Voice interaction method, voice interaction device and electronic equipment
By obtaining historical consultation data, dividing the consultation age group and matching appropriate service methods, the problem of poor acceptance of consulting personnel of different age groups in intelligent robot services is solved, and the service quality and experience are improved.
Patent Information
- Application Number
- CN202411131043.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-26
AI Technical Summary
In the prior art, when intelligent robots provide services to customers, the service experience is poor due to the different acceptance of intelligent voice answering robots of consultants of different ages. The randomly allocated voice interaction method reduces service quality and wastes consultants. time.
By obtaining multiple historical consultation data, dividing the preset consultation age group, and determining the intelligent reception level based on the historical consultation information and preset procedures, matching the current consultant to the target consultation age group, using voice interaction methods of intelligent robots or manual services Improve service quality.
It improves the quality of consulting services, reduces the time waste of consulting personnel, and provides a better service experience.
Smart Images

Figure CN119031073A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a voice interaction method, a voice interaction device, a computer-readable storage medium, and an electronic device. Background Art
[0002] Enterprises use intelligent robots to provide consulting services to customers instead of human agents through voice interaction. They use traditional voice telephone systems combined with AI intelligent voice customer service robots to realize the call center virtual agent function. They use intelligent interaction, voice recognition and other technologies to provide call centers with complete AI intelligent voice services, realizing functions such as robot answering of calls, intelligent voice recognition of user needs, intelligent distribution and transfer, intelligent knowledge base consulting services, fault statistical analysis, etc., to achieve the goal of unmanned, automated and intelligent fault reporting.
[0003] However, when applying intelligent robots to interactive customer consulting services, since consultants of different age groups have different levels of acceptance of intelligent voice answering robots, the existing technology will randomly assign voice interaction methods when providing services to customers through intelligent robots. This random assignment will reduce the service quality, waste the consultant's time, and cause a bad service experience for the consultant.
[0004] Based on this, a voice interaction method is proposed to at least solve the problem that the voice interaction method in the prior art leads to poor service experience for consultants due to the different acceptance levels of consultants of different age groups to the intelligent voice answering robot. Summary of the invention
[0005] The main purpose of the present application is to provide a voice interaction method, a voice interaction device, a storage medium, a processor and an electronic device, so as to at least solve the problem that the voice interaction mode in the prior art leads to a poor service experience for consultants.
[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a voice interaction method is provided, including: obtaining historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultant information and historical consultation information, at least one historical consultant information corresponding to a preset consultation age group; determining the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program; obtaining the current consultant information corresponding to the current consultation; determining the target consultation age group according to the current consultant information and the preset consultation age group, the target consultation age group being one of multiple preset consultation age groups; determining the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group, the target reception level being the intelligent reception level corresponding to the target consultation age group, and the target voice interaction mode including: performing voice interaction with the current consultant using intelligent robots and manual services, or performing voice interaction with the current consultant using manual services.
[0007] Optionally, the preset program includes a first preset program and a second preset program, and determines the intelligent reception level corresponding to each preset consultation age group based on historical consultation information and the preset program, including: determining the target reception coefficient corresponding to each preset consultation age group based on historical consultation information and the first preset program; determining the intelligent reception level corresponding to each target reception coefficient based on the target reception coefficient and the second preset program.
[0008] Optionally, based on historical consultation information and a first preset program, a target reception coefficient corresponding to each preset consultation age group is determined, including: based on historical consultation information and a preset relationship, determining the year consultation duration and year consultation coefficient corresponding to each preset consultation age group; based on the year consultation duration and a preset formula, determining the target reception coefficient, the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the year consultation duration, and Xa is the year consultation coefficient.
[0009] Optionally, the preset relationship includes a first preset relationship and a second preset relationship, each preset consultation age group includes at least one first historical consultation among multiple historical consultations, and the historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation result. According to the historical consultation information and the preset relationship, the year consultation duration and year consultation coefficient corresponding to each preset consultation age group are determined, including: determining the year consultation duration corresponding to each preset consultation age group according to at least one historical consultation duration corresponding to at least one first historical consultation and the first preset relationship; determining the year consultation coefficient corresponding to each preset consultation age group according to at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship, and the historical consultation result includes one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
[0010] Optionally, based on at least one historical consultation duration corresponding to at least one first historical consultation and a first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: obtaining the standard deviation of at least one historical consultation duration corresponding to at least one first historical consultation; and determining the age consultation duration corresponding to each preset consultation age group based on the standard deviation and the first preset relationship.
[0011] Optionally, based on the standard deviation and the first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: judging whether the standard deviation is less than or equal to a first preset threshold value to obtain a first judgment result; when the first judgment result indicates yes, determining that the average of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration; when the first judgment result indicates no, determining that the average of the maximum and minimum values of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration.
[0012] Optionally, based on at least one historical consultation result corresponding to at least one first historical consultation and a second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined, including: obtaining the first number, the second number, and the third number in at least one first historical consultation, the first number being the number of successful consultations in at least one first historical consultation, the second number being the number of failed consultations in at least one first historical consultation, and the third number being the number of times at least one first historical consultation is transferred for manual processing; based on the first number, the second number, the third number, and the second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined.
[0013] According to another aspect of the present application, a voice interaction system is provided, including: a first acquisition module, used to acquire historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultant information and historical consultation information, at least one historical consultant information corresponds to a preset consultation age group; a first determination module, used to determine the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program; a second acquisition module, used to acquire the current consultant information corresponding to the current consultation; a second determination module, used to determine the target consultation age group according to the current consultant information and the preset consultation age group, the target consultation age group being one of multiple preset consultation age groups; a third determination module, used to determine the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group, the target reception level being the intelligent reception level corresponding to the target consultation age group, and the target voice interaction mode including using an intelligent robot and manual service to perform voice interaction with the current consultant or using manual service to perform voice interaction with the current consultant.
[0014] According to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the voice interaction methods.
[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the voice interaction methods.
[0016] By applying the technical solution of the present application, when obtaining historical consultation data corresponding to multiple historical consultations, different preset consultation age groups can be first divided according to the historical consultation personnel information in the historical consultation data, and then the intelligent reception level corresponding to each preset consultation age group can be determined according to the historical consultation information and preset program in each preset consultation age group. On this basis, since the current consultant information corresponding to the current consultation can be obtained when a new consultation occurs, and the current consultant information can be matched with the preset consultation age group, the current consultant corresponding to the current consultant information can be divided into the corresponding preset consultation age group, that is, the target consultation age group. At this time, since each preset consultation age group has a corresponding intelligent reception level, the target reception level corresponding to the target consultation age group can be determined, and then the voice interaction method corresponding to the target reception level (that is, the target voice interaction method) can be used to perform voice interaction with the current consultant, wherein the target voice interaction method includes a method of using an intelligent robot and manual service to perform voice interaction with the current consultant or a method of using manual service to perform voice interaction with the current consultant. It can be seen that the present application takes into account the phenomenon that consultants of different age groups have different degrees of acceptance of intelligent robots. When a new consultation occurs, the consultants can first be divided into different preset consultation age groups, and then different voice interaction methods are adopted for consultants of different preset consultation age groups, thereby improving the service quality of consulting services and reducing the waste of consultants' time, thereby solving the problem of poor service experience for consultants caused by voice interaction methods in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a voice interaction method provided in an embodiment of the present application is shown;
[0019] Figure 2 A flow chart of a voice interaction method provided according to an embodiment of the present application is shown;
[0020] Figure 3 A structural block diagram of a voice interaction device provided according to an embodiment of the present application is shown.
