Voice information generation method and device of intelligent robot, electronic equipment and medium

Abstract

The invention provides a voice information generation method and device of an intelligent robot, electronic equipment and a medium, and relates to the field of robot telephone communication, and the method comprises the steps: obtaining a to-be-processed case list of the intelligent robot, the case list comprising a plurality of target cases and target stages and case attributes of the corresponding target cases; for any target case, determining a target communication template corresponding to a target stage of the target case based on a corresponding relationship between different configured case stages and different communication templates; determining actual information corresponding to the variable information based on the case attribute, and determining a verbal skill instance according to the actual information and the fixed information; and according to the case attribute, processing the verbal skill instance, and generating voice information of the intelligent robot, so that the intelligent robot communicates with a communication object in the case attribute according to the voice information and the verbal skill instance. The outbound communication quality of the intelligent robot can be improved, and the hang-up rate of the communication object can be reduced at the same time.

Description

Technical Field

[0001] The present application relates to the field of robot telephone communication, and more specifically, to a method, device, electronic equipment and medium for generating voice information of an intelligent robot. Background Art

[0002] More and more outbound intelligent robots have been put into practice in real business scenarios, and the market feedback has been good, replacing a large amount of manpower. However, in the existing technology, the question-and-answer response mode of intelligent robots is still based on fixed template configuration. Although the convenient front-end visual interface allows the configuration of multiple templates, in a conversation, only one template can usually be enabled. This results in a rigid interaction between the intelligent robot and the communication object, and the intelligent robot cannot adjust its own speech or question-and-answer strategy according to the emotional state of the communication object. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method for generating voice information of an intelligent robot, an apparatus electronic device and a medium, so as to solve the above-mentioned problems existing in the prior art and improve the quality of outbound calls of the intelligent robot.

[0004] In a first aspect, a method for generating voice information of an intelligent robot is provided, and the method may include: Obtaining a list of cases to be processed by the intelligent robot, wherein the list of cases includes a plurality of target cases and target stages and case attributes of the corresponding target cases; For any target case, based on the correspondence between different case stages and different communication templates, determine the target communication template corresponding to the target stage of the target case; the target communication template includes variable information and fixed information; Based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; According to the case attributes, the speech instance is processed to generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information includes timbre and volume.

[0005] In a possible implementation, the configuration process of the correspondence between different case stages and different communication templates includes: Obtain the communication completion rates of multiple different historical communication templates corresponding to each historical case stage within the configured historical period; For any historical case stage, the historical communication template corresponding to the maximum communication completion rate among multiple communication completion rates of the historical case stage is determined as the target historical communication template of the historical case stage; Based on the correspondence between each historical case stage and the corresponding target historical communication template, the correspondence between different case stages and different communication templates is determined.

[0006] In a possible implementation, after determining the voice information of the intelligent robot, the method further includes: Dividing the speech instance to determine multiple sub-contents and the communication order of the multiple sub-contents; When the intelligent robot communicates with the communication object in the case attribute according to the current sub-content, obtaining first feedback information from the communication object; A target sub-content among the multiple sub-contents is determined according to the first feedback information.

[0007] In a possible implementation, determining a target sub-content among multiple sub-contents according to the first feedback information includes: The first feedback information is processed by a configured preset ASR model to determine a feedback type corresponding to the first feedback information: If the feedback type is interest and the current sub-content has not been fully communicated, the current sub-content is determined as the target sub-content; If the feedback type is interest and the current sub-content has been communicated, then the next sub-content of the current sub-content is determined as the target sub-content according to the communication sequence of the multiple sub-contents.

[0008] In a possible implementation, determining the feedback type corresponding to the first feedback information further includes: If the feedback type is disinterest, determining a target level of disinterest; According to the correspondence between different levels of configuration and different soothing information, the target soothing information corresponding to the target level is determined, so that the intelligent robot communicates with the communication object according to the target soothing information.

