Voice communication method, system and device for private number of call center, and medium

Abstract

The invention provides a voice communication method and system for a private number of a call center, a system, equipment and a medium, and relates to the technical field of communication, the method comprises the following steps: receiving a call request, and obtaining user information corresponding to a calling user and a called user; acquiring historical behavior data of the user based on the user information, and generating a privacy number based on the historical behavior data; acquiring a user verification code and a call center identity code, and performing bidirectional identity verification; and after the two-way identity verification is passed, establishing an encrypted call channel between the calling user and the called user, and displaying the privacy number of the opposite party on the two sides of the call. The privacy number dynamically generated based on the user behavior data can be adjusted in real time along with the change of the user behavior. For example, when the call object, the call frequency and the call content of the user are changed, the privacy number is correspondingly updated, so that the difficulty of cracking and associating the number is greatly increased, and a third party is effectively prevented from tracking the user through the number.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a voice communication method and system for a private number in a call center, a system, a device, and a medium. Background Art

[0002] Common voice communication privacy protection measures in existing technologies include "intermediary number services" or "anonymous calling." Intermediary number services establish communication between two parties through a call center and provide them with private numbers, thereby protecting privacy. Existing methods for generating private numbers mainly include randomly assigning numbers from an existing number pool or generating private numbers based on order numbers or number regions. However, these methods often have limitations. Randomly assigned private numbers may be reused by different users or analyzed by criminals through large amounts of data to identify patterns. Numbers generated based on order numbers and regions also have a certain degree of predictability, which poses a risk of being cracked and easily identified and attacked by third parties. Summary of the Invention

[0003] The present invention aims to provide a method, system, device, and medium for voice communication of private call center numbers to improve the above-mentioned problems. To achieve the above-mentioned objectives, the present invention adopts the following technical solutions:

[0004] In a first aspect, the present application provides a voice communication method for a call center privacy number, comprising:

[0005] Receive call requests and obtain user information of the corresponding calling and called users;

[0006] Acquiring historical behavior data of the user based on the user information, and generating a private number based on the historical behavior data;

[0007] Obtain user verification code and call center ID code for two-way identity authentication;

[0008] After two-way authentication is passed, an encrypted call channel is established between the calling and called parties, and the other party's private number is displayed on both sides of the call.

[0009] In a second aspect, the present application further provides a voice communication system for a call center privacy number, comprising:

[0010] The first module is used to receive a call request and obtain user information of the corresponding calling user and called user;

[0011] A second module is configured to obtain historical behavior data of the user based on the user information, and generate a private number based on the historical behavior data;

[0012] The third module is used to obtain the user verification code and the call center identity code for two-way identity authentication;

[0013] The fourth module is used to establish an encrypted call channel between the calling user and the called user after the two-way identity authentication is passed, and display the other party's private number on both sides of the call.

[0014] In a third aspect, the present application also provides a voice communication device for a call center privacy number, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the voice communication method for the call center privacy number as described above when executing the computer program.

[0015] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the voice communication method for the call center privacy number as described above.

[0016] The beneficial effects of the present invention are:

[0017] The privacy number dynamically generated based on user behavior data adjusts in real time as user behavior changes. If the user's call recipients, call frequency, or call content change, the privacy number will be updated accordingly, significantly increasing the difficulty of number decryption and association, effectively preventing third parties from tracking users through their numbers.

[0018] Other features and advantages of the present invention will be set forth in the following description, and in part will be apparent from the description, or may be learned by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a flow chart of the voice communication method for a call center privacy number in an embodiment of the present application;

[0021] Figure 2 Schematic diagram of a voice communication system for a call center privacy number in an embodiment of the present application;

[0022] Figure 3 Schematic diagram of the voice communication equipment for the call center privacy number in an embodiment of the present application.

[0023] Markings in the figure: 100-first module; 200-second module; 210-first unit; 220-second unit; 230-third unit; 240-fourth unit; 300-third module; 400-fourth module; 800-voice communication equipment for call center privacy numbers; 801-processor; 802-memory; 803-multimedia component; 804-I / O interface; 805-communication component. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0026] Example 1

[0027] This embodiment provides a voice communication method for a private number in a call center, comprising steps S100, S200, S300, and S400;

[0028] S100: Receive a call request and obtain user information of the corresponding calling user and called user;

[0029] When a caller makes a call request, they need to enter a specific account code (such as the last four digits of their account number) for the call center to identify them.

