Identity recognition method, electronic equipment and computer readable medium

Abstract

The invention provides an identity recognition method, and the method comprises the steps: obtaining communication information outputted by a target user in a communication process with the target user, and obtaining a recognition identity of the target user; obtaining a historical term set corresponding to the identification identity; matching the communication information with a historical term set to obtain a matching result; and determining the identity of the target user according to the matching result. The invention further provides electronic equipment and a computer readable medium.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an identity recognition method, an electronic device, and a computer-readable medium. Background Art

[0002] At present, when a user uses a terminal device, such as a mobile phone, to communicate with other users, such as by at least one of voice calls, video calls, or text conversations, in certain scenarios, it is usually necessary to accurately identify the identity of the user at the other end of the communication to protect the privacy and security of the user. However, in the related art, when performing identity recognition processing, there is often a problem that the recognition result is not accurate enough. Summary of the invention

[0003] The present disclosure provides an identity recognition method, an electronic device, and a computer-readable medium.

[0004] In a first aspect, an embodiment of the present disclosure provides an identity recognition method, including:

[0005] During the communication process with the target user, obtaining the communication information output by the target user and obtaining the identification identity of the target user;

[0006] Obtaining a set of historical terms corresponding to the identified identity;

[0007] Matching the communication information with the historical term set to obtain a matching result;

[0008] The identity of the target user is determined according to the matching result.

[0009] In a second aspect, an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; a memory on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the identity recognition method described in the first aspect of the embodiment of the present disclosure.

[0010] In a third aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon, and when the program is executed by a processor, the identity recognition method described in the first aspect of the embodiment of the present disclosure is implemented.

[0011] In the identity recognition method provided by the embodiment of the present disclosure, the communication information output by the target user and the identification identity of the target user are obtained, and a historical phraseology set corresponding to the identification identity is obtained; because the terms used by the same user usually do not deviate greatly, the communication information output by the target user during the current communication with the target user is matched with the historical phraseology set corresponding to the identification identity, and the identity of the target user can be conveniently and accurately determined based on the matching result. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of an identity recognition method provided by an embodiment of the present disclosure;

[0013] Figure 2 A flowchart of identity recognition processing provided by an embodiment of the present disclosure;

[0014] Figure 3 A flowchart for obtaining matching results provided in an embodiment of the present disclosure;

[0015] Figure 4 A flow chart for obtaining a first term difference value provided by an embodiment of the present disclosure;

[0016] Figure 5 A flow chart for obtaining a target difference value provided by an embodiment of the present disclosure;

[0017] Figure 6 A flowchart for obtaining an identification identity provided by an embodiment of the present disclosure;

[0018] Figure 7 A block diagram of an electronic device provided in an embodiment of the present disclosure;

[0019] Figure 8 A block diagram of a computer-readable medium provided for an embodiment of the present disclosure;

[0020] Fig. 9 A schematic diagram of identity recognition processing provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the identity recognition method provided by the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0022] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0023] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0024] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0025] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0026] Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined in this disclosure.

[0027] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution complies with relevant national laws and regulations (for example, the "Information Security Technology Personal Information Security Specification", etc.). For example: corresponding prescribed measures are taken for personal information access control; the display of personal information is subject to prescribed restrictions; the purpose of using personal information does not exceed the scope of direct or reasonable association; when using personal information, clear identity orientation is eliminated to avoid precise positioning of specific individuals.

[0028] To protect user privacy and security, during user communications, such as a voice call, voice data of the voice call can be obtained with the authorization of both parties in the voice call, and the call text can be obtained by performing voice recognition processing on the voice data. It is then determined whether the call text contains preset keywords, for example, whether it contains preset keywords such as "transfer" and "verification code", so as to identify the identity of the user on the other end of the call, for example, to identify whether the user on the other end of the call is a user who has engaged in deceptive behavior.

[0029] That is, when performing identity recognition processing, the user's identity can be identified by determining whether the communication information contains preset keywords. However, if the communication information does not contain the preset keywords, this type of method often cannot identify the user's identity. In addition, in some scenarios, even if the communication information contains preset keywords, the user at the other end of the communication may also be a user with a confirmed identity. For example, friends do ask for verification codes through communication. In this case, if identity recognition processing is performed by determining whether the communication information contains preset keywords, a wrong judgment may occur, thereby giving the user a bad experience.

[0030] In view of this, in the embodiments of the present disclosure, in order to improve the accuracy of identity recognition results, taking into account that the terms used by the same user usually do not deviate significantly, therefore, during the communication process with the target user, by obtaining the communication information output by the target user and obtaining the identification identity of the target user, obtaining the historical term set corresponding to the identification identity, matching the communication information with the historical term set, and determining whether the term of the target user deviates significantly based on the matching results, the identity of the target user can be conveniently and accurately determined.

[0031] Figure 1 A flowchart of an identity recognition method provided in an embodiment of the present disclosure.

[0032] First, refer to Figure 1 , the embodiment of the present disclosure provides an identity recognition method, which can be executed by an electronic device such as a terminal device or a server. The terminal device can be a vehicle-mounted device, a user equipment (UE, User Equipment), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA, Personal Digital Assistant), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The method can be implemented by a processor calling a computer-readable program instruction stored in a memory. Alternatively, the method can be executed by a server. It can be understood that the electronic device used to execute the identity recognition method described in the embodiment of the present disclosure can be a terminal device used by a user, or it can also be other terminal devices or servers that are communicatively connected to the terminal device used by the user.

[0033] like Figure 1 As shown, the method may include the following steps S1-S4, which are described in detail below.

[0034] Step S1: during the communication process with the target user, obtaining the communication information output by the target user and obtaining the identification identity of the target user.

[0035] The target user refers to the user whose identity is to be determined during the communication process. For example, during the communication process between the first user and the second user, from the perspective of the first user, the second user is the target user, and from the perspective of the second user, the first user is the target user, wherein the first user and the second user can be any user who interacts in the communication.

