A voice broadcast method, device and computer readable storage medium
By adjusting the voice broadcast order according to the user type, the problem of low voice broadcast efficiency in the IVR menu is solved, and more efficient user experience and resource utilization are achieved.
Patent Information
- Application Number
- CN202111409082.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-19
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2041-11-19
AI Technical Summary
When a user calls the customer service phone, the voice broadcasting efficiency in the IVR menu is inefficient, resulting in long wait times and wasting communication resources.
Determine the target voice broadcast rules according to the user type, adjust the original voice broadcast order, and adopt rules such as priority recommendation algorithms to improve voice broadcast efficiency, shorten user waiting time and save communication resources.
By dynamically adjusting the order of voice broadcasts, the efficiency of voice broadcasts is improved, the waiting time for users is shortened, the waste of communication resources is avoided, and the user experience and service quality are improved.
Smart Images

Figure CN114125159B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a voice broadcasting method, device and computer-readable storage medium. Background Art
[0002] Usually, when a user dials a customer service number, the voice broadcast terminal of the customer service platform will broadcast the IVR (Interactive Voice Response) menu in a pre-set fixed order. The user presses the corresponding button according to the voice broadcast, and the customer service platform provides the user with the service corresponding to the button. In practice, it has been proved that if the service that the user needs to handle is relatively late in the IVR menu, not only will the user wait for a long time, but the voice broadcast efficiency is not high, and communication resources are wasted. Summary of the invention
[0003] The embodiments of the present application provide a voice broadcast method, device and computer-readable storage medium, which can improve the efficiency of voice broadcast, reduce the waiting time of users and save communication resources.
[0004] The present application provides a voice broadcast method, including:
[0005] In response to a voice broadcast start instruction from a target user, obtaining an original voice broadcast sequence corresponding to the service options;
[0006] Determine a target voice broadcast rule according to the type of the target user; the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order;
[0007] The service options are voice announced according to the target voice announcement rule.
[0008] The present application provides a voice broadcasting device, including:
[0009] An acquisition module, configured to respond to a target user's voice broadcast start instruction and acquire an original voice broadcast sequence corresponding to the service options;
[0010] A determination module, used to determine a target voice broadcast rule according to the type of the target user; the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order;
[0011] The announcement module is used to perform voice announcement of the service options according to the target voice announcement rule.
[0012] On the one hand, an embodiment of the present application provides a computer device, including: a processor, a memory, and a network interface; the processor is connected to the memory and the network interface, wherein the network interface is used to provide a network communication function, the memory is used to store program code, and the processor is used to call the program code to execute the voice broadcast method in the embodiment of the present application.
[0013] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, the voice broadcast method in the embodiment of the present application is executed.
[0014] Accordingly, the embodiment of the present application provides a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the voice broadcast method provided in one aspect of the embodiment of the present application.
[0015] In the embodiment of the present application, the corresponding voice broadcast rules are matched according to the user type, and the service options are broadcast according to the voice broadcast rules. Since the voice broadcast rules can adjust the original voice broadcast order, it is no longer necessary to follow the fixed voice broadcast order for broadcasting, but to adaptively adjust the broadcasting. In this way, different types of users can be matched with different voice broadcast rules, and the original voice broadcast order can be changed in accordance with the voice broadcast rules, so that the voice broadcast order and user needs can be matched to the maximum extent, which can improve the efficiency of voice broadcasting to a certain extent, shorten the waiting time of users, and avoid the waste of communication resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 It is an architectural diagram of a voice broadcast system provided by an exemplary embodiment of the present application;
[0018] Figure 2 It is a flowchart of a voice broadcast method provided by an exemplary embodiment of the present application;
[0019] Figure 3It is a flowchart of another voice broadcast method provided by an exemplary embodiment of the present application;
[0020] Figure 4 It is a structural schematic diagram of a voice broadcasting device provided by an exemplary embodiment of the present application;
[0021] Figure 5 It is a structural diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0022] 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 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 are within the scope of protection of this application.
[0023] In order to better understand the solutions of the embodiments of the present application, the relevant terms and concepts that may be involved in the embodiments of the present application are first introduced below.
[0024] IVR menu: IVR (Interactive Voice Response) can perform simple menu grading. IVR menu can also be called an automatic telephone system or telephone voice menu. As a powerful telephone automatic answering system, it can provide customers with menu navigation functions. IVR can be divided into traditional IVR and intelligent IVR. Traditional IVR uses pre-recorded audio to conduct touch-tone voice interactive Q&A with customers, requiring users to continuously press keys to obtain the required knowledge step by step. With the development of artificial intelligence, intelligent IVR that integrates intelligent voice recognition technology can directly let users say the business they need to handle, identify according to the user's answer, support random jumps to any node, and flatten the voice menu navigation.
[0025] Service options: When navigating a voice menu, numbers 0 to 9 are usually used to represent the services provided in the voice broadcast menu. Users can select the corresponding numbers through voice triggers or button triggers to select the service. Therefore, when voice broadcasting, numbers and service content are usually combined. For example, "0 manual service" is a service option.
[0026] The architecture of the voice broadcast system provided in the embodiment of the present application will be introduced below in conjunction with the accompanying drawings.
[0027] See also Figure 1 , Figure 1FIG. 1 is a schematic diagram of the architecture of a voice broadcast system provided by an exemplary embodiment of the present application. Figure 1 As shown, the voice broadcast system includes a terminal device 100 and a server 101. The terminal device 100 and the server 101 can be connected to each other by wire or wireless communication.
[0028] Among them, the terminal device 100 can be a smart phone, a tablet computer, a smart wearable device, an intelligent voice interaction device, a smart home appliance, a personal computer, a car terminal, etc., which has the function of incoming and outgoing calls, and there is no restriction here; the server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms and other basic cloud computing services, and there is no restriction here.
