Outbound calling method, device, medium, server and intelligent robot

Abstract

The present disclosure provides an outbound call method, device, medium, server, and intelligent robot. The method includes: when the current working scenario is an outbound call scenario, sorting the outbound call data corresponding to the first identifier to obtain an outbound call list, wherein the outbound call data includes the second identifier; generating an outbound call instruction, and sending the outbound call instruction to the intelligent robot; wherein the outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein the outbound call instruction is used to instruct the intelligent robot to obtain a communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiating an outbound call operation for the second identifier in the outbound call list. The present disclosure is used to solve a series of defects in the prior art when using intelligent robots to assist manual operations, and realizes active control of the intelligent robot to perform outbound call operations that match manual outbound calls.

Description

Technical Field

[0001] The present disclosure relates to the field of human-computer interaction technology, and in particular to an outbound calling method, device, medium, server, and intelligent robot. Background Art

[0002] Industries that rely heavily on manual phone calls are introducing intelligent robots to assist them in reducing the workload. In actual use, customer service personnel assign tasks to the robots, which then make outbound calls based on the assigned tasks.

[0003] In the prior art, it is necessary to manually assign tasks to the intelligent robot to trigger the outbound call operation of the intelligent robot, and it is impossible to automatically control the intelligent robot to perform outbound call operations. In addition, the outbound call operation of the existing intelligent robot and the outbound call operation of the manual operation do not provide the same experience to the customer. Summary of the Invention

[0004] The present disclosure provides an outbound calling method, device, medium, server and intelligent robot to solve a series of defects in the prior art when using intelligent robots to assist manual operations, and realize active control of the intelligent robot to perform outbound calling operations that match manual outbound calls.

[0005] The present disclosure provides an outbound calling method, applied to a server, the method comprising:

[0006] When the current working scenario is an outbound call scenario, sorting the outbound call data corresponding to the first identifier to obtain an outbound call list, wherein the outbound call data includes the second identifier, and the first identifier and the second identifier indicate different user roles;

[0007] Generate an outbound call instruction and send the outbound call instruction to the intelligent robot;

[0008] The outbound call instruction includes: the tone type of the first identifier and the outbound call list;

[0009] Among them, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiate an outbound call operation for the second identifier in the outbound call list.

[0010] According to an outbound call method provided by the present disclosure, the step of sorting the outbound call data corresponding to the first identifier to obtain an outbound call list includes:

[0011] Obtaining a historical communication record corresponding to the second identifier in the pending outbound call data;

[0012] Determining an outbound call success rate for each second identifier based on the historical communication records;

[0013] Based on the outbound call success rate, the second identifiers in the pending outbound call data are sorted to obtain the outbound call list.

[0014] According to an outbound call method provided by the present disclosure, before generating the outbound call instruction, the method further includes:

[0015] Obtaining audio data corresponding to the first identifier;

[0016] Inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a timbre type corresponding to the target audio data;

[0017] The target audio data is a voice corresponding to the timbre of the first identifier;

[0018] The speech generation model is obtained by training audio data samples, target audio data samples and timbre type samples.

[0019] According to an outbound call method provided by the present disclosure, inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a timbre type corresponding to the target audio data includes:

[0020] Inputting the audio data into the feature extraction layer of the speech generation model to obtain the timbre features output by the feature extraction layer;

[0021] The timbre feature is input into the speech generation layer of the speech generation model to obtain the target audio data output by the speech generation layer and the timbre type corresponding to the target audio data.

[0022] According to an outbound call method provided by the present disclosure, before generating the outbound call instruction, the method further includes:

[0023] Obtaining a historical communication record corresponding to the second identifier in the pending outbound call data;

[0024] determining, based on the historical communication records, a behavioral characteristic corresponding to the second identifier;

[0025] Generate a communication strategy corresponding to the behavioral characteristics, and send the communication strategy to the intelligent robot.

[0026] The present disclosure provides an outbound calling method, which is applied to an intelligent robot, and the method comprises:

[0027] receiving an outbound call instruction sent by a server, wherein the outbound call instruction includes: a tone type of a first identifier and an outbound call list;

[0028] Acquire a communication strategy corresponding to a second identifier in the outbound call list, wherein the first identifier and the second identifier indicate different user roles;

[0029] Based on the tone type and the communication strategy, an outbound call operation is initiated for the second identifier in the outbound call list.

[0030] According to an outbound call method provided by the present disclosure, before acquiring the communication strategy corresponding to the second identifier in the outbound call list, the method further includes:

[0031] receiving a communication strategy sent by the server;

[0032] Based on the second identifier corresponding to the communication strategy, storing the communication strategy in a node of the multi-branch tree;

[0033] The acquiring of the communication strategy corresponding to the second identifier in the outbound call list includes:

[0034] Based on the second identifier in the outbound call list, a target node is determined from the multi-branch tree, and the communication strategy is obtained from the target node.