[0021] The above drawings include the following reference numerals:
[0022] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION
[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0026] As introduced in the background technology, when intelligent robots are used for interactive customer consulting services, since consultants of different age groups have different levels of acceptance of intelligent voice answering robots, the existing technology will randomly assign voice interaction methods when providing services to customers through intelligent robots. This random assignment will reduce the service quality, waste the consultant's time, and cause a bad service experience for the consultant.
[0027] Based on this, the present application proposes a voice interaction method, a voice interaction device, a computer-readable storage medium and an electronic device, so as to at least solve the problem that the voice interaction method in the prior art leads to a poor service experience for consultants due to the different acceptance levels of consultants of different age groups to the intelligent voice answering robot.
[0028] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.
[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a voice interaction method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the voice interaction method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0031] In this embodiment, a voice interaction method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0032] Figure 2 is a flow chart of a voice interaction method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:
[0033] Step S201, obtaining historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultation personnel information and historical consultation information, at least one historical consultation personnel information corresponds to a preset consultation age group;
[0034] Specifically, each consultation has corresponding consultation data, and the consultation data of each consultation may include consultant information and consultation information. Therefore, when historical consultation data corresponding to multiple historical consultations are obtained, the above historical consultation data may include historical consultant information and historical consultation information of multiple historical consultations.
[0035] For example, the above historical consultant information may include but is not limited to the ages of multiple historical consultants corresponding to multiple historical consultations. The above historical consultation information may include but is not limited to the duration of multiple historical consultations corresponding to multiple historical consultations, whether each historical consultation was successful for the historical consultant corresponding to the historical consultation, and whether the historical consultation was transferred to manual processing during the consultation process.
[0036] Furthermore, there is a mapping relationship between the consultant information and the consultation age group, that is, the multiple consultants corresponding to the multiple consultations can be divided into the consultation age group corresponding to the consultant information according to the corresponding multiple consultant information, so that after obtaining the historical consultant information corresponding to the multiple historical consultations, the historical consultant information corresponding to the multiple historical consultations can be divided into different preset consultation age groups. It can be understood that since the preset consultation age group is divided by the historical consultant information corresponding to the above multiple historical consultations, each preset consultation age group includes at least one historical consultant information corresponding to at least one historical consultation.
[0037] Step S202, determining the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program;
[0038] From the above, it can be seen that each historical consultation can determine the preset consultation age group to which it belongs through the corresponding information of each historical consultant, so that each preset consultation age group can correspond to at least one historical consultation information corresponding to at least one historical consultation, and then according to the historical consultation information corresponding to each preset consultation age group and the above preset program, an intelligent reception level corresponding to each preset consultation age group can be determined.
[0039] Step S203, obtaining the current consultant information corresponding to the current consultation;
[0040] Specifically, the above-mentioned consultation is the new consultation that has arisen.
[0041] Step S204, determining a target consultation age group according to the current consultant information and the preset consultation age group, where the target consultation age group is one of a plurality of preset consultation age groups;
[0042] Specifically, since there are multiple different preset consultation age groups, when obtaining the current consultant information of the current consultation, the preset consultation age group to which the current consultant information belongs can be determined as the target consultation age group through the matching results of multiple preset consultation age groups with the current consultant information.
[0043] Step S205, determines the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group. The target reception level is the intelligent reception level corresponding to the target consultation age group. The target voice interaction mode includes: using intelligent robots and manual service methods to perform voice interaction with the current consultant, or using manual service methods to perform voice interaction with the current consultant.
[0044] Specifically, there is a mapping relationship between the preset consultation age group and the intelligent reception level, that is, different preset consultation age groups correspond to different intelligent reception levels, so that after determining the target consultation age group to which the current consultant information belongs, the target reception level corresponding to the target consultation age group can be determined based on the mapping relationship between the preset consultation age group and the intelligent reception level. Furthermore, since the intelligent reception level and the voice interaction mode have a mapping relationship, that is, different intelligent reception levels correspond to different voice interaction modes, when determining the above-mentioned target reception level, the target voice interaction mode corresponding to the target reception level can be determined based on the mapping relationship between the above-mentioned intelligent reception level and the voice interaction mode. It can be understood that the target reception level is one of a plurality of different intelligent reception levels, and the target voice interaction mode is one of a plurality of voice interaction modes.
[0045] Through this embodiment, when the historical consultation data corresponding to multiple historical consultations are obtained, different preset consultation age groups can be first divided according to the historical consultation personnel information in the historical consultation data, and then the intelligent reception level corresponding to each preset consultation age group can be determined according to the historical consultation information and preset program in each preset consultation age group. On this basis, since the current consultant information corresponding to the current consultation can be obtained when a new consultation occurs, and the current consultant information can be matched with the preset consultation age group, the current consultant corresponding to the current consultant information can be divided into the corresponding preset consultation age group, that is, the target consultation age group. At this time, since each preset consultation age group has a corresponding intelligent reception level, the target reception level corresponding to the target consultation age group can be determined, and then the voice interaction method corresponding to the target reception level (that is, the target voice interaction method) can be used to perform voice interaction with the current consultant, wherein the target voice interaction method includes a method of using an intelligent robot and manual service to perform voice interaction with the current consultant or a method of using manual service to perform voice interaction with the current consultant. It can be seen that the present application takes into account the phenomenon that consultants of different age groups have different degrees of acceptance of intelligent robots. When a new consultation occurs, the consultants can first be divided into different preset consultation age groups, and then different voice interaction methods are adopted for consultants of different preset consultation age groups, thereby improving the service quality of consulting services and reducing the waste of consultants' time, thereby solving the problem of poor service experience for consultants caused by voice interaction methods in the prior art.
[0046] In order to match multiple preset consultation age groups with corresponding multiple intelligent reception levels, in some optional embodiments, the preset program includes a first preset program and a second preset program, and determines the intelligent reception level corresponding to each preset consultation age group based on historical consultation information and the preset program, including: determining the target reception coefficient corresponding to each preset consultation age group based on historical consultation information and the first preset program; determining the intelligent reception level corresponding to each target reception coefficient based on the target reception coefficient and the second preset program.
[0047] Specifically, multiple preset consultation age groups correspond one-to-one to multiple intelligent reception levels.
[0048] Optionally, multiple preset consultation age groups may not overlap with each other, and multiple intelligent reception levels may be different from each other.
[0049] Among them, for any preset consultation age group, the analysis step of matching the preset consultation age group with the corresponding intelligent reception coefficient can be: according to the historical consultation information corresponding to multiple historical consultations within the preset consultation age group and the first preset program, the target reception coefficient corresponding to the preset consultation age group can be determined. Then, according to the target reception coefficient corresponding to the preset consultation age group and the second preset program, the intelligent reception level corresponding to the target reception coefficient corresponding to the preset consultation age group can be determined. Therefore, based on the above analysis steps for any preset consultation age group, multiple intelligent reception levels corresponding to multiple preset consultation age groups can be obtained by analogy, which will not be repeated here.
