Method, apparatus and electronic device for processing identity information

Abstract

The present application provides a kind of identity information processing method, device and electronic equipment, the method is by according to the voice characteristic description text of speaker and face characteristic description text, to generate speech and portrait respectively, and according to the multiple query identities of speech and portrait generation, to determine the identity information of unknown identity person comprehensively, improve the accuracy of identity confirmation, to solve the problem that the prior art lacks the technical scheme of directly generating speech and portrait according to the text of unknown identity person's characteristics described by the speaker, and simultaneously determining the identity of unknown identity person according to speech and portrait.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method, apparatus, computer-readable storage medium, and electronic device for processing identity information. Background Technology

[0002] Existing solutions only offer two methods for identity recognition: either identifying an unknown person by sampling their speech, or identifying an unknown person by having a portrait drawn manually based on the speaker's description of their characteristics. In particular, manual drawing is inefficient. As a result, there is a lack of existing technologies that can directly generate both speech and portrait based on the text describing the characteristics of an unknown person, and simultaneously identify the unknown person based on both speech and portrait. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, computer-readable storage medium, and electronic device for processing identity information, so as to at least solve the problem in the prior art of lacking a technical solution for directly generating speech and human image based on text describing the characteristics of an unknown person from a speaker, and simultaneously determining the identity of the unknown person based on the speech and human image.

[0004] To achieve the above objectives, according to one aspect of this application, a method for processing identity information is provided, the method comprising:

[0005] The system obtains the descriptive text of the speaker sent by the user terminal, and filters the descriptive text of the speaker to obtain the descriptive text of human voice features and the descriptive text of human face features. The descriptive text of the speaker is the text describing the features of an unknown person described by the speaker.

[0006] A first human voice audio corresponding to the human voice feature description text is determined, a target face image corresponding to the face feature description text is determined, and a second human voice audio corresponding to the target face image is determined;

[0007] Based on the voice database, a first query identity corresponding to the first voice audio and a second query identity corresponding to the second voice audio are determined. Based on the face database, a third query identity corresponding to the target face image is determined. The voice database stores multiple voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The voice audios and identities are in one-to-one correspondence, as are the face images and identities. The identities stored in the face database and the identities stored in the voice database are in one-to-one correspondence.

[0008] The identity information of the unknown person is determined based on at least the first queried identity, the second queried identity, and the third queried identity, wherein the identity information of the unknown person is the one with the highest repetition among the queried identities.

[0009] Optionally, determining the first human voice audio corresponding to the human voice feature description text includes: a first modification step: upon receiving human voice text modification information sent by the user terminal, modifying the human voice feature description text using the human voice text modification information, and determining the first human voice audio corresponding to the modified human voice feature description text; repeating the first modification step at least once until a human voice audio correct instruction sent by the user terminal is received, the human voice audio correct instruction being used to indicate that the first human voice audio matches the voice of the unknown person.

[0010] Optionally, determining the identity information of the unknown person based at least on the first query identity, the second query identity, and the third query identity includes: converting all voices in the voice database into multiple preset voice description texts; upon receiving a correct voice audio instruction sent by the user terminal, performing similarity comparison processing between the corrected voice feature description text at the current moment and each of the preset voice description texts to obtain multiple first similarities; determining the fourth query identity as the identity corresponding to the preset voice description text corresponding to the maximum value among all the first similarities; and determining the identity information of the unknown person based on the first query identity, the second query identity, the third query identity, and the fourth query identity.

[0011] Optionally, determining the target face image corresponding to the facial feature description text includes: a second modification step: upon receiving facial text modification information sent by the user terminal, modifying the facial feature description text using the facial text modification information, and determining the target face image corresponding to the modified facial feature description text; repeating the second modification step at least once until a face correctness instruction sent by the user terminal is received, the face correctness instruction being used to indicate that the target face image matches the facial image of the unknown person.

[0012] Optionally, determining the identity information of the unknown person based at least on the first query identity, the second query identity, and the third query identity includes: converting all face images in the face database into multiple preset face description texts; upon receiving the face correctness instruction sent by the user terminal, performing similarity comparison processing between the corrected face feature description text at the current moment and each of the preset face description texts to obtain multiple second similarities; determining the fifth query identity as the identity corresponding to the preset face description text corresponding to the maximum value among all the second similarities; and determining the identity information of the unknown person based on the first query identity, the second query identity, the third query identity, and the fifth query identity.