[0036] The communication process may be a voice call or a text conversation, for example, a voice call may be made using a target communication number, or a voice call or a text conversation may be made using an instant messaging application based on a target communication account. Of course, in some embodiments, the communication process may also be a video call, in which case the identity of the target user at the other end of the video call may be determined based on the method provided in the embodiment of the present disclosure to determine whether the user has engaged in a disguised facial expression.

[0037] That is, the communication information may be text data output by the target user during the communication process, and the text data includes at least one term used by the target user during the current communication process. The text data may be text data during the communication process, or may be text data obtained after performing speech recognition (ASR, Automatic Speech Recognition) processing on speech data during the communication process.

[0038] For example, the communication information acquisition process may be: obtaining voice data of a target user whose identity is to be determined having a voice call with a second user based on a communication device, such as a landline or mobile phone, and performing voice recognition processing on the voice data to obtain the communication information.

[0039] For another example, the process of acquiring the communication information may also be: acquiring at least one of the voice data, real-time text data or video data during the voice, video and text conversation between the target user and the second user based on the instant messaging application in the terminal device, and obtaining the communication information based on at least one of the voice data, real-time text data or video data, without special limitation here.

[0040] In some embodiments, the communication information may be communication information during a process in which the target user communicates with the second user using the target communication number or the target communication account.

[0041] The target communication number may be any communication number. In some embodiments, the target communication number may be, for example, a number outside a preset communication number set, and the preset communication number set is used to store the communication numbers of users whose identities have been determined. For example, during a voice call between the target user and a second user based on the target communication number, the preset communication number set may be a number set consisting of numbers in the address book used by the second user, that is, the user whose identity has been determined may be, for example, an "acquaintance", that is, a user with a high degree of intimacy with the second user.

[0042] The target communication account, for example, may be an application account used by the target user to communicate with the second user based on an instant messaging application.

[0043] In the embodiments of the present disclosure, unless otherwise specified, the communication information is taken as an example: information obtained by voice recognition processing of voice data of a target user during a voice call with a second user based on a target communication number, including at least one term used by the target user. The target communication number may be a number outside the preset communication number set, that is, a "strange" number.

[0044] Specifically, in the disclosed embodiments, the method can be applied to the following application scenarios: the target user makes a call with the second user based on an unfamiliar number, and the terminal device used by the second user obtains the voice data during the call after obtaining authorization from both parties to use the voice data, obtains the corresponding communication information by performing voice recognition processing on the voice data, and performs identity recognition processing on the target user based on the terminology currently used by the target user in the communication information, so as to avoid the second user from misjudging the identity of the target user and bringing risks to his own privacy security. Of course, this is only an example, and in actual implementation, the method can also be applied to any application scenario where the identity of at least one of the two communicating parties needs to be determined as needed, and no special limitation is made here.

[0045] In some embodiments, the communication information may include at least one term currently used by the target user, and may also include the number of times each term is used. For example, after performing speech recognition processing on the voice data to obtain text data corresponding to the voice data, the text data may be segmented, and the communication information may be constructed based on the obtained terms and the number of times each term is used.

[0046] For example, if the text data obtained after voice recognition processing of the voice data in the communication process is "OK, got it!", then the two terms "OK" and "got it" can be obtained through word segmentation. If the two terms only appear once in the communication process, the communication information [("OK", 1), ("got it", 1)] can be constructed. Of course, here it is in the form of a set of terms in the communication information, that is, [("term 1", number of times used 1), ("term 2", number of times used 2), ..., ("term n", number of times used n)], and n is a positive integer. In actual processing, the communication information can also be in other forms, which is not specifically limited here.

[0047] The identified identity may be the identity to be determined obtained after identification processing is performed on the target user.

[0048] In actual implementation, the identification identity can be the identity claimed by the target user during the communication process. For example, if the target user claims to be "Li xx" during the communication process, the target user can be temporarily identified as the identification identity "Li xx" by identifying the claimed information, and the identification identity can be confirmed in the subsequent processing process. Of course, in actual implementation, the identification identity can also be obtained by other means, which is not specifically limited here.

[0049] It should be noted that in the related art, users are usually uniquely identified based on their communication numbers or communication accounts. However, since the same communication number or communication account may be used by different users, in order to avoid misjudgment of user identity, in the embodiments of the present disclosure, for users whose identities have been determined, the user is not identified by the communication number used by the user, but is identified by generating a unique identifier for the user, so as to improve the accuracy of the identity recognition process.

[0050] In the embodiments of the present disclosure, unless otherwise specified, the second user is the call recipient, i.e., the called user, the first user is the call initiator, i.e., the calling user, and the communication information is the terminology obtained after voice recognition processing and word segmentation processing of the voice data during the voice call, as an example, to illustrate how to determine the identity of the first user, i.e., the target user, from the perspective of the second user. Of course, in some embodiments, when the identity recognition method described in the embodiments of the present disclosure is applied to electronic devices other than the terminal devices used by the first user and the second user, the electronic device can also simultaneously identify the identities of the first user and the second user based on the method, without special limitation here.

[0051] It should be noted that, in the embodiment of the present disclosure, before obtaining the communication information, it is necessary to obtain the authorization of both parties to the communication. When both parties to the communication authorize and agree to obtain their communication data for identity identification processing, the communication information is obtained, and the identity identification method of the embodiment of the present disclosure is executed based on the communication information. If either of the two parties to the communication does not agree to obtain and use the communication information, the electronic device does not obtain the communication information, and stops executing the identity identification method of the embodiment of the present disclosure. In actual implementation, the authorization process can be when the user first uses the communication application, asking the user for authorization to obtain their communication information during each subsequent communication process to perform identity identification processing on the identity of the target user at the other end of the communication, or it can also be before the user initiates each communication, asking the user for authorization to obtain the communication information during this communication process and to perform identity identification processing on the identity of the target user at the other end of the communication. No special limitation is made here.

[0052] Step S2: Obtain a historical term set corresponding to the identified identity.

[0053] In some embodiments, the historical term set may be obtained from a preset term set.