[0029] Server 101 includes but is not limited to a business server and an interactive voice response server, and is a voice broadcast terminal. The business server is used to store the user's service information and user information (such as a phone number) that uniquely identifies the user, and the service information includes but is not limited to historical call records, business information indicating the business handled by the user, etc. The business server can also provide business handling for the user; the interactive voice response server can respond to the instruction triggered by the voice broadcast start operation initiated by the user (such as the user dialing the customer service phone), determine the user's type, and then match different voice broadcast rules according to the user's type, and provide the user with a navigation broadcast of the voice menu under the voice broadcast rule.
[0030] The following takes the voice broadcast scenario of user U calling into customer service platform B as an example to explain the processing flow of the voice broadcast system:
[0031] a. User U dials the customer service telephone number through the terminal device 100, accesses the customer service platform B, and initiates a voice broadcast start instruction to the server 101 where the customer service platform B is located;
[0032] b. The interactive response server in the server 101 receives and responds to the voice broadcast start instruction, and obtains the original voice broadcast order corresponding to the service options from the business server. The original broadcast order is the broadcast order preset by the server for all service options in each level of the menu. The server obtains user information (such as a telephone number) of the user U. The user information here is used to determine the type of the user U, and the corresponding voice broadcast rule can be determined according to the type of the user U.
[0033] c. The interactive response server in the server 101 broadcasts the service options according to the specified voice broadcast rules and based on the original voice broadcast order. In one embodiment, by determining whether the user U is a new user or an old user, different voice broadcast rules can be used for broadcasting: when the user U is a new user, the service options are broadcasted using the first voice broadcast rule (such as a priority recommendation algorithm); when the user U is an old user, the service options are broadcasted using the target voice broadcast order determined by the second voice broadcast rule.
[0034] The voice broadcast system provided by this application can be applied to the scenario where a user dials a customer service phone to provide a voice broadcast service, such as the navigation broadcast provided to the user in the IVR menu navigation broadcast system. By matching corresponding voice broadcast rules for different types of users, the original voice broadcast order is adjusted by the voice broadcast rules, thereby improving the voice broadcast efficiency to a certain extent, shortening the user's waiting time, and avoiding the waste of communication resources.
[0035] The specific implementation of the voice broadcast method proposed in the embodiment of the present application is described in detail below in conjunction with the accompanying drawings.
[0036] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of a voice broadcast method provided by an exemplary embodiment of the present application. The method can be performed by a computer device (e.g. Figure 1 The server 101 shown in the figure is executed. The voice broadcast method includes but is not limited to the following steps.
[0037] S201, in response to a voice broadcast start instruction from a target user, obtaining an original voice broadcast sequence corresponding to a service option.
[0038] The target user is the user who initiates the trigger operation corresponding to the voice broadcast start instruction. The trigger operation can be, for example, that the user dials the customer service phone and accesses the customer service platform. The voice broadcast start instruction can be generated by the trigger operation generated by the target user through the terminal device. The terminal device sends a request carrying the voice broadcast start instruction to the server of the voice broadcast end. The voice broadcast end can respond to the voice broadcast start instruction carried in the request to perform subsequent operations, that is, the voice broadcast end can pull the original voice broadcast sequence corresponding to the service option from the database. The original voice broadcast sequence is a fixed broadcast sequence pre-set by the server for all service options. For example, in the scenario of push-button navigation, the voice broadcast content is usually as follows: "Welcome to call XXX customer service hotline, please press 1 for business processing, press 2 for telephone charge service...Please press 9 for re-listening, and press 0 for manual service", where the first broadcast service option is "business processing", the second broadcast service option is "telephone charge service",..., and so on. The voice broadcast sequence formed can be the original voice broadcast sequence.
[0039] In some cases, the original voice broadcast order is used for each user who accesses the customer service platform, which may cause the user to wait for a long time before selecting the desired service option. For this reason, the original voice broadcast order can be adjusted using preset rules to achieve more flexible voice broadcast.
[0040] Optionally, the server may respond to the voice broadcast start instructions of multiple target users at the same time, obtain the original voice broadcast order corresponding to the service options, and subsequently the voice broadcast order of the service options of each target user is adjusted based on the original voice broadcast order and then broadcast.
[0041] S202: Determine a target voice broadcast rule according to the type of the target user.
[0042] In the embodiment of the present application, the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order.
[0043] The first voice broadcast rule and the second voice broadcast rule are different, but both can be used to adjust the original voice broadcast order. The adjustment of the original voice broadcast order can be to pre-adjust to obtain the final voice broadcast order, or it can be in the process of voice broadcast: respond to the target user's selection instruction to dynamically adjust the original voice broadcast order. When dynamically adjusting, the voice broadcast order will be triggered according to the adjustment rule (for example, the service option has exceeded the preset waiting time and has not been selected) to adjust the current voice broadcast order.
[0044] In one embodiment, the specific implementation of S202 includes: obtaining the user information of the target user, and determining the type of the target user according to the user information; if the type of the target user is the first type, the first voice broadcast rule is determined as the target voice broadcast rule; if the type of the target user is the second type, the second voice broadcast rule is determined as the target voice broadcast rule. Here, the first type of target user refers to a new user, and the second type of target user refers to an old user. The target user dials the customer phone and accesses the customer service platform. The voice broadcast terminal can judge whether the target user is a new user (the voice broadcast system does not record that the target user has dialed the customer service phone and has not handled business on the platform) or an old user (dialed the customer service phone, or handled business on the platform) according to user information (such as telephone number). If it is a new user, it is broadcast according to the first voice broadcast rule, and if it is an old user, it is broadcast according to the second voice broadcast rule. By dividing users into these two types, targeted voice broadcast adjustments can be made and voice broadcast services can be matched with users. This can provide personalized voice broadcast services to old users, and for new users, the original voice broadcast order can be broken by voice broadcast rules. In some cases, the broadcast time for service options to be selected by users can be shortened, thereby providing voice broadcast services more efficiently.
[0045] In a possible embodiment, the voice broadcast rule can be reflected by a priority recommendation algorithm. The priority recommendation algorithm can be used to provide users with priority broadcast service options to reduce the user's waiting time and improve the efficiency of voice broadcast. The priority recommendation algorithm is first introduced below.