[0013] Optionally, the identity information of the unknown person is determined based at least on the first query identity, the second query identity, and the third query identity, including: when the first query identity, the second query identity, and the third query identity are all different, the identity information of the unknown person is determined to be the first query identity.

[0014] Optionally, the identity information of the unknown person is determined based on at least the first query identity, the second query identity, and the third query identity, including: determining the identity information of the unknown person as the one with the highest degree of repetition among the first query identity, the second query identity, and the third query identity, based on the first query identity, the second query identity, and the third query identity.

[0015] According to another aspect of this application, an identity information processing apparatus is provided, the apparatus comprising:

[0016] The acquisition unit is used to acquire the descriptive text of the speaker sent by the user terminal, and to filter the descriptive text of the speaker to obtain the descriptive text of human voice features and the descriptive text of human face features, wherein the descriptive text of the speaker is the text describing the features of an unknown person described by the speaker.

[0017] The first determining unit is used to determine a first human voice audio corresponding to the human voice feature description text, and to determine a target face image corresponding to the face feature description text, and to determine a second human voice audio corresponding to the target face image;

[0018] The second determining unit is configured to determine a first query identity corresponding to the first human voice audio and a second query identity corresponding to the second human voice audio based on a human voice database, and to determine a third query identity corresponding to a target face image based on a face database. The human voice database stores multiple human voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The human voice audios and identities are in one-to-one correspondence, as are the face images and identities. The identities stored in the face database and the identities stored in the human voice database are in one-to-one correspondence.

[0019] The third determining unit is used to determine the identity information of the unknown person based at least on the first query identity, the second query identity, and the third query identity, wherein the identity information of the unknown person is the one with the highest repetition rate among the query identities.

[0020] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0021] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0022] By applying the technical solution of this application, voice and image are generated respectively by describing the voice characteristics and facial features of the speaker. Multiple query identities generated from the voice and image are then used to comprehensively determine the identity information of an unknown person, thereby improving the accuracy of identity confirmation. This solves the problem in the prior art of lacking a technical solution that directly generates voice and image based on the text describing the features of an unknown person from the speaker, and simultaneously determines the identity of an unknown person based on the voice and image. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 A flowchart illustrating an identity information processing method according to an embodiment of this application is shown.

[0025] Figure 2A flowchart illustrating another method for processing identity information according to an embodiment of this application is shown;

[0026] Figure 3 A structural block diagram of an identity information processing apparatus provided according to an embodiment of this application is shown. Detailed Implementation

[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] As described in the background section, existing solutions only offer two methods for identity recognition: either identifying an unknown person by sampling their speech, or identifying an unknown person by having a portrait manually drawn based on a description of their features by the speaker. Manual drawing, in particular, is inefficient. Consequently, existing technologies lack a technical solution for directly generating speech and a portrait from text describing the features of an unknown person, and simultaneously determining the identity of an unknown person based on both. To address this problem, embodiments of this application provide a method, apparatus, computer-readable storage medium, and electronic device for processing identity information.

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] This embodiment provides a method for processing identity information. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] Figure 1 This is a flowchart illustrating a method for processing identity information according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0034] Step S101: Obtain the description text of the speaker sent by the user terminal, and filter the description text of the speaker to obtain the voice feature description text and the face feature description text respectively. The description text of the speaker is the text of the features of the unknown person described by the speaker.

[0035] Specifically, based on the description text of the speaker, text describing human voice characteristics and text describing human face characteristics are filtered out;

[0036] Step S102: Determine the first human voice audio corresponding to the above-mentioned human voice feature description text, determine the target face image corresponding to the above-mentioned face feature description text, and determine the second human voice audio corresponding to the above-mentioned target face image;

[0037] Specifically, the specific implementation method for determining the first human voice audio corresponding to the aforementioned human voice feature description text can be implemented using a neural network model. Similarly, determining the target face image corresponding to the aforementioned face feature description text and determining the second human voice audio corresponding to the aforementioned target face image can also be implemented using a neural network model, just like the specific implementation method for determining the first human voice audio corresponding to the aforementioned human voice feature description text. These will not be elaborated further here.