[0054] The preset word set may be a set of historical words for storing all users whose identities have been determined, and the historical word set may be composed of the identity identifier of each user and the corresponding historical word set. That is, the preset word set in the embodiment of the present disclosure may include at least one historical word set, and each historical word set corresponds to the identity identifier of a user whose identity has been determined. For example, the preset word set may be in the form of [(identity identifier 1, historical word set 1), (identity identifier 2, historical word set 2), ...].

[0055] The acquiring of the historical term set corresponding to the identified identity may be to acquire an identification identifier of the identified identity, and obtain the historical term set from the preset term set based on the identification identifier.

[0056] The historical term set can be used to record the historical terms used by the identified user in the historical communication process. The historical term set may include at least one historical term group, and each historical term group may include multiple historical terms with matching meanings. It can be understood that the meanings of different historical term groups in the same historical term set do not match.

[0057] In some embodiments, the historical term group may also include the historical usage counts corresponding to the historical term, that is, each historical term group may include at least one term data pair with matching meanings, and each term data pair may include a historical term and the historical usage counts corresponding to the historical term. In this embodiment, the historical term set may be, for example, in the form of [(historical term group 1), (historical term group 2), ...}, and each historical term group may be in the form of [(term data pair 1), (term data pair 2), ...}, and each term data pair may include at least one historical term and the historical usage counts corresponding to the historical term. For example, a historical term group may be in the form of [("know", 100), ("know", 50)].

[0058] In actual implementation, the data in the preset term set can be stored in a data table of a database, for example, can be stored in a "term table", and a record in the table can store historical terms used by a user with an identified identity, that is, a record in the "term table" can include the fields "identity identification" and "historical terms", and a plurality of term groups with mismatched meanings are stored in the "historical terms" field, and the meanings of at least one term data pair in the same term group match; or, in the "term table", the historical terms of a user with an identified identity can be stored in the form of multiple records, and in this storage method, each record is used to store a group of terms of the user, which is not specifically limited here.

[0059] Step S3, matching the communication information with the historical term set to obtain a matching result;

[0060] Step S4: Determine the identity of the target user based on the matching result.

[0061] After obtaining the communication information used by the target user during the communication process and the historical term set corresponding to the identification identity of the target user based on the above steps, the communication information can be matched with the historical term set to accurately determine the identity of the target user based on the matching results. For example, the identity of the target user can be determined to be the identified identity.

[0062] For example, in the current communication process, if the target user expresses the meaning of "know", by querying the historical term set corresponding to his identification identity, it is found that in the historical communication process, the target user used "know" 100 times and "know" 50 times, and did not use other terms to express the meaning of "know". However, in the communication information obtained in the current communication process, it is found that the target user only used the term "understand" to express the meaning of "know". Since the terms used by users usually do not deviate greatly, if the terms used by the target user to express the same meaning in a communication process deviate greatly from the historical terms used by the user of his identification identity to express the same meaning in the historical communication process, it can usually be determined that the identity of the target user is not the identification identity.

[0063] For example, user 1 uses an unfamiliar number to call user 2. After obtaining authorization from both parties to use their voice data, it is discovered based on the voice data during the communication that user 1 is identified as "Friend 1", a contact in user 2's address book. Afterwards, based on the identity identifier of "Friend 1", it is found that the corresponding phrase group in the historical phrase collection when "Friend 1" expresses the meaning of "know" is [("know", 100), ("know", 50)], that is, in previous communications, "Friend 1" used the word "know" 100 times to express the meaning of "know", and used the word "know" 50 times to express the meaning of "know", while during the call between user 1 and user 2, user 1 only used the word "understand" 10 times to express the meaning of "know". In this case, it can usually be determined that user 1 is not "Friend 1" of user 2, that is, user 1 may be a user who has engaged in deceptive behavior.

[0064] It can be seen that in the identity identification method provided in the embodiment of the present disclosure, the communication information output by the target user is obtained, the identification identity of the target user is obtained, and the historical terminology set corresponding to the identification identity is obtained; because the terms used by the same user usually do not deviate greatly, therefore, by matching the communication information output by the target user during the current communication with the target user with the historical terminology set corresponding to the identification identity, the identity of the target user can be conveniently and accurately determined based on the matching result.

[0065] In some embodiments, see Figure 2 In the above step S4, determining the identity of the target user according to the matching result may include:

[0066] Step S41, obtaining a target term difference value according to the matching result, wherein the target term difference value term represents the degree of difference between the term in the communication information and the term in the historical term set;

[0067] Step S42: Determine the identity of the target user according to the target term difference value.

[0068] That is, after matching the target user's communication information with the historical term set corresponding to his / her identification identity, a matching result can be obtained to determine a target term difference value indicating the degree of difference between the currently used term and the historical term, and the identity of the target user can be determined by comparing the target term difference value with a preset difference threshold.

[0069] The matching result can be determined, for example, by the number of times a new term is used by the target user. The new term can be a term used by the target user to express the target meaning in the current communication process, but the number of times the term is used to express the target meaning in historical terms is less than or equal to a preset threshold. The target meaning can be any meaning.

[0070] That is, in some embodiments, the matching result may include at least one first term, and the first term may include: a term that satisfies a preset condition between the term in the communication information and the term in the historical term set; in the above step S41, obtaining the target term difference value based on the matching result may include: obtaining the first term difference value corresponding to each first term to obtain at least one first term difference value; and obtaining the target term difference value based on the at least one first term difference value.

[0071] The first term difference value may be used to represent a numerical value of the degree of difference between the corresponding first term and a matching term in the historical term set.

[0072] That is, the first term difference value corresponding to each term may be obtained, and then the target term difference value may be obtained according to all the obtained first term difference values.

[0073] In this embodiment, the historical term set may include at least one historical term group. Figure 3 In the above step S3, matching the communication information with the historical term set to obtain a matching result may include:

[0074] Step S31, obtaining, from the communication information, a term that has a corresponding matching historical term group in at least one historical term group and whose corresponding historical usage times are less than or equal to a preset threshold as a first term, thereby obtaining at least one first term;

[0075] Step S32: Obtain a matching result based on at least one first term; wherein the matching historical term group corresponding to the first term includes: a historical term group whose corresponding word meaning in at least one historical term group matches the first term.