[0035] According to an outbound call method provided by the present disclosure, determining a target node from the multi-branch tree based on the second identifier in the outbound call list, and obtaining the communication strategy from the target node include:

[0036] determining an initial target node based on a second identifier in the outbound call list, and obtaining an initial communication strategy from the initial target node;

[0037] The initiating an outbound call operation for the second identifier in the outbound call list based on the timbre type and the communication strategy includes:

[0038] Initiating an outbound call operation for the second identifier based on the timbre type and the initial communication strategy;

[0039] After initiating an outbound call operation for the second identifier based on the tone type and the initial communication strategy, the method further includes:

[0040] Obtaining a current communication record corresponding to the second identifier;

[0041] Based on the current communication record, a current target node is determined from the multi-branch tree, the current communication strategy is obtained from the current target node, and the obtained current communication strategy is played.

[0042] According to an outbound calling method provided by the present disclosure, the method further includes:

[0043] When the current working scene is a manual working scene, obtaining a current communication record corresponding to the second identifier;

[0044] Based on the current communication record, a current target node is determined from the multi-branch tree, a current communication strategy is obtained from the current target node, and the current communication strategy is recommended to the first identifier.

[0045] The present disclosure also provides an outbound calling device, comprising:

[0046] a sorting module, configured to, when the current working scenario is an outbound call scenario, sort the pending outbound call data corresponding to the first identifier to obtain an outbound call list, wherein the pending outbound call data includes the second identifier, and the first identifier and the second identifier indicate different user roles;

[0047] A sending module, configured to generate an outbound call instruction and send the outbound call instruction to the intelligent robot;

[0048] The outbound call instruction includes: the tone type of the first identifier and the outbound call list;

[0049] Among them, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiate an outbound call operation for the second identifier in the outbound call list.

[0050] The present disclosure also provides an outbound calling device, comprising:

[0051] A receiving module, configured to receive an outbound call instruction sent by a server, wherein the outbound call instruction includes: a tone type of a first identifier and an outbound call list;

[0052] An acquisition module, configured to acquire a communication strategy corresponding to a second identifier in the outbound call list, wherein the first identifier and the second identifier indicate different user roles;

[0053] An outbound call module is used to initiate an outbound call operation for the second identifier in the outbound call list based on the tone type and the communication strategy.

[0054] The present disclosure further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the outbound calling method applied to a server as described in any one of the above is implemented.

[0055] The present disclosure also provides a server for implementing any of the above-mentioned outbound calling methods applied to the server.

[0056] The present disclosure also provides an intelligent robot, comprising: a robot body and a controller, wherein the controller is used to implement the outbound calling method applied to the intelligent robot as described in any one of the above items.

[0057] The outbound call method, device, medium, server and intelligent robot provided by the present disclosure obtain an outbound call list by sorting the outbound call data corresponding to the first identifier when the current working scene is an outbound call scene. The outbound call data includes the second identifier. It can be seen that the present disclosure monitors the working scene in real time, and generates an outbound call list in the outbound call scene to provide effective data for actively controlling the intelligent robot to initiate an outbound call operation; then, an outbound call instruction is generated and sent to the intelligent robot to realize active control of the intelligent robot to initiate an outbound call operation; wherein the outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, an outbound call operation is initiated for the second identifier in the outbound call list. It can be seen that the intelligent robot of the present disclosure adopts the tone consistent with the first identifier and the communication strategy matching the second identifier when performing an outbound call operation, which effectively improves the customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the present disclosure or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0059] Figure 1 This is a flow chart of an outbound calling method applied to a server provided by the present disclosure;

[0060] Figure 2 This is a flow chart of the outbound calling method applied to an intelligent robot provided by the present disclosure;

[0061] Figure 3 It is a structural diagram of the outbound calling system provided by the present disclosure;

[0062] Figure 4 This is a signaling diagram for implementing an outbound call of the outbound call system provided by the present disclosure;

[0063] Figure 5 This is one of the structural diagrams of the outbound calling device provided by the present disclosure;

[0064] Figure 6 This is one of the structural diagrams of the outbound calling device provided by the present disclosure;

[0065] Figure 7It is a structural diagram of the electronic device provided by the present disclosure. DETAILED DESCRIPTION

[0066] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the embodiments of the present disclosure.

[0067] The following combination Figure 1-Figure 4 The outbound calling method according to the embodiment of the present disclosure is described.

[0068] In order to clearly illustrate the outbound calling method disclosed herein, the application background is further described in detail below:

[0069] While replacing manual labor with intelligent robots is a major industry trend, there's still a long way to go. Currently, utilizing intelligent robots to improve human efficiency remains a major pain point. Because intelligent robot outbound call services are intelligent voice services, they are typically assigned directly to the robots using a pre-set model, or the initiation of intelligent robot outbound call tasks is centrally managed by the head of the organization.