[0009] In a possible implementation, after determining the target appeasement information corresponding to the target level, the method further includes: Obtaining second feedback information after the intelligent robot communicates with the communication object according to the target comforting information; determining the communication intention of the communication object according to the second feedback information; If the communication intention is to continue communication, a sub-content that is not related to the current sub-content is determined as a target sub-content among the multiple sub-contents.

[0010] In a possible implementation, determining the communication intention of the communication object further includes: If the communication intention is to refuse communication, then an end communication template corresponding to the refusal of communication is determined, so that the intelligent robot ends the communication according to the end communication template.

[0011] In a second aspect, a voice information generating device for an intelligent robot is provided, and the device may include: An acquisition unit, used to acquire a list of cases to be processed by the intelligent robot, wherein the list of cases includes a plurality of target cases and target stages and case attributes of the corresponding target cases; A determination unit, for determining, for any target case, a target communication template corresponding to the target stage of the target case based on the configured correspondence between different case stages and different communication templates; the target communication template includes variable information and fixed information; And, based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; A generation unit is used to process the speech instance according to the case attributes and generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information includes timbre and volume.

[0012] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0013] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0014] The present application provides a method for generating voice information of an intelligent robot, the method comprising: obtaining a list of cases to be processed by the intelligent robot, the list of cases comprising multiple target cases and the target stages and case attributes of the corresponding target cases; for any target case, based on the correspondence between the configured different case stages and different communication templates, determining the target communication template corresponding to the target stage of the target case; the target communication template comprises variable information and fixed information; based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; according to the case attributes, processing the speech instance, generating the voice information of the intelligent robot, so that the intelligent robot communicates with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information comprises timbre and volume. The present application can improve the communication quality of the outbound call of the intelligent robot while reducing the hang-up rate of the communication object. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A system architecture diagram of a method for generating voice information applied to an intelligent robot provided in an embodiment of the present application; Figure 2 A flowchart of a method for generating voice information of an intelligent robot provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a voice information generating device for an intelligent robot provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] The method for generating voice information of an intelligent robot provided in the embodiment of the present application can be applied in Figure 1 In the system architecture shown in Figure 1As shown, the system may include: a terminal, a server and an intelligent robot. The server may be a physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal may be a user equipment (UE) such as a mobile phone, smart phone, laptop, digital broadcast receiver, personal digital assistant (PDA), tablet computer (PAD), handheld device, vehicle-mounted device, wearable device, computing device or other processing device connected to a wireless modem, mobile station (MS), mobile terminal, etc. The terminal and the server may be directly or indirectly connected via wired or wireless communication, which is not limited in this application.

[0019] The terminal is used to obtain a list of cases to be processed and send the list of cases to the server.

[0020] The server is used to obtain the list of pending cases sent by the terminal to execute a method for generating voice information of an intelligent robot provided in the present application, and send the generated voice information to the controller of the intelligent robot.

[0021] The controller of the intelligent robot is used to control the intelligent robot to communicate with the communication object according to voice information.

[0022] More and more outbound intelligent robots have been put into practice in real business scenarios, and the market feedback has been good, replacing a large amount of manpower. However, in the existing technology, the question-and-answer response mode of intelligent robots is still based on fixed template configuration. Although the convenient front-end visual interface allows the configuration of multiple templates, in a conversation, only one template can usually be enabled. This results in a rigid interaction between the intelligent robot and the communication object, and the intelligent robot cannot adjust its own speech or question-and-answer strategy according to the emotional state of the communication object.

[0023] Therefore, the present application provides a method for generating voice information of an intelligent robot, which is used to solve the above-mentioned problems existing in the prior art and can improve the quality of outbound calls of the intelligent robot.

[0024] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0025] Figure 2 The following is a flow chart of a method for generating voice information of an intelligent robot provided in an embodiment of the present application. Figure 2 As shown, the method may include: Step S210: Obtain a list of cases to be processed by the intelligent robot.

