CN114358790A - Method and device for identifying object, computer readable storage medium and electronic equipment - Google Patents
Method and device for identifying object, computer readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114358790A CN114358790A CN202210017887.XA CN202210017887A CN114358790A CN 114358790 A CN114358790 A CN 114358790A CN 202210017887 A CN202210017887 A CN 202210017887A CN 114358790 A CN114358790 A CN 114358790A
- Authority
- CN
- China
- Prior art keywords
- target
- voiceprint
- identity
- matching result
- information
- 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
Images
Abstract
The invention discloses a method and a device for identifying an object, a computer readable storage medium and electronic equipment. Relating to the field of financial science and technology, the method comprises the following steps: acquiring voice information replied by an object to be recognized to a preset problem, wherein the preset problem is associated with target identity information of a target object; performing feature extraction on the voice information to obtain voice content and voiceprint features corresponding to the voice information; matching the voiceprint features with the target voiceprint features to obtain a voiceprint matching result; matching the voice content with the target identity information to obtain an identity matching result; and determining whether the object to be identified is the target object or not based on the voiceprint matching result and the identity matching result. The invention solves the technical problem of low transaction safety caused by inaccurate identity recognition of the consumer in the prior art.
Description
Technical Field
The invention relates to the field of financial science and technology, in particular to a method and a device for identifying an object, a computer-readable storage medium and electronic equipment.
Background
With the vigorous development of domestic internet application, the online and self-help degrees of bank credit card business are higher and higher. The customer can perform various services such as online consumption, self-service staging, transfer and the like through a mobile phone bank, an online bank, or a self-service channel such as binding WeChat and Payment treasure. There is a significant security risk of online transaction authenticity compared to traditional offline business. Especially if the mobile phone is not intended by a card-holding client, if the mobile phone is taken by a family who is mistakenly in the wrong way to a bank card or a criminal obtains a mobile phone bound with a WeChat or a Payment treasure, the mobile phone may be swiped illegally by a large amount or repeatedly.
At present, in the prior art, the identification method for the consuming user cannot accurately judge the identity of the user, so that the economic loss of the user is easily caused.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying an object, a computer readable storage medium and electronic equipment, which are used for at least solving the technical problem of low transaction security caused by inaccurate identity identification of a consuming user in the prior art.
According to an aspect of an embodiment of the present invention, there is provided a method of identifying an object, including: acquiring voice information replied by an object to be recognized to a preset problem, wherein the preset problem is associated with target identity information of a target object; performing feature extraction on the voice information to obtain voice content and voiceprint features corresponding to the voice information; matching the voiceprint features with the target voiceprint features to obtain a voiceprint matching result; matching the voice content with the target identity information to obtain an identity matching result; and determining whether the object to be identified is the target object or not based on the voiceprint matching result and the identity matching result.
Optionally, the method for identifying an object further includes: before acquiring voice information of an object to be recognized for replying to a preset problem, acquiring consumption information of a target object and at least one consumption limiting condition of the target object; and when the consumption information meets at least one consumption limiting condition, generating a preset problem based on the target identity information.
Optionally, the method for identifying an object further includes: acquiring target voice information of a target object before matching the voiceprint features with the target voiceprint features to obtain a voiceprint matching result; extracting the characteristics of the target voice information to obtain target characteristic parameters corresponding to the target voice information; and training the target characteristic parameters to obtain the target voiceprint characteristics.
Optionally, the method for identifying an object further includes: after the voiceprint features are matched with the target voiceprint features to obtain a voiceprint matching result, determining whether the identity type of the object to be recognized is a first type or not based on the voiceprint matching result, wherein the first type represents that the association degree between the object to be recognized and the target object is greater than the preset association degree; under the condition that the identity type of the object to be recognized is determined to be the first type, matching the voice content with the target identity information to obtain an identity matching result; and under the condition that the identity type of the object to be recognized is determined to be a second type, determining that the object to be recognized is not the target object, wherein the association degree between the object to be recognized and the target object represented by the second type is smaller than or equal to the preset association degree.
Optionally, the method for identifying an object further includes: converting the voice content to obtain text information corresponding to the voice content; and matching the text information with the target identity information to obtain an identity matching result.