[0030] When the call center receives a call request from a calling user, it assigns a customer service representative to the user and connects the call signal to the customer service representative's corresponding device. At the same time, it searches for the user information corresponding to the calling user based on the account code entered by the user, and searches for the user information of the called user.

[0031] S200, obtaining historical behavior data of the user based on the user information, and generating a private number based on the historical behavior data;

[0032] S210, extracting frequency features based on the call frequency, extracting service features based on the service records, and extracting call features based on the call records;

[0033] Calculate the user's call frequency based on the number and duration of past calls and obtain the frequency characteristics;

[0034] Retrieve the user's business records. For example, for a medical consultation call center, the user's medical records can be retrieved, and word embedding technology can be used to generate business features based on the medical records. For a financial consultation call center, the name and type of the user's previous business can be retrieved, and the generated business features are type features.

[0035] For call records, this application encrypts and stores the audio of each call of the user in the database; the call record includes multiple audio data; the most recently saved audio data is selected from the multiple audio data, and multiple other audio data are randomly selected to obtain multiple backup audios;

[0036] The most recently saved audio data, that is, the audio data of the user's last call, can ensure that the information used to generate this privacy number is the first time it is used and is not repeated in the past; the user may have a lot of historical audio data, and this application randomly selects several audio data from them as the basis for generating this privacy number. Since it is randomly selected and includes an audio data used for the first time, it can effectively ensure the difference in the call characteristics generated each time.

[0037] This application modifies the backup audio based on the differential privacy mechanism. On the one hand, it can prevent the user's privacy from being leaked; on the other hand, since the noise added each time is different, the unpredictability of the privacy number can be further improved.

[0038] Determining a privacy budget based on the user's call frequency and service record, and adding Laplace noise to each of the backup audios according to the privacy budget and a differential privacy mechanism to obtain processed audio;

[0039] Differential privacy prevents the leakage of individual information by introducing noise into the data. The privacy budget is usually between 0.1 and 10. A larger privacy budget means less noise is added, which interferes with the data less; a smaller privacy budget means more noise is added, which interferes with the data more.

[0040] This application determines the privacy budget based on the user's call frequency and business records. The privacy budget will change as the user's behavior changes. When the call frequency is high, a low privacy budget should be assigned. If the user's business records involve highly sensitive business, the privacy budget should also be assigned an even lower one.

[0041] As an example, first, a basic privacy budget value X is preset, for example, 3; based on the user's current call frequency, the corresponding sensitivity is determined to be a; the user's business records involve n kinds of sensitive services (non-sensitive services are not considered), each sensitive service has a pre-given sensitivity, the sensitivity of sensitive service 1 is b1, the sensitivity of sensitive service 2 is b2, and the sensitivity of sensitive service n is b n ;

[0042] The total sensitivity of the three sensitive services is Constructing an inverse function k is a positive constant used to control the range of output values;

[0043] The basic privacy budget value is adjusted using the sensitivity of sensitive services and call frequency. The final privacy budget ∈:

[0044]

[0045] Among them, α is the weight coefficient.

[0046] Calculate the scale parameter r of the Laplace noise according to the privacy budget ∈:

[0047] r=Δf / ∈

[0048] Among them, Δf is the global sensitivity, which is the maximum change of the query function f on adjacent data sets. The specific calculation method depends on the query type.

[0049] The default value of the noise location parameter u is 0. The location parameter u determines the center position of the noise distribution. When adding Laplace noise, the location parameter of the noise is 0, which ensures that the expectation of the noise is 0.

[0050] The Mel-Frequency Cepstral Coefficients (MFCC) of each processed audio are extracted and concatenated to obtain the call features.

[0051] The extraction of Mel-frequency cepstral coefficients is to convert the sound signal into a set of coefficients representing the spectrum envelope by simulating the nonlinear perception of the human ear to frequency, which can reflect timbre information, emotional information, spectral feature information, etc.

[0052] The splicing process in this step can be performed sequentially according to the timestamps of the audios, or the order of the audios can be disrupted and spliced ​​in a random order.

[0053] S220, converting the frequency characteristics, service characteristics, and call characteristics into one-dimensional arrays respectively, concatenating multiple one-dimensional arrays and inputting them into a hash function to obtain a hash value;

[0054] If the frequency feature is directly used as the frequency value, it is one-dimensional data, so no conversion is required.

[0055] Business features and call features are generally multi-dimensional arrays, which can be transformed into one-dimensional arrays by flattening them in row or column order.