[0026] The case list includes multiple target cases and the target stages and case attributes of the corresponding target cases.

[0027] The case attributes include case category, the communication party's phone number, the location of the phone number, the communication party's gender, age and other information.

[0028] Specifically, the case list includes multiple pending target cases of the same category, and the target stages of the pending target cases may be the same or different.

[0029] Step S220: For any target case, based on the configured correspondence between different case stages and different communication templates, determine the target communication template corresponding to the target stage of the target case.

[0030] Specifically, before executing step S220, the method further includes: Configure the correspondence between different case stages and different communication templates. Specifically, it can be: Obtaining the communication completion rates of multiple different historical communication templates corresponding to each historical case stage of historical cases within a configured historical period; For any historical case stage, the historical communication template corresponding to the maximum communication completion rate among multiple communication completion rates of the historical case stage is determined as the target historical communication template of the historical case stage; Based on the correspondence between each historical case stage and the corresponding target historical communication template, the correspondence between different case stages and different communication templates is determined.

[0031] It should be noted that historical cases and target cases are cases of the same category. That is, the correspondence between different case stages and different communication templates of target cases of the same category is determined.

[0032] In some embodiments, different case stages may correspond to multiple communication templates, which are templates for different scenarios when the communication object is answering the phone. For example, when the communication object is driving a vehicle when answering the phone, one communication template may correspond to it. When the communication object is in a meeting when answering the phone, another communication template may correspond to it.

[0033] Furthermore, the communication template includes variable information and fixed information. Variable information can be understood as information that changes with the attributes of the case; fixed information is fixed information. Variable information can also be information generated in real time during the communication process with the communication object, such as the address, mobile phone number, mood, gender, etc. mentioned by the communication object.

[0034] Afterwards, the target communication template corresponding to the target stage of the target case can be determined based on the configured correspondence between different case stages and different communication templates.

[0035] It is understandable that the target communication template also includes variable information and fixed information.

[0036] The communication template may be composed of multiple sub-templates, and the combination of the communication templates may be determined according to the communication completion rate. The completion rate includes the sub-template completion rate and the communication template completion rate, and the new combination with the highest overall completion rate is selected as the new communication template.

[0037] Template update mechanism: Real-time data collection: During the communication process between the intelligent robot and the communication object, data is collected in real time, including feedback information from the communication object, communication time, number of successful communications, etc.

[0038] Data preprocessing: Clean and annotate the collected data, remove invalid data and noise data, and perform word segmentation and part-of-speech tagging on the text data.

[0039] Model update: Build a machine learning-based model, such as a reinforcement learning model, which will dynamically adjust the correspondence between different case stages and communication templates based on real-time collected data. The goal of the model is to optimize communication effectiveness and improve communication completion and success rates. Using incremental learning technology, as new data is continuously collected, the model can be updated online in real time, rather than waiting for a large amount of data to accumulate before offline training.

[0040] Template evaluation mechanism: Communication completion rate calculation: For each communication template, calculate its communication completion rate, including the sub-template completion rate and the overall communication template completion rate. The communication completion rate can be calculated using the following formula: Communication completion rate = number of successful communications / total number of communications; Sub-template evaluation: For each sub-template, calculate its sub-template completion rate, and evaluate and sort the sub-templates according to the sub-template completion rate. The sub-template completion rate can be calculated using the following formula: Sub-template completion rate = number of successful sub-template communications / total number of sub-template communications.

[0041] Template combination evaluation: For different template combinations, calculate their overall communication completion rate, and evaluate and sort the template combinations based on the overall communication completion rate. The overall communication completion rate can be calculated using the following formula: Overall communication completion rate = overall number of successful communications / overall total number of communications; Template optimization mechanism: Select the best combination: Based on the overall communication completion rate, select the new combination with the highest overall completion rate as the new communication template. If the overall communication completion rates of multiple combinations are similar, other factors such as communication efficiency and communication object satisfaction can be considered for comprehensive evaluation and selection.