Optionally, the method for identifying an object further includes: determining that the object to be identified is not the target object under the condition that the voiceprint matching result represents that the voiceprint features are not matched with the target voiceprint features or the identity matching result represents that the voice content is not matched with the target identity information; and under the condition that the voiceprint matching result represents that the voiceprint features are matched with the target voiceprint features and the identity matching result represents that the voice content is matched with the target identity information, determining the object to be identified as the target object.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for identifying an object, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring voice information replied by an object to be recognized to a preset problem, and the preset problem is associated with target identity information of a target object; the extraction module is used for extracting the characteristics of the voice information to obtain the voice content and the voiceprint characteristics corresponding to the voice information; the first matching module is used for matching the voiceprint features with the target voiceprint features to obtain a voiceprint matching result; the second matching module is used for matching the voice content with the target identity information to obtain an identity matching result; and the determining module is used for determining whether the object to be identified is the target object or not based on the voiceprint matching result and the identity matching result.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for identifying an object when running.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including one or more processors; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a method for running a program, wherein the program is arranged to perform the above-described method of identifying an object when run.
According to another aspect of the embodiments of the present invention, there is also provided a computer program product, which includes a computer program/instructions, and the computer program/instructions, when executed by a processor, implement the above method for identifying an object.
In the embodiment of the invention, the voice content and the voiceprint characteristics of the object to be recognized are adopted to recognize the identity of the object to be recognized, the voiceprint matching result is obtained by acquiring the voice information replied by the object to be recognized to the preset problem, then matching the voiceprint characteristics with the target voiceprint characteristics, and the voice content is matched with the target identity information to obtain the identity matching result, so that whether the object to be recognized is the target object is determined based on the voiceprint matching result and the identity matching result. Wherein the preset question is associated with target identity information of the target object.
In the above process, since the voiceprint differs from person to person, the voiceprint matching result can be obtained by matching the voiceprint feature in the speech information of the object to be recognized with the target voiceprint feature of the target object to preliminarily determine the degree of association between the object to be recognized and the target object, however, since other people can acquire the voice information of the target object by recording and the like to impersonate consumption, therefore, on the basis, matching the voice content in the voice information replied by the object to be recognized aiming at the preset problem with the target identity information of the target object to obtain an identity matching result, determining whether the object to be recognized is the target object or not from two aspects by combining the voiceprint matching result and the identity matching result, therefore, the identity of the object to be recognized can be accurately determined, and the transaction safety of the target object is improved.
Therefore, the scheme provided by the application achieves the purpose of acquiring the voice content and the voiceprint characteristics of the object to be recognized to determine the identity of the object to be recognized, thereby achieving the technical effect of improving the transaction security of the target object and further solving the technical problem of low transaction security caused by inaccurate identity recognition of the consumer in the prior art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of an alternative evaluation system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the operation of an alternative evaluation system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an alternative method of identifying an object according to an embodiment of the invention;
FIG. 4 is a schematic diagram of an alternative voiceprint recognition module according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an alternative apparatus for identifying objects in accordance with embodiments of the present invention;
FIG. 6 is a schematic diagram of an alternative electronic device according to an embodiment of the invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, etc.) referred to in the present disclosure are information and data authorized by the user or sufficiently authorized by each party.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a method of identifying an object, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than here.
In an optional embodiment, an evaluation system is used to execute the method provided in the present application, fig. 1 is a schematic diagram of an optional evaluation system according to an embodiment of the present invention, and fig. 2 is a schematic diagram of an optional evaluation system according to an embodiment of the present invention, as shown in fig. 1 and fig. 2, the evaluation system includes a reservation information acquisition module, a voiceprint recognition module, a voice acquisition module, a voiceprint matching module, an identity matching module, and a determination module, and the voice acquisition module includes a credit card system, an outbound module, and an acquisition module, which are connected in sequence. The reserved information acquisition module is respectively connected with the voiceprint recognition module and the credit card system, the acquisition module is connected with the voiceprint matching module, the voiceprint matching module is respectively connected with the identity matching module and the judgment module, and the identity matching module is also connected with the judgment module.
Fig. 3 is a schematic diagram of an alternative method for identifying an object according to an embodiment of the present invention, as shown in fig. 3, the method including the steps of:
step S101, voice information of the object to be recognized for replying to a preset question is obtained, wherein the preset question is associated with target identity information of the target object.