[0076] The first term in the embodiment of the present disclosure refers to the "new term" in the above description, that is, it can be a word used by the target user to express the target meaning in the current communication process, but the number of times used to express the target meaning in historical terms is less than or equal to a preset threshold, and the target meaning can be any meaning.

[0077] That is, in some embodiments, the preset condition may be that: the term in the communication information has a matching historical term group in at least one historical term group, and the corresponding historical usage count is less than or equal to a preset threshold, wherein the preset threshold may be 0, or may be set as needed.

[0078] The matching historical term group corresponding to the term in the communication information may be: a historical term group in which the corresponding word meaning in at least one historical term group matches the term in the communication information.

[0079] For example, assuming that the preset threshold is 0, the term "understand" in the communication information output by the target user has the meaning of "know". If the historical term group used to express this meaning in the historical term set obtained based on the identification identity of the target user is [("know", 100), ("know", 50)], it can be obtained that the term "understand" has a matching historical term group, and its historical usage count is 0. Therefore, the term "understand" can be used as a first term, and a matching result can be generated based on the first term, so as to determine the identity of the target user based on the first term in the subsequent processing process.

[0080] In actual implementation, in the above step S32, obtaining a matching result according to at least one first term may include: obtaining the matching result according to the at least one first term and a corresponding number of times of use.

[0081] That is, the matching result may be in the form of [(first term 1, number of times used 1), (first term 2, number of times used 2), ...]. For example, the matching result may be [("understand", 10), "OK", "5"].

[0082] After matching the communication information with the historical term set to obtain a matching result, since the terms used by the same user to express the same meaning currently are obviously different from the historical terms used by the user, it often indicates that the user's identity is different from his or her identified identity. Therefore, based on the matching result, the target term difference value can be obtained, and then based on the target difference value, the identity of the target user can be accurately determined.

[0083] It should be noted that the word meaning matching described in the embodiments of the present disclosure may be to use a word meaning matching degree determination model to obtain the word meaning matching degree between one or more terms to determine whether their word meanings match. The word meaning matching degree determination model may be to construct training data with multiple synonyms corresponding to different word meanings, and the detailed processing process of the network model obtained by training based on the training data will not be repeated here.

[0084] Of course, in actual implementation, in order to reduce the amount of calculation, a synonym table (also called a synonym dictionary or a synonym dictionary) as shown in Table 1 below can also be constructed in advance. The synonym table may include multiple records, each record corresponding to a word meaning, and a record may include at least two words with matching meanings.

[0085]

[0086] Table 1

[0087] In this implementation, when judging whether a term in the communication information matches the meaning of a historical term group in the historical term set, it can be as follows: judge whether the term and any historical term in the historical term group are in the same record in the synonym table; if so, it can be determined that the term matches the meaning corresponding to the historical term group, that is, the historical term group can be determined as the matching historical term group of the term; in this way, the matching historical term group of each term in the communication information can be quickly obtained through a simple table lookup operation, thereby reducing the amount of calculation and improving the processing speed of identity recognition.

[0088] In some embodiments, each term group may include at least one term data pair with matching meanings, and each term data pair includes a historical term and the number of historical usages corresponding to the historical term; see Figure 4 The step of obtaining the first term difference value corresponding to the first term in the above step includes:

[0089] Step S411, obtaining a target usage frequency of the first term in the communication information;

[0090] Step S412: Obtain the target matching historical phrase group corresponding to the first term;

[0091] Step S413: Obtain the sum value of the historical usage times of the historical phrases in each phrase data pair of the target matching historical phrase group;

[0092] Step S414: Obtain the first current difference value of the first term according to the target usage times sum value.

[0093] In the embodiment of the present disclosure, considering that if a user said "chat" 300 times in historical communications and did not use other synonyms, then it can be determined that when the user communicates with other users again, the user will have a high probability of continuing to use the word "chat" to express the meaning of "chat", and a low probability of directly using the word "chat" to express the meaning of "chat". Therefore, the following formula 1 can be used to represent the probability that a user uses a first term with a historical usage times lower than a preset threshold to express the same semantic meaning during the current communication process:

[0094]

[0095]

[0096]

[0097] Where p represents the probability that the user uses the first term with a historical usage times less than or equal to the preset threshold during the current call process, that is, the probability of using the "new term" to express the same semantic meaning, and n is the sum value of the historical usage times of all the historical phrases in the matching historical phrase group corresponding to the first term. For example, if in the current communication process the target user uses the term "chat" to express the meaning of "chat", however, if the matching historical phrase group corresponding to the term "chat" is [("chat", 300), ("chat", 400)], that is, in the historical communication process of identifying the identity of the target user, the user with the identified identity used "chat" 300 times and "chat" 400 times to express the meaning of "chat" in the historical communication process, then n = 300 + 400 = 700.Considering that if a user uses a word with a historical usage count of 0 or a relatively small number when expressing the same semantic meaning during the current communication process, it often indicates a difference in the words used before and after. For example, if the word "chat" was used 300 times in historical communications to represent the semantic meaning of "chat", but in the current communication, the word "chat" is used to represent this semantic meaning, it can be considered that there is a relatively large difference in the user's habitual expressions before and after; and if it was used more times, for example, 1000 times "chat" to represent the semantic meaning of "chat" in historical communications, but in the current communication, the word "chat" is used to represent this semantic meaning, it can be considered that the difference in the words used by the user before and after is even greater (that is, compared with the case of using "chat" 300 times, the represented difference is greater). Therefore, in the embodiments of the present disclosure, the uncertainty function in information theory can be introduced:

[0098]

[0099] where f represents the difference value brought by using a first term with a historical usage count less than or equal to a preset threshold in the current communication, that is, using a first term.

[0100] Substituting the above formula (1) into formula (2) gives formula (3):

[0101] f = log2(n + 1) (3);

[0102] If a first term is used more than once in the current communication, the difference value of the difference degree of the user's words before and after represented by this term, that is, the first term difference value, can be obtained through the following formula (4):

[0103] f = (log2(n + 1)) * m (4);

[0104] where m represents the number of times a first term is used in the current communication process.