[0042] Sub-template optimization: Optimize sub-templates based on their completion rates. Sub-templates with low completion rates can be modified and adjusted, such as adjusting the content, tone, and sequence of the sub-template to improve their completion rates.

[0043] Template combination optimization: Optimize the template combination method based on the template combination evaluation results. You can try different combination methods, such as adjusting the order of sub-templates, adding or reducing sub-templates, etc., to improve the overall communication completion rate.

[0044] Template diversity maintenance: Diversity assessment: Regularly assess the diversity of communication templates to ensure the diversity of the template set. Diversity metrics such as the similarity between templates and the range of scenarios covered by templates can be used for assessment.

[0045] Diversity optimization: If the template set is not diverse enough, you can take the following measures to optimize it: Introduce new templates: Introduce new communication templates from other case categories or scenarios to increase the diversity of the template set.

[0046] Template mutation: Perform mutation operations on existing templates, such as randomly adjusting the content, tone, order, etc. of the template to generate a new template.

[0047] Template combination mutation: Perform mutation operations on the template combination method, such as randomly adjusting the order of sub-templates, adding or reducing sub-templates, etc., to generate new template combinations.

[0048] In order to increase the richness of samples, random parameters can be introduced when combining templates to randomly select sub-templates with higher scores or newly optimized sub-templates. The following is a specific solution: Sub-template rating: Each sub-template is scored based on indicators such as the completion rate of the sub-template, communication efficiency, and satisfaction of the communication object.

[0049] The sub-template score can be calculated using the following formula: Sub-template score = w1 × sub-template completion rate + w2 × communication efficiency + w3 × communication object satisfaction; Among them, w1, w2, and w3 are weight coefficients.

[0050] Random Selection: When combining templates, a random parameter α is introduced, and the value range of α is [0, 1].

[0051] According to the value of α, a sub-template is randomly selected: When α is small (e.g., α < 0.3), sub-templates with higher scores tend to be selected.

[0052] When α is large (e.g. α>0.7), the newly optimized sub-template tends to be selected.

[0053] When α is in the middle range (e.g., 0.3≤α≤0.7), a sub-template with a higher score or a newly optimized one is randomly selected.

[0054] Dynamic adjustment of random parameters: The random parameter α can be dynamically adjusted according to time or the number of communications. For example, as the number of communications increases, the value of α is gradually increased to increase the probability of selecting a new optimized sub-template.

[0055] The dynamic adjustment of α can be achieved by the following formula: α=α0+β*t Among them, α0 is the initial value, β is the adjustment coefficient, and t is the time or number of communications.

[0056] The score is calculated for each sub-template, and the scoring formula is as described above.

[0057] Generate a random parameter α, the value range of α is [0, 1].

[0058] According to the value of α, select the sub-template: When α < 0.3, the sub-template with the highest score is selected.

[0059] When α>0.7, a new optimized sub-template is selected.

[0060] When 0.3≤α≤0.7, a sub-template with a higher score or a newly optimized one is randomly selected.

[0061] Based on the selected sub-templates, a new communication template is combined.

[0062] The template combination method is updated according to the communication completion rate of the new communication template. If the communication completion rate of the new combination method is higher, it is used as the new communication template.

[0063] Step S230: Based on the case attributes, determine the actual information corresponding to the variable information, and determine the speech instance based on the actual information and the fixed information.

[0064] Specifically, according to the information of the communication object in the case attributes of the target case, the actual information corresponding to the variable information in the target communication template is determined. For example, if the communication object in the case attributes of the target case works at a school and the communication object is Mr. Li, then the actual information corresponding to the address variable in the target communication template is determined to be: Mr. Li.