[0070] However, for scenarios requiring long-term follow-up with customers, such as repayment reminders, the above two solutions are not sufficient to improve efficiency and resolve the problem. For example, in repayment reminder scenarios, frontline staff are increasingly seeking to use intelligent robots to handle specific cases to improve efficiency and enhance performance while maintaining a good customer experience.

[0071] The following uses the repayment reminder field as an example to illustrate:

[0072] In the repayment reminder scenario, cases that have just become overdue will generally be initially triggered by an intelligent robot using a pre-set model. After a period of time, cases that are still overdue will be handed over to human customer service. During this period, no further calls will be made by the model-driven intelligent robot.

[0073] Furthermore, after assigning a task to an agent, a human needs to manually initiate an outbound call with the intelligent robot. This process relies too much on manual experience, making it difficult to effectively screen new employees and resulting in a waste of outbound call resources. When the intelligent robot initiates an outbound call, the voice of the robot differs from that of a human, leading to inconsistent customer experiences and a poor user experience.

[0074] In order to effectively solve the above problems, the embodiment of the present disclosure provides an outbound calling method applied to a server, such as Figure 1 As shown, the method includes:

[0075] Step 101: When the current working scenario is an outbound call scenario, sort the outbound call data corresponding to the first identifier to obtain an outbound call list.

[0076] The data to be called outbound includes a second identifier.

[0077] The first identifier and the second identifier indicate different user roles. The first identifier is a customer service identifier, that is, an identifier that can represent a customer service identity role; the second identifier is a customer identifier, that is, an identifier that can represent a customer identity role.

[0078] Among them, work scenarios include: manual operation scenarios and outbound call scenarios.

[0079] Among them, outbound call scenarios include: scenarios where customer service pre-sets scheduled tasks that require intelligent robots to make outbound calls, and scenarios where customer service fails to perform manual operations on time.

[0080] Among them, the scenario when the customer service is not in the manual operation scenario on time is: the customer service manual operation is required within a preset time period, but the customer service is not operating within the time period.

[0081] Specifically, determine whether the current working scene is an outbound call scene. If it is determined that the current working scene is an outbound call scene, sort the outbound call data corresponding to the first identifier to obtain an outbound call list; if it is determined that the current working scene is a manual operation scene, receive a user request based on the first identifier input, and execute the operation corresponding to the user request.

[0082] In a specific embodiment, the specific implementation method of obtaining the outbound call list is as follows:

[0083] Obtain historical communication records corresponding to the second identifier in the outbound call data; determine the outbound call success rate for each second identifier based on the historical communication records; and sort the second identifiers in the outbound call data based on the outbound call success rate to obtain an outbound call list.

[0084] Among them, historical communication records include: historical communication records between customer service and customers and historical communication records between intelligent robots and customers.

[0085] Among them, historical communication records include: communication time, whether the connection is successful, communication duration and communication content, etc.

[0086] Among them, for the repayment reminder scenario, the outbound call success rate is used to indicate the repayment probability of the second identifier; for the product promotion scenario, the outbound call success rate is used to indicate the purchase probability of the second identifier; etc.

[0087] The second identifier is data that can uniquely represent customer information.

[0088] Specifically, based on historical communication records, the connection rate, optimal broadcast time and optimal broadcast number corresponding to each second identifier are determined; based on the connection rate, optimal broadcast time, optimal broadcast duration and optimal broadcast number, the outbound call success rate is determined; based on the outbound call success power, the second identifiers are sorted in descending order to obtain an outbound call list.

[0089] Among them, the outbound call list includes at least a mobile phone number identifier, so that the intelligent robot can make outbound calls based on the mobile phone number identifier.

[0090] The present invention determines the outbound call success rate of each second identifier through historical communication records to sort the second identifiers in the outbound call data. The purpose is to enable the intelligent robot to make outbound calls according to the outbound call list, ensure the effectiveness of the outbound call operation, and improve the overall operation efficiency.

[0091] In a specific embodiment, to ensure user experience, the present disclosure ensures that the voice of the intelligent robot during outbound calls is consistent with that of the customer service representative. This is accomplished by obtaining audio data corresponding to a first identifier; inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and the timbre type corresponding to the target audio data; wherein the target audio data is speech corresponding to the timbre of the first identifier; and wherein the speech generation model is trained using audio data samples, target audio data samples, and timbre type samples.

[0092] Among them, each customer service staff pre-records audio data.

[0093] In a specific embodiment, audio data is input into the feature extraction layer of the speech generation model to obtain the timbre features output by the feature extraction layer; the timbre features are input into the speech generation layer of the speech generation model to obtain the target audio data output by the speech generation layer and the timbre type corresponding to the target audio data.