[0038] The determination of the first human voice audio corresponding to the aforementioned human voice feature description text in step S102 includes: a first modification step: upon receiving the human voice text modification information sent by the user terminal, the human voice text modification information is used to correct the aforementioned human voice feature description text, and the first human voice audio corresponding to the corrected human voice feature description text is determined; the first modification step is repeated at least once until a correct human voice audio instruction is received from the user terminal, wherein the correct human voice audio instruction is used to indicate that the aforementioned first human voice audio matches the voice of the aforementioned unknown person.

[0039] Specifically, in order to ensure that the first voice audio can accurately present the voice characteristics of the unknown person, the speaker needs to continuously revise the text describing the voice characteristics until the first voice audio can present the voice characteristics of the unknown person.

[0040] The determination of the target face image corresponding to the aforementioned face feature description text in step S102 includes: a second modification step: upon receiving the face text modification information sent by the user terminal, the face feature description text is modified using the aforementioned face text modification information, and the target face image corresponding to the modified face feature description text is determined; the second modification step is repeated at least once until a face correctness instruction is received from the user terminal, wherein the face correctness instruction is used to indicate that the target face image matches the face image of the aforementioned unknown person.

[0041] Specifically, in order to ensure that the target facial image can accurately represent the appearance of the unknown person, the speaker needs to continuously revise the facial feature description text until the target facial image can represent the appearance of the unknown person.

[0042] Step S103: Based on the voice database, determine the first query identity corresponding to the first voice audio and the second query identity corresponding to the second voice audio; and based on the face database, determine the third query identity corresponding to the target face image. The voice database stores multiple voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The voice audios and identities are in one-to-one correspondence, as are the face images and identities. The identities stored in the face database and the identities stored in the voice database are in one-to-one correspondence.

[0043] Specifically, the identity corresponding to the first human voice audio in the human voice database is the first query identity, the identity corresponding to the second human voice audio in the human voice database is the second query identity, and the identity corresponding to the target face image in the face database is the third query identity. The identities in the two databases are in one-to-one correspondence, and the identities in one-to-one correspondence are the same. That is, the face database stores identity A, identity B, and identity C, and the human voice database also stores identity A, identity B, and identity C.

[0044] Step S104: Determine the identity information of the unknown person based at least on the first queried identity, the second queried identity, and the third queried identity. The identity information of the unknown person is the one with the highest repetition rate among the queried identities.

[0045] In the above steps, voice and image are generated respectively by describing the speaker's voice characteristics and facial features. Multiple query identities generated from the voice and image are then used to comprehensively determine the identity information of the unknown person, improving the accuracy of identity confirmation. This solves the problem in the existing technology of lacking a technical solution to directly generate voice and image based on the text describing the characteristics of the unknown person from the speaker, and to determine the identity of the unknown person based on the voice and image.

[0046] Step S104 involves determining the identity information of the unknown person based at least on the first queried identity, the second queried identity, and the third queried identity, including several specific implementation methods:

[0047] The first specific implementation method is as follows: convert all the voices in the above-mentioned voice database into multiple preset voice description texts; when the above-mentioned user terminal sends the above-mentioned voice audio correct instruction, perform similarity comparison processing between the corrected voice feature description text at the current moment and each of the above-mentioned preset voice description texts to obtain multiple first similarities; determine the fourth query identity as the identity corresponding to the above-mentioned preset voice description text corresponding to the maximum value among all the above-mentioned first similarities.

[0048] Specifically, each preset human voice description text corresponds to an identity stored in a human voice database. That is, the preset human voice description text corresponding to the maximum similarity is found through similarity, and then the identity stored in the human voice database corresponding to the preset human voice description text is found. This identity is the fourth query identity.

[0049] All face images in the aforementioned face database are converted into multiple preset face description texts. Upon receiving the aforementioned face correctness instruction sent by the aforementioned user terminal, the corrected face feature description text at the current moment is compared with each of the aforementioned preset face description texts to obtain multiple second similarities. The fifth query identity is determined to be the identity corresponding to the aforementioned preset face description text corresponding to the maximum value among all the aforementioned second similarities.

[0050] Specifically, each preset face description text corresponds to an identity stored in the face database. That is, the preset face description text corresponding to the maximum similarity is found by using similarity, and then the identity stored in the face database corresponding to the preset face description text is found. This identity is the fifth query identity.

[0051] Based on the first, second, third, fourth, and fifth queried identities mentioned above, the identity information of the aforementioned unknown person is determined.