[0105] Let i represent the first term, and k represent the number of all first terms in the matching result. Among them, both i and k are positive integers, and i ≤ k. Let m i represent the target usage count of the first term for which the first term difference value is to be determined currently, and let n i represent the sum value of the historical usage counts of the historical terms in each term data pair of the matching historical term group corresponding to this first term. Then the target term difference value F can be obtained through the following formula (5):

[0106]

[0107] That is, in some embodiments, obtaining the target terminology difference value according to at least one first terminology difference value in the above steps may be: obtaining a first sum of the at least one first terminology difference value; and obtaining the target terminology difference value according to the first sum.

[0108] In this implementation, the first sum value may be a cumulative sum of the at least one first term difference value.

[0109] Of course, in some embodiments, the first sum value may be obtained by weighted summing up the at least one first term difference value. In this embodiment, the weight corresponding to each first term difference value may be determined based on the first term corresponding to the first term difference value, or may be a preset value, which is not specifically limited here.

[0110] In addition, after obtaining the first sum value, the first sum value may be used as the target term difference value, or the target term difference value may be obtained by performing other processing on the first sum value, which is not particularly limited here.

[0111] It should be noted that, in some embodiments, the matching result obtained in the above step S3 may also include at least one second term, and the second term may be: a term corresponding to the communication information of the matching historical term group that does not have a matching meaning in the historical term set; see Figure 5 In this implementation, in the above step S41, obtaining the target term difference value according to the matching result may include:

[0112] Step S51, obtaining a second term difference value corresponding to each second term to obtain at least one second term difference value;

[0113] Step S52: Obtain a target term difference value according to at least one first term difference value and at least one second term difference value.

[0114] The second term may be a term in the communication information output by the target user, for which there is no matching historical term group with a matching meaning in the historical term set. That is, if the target user has never used a term with a certain meaning before, but uses a term used to express the meaning in the current communication process, it may often indicate that there is a large deviation between the user's previous and subsequent terms. In this case, the second term difference value of this type of term may be set to a preset value with a larger value to improve the accuracy of obtaining the target term difference value.

[0115] In actual implementation, in the above step S52, the target term difference value is obtained according to at least one first term difference value and at least one second term difference value, and the cumulative sum of the at least one first term difference value and the at least one second term difference value is obtained as the target term difference value.

[0116] In some embodiments, in the above step S42, determining the identity of the target user based on the target terminology difference value includes: when the target terminology difference value is less than or equal to a preset difference threshold, determining the identity of the target user as an identification identity; when the target terminology difference value is greater than the preset difference threshold, determining the identity of the target user as an identity other than the identification identity.

[0117] The preset difference threshold can be set as needed, for example, it can be set to 10 or other values, and is not specifically limited here.

[0118] In an embodiment of the present disclosure, when the target term difference value is less than or equal to a preset difference threshold, the identity of the target user can be determined to be the identification identity obtained by initial identification, for example, it can be the identity claimed by the target user during the communication process, or it can be the identity obtained by identification based on the target communication number or target communication account used by the target user; otherwise, when the target term difference value is greater than the preset difference threshold, it can be determined that the actual identity of the user is inconsistent with the identification identity obtained by initial identification, and the target user may be an identity other than the identification identity, that is, the target user is a user with an unknown identity.

[0119] In some embodiments, when it is determined that the identity of the target user is an identity other than the identified identity, the method may further include: generating first prompt information, wherein the first prompt information is used to prompt that the identity of the target user is an identity other than the identified identity.

[0120] That is, if during the communication process, after identity recognition processing is performed on the target user, it is determined that his identity is not the recognized identity, since the recognized identity is usually a user whose identity has been determined by the second user, for example, a friend in his address book, therefore, in this case, it is usually indicated that the target user may be imitating the user's "acquaintance" to communicate with the user. In this case, the user needs to be reminded that the target user is imitating other users.

[0121] The first prompt information may be, for example, "The other party's language is different from before, and it is suspected that the stranger is imitating the language of the acquaintance, please pay attention to protect privacy." Of course, this is only an example, and in actual implementation, the first prompt information can also be set as needed, and is not specifically limited here.

[0122] After the first prompt information is generated, the terminal device can notify the user to protect the privacy data by displaying the first prompt information based on the first prompt information. For example, the user can be prompted by sending a notification bar message, a text message, etc. Of course, while displaying the first prompt information, the terminal device can also notify the user to protect the privacy data by vibrating or sending a preset prompt sound. There is no special limitation here.

[0123] Also, see Figure 6 In some embodiments, obtaining the identification of the target user in step S1 may include:

[0124] Step S11, obtaining at least one of a target communication number, a target communication account, a target voiceprint feature, and a target claimed identity corresponding to the target user; wherein the target voiceprint feature includes a voiceprint feature extracted from voice data output by the target user during the communication process, and the target claimed identity includes the identity claimed by the target user obtained from the communication information;

[0125] Step S12: determining the identification identity of the target user according to at least one of the target communication number, the target communication account, the target voiceprint feature, and the target claimed identity.

[0126] The target communication number may be a communication number used by the target user during the communication process, for example, may be a number used by the target user during the communication process of making a voice call.

[0127] The target communication account may be a communication account used by the target user during the communication process, for example, may be an application account used by the target user during the communication process based on an instant messaging application.

[0128] The target claimed identity may be the identity claimed by the target user during the communication process, for example, the identity claimed by the target user in the communication information output by the target user during the communication process.

[0129] The target voiceprint feature may be a voiceprint feature extracted from the voice data output by the target user during the communication process. That is, in some embodiments, when determining the identification of the target user, the identification identifier may be obtained by voiceprint comparison. For example, after obtaining the target voiceprint feature, the identification identity may be obtained by querying from preset voiceprint mapping data. The preset voiceprint mapping data may be preset voiceprint data, or may be public voiceprint mapping data obtained with the user's authorization. No special limitation is made here.

