
Multiple vocabulary carry out lexical analysis.Wherein, when segmenting to live text, the participle tool of open source can be called, such as
Analyzer participle tool etc..
In S502, if exporting and executing the result of safety detection is uneasiness containing default vocabulary in the scene text
Entirely.
In embodiments of the present invention, terminal device obtains default vocabulary, and the multiple vocabulary that will be separated based on live text
It is compared with default vocabulary, if identical as default vocabulary based on some or certain several vocabulary that live text separates, exports
It is dangerous for executing the result of safety detection;If being different from based on all vocabulary that live text separates with default vocabulary,
The result that output executes safety detection is safety.Default vocabulary can be configured according to practical application scene, for example can will be preset
Vocabulary is set as " plundering ", wherein default vocabulary may be configured as one or more.
By embodiment illustrated in fig. 5 it is found that in embodiments of the present invention, if identifying in primary scene image comprising multiple
Facial image, then collection site voice, is converted to live text for field speech, and carry out lexical analysis to live text, if
Containing default vocabulary in live text, then export execute safety detection result be it is dangerous, the embodiment of the present invention is having more people
When positioned at transaction scene, collected field speech is analyzed, to identify whether user is coerced, is further promoted
The safety of transaction.
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.
Fig. 6 shows the structural block diagram of terminal device provided in an embodiment of the present invention, each unit which includes
For executing each step in the corresponding embodiment of Fig. 1.It is retouched referring specifically to Fig. 1 is related in embodiment corresponding to Fig. 1
It states.For ease of description, only the parts related to this embodiment are shown.
Referring to Fig. 6, the terminal device includes:
Recognition unit 61, for carrying out people to the collected primary scene image of camera after transaction event is triggered
Face identification analyzes the facial image to obtain the first expression if including facial image in the primary scene image
State;
Detection unit 62 for obtaining the mapping relations between preset multiple emotional states and mood grade, and is based on
The mapping relationship searching mood grade corresponding with first emotional state, if the mood grade is more than grade threshold
Value, then after receiving trading password relevant to the transaction event, freeze the transaction event, and execute safety
Detection, the mood grade are used to indicate the severity of the emotional state;
Execution unit 63 thaws to the transaction event if the result for executing safety detection is safety, and
The transaction event is executed based on the trading password;
Alarm Unit 64, if result for executing safety detection be it is dangerous, generated simultaneously based on the transaction event
Outputting alarm information.
Optionally, there are preset similar value between different emotional states, detection unit 62 includes:
It is spaced recognition unit, is used for after preset interval duration, to the collected secondary scene figure of the camera
As carrying out recognition of face, if including facial image in the secondary scene image, the facial image is analyzed to obtain
Second emotional state;
First output subelement, if being more than the grade threshold for the corresponding mood grade of second emotional state
Value, then it is dangerous for exporting and executing the result of safety detection;
Second output subelement, if being less than the grade for the corresponding mood grade of second emotional state
Threshold value, and the similar value between first emotional state and second emotional state is more than preset similar value threshold
Value, then exporting and executing the result of safety detection is safety.
Optionally, detection unit 62 further include:
Judging unit examines password for obtaining, and judges whether the trading password is identical as the inspection password, institute
It states and examines password for examining whether the transaction event is voluntarily triggered by user;
Input unit again exports described in input again if identical as the inspection password for the trading password
The prompt of trading password, and after receiving the trading password inputted again, the friendship is executed based on the trading password
Easy event;
Freezing unit executes described to the transaction if not identical for the trading password and the inspection password
The operation that event is freezed.
Optionally, detection unit 62 includes:
It is placed in unit, for pond to be freezed in transaction event merging, and the transaction event is recorded and is located at described freeze
Pond there are durations;
Third export subelement, if for it is described there are duration be more than preset alarm duration, camera is collected
Third live image carry out recognition of face, if in the third live image be not present facial image, export and execute safety
The result of detection is dangerous.
Optionally, detection unit 62 includes:
Lexical analysis unit, if being adopted for identifying in the primary scene image comprising multiple facial images
Collect field speech, the field speech is converted into live text, and lexical analysis is carried out to the live text;
4th output subelement, if for, containing default vocabulary, exporting in the live text and executing safety detection
It as a result is dangerous.
Therefore, terminal device provided in an embodiment of the present invention is realized by setting Emotion identification and the mechanism of safety detection
Effective judgement for whether being coerced user, improves the safety of transaction.