[0046] 1. Waiting time priority recommendation algorithm
[0047] This algorithm mainly determines the length of time the user waits for the desired service option to give priority to recommending service options. For better explanation, it is assumed that the voice broadcast terminal contains n service options, and the broadcast time of each service option is x seconds. According to the original voice broadcast order, the time required to broadcast from the first service option to the last service option is t=nx, where n is the number of service options and t is the waiting time. If n is 10 and x is 2, it can be seen from the formula that the time required for the user to wait until the last service option is broadcast is: 20 seconds. It can be deduced that the time to wait for the first service option is 2 seconds, the time to wait for the second service option is 4 seconds, and the time to wait for the third service option is 6 seconds. The waiting time for subsequent service options is deduced accordingly. A rule is set here: when the user's waiting time is greater than or equal to the preset broadcast time (for example, 2 seconds), the last service option in the original voice broadcast order is inserted into the current position, and the remaining service options are postponed. When the current service option is broadcast, the last service option placed after the broadcast service option is broadcast until all service options are broadcast. Exemplarily, the original voice broadcast order includes 10 service options, and the first and second items are broadcast in sequence. When the second item is broadcast, the user has not made a selection, that is, the user's selection instruction has not been responded to, so the tenth item is placed after the second item for broadcast. In this way, the option that originally took 20 seconds to broadcast (that is, the tenth item is broadcast from the 19th to the 20th seconds) is increased to 6 seconds (the tenth item is broadcast from the 5th to the 6th seconds), and then the original third item is placed after the tenth item and continued to be broadcast. After the third item is broadcast, the user waits for 8 seconds. If the user needs the tenth item, the user waits for 6 seconds. Similarly, if the user needs the third item, he only needs to wait for 8 seconds. According to the above order, if the user does not select any item during the voice broadcast process, the broadcast order of the 10 service options is: 1, 2, 10, 3, 9, 4, 8, 5, 7, 6. That is, the later service options are interspersed with the earlier service options for broadcast. The advantage of this algorithm is that the later the service option is, the more likely it is to be recommended first. In this way, the later the service option the user needs, the less waiting time the user needs.
[0048] 2. Equal Duration Priority Recommendation Algorithm This algorithm mainly sets the waiting time of all service options to be equal, that is, the broadcasting order is not pre-set (that is, it is not broadcasted in the original voice broadcasting order), and the service options are sorted by the priority recommendation algorithm. The specific content is: Assuming that the service options in the original voice broadcasting order include S, the first service option and the last service option are broadcast first to meet the user's preference for the first or last service option, and then take the middle two of all the remaining service options (represented by M and N respectively, and M<N is set), and divide them into two sets, which are called A set and B set here. The number of service options in A set and B set may be equal or unequal. Starting from MK, move right in A set, where K∈(1, M), represents the number of options from the 1st to the Mth position in A set, starting from N+J position, converge to the left in B set, J∈(1, SN), represents the number of options from the 1st to the last position in B set, and M and N are broadcasted alternately. For ease of understanding, assume that the total number of service options S = 10, and service option 1 and service option 10 are broadcasted first. The remaining 8 service options include: 2, 3, 4, 5, 6, 7, 8, 9. Take the middle two digits 5 and 6, set A = {2, 3, 4, 5}, set B = {6, 7, 8, 9}, start broadcasting from 5-K = 1 (K = 4), that is, service option 2, and start from service option 6 + J = 9 (J = 3) in set B to move to the left, broadcast service option 2 first, then broadcast service option 9, and so on, broadcast service option 3, broadcast service option 8, and the corresponding broadcast order of all service options is: 1, 10, 2, 9, 3, 8, 4, 7, 5, 6. It can be seen that the advantage of this algorithm is that the options at the two ends will be recommended to users in advance.
[0049] It should be noted that the above-mentioned set is preferably divided evenly. If the remaining service options are an odd number and cannot be divided evenly, they can be divided in a way that the difference is one service option. For example, if the remaining service options are 9, the two sets are the first 4 service options and the last 5 service options. In addition, when this algorithm is used alone as a voice broadcast rule, the division of the set is not necessary. All service options can also be regarded as a set, and the service options can be cross-broadcasted from both ends to the middle based on the original voice broadcast order, which will not affect the voice broadcast order.
[0050] 3. Option Recommendation Algorithm
[0051] This algorithm mainly determines whether the user is waiting for the expected service option to give priority to recommending service options. After the first item is broadcasted, the last item will be broadcasted. If the user does not select an option after the last item is broadcasted, the remaining options will be divided into two sets according to the initial order. For example, assuming that there are 10 service options in total, they are divided into set A {2, 3, 4, 5} and set B {6, 7, 8, 9}. Through a random algorithm, one service option is selected from each set, and the service options are broadcast in the order of B->A->B sets until all service options are broadcasted. For example, if the user does not select a service option during the broadcast, the broadcast order of all service options can be: 1, 10, 6, 3, 7, 2, 9, 5, 8, 4. This can shorten the time it takes for users to hit the later service options to a certain extent. For example, assuming that the broadcast time of each service option is 2 seconds, the time required to broadcast to the last item is: 2n, where n is the number of service options, and the waiting time required to complete all broadcasts is 20 seconds. If the user originally needs to choose the sixth service option, then there is a one-quarter chance that the user only needs to wait for 6 seconds. The advantage of this algorithm is that the later service options can be recommended in advance.
[0052] The first voice broadcast rule can be any one of the above algorithms or a combination of multiple algorithms. The first voice broadcast rule is applied to the scenario where a new user accesses the customer service platform. Since there is no historical service information of the new user, the rules here are used to predict the service options or waiting times expected by the new user, and the broadcast time point of the later service options is advanced, thereby shortening the time for the user to select the later service options.