[0050] During the specific implementation process, in order to match the corresponding target reception coefficient for each preset consultation age group, the target reception coefficient corresponding to each preset consultation age group is determined according to the historical consultation information and the first preset program, including: determining the year consultation time and year consultation coefficient corresponding to each preset consultation age group according to the historical consultation information and the preset relationship; determining the target reception coefficient according to the year consultation time and the preset formula, the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the year consultation time, and Xa is the year consultation coefficient.
[0051] Specifically, multiple preset consultation age groups correspond one-to-one with multiple age consultation durations, and multiple preset consultation age groups correspond one-to-one with multiple age consultation coefficients.
[0052] In a specific implementation, the preset relationship may include a first preset relationship and a second preset relationship. Each preset consultation age group includes at least one first historical consultation among multiple historical consultations. The historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation results. The historical consultation results include one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
[0053] It should be noted that successful consultation means that the consultant's consulting problem has been solved; failed consultation means that the consultant's consulting problem has not been solved; transfer to manual processing means that the consultant's consulting problem has not been solved during the voice interaction with the intelligent robot and has been transferred to manual processing and solved. It is mentioned here that consultation failure can include any of the following two situations: first, the consultant's consulting problem has not been solved during the voice interaction with the intelligent robot and has not been transferred to manual processing; second, the consultant's consulting problem has not been solved during the voice interaction with the intelligent robot and has not been solved after being transferred to manual processing.
[0054] Based on the above-mentioned first preset relationship and second preset relationship, in some optional embodiments, in order to determine the age consultation time and age consultation coefficient corresponding to each preset consultation age group according to historical consultation information and the preset relationship, the step may include: determining the age consultation time corresponding to each preset consultation age group according to at least one historical consultation time corresponding to at least one first historical consultation and the first preset relationship; and determining the age consultation coefficient corresponding to each preset consultation age group according to at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship.
[0055] Specifically, historical consultation may be a name before being classified into the preset consultation age group. After multiple historical consultations are classified into the preset consultation age group, each preset consultation age group may include at least one historical consultation, and the historical consultation classified into the preset consultation age group may be recorded as the first historical consultation.
[0056] Among them, based on the above-mentioned first preset relationship, in order to obtain the age consultation time corresponding to each preset consultation age group, in some optional implementations, the age consultation time corresponding to each preset consultation age group is determined according to at least one historical consultation time corresponding to at least one first historical consultation and the first preset relationship, including: obtaining the standard deviation of at least one historical consultation time corresponding to at least one first historical consultation; determining the age consultation time corresponding to each preset consultation age group according to the standard deviation and the first preset relationship.
[0057] Exemplarily, for any preset consultation age group, if the preset consultation age group includes multiple first historical consultations, the analysis steps for obtaining the year-segment consultation duration corresponding to the preset consultation age group can be: obtaining multiple historical consultation durations corresponding one-to-one to the multiple first historical consultations, and then calculating the standard deviation of the multiple historical consultation durations corresponding one-to-one to the multiple first historical consultations, and finally determining the year-segment consultation duration corresponding to the preset consultation age group based on the standard deviation and the first preset relationship. It can be understood that based on the above analysis steps for obtaining the corresponding year-segment consultation duration for any preset consultation age group, multiple year-segment consultation durations corresponding one-to-one to multiple preset consultation age groups can be obtained by analogy, which will not be repeated here.
[0058] Specifically, in some optional embodiments, the age consultation duration corresponding to each preset consultation age group is determined based on the standard deviation and the first preset relationship, including: judging whether the standard deviation is less than or equal to the first preset threshold value to obtain a first judgment result; when the first judgment result indicates yes, determining that the average of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration; when the first judgment result indicates no, determining that the average of the maximum and minimum values of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration.
[0059] Exemplarily, for any preset consultation age group including multiple first historical consultations, when the standard deviation of multiple historical consultation durations corresponding to multiple first historical consultations is less than or equal to the first preset threshold, the average consultation duration of multiple historical consultation durations corresponding to multiple first historical consultations can be calculated, and then the average consultation duration can be determined as the year-segment consultation duration of the preset consultation age group; when the standard deviation of multiple historical consultation durations corresponding to multiple first historical consultations is greater than the first preset threshold, the longest historical consultation duration and the shortest historical consultation duration among the multiple historical consultation durations can be obtained, and then after calculating the average consultation duration of the longest historical consultation duration (maximum value) and the shortest historical consultation duration (minimum value), the average consultation duration can be determined as the year-segment consultation duration of the preset consultation age group. By analogy, multiple year-segment consultation durations corresponding to multiple preset consultation age groups can be obtained, which will not be repeated here.
[0060] Based on the above-mentioned second preset relationship, in order to obtain the age consultation coefficient corresponding to each preset consultation age group, in some optional embodiments, the age consultation coefficient corresponding to each preset consultation age group is determined according to at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship, including: obtaining the first number, the second number and the third number in at least one first historical consultation, the first number being the number of successful consultations in at least one first historical consultation, the second number being the number of failed consultations in at least one first historical consultation, and the third number being the number of times at least one first historical consultation is transferred for manual processing; determining the age consultation coefficient corresponding to each preset consultation age group according to the first number, the second number, the third number and the second preset relationship.
[0061] Specifically, the above-mentioned second preset relationship can be: X1=[1-(E1×β3) / b]+(E2×β4+E3×β5) / b, wherein X1 represents the above-mentioned age group consultation coefficient, E1 represents the above-mentioned first number, E2 represents the above-mentioned second number, E3 represents the above-mentioned third number, β3, β4 and β5 are all fixed coefficients, 1=β3+β4+β5, β3<β4<β5.
[0062] On this basis, for example, for any preset consultation age group including multiple first historical consultations, the analysis steps for obtaining the age consultation coefficient corresponding to the preset consultation age group can be: obtain the number of successful consultations for the consultant in multiple first historical consultations and record it as the first number, the number of failed consultations for the consultant in multiple first historical consultations and record it as the second number, and the number of manual processing for the consultant in multiple first historical consultations and record it as the third number, and then according to the above-mentioned first number, second number, third number and the second preset relationship, the age consultation coefficient corresponding to the preset consultation age group can be calculated. By analogy, multiple age consultation coefficients corresponding to multiple preset consultation age groups can be obtained, which will not be repeated here.
[0063] In addition, in some optional embodiments, according to the target reception coefficient and the second preset program, the step of determining the intelligent reception level corresponding to each target reception coefficient may include: judging whether the target reception coefficient is less than or equal to the second preset threshold value to obtain a second judgment result; when the second judgment result indicates yes, determining that the intelligent reception level corresponding to the target reception coefficient is the first reception level, wherein the voice interaction method corresponding to the first reception level is to conduct voice interaction with the consultant by means of intelligent robots and manual service; when the second judgment result indicates no, determining that the intelligent reception level corresponding to the target reception coefficient is the second reception level, wherein the voice interaction method corresponding to the second reception level is to conduct voice interaction with the consultant by means of manual service.
[0064] Further, when the second judgment result indicates yes, the step of determining the intelligent reception level as the first reception level includes: determining whether the target reception coefficient is less than a third preset threshold value, the third preset threshold value is less than the second preset threshold value, and when the third judgment result indicates yes, determining the intelligent reception level corresponding to the target reception coefficient as the first reception level; when the third judgment result indicates no, determining the intelligent reception level corresponding to the target reception coefficient as the second reception level, the first reception level includes the first reception level and the second reception level, and the first reception level and the second reception level correspond to different voice interaction modes. Among them, the above-mentioned warning duration can be a preset duration.