Fig. 7 is the schematic diagram of terminal device provided in an embodiment of the present invention.As shown in fig. 7, the terminal device 7 of the embodiment
Include: processor 70, memory 71 and is stored in the calculating that can be run in the memory 71 and on the processor 70
Machine program 72, such as the transaction authentication program based on Emotion identification.The processor 70 executes real when the computer program 72
Step in existing above-mentioned each business confirmation method embodiment based on Emotion identification, such as step S101 shown in FIG. 1 is extremely
S104.Alternatively, the processor 70 realizes each unit in above-mentioned each terminal device embodiment when executing the computer program 72
Function, such as the function of unit 61 to 64 shown in Fig. 6.
Illustratively, the computer program 72 can be divided into one or more units, one or more of
Unit is stored in the memory 71, and is executed by the processor 70, to complete the present invention.One or more of lists
Member can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing the computer journey
Implementation procedure of the sequence 72 in the terminal device 7.For example, the computer program 72 can be divided into recognition unit, inspection
It is as follows to survey unit, execution unit and Alarm Unit, each unit concrete function:
Recognition unit, for carrying out face to the collected primary scene image of camera after transaction event is triggered
Identification analyzes the facial image to obtain the first expression shape if including facial image in the primary scene image
State;
Detection unit for obtaining the mapping relations between preset multiple emotional states and mood grade, and is based on institute
The mapping relationship searching mood grade corresponding with first emotional state is stated, if the mood grade is more than grade threshold
Value, then after receiving trading password relevant to the transaction event, freeze the transaction event, and execute safety
Detection, the mood grade are used to indicate the severity of the emotional state;
Execution unit thaws to the transaction event, and base if the result for executing safety detection is safety
The transaction event is executed in the trading password;
Alarm Unit, if result for executing safety detection be it is dangerous, generated based on the transaction event and defeated
Warning information out.
The terminal device 7 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 70, memory 71.It will be understood by those skilled in the art that Fig. 7
The only example of terminal device 7 does not constitute the restriction to terminal device 7, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 70 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 71 can be the internal storage unit of the terminal device 7, such as the hard disk or interior of terminal device 7
It deposits.The memory 71 is also possible to the External memory equipment of the terminal device 7, such as be equipped on the terminal device 7
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 71 can also both include the storage inside list of the terminal device 7
Member also includes External memory equipment.The memory 71 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 71 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit division progress for example, in practical application, can according to need and by above-mentioned function distribution by different functions
Unit is completed, i.e., the internal structure of the terminal device is divided into different functional units, to complete whole described above
Or partial function.Each functional unit in embodiment can integrate in one processing unit, be also possible to each unit list
It is solely physically present, can also be integrated in one unit with two or more units, above-mentioned integrated unit can both use
Formal implementation of hardware can also be realized in the form of software functional units.In addition, the specific name of each functional unit also only
It is the protection scope that is not intended to limit this application for the ease of mutually distinguishing.The specific work process of unit in above system,
It can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed terminal device and method can pass through it
Its mode is realized.For example, terminal device embodiment described above is only schematical, for example, the unit is drawn
Point, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling or direct-coupling or communication connection of opinion can be through some interfaces, the INDIRECT COUPLING of device or unit
Or communication connection, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-described embodiment side
All or part of the process in method can also instruct relevant hardware to complete, the computer by computer program
Program can be stored in a computer readable storage medium, and the computer program is when being executed by processor, it can be achieved that above-mentioned each
The step of a embodiment of the method.Wherein, the computer program includes computer program code, and the computer program code can
Think source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium can be with
It include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, light that can carry the computer program code
Disk, computer storage, read-only memory (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described computer-readable
The content that medium includes can carry out increase and decrease appropriate according to the requirement made laws in jurisdiction with patent practice, such as at certain
A little jurisdictions do not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
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 business confirmation method based on Emotion identification characterized by comprising
After transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera, if described first is existing
Include facial image in field picture, then the facial image is analyzed to obtain the first emotional state;
The mapping relations between preset multiple emotional states and mood grade are obtained, and are based on the mapping relationship searching and institute
State the corresponding mood grade of the first emotional state, if the mood grade be more than grade threshold, receive with it is described
After the relevant trading password of transaction event, the transaction event is freezed, and execute safety detection, the mood grade is used
In the severity for indicating the emotional state;
If the result for executing safety detection is safety, thaw to the transaction event, and is held based on the trading password
The row transaction event;
If execute safety detection result be it is dangerous, based on the transaction event generate and outputting alarm information.