[0053] The second voice broadcast rule for old users is mainly to personalize the original service option broadcast order according to the service information generated by the old users in the past (such as business information, call records, etc.), so as to better provide old users with targeted voice broadcast services, improve voice broadcast efficiency and service quality, and thus improve user stickiness.
[0054] S203: Voice broadcast the service options according to the target voice broadcast rule.
[0055] From the above steps, the target voice broadcast rule is determined according to the type of target user, then: for the first type of user, the service options are voice broadcast according to the first voice broadcast rule; for the second type of user, the service options are voice broadcast according to the second voice broadcast rule. It should be noted that the service options here may refer to all service options under a single-layer menu. For example, if there are 3 layers of menu levels, the number of service options in each layer of menu may be the same or different, but all service options in the menu of that layer can be voice broadcast according to the target voice broadcast rule.
[0056] According to the priority recommendation algorithm introduced in step S202, its corresponding idea can be directly or indirectly applied as the target voice broadcast rule. Therefore, voice broadcast according to the target voice broadcast rule is performed by changing the original fixed order of broadcast, which can shorten the waiting time of new users to a certain extent, thereby improving user stickiness and avoiding waste of communication resources.
[0057] For the implementation method of voice broadcasting the service options according to the first voice broadcasting rule, please refer to the following introduction; for the implementation method of voice broadcasting the service options according to the second voice broadcasting rule, please refer to Figure 3 Corresponding embodiment.
[0058] In one embodiment, the target voice broadcast rule is a first voice broadcast rule, and voice broadcasting the service option according to the target voice broadcast rule includes the following steps (1) to (3):
[0059] (1) Announce the first service option and the last service option in the original voice announcement sequence.
[0060] Assume that there are 10 service options corresponding to the original voice broadcast order. When user U calls the customer service phone and accesses the customer service platform, the voice broadcast terminal can first use the equal duration priority recommendation algorithm to broadcast service option 1 and service option 10. There is no restriction on the order of broadcasting service option 10 and service option 1. If the user selects service option 1 or service option 10, that is, service option 1 or service option 10 is hit, then no subsequent operation will be performed, that is, steps (2) and (3) will not be executed. Conversely, if neither the broadcasted service option 1 nor the service option 10 is hit, then steps (2) and (3) can be executed.
[0061] (2) When no selection instruction is received, the service options in the first set and the second set are alternately voice broadcasted in a manner of traversing the first set in order and traversing the second set in reverse order.
[0062] Among them, the first set and the second set are obtained by dividing the service options except the first service option and the last service option in the original voice broadcast order, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast order. For example, after service option 1 and service option 10 are broadcast, there are 8 service options remaining. These service options are evenly divided, and the first set obtained is {2, 3, 4, 5}, and the second set is {6, 7, 8, 9}. It should be noted that these sets can be divided in advance, or they can be divided after the service options in step (1) are broadcasted but before receiving the selection instruction initiated by the user side.
[0063] It should be noted that the division of the sets here is necessary. By dividing the sets, the coupling of the order between the service options can be reduced, and the variability of the service options arranged in different positions can be more flexible. The alternating broadcast of the first set and the second set can be a single alternating broadcast or multiple alternating broadcasts, and the service options in the first set or the second set are used as the service options for the initial broadcast. Exemplarily, the first set is still {2,3,4,5} and the second set is {6,7,8,9} for explanation. For example, starting from the first set, the first set is traversed in order, the second set is traversed in reverse order, and the broadcast order of the two sets is: 2, 9, 3, 8, 4, 7, 5, 6. If it is multiple alternating broadcasts, such as two alternating broadcasts, the corresponding broadcast order is: 2, 3, 9, 8, 4, 5, 7, 6. There is no limitation here.
[0064] Therefore, in combination with the above content, when the announced service options 1 and 10 are not selected by user U, that is, the voice announcement terminal does not receive the selection instructions for the first service option and the last service option, the equal duration priority recommendation algorithm is first used to take the 5th and 6th positions, and the A set is obtained as {2, 3, 4, 5}, and the B set is {6, 7, 8, 9}. According to the principle of the equal duration priority recommendation algorithm, the service options are announced in the order of the above examples. It should be noted that during the announcement process, the announcement order is not fixed, but is adaptively adjusted under the specified rules, that is, the content of the following step (3).
[0065] (3) When the broadcasting time reaches a preset broadcasting time and no selection instruction is received, the arrangement order of the service options in the first set is adjusted, and the service options in the second set that have not been broadcasted and the service options in the adjusted first set that have not been broadcasted are alternately voice broadcasted.
[0066] The broadcast duration here can also be called waiting time. For example, it takes 3 seconds to broadcast a service option, that is, the broadcast duration is 3 seconds. The preset broadcast duration can usually correspond to the broadcast of one or more service options. For example, 6 seconds can correspond to the broadcast of two service options. According to the above rules, if the user has not made a choice after a fixed number of service options have been broadcast, the arrangement order of the service options in the first set can be adjusted accordingly, and the service options arranged in the second set can maintain the original arrangement order, and then the remaining service options in the two sets are broadcast according to the broadcast order in step (2). The adjustment of the first set can adopt the waiting time priority recommendation algorithm to insert the later service options into the front position, and the other service options are adjusted accordingly.
[0067] Exemplarily, the above method corresponds to the result of the interaction between the waiting time priority recommendation algorithm and the equal duration priority algorithm. The first set is still {2,3,4,5} and the second set is {6,7,8,9} for explanation. Assuming that the user's target service option is service option 8, the waiting time priority recommendation algorithm is used to broadcast service option 2 in set A. Under the condition that service option 2 is broadcast but the user does not hit the service option, the last service option in set A, that is, service option 5, is inserted after service option 2, and service option 9 is switched to set B for broadcast. After service option 9 is broadcast, set A is switched to broadcast service option 5. After service option 5 is broadcast, the target service option 8 still does not appear. At this time, according to the equal duration priority recommendation algorithm, option 8 of set B is broadcasted, so it takes at most 12 seconds to reach service option 8. If service option 8 is broadcasted but the target service option has not yet been reached, it is switched to set A and broadcasted alternately in the order of set A->B->A. In this way, after all service options are reported, the order of reporting is: 1, 10, 2, 9, 5, 8, 3, 7, 4, 6.