[0065] Among them, the voice interaction method corresponding to the first-level reception level can be: first use an intelligent robot to interact with the consultant, and when the duration of the voice interaction between the intelligent robot and the consultant is greater than twice the warning duration, then use manual service to interact with the consultant. The voice interaction method corresponding to the second-level reception level can be: first use an intelligent robot to interact with the consultant, and when the duration of the voice interaction between the intelligent robot and the consultant is greater than the warning duration and less than or equal to twice the warning duration, then use manual service to interact with the consultant. The second reception level can be regarded as the third reception level.
[0066] It should be noted that the target voice interaction method may be one of the above-mentioned voice interaction methods.
[0067] Furthermore, in some optional implementations, when the duration of the voice interaction between the intelligent robot and the consultant is longer than the warning duration, a manual service prompt may be generated to inquire whether the consultant needs to be transferred to manual service. Similarly, when the duration of the voice interaction between the intelligent robot and the consultant is longer than twice the warning duration, a manual service prompt may be generated to inquire whether the consultant needs to be transferred to manual service.
[0068] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the voice interaction method of the present application will be described in detail below in combination with specific embodiments.
[0069] This embodiment relates to a specific voice interaction method, including the following steps:
[0070] Step S1: Obtain the current consultant information corresponding to the current consultation;
[0071] Step S2: determining a target consultation age group according to the current consultant information and the preset consultation age group, where the target consultation age group is one of a plurality of preset consultation age groups;
[0072] Step S3: Determine the target voice interaction mode of the current consultant based on the target consultation age group and the target reception level. The target reception level is one of the preset reception levels, which include the first-level reception level, the second-level reception level and the third-level reception level.
[0073] Specifically, when the target reception level corresponding to the current consultant information is the third-level reception level, it can be directly transferred to manual processing, so as to conduct voice interaction with the current consultant in the form of manual service; when the target reception level corresponding to the current consultant information is the second-level reception level, an intelligent robot can be used to serve the current consultant, and when the service time is longer than the above-mentioned warning time, a manual service prompt can be generated to ask the current consultant whether it needs to be transferred to manual processing; when the target reception level corresponding to the current consultant information is the first-level reception level, an intelligent robot can be used to serve the current consultant, and when the service time is longer than twice the above-mentioned warning time, a manual service prompt can be generated to ask the current consultant whether it needs to be transferred to manual processing.
[0074] The embodiment of the present application also provides a voice interaction device. It should be noted that the voice interaction device of the embodiment of the present application can be used to execute the voice interaction method provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions have been omitted. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0075] The following is an introduction to the voice interaction device provided in the embodiment of the present application.
[0076] Figure 3 is a schematic diagram of a voice interaction device according to an embodiment of the present application. Figure 3 As shown, the device comprises:
[0077] A first acquisition module 10 is used to acquire historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultation personnel information and historical consultation information, at least one historical consultation personnel information corresponds to a preset consultation age group;
[0078] Specifically, each consultation has corresponding consultation data, and the consultation data of each consultation may include consultant information and consultation information. Therefore, when historical consultation data corresponding to multiple historical consultations are obtained, the above historical consultation data may include historical consultant information and historical consultation information of multiple historical consultations.
[0079] For example, the above historical consultant information may include but is not limited to the ages of multiple historical consultants corresponding to multiple historical consultations. The above historical consultation information may include but is not limited to the duration of multiple historical consultations corresponding to multiple historical consultations, whether each historical consultation was successful for the historical consultant corresponding to the historical consultation, and whether the historical consultation was transferred to manual processing during the consultation process.
[0080] Furthermore, there is a mapping relationship between the consultant information and the consultation age group, that is, the multiple consultants corresponding to the multiple consultations can be divided into the consultation age group corresponding to the consultant information according to the corresponding multiple consultant information, so that after obtaining the historical consultant information corresponding to the multiple historical consultations, the historical consultant information corresponding to the multiple historical consultations can be divided into different preset consultation age groups. It can be understood that since the preset consultation age group is divided by the historical consultant information corresponding to the above multiple historical consultations, each preset consultation age group includes at least one historical consultant information corresponding to at least one historical consultation.
[0081] A first determination module 20, for determining the intelligent reception level corresponding to each preset consultation age group according to historical consultation information and preset programs;
[0082] From the above, it can be seen that each historical consultation can determine the preset consultation age group to which it belongs through the corresponding information of each historical consultant, so that each preset consultation age group can correspond to at least one historical consultation information corresponding to at least one historical consultation, and then according to the historical consultation information corresponding to each preset consultation age group and the above preset program, an intelligent reception level corresponding to each preset consultation age group can be determined.
[0083] The second acquisition module 30 is used to obtain the current consultant information corresponding to the current consultation;
[0084] Specifically, the above-mentioned consultation is the new consultation that has arisen.
[0085] A second determination module 40 is used to determine a target consultation age group according to the current consultant information and the preset consultation age group, where the target consultation age group is one of the multiple preset consultation age groups;
[0086] Specifically, since there are multiple different preset consultation age groups, when obtaining the current consultant information of the current consultation, the preset consultation age group to which the current consultant information belongs can be determined as the target consultation age group through the matching results of multiple preset consultation age groups with the current consultant information.
[0087] The third determination module 50 is used to determine the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group. The target reception level is the intelligent reception level corresponding to the target consultation age group. The target voice interaction mode includes: using intelligent robots and manual service methods to perform voice interaction with the current consultant, or using manual service methods to perform voice interaction with the current consultant.
[0088] Specifically, there is a mapping relationship between the preset consultation age group and the intelligent reception level, that is, different preset consultation age groups correspond to different intelligent reception levels, so that after determining the target consultation age group to which the current consultant information belongs, the target reception level corresponding to the target consultation age group can be determined based on the mapping relationship between the preset consultation age group and the intelligent reception level. Furthermore, since the intelligent reception level and the voice interaction mode have a mapping relationship, that is, different intelligent reception levels correspond to different voice interaction modes, when determining the above-mentioned target reception level, the target voice interaction mode corresponding to the target reception level can be determined based on the mapping relationship between the above-mentioned intelligent reception level and the voice interaction mode. It can be understood that the target reception level is one of a plurality of different intelligent reception levels, and the target voice interaction mode is one of a plurality of voice interaction modes.
[0089] Through this embodiment, when the historical consultation data corresponding to multiple historical consultations are obtained, different preset consultation age groups can be first divided according to the historical consultation personnel information in the historical consultation data, and then the intelligent reception level corresponding to each preset consultation age group can be determined according to the historical consultation information and preset program in each preset consultation age group. On this basis, since the current consultant information corresponding to the current consultation can be obtained when a new consultation occurs, and the current consultant information can be matched with the preset consultation age group, the current consultant corresponding to the current consultant information can be divided into the corresponding preset consultation age group, that is, the target consultation age group. At this time, since each preset consultation age group has a corresponding intelligent reception level, the target reception level corresponding to the target consultation age group can be determined, and then the voice interaction method corresponding to the target reception level (that is, the target voice interaction method) can be used to perform voice interaction with the current consultant, wherein the target voice interaction method includes a method of using an intelligent robot and manual service to perform voice interaction with the current consultant or a method of using manual service to perform voice interaction with the current consultant. It can be seen that the present application takes into account the phenomenon that consultants of different age groups have different degrees of acceptance of intelligent robots. When a new consultation occurs, the consultants can first be divided into different preset consultation age groups, and then different voice interaction methods are adopted for consultants of different preset consultation age groups, thereby improving the service quality of consulting services and reducing the waste of consultants' time, thereby solving the problem of poor service experience for consultants caused by voice interaction methods in the prior art.