[0094] Among them, the speech generation model disclosed in the present invention is composed of a neural network (Tacotron2) and a neural network (waveglow).

[0095] Among them, Tacotron2 is a speech synthesis framework, which includes a spectrogram prediction network (feature extraction layer) and a vocoder (speech generation layer).

[0096] The spectrogram prediction network is used to predict the input audio data into a frame sequence of Mel spectrum, wherein the audio data is represented in the form of a character sequence, and the frame sequence of Mel spectrum is the timbre feature.

[0097] The vocoder is used to generate a time domain waveform from the predicted Mel spectrum frame sequence to obtain target audio data.

[0098] The speech generation model disclosed in the present invention can further determine the corresponding timbre type based on the timbre features.

[0099] The target audio data generated by the present disclosure sounds very similar to a real person, and has a high user call perception value (MOS value), for example, 4.5 points. This enables the intelligent robot to emit a voice consistent with that of customer service when making outbound calls, thereby improving the user experience.

[0100] In one specific embodiment, to ensure effective communication between an intelligent robot and a customer, the present disclosure configures a communication strategy for the intelligent robot that corresponds to the customer. This involves obtaining historical communication records corresponding to a second identifier in the outbound call data; determining behavioral characteristics corresponding to the second identifier based on the historical communication records; generating a communication strategy corresponding to the behavioral characteristics; and transmitting the communication strategy to the intelligent robot.

[0101] Among them, communication strategies include: specific communication language and communication types with corresponding customers, among which communication types include: pressure type and appeasement type, etc.

[0102] Different communication types are pre-matched with corresponding tones. Ultimately, the intelligent robot uses the tone and communication language corresponding to the customer service, as well as the tone corresponding to the customer, to make outbound calls.

[0103] Among them, historical communication records also include: communication attitude score, communication tone score and customer communication speech quality score, etc.

[0104] Based on the communication attitude score, the communication tone score, and the customer's speech quality score, the behavioral characteristics corresponding to the second identifier are determined.

[0105] For example, when the behavioral characteristics indicate that the second identifier is tough, a corresponding pressure-type communication strategy is generated; for another example, when the behavioral characteristics indicate that the second identifier is anxious, a corresponding comfort-type communication strategy is generated; and so on.

[0106] The present disclosure generates a communication strategy corresponding to the customer's behavioral characteristics, so that the intelligent robot communicates with the customer using the generated communication strategy, thereby improving the efficiency of communication.

[0107] Step 102: Generate an outbound call instruction and send the outbound call instruction to the intelligent robot.

[0108] The outbound call instruction includes: a tone type of the first identifier and an outbound call list.

[0109] Among them, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and communication strategy, initiate an outbound call operation for the second identifier in the outbound call list.

[0110] If the customer service representative fails to arrive on time, the system will automatically initiate an outbound call with the intelligent robot for the outbound call data under the name of the customer service representative; if the customer service representative has agreed on a communication time with the customer, the system will automatically initiate an outbound call with the intelligent robot according to the communication time; the system will automatically schedule an active outbound call operation with the intelligent robot, and when the scheduled date arrives, the intelligent robot will be actively controlled or the intelligent robot will automatically initiate an outbound call operation.

[0111] The outbound call method applied to the server provided by the present disclosure obtains an outbound call list by sorting the outbound call data corresponding to the first identifier when the current working scene is an outbound call scene. The outbound call data includes the second identifier. It can be seen that the present disclosure monitors the working scene in real time, and generates an outbound call list in the outbound call scene to provide effective data for actively controlling the intelligent robot to initiate an outbound call operation; then, an outbound call instruction is generated, and the outbound call instruction is sent to the intelligent robot to realize active control of the intelligent robot to initiate an outbound call operation; wherein, the outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, an outbound call operation is initiated for the second identifier in the outbound call list. It can be seen that the intelligent robot of the present disclosure adopts the tone consistent with the first identifier and the communication strategy matching the second identifier when performing an outbound call operation, which effectively improves the customer experience.

[0112] The embodiment of the present disclosure also provides an outbound calling method applied to an intelligent robot, as shown in 2, the method comprising:

[0113] Step 201: Receive an outbound call instruction sent by a server.

[0114] The outbound call instruction includes: a tone type of the first identifier and an outbound call list.

[0115] Among them, different customer service staff can correspond to one intelligent robot, or one customer service staff can correspond to one intelligent robot.

[0116] In a specific embodiment, before receiving the outbound call instruction sent by the server, a communication strategy sent by the server is received; based on the second identifier corresponding to the communication strategy, the communication strategy is stored in a node of the multi-branch tree; then, after receiving the outbound call instruction sent by the server, based on the second identifier in the outbound call list, the target node is determined from the multi-branch tree, and the communication strategy is obtained from the target node.