In step S101, a voice information of the object to be recognized replying to the preset question may be acquired through the voice collecting module, where the preset question may be generated through a credit card system, as shown in fig. 2, target identity information of a target object associated with the preset question may be acquired through the reserved information collecting module and stored in the credit card system, and the target identity information may be information in a credit card application form filled by the target object when applying for a credit card, or may be other information that is reserved by the target object and can be used for representing the identity of the target object.
Optionally, the credit card system randomly generates a preset question based on the relevant data in the credit card application form information, for example: generate "please answer the day of birth of your message" for the identification number information in the application form information? "where do you answer your hometown? "wait to predetermine the question, or directly generate the same problem of predetermineeing to the question that reserves in the application form information, later, as shown in fig. 2, send the aforesaid predetermined question that generates to the module of exhaling outward, exhale the module outward and acquire the predetermined question, and the terminal equipment (such as cell-phone, panel etc. electronic equipment based on the communication of phone card) of calling the target object based on the reservation cell-phone number of target object, broadcast and predetermine the question and supply the target object of waiting to discern to answer, later through the answer content of collection module collection object of waiting to discern, thereby realize treating the acquisition of the speech information that the target of discerning replied to the predetermined question.
It should be noted that by acquiring the voice information of the object to be recognized replying to the preset problem, the acquisition of the voiceprint features and the voice content of the subsequent object to be recognized and the limitation of the expression content of the voice content can be realized, so that the accurate voiceprint matching result and identity matching result can be acquired subsequently.
Step S102, extracting the characteristics of the voice information to obtain the voice content and the voiceprint characteristics corresponding to the voice information.
In step S102, as shown in fig. 2, the voice information may be subjected to feature extraction by the acquisition module to obtain voice content and voiceprint features, or the voice information may be subjected to feature extraction by the voiceprint matching module to obtain voiceprint features, and the voice information is subjected to feature extraction by the identity matching module to obtain voice content. The vocal print characteristics are a sound wave frequency spectrum which can reflect physiological and behavioral characteristics of speakers, and the vocal print characteristics of each person are different because the vocal organs (tongue, teeth, larynx, lung and nasal cavity) of each person are different in size and shape; speech content is data that characterizes the content represented by an object to be recognized.
Optionally, the voiceprint feature of the object to be recognized may be Mel-Frequency cepstral coefficients (MFCCs), or may be a voiceprint Model, where the voiceprint Model may be calculated based on Mel-Frequency cepstral coefficients (MFCCs) and a Gaussian Mixture Model (GMM), and in this embodiment, the voiceprint feature of the object to be recognized is an MFCC parameter.
It should be noted that the voice content and the voiceprint feature are obtained by extracting the features of the voice information, so that the voiceprint matching result and the identity matching result can be successfully obtained subsequently, and the identity of the object to be recognized is recognized.
And step S103, matching the voiceprint characteristics with the target voiceprint characteristics to obtain a voiceprint matching result.
In step S103, as shown in fig. 2, the voiceprint matching model may match the MFCC parameter of the speech information of the object to be recognized with the target voiceprint feature based on a preset matching operation function, so as to obtain a voiceprint matching result. In this embodiment, the target voiceprint feature is a voiceprint model obtained based on MFCC parameters and GMM training, and is stored in the credit card system as structured data, and the voiceprint matching result is used to characterize whether the voiceprint feature matches the target voiceprint feature.
It should be noted that, based on the uniqueness of each person's voice, by matching the voiceprint features with the target voiceprint features, it is possible to realize the preliminary judgment of whether the object to be recognized is the target object, and have the advantage of high accuracy.
And step S104, matching the voice content with the target identity information to obtain an identity matching result.
In step S104, another matching operation function may be preset in the identity matching module or the determining module, and the identity matching module or the determining module matches the voice content of the object to be recognized with the target identity information to obtain an identity matching result. In this embodiment, the target identity information is information in the credit card application form, and the identity matching result is used to represent whether the voice content matches the target identity information.
It should be noted that, by matching the voice content with the target identity information, it is effectively prevented that other people have previously recorded the audio of the target object to cope with the voiceprint matching, thereby improving the accuracy of determining whether the target object to be recognized is the target object.