[0090] In order to match multiple preset consultation age groups with corresponding multiple intelligent reception levels, in some optional embodiments, the preset program includes a first preset program and a second preset program, and the first determination module includes: a first determination unit, used to determine the target reception coefficient corresponding to each preset consultation age group based on historical consultation information and the first preset program; a second determination unit, used to determine the intelligent reception level corresponding to each target reception coefficient based on the target reception coefficient and the second preset program.
[0091] Specifically, multiple preset consultation age groups correspond one-to-one to multiple intelligent reception levels.
[0092] Optionally, multiple preset consultation age groups may not overlap with each other, and multiple intelligent reception levels may be different from each other.
[0093] Among them, for any preset consultation age group, the analysis step of matching the preset consultation age group with the corresponding intelligent reception coefficient can be: according to the historical consultation information corresponding to multiple historical consultations within the preset consultation age group and the first preset program, the target reception coefficient corresponding to the preset consultation age group can be determined. Then, according to the target reception coefficient corresponding to the preset consultation age group and the second preset program, the intelligent reception level corresponding to the target reception coefficient corresponding to the preset consultation age group can be determined. Therefore, based on the above analysis steps for any preset consultation age group, multiple intelligent reception levels corresponding to multiple preset consultation age groups can be obtained by analogy, which will not be repeated here.
[0094] During the specific implementation process, in order to match the corresponding target reception coefficient for each preset consultation age group, the first determination unit includes: a first subunit, used to determine the year consultation time and year consultation coefficient corresponding to each preset consultation age group according to historical consultation information and preset relationship; a second subunit, used to determine the target reception coefficient according to the year consultation time and a preset formula, and the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the year consultation time, and Xa is the year consultation coefficient.
[0095] Specifically, multiple preset consultation age groups correspond one-to-one with multiple age consultation durations, and multiple preset consultation age groups correspond one-to-one with multiple age consultation coefficients.
[0096] In a specific implementation, the preset relationship may include a first preset relationship and a second preset relationship. Each preset consultation age group includes at least one first historical consultation among multiple historical consultations. The historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation results. The historical consultation results include one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
[0097] It should be noted that successful consultation means that the consultant's consulting problem has been solved; failed consultation means that the consultant's consulting problem has not been solved; transfer to manual processing means that the consultant's consulting problem has not been solved during the voice interaction with the intelligent robot and has been transferred to manual processing and solved. It is mentioned here that consultation failure can include any of the following two situations: first, the consultant's consulting problem has not been solved during the voice interaction with the intelligent robot and has not been transferred to manual processing; second, the consultant's consulting problem has not been solved during the voice interaction with the intelligent robot and has not been solved after being transferred to manual processing.
[0098] Based on the above-mentioned first preset relationship and second preset relationship, in some optional embodiments, the first subunit may include: a second subunit, used to determine the age consultation duration corresponding to each preset consultation age group based on at least one historical consultation duration corresponding to at least one first historical consultation and the first preset relationship; a third subunit, used to determine the age consultation coefficient corresponding to each preset consultation age group based on at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship.
[0099] Specifically, historical consultation may be a name before being classified into the preset consultation age group. After multiple historical consultations are classified into the preset consultation age group, each preset consultation age group may include at least one historical consultation, and the historical consultation classified into the preset consultation age group may be recorded as the first historical consultation.
[0100] Among them, based on the above-mentioned first preset relationship, in order to obtain the year consultation time corresponding to each preset consultation age group, in some optional embodiments, the second subunit includes: a fourth subunit, used to obtain the standard deviation of at least one historical consultation time corresponding to at least one first historical consultation; a fifth subunit, used to determine the year consultation time corresponding to each preset consultation age group based on the standard deviation and the first preset relationship.
[0101] Exemplarily, for any preset consultation age group, if the preset consultation age group includes multiple first historical consultations, the analysis steps for obtaining the year-segment consultation duration corresponding to the preset consultation age group can be: obtaining multiple historical consultation durations corresponding one-to-one to the multiple first historical consultations, and then calculating the standard deviation of the multiple historical consultation durations corresponding one-to-one to the multiple first historical consultations, and finally determining the year-segment consultation duration corresponding to the preset consultation age group based on the standard deviation and the first preset relationship. It can be understood that based on the above analysis steps for obtaining the corresponding year-segment consultation duration for any preset consultation age group, multiple year-segment consultation durations corresponding one-to-one to multiple preset consultation age groups can be obtained by analogy, which will not be repeated here.
[0102] Specifically, in some optional embodiments, the fifth subunit includes: a sixth subunit, used to determine whether the standard deviation is less than or equal to a first preset threshold value to obtain a first judgment result; a seventh subunit, used to determine, when the first judgment result indicates yes, the average of at least one historical consultation duration corresponding to at least one first historical consultation as the year-stage consultation duration; an eighth subunit, used to determine, when the first judgment result indicates no, the average of the maximum and minimum values of at least one historical consultation duration corresponding to at least one first historical consultation as the year-stage consultation duration.
[0103] Exemplarily, for any preset consultation age group including multiple first historical consultations, when the standard deviation of multiple historical consultation durations corresponding to multiple first historical consultations is less than or equal to the first preset threshold, the average consultation duration of multiple historical consultation durations corresponding to multiple first historical consultations can be calculated, and then the average consultation duration can be determined as the year-segment consultation duration of the preset consultation age group; when the standard deviation of multiple historical consultation durations corresponding to multiple first historical consultations is greater than the first preset threshold, the longest historical consultation duration and the shortest historical consultation duration among the multiple historical consultation durations can be obtained, and then after calculating the average consultation duration of the longest historical consultation duration (maximum value) and the shortest historical consultation duration (minimum value), the average consultation duration can be determined as the year-segment consultation duration of the preset consultation age group. By analogy, multiple year-segment consultation durations corresponding to multiple preset consultation age groups can be obtained, which will not be repeated here.
[0104] Based on the above-mentioned second preset relationship, in order to obtain the year consultation coefficient corresponding to each preset consultation age group, in some optional embodiments, the third subunit includes: a ninth subunit, used to obtain the first number, the second number and the third number in at least one first historical consultation, the first number being the number of successful consultations in at least one first historical consultation, the second number being the number of failed consultations in at least one first historical consultation, and the third number being the number of times at least one first historical consultation was transferred for manual processing; a tenth subunit, used to determine the year consultation coefficient corresponding to each preset consultation age group based on the first number, the second number, the third number and the second preset relationship.
[0105] Specifically, the above-mentioned second preset relationship can be: X1=[1-(E1×β3) / b]+(E2×β4+E3×β5) / b, wherein X1 represents the above-mentioned age group consultation coefficient, E1 represents the above-mentioned first number, E2 represents the above-mentioned second number, E3 represents the above-mentioned third number, β3, β4 and β5 are all fixed coefficients, 1=β3+β4+β5, β3<β4<β5.