[0130] That is, in the embodiment of the present disclosure, when identifying the identity of a user, the identification identity of the target user is determined based on at least one of the target communication number, target communication account, target voiceprint feature, and target claimed identity corresponding to the target user, so that the historical term set corresponding to the target user can be obtained based on the identification identity, so as to conveniently and accurately determine the identity of the target user by matching the communication information output by the target user in the current communication process with the historical term set.

[0131] It should be noted that, in some embodiments, in step S12, the identification identity of the target user is determined based on at least one of the target communication number, the target communication account, the target voiceprint feature and the target claimed identity. This can be as follows: at least two candidate identities corresponding to the target user are obtained based on at least two of the target communication number, the target communication account, the target voiceprint feature and the target claimed identity; when the at least two candidate identities match, the identification identity of the target user is determined to be the candidate identity.

[0132] In actual implementation, the two candidate identities match, which may be that the two candidate identities are the same.

[0133] For example, in the process of determining the identification identity of the target user, the candidate identity 1 corresponding to the target user can be obtained based on the target communication number, and the candidate identity 2 corresponding to the target user can be obtained based on the target voiceprint feature; when the candidate identity 1 and the second candidate identity 2 match, the identification identity of the target user is determined.

[0134] In this embodiment, the method may further include: generating an identification determination page based on the at least two candidate identities when the at least two candidate identities do not match; displaying the identification determination page; and obtaining the identification identity of the target user based on the received input result.

[0135] The identification and determination page may display the at least two candidate identities for the second user to determine.

[0136] The input result may be used to represent the input result of the second user on the identification and identity determination page, for example, it may be the selection result of the second user on the identification and identity determination page, or it may be the identity of the target user judged by the second user input on the identification and identity determination page.

[0137] For example, if the candidate identity 1 and candidate identity 2 obtained above do not match, a page for displaying the candidate identity 1 and the candidate identity 2 can be generated for the second user to determine which identity to use as the identification identity of the target user. If the second user selects candidate identity 1, then candidate identity 1 can be used as the identification identity of the target user; if the second user does not select the two candidate identities, but enters the candidate identity 3 of the target user determined by himself in the input box of the page, then candidate identity 3 can be used as the identification identity of the target user.

[0138] Of course, in actual implementation, the identification identity of the target user may also be determined by other means, which will not be elaborated here.

[0139] It is understandable that, in some embodiments, when the identity of the target user is determined to be the identification identity, the method may further include: updating the historical term set according to the communication information.

[0140] That is, if the identity of the target user is determined to be the identity obtained by initial identification, since the target user can be regarded as a user with a determined identity in this case, in order to ensure the accuracy of subsequent identification of the target user's identity, the corresponding historical term set can be updated based on the communication information output by the target user during the current communication process.

[0141] In some embodiments, before executing the step of obtaining a set of historical terms corresponding to the identified identity described in step S2 above, the method may also include: generating a second prompt message when the identified identity is not obtained, wherein the second prompt message is used to prompt that the target user is a user whose identity is not determined.

[0142] That is, in the embodiment of the present disclosure, if the target user is determined to be an identity other than the identified identity, since it is impossible to obtain the historical term set corresponding to the identified identity in the subsequent processing to match the communication information output by the target user in the current communication process, in this case, subsequent processing may not be performed, and a second prompt message may be given to prompt the second user that the first user is a user whose identity has not been determined.

[0143] The second prompt information may be, for example, a prompt information of "The identity of the other party is not confirmed, please protect privacy", to prompt the second user to be careful not to disclose private data when talking with the first user. Of course, this is only an example, and in actual implementation, the second prompt information may also be other information used to prompt that the target user is an unknown user, which is not specifically limited here.

[0144] In some embodiments, the preset term set in the embodiments of the present disclosure can be obtained by the following steps: in the process of communicating with a third user, determining the identity of the third user; when the identity of the third user is determined, obtaining the communication information output by the third user during the communication process; based on the communication information output by the third user, updating the historical term set corresponding to the third user in the preset term set.

[0145] That is, in the embodiments of the present disclosure, the preset term set may be a public term set obtained by the user with authorization. However, considering that there may be errors in the public term set, in order to improve the accuracy of identity recognition, in the embodiments of the present disclosure, the preset term set may be used by the electronic device to determine the identity of the third user during the communication between the second user and any third user. For example, the electronic device prompts the second user through a pop-up window whether to confirm the identity of the third user. If confirmed, the communication information output by the third user during the call can be obtained, and the historical term set corresponding to the third user in the preset term set is updated according to the communication information.

[0146] It should be noted that, in the embodiments of the present disclosure, the updating of the historical term set corresponding to the third user in the preset term set based on the communication information output by the third user may be as follows: if there is a historical term set corresponding to the third user in the preset term set, the updating of the historical term set corresponding to the third user is performed based on the communication information output by the third user; if there is no historical term set corresponding to the third user in the preset term set, then creating a historical term set corresponding to the third user based on the communication information output by the third user.

[0147] Taking the third user's identity identifier "uuid1" as an example, after the second user completes the communication with the third user, the terminal device used by the second user, such as a mobile phone, can provide a pop-up window for the second user to confirm the identity of the third user. If the second user confirms the identity of the third user, the communication information 1 output by the identity identifier "uuid1" during the call can be obtained, and based on the identity identifier "uuid1", it can be determined whether there is a historical term set of the third user in the preset term set. If so, the historical term set is updated; if not, the historical term set can be created, so as to accurately identify whether the user on the other end of the call is actually the third user when communicating with the third user subsequently, or when receiving communication from a fourth user imitating the identity of the third user.

[0148] Of course, in the embodiment, the historical term set corresponding to the third user in the preset term set can also be updated by the second user manually inputting the term set of the third user. That is, the user can manually maintain the preset term set. For example, if the historical term set of the third user does not exist in the preset term set, the second user can manually add the historical term set of the third user to the preset term set; or, if the historical term set of the third user already exists in the preset term set, the second user can update the historical term set, for example, modify some terms used by the third user and the number of times they are used, which is not specifically limited here.