[0056] Thus, three one-dimensional arrays can be obtained. The three are directly concatenated and then mapped into hash values ​​using non-encrypted hash functions such as MurMurHash and FNV Hash. This step does not require encryption, and the use of non-encrypted hash functions can achieve faster computing speeds and occupy less storage space.

[0057] S230, converting the hash value into a digital format of a preset length to obtain a feature code;

[0058] In this step, the hash value can be converted to Base-N encoding (such as Base10), and then a fixed length is cut off to serve as the signature. Alternatively, some bytes of the hash value can be converted to integers, and then their length is limited to serve as the signature.

[0059] S240: Combine the feature code with the random number to obtain a private number. The private number is valid only during the call and becomes invalid immediately after the call ends.

[0060] If the user calls the same person each time, the calls are short and the content is similar, the extracted call features may be similar each time. In addition, the user's call frequency and service records may not change significantly over a period of time, which may lead to a high similarity between recently generated private numbers, which is not conducive to privacy protection. Therefore, this application also proposes the following method to update noise:

[0061] Search for the most recent user's historical call features and historical feature codes according to a preset quantity requirement; for example, search for the most recent 5 historical call features and the most recent 5 historical feature codes according to timestamps.

[0062] Calculating similarities between historical call features and historical feature codes respectively to obtain multiple similarity values;

[0063] Calculate similarity between each of the five historical call features. Similarly, calculate the historical feature code. For historical call features, calculate the Manhattan distance between each pair. For historical feature codes, since they are non-vectors, use the Hamming distance as the preferred similarity measure.

[0064] If any similarity value reaches a preset threshold, the position parameters of the Laplace noise of each backup audio are generated through chaotic mapping to perform noise update.

[0065] The preset thresholds for historical call characteristics and historical signature codes are set to different values. When the similarity value of either reaches the preset threshold, it indicates that similar historical call characteristics or signature codes have appeared recently, and interference is needed to increase the unpredictability of the private number. Therefore, this step chooses to change the location of noise addition through chaotic mapping to significantly change the call characteristics.

[0066] A chaotic map is used to generate a chaotic sequence. The number of position parameters generated by the chaotic map is the same as the number of backup audio tracks. This means that each backup audio track has unique noise position parameters. After the noise update process, even if the user's calls are similar, different call signatures can be generated, maximizing the diversity and randomness of each private number used. The updated noise position parameters remain unchanged until a similar call signature or code is encountered again in recent historical calls, at which point a new noise update is performed.

[0067] S300, obtaining the user verification code and the call center identity code, and performing two-way identity authentication;

[0068] Most call center implementations are user-centric and generally only verify the user's identity, or even only the calling user's identity, which can lead to information security risks. In this application, not only the identities of both users are verified, but also the identity of the call center's customer service representative is verified, as follows:

[0069] S310: Generate a random verification code and send it to the user, and receive the verification code returned by the user for verification;

[0070] After receiving the user's call request, a random verification code is generated and sent to the user via the user's registered mobile phone number or email; the user returns the received random verification code to the call center to complete the identity verification.

[0071] S320: Obtain device information for receiving the call request and corresponding customer service information, and retrieve an authentication identity code based on the device information and customer service information;

[0072] In step S100, a device is allocated to each user's call request. This step obtains the device information and the corresponding customer service information, and then retrieves the corresponding authentication identity code. The authentication identity code can be updated every day to ensure dynamic changes.

[0073] S330, obtaining the input identity code, and checking whether the input identity code is consistent with the authentication identity code;

[0074] Before the customer service establishes a call connection for the calling user and the called user, the calling user needs to enter their authentication identity code, that is, enter the identity code, and check whether the input identity code is consistent with the authentication identity code. If they are consistent, the call connection is allowed to be established.

[0075] S340: Send the verification result of the user verification code and the identity code to the user.

[0076] The verification results include the verification results of the calling user, the called user and the customer service identity. If there is a security risk on one party, the user can be informed of the current risk hazards in the first time.

[0077] S400: After the two-way identity authentication is passed, an encrypted call channel is established between the calling user and the called user, and the private number of the other party is displayed on both sides of the call.

[0078] To protect users from attacks during calls, such as man-in-the-middle attacks and content theft, this application uses AES 256-bit encryption technology to encrypt call content, ensuring data confidentiality during transmission. TLS is also used to establish a secure call network, protecting data from eavesdropping or interception. During a call, a new dynamic encryption key is generated for each audio packet to prevent man-in-the-middle attacks.