[0065] In some embodiments, a greeting corresponding to the outbound call time may be added before the salutation variable according to the outbound call time; for example: Good morning, Mr. Li.

[0066] Afterwards, based on the confirmed actual information and fixed information, determine the speech examples for this communication with the corresponding communication object.

[0067] It should be noted that what is currently determined is not a single speech instance. As mentioned above, one case stage can correspond to multiple communication templates. Therefore, the determined speech instances are also multiple speech instances in different scenarios.

[0068] Step S240: Process the dialogue instance according to the case attributes to generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the dialogue instance.

[0069] Among them, voice information includes timbre and volume.

[0070] Before executing step S240, the method may further include: Using TTS (Text-to-Speech) technology, different voices are generated, and each voice is configured with a corresponding volume range.

[0071] Step S240 specifically includes: when the case category in the case attributes is product promotion, the timbre of the voice information of the intelligent robot can be determined as mature and stable.

[0072] When the case category in the case attributes is customer service, the tone of the intelligent robot's voice message can be determined to be cordial and friendly.

[0073] When the case category in the case attributes is business communication or professional consulting services, the timbre of the intelligent robot's voice information can be determined to be professional and formal.

[0074] After the corresponding timbre is determined, the current volume interval corresponding to the current timbre is determined according to the corresponding relationship between the configured different timbres and the different volume intervals.

[0075] It should be noted that when an outbound call is connected, the volume of the intelligent robot communicating with the communication object is determined within the volume range based on the background volume of the communication object.

[0076] In some embodiments, the background sound is environmental noise, and when the background volume reaches a preset background volume, the starting volume is adjusted according to the configured adjustment range to determine the current communication volume to ensure that the communication object can clearly hear the voice of the intelligent robot. The starting volume can be the middle value of the volume range.

[0077] When the background volume does not reach the preset background volume during quiet periods such as morning and evening, the communication object is communicated with at the lowest value of the volume range; when the communication object's feedback cannot be heard clearly, the lowest value of the volume range is adjusted according to the configured adjustment range to determine the current communication volume to ensure that the communication object can clearly hear the voice of the intelligent robot.

[0078] It should be noted that the current volume is adjusted at any time according to the actual situation during the overall process of communication between the intelligent robot and the communication object.

[0079] After determining the voice information of the intelligent robot, the method further includes: Divide the dialogue instance to determine multiple sub-contents and the communication order of multiple sub-contents; When the intelligent robot communicates with the communication object in the case attributes according to the current sub-content, obtaining the first feedback information of the communication object; According to the first feedback information, a target sub-content among the multiple sub-contents is determined. Specifically, the first feedback information is processed by a configured preset ASR model to determine the feedback type corresponding to the first feedback information: if the feedback type is interested and the current sub-content has not been communicated, the current sub-content is determined as the target sub-content; that is, the current sub-content continues to be communicated.

[0080] If the feedback type is interested and the current sub-content has been communicated, the next sub-content of the current sub-content is determined as the target sub-content according to the communication order of the multiple sub-contents.

[0081] If the feedback type is not interested, determine the target level of not interested; specifically, determine the target text corresponding to the first feedback information of the communication object; and determine the target level corresponding to the target text according to the configured correspondence between different not interested texts and different levels.

[0082] According to the correspondence between different levels of configuration and different soothing information, the target soothing information corresponding to the target level is determined, so that the intelligent robot communicates with the communication object according to the target soothing information.

[0083] Afterwards, obtaining second feedback information after the intelligent robot communicates with the communication object according to the target comforting information; Determining the communication intention of the communication object according to the second feedback information; For example: when the intelligent robot asks some questions related to personal information, and the first feedback information of the communication object indicates that the feedback type is not interested or unwilling to answer such questions, in some embodiments, the target level can be determined according to the tone in the first feedback information, thereby determining the corresponding soothing information; after the intelligent robot communicates with the communication object according to the soothing information, it obtains the second feedback information, that is, according to the second feedback information, determines the communication willingness of the communication object.