[0149] In addition, in some embodiments, when the communication process is a voice call, if there are multiple users on the other end of the voice call who are simultaneously having voice calls with the second user, in this embodiment, the voiceprint features of the multiple users can be extracted separately based on voice recognition and separation technology, and the multiple users can be identified, and the communication information output by different users during the current voice call can be established separately according to the identification results; after the call is completed, the second user can confirm the identities of the multiple users in the form of a pop-up window, and according to the selection result of the second user, the historical term set of the users whose identities have been determined among the multiple users is updated.

[0150] For example, if during a voice call, two users with identities "uuid1" and "uuid2" are talking to the second user at the same time, then by identifying the voiceprints of the two users, a term set 1 corresponding to the user "uuid1" and a term set 2 corresponding to the user "uuid2" can be established respectively; after the call is completed, the terminal device of the second user can provide a pop-up window for the second user to confirm the identities of the two users with identities "uuid1" and "uuid2", that is, to confirm whether the two users are For the user "uuid1", if the second user determines that the identities of the two users are both certain, the historical terminology set 1 corresponding to "uuid1" in the preset terminology set can be updated according to terminology set 1, and the historical terminology set 2 corresponding to "uuid2" in the preset terminology set can be updated according to terminology set 2; if the second user only confirms the identity of the user "uuid1", only the historical terminology set 1 corresponding to "uuid1" in the preset terminology set is updated according to terminology set 1, and the historical terminology set 2 is not updated.

[0151] It can be seen that in the embodiments of the present disclosure, by performing identity recognition processing based on the preset term set constructed by execution, the accuracy of identity recognition can be improved, and the problem of misjudging the user's identity due to errors in the public term set when using the public term set can be avoided.

[0152] Second, refer to Figure 7 , an embodiment of the present disclosure provides an electronic device, comprising:

[0153] One or more processors 101;

[0154] A memory 102, on which one or more programs are stored. When the one or more programs are executed by one or more processors, the one or more processors implement the identity determination method described in the first aspect of the embodiment of the present disclosure;

[0155] One or more I / O interfaces 103 are connected between the processor and the memory and are configured to implement information exchange between the processor and the memory.

[0156] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU) and the like; the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus) and the like.

[0157] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0158] Thirdly, refer to Figure 8 The embodiment of the present disclosure provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the identity recognition method described in the first aspect of the embodiment of the present disclosure is implemented.

[0159] In order to enable those skilled in the art to more clearly understand the technical solutions provided by the embodiments of the present disclosure, the technical solutions provided by the embodiments of the present disclosure are described in detail below through specific embodiments:

[0160] Example

[0161] The identity recognition method provided by the embodiment of the present disclosure can be applied to anti-fraud scenarios, see Fig. 9 In this application scenario, the method can be applied to the terminal device of user 2, such as a mobile phone, and may specifically include:

[0162] Step S101 : In response to a voice call request initiated by user 1 using an unfamiliar number, user 2 makes a voice call with user 1 .

[0163] The unfamiliar number may be a number that does not exist in the address book of user 2, that is, a communication number that user 2 is not familiar with.

[0164] After step S101, the terminal device of user 2 may, when obtaining authorization from user 1 and user 2 to obtain current voice data and identify the identity of user 1, execute step S102 to obtain communication information A output by user 1 during the voice call or after the voice call is completed; and execute step S103 to obtain the voiceprint feature of user 1 in the voice data, and query and obtain the identification identity 1 of user 1 based on the voiceprint feature;

[0165] Step S104: determine whether user 1 is an "acquaintance" based on the identified identity 1; if not, then execute step S105 to prompt user 1 that user 1 is a stranger;

[0166] That is, if the identification identity 1 is empty, it means that the terminal device used by user 2 has not established the corresponding relationship between the voiceprint characteristics and identity identification of user 1 in its preset voiceprint mapping data. In this case, it can be indicated that user 1 is a stranger, and user 2 needs to pay attention to protecting his or her privacy during or after the call.

[0167] In step S104, if it is determined that user 1 is an "acquaintance", that is, identification identity 1 is not empty, step S106 may be executed to obtain a historical term set A corresponding to identification identity 1 from the preset term set corresponding to user 2;

[0168] Step S107: Match the communication information A with the historical term set A, and determine the identity of user 1 according to the matching result.

[0169] Specifically, take the communication information A output by user 1 including the content: [("know", 10), ("chat", 20), ("talk", 30),], and the historical idiom set A including the content: {[("know", 200)], [("chat", 300), ("talk about everything", 400)], ...} as an example.

[0170] In actual implementation, in the terminal device used by User 2, a synonym table as shown in Table 1 above can be pre-constructed and stored. Therefore, by querying, it can be obtained that the meaning of the term "know" in communication information A matches the historical term group [("understand", 200)] in historical term set A, and the meanings of the terms "chat" and "chat casually" both match the historical term groups [("chat", 300), ("shoot the breeze", 400)] in historical term set A. When the preset threshold is 0, it can be determined that the historical usage times of these three terms in communication information A in their corresponding matching historical term groups are all less than or equal to the preset threshold. Therefore, these three terms can be determined as the first terms, and the usage times of each first term in the current call process can be obtained to get matching result A: [("know", 10), ("chat", 20), ("chat casually", 30)]. Then, the target difference value F1 can be calculated through the above formula 5 as follows:

[0171] F1 = (log2(200 + 1)) * 10 + (log2(700 + 1)) * 20 + (log2(700 + 1)) * 30;

[0172] It should be noted that in actual implementation, considering that in the matching result, the matching historical term groups corresponding to multiple first terms with matching meanings are the same. Therefore, when calculating the target difference value, it is also possible to first group the first terms with matching meanings in the matching result, and then obtain the sum value of the usage times of each first term in the same group, and calculate the current term difference value of this group of first terms based on this sum value.

[0173] For example, considering that the meanings of both "chat" and "chat casually" match the historical term groups [("chat", 300), ("shoot the breeze", 400)] in historical term set A, these two terms in matching result A can be first grouped together, and the sum value of their usage times can be calculated, that is, 20 + 30 = 50 times. Then, the target difference value F1 can be:

[0174] F1 = (log2(200 + 1)) * 10 + (log2(700 + 1)) * 50.