And step S105, determining whether the object to be identified is the target object or not based on the voiceprint matching result and the identity matching result.
In step S105, as shown in fig. 2, in the case that the voiceprint matching result represents that the voiceprint feature does not match the target voiceprint feature or the identity matching result represents that the voice content does not match the target identity information, it is determined that the object to be recognized is not the target object, and in the case that the voiceprint matching result represents that the voiceprint feature matches the target voiceprint feature and the identity matching result represents that the voice content matches the target identity information, it is determined that the object to be recognized is the target object.
It should be noted that, by determining the object to be recognized as the target object only when the voiceprint matching result and the identity matching result both represent the information of the object to be recognized and the information of the target object are matched, the accuracy of the identity recognition of the target object can be improved, thereby avoiding the consumption of the unreal intention of the target object from a large probability, and further improving the security of the transaction of the target object.
Further, it is emphasized that some of the contents of the foregoing steps S102-S104 may be changed in order from one another. Specifically, feature extraction may be performed on the voice information to obtain voice content and voiceprint features corresponding to the voice information, and then the content in step S103 and the content in step S104 are performed at the same time, or the content in any one of step S103 and step S104 is performed first, and then the content in the other of step S103 and step S104 is performed.
Based on the schemes defined in the above steps S101 to S105, it can be known that, in the embodiment of the present invention, the voice content and the voiceprint feature of the object to be recognized are used to recognize the identity of the object to be recognized, the voice information of the object to be recognized replying to the preset problem is obtained, then the voiceprint feature is matched with the target voiceprint feature to obtain a voiceprint matching result, and the voice content is matched with the target identity information to obtain an identity matching result, so as to determine whether the object to be recognized is the target object based on the voiceprint matching result and the identity matching result. Wherein the preset question is associated with target identity information of the target object.
It is to be readily noted that, in the above-described process, since the voiceprint differs from person to person, the voiceprint matching result can be obtained by matching the voiceprint feature in the speech information of the object to be recognized with the target voiceprint feature of the target object to preliminarily determine the degree of association between the object to be recognized and the target object, however, since other people can acquire the voice information of the target object by recording and the like to impersonate consumption, therefore, on the basis, matching the voice content in the voice information replied by the object to be recognized aiming at the preset problem with the target identity information of the target object to obtain an identity matching result, determining whether the object to be recognized is the target object or not from two aspects by combining the voiceprint matching result and the identity matching result, therefore, the identity of the object to be recognized can be accurately determined, and the transaction safety of the target object is improved.
Therefore, the scheme provided by the application achieves the purpose of acquiring the voice content and the voiceprint characteristics of the object to be recognized to determine the identity of the object to be recognized, thereby achieving the technical effect of improving the transaction security of the target object and further solving the technical problem of low transaction security caused by inaccurate identity recognition of the consumer in the prior art.
In an alternative embodiment, it may be set that the voice message replied by the object to be recognized is acquired only under a specific condition, specifically, the consumption information of the target object and at least one consumption limiting condition of the target object are acquired first; and then generating a preset question based on the target identity information when the consumption information meets at least one consumption limiting condition.
The consumption information of the target object and at least one consumption limiting condition of the target object can be obtained through the credit card system, and the consumption limiting condition can be stored in the credit card application table or other information tables. In this embodiment, the consumption information of the target object includes, but is not limited to, consumption times, consumption amount, consumption time, etc. of the target object, and the consumption limit conditions include, but are not limited to, limits on the consumption times, consumption amount, and consumption time.
Further, when the credit card system judges that the single consumption amount of the credit card exceeds the upper limit of the single consumption amount set by the target customer or counts that the consumption times of the credit card in one week reach the upper limit, the credit card system generates the preset question based on the target identity information for the object to be identified to answer.
It should be noted that, by setting to acquire the voice information replied by the object to be recognized only under the specific condition, that is, only calling the user under the specific condition, on one hand, the problem of poor user experience caused by too many calling times of the user can be avoided, and on the other hand, too much loss caused when the credit card of the user is stolen can be prevented.
In an optional embodiment, before matching the voiceprint features with the target voiceprint features to obtain a voiceprint matching result, the target voiceprint features of the target object need to be obtained first.