[0117] Among them, a plurality of multi-branch trees are stored in an intelligent robot, one multi-branch tree corresponds to one second identifier, one multi-branch tree includes a plurality of nodes, and each node includes a communication strategy and a strategy tag corresponding to the communication strategy.

[0118] The present disclosure reduces the tree layer height by using a multi-branch tree storage communication strategy, reduces the number of nodes traversed during search, improves data search speed, and reduces data search time.

[0119] Step 202: Acquire a communication strategy corresponding to the second identifier in the outbound call list.

[0120] In a specific embodiment, the specific implementation method of obtaining the communication strategy is as follows: based on the second identifier in the outbound call list, the initial target node is determined, and the initial communication strategy is obtained from the initial target node; based on the tone type and the initial communication strategy, an outbound call operation is initiated for the second identifier; based on the tone type and the initial communication strategy, after initiating an outbound call operation for the second identifier, the current communication record corresponding to the second identifier is obtained; based on the current communication record, the current target node is determined from the multi-branch tree, the current communication strategy is obtained from the current target node, and the obtained current communication strategy is played.

[0121] Specifically, upon receiving an outbound call instruction, the system retrieves an initial communication strategy from the multitree based on the second identifier. Then, based on the timbre type and the initial communication strategy, it initiates an outbound call for the second identifier. After the outbound call is confirmed to be connected, the system retrieves the current communication record corresponding to the second identifier, analyzes the record, obtains a strategy tag, locates the current target node from the multitree based on the strategy tag, and then retrieves and plays the current communication strategy from the target node until the call ends.

[0122] The intelligent robot disclosed herein communicates with customers based on pre-configured communication strategies, thereby ensuring customer experience and improving the success rate of outbound calls.

[0123] Step 203: Initiate an outbound call operation for the second identifier in the outbound call list based on the tone type and the communication strategy.

[0124] In a specific embodiment, when the current work scenario is a manual work scenario, the current communication record corresponding to the second identifier is obtained; based on the current communication record, the current target node is determined from the multi-branch tree, the current communication strategy is obtained from the current target node, and the current communication strategy is recommended to the first identifier.

[0125] The intelligent robot disclosed herein monitors the communication content between customer service personnel and customers in real time, analyzes the customer's current communication records, obtains strategy tags, finds the current target node from the multi-branch tree based on the strategy tags, and then obtains the current communication strategy from the current target node, and sends the communication strategy to a computer or mobile phone to provide communication assistance to customer service.

[0126] The present disclosure monitors manual operation scenarios, avoids the problem of inaccurate wording in human communication, ensures communication quality, and improves user experience.

[0127] The outbound call method applied to the intelligent robot provided by the present disclosure receives the outbound call instruction sent by the server; obtains the communication strategy corresponding to the second identifier in the outbound call list to ensure the effectiveness of communication; and initiates an outbound call operation for the second identifier in the outbound call list based on the tone type and the communication strategy. It can be seen that the intelligent robot of the present disclosure adopts the tone consistent with the first identifier and the communication strategy matching the second identifier when performing the outbound call operation, which effectively improves the customer experience.

[0128] The embodiment of the present disclosure further provides an outbound call system. The outbound call system described below and the outbound call method described above can be referred to each other, and the repeated parts will not be repeated. Figure 3 As shown, the system includes a server 301 and an intelligent robot 302.

[0129] Next, through Figure 4 The specific implementation of this system is described as follows:

[0130] S401, the server obtains a timbre type corresponding to the audio data through a speech generation model;

[0131] S402, the server obtains a communication strategy through historical communication records;

[0132] S403, the server sends the communication strategy to the intelligent robot;

[0133] S404: When the server determines that the working scenario is an outbound call scenario, it sorts the pending outbound call data corresponding to the first identifier based on the historical communication records to obtain an outbound call list;

[0134] S405, the server generates an outbound call instruction;

[0135] S406, the server sends the outbound call instruction to the intelligent robot;

[0136] S407, the intelligent robot receives an outbound call instruction;

[0137] S408, the intelligent robot obtains the communication strategy corresponding to the second identifier in the outbound call list;

[0138] S409: The intelligent robot initiates an outbound call operation to the second identifier based on the tone type and communication strategy.

[0139] The present invention realizes active control of the outbound call operation of the intelligent robot through the outbound call system, standardizes some manual operations, and achieves a significant improvement in resource utilization.