[0106] On this basis, for example, for any preset consultation age group including multiple first historical consultations, the analysis steps for obtaining the age consultation coefficient corresponding to the preset consultation age group can be: obtain the number of successful consultations for the consultant in multiple first historical consultations and record it as the first number, the number of failed consultations for the consultant in multiple first historical consultations and record it as the second number, and the number of manual processing for the consultant in multiple first historical consultations and record it as the third number, and then according to the above-mentioned first number, second number, third number and the second preset relationship, the age consultation coefficient corresponding to the preset consultation age group can be calculated. By analogy, multiple age consultation coefficients corresponding to multiple preset consultation age groups can be obtained, which will not be repeated here.
[0107] In addition, in some optional embodiments, the second determination unit may include: a first processing unit, used to determine whether the target reception coefficient is less than or equal to a second preset threshold value to obtain a second judgment result; a second processing unit, used to determine, when the second judgment result indicates yes, that the intelligent reception level corresponding to the target reception coefficient is a first reception level, wherein the voice interaction method corresponding to the first reception level is to perform voice interaction with the consultant by using an intelligent robot and manual service; a third processing unit, used to determine, when the second judgment result indicates no, that the intelligent reception level corresponding to the target reception coefficient is a second reception level, wherein the voice interaction method corresponding to the second reception level is to perform voice interaction with the consultant by using manual service.
[0108] Further, the second processing unit includes: a first sub-processing unit, which is used to determine whether the target reception coefficient is less than a third preset threshold value, and the third preset threshold value is less than the second preset threshold value. If the third judgment result indicates yes, the intelligent reception level corresponding to the target reception coefficient is determined to be a first-level reception level; a second sub-processing unit, which is used to determine that if the third judgment result indicates no, the intelligent reception level corresponding to the target reception coefficient is a second-level reception level, and the first reception level includes a first-level reception level and a second-level reception level, and the first-level reception level and the second-level reception level have different voice interaction modes. Among them, the above-mentioned warning duration can be a preset duration.
[0109] Among them, the voice interaction method corresponding to the first-level reception level can be: first use an intelligent robot to interact with the consultant, and when the duration of the voice interaction between the intelligent robot and the consultant is greater than twice the warning duration, then use manual service to interact with the consultant. The voice interaction method corresponding to the second-level reception level can be: first use an intelligent robot to interact with the consultant, and when the duration of the voice interaction between the intelligent robot and the consultant is greater than the warning duration and less than or equal to twice the warning duration, then use manual service to interact with the consultant. The second reception level can be regarded as the third reception level.
[0110] It should be noted that the target voice interaction method may be one of the above-mentioned voice interaction methods.
[0111] Furthermore, in some optional implementations, when the duration of the voice interaction between the intelligent robot and the consultant is longer than the warning duration, a manual service prompt may be generated to inquire whether the consultant needs to be transferred to manual service. Similarly, when the duration of the voice interaction between the intelligent robot and the consultant is longer than twice the warning duration, a manual service prompt may be generated to inquire whether the consultant needs to be transferred to manual service.
[0112] The voice interaction device includes a processor and a memory, and the first acquisition module, the first determination module, the second acquisition module, the second determination module, and the third determination module are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The above modules are all located in the same processor; or, the above modules are located in different processors in any combination.
[0113] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of poor service experience for consultants caused by the voice interaction method in the prior art can be solved by adjusting the kernel parameters.
[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0115] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, a device where the computer-readable storage medium is located is controlled to execute a voice interaction method.
[0116] Specifically, the voice interaction method includes:
[0117] Step S201, obtaining historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultation personnel information and historical consultation information, at least one historical consultation personnel information corresponds to a preset consultation age group;
[0118] Specifically, each consultation has corresponding consultation data, and the consultation data of each consultation may include consultant information and consultation information. Therefore, when historical consultation data corresponding to multiple historical consultations are obtained, the above historical consultation data may include historical consultant information and historical consultation information of multiple historical consultations.
[0119] For example, the above historical consultant information may include but is not limited to the ages of multiple historical consultants corresponding to multiple historical consultations. The above historical consultation information may include but is not limited to the duration of multiple historical consultations corresponding to multiple historical consultations, whether each historical consultation was successful for the historical consultant corresponding to the historical consultation, and whether the historical consultation was transferred to manual processing during the consultation process.
[0120] Furthermore, there is a mapping relationship between the consultant information and the consultation age group, that is, the multiple consultants corresponding to the multiple consultations can be divided into the consultation age group corresponding to the consultant information according to the corresponding multiple consultant information, so that after obtaining the historical consultant information corresponding to the multiple historical consultations, the historical consultant information corresponding to the multiple historical consultations can be divided into different preset consultation age groups. It can be understood that since the preset consultation age group is divided by the historical consultant information corresponding to the above multiple historical consultations, each preset consultation age group includes at least one historical consultant information corresponding to at least one historical consultation.
[0121] Step S202, determining the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program;
[0122] From the above, it can be seen that each historical consultation can determine the preset consultation age group to which it belongs through the corresponding information of each historical consultant, so that each preset consultation age group can correspond to at least one historical consultation information corresponding to at least one historical consultation, and then according to the historical consultation information corresponding to each preset consultation age group and the above preset program, an intelligent reception level corresponding to each preset consultation age group can be determined.
[0123] Step S203, obtaining the current consultant information corresponding to the current consultation;
[0124] Specifically, the above-mentioned consultation is the new consultation that has arisen.
[0125] Step S204, determining a target consultation age group according to the current consultant information and the preset consultation age group, where the target consultation age group is one of a plurality of preset consultation age groups;
[0126] Specifically, since there are multiple different preset consultation age groups, when obtaining the current consultant information of the current consultation, the preset consultation age group to which the current consultant information belongs can be determined as the target consultation age group through the matching results of multiple preset consultation age groups with the current consultant information.
[0127] Step S205, determines the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group. The target reception level is the intelligent reception level corresponding to the target consultation age group. The target voice interaction mode includes: using intelligent robots and manual service methods to perform voice interaction with the current consultant, or using manual service methods to perform voice interaction with the current consultant.
[0128] Specifically, there is a mapping relationship between the preset consultation age group and the intelligent reception level, that is, different preset consultation age groups correspond to different intelligent reception levels, so that after determining the target consultation age group to which the current consultant information belongs, the target reception level corresponding to the target consultation age group can be determined based on the mapping relationship between the preset consultation age group and the intelligent reception level. Furthermore, since the intelligent reception level and the voice interaction mode have a mapping relationship, that is, different intelligent reception levels correspond to different voice interaction modes, when determining the above-mentioned target reception level, the target voice interaction mode corresponding to the target reception level can be determined based on the mapping relationship between the above-mentioned intelligent reception level and the voice interaction mode. It can be understood that the target reception level is one of a plurality of different intelligent reception levels, and the target voice interaction mode is one of a plurality of voice interaction modes.
[0129] Optionally, the preset program includes a first preset program and a second preset program, and determines the intelligent reception level corresponding to each preset consultation age group based on historical consultation information and the preset program, including: determining the target reception coefficient corresponding to each preset consultation age group based on historical consultation information and the first preset program; determining the intelligent reception level corresponding to each target reception coefficient based on the target reception coefficient and the second preset program.
[0130] Optionally, based on historical consultation information and a first preset program, a target reception coefficient corresponding to each preset consultation age group is determined, including: based on historical consultation information and a preset relationship, determining the year consultation duration and year consultation coefficient corresponding to each preset consultation age group; based on the year consultation duration and a preset formula, determining the target reception coefficient, the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the year consultation duration, and Xa is the year consultation coefficient.