[0052] Specifically, for example, if the first, second, and third query identities are all A, and the fourth and fifth query identities are all B, then the identity information of the unknown person is A. That is, the identity with the highest repetition is selected as the identity information of the unknown person, thereby improving the accuracy of identity confirmation.

[0053] The second specific implementation method is as follows: when the first query identity, the second query identity, and the third query identity are all different, the identity information of the unknown person is determined to be the first query identity; based on the first query identity, the second query identity, and the third query identity, the identity information of the unknown person is determined to be the one with the highest degree of repetition among the first query identity, the second query identity, and the third query identity.

[0054] Specifically, the first query identity has the highest priority. If the first query identity and the second query identity are the same, and the third query identity is different from the first query identity, the identity information of the unknown person is determined to be either the first query identity or the second query identity.

[0055] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the identity information processing method of this application will be described in detail below with reference to specific embodiments.

[0056] This embodiment relates to a specific method for processing identity information, such as... Figure 2 As shown, it includes the following steps:

[0057] Step S1: Obtain the description text of the speaker sent by the user terminal, and filter the description text of the speaker to obtain the voice feature description text and the face feature description text respectively. The description text of the speaker is the text of the features of the unknown person described by the speaker.

[0058] Step S2: Determine the first human voice audio corresponding to the human voice feature description text, determine the target face image corresponding to the face feature description text, and determine the second human voice audio corresponding to the target face image;

[0059] Specifically, determining the first human voice audio corresponding to the human voice feature description text includes: a first modification step: upon receiving human voice text modification information sent by the user terminal, the human voice text modification information is used to correct the human voice feature description text, and the first human voice audio corresponding to the corrected human voice feature description text is determined; the first modification step is repeated at least once until a correct human voice audio instruction is received from the user terminal, the correct human voice audio instruction being used to indicate that the first human voice audio matches the voice of an unknown person;

[0060] Determining the target face image corresponding to the face feature description text includes: a second modification step: upon receiving face text modification information sent by the user terminal, the face feature description text is corrected using the face text modification information, and the target face image corresponding to the corrected face feature description text is determined; the second modification step is repeated at least once until a face correctness instruction is received from the user terminal, the face correctness instruction being used to indicate that the target face image matches the face image of an unknown person;

[0061] Step S3: Based on the voice database, determine the first query identity corresponding to the first voice audio and the second query identity corresponding to the second voice audio, and based on the face database, determine the third query identity corresponding to the target face image. The voice database stores multiple voice audios and multiple identities, and the face database stores multiple face images and multiple identities. Voice audios and identities are in one-to-one correspondence, as are face images and identities. The identities stored in the face database and the identities stored in the voice database are in one-to-one correspondence.

[0062] Step S4: Convert all human voices in the human voice database into multiple preset human voice description texts; upon receiving the correct human voice audio command sent by the user terminal, perform similarity comparison processing between the corrected human voice feature description text at the current moment and each preset human voice description text to obtain multiple first similarities; determine the fourth query identity as the identity corresponding to the preset human voice description text corresponding to the maximum value among all first similarities.

[0063] Step S5: Convert all face images in the face database into multiple preset face description texts; upon receiving a correct face command from the user, perform similarity comparison processing between the corrected face feature description text at the current moment and each preset face description text to obtain multiple second similarities; determine the identity of the fifth query identity as the identity corresponding to the preset face description text corresponding to the maximum value among all second similarities;

[0064] Step S6: Based on the first, second, third, fourth, and fifth queried identities, determine the identity information of the unknown person. The identity information of the unknown person is the one with the highest repetition rate among the queried identities.

[0065] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0066] This application also provides an identity information processing apparatus. It should be noted that the identity information processing apparatus of this application can be used to execute the identity information processing method provided in this application. This apparatus is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0067] The following describes the identity information processing apparatus provided in the embodiments of this application.

[0068] Figure 3 This is a structural block diagram of an identity information processing apparatus provided according to an embodiment of this application. Figure 3 As shown, the device includes:

[0069] The acquisition unit 31 is used to acquire the description text of the speaker sent by the user terminal, and to filter the description text of the speaker to obtain the voice feature description text and the face feature description text respectively. The description text of the speaker is the text describing the features of the unknown person described by the speaker.

[0070] The first determining unit 32 is used to determine a first human voice audio corresponding to the above-mentioned human voice feature description text, and to determine a target face image corresponding to the above-mentioned face feature description text, and to determine a second human voice audio corresponding to the above-mentioned target face image.