Optionally, as shown in fig. 2, the reserved information collection module may collect target voice information of the target object first, then the voiceprint recognition module performs feature extraction on the target voice information to obtain target feature parameters corresponding to the target voice information, and finally the target feature parameters are trained to obtain target voiceprint features. The target characteristic parameters are MFCC parameters, and the MFCC parameters are trained through the GMM.
Specifically, in this embodiment, the reserved information collection module includes a voiceprint collection device, and the voiceprint collection device can collect high-quality voiceprint data meeting the requirement of establishing a library for various voiceprints only through one-time voice input. The reservation information acquisition module can be arranged on a self-service terminal of a bank outlet or a counter of the outlet and other banks with own credible channels for a user to search, when the user needs to reserve the target voice information, the reservation information acquisition module randomly prompts 10 Chinese words to be displayed on a display interface of related equipment, requires the user to read the 10 Chinese words aloud, and records audio through the voiceprint acquisition equipment so as to finish the acquisition of the target voice information.
Further, fig. 4 is a schematic working diagram of an optional voiceprint recognition module according to an embodiment of the present invention, and as shown in fig. 2 and fig. 4, a process of extracting a target voiceprint feature by the voiceprint recognition module is described in detail as follows.
When the voiceprint recognition module acquires the target voice information, the voiceprint recognition module firstly preprocesses the target voice information, namely, pre-emphasizes a voiceprint data sequence, so that the high-frequency part is improved, the frequency spectrum of the signal becomes flat, and the signal is kept in the whole frequency band from low frequency to high frequency, namely, the target voice information passes through a high-pass filter. The formula is shown below, where μ ═ 0.97.
H(Z)＝1-μz-1
Then, 256 sampling points are taken to synthesize one observation unit as one frame. The formula for multiplying each frame by the "Hamming window" is as follows:
where a is 0.46 and N represents the number of samples in each frame, i.e. 256.
Next, fourier transform is performed on the minute hand signal of each frame multiplied by the "hamming window" to obtain the frequency spectrum of each frame, and the formula is as follows:
wherein, Xa(k) The spectrum of each frame is represented, N represents the number of fourier transform points, and x (N) is the voiceprint input signal.
Then, the energy spectrum is passed through a set of Mel-scale filters, which in this embodiment are triangular filter banks, to eliminate harmonics.
Then, the logarithmic energy is calculated and the MFCC parameters are obtained, the formula is as follows:
where s (M) represents the log energy of the filter bank output, M represents the number of filters, Hm(k) Representing the frequency response of the triangular filter.
Wherein, C (n) represents MFCC parameters, and L represents the order of the MFCC parameters.
And finally, training the MFCC parameters through GMM to obtain a target voiceprint model, namely a target voiceprint characteristic, and storing the target voiceprint model in a voiceprint recognition module, wherein the formula is as follows:
therefore, the target voiceprint characteristics are acquired.
It should be noted that, by extracting the target voiceprint features, when the evaluation system acquires the voiceprint features of the object to be recognized, the voiceprint features of the object to be recognized can be accurately judged, so that whether the object to be recognized is the target object or not can be accurately judged.
In an optional embodiment, after the voiceprint matching module matches the voiceprint features with the target voiceprint features to obtain a voiceprint matching result, the identity type of the object to be recognized is judged to determine whether the identity matching result is obtained.
Optionally, as shown in fig. 2, the voiceprint matching module determines, based on the voiceprint matching result, whether the identity type of the object to be recognized is the first type (corresponding to "whether to match" of the voiceprint matching module part in the drawing), and when the identity type of the object to be recognized is determined to be the first type, the voiceprint matching module sends the prompt information or the voice content of the object to be recognized to the identity matching module, so that the identity matching module matches the voice content with the target identity information to obtain an identity matching result; on the contrary, when the voiceprint matching module determines that the identity type of the object to be recognized is the second type, the object to be recognized is determined not to be the target object, and the judgment result is directly sent to the judgment module, wherein the association degree between the object to be recognized and the target object represented by the first type is larger than the preset association degree, and the association degree between the object to be recognized and the target object represented by the second type is smaller than or equal to the preset association degree.