[0068] It can be seen that in this way, the first voice broadcast rule is formed by the combined effect of the waiting time priority recommendation algorithm and the equal duration priority recommendation algorithm introduced above. Under such a voice broadcast rule, it is possible to detect in real time whether the terminal device on the user side has issued a selection instruction, thereby dynamically adjusting the broadcast order of the service options according to the time point when the selection instruction is not received, thereby improving the efficiency of voice broadcast.
[0069] Optionally, when the broadcast duration reaches the preset broadcast duration and no selection instruction is received, the arrangement order of the service options in the first set is adjusted, and the service options in the second set that have not been broadcast and the service options in the adjusted first set that have not been broadcast are voice broadcasted in turn. That is to say, after the service options in the second set are broadcasted in reverse order, the remaining options in the adjusted first set that have not been broadcasted are broadcasted in sequence. Continuing with the above example content, after broadcasting service option 5 in set A, the target service option still does not appear, switch to the option line sequence of service options 8->7->6 in set B for broadcasting. If the target service option has not been reached after broadcasting set B, switch to set A and broadcast the remaining service options, that is, the order in which all service options are broadcasted is: 1, 10, 2, 9, 5, 8, 7, 6, 3, 4.
[0070] In another embodiment, the target voice broadcast rule is a first voice broadcast rule, and S203 may specifically include the following steps (1) to (2):
[0071] (1) Announce the first service option and the last service option in the original voice announcement sequence.
[0072] (2) Starting from the second set, service options are randomly selected from the second set and the first set alternately for voice broadcasting.
[0073] The limitation and specific examples of the first set and the second set in this manner can be found in (2) of the previous implementation, and will not be described in detail here. In this implementation, the first set and the second set are divided in order to intersperse the voice broadcast of the front and back service options. For the specific implementation of the implementation, please refer to the description of the option priority recommendation algorithm introduced above, where the first set corresponds to set A, and the second set corresponds to set B. The rest of the content will not be described in detail here.
[0074] It should be noted that, for a multi-level menu, all service options included in each level of the menu can be broadcast according to the above implementation method. The specific implementation method can be determined according to the situation and is not limited here.
[0075] The voice broadcast solution provided in this embodiment assigns different voice broadcast rules to different types of users, and then provides voice broadcast services to users according to different voice broadcast rules, which can improve the quality of voice broadcast services and improve user experience. For new users, under the first voice broadcast rule, the original voice broadcast order is adjusted by one or more voice broadcast priority recommendation algorithms. In this process, according to the timing of the user issuing the selection instruction, the current voice broadcast order can be continuously adjusted, mainly to broadcast the service options at the back of the original voice broadcast order in advance, so that when the service options required by the user are at the back, the user's waiting time can be greatly reduced.
[0076] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of another voice broadcast method provided by an exemplary embodiment of the present application. The method can be performed by a computer device (e.g. Figure 1 The server 101 shown in the figure is executed. The voice broadcast method includes but is not limited to the following steps.
[0077] S301, in response to a voice broadcast start instruction from a target user, obtaining an original voice broadcast sequence corresponding to a service option.
[0078] S302: Determine a target voice broadcast rule according to the type of the target user.
[0079] The specific implementation of the above steps can be found in Figure 2 S201 to S202 in the corresponding embodiment are not described in detail here. In addition, it should be noted that when the target voice broadcast rule is the second voice broadcast rule, the following steps S303 to S305 may be performed.
[0080] S303, obtaining service information of the target user.
[0081] The target user here is the second type of user, which includes old users. For the convenience of description, the users in the subsequent content are the target users. The service information may include the user's business information (including the business that the user has handled and the business that the user may handle, such as the business record of purchasing financial products on the financial business platform) and the user's historical call record (i.e. the historical record of calling the customer service phone).
[0082] S304: Determine a target voice broadcast order based on the service information of the target user and the original voice broadcast order.
[0083] Based on the above service information, the service options for priority broadcasting can be screened out, so that all service options do not need to be broadcasted in the original voice broadcasting order, but there is a new voice broadcasting order, which is used as the target voice broadcasting order.
[0084] In one embodiment, the service information includes business information and historical call records. S304 is specifically implemented in any of the following two ways:
[0085] Method 1: obtaining service options related to the business information of the target user, and determining the target voice broadcasting order according to the service options related to the business information and the original voice broadcasting order.
[0086] Optionally, when the target user is an old user, the business information of the target user can be extracted to obtain service options related to the business information, such as service options corresponding to the business that the user has handled and service options that the user may handle, so as to give priority to broadcasting options related to the business information. For example, if the user has an outstanding loan on the platform, repayment service options will be broadcasted first, and if the user has paid off the loan on the platform, loan service options can be broadcasted.
[0087] In one implementation, the target voice broadcast order may be determined by the following steps:
[0088] ① Assigning a first priority to the service options related to the business information, and assigning a second priority to the service options other than the service options related to the business information in the original voice broadcast order; the first priority is greater than the second priority; ② Generate a target voice broadcast order corresponding to the service options based on the first priority and the second priority.
[0089] That is to say, among all the service options included in the original voice broadcast order, the service options related to the business information are assigned a higher priority (i.e., the first priority), and the service options unrelated to the business information are assigned a lower priority (the second priority), and then the target voice broadcast order is constructed according to the priority sorting, and the priority broadcast of the service options related to the business information will be realized according to the target voice broadcast order later. If there are multiple service options related to the business information, the priorities assigned to these service options are collectively referred to as the first priority, and the priorities assigned to the remaining service options are the second priority. The service options of the first priority can be further compared with the historical business to sort or randomly sort the service options included in it, and the service options of the second priority can be randomly sorted. For example, if there are 10 service options (represented by numbers 1 to 10 respectively), and the service options related to the business information include 3 (respectively 2, 4, and 7), the first priorities of these 3 service options are consistent, and they can be randomly arranged and broadcasted, and the remaining service options include 7 that are randomly broadcasted after that, or they are arranged and broadcasted according to the size in the original voice broadcast order.