[0071] The second determining unit 33 is used to determine, based on the voice database, a first query identity corresponding to the first voice audio and a second query identity corresponding to the second voice audio, and based on the face database, a third query identity corresponding to the target face image. The voice database stores multiple voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The voice audios and identities are in one-to-one correspondence, as are the face images and identities. The identities stored in the face database and the identities stored in the voice database are in one-to-one correspondence.

[0072] The third determining unit 34 is used to determine the identity information of the unknown person based at least on the first query identity, the second query identity, and the third query identity, wherein the identity information of the unknown person is the one with the highest repetition among the query identities.

[0073] In the aforementioned device, voice and image are generated respectively by describing the voice characteristics and facial features of the speaker. Multiple query identities generated from the voice and image are then used to comprehensively determine the identity information of an unknown person, thereby improving the accuracy of identity confirmation. This solves the problem in the prior art of lacking a technical solution that directly generates voice and image based on the text describing the characteristics of an unknown person from the speaker, and simultaneously determines the identity of an unknown person based on the voice and image.

[0074] In one embodiment of this application, the first determining unit includes a first processing module and a second processing module. The first processing module is used for a first modification step: upon receiving the human voice text modification information sent by the user terminal, the human voice feature description text is modified using the human voice text modification information, and the first human voice audio corresponding to the modified human voice feature description text is determined. The second processing module is used to repeatedly execute the first modification step at least once until a correct human voice audio instruction is received from the user terminal. The correct human voice audio instruction is used to indicate that the first human voice audio matches the voice of the unknown person.

[0075] In one embodiment of this application, the third determining unit includes a third processing module, a fourth processing module, a first determining module, and a second determining module. The third processing module is used to convert all the voices in the aforementioned voice database into multiple preset voice description texts. The fourth processing module is used to, upon receiving the correct voice audio instruction sent by the aforementioned user terminal, perform similarity comparison processing between the corrected voice feature description text at the current moment and each of the aforementioned preset voice description texts to obtain multiple first similarities. The first determining module is used to determine the fourth query identity as the identity corresponding to the preset voice description text corresponding to the maximum value among all the aforementioned first similarities. The second determining module is used to determine the identity information of the aforementioned unknown person based on the aforementioned first query identity, the aforementioned second query identity, the aforementioned third query identity, and the aforementioned fourth query identity.

[0076] In one embodiment of this application, the first determining unit includes a fifth processing module and a sixth processing module. The fifth processing module is used for the second modification step: upon receiving the face text modification information sent by the user terminal, the face text modification information is used to correct the face feature description text, and the target face image corresponding to the corrected face feature description text is determined. The sixth processing module is used to repeatedly execute the second modification step at least once until a face correctness instruction is received from the user terminal. The face correctness instruction is used to indicate that the target face image matches the face image of the unknown person.

[0077] In one embodiment of this application, the third determining unit includes a seventh processing module, an eighth processing module, a third determining module, and a fourth determining module. The seventh processing module is used to convert all face images in the face database into multiple preset face description texts. The eighth processing module is used to, upon receiving the correct face command sent by the user terminal, perform similarity comparison processing between the corrected face feature description text at the current moment and each of the preset face description texts to obtain multiple second similarities. The third determining module is used to determine the identity of the fifth query identity as the identity corresponding to the preset face description text corresponding to the maximum value among all the second similarities. The fourth determining module is used to determine the identity information of the unknown person based on the first query identity, the second query identity, the third query identity, and the fifth query identity.

[0078] In one embodiment of this application, the third determining unit includes a fifth determining module, which is used to determine the identity information of the unknown person as the first query identity when the first query identity, the second query identity, and the third query identity are all different.

[0079] In one embodiment of this application, the third determining unit includes a sixth determining module, which is used to determine the identity information of the unknown person, including: determining the identity information of the unknown person as the one with the highest repetition among the first query identity, the second query identity, and the third query identity based on the first query identity, the second query identity, and the third query identity.

[0080] The aforementioned identity information processing device includes a processor and a memory. The aforementioned acquisition unit, first determination unit, second determination unit, and third determination unit are all stored as program units in the memory, and the processor executes the aforementioned program units stored in the memory to achieve the corresponding functions. All of the aforementioned modules are located in the same processor; alternatively, the aforementioned modules may be located in different processors in any combination.