2. business confirmation method as described in claim 1, which is characterized in that exist between the different emotional states default
Similar value, the execution safety detection, comprising:
After preset interval duration, recognition of face is carried out to the collected secondary scene image of the camera, if described
Include facial image in the image of the secondary scene, then the facial image is analyzed to obtain the second emotional state;
If the corresponding mood grade of second emotional state is more than the grade threshold, exports and execute safety detection
It as a result is dangerous;
If the corresponding mood grade of second emotional state is less than the grade threshold, and first emotional state
The similar value between second emotional state is more than preset similar value threshold value, then exports the knot for executing safety detection
Fruit is safety.
3. business confirmation method as described in claim 1, which is characterized in that it is described receive it is related to the transaction event
Trading password after, further includes:
It obtains and examines password, and judge whether the trading password is identical as the inspection password, the inspection password is for examining
Test whether the transaction event is voluntarily triggered by user;
If the trading password is identical as the inspection password, the prompt for inputting the trading password again is exported, and connecing
After receiving the trading password inputted again, the transaction event is executed based on the trading password;
If the trading password and the inspection password be not identical, the behaviour freezed to the transaction event is executed
Make.
4. business confirmation method as described in claim 1, which is characterized in that it is described that the transaction event is freezed, and
Execute safety detection, comprising:
Pond is freezed into transaction event merging, and record the transaction event be located at it is described freeze pond there are durations;
If it is described there are duration be more than preset alarm duration, to the collected third live image of camera carry out face knowledge
Not, if facial image is not present in the third live image, it is dangerous for exporting and executing the result of safety detection.
5. business confirmation method as described in claim 1, which is characterized in that the execution safety detection, comprising:
If identifying in the primary scene image comprising multiple facial images, collection site voice, by the scene
Voice is converted to live text, and carries out lexical analysis to the live text;
If it is dangerous for exporting and executing the result of safety detection containing default vocabulary in the scene text.
6. a kind of terminal device, which is characterized in that the terminal device includes memory, processor and is stored in the storage
In device and the computer program that can run on the processor, the processor are realized as follows when executing the computer program
Step:
After transaction event is triggered, recognition of face is carried out to the collected primary scene image of camera, if described first is existing
Include facial image in field picture, then the facial image is analyzed to obtain the first emotional state;
The mapping relations between preset multiple emotional states and mood grade are obtained, and are based on the mapping relationship searching and institute
State the corresponding mood grade of the first emotional state, if the mood grade be more than grade threshold, receive with it is described
After the relevant trading password of transaction event, the transaction event is freezed, and execute safety detection, the mood grade is used
In the severity for indicating the emotional state;
If the result for executing safety detection is safety, thaw to the transaction event, and is held based on the trading password
The row transaction event;
If execute safety detection result be it is dangerous, based on the transaction event generate and outputting alarm information.
7. terminal device as claimed in claim 6, which is characterized in that there are preset phases between the different emotional states
Like value, the execution safety detection, comprising:
After preset interval duration, recognition of face is carried out to the collected secondary scene image of the camera, if described
Include facial image in the image of the secondary scene, then the facial image is analyzed to obtain the second emotional state;
If the corresponding mood grade of second emotional state is more than the grade threshold, exports and execute safety detection
It as a result is dangerous;
If the corresponding mood grade of second emotional state is less than the grade threshold, and first emotional state
The similar value between second emotional state is more than preset similar value threshold value, then exports the knot for executing safety detection
Fruit is safety.
8. terminal device as claimed in claim 6, which is characterized in that described to receive friendship relevant to the transaction event
After easy password, further includes:
It obtains and examines password, and judge whether the trading password is identical as the inspection password, the inspection password is for examining
Test whether the transaction event is voluntarily triggered by user;
If the trading password is identical as the inspection password, the prompt for inputting the trading password again is exported, and connecing
After receiving the trading password inputted again, the transaction event is executed based on the trading password;
If the trading password and the inspection password be not identical, the behaviour freezed to the transaction event is executed
Make.