[0090] Method 2: determining the target voice broadcast order based on the historical call records of the target user.
[0091] The historical call records are the historical records of users calling the customer service phone. The historical call records are used to record the service selection path for accessing the customer service platform. Based on the historical records, relevant service options can be reported to users first (for example, the service option is selected the most times). The historical call records include M service selection paths, where M is an integer greater than or equal to 1.
[0092] When the voice broadcast menu of the voice broadcast terminal is composed of multiple layers, then from the first layer to the second layer, or even to the nth layer, each layer can be Figure 2 In the corresponding embodiment, the service options are broadcasted according to the first voice broadcast rule. After the user selects the corresponding service option, the customer service platform can save the user's selection path, that is, the service selection path. The M service selection paths correspond to the number of times the user has been served when accessing the customer service platform. In this way, when the user dials in again, the target voice broadcast sequence can be constructed according to the historically selected service options included in these service selection paths, which can be closer to the user's needs.
[0093] In one embodiment, the optional implementation step of determining the target voice broadcast order according to the historical call records may include: for the service options of any level menu, obtaining the number of selections of the relevant service options in the service options of the any level menu according to each service selection path in the M service selection paths; generating the target voice broadcast order of the service options of the any level menu according to the order of the number of selections of the relevant service options from high to low. The relevant service options are the service options recorded in the service selection path, and the number of selections is the number of times the service options appear in the service path. The service option with the largest number of appearances is used as the best recommendation item, and the second one is used as the second recommendation item. By analogy, the service options appearing in the menu at this level can be sorted to obtain a broadcast order. The service selection path recorded in any level menu may cover all service options under the menu of this level, or may cover a part. When all service options are covered, the final broadcast order can be generated according to the number of selections from high to low. However, when a part is covered, the service options not recorded in the service selection path are arranged according to other rules or randomly arranged to generate the target voice broadcast order.
[0094] For example, suppose there are the following service selection paths in the historical call records:
[0095] a) L1-Option 1 -> L2-Option 3 -> L3-Option 6
[0096] b) L1-Option 2 -> L2-Option 5 -> L3-Option 8
[0097] c) L1-Option 8 -> L2-Option 6 -> L3-Option 8
[0098] d) L1-Option 8 -> L2-Option 3 -> L3-Option 4
[0099] Among them, L1, L2, and L3 represent the voice menu levels, namely the first, second, and third level menus, respectively. Each level of the menu includes multiple service options. For ease of description, the above "options" and "service options" have the same meaning. The next time the user dials in again, the option that appears most frequently in the L1 layer will be used as the best recommendation, and the next one will be used as the second recommendation. Similarly, the option that appears most frequently in the L2 layer will be used as the best recommendation for the L2 layer, and the next one will be used as the second recommendation. The rest are similar. The option that appears most frequently in the L3 layer will be used as the best recommendation for the L3 layer, and the same is true for the above. In this way, there is a target voice broadcast order for each level of the menu. For example, the target voice broadcast order for L1 is option 8->option 2->option 1. Under the target voice broadcast order, service options are always provided to users according to the best recommendation. The more times a service option is selected, the greater the probability that the user will select it. When it is broadcasted first and can be selected by the user, the service progress can be improved.
[0100] S305: Voice broadcast the service options according to the target voice broadcast order.
[0101] According to the above steps, the service options can be voice announced according to the target voice announcement sequence obtained in the first or second method.
[0102] In one embodiment, if we look at the service selection path formed by all levels of menus, the service options of each menu can also be announced in the following manner, namely: determine the target service selection path from the M service selection paths, and use the target service selection path as the target voice announcement path; the service options in the target voice announcement path are the service options selected most times in the menus at all levels; and voice announce the service options included in the target voice announcement path.
[0103] That is to say, according to the service option with the most selections in each menu layer, one path is selected from multiple paths for broadcasting, and only one service option is broadcasted in each menu layer. For example, the service option with the most appearances in the L1 menu is service option 8. From the service selection path where service option 8 is recorded in L1, it is found that the service option with the most appearances in the L2 menu is service option 6. By analogy, the target service selection path is obtained, which is L1-option 8->L2-option 6->L3-option 4. It is used as the target voice broadcast path, and broadcasted according to the target voice broadcast path, with one service option broadcasted in each layer.
[0104] Furthermore, if there are untriggered service options in the target broadcast path, the service options of each level of menus are voice broadcasted according to the first broadcast order, or the service options of each level of menus are voice broadcasted according to the second broadcast order determined by the service options related to the business information. Since only one service option is broadcasted for each level of menus in the target broadcast path, once the service option is not hit, the remaining service options in the voice broadcast path cannot be broadcasted. At this time, other voice broadcast rules can be used to voice broadcast the service options included in the menu at the level where the service option is located and the remaining levels of menus, that is, all service options in each level of menus must be broadcasted.
[0105] For example, if option 8 in L1 in the target service selection path of the aforementioned example is not hit, then all subsequent levels of menus, including L2 and L3, can be broadcast according to the second voice broadcast rule determined according to the business information, and all service options in L1 can also be broadcast according to the second voice broadcast rule, instead of just broadcasting option 8.
[0106] The solution provided by the embodiment of the present application applies the second voice broadcast rule to the voice broadcast service provided to old users. Under the second voice broadcast rule, the service information of old users can be fully utilized to pre-construct the target voice broadcast order, and then the most relevant service options are recommended to old users first, or according to the historical selection of service options by old users, the service options that are most likely to be selected next time are recommended first, so as to improve the hit probability of the service options that are prioritized. In particular, when these prioritized recommended service options are selected, the waiting time for users to obtain services can be further reduced, thereby improving the efficiency of voice broadcast and reducing the consumption of communication resources.