[0140] The following describes the outbound calling device provided by the embodiment of the present disclosure. The outbound calling device described below and the outbound calling method described above can be referred to each other, and the repeated parts will not be repeated. Figure 5 As shown, the device includes:

[0141] A sorting module 501 is configured to, when the current working scenario is an outbound call scenario, sort the pending outbound call data corresponding to the first identifier to obtain an outbound call list, where the pending outbound call data includes the second identifier, and the first identifier and the second identifier indicate different user roles;

[0142] The sending module 502 is used to generate an outbound call instruction and send the outbound call instruction to the intelligent robot;

[0143] The outbound call instruction includes: a tone type of the first identifier and an outbound call list;

[0144] Among them, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and communication strategy, initiate an outbound call operation for the second identifier in the outbound call list.

[0145] In a specific embodiment, the sorting module 501 is specifically used to obtain the historical communication records corresponding to the second identifier in the outbound call data; based on the historical communication records, determine the outbound call success rate of each second identifier; based on the outbound call success rate, sort the second identifier in the outbound call data to obtain an outbound call list.

[0146] In a specific embodiment, the device also includes a first generation module for obtaining audio data corresponding to a first identifier; inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a timbre type corresponding to the target audio data; wherein the target audio data is speech corresponding to the timbre of the first identifier; wherein the speech generation model is trained through audio data samples, target audio data samples and timbre type samples.

[0147] In a specific embodiment, the first generation module is specifically used to input audio data into the feature extraction layer of the speech generation model to obtain the timbre features output by the feature extraction layer; input the timbre features into the speech generation layer of the speech generation model to obtain the target audio data output by the speech generation layer and the timbre type corresponding to the target audio data.

[0148] In a specific embodiment, the device also includes a second generation module for obtaining historical communication records corresponding to the second identifier in the outbound call data; determining the behavioral characteristics corresponding to the second identifier based on the historical communication records; generating a communication strategy corresponding to the behavioral characteristics, and sending the communication strategy to the intelligent robot.

[0149] The following describes the outbound calling device provided by the embodiment of the present disclosure. The outbound calling device described below and the outbound calling method described above can be referred to each other, and the repeated parts will not be repeated. Figure 6 As shown, the device includes:

[0150] The receiving module 601 is configured to receive an outbound call instruction sent by a server, wherein the outbound call instruction includes: a tone type of a first identifier and an outbound call list;

[0151] An acquisition module 602 is configured to acquire a communication strategy corresponding to a second identifier in the outbound call list, wherein the first identifier and the second identifier indicate different user roles;

[0152] The outbound calling module 603 is configured to initiate an outbound calling operation for the second identifier in the outbound calling list based on the tone type and the communication strategy.

[0153] In a specific embodiment, the acquisition module 602 is also used to receive the communication strategy sent by the server; based on the second identifier corresponding to the communication strategy, the communication strategy is stored in the node of the multi-branch tree; the acquisition module 602 is specifically used to determine the target node from the multi-branch tree based on the second identifier in the outbound call list, and obtain the communication strategy from the target node.

[0154] In a specific embodiment, the acquisition module 602 is specifically used to determine the initial target node based on the second identifier in the outbound call list, and obtain the initial communication strategy from the initial target node; the outbound call module 603 is specifically used to initiate an outbound call operation for the second identifier based on the tone type and the initial communication strategy; the outbound call module 603 is also used to obtain the current communication record corresponding to the second identifier; based on the current communication record, determine the current target node from the multi-branch tree, obtain the current communication strategy from the current target node, and play the obtained current communication strategy.

[0155] In a specific embodiment, the device also includes a recommendation module for obtaining a current communication record corresponding to the second identifier when the current work scene is a manual work scene; based on the current communication record, determining the current target node from the multi-branch tree, obtaining the current communication strategy from the current target node, and recommending the current communication strategy to the first identifier.

[0156] The embodiment of the present disclosure further provides a server, which is used to implement the outbound calling method applied to the server as described in any of the above embodiments.

[0157] An embodiment of the present disclosure further provides an intelligent robot, which includes a robot body and a controller, wherein the controller is used to implement the outbound calling method applied to the intelligent robot as described in any of the above embodiments.

[0158] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor (processor) 701, a communication interface (Communications Interface) 702, a memory (memory) 703 and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704. The processor 701 can call the logical instructions in the memory 703 to execute an outbound call method applied to the server, the method including: when the current working scene is an outbound call scene, sorting the outbound call data corresponding to the first identifier to obtain an outbound call list, the outbound call data including the second identifier, the first identifier and the second identifier indicating different user roles; generating an outbound call instruction, and sending the outbound call instruction to the intelligent robot; wherein the outbound call instruction includes: the tone type and the outbound call list of the first identifier; wherein the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiating an outbound call operation for the second identifier in the outbound call list, or, executing an outbound call method applied to the intelligent robot, the method including: receiving the outbound call instruction sent by the server, the outbound call instruction includes: the tone type and the outbound call list of the first identifier; obtaining the communication strategy corresponding to the second identifier in the outbound call list, the first identifier and the second identifier indicating different user roles; based on the tone type and the communication strategy, initiating an outbound call operation for the second identifier in the outbound call list.