[0079] In addition, during the call, the call status is monitored in real time and security assessment is performed, as follows:

[0080] Obtain the current call duration and audio information between the calling and called users, and perform intonation and sentiment analysis and vocabulary extraction based on the audio information;

[0081] A first risk value is calculated based on call duration, tone of voice, and vocabulary;

[0082] A pre-trained analysis model is used to perform feature processing and emotion classification on audio information to obtain emotion labels. Each emotion label has a pre-given risk value. In addition, the intensity of emotions is analyzed through intonation features as the weight of each emotion.

[0083] For vocabulary extraction, the audio is first converted into text using a speech recognition tool. Keywords are then extracted from the text to obtain vocabulary. Risk vocabulary is then screened out based on a pre-set risk vocabulary list. Each risk vocabulary has a pre-defined risk value.

[0084] A first risk value is calculated based on the call duration, the emotion label risk value, and the risk word risk value.

[0085] The second risk value is obtained by obtaining the frequency of changes in the call center's identity code during the call; that is, monitoring whether the call center customer service frequently changes their identity to determine whether there is any abnormality on the customer service side.

[0086] Determine whether the first risk value or the second risk value is greater than a preset safety reference value. If so, interrupt the call channel and generate an alarm message.

[0087] The present invention monitors the security of calls in real time, assesses and issues alerts for suspicious activities. Once suspicious behavior is detected, the system immediately issues an alert, proactively interrupts the call and notifies the user.

[0088] After the call ends, the mapping between the private number and the user's real number is automatically recorded. All call content is encrypted and stored in the call record module to ensure that the data cannot be tampered with. Upon user request, this data can be subsequently queried and audited.

[0089] Example 2

[0090] This embodiment provides a voice communication system for a call center private number, including:

[0091] The first module 100 is used to receive a call request and obtain user information of the corresponding calling user and called user;

[0092] The second module 200 is configured to obtain historical behavior data of the user based on the user information, and generate a private number based on the historical behavior data;

[0093] The third module 300 is used to obtain the user verification code and the call center identity code to perform two-way identity authentication;

[0094] The fourth module 400 is used to establish an encrypted call channel between the calling user and the called user after the two-way identity authentication is passed, and display the other party's private number on both sides of the call.

[0095] As an optional implementation, the second module 200 includes:

[0096] The first unit 210 is configured to extract frequency features based on the call frequency, extract service features based on the service records, and extract call features based on the call records;

[0097] The second unit 220 is configured to convert the frequency characteristics, service characteristics, and call characteristics into one-dimensional arrays, concatenate multiple one-dimensional arrays, and input them into a hash function to obtain a hash value;

[0098] The third unit 230 is configured to convert the hash value into a digital format of a preset length to obtain a feature code;

[0099] The fourth unit 240 is configured to combine the feature code with the random number to obtain a private number.

[0100] Example 3

[0101] Corresponding to the above method embodiment, this embodiment also provides a voice communication device for a call center privacy number. The voice communication device for a call center privacy number described below and the voice communication method for a call center privacy number described above can be referred to each other.

[0102] Figure 3 FIG. 8 is a block diagram of a voice communication device 800 for a call center privacy number according to an exemplary embodiment. Figure 3 As shown, the voice communication device 800 for a call center privacy number includes a processor 801 and a memory 802. The voice communication device 800 for a call center privacy number may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805. The processor 801 is used to control the overall operation of the voice communication device 800 for a call center privacy number to complete all or part of the steps in the voice communication method for a call center privacy number described above. The memory 802 is used to store various types of data to support the operation of the voice communication device 800 for a call center privacy number. Such data may, for example, include commands for any application or method operating on the voice communication device 800 for a call center privacy number, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0103] The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals.

[0104] The received audio signal can be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules. The above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the voice communication device 800 of the call center privacy number and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0105] In an exemplary embodiment, the device 800 for mutual signing and verification of digital files may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned voice communication method for call center privacy numbers.

[0106] In another exemplary embodiment, a computer-readable storage medium including program commands is also provided. When executed by a processor, the program commands implement the steps of the aforementioned method for voice communication with a private call center number. For example, the computer-readable storage medium may be the aforementioned memory 802 including the program commands. The program commands may be executed by the processor 801 of the voice communication device 800 for a private call center number to implement the aforementioned method for voice communication with a private call center number.