[0084] If the communication intention is to continue the communication, a sub-content that is not related to the current sub-content is determined as a target sub-content among the multiple sub-contents.

[0085] If the communication intention is to refuse communication, then the communication ending template corresponding to the communication rejection is determined, so that the intelligent robot ends the communication according to the communication ending template.

[0086] In some embodiments, the determination of communication intention or feedback type after using a model to analyze natural language may be affected by the differences in languages ​​of different regions, resulting in inaccurate results. At this time, the preset ASR model involves different languages ​​(dialects) from different regions, so as to determine the region to which the language of the communication object belongs, and the first feedback information and the second feedback information can be analyzed based on the region to which they belong.

[0087] That is to say, a data set containing different cultural customs and etiquette is established in the preset ASR model, so that the intelligent robot can make appropriate responses in different cultural backgrounds. In simple terms, the first feedback information and / or the second feedback information of the communication object is converted into text according to different local dialects through the preset ASR model to obtain accurate text information.

[0088] Similarly, cultural markers can be added to speech instances based on case attributes so that the preset ASR model can better recognize and process speech instances.

[0089] In some embodiments, in order to ensure the security of all voice data, that is, the first feedback information and / or the second feedback information of the communication object during processing by the preset ASR model, an encryption mechanism is added to the preset ASR model to prevent data leakage.

[0090] The present application provides a method for generating voice information of an intelligent robot, the method comprising: obtaining a list of cases to be processed by the intelligent robot, the list of cases comprising multiple target cases and the target stages and case attributes of the corresponding target cases; for any target case, based on the correspondence between the configured different case stages and different communication templates, determining the target communication template corresponding to the target stage of the target case; the target communication template comprises variable information and fixed information; based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; according to the case attributes, processing the speech instance, generating the voice information of the intelligent robot, so that the intelligent robot communicates with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information comprises timbre and volume. The present application can improve the communication quality of the outbound call of the intelligent robot while reducing the hang-up rate of the communication object.

[0091] Corresponding to the above method, the embodiment of the present application also provides a voice information generating device for an intelligent robot, such as Figure 3 As shown, the device comprises: An acquisition unit 310 is used to acquire a list of cases to be processed by the intelligent robot, wherein the list of cases includes a plurality of target cases and target stages and case attributes of the corresponding target cases; The determination unit 320 is used to determine, for any target case, a target communication template corresponding to the target stage of the target case based on the configured correspondence between different case stages and different communication templates; the target communication template includes variable information and fixed information; And, based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; The generation unit 330 is used to process the speech instance according to the case attributes and generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information includes timbre and volume.

[0092] The functions of the various functional units of the voice information generating device of an intelligent robot provided in the above-mentioned embodiment of the present application can be realized through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the voice information generating device of an intelligent robot provided in the embodiment of the present application will not be repeated here.

[0093] The present application also provides an electronic device, such as Figure 4As shown, it includes a processor 410 , a communication interface 420 , a memory 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other via the communication bus 440 .

[0094] Memory 430, for storing computer programs; The processor 410 is used to execute the program stored in the memory 430 to implement the following steps: Obtaining a list of cases to be processed by the intelligent robot, wherein the list of cases includes a plurality of target cases and target stages and case attributes of the corresponding target cases; For any target case, based on the correspondence between different case stages and different communication templates, determine the target communication template corresponding to the target stage of the target case; the target communication template includes variable information and fixed information; Based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; According to the case attributes, the speech instance is processed to generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information includes timbre and volume.

[0095] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0096] The communication interface is used for communication between the above electronic device and other devices.

[0097] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0098] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0099] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 2 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0100] In another embodiment provided in the present application, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes a method for generating voice information of an intelligent robot as described in any of the above embodiments.

[0101] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute a method for generating voice information of an intelligent robot as described in any one of the above embodiments.