[0159] In addition, the logic instructions in the above-mentioned memory 703 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, 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.

[0160] On the other hand, the present disclosure also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the outbound call method applied to the server provided by the above methods, the method including: when the current working scene is an outbound call scene, sorting the outbound call data corresponding to the first identifier to obtain an outbound call list, the outbound call data including a second identifier, the first identifier and the second identifier indicating different user roles; generating an outbound call instruction, and sending the outbound call instruction to an intelligent robot; wherein the outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiating an outbound call operation for the second identifier in the outbound call list.

[0161] On the other hand, the present disclosure also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned outbound call methods applied to the server, the method comprising: when the current working scenario is an outbound call scenario, sorting the outbound call data corresponding to the first identifier to obtain an outbound call list, the outbound call data including a second identifier, the first identifier and the second identifier indicating different user roles; generating an outbound call instruction, and sending the outbound call instruction to an intelligent robot; wherein the outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein the outbound call instruction is used to instruct the intelligent robot to obtain a communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiating an outbound call operation for the second identifier in the outbound call list.

[0162] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0163] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure.

Claims

1. An outbound calling method, characterized in that: Applied to a server, the method includes: When the current working scenario is an outbound call scenario, sorting the outbound call data corresponding to the first identifier to obtain an outbound call list, wherein the outbound call data includes the second identifier, and the first identifier and the second identifier indicate different user roles; Generate an outbound call instruction and send the outbound call instruction to the intelligent robot; The outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiate an outbound call operation to the user corresponding to the second identifier in the outbound call list; wherein, the communication strategy corresponds to the user's behavioral characteristics; the behavioral characteristics are determined based on the historical communication records corresponding to the second identifier in the outbound call data; the communication strategy includes specific communication words and communication types with the corresponding customers, and the communication types include pressure types and soothing types; wherein different communication types are pre-matched with corresponding intonations, and the intelligent robot uses the tone type and specific communication words corresponding to the customer service and the intonation corresponding to the customer to make outbound calls; the historical communication records also include: communication attitude score, communication statement score and customer's communication speech quality score, and the behavioral characteristics corresponding to the second identifier are determined based on the communication attitude score, the communication statement score and the customer's communication speech quality score.

2. The outbound calling method according to claim 1, characterized in that: The step of sorting the outbound call data corresponding to the first identifier to obtain an outbound call list includes: Obtaining a historical communication record corresponding to the second identifier in the pending outbound call data; Determining, based on the historical communication records, an outbound call success rate of the user corresponding to each second identifier; Based on the outbound call success rate, the second identifiers in the pending outbound call data are sorted to obtain the outbound call list.

3. The outbound calling method according to claim 1, characterized in that: Before generating the outbound call instruction, the method further includes: Obtaining audio data corresponding to the first identifier; Inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a timbre type corresponding to the target audio data; The target audio data is a voice corresponding to the timbre of the user corresponding to the first identifier; The speech generation model is obtained by training audio data samples, target audio data samples and timbre type samples.

4. The outbound calling method according to claim 3, characterized in that: The step of inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a timbre type corresponding to the target audio data includes: Inputting the audio data into the feature extraction layer of the speech generation model to obtain the timbre features output by the feature extraction layer; The timbre feature is input into the speech generation layer of the speech generation model to obtain the target audio data output by the speech generation layer and the timbre type corresponding to the target audio data.

5. The outbound calling method according to any one of claims 1 to 4, characterized in that: Before generating the outbound call instruction, the method further includes: Obtaining a historical communication record corresponding to the second identifier in the pending outbound call data; determining, based on the historical communication records, a behavioral characteristic of the user corresponding to the second identifier; Generate a communication strategy corresponding to the behavioral characteristics, and send the communication strategy to the intelligent robot.

6. An outbound calling method, characterized in that: Applied to an intelligent robot, the method includes: receiving an outbound call instruction sent by a server, wherein the outbound call instruction includes: a tone type of a first identifier and an outbound call list; Obtaining a communication strategy corresponding to a second identifier in the outbound call list, wherein the first identifier and the second identifier indicate different user roles; wherein the communication strategy corresponds to a user's behavioral characteristics; the behavioral characteristics are determined based on historical communication records corresponding to the second identifier in the pending outbound call data; the communication strategy includes specific communication techniques and communication types with the corresponding customer, wherein the communication types include pressure-based and soothing types; Based on the tone type and the communication strategy, an outbound call operation is initiated to the user corresponding to the second identifier in the outbound call list; wherein, different communication types are pre-matched with corresponding intonations, and the intelligent robot uses the tone type and specific communication language corresponding to the customer service and the intonation corresponding to the customer to make outbound calls; the historical communication records also include: a communication attitude score, a communication statement score and the customer's communication speech quality score, and the behavioral characteristics corresponding to the second identifier are determined based on the communication attitude score, the communication statement score and the customer's communication speech quality score.