Specifically, a preset association degree and an association degree corresponding to the voiceprint matching result and the identity matching result respectively may be set in the voiceprint matching module and the determination module, for example, if the voiceprint matching result represents that the voiceprint feature of the object to be recognized matches the target voiceprint feature, the association degree between the object to be recognized and the target object is increased by 50, otherwise, if the voiceprint matching result represents that the voiceprint feature of the object to be recognized does not match the target voiceprint feature, the association degree between the object to be recognized and the target object is not changed. Similarly, the same setting is performed on the association degrees corresponding to the identity matching results by referring to the setting method. Further, the preset association degree is set in the interval of (0, 50), that is, the judgment of the identity type to be recognized can be realized, and the higher the association degree is, the more likely the representation object to be recognized is to be the target object.
It should be noted that, when the voiceprint matching result represents that the voice information is not matched with the target voice information, it is already stated that the object to be recognized is not the target object, and therefore, after the voiceprint matching result is obtained, the identity type of the object to be recognized is judged to determine whether the identity matching result is obtained, so that the workload of the evaluation system can be effectively reduced, the final recognition result cannot be influenced, the calculation cost is reduced, and the work efficiency is improved.
In an alternative embodiment, as shown in fig. 2, the voice content may be converted to obtain text information corresponding to the voice content, and then the text information is matched with the target identity information to obtain an identity matching result.
Optionally, the identity matching module may directly obtain the voice content from the acquisition module or the voiceprint matching module, or may obtain the voice information from the acquisition module or the voiceprint matching module first, and then extract the voice information by the identity matching module to obtain the voice content. After the identity matching module acquires the voice content, the conversion equipment cuts off sound waves of the voice content according to frames, forms a state by using the frames, forms phonemes by using the state, synthesizes the phonemes into words, and can realize extraction of text information. In the prior art, there are many conversion devices with high recognition rate and high accuracy, and these conversion devices support multiple languages and dialects, and even have a function of hybrid recognition.
It should be noted that the voice content is converted into the text information, so as to facilitate comparison with the target identity information, and further improve the working efficiency of the application.
In an optional embodiment, when the judging module determines that the object to be identified is the target object based on the voiceprint matching result and the identity matching result, the judging module sends the result to the outbound module, so that the outbound module inquires the target object about fields of 'whether to approve the consumption, approve to press a 1 key and disapprove to press a 2 key', the acquisition module acquires the consumption intention input by the target object, and the judging module makes a decision according to the acquisition intention to finally allow the target object to be successfully consumed by swiping a card.
In another optional embodiment, the outbound module may also directly play the inquiry field after playing the preset question, the acquisition module acquires the consumption intention input by the target object, and the determination module makes a decision according to the acquisition intention to finally allow the target object to be consumed successfully by swiping a card after the determination module determines that the object to be identified is the target object. And if the judging module determines that the object to be identified is not the target object, the judging module sends warning information to the credit card system to prevent the consumption.
It should be noted that, the invention carries out the evaluation of the credit card consumption will authenticity after carrying out the technical processing on the reserved information when the client applies for the credit card and the voice information acquired during the real-time consumption by the voiceprint recognition technology, which can effectively prevent the credit card from being embezzled, thus greatly improving the security of the risk prevention system of the financial institution, strengthening the wind control capability, increasing the security of the user and preventing identity fraud. The condition of over consumption of the consumer can be controlled, and the risk of the bank credit card after the credit card is credited is greatly reduced.
Example 2
According to an embodiment of the present invention, an embodiment of an apparatus for identifying an object is provided, where fig. 5 is a schematic diagram of an alternative apparatus for identifying an object according to an embodiment of the present invention, as shown in fig. 5, the apparatus includes:
an obtaining module 501, configured to obtain voice information of an object to be recognized replying to a preset question, where the preset question is associated with target identity information of a target object;
an extraction module 502, configured to perform feature extraction on the voice information to obtain voice content and voiceprint features corresponding to the voice information;
a first matching module 503, configured to match the voiceprint feature with the target voiceprint feature to obtain a voiceprint matching result;
a second matching module 504, configured to match the voice content with the target identity information to obtain an identity matching result;
and a determining module 505, configured to determine whether the object to be identified is the target object based on the voiceprint matching result and the identity matching result.
It should be noted that the obtaining module 501, the extracting module 502, the first matching module 503, the second matching module 504, and the determining module 505 correspond to steps S101 to S105 in the foregoing embodiment, and the five modules are the same as the corresponding steps in the implementation example and application scenarios, but are not limited to the disclosure in embodiment 1.