[0081] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the current lack of a technical solution for directly generating speech and facial images based on text describing the characteristics of an unknown person, and simultaneously determining the identity of the unknown person based on both speech and facial images.

[0082] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0083] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the method for processing the identity information.

[0084] This invention provides a processor for running a program, wherein the program executes the method for processing the aforementioned identity information.

[0085] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: acquiring a descriptive text of a speaker sent by a user terminal, and filtering the descriptive text to obtain a voice feature description text and a facial feature description text, wherein the voice feature description text is text describing the characteristics of an unknown person; determining a first voice audio corresponding to the voice feature description text, determining a target face image corresponding to the facial feature description text, and determining a second voice audio corresponding to the target face image; and determining a first... The system queries the identity of the person and the second identity corresponding to the second audio recording. Based on a face database, it determines the third identity corresponding to the target face image. The voice database stores multiple audio recordings and identities, and the face database stores multiple face images and identities. There is a one-to-one correspondence between the audio recordings and identities, the face images and identities, and the identities stored in the face database and the voice database. At least based on the first, second, and third identities, the system determines the identity information of the unknown person, which is the identity with the highest repetition rate among the queried identities. The devices mentioned in this document can be servers, PCs, tablets, mobile phones, etc.

[0086] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: obtaining a description text of a speaker sent by a user terminal, and filtering the description text to obtain a voice feature description text and a face feature description text, wherein the description text of the speaker is text describing the features of an unknown person described by the speaker; determining a first voice audio corresponding to the voice feature description text, determining a target face image corresponding to the face feature description text, and determining a second voice audio corresponding to the target face image; and determining a first query identity corresponding to the first voice audio and a second query identity corresponding to the first voice audio based on a voice database. The second query identity corresponding to the second human voice audio is determined, and a third query identity corresponding to the target face image is determined based on the face database. The human voice database stores multiple human voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The human voice audios and the aforementioned identities are in one-to-one correspondence, as are the face images and the aforementioned identities. The identities stored in the face database and the identities stored in the human voice database are in one-to-one correspondence. At least based on the first query identity, the second query identity, and the third query identity, the identity information of the unknown person is determined, and the identity information of the unknown person is the one with the highest repetition rate among the query identities.

[0087] This application also provides an electronic device, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described methods. By generating speech and facial images respectively based on text describing the characteristics of the speaker's voice and text describing the characteristics of the speaker's face, and by comprehensively determining the identity information of an unknown person based on multiple query identities generated from the speech and facial images, the accuracy of identity verification is improved. This solves the problem in the prior art of lacking a technical solution for directly generating speech and facial images based on text describing the characteristics of an unknown person's voice, and simultaneously determining the identity of an unknown person based on the speech and facial images.

[0088] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0089] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0094] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0095] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0096] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0097] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0098] 1) The identity information processing method of this application generates voice and image respectively by describing the voice characteristics and facial characteristics of the speaker, and comprehensively determines the identity information of the unknown person based on multiple query identities generated by the voice and image, thereby improving the accuracy of identity confirmation. This solves the problem in the prior art of lacking a technical solution to directly generate voice and image based on the text describing the characteristics of the unknown person from the speaker, and simultaneously determine the identity of the unknown person based on the voice and image.

[0099] 2) The identity information processing device of this application generates voice and image respectively based on the text describing the voice characteristics and the text describing the facial characteristics of the speaker, and comprehensively determines the identity information of the unknown person based on multiple query identities generated from the voice and image, thereby improving the accuracy of identity confirmation. This solves the problem in the prior art of lacking a technical solution to directly generate voice and image based on the text describing the characteristics of the unknown person from the speaker, and simultaneously determine the identity of the unknown person based on the voice and image.

[0100] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for processing identity information, characterized in that, include: The system obtains the descriptive text of the speaker sent by the user terminal, and filters the descriptive text of the speaker to obtain the descriptive text of human voice features and the descriptive text of human face features. The descriptive text of the speaker is the text describing the features of an unknown person described by the speaker. A first human voice audio corresponding to the human voice feature description text is determined, a target face image corresponding to the face feature description text is determined, and a second human voice audio corresponding to the target face image is determined; Based on the voice database, a first query identity corresponding to the first voice audio and a second query identity corresponding to the second voice audio are determined. Based on the face database, a third query identity corresponding to the target face image is determined. The voice database stores multiple voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The voice audios and identities are in one-to-one correspondence, the face images and identities are in one-to-one correspondence, and the identities stored in the face database and the identities stored in the voice database are in one-to-one correspondence. The identity information of the unknown person is determined based on at least the first queried identity, the second queried identity, and the third queried identity, wherein the identity information of the unknown person is the one with the highest repetition among the queried identities.