9. terminal device as claimed in claim 6, which is characterized in that it is described that the transaction event is freezed, and execute
Safety detection, comprising:
Pond is freezed into transaction event merging, and record the transaction event be located at it is described freeze pond there are durations;
If it is described there are duration be more than preset alarm duration, to the collected third live image of camera carry out face knowledge
Not, if facial image is not present in the third live image, it is dangerous for exporting and executing the result of safety detection.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the step of realization business confirmation method as described in any one of claim 1 to 5 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811203293.8A CN109472608A (en) | 2018-10-16 | 2018-10-16 | Business confirmation method and terminal device based on Emotion identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811203293.8A CN109472608A (en) | 2018-10-16 | 2018-10-16 | Business confirmation method and terminal device based on Emotion identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109472608A true CN109472608A (en) | 2019-03-15 |
Family
ID=65665014
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811203293.8A Pending CN109472608A (en) | 2018-10-16 | 2018-10-16 | Business confirmation method and terminal device based on Emotion identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109472608A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111874A (en) * | 2019-04-18 | 2019-08-09 | 上海图菱新能源科技有限公司 | Artificial intelligence Emotion identification management migrates interactive process and method |
CN110298301A (en) * | 2019-04-17 | 2019-10-01 | 国网江苏省电力有限公司 | A kind of establishment officer's phychology prediction technique |
CN111080874A (en) * | 2019-12-31 | 2020-04-28 | 中国银行股份有限公司 | Face image-based vault safety door control method and device |
CN111126244A (en) * | 2019-12-20 | 2020-05-08 | 南京邮电大学 | Security authentication system and method based on facial expressions |
CN111311755A (en) * | 2020-02-05 | 2020-06-19 | 中国建设银行股份有限公司 | Service method and device based on AR equipment and physiological data |
CN111428572A (en) * | 2020-02-28 | 2020-07-17 | 中国工商银行股份有限公司 | Information processing method, information processing apparatus, electronic device, and medium |
CN111625799A (en) * | 2020-06-04 | 2020-09-04 | 中国银行股份有限公司 | Processing method and device based on face unlocking |
CN111736937A (en) * | 2020-06-19 | 2020-10-02 | 中国银行股份有限公司 | Service processing method and device |
CN111931675A (en) * | 2020-08-18 | 2020-11-13 | 熵基科技股份有限公司 | Coercion alarm method, device, equipment and storage medium based on face recognition |
CN112150288A (en) * | 2020-09-30 | 2020-12-29 | 南宁学院 | Stock transaction risk warning system based on expression recognition |
WO2021073270A1 (en) * | 2019-10-17 | 2021-04-22 | 平安科技(深圳)有限公司 | Method and apparatus for risk management and control, computer apparatus, and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007310630A (en) * | 2006-05-18 | 2007-11-29 | Bank Of Tokyo-Mitsubishi Ufj Ltd | Recovery system and method for function of personal identification |
US20150066764A1 (en) * | 2013-09-05 | 2015-03-05 | International Business Machines Corporation | Multi factor authentication rule-based intelligent bank cards |
CN104574088A (en) * | 2015-02-04 | 2015-04-29 | 华为技术有限公司 | Payment authorization method and device |
CN104680375A (en) * | 2015-02-28 | 2015-06-03 | 优化科技(苏州)有限公司 | Identification verifying system for living human body for electronic payment |
CN107705128A (en) * | 2017-09-05 | 2018-02-16 | 深圳支点电子智能科技有限公司 | A kind of payment verification method and system |
CN108389052A (en) * | 2018-02-27 | 2018-08-10 | 平安科技(深圳)有限公司 | Prevent bank card from stealing method, apparatus, computer equipment and the storage medium of brush |
-
2018
- 2018-10-16 CN CN201811203293.8A patent/CN109472608A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007310630A (en) * | 2006-05-18 | 2007-11-29 | Bank Of Tokyo-Mitsubishi Ufj Ltd | Recovery system and method for function of personal identification |
US20150066764A1 (en) * | 2013-09-05 | 2015-03-05 | International Business Machines Corporation | Multi factor authentication rule-based intelligent bank cards |
CN104574088A (en) * | 2015-02-04 | 2015-04-29 | 华为技术有限公司 | Payment authorization method and device |
CN104680375A (en) * | 2015-02-28 | 2015-06-03 | 优化科技(苏州)有限公司 | Identification verifying system for living human body for electronic payment |
CN107705128A (en) * | 2017-09-05 | 2018-02-16 | 深圳支点电子智能科技有限公司 | A kind of payment verification method and system |