7. The outbound calling method according to claim 6, characterized in that: Before acquiring the communication strategy corresponding to the second identifier in the outbound call list, the method further includes: receiving a communication strategy sent by the server; Based on the second identifier corresponding to the communication strategy, storing the communication strategy in a node of the multi-branch tree; The acquiring of the communication strategy corresponding to the second identifier in the outbound call list includes: Based on the second identifier in the outbound call list, a target node is determined from the multi-branch tree, and the communication strategy is obtained from the target node.

8. The outbound calling method according to claim 7, characterized in that: The determining a target node from the multi-branch tree based on the second identifier in the outbound call list, and acquiring the communication strategy from the target node includes: determining an initial target node based on a second identifier in the outbound call list, and obtaining an initial communication strategy from the initial target node; The initiating an outbound call operation for the second identifier in the outbound call list based on the timbre type and the communication strategy includes: Initiating an outbound call operation to the user corresponding to the second identifier based on the tone type and the initial communication strategy; After initiating an outbound call operation for the second identifier based on the tone type and the initial communication strategy, the method further includes: Obtaining a current communication record corresponding to the second identifier; Based on the current communication record, a current target node is determined from the multi-branch tree, a current communication strategy is obtained from the current target node, and the obtained current communication strategy is played.

9. The outbound calling method according to any one of claims 6 to 8, characterized in that: The method further comprises: When the current working scene is a manual working scene, obtaining a current communication record corresponding to the second identifier; Based on the current communication record, a current target node is determined from the multi-branch tree, a current communication strategy is obtained from the current target node, and the current communication strategy is recommended to the user corresponding to the first identifier.

10. An outbound calling device, characterized in that: include: a sorting module, configured to, when the current working scenario is an outbound call scenario, sort the pending outbound call data corresponding to the first identifier to obtain an outbound call list, wherein the pending outbound call data includes the second identifier, and the first identifier and the second identifier indicate different user roles; A sending module, configured to generate an outbound call instruction and send the outbound call instruction to the intelligent robot; The outbound call instruction includes: the tone type of the first identifier and the outbound call list; wherein, the outbound call instruction is used to instruct the intelligent robot to obtain the communication strategy corresponding to the second identifier in the outbound call list; based on the tone type and the communication strategy, initiate an outbound call operation to the user corresponding to the second identifier in the outbound call list; wherein, the communication strategy corresponds to the user's behavioral characteristics; the behavioral characteristics are determined based on the historical communication records corresponding to the second identifier in the outbound call data; the communication strategy includes specific communication words and communication types with the corresponding customers, and the communication types include pressure types and soothing types; wherein different communication types are pre-matched with corresponding intonations, and the intelligent robot uses the tone type and specific communication words corresponding to the customer service and the intonation corresponding to the customer to make outbound calls; the historical communication records also include: communication attitude score, communication statement score and customer's communication speech quality score, and the behavioral characteristics corresponding to the second identifier are determined based on the communication attitude score, the communication statement score and the customer's communication speech quality score.

11. An outbound calling device, characterized in that: include: A receiving module, configured to receive an outbound call instruction sent by a server, wherein the outbound call instruction includes: a tone type of a first identifier and an outbound call list; an acquisition module, configured to acquire a communication strategy corresponding to a second identifier in the outbound call list, wherein the first identifier and the second identifier indicate different user roles; wherein the communication strategy corresponds to a user's behavioral characteristics; the behavioral characteristics are determined based on historical communication records corresponding to the second identifier in the pending outbound call data; the communication strategy includes specific communication techniques and communication types with the corresponding customer, wherein the communication types include pressure-based and soothing types; An outbound call module is used to initiate an outbound call operation to the user corresponding to the second identifier in the outbound call list based on the tone type and the communication strategy; wherein different communication types are pre-matched with corresponding intonations, and the intelligent robot uses the tone type and specific communication words corresponding to the customer service and the intonation corresponding to the customer to make outbound calls; the historical communication records also include: a communication attitude score, a communication statement score and the customer's communication speech quality score, and the behavioral characteristics corresponding to the second identifier are determined based on the communication attitude score, the communication statement score and the customer's communication speech quality score.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the outbound calling method according to any one of claims 1 to 5 is implemented.

13. A server, characterized in that: Used to implement the outbound calling method as described in any one of claims 1 to 5.

14. An intelligent robot, characterized in that: It comprises a robot body and a controller, and the controller is used to implement the outbound calling method according to any one of claims 6 to 9.

Images