[0107] See also Figure 4 , Figure 4 1 is a schematic diagram of the structure of a voice broadcast device provided by an exemplary embodiment of the present application. The above-mentioned voice broadcast device can be a computer program (including program code) running in a computer device, for example, the voice broadcast device is an application software; the voice broadcast device can be used to execute the corresponding steps of the method provided by the embodiment of the present application. Figure 4 As shown, the voice broadcasting device 400 may include: an acquisition module 401 , a determination module 402 , and a broadcasting module 403 .
[0108] The acquisition module 401 is used to obtain the original voice broadcast sequence corresponding to the service options in response to the voice broadcast start instruction of the target user;
[0109] The determination module 402 is used to determine a target voice broadcast rule according to the type of the target user; the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order;
[0110] The announcement module 403 is used to perform voice announcement of the service options according to the target voice announcement rule.
[0111] In one embodiment, the determination module 402 is specifically used to: obtain user information of the target user, and determine the type of the target user based on the user information; if the type of the target user is the first type, determine the first voice broadcast rule as the target voice broadcast rule; if the type of the target user is the second type, determine the second voice broadcast rule as the target voice broadcast rule.
[0112] In one embodiment, the target voice broadcast rule is the first voice broadcast rule, and the broadcast module 403 is specifically used to: broadcast the first service option and the last service option in the original voice broadcast order; when no selection instruction is received, alternately voice broadcast the service options in the first set and the second set by traversing the first set in sequence and traversing the second set in reverse order; when the broadcast time reaches a preset broadcast time and no selection instruction is received, adjust the arrangement order of the service options in the first set, and alternately voice broadcast the service options in the second set that have not been broadcast and the service options in the adjusted first set that have not been broadcast; wherein the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast order, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast order.
[0113] In another embodiment, the target voice broadcast rule is the first voice broadcast rule, and the broadcast module 403 is specifically used to: broadcast the first service option and the last service option in the original voice broadcast sequence; starting from the second set, randomly select service options from the second set and the first set alternately for voice broadcast; wherein, the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast sequence, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast sequence.
[0114] In one embodiment, the target voice broadcast rule is the second voice broadcast rule; the broadcast module 403 is specifically used to: obtain the service information of the target user; determine the target voice broadcast order based on the service information of the target user and the original voice broadcast order; and voice broadcast the service options according to the target voice broadcast order.
[0115] In one embodiment, the service information includes business information and historical call records; the broadcast module 403 is specifically used to: obtain service options related to the business information of the target user, and determine the target voice broadcast order according to the service options related to the business information and the original voice broadcast order; or, determine the target voice broadcast order based on the historical call records of the target user.
[0116] In one embodiment, the broadcast module 403 is specifically used to: assign a first priority to the service options related to the business information, and assign a second priority to the service options other than the service options related to the business information in the original voice broadcast order; the first priority is greater than the second priority; and generate a target voice broadcast order corresponding to the service options based on the first priority and the second priority.
[0117] In one embodiment, the historical call record includes M service selection paths, where M is an integer greater than or equal to 1, and each service selection path is composed of service options selected by the target user in menus at each level; the broadcast module 403 is specifically used to: for the service options of any level of menu, obtain the number of selections of related service options in the service options of any level of menu according to each service selection path in the M service selection paths; and generate a target voice broadcast order for the service options of any level of menu according to the order of the number of selections of the related service options from high to low.
[0118] In one embodiment, the broadcast module 403 is also used to: determine a target service selection path from the M service selection paths, and use the target service selection path as a target voice broadcast path; the service options in the target voice broadcast path are the service options selected most times in each level of menus; and voice broadcast the service options included in the target voice broadcast path.
[0119] In one embodiment, the broadcast module 403 is specifically used to: if there are untriggered service options in the target broadcast path, voice broadcast the service options of each level of menus according to the first broadcast order, or voice broadcast the service options of each level of menus according to the second broadcast order determined according to the service options related to the business information.
[0120] It is understandable that the functions of the functional modules of the voice broadcast device described in the embodiment of the present application can be specifically implemented according to the method in the above method embodiment, and its specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here. In addition, the description of the beneficial effects of adopting the same method will not be repeated.
[0121] See also Figure 5 , Figure 55 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device 500 may include an independent device (e.g., one or more of a server, a node, a terminal, etc.), or may include components inside an independent device (e.g., a chip, a software module, or a hardware module, etc.). The computer device 500 may include at least one processor 501 and a communication interface 502. Further optionally, the computer device 500 may also include at least one memory 503 and a bus 504. The processor 501, the communication interface 502, and the memory 503 are connected via a bus 504.
[0122] Among them, the processor 501 is a module that performs arithmetic operations and / or logical operations, and can specifically be a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), a coprocessor (assisting the central processing unit to complete corresponding processing and applications), a microcontroller unit (MCU) and other processing modules, or a combination of multiple of them.
[0123] The communication interface 502 may be used to provide information input or output for the at least one processor. And / or, the communication interface 502 may be used to receive data sent externally and / or send data externally, and may be a wired link interface including, for example, an Ethernet cable, or a wireless link (Wi-Fi, Bluetooth, general wireless transmission, vehicle-mounted short-range communication technology, and other short-range wireless communication technologies, etc.) interface.
[0124] The memory 503 is used to provide a storage space, in which data such as an operating system and a computer program can be stored. The memory 503 can be a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a portable read-only memory (CD-ROM), etc., or a combination of multiple thereof.
[0125] At least one processor 501 in the computer device 500 is used to call a computer program stored in at least one memory 503 to execute the aforementioned voice broadcast method, such as the aforementioned Figure 2 and Figure 3 The voice broadcast method described in the illustrated embodiment.
[0126] In one possible implementation, the processor 501 in the computer device 500 is used to call a computer program stored in at least one memory 503 to perform the following operations: obtain the original voice broadcast order corresponding to the service options in response to the voice broadcast start instruction of the target user through the communication interface 502; determine the target voice broadcast rule according to the type of the target user; the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order; and voice broadcast the service options according to the target voice broadcast rule.