CN108389052A (en) * | 2018-02-27 | 2018-08-10 | 平安科技(深圳)有限公司 | Prevent bank card from stealing method, apparatus, computer equipment and the storage medium of brush |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110298301A (en) * | 2019-04-17 | 2019-10-01 | 国网江苏省电力有限公司 | A kind of establishment officer's phychology prediction technique |
CN110298301B (en) * | 2019-04-17 | 2021-09-07 | 国网江苏省电力有限公司 | Method for predicting psychological states of organization personnel |
CN110111874A (en) * | 2019-04-18 | 2019-08-09 | 上海图菱新能源科技有限公司 | Artificial intelligence Emotion identification management migrates interactive process and method |
WO2021073270A1 (en) * | 2019-10-17 | 2021-04-22 | 平安科技(深圳)有限公司 | Method and apparatus for risk management and control, computer apparatus, and storage medium |
CN111126244A (en) * | 2019-12-20 | 2020-05-08 | 南京邮电大学 | Security authentication system and method based on facial expressions |
CN111080874A (en) * | 2019-12-31 | 2020-04-28 | 中国银行股份有限公司 | Face image-based vault safety door control method and device |
CN111311755A (en) * | 2020-02-05 | 2020-06-19 | 中国建设银行股份有限公司 | Service method and device based on AR equipment and physiological data |
CN111311755B (en) * | 2020-02-05 | 2023-07-14 | 中国建设银行股份有限公司 | Service method and device based on AR equipment and physiological data |
CN111428572A (en) * | 2020-02-28 | 2020-07-17 | 中国工商银行股份有限公司 | Information processing method, information processing apparatus, electronic device, and medium |
CN111428572B (en) * | 2020-02-28 | 2023-07-25 | 中国工商银行股份有限公司 | Information processing method, device, electronic equipment and medium |
CN111625799A (en) * | 2020-06-04 | 2020-09-04 | 中国银行股份有限公司 | Processing method and device based on face unlocking |
CN111736937A (en) * | 2020-06-19 | 2020-10-02 | 中国银行股份有限公司 | Service processing method and device |
CN111736937B (en) * | 2020-06-19 | 2024-02-27 | 中国银行股份有限公司 | Service processing method and device |
CN111931675A (en) * | 2020-08-18 | 2020-11-13 | 熵基科技股份有限公司 | Coercion alarm method, device, equipment and storage medium based on face recognition |
CN112150288A (en) * | 2020-09-30 | 2020-12-29 | 南宁学院 | Stock transaction risk warning system based on expression recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109472608A (en) | Business confirmation method and terminal device based on Emotion identification | |
US11281552B2 (en) | Self-learning alerting and anomaly detection | |
CN106803168B (en) | Abnormal transfer detection method and device | |
US6542881B1 (en) | System and method for revealing necessary and sufficient conditions for database analysis | |
CN104598367B (en) | Data center's event of failure management specialty and method | |
CN107767021A (en) | A kind of risk control method and equipment | |
CN108170580A (en) | A kind of rule-based log alarming method, apparatus and system | |
US9854098B2 (en) | Electronic communication routing based data accuracy | |
CN110866820A (en) | Real-time monitoring system, method, equipment and storage medium for banking business | |
CN110909165A (en) | Data processing method, device, medium and electronic equipment | |
CN109345375A (en) | A kind of suspicious money laundering Activity recognition method and device | |
CN110008979A (en) | Abnormal data prediction technique, device, electronic equipment and computer storage medium | |
CN111522987A (en) | Image auditing method and device and computer readable storage medium | |
CN110287316A (en) | A kind of Alarm Classification method, apparatus, electronic equipment and storage medium | |
CN109785123A (en) | A kind of business handling assisted method, device and terminal device | |
CN111770353A (en) | Live broadcast monitoring method and device, electronic equipment and storage medium | |
CN108092985A (en) | Network safety situation analysis method, device, equipment and computer storage media | |
CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
CN110415427A (en) | A kind of auto inventory method, apparatus, equipment and the medium of self-service device | |
CN109934723A (en) | A kind of medical insurance fraud recognition methods, device and equipment | |
CN115204886A (en) | Account identification method and device, electronic equipment and storage medium | |
CN116956896A (en) | Text analysis method, system, electronic equipment and medium based on artificial intelligence | |
US11971873B2 (en) | Real-time anomaly determination using integrated probabilistic system | |
CN107871213B (en) | Transaction behavior evaluation method, device, server and storage medium | |
CN109816893A (en) | Method for sending information, device, server 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 |