[0131] Optionally, the preset relationship includes a first preset relationship and a second preset relationship, each preset consultation age group includes at least one first historical consultation among multiple historical consultations, and the historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation result. According to the historical consultation information and the preset relationship, the year consultation duration and year consultation coefficient corresponding to each preset consultation age group are determined, including: determining the year consultation duration corresponding to each preset consultation age group according to at least one historical consultation duration corresponding to at least one first historical consultation and the first preset relationship; determining the year consultation coefficient corresponding to each preset consultation age group according to at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship, and the historical consultation result includes one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
[0132] Optionally, based on at least one historical consultation duration corresponding to at least one first historical consultation and a first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: obtaining the standard deviation of at least one historical consultation duration corresponding to at least one first historical consultation; and determining the age consultation duration corresponding to each preset consultation age group based on the standard deviation and the first preset relationship.
[0133] Optionally, based on the standard deviation and the first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: judging whether the standard deviation is less than or equal to a first preset threshold value to obtain a first judgment result; when the first judgment result indicates yes, determining that the average of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration; when the first judgment result indicates no, determining that the average of the maximum and minimum values of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration.
[0134] Optionally, based on at least one historical consultation result corresponding to at least one first historical consultation and a second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined, including: obtaining the first number, the second number, and the third number in at least one first historical consultation, the first number being the number of successful consultations in at least one first historical consultation, the second number being the number of failed consultations in at least one first historical consultation, and the third number being the number of times at least one first historical consultation is transferred for manual processing; based on the first number, the second number, the third number, and the second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined.
[0135] An embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements at least the following steps when executing the program: obtaining historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultation personnel information and historical consultation information, at least one historical consultation personnel information corresponding to a preset consultation age group; determining the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program; obtaining the current consultant information corresponding to the current consultation; determining the target consultation age group according to the current consultant information and the preset consultation age group, the target consultation age group being one of the multiple preset consultation age groups; determining the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group, the target reception level being the intelligent reception level corresponding to the target consultation age group, and the target voice interaction mode including: using intelligent robots and manual service methods to perform voice interaction with the current consultant, or using manual service methods to perform voice interaction with the current consultant. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.
[0136] Optionally, the preset program includes a first preset program and a second preset program, and determines the intelligent reception level corresponding to each preset consultation age group based on historical consultation information and the preset program, including: determining the target reception coefficient corresponding to each preset consultation age group based on historical consultation information and the first preset program; determining the intelligent reception level corresponding to each target reception coefficient based on the target reception coefficient and the second preset program.
[0137] Optionally, based on historical consultation information and a first preset program, a target reception coefficient corresponding to each preset consultation age group is determined, including: based on historical consultation information and a preset relationship, determining the year consultation duration and year consultation coefficient corresponding to each preset consultation age group; based on the year consultation duration and a preset formula, determining the target reception coefficient, the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the year consultation duration, and Xa is the year consultation coefficient.
[0138] Optionally, the preset relationship includes a first preset relationship and a second preset relationship, each preset consultation age group includes at least one first historical consultation among multiple historical consultations, and the historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation result. According to the historical consultation information and the preset relationship, the year consultation duration and year consultation coefficient corresponding to each preset consultation age group are determined, including: determining the year consultation duration corresponding to each preset consultation age group according to at least one historical consultation duration corresponding to at least one first historical consultation and the first preset relationship; determining the year consultation coefficient corresponding to each preset consultation age group according to at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship, and the historical consultation result includes one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
[0139] Optionally, based on at least one historical consultation duration corresponding to at least one first historical consultation and a first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: obtaining the standard deviation of at least one historical consultation duration corresponding to at least one first historical consultation; and determining the age consultation duration corresponding to each preset consultation age group based on the standard deviation and the first preset relationship.
[0140] Optionally, based on the standard deviation and the first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: judging whether the standard deviation is less than or equal to a first preset threshold value to obtain a first judgment result; when the first judgment result indicates yes, determining that the average of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration; when the first judgment result indicates no, determining that the average of the maximum and minimum values of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration.
[0141] Optionally, based on at least one historical consultation result corresponding to at least one first historical consultation and a second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined, including: obtaining the first number, the second number, and the third number in at least one first historical consultation, the first number being the number of successful consultations in at least one first historical consultation, the second number being the number of failed consultations in at least one first historical consultation, and the third number being the number of times at least one first historical consultation is transferred for manual processing; based on the first number, the second number, the third number, and the second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined.
[0142] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes at least the following method steps: obtaining historical consultation data corresponding to multiple historical consultations, the historical consultation data including historical consultant information and historical consultation information, at least one historical consultant information corresponding to a preset consultation age group; determining the intelligent reception level corresponding to each preset consultation age group based on the historical consultation information and the preset program; obtaining the current consultant information corresponding to the current consultation; determining the target consultation age group based on the current consultant information and the preset consultation age group, the target consultation age group being one of multiple preset consultation age groups; determining the target voice interaction mode of the current consultant based on the target reception level corresponding to the target consultation age group, the target reception level being the intelligent reception level corresponding to the target consultation age group, and the target voice interaction mode including: using intelligent robots and manual services to perform voice interaction with the current consultant, or using manual services to perform voice interaction with the current consultant.
[0143] Optionally, the preset program includes a first preset program and a second preset program, and determines the intelligent reception level corresponding to each preset consultation age group based on historical consultation information and the preset program, including: determining the target reception coefficient corresponding to each preset consultation age group based on historical consultation information and the first preset program; determining the intelligent reception level corresponding to each target reception coefficient based on the target reception coefficient and the second preset program.
[0144] Optionally, based on historical consultation information and a first preset program, a target reception coefficient corresponding to each preset consultation age group is determined, including: based on historical consultation information and a preset relationship, determining the year consultation duration and year consultation coefficient corresponding to each preset consultation age group; based on the year consultation duration and a preset formula, determining the target reception coefficient, the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the year consultation duration, and Xa is the year consultation coefficient.
[0145] Optionally, the preset relationship includes a first preset relationship and a second preset relationship, each preset consultation age group includes at least one first historical consultation among multiple historical consultations, and the historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation result. According to the historical consultation information and the preset relationship, the year consultation duration and year consultation coefficient corresponding to each preset consultation age group are determined, including: determining the year consultation duration corresponding to each preset consultation age group according to at least one historical consultation duration corresponding to at least one first historical consultation and the first preset relationship; determining the year consultation coefficient corresponding to each preset consultation age group according to at least one historical consultation result corresponding to at least one first historical consultation and the second preset relationship, and the historical consultation result includes one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
[0146] Optionally, based on at least one historical consultation duration corresponding to at least one first historical consultation and a first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: obtaining the standard deviation of at least one historical consultation duration corresponding to at least one first historical consultation; and determining the age consultation duration corresponding to each preset consultation age group based on the standard deviation and the first preset relationship.
[0147] Optionally, based on the standard deviation and the first preset relationship, the age consultation duration corresponding to each preset consultation age group is determined, including: judging whether the standard deviation is less than or equal to a first preset threshold value to obtain a first judgment result; when the first judgment result indicates yes, determining that the average of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration; when the first judgment result indicates no, determining that the average of the maximum and minimum values of at least one historical consultation duration corresponding to at least one first historical consultation is the age consultation duration.