2. The method according to claim 1, characterized in that, Determining the first human voice audio corresponding to the human voice feature description text includes: First modification step: Upon receiving the human voice text modification information sent by the user terminal, the human voice feature description text is corrected using the human voice text modification information, and the first human voice audio corresponding to the corrected human voice feature description text is determined; The first modification step is repeated at least once until a correct human voice audio instruction is received from the user terminal. The correct human voice audio instruction is used to indicate that the first human voice audio matches the voice of the unknown person.

3. The method according to claim 2, characterized in that, The identity information of the unknown person is determined based on at least the first query identity, the second query identity, and the third query identity, including: Each of the human voices in the human voice database is converted into multiple preset human voice description texts; Upon receiving the correct voice audio instruction sent by the user terminal, the corrected voice feature description text at the current moment is compared with each of the preset voice description texts to obtain multiple first similarity scores. The fourth query identity is determined to be the identity corresponding to the preset human voice description text corresponding to the maximum value among all the first similarities; The identity information of the unknown person is determined based on the first queried identity, the second queried identity, the third queried identity, and the fourth queried identity.

4. The method according to claim 1, characterized in that, Determining the target face image corresponding to the facial feature description text includes: The second modification step is as follows: Upon receiving the face text modification information sent by the user terminal, the face text modification information is used to correct the face feature description text, and the target face image corresponding to the corrected face feature description text is determined. The second modification step is repeated at least once until a face correctness instruction is received from the user terminal. The face correctness instruction is used to indicate that the target face image matches the face image of the unknown person.

5. The method according to claim 4, characterized in that, The identity information of the unknown person is determined based on at least the first query identity, the second query identity, and the third query identity, including: All face images in the face database are converted into multiple preset face description texts; Upon receiving the correct face command sent by the user terminal, the corrected face feature description text at the current moment is compared with each of the preset face description texts to obtain multiple second similarities. The fifth query identity is determined to be the identity corresponding to the preset face description text corresponding to the maximum value among all the second similarities; The identity information of the unknown person is determined based on the first queried identity, the second queried identity, the third queried identity, and the fifth queried identity.

6. The method according to any one of claims 1 to 5, characterized in that, The identity information of the unknown person is determined based on at least the first query identity, the second query identity, and the third query identity, including: If the first queried identity, the second queried identity, and the third queried identity are all different, the identity information of the unknown person is determined to be the first queried identity.

7. The method according to any one of claims 1 to 5, characterized in that, The identity information of the unknown person is determined based on at least the first query identity, the second query identity, and the third query identity, including: Based on the first query identity, the second query identity, and the third query identity, the identity information of the unknown person is determined to be the one with the highest degree of repetition among the first query identity, the second query identity, and the third query identity.

8. An identity information processing device, characterized in that, include: The acquisition unit is used to acquire the descriptive text of the speaker sent by the user terminal, and to filter the descriptive text of the speaker to obtain the descriptive text of human voice features and the descriptive text of human face features, wherein the descriptive text of the speaker is the text describing the features of an unknown person described by the speaker. The first determining unit is used to determine a first human voice audio corresponding to the human voice feature description text, and to determine a target face image corresponding to the face feature description text, and to determine a second human voice audio corresponding to the target face image; The second determining unit is configured to determine a first query identity corresponding to the first human voice audio and a second query identity corresponding to the second human voice audio based on a human voice database, and to determine a third query identity corresponding to a target face image based on a face database. The human voice database stores multiple human voice audios and multiple identities, and the face database stores multiple face images and multiple identities. The human voice audios and the identities are in one-to-one correspondence, the face images and the identities are in one-to-one correspondence, and the identities stored in the face database and the identities stored in the human voice database are in one-to-one correspondence. The third determining unit is used to determine the identity information of the unknown person based at least on the first query identity, the second query identity, and the third query identity, wherein the identity information of the unknown person is the one with the highest repetition rate among the query identities.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 7.

Images