[0102] Those skilled in the art will appreciate that the embodiments in the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments in the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments in the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0103] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which the present invention belongs. "First", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect", "couple" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0107] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the present application embodiments are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application embodiments.

[0108] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application are within the scope of the embodiments in the present application and their equivalents, the embodiments in the present application are also intended to include these modifications and variations.

Claims

1. A method for generating voice information of an intelligent robot, characterized in that: The method comprises: Obtaining a list of cases to be processed by the intelligent robot, wherein the list of cases includes a plurality of target cases and target stages and case attributes of the corresponding target cases; For any target case, based on the correspondence between different case stages and different communication templates, determine the target communication template corresponding to the target stage of the target case; the target communication template includes variable information and fixed information; Based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; According to the case attributes, the speech instance is processed to generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information includes timbre and volume.

2. The method according to claim 1, characterized in that The configuration process of the correspondence between different case stages and different communication templates includes: Obtain the communication completion rates of multiple different historical communication templates corresponding to each historical case stage within the configured historical period; For any historical case stage, the historical communication template corresponding to the maximum communication completion rate among multiple communication completion rates of the historical case stage is determined as the target historical communication template of the historical case stage; Based on the correspondence between each historical case stage and the corresponding target historical communication template, the correspondence between different case stages and different communication templates is determined.

3. The method according to claim 1, characterized in that After determining the voice information of the intelligent robot, the method further includes: Dividing the speech instance to determine multiple sub-contents and the communication order of the multiple sub-contents; When the intelligent robot communicates with the communication object in the case attribute according to the current sub-content, obtaining first feedback information from the communication object; A target sub-content among the multiple sub-contents is determined according to the first feedback information.

4. The method according to claim 3, characterized in that Determining a target sub-content among the multiple sub-contents according to the first feedback information includes: The first feedback information is processed by a configured preset ASR model to determine a feedback type corresponding to the first feedback information: If the feedback type is interest and the current sub-content has not been fully communicated, the current sub-content is determined as the target sub-content; If the feedback type is interest and the current sub-content has been communicated, then the next sub-content of the current sub-content is determined as the target sub-content according to the communication sequence of the multiple sub-contents.

5. The method according to claim 4, characterized in that Determining the feedback type corresponding to the first feedback information further includes: If the feedback type is disinterest, determining a target level of disinterest; According to the correspondence between different levels of configuration and different soothing information, the target soothing information corresponding to the target level is determined, so that the intelligent robot communicates with the communication object according to the target soothing information.

6. The method according to claim 5, characterized in that After determining the target appeasement information corresponding to the target level, the method further includes: Obtaining second feedback information after the intelligent robot communicates with the communication object according to the target comforting information; determining the communication intention of the communication object according to the second feedback information; If the communication intention is to continue communication, a sub-content that is not related to the current sub-content is determined as a target sub-content among the multiple sub-contents.

7. The method according to claim 6, characterized in that Determine the communication object's communication willingness, including: If the communication intention is to refuse communication, then an end communication template corresponding to the refusal of communication is determined, so that the intelligent robot ends the communication according to the end communication template.

8. A voice information generating device for an intelligent robot, characterized in that: The device comprises: An acquisition unit, used to acquire a list of cases to be processed by the intelligent robot, wherein the list of cases includes a plurality of target cases and target stages and case attributes of the corresponding target cases; A determination unit, for determining, for any target case, a target communication template corresponding to the target stage of the target case based on the configured correspondence between different case stages and different communication templates; the target communication template includes variable information and fixed information; And, based on the case attributes, determining the actual information corresponding to the variable information, and determining the speech instance according to the actual information and the fixed information; A generation unit is used to process the speech instance according to the case attributes and generate voice information of the intelligent robot, so that the intelligent robot can communicate with the communication object in the case attributes according to the voice information and the speech instance; wherein the voice information includes timbre and volume.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.

Images