[0148] Optionally, based on at least one historical consultation result corresponding to at least one first historical consultation and a second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined, including: obtaining the first number, the second number, and the third number in at least one first historical consultation, the first number being the number of successful consultations in at least one first historical consultation, the second number being the number of failed consultations in at least one first historical consultation, and the third number being the number of times at least one first historical consultation is transferred for manual processing; based on the first number, the second number, the third number, and the second preset relationship, the year consultation coefficient corresponding to each preset consultation age group is determined.
[0149] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0150] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0151] The present application is 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 generate 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 flowchart and / or block diagram. 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.
[0152] 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.
[0153] 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.
[0154] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0155] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0156] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0157] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0158] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:
[0159] By applying the technical solution of the present application, when obtaining historical consultation data corresponding to multiple historical consultations, different preset consultation age groups can be first divided according to the historical consultation personnel information in the historical consultation data, and then the intelligent reception level corresponding to each preset consultation age group can be determined according to the historical consultation information and preset program in each preset consultation age group. On this basis, since the current consultant information corresponding to the current consultation can be obtained when a new consultation occurs, and the current consultant information can be matched with the preset consultation age group, the current consultant corresponding to the current consultant information can be divided into the corresponding preset consultation age group, that is, the target consultation age group. At this time, since each preset consultation age group has a corresponding intelligent reception level, the target reception level corresponding to the target consultation age group can be determined, and then the voice interaction method corresponding to the target reception level (that is, the target voice interaction method) can be used to perform voice interaction with the current consultant, wherein the target voice interaction method includes a method of using an intelligent robot and manual service to perform voice interaction with the current consultant or a method of using manual service to perform voice interaction with the current consultant. It can be seen that the present application takes into account the phenomenon that consultants of different age groups have different degrees of acceptance of intelligent robots. When a new consultation occurs, the consultants can first be divided into different preset consultation age groups, and then different voice interaction methods are adopted for consultants of different preset consultation age groups, thereby improving the service quality of consulting services and reducing the waste of consultants' time, thereby solving the problem of poor service experience for consultants caused by voice interaction methods in the prior art.
[0160] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A voice interaction method, characterized in that: include: Acquire historical consultation data corresponding to multiple historical consultations, wherein the historical consultation data includes historical consultation personnel information and historical consultation information, and at least one of the historical consultation personnel information corresponds to a preset consultation age group; Determine the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program; Get the current consultant information corresponding to the consultation; Determine a target consultation age group according to the current consultant information and the preset consultation age group, wherein the target consultation age group is one of the plurality of preset consultation age groups; According to the target reception level corresponding to the target consultation age group, the target voice interaction mode of the current consultant is determined, the target reception level is the intelligent reception level corresponding to the target consultation age group, and the target voice interaction mode includes: using intelligent robots and manual service to perform voice interaction with the current consultant, or using manual service to perform voice interaction with the current consultant.
2. The voice interaction method according to claim 1, characterized in that: The preset program includes a first preset program and a second preset program, and according to the historical consultation information and the preset program, the intelligent reception level corresponding to each preset consultation age group is determined, including: Determining a target reception coefficient corresponding to each of the preset consultation age groups according to the historical consultation information and the first preset program; According to the target reception coefficient and the second preset program, an intelligent reception level corresponding to each target reception coefficient is determined.
3. The voice interaction method according to claim 2, characterized in that: Determining a target reception coefficient corresponding to each of the preset consultation age groups according to the historical consultation information and the first preset program includes: Determine the age consultation duration and age consultation coefficient corresponding to each preset consultation age group according to the historical consultation information and the preset relationship; The target reception coefficient is determined based on the consultation time for the said year group and the preset formula, and the preset formula is K=β1×Na+β2×Xa, wherein K is the target reception coefficient, β1 and β2 are both preset coefficients, Na is the consultation time for the said year group, and Xa is the consultation coefficient for the said year group.
4. The voice interaction method according to claim 3, characterized in that: The preset relationship includes a first preset relationship and a second preset relationship, each of the preset consultation age groups includes at least one first historical consultation among the multiple historical consultations, the historical consultation information corresponding to the first historical consultation includes the historical consultation duration and the historical consultation result, and the year consultation duration and year consultation coefficient corresponding to each of the preset consultation age groups are determined according to the historical consultation information and the preset relationship, including: Determine the age consultation duration corresponding to each preset consultation age group according to at least one of the historical consultation durations corresponding to at least one of the first historical consultations and the first preset relationship; Based on at least one of the historical consultation results corresponding to at least one of the first historical consultations and the second preset relationship, the age group consultation coefficient corresponding to each of the preset consultation age groups is determined, and the historical consultation results include one of the following three situations: successful consultation, failed consultation, and transfer to manual processing.
5. The voice interaction method according to claim 4, characterized in that: Determining the age consultation duration corresponding to each preset consultation age group according to at least one of the historical consultation durations corresponding to at least one of the first historical consultations and the first preset relationship, including: Obtaining a standard deviation of at least one of the historical consultation durations corresponding to at least one of the first historical consultations; The age consultation duration corresponding to each preset consultation age group is determined based on the standard deviation and the first preset relationship.
6. The voice interaction method according to claim 5, characterized in that: Determining the age consultation duration corresponding to each preset consultation age group according to the standard deviation and the first preset relationship includes: Determine whether the standard deviation is less than or equal to a first preset threshold value, and obtain a first determination result; When the first judgment result indicates yes, determining that the average of at least one of the historical consultation durations corresponding to at least one of the first historical consultations is the consultation duration for the year period; When the first judgment result indicates no, the average of the maximum and minimum values of at least one of the historical consultation durations corresponding to at least one of the first historical consultations is determined as the annual consultation duration.
7. The voice interaction method according to claim 4, characterized in that: Determining the age group consultation coefficient corresponding to each preset consultation age group according to at least one of the historical consultation results corresponding to at least one of the first historical consultations and a second preset relationship, including: Obtain the first number, the second number, and the third number in at least one of the first historical consultations, wherein the first number is the number of successful consultations in at least one of the first historical consultations, the second number is the number of failed consultations in at least one of the first historical consultations, and the third number is the number of times the at least one first historical consultation was transferred to manual processing; According to the first number, the second number, the third number and the second preset relationship, the age group consultation coefficient corresponding to each preset consultation age group is determined.
8. A voice interaction system, characterized in that: include: A first acquisition module is used to acquire historical consultation data corresponding to multiple historical consultations, wherein the historical consultation data includes historical consultation personnel information and historical consultation information, and at least one historical consultation personnel information corresponds to a preset consultation age group; A first determination module is used to determine the intelligent reception level corresponding to each preset consultation age group according to the historical consultation information and the preset program; The second acquisition module is used to obtain the current consultant information corresponding to the current consultation; A second determination module is used to determine a target consultation age group according to the current consultant information and the preset consultation age group, wherein the target consultation age group is one of the plurality of preset consultation age groups; The third determination module is used to determine the target voice interaction mode of the current consultant according to the target reception level corresponding to the target consultation age group, the target reception level is the intelligent reception level corresponding to the target consultation age group, and the target voice interaction mode includes using intelligent robots and manual service to perform voice interaction with the current consultant or using manual service to perform voice interaction with the current consultant.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the voice interaction method according to any one of claims 1 to 7.
10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the voice interaction method described in any one of claims 1 to 7.