[0107] Example 4

[0108] Corresponding to the above method embodiment of voice communication of a call center privacy number, this embodiment further provides a readable storage medium. The readable storage medium described below and the voice communication method of the call center privacy number described above can be referenced to each other.

[0109] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned embodiment of the voice communication method for a private number in a call center.

[0110] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0111] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0112] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A voice communication method for a call center private number, characterized in that: include: Receive call requests and obtain user information of the corresponding calling and called users; Acquiring historical behavior data of the user based on the user information, and generating a private number based on the historical behavior data; Obtain user verification code and call center ID code for two-way identity authentication; After two-way authentication is passed, an encrypted call channel is established between the calling and called parties, and the other party's private number is displayed on both sides of the call.

2. The voice communication method for a call center private number according to claim 1, characterized in that: The historical behavior data includes call frequency, business records and call records; Generating a private number based on the historical behavior data includes: Extracting frequency features based on the call frequency, extracting service features based on the service records, and extracting call features based on the call records; Convert the frequency characteristics, service characteristics, and call characteristics into one-dimensional arrays respectively, concatenate multiple one-dimensional arrays and input them into a hash function to obtain a hash value; Converting the hash value into a digital format of a preset length to obtain a feature code; The feature code is combined with a random number to obtain a private number.

3. The voice communication method for a call center private number according to claim 2, characterized in that: The call record includes a plurality of audio data; and extracting call features based on the call record includes: Selecting a most recently saved audio data from a plurality of audio data and randomly selecting a plurality of other audio data to obtain a plurality of backup audio data; Determining a privacy budget based on the user's call frequency and service record, and adding Laplace noise to each of the backup audios according to the privacy budget and a differential privacy mechanism to obtain processed audio; The Mel-frequency cepstral coefficients of each processed audio are extracted and concatenated to obtain the call features.

4. The voice communication method for a call center private number according to claim 3, characterized in that: The method comprises: Search for the most recent user's historical call features and historical feature codes based on a preset number of requirements; Calculate similarity between historical call features and historical feature codes respectively to obtain multiple similarity values; If any similarity value reaches a preset threshold, the position parameters of the Laplace noise of each backup audio are generated through chaotic mapping to perform noise update.

5. The voice communication method for a call center private number according to claim 1, characterized in that: Obtain the user verification code and the call center's identity code for two-way identity verification, including: Generate a random verification code and send it to the user, and accept the verification code returned by the user for verification; Obtain the device information and corresponding customer service information of the receiving call request, and retrieve the authentication identity code based on the device information and customer service information; Obtain the input identity code and check whether the input identity code is consistent with the authentication identity code; The user verification code verification result and identity code verification result are sent to the user.

6. The voice communication method for a call center private number according to claim 1, characterized in that: The method comprises: Obtain the current call duration and audio information between the calling and called users, and perform intonation and sentiment analysis and vocabulary extraction based on the audio information; The first risk value is calculated based on call duration, tone of voice, and vocabulary Obtaining a frequency of changes in the call center's identity code during the call to obtain a second risk value; Determine whether the first risk value or the second risk value is greater than a preset safety reference value. If so, interrupt the call channel and generate an alarm message.

7. A voice communication system for a call center private number, characterized in that: include: The first module is used to receive a call request and obtain user information of the corresponding calling user and called user; A second module is configured to obtain historical behavior data of the user based on the user information, and generate a private number based on the historical behavior data; The third module is used to obtain the user verification code and the call center identity code for two-way identity authentication; The fourth module is used to establish an encrypted call channel between the calling user and the called user after the two-way identity authentication is passed, and display the other party's private number on both sides of the call.

8. The voice communication system for call center private numbers according to claim 7, characterized in that: The second module includes: A first unit is configured to extract frequency features based on the call frequency, extract service features based on the service records, and extract call features based on the call records; The second unit is configured to convert the frequency characteristics, service characteristics, and call characteristics into one-dimensional arrays respectively, concatenate multiple one-dimensional arrays, and input them into a hash function to obtain a hash value; The third unit is configured to convert the hash value into a digital format of a preset length to obtain a feature code; The fourth unit is used to combine the feature code with the random number to obtain a private number.

9. A voice communication device for a call center private number, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method implements the steps of the voice communication method for a call center privacy number as claimed in any one of claims 1 to 6.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the voice communication method for a call center privacy number according to any one of claims 1 to 6.

Images