Optionally, the apparatus for identifying an object further includes: the sub-acquisition module is used for acquiring consumption information of the target object and at least one consumption limiting condition of the target object; and the generating module is used for generating a preset problem based on the target identity information when the consumption information meets at least one consumption limiting condition.
Optionally, the apparatus for identifying an object further includes: the acquisition module is used for acquiring target voice information of a target object; the extraction module is used for extracting the characteristics of the target voice information to obtain target characteristic parameters corresponding to the target voice information; and the training module is used for training the target characteristic parameters to obtain the target voiceprint characteristics.
Optionally, the apparatus for identifying an object further includes: the first sub-determination module is used for determining whether the identity type of the object to be recognized is a first type or not based on the voiceprint matching result, wherein the association degree between the object to be recognized and the target object represented by the first type is larger than the preset association degree; the second sub-determination module is used for matching the voice content with the target identity information to obtain an identity matching result under the condition that the identity type of the object to be recognized is determined to be the first type; and the third sub-determination module is used for determining that the object to be recognized is not the target object under the condition that the identity type of the object to be recognized is determined to be the second type, wherein the association degree between the object to be recognized and the target object represented by the second type is smaller than or equal to the preset association degree.
Optionally, the second matching module further includes: the conversion module is used for converting the voice content to obtain text information corresponding to the voice content; and the matching module is used for matching the text information with the target identity information to obtain an identity matching result.
Optionally, the determining module further includes: the fourth sub-determination module is used for determining that the object to be identified is not the target object under the condition that the voiceprint matching result represents that the voiceprint characteristics are not matched with the target voiceprint characteristics or the identity matching result represents that the voice content is not matched with the target identity information; and the fifth sub-determination module is used for determining that the object to be identified is the target object under the condition that the voiceprint matching result represents that the voiceprint features are matched with the target voiceprint features and the identity matching result represents that the voice content is matched with the target identity information.
Example 3
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for identifying an object when running.
Example 4
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, wherein fig. 6 is a schematic diagram of an alternative electronic device according to the embodiments of the present invention, as shown in fig. 6, the electronic device includes one or more processors; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a method for running a program, wherein the program is arranged to perform the above-described method of identifying an object when run.
Example 5
According to another aspect of the embodiments of the present invention, there is also provided a computer program product, which includes a computer program/instructions, and the computer program/instructions, when executed by a processor, implement the above method for identifying an object.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method of identifying an object, comprising:
acquiring voice information replied by an object to be recognized to a preset problem, wherein the preset problem is associated with target identity information of a target object;
extracting the characteristics of the voice information to obtain the voice content and the voiceprint characteristics corresponding to the voice information;
matching the voiceprint features with target voiceprint features to obtain a voiceprint matching result;
matching the voice content with the target identity information to obtain an identity matching result;
and determining whether the object to be identified is the target object or not based on the voiceprint matching result and the identity matching result.
2. The method for recognizing the object according to claim 1, wherein before acquiring the voice message of the object to be recognized replying to the preset question, the method comprises:
acquiring consumption information of the target object and at least one consumption limiting condition of the target object;
and when the consumption information meets the at least one consumption limiting condition, generating the preset problem based on the target identity information.
3. The method of identifying an object according to claim 1, wherein before matching the voiceprint features with target voiceprint features to obtain a voiceprint matching result, the method comprises:
collecting target voice information of the target object;
extracting the characteristics of the target voice information to obtain target characteristic parameters corresponding to the target voice information;
and training the target characteristic parameters to obtain the target voiceprint characteristics.
4. The method of identifying an object according to claim 1, wherein after matching the voiceprint features with target voiceprint features to obtain a voiceprint matching result, the method further comprises:
determining whether the identity type of the object to be recognized is a first type or not based on the voiceprint matching result, wherein the first type represents that the association degree between the object to be recognized and the target object is greater than a preset association degree;
under the condition that the identity type of the object to be recognized is determined to be the first type, matching the voice content with the target identity information to obtain an identity matching result;
and under the condition that the identity type of the object to be recognized is determined to be a second type, determining that the object to be recognized is not the target object, wherein the second type represents that the association degree between the object to be recognized and the target object is less than or equal to the preset association degree.