[0175] After determining the identity of User 1 based on step S107, the method may further include:

[0176] Step S108, determine whether the identity of User 1 is the recognized identity 1; if so, step S109 can be executed to update historical term set A according to communication information A; if not, step S110 can be executed to prompt User 1 that it is suspected of acquaintance fraud and pay attention to protecting privacy.

[0177] It can be seen that based on the method provided by the embodiment of the present disclosure, in an anti-fraud scenario, when a stranger uses an unfamiliar call to imitate the user's acquaintances or friends to commit fraud, the identity of the stranger can be accurately identified, thereby improving the fraud recognition rate, and reminding the call recipient to pay attention to protecting privacy, thereby improving the security of the user's privacy and property.

[0178] It should be noted that the above method is applied to a scenario in which a voice call is made based on a communication number. In actual implementation, the method can also be applied to other communication scenarios. For example, the method can also be applied to a scenario in which communication is made based on an instant messaging application. In this application scenario, for example, user 1 may use an instant messaging application to initiate a voice call request to user 2. During the call, the identification identity of user 1 may be the identity marked by user 2 for user 1 in the instant messaging application, that is, the identification identity may be obtained through the communication account used by user 1, and / or the identification identity may be obtained by identifying the voiceprint feature of user 1. After obtaining the identification identity of user 1, the communication information B output by user 1 during the communication process may be obtained, as well as the historical term set B corresponding to the identification identity, so as to identify the identity of user 1 based on the method provided in the embodiment of the present disclosure. The detailed processing process will not be repeated here.

[0179] Those skilled in the art will appreciate that all or some of the steps, systems, and functional modules / units in the apparatus disclosed above may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0180] In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation.

[0181] Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit (CPU), a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-temporary medium) and a communication medium (or temporary medium). As known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH) or other disk storage; read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical disk storage; magnetic cassettes, magnetic tapes, disk storage or other magnetic storage; any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0182] The present disclosure has disclosed example embodiments, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for limiting purposes. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly stated, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, those skilled in the art will appreciate that various changes in form and detail may be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

1. An identity recognition method, comprising: During the communication process with the target user, obtaining the communication information output by the target user and obtaining the identification identity of the target user; Obtaining a set of historical terms corresponding to the identified identity; Matching the communication information with the historical term set to obtain a matching result; The identity of the target user is determined according to the matching result.

2. The method according to claim 1, wherein: Determining the identity of the target user according to the matching result includes: According to the matching result, obtaining a target term difference value, wherein the target term difference value is used to indicate the degree of difference between the term in the communication information and the term in the historical term set; The identity of the target user is determined according to the target term difference value.

3. The method according to claim 2, wherein: The matching result includes at least one first term, wherein the first term includes: a term in the communication information that satisfies a preset condition with a term in the historical term set; The step of obtaining a target term difference value according to the matching result includes: Obtaining a first term difference value corresponding to each of the first terms to obtain at least one first term difference value; The target term difference value is obtained according to the at least one first term difference value.

4. The method according to claim 3, wherein: The historical term collection includes at least one historical term group; The matching of the communication information with the historical term set to obtain a matching result includes: From the communication information, a term having a corresponding matching historical term group in the at least one historical term group and having a corresponding historical usage count less than or equal to a preset threshold is obtained as the first term, to obtain the at least one first term; Obtaining the matching result according to the at least one first term; Among them, the matching historical term group corresponding to the first term includes: a historical term group in the at least one historical term group whose corresponding word meaning matches the first term.

5. The method according to claim 4, wherein: Each historical term group includes at least one term data pair with matching word meanings, and each term data pair includes a historical term and the number of historical usages corresponding to the historical term; The obtaining of the first term difference value corresponding to the first term includes: Obtaining a target usage count of the first term in the communication information; Obtaining a target matching historical term group corresponding to the first term; Obtaining a sum of the number of historical usages of the historical terms in each term data pair of the target matching historical term group; A first term difference value corresponding to the first term is obtained according to the target usage times and the sum value.

6. The method according to claim 3, wherein: The matching result further includes at least one second term, the second term including: a term corresponding to the communication information in which there is no matching historical term group with matching meaning in the historical term set; The step of obtaining the target term difference value according to the matching result further includes: Obtaining a second term difference value corresponding to each of the second terms to obtain at least one second term difference value; The target term difference value is obtained according to the at least one first term difference value and the at least one second term difference value.

7. The method according to claim 2, wherein: The determining the identity of the target user according to the target term difference value includes: When the target term difference value is less than or equal to a preset difference threshold, determining the identity of the target user as the identified identity; When the target term difference value is greater than the preset difference threshold, the identity of the target user is determined to be another identity other than the identified identity.

8. The method according to claim 7, wherein: In the case where it is determined that the identity of the target user is another identity other than the identified identity, the method further includes: Generate first prompt information, wherein the first prompt information is used to prompt that the identity of the target user is another identity other than the identified identity.

9. The method according to claim 1, wherein: The obtaining the identification identity of the target user includes: Obtain at least one of a target communication number, a target communication account, a target voiceprint feature, and a target claimed identity corresponding to the target user; wherein the target voiceprint feature includes a voiceprint feature extracted from voice data output by the target user during the communication process, and the target claimed identity includes the claimed identity of the target user obtained from the communication information; The identification identity of the target user is determined according to at least one of the target communication number, the target communication account, the target voiceprint feature, and the target claimed identity.

10. The method according to claim 1, wherein: Before executing the step of acquiring the historical term set corresponding to the identified identity, the method further includes: In the case where the identification identity is not obtained, second prompt information is generated, wherein the second prompt information is used to prompt that the target user is a user whose identity is not determined.

11. The method according to claim 7, wherein: In the case where the identity of the target user is determined to be the identification identity, the method further includes: The historical term set is updated according to the communication information.

12. An electronic device comprising: one or more processors; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the identity recognition method according to any one of claims 1 to 11.

13. A computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the identity recognition method according to any one of claims 1 to 11 is implemented.

Images