5. The method of any one of claims 1 or 4, wherein matching the voice content with the target identity information to obtain an identity matching result comprises:
converting the voice content to obtain text information corresponding to the voice content;
and matching the text information with the target identity information to obtain the identity matching result.
6. The method of identifying an object according to claim 1, wherein determining whether the object to be identified is the target object based on the voiceprint matching result and the identity matching result comprises:
determining that the object to be identified is not the target object under the condition that the voiceprint matching result represents that the voiceprint features are not matched with the target voiceprint features or the identity matching result represents that the voice content is not matched with the target identity information;
and determining the object to be identified as the target object under the condition that the voiceprint matching result represents that the voiceprint features are matched with the target voiceprint features and the identity matching result represents that the voice content is matched with the target identity information.
7. An apparatus for identifying an object, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring voice information replied by an object to be recognized to a preset problem, and the preset problem is associated with target identity information of a target object;
the extraction module is used for extracting the characteristics of the voice information to obtain the voice content and the voiceprint characteristics corresponding to the voice information;
the first matching module is used for matching the voiceprint features with the target voiceprint features to obtain a voiceprint matching result;
the second matching module is used for matching the voice content with the target identity information to obtain an identity matching result;
and the determining module is used for determining whether the object to be identified is the target object or not based on the voiceprint matching result and the identity matching result.
8. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to carry out the method of identifying an object as claimed in any one of claims 1 to 6 when executed.
9. An electronic device, wherein the electronic device comprises one or more processors; memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a method for running a program, wherein the program is arranged to, when run, perform the method of identifying an object as claimed in any of claims 1 to 6.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the method of identifying an object of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210017887.XA CN114358790A (en) | 2022-01-07 | 2022-01-07 | Method and device for identifying object, computer readable storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210017887.XA CN114358790A (en) | 2022-01-07 | 2022-01-07 | Method and device for identifying object, computer readable storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358790A true CN114358790A (en) | 2022-04-15 |
Family
ID=81107721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210017887.XA Pending CN114358790A (en) | 2022-01-07 | 2022-01-07 | Method and device for identifying object, computer readable storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358790A (en) |
-
2022
- 2022-01-07 CN CN202210017887.XA patent/CN114358790A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108039176B (en) | Voiceprint authentication method and device for preventing recording attack and access control system | |
| CN106847292B (en) | Method for recognizing sound-groove and device | |
| CN106373575B (en) | User voiceprint model construction method, device and system | |
| Naik | Speaker verification: A tutorial | |
| WO2020181824A1 (en) | Voiceprint recognition method, apparatus and device, and computer-readable storage medium | |
| US20150142446A1 (en) | Credit Risk Decision Management System And Method Using Voice Analytics | |
| CN109215665A (en) | A kind of method for recognizing sound-groove based on 3D convolutional neural networks | |
| Vestman et al. | Voice mimicry attacks assisted by automatic speaker verification | |
| WO2010025523A1 (en) | Voice authentication system and methods | |
| EP2879130A1 (en) | Methods and systems for splitting a digital signal | |
| Liu et al. | A Spearman correlation coefficient ranking for matching-score fusion on speaker recognition | |
| CN106709804A (en) | Interactive wealth planning consulting robot system | |
| CN108985776A (en) | Credit card security monitoring method based on multiple Information Authentication | |
| CN110473552A (en) | Speech recognition authentication method and system | |
| CN111160928A (en) | Identity verification method and device | |
| GB2521050A (en) | Credit risk decision management system and method using voice analytics | |
| WO2022126964A1 (en) | Service data verification method and apparatus, device and storage medium | |
| CN107025558A (en) | A kind of transaction system and transaction processing method | |
| CN113782032A (en) | Voiceprint recognition method and related device | |
| CN113112992B (en) | Voice recognition method and device, storage medium and server | |
| CN108447489A (en) | A kind of continuous voiceprint authentication method and system of band feedback | |
| CN112417412A (en) | Bank account balance inquiry method, device and system | |
| CN111833068A (en) | Identity verification system and method based on voiceprint recognition | |
| CN114358790A (en) | Method and device for identifying object, computer readable storage medium and electronic equipment | |
| CN108630208B (en) | Server, voiceprint-based identity authentication method 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 |