[0127] In one embodiment, the processor 501 is specifically used to: obtain user information of the target user, and determine the type of the target user based on the user information; if the type of the target user is the first type, determine the first voice broadcast rule as the target voice broadcast rule; if the type of the target user is the second type, determine the second voice broadcast rule as the target voice broadcast rule.
[0128] In one embodiment, the target voice broadcast rule is the first voice broadcast rule; the processor 501 is specifically used to: broadcast the first service option and the last service option in the original voice broadcast order; when no selection instruction is received, alternately voice broadcast the service options in the first set and the second set by traversing the first set in sequence and traversing the second set in reverse order; when the broadcast time reaches a preset broadcast time and no selection instruction is received, adjust the arrangement order of the service options in the first set, and alternately voice broadcast the service options in the second set that have not been broadcast and the service options in the adjusted first set that have not been broadcast; wherein the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast order, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast order.
[0129] In another embodiment, the target voice broadcast rule is the first voice broadcast rule, and the processor 501 is specifically used to: broadcast the first service option and the last service option in the original voice broadcast order; starting from the second set, randomly select service options from the second set and the first set alternately for voice broadcast; wherein, the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast order, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast order.
[0130] In one embodiment, the target voice broadcast rule is the second voice broadcast rule; the processor 501 is specifically used to: obtain service information of the target user; determine the target voice broadcast order based on the service information of the target user and the original voice broadcast order; and voice broadcast the service options according to the target voice broadcast order.
[0131] In one embodiment, the service information includes business information and historical call records; the processor 501 is specifically used to: obtain service options related to the business information of the target user, and determine the target voice broadcast order according to the service options related to the business information and the original voice broadcast order; or, determine the target voice broadcast order based on the historical call records of the target user.
[0132] In one embodiment, the processor 501 is specifically used to: assign a first priority to a service option related to the business information, and assign a second priority to a service option other than the service option related to the business information in the original voice broadcast order; the first priority is greater than the second priority; and generate a target voice broadcast order corresponding to the service options based on the first priority and the second priority.
[0133] In one embodiment, the historical call record includes M service selection paths, where M is an integer greater than or equal to 1, and each service selection path is composed of service options selected by the target user in menus at various levels; the processor 501 is specifically used to: for the service options of any level of menu, obtain the number of selections of related service options in the service options of any level of menu according to each service selection path in the M service selection paths; and generate a target voice broadcast order for the service options of any level of menu according to the order of the number of selections of the related service options from high to low.
[0134] In one embodiment, the processor 501 is also used to: determine a target service selection path from the M service selection paths, and use the target service selection path as a target voice broadcast path; the service options in the target voice broadcast path are the service options selected most times in each level of menus; and voice broadcast the service options included in the target voice broadcast path.
[0135] In one embodiment, the processor 501 is specifically used to: if there are untriggered service options in the target broadcast path, voice broadcast the service options of each level of menus according to the first broadcast order, or voice broadcast the service options of each level of menus according to the second broadcast order determined according to the service options related to the business information.
[0136] It should be understood that the computer device 500 described in the embodiment of the present application can execute the description of the voice broadcast method in the above corresponding embodiment, and can also execute the above Figure 4 The description of the voice broadcasting device 400 in the corresponding embodiment will not be repeated here. In addition, the description of the beneficial effects of adopting the same method will not be repeated here either.
[0137] In addition, it should be noted that an exemplary embodiment of the present application also provides a storage medium, in which a computer program of the aforementioned voice broadcast method is stored, and the computer program includes program instructions. When one or more processors load and execute the program instructions, the description of the voice broadcast method in the embodiment can be implemented, which will not be repeated here, and the description of the beneficial effects of using the same method will not be repeated here. It is understandable that the program instructions can be deployed on one or multiple computer devices that can communicate with each other for execution.
[0138] The computer-readable storage medium may be the voice broadcast device provided in any of the aforementioned embodiments or the internal storage unit of the computer device, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the computer device. Further, the computer-readable storage medium may also include both the internal storage unit of the computer device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
[0139] In one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in one aspect of the embodiments of the present application.
[0140] In one aspect of the present application, another computer program product is provided, which includes a computer program or computer instructions, and when the computer program or computer instructions are executed by a processor, the steps of the voice broadcast method provided in the embodiment of the present application are implemented.
[0141] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.
Claims
1. A voice broadcasting method, It is characterized in that The method comprises: In response to a voice broadcast start instruction from a target user, obtaining an original voice broadcast sequence corresponding to the service options; Determine a target voice broadcast rule according to the type of the target user; the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order; Performing voice broadcasting of the service options according to the target voice broadcasting rule; Wherein, determining the target voice broadcast rule according to the type of the target user includes: obtaining user information of the target user, and determining the type of the target user according to the user information; if the type of the target user is the first type, determining the first voice broadcast rule as the target voice broadcast rule; if the type of the target user is the second type, determining the second voice broadcast rule as the target voice broadcast rule; Among them, when the target voice broadcast rule is the first voice broadcast rule; the voice broadcasting of the service option according to the target voice broadcast rule includes: The first service option and the last service option in the original voice broadcast sequence are broadcasted; when no selection instruction is received, the service options in the first set and the second set are alternately voice broadcasted in a manner of traversing the first set in order and traversing the second set in reverse order; when the broadcasting time reaches a preset broadcasting time and no selection instruction is received, the arrangement order of the service options in the first set is adjusted, and the service options in the second set that have not been broadcasted and the service options in the adjusted first set that have not been broadcasted are alternately voice broadcasted; wherein the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast sequence, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast sequence; Alternatively, the first service option and the last service option in the original voice broadcast sequence are broadcast; starting from the second set, service options are randomly selected from the second set and the first set alternately for voice broadcast; wherein the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast sequence, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast sequence.
2. The method according to claim 1, It is characterized in that The target voice broadcast rule is the second voice broadcast rule; and the voice broadcasting of the service option according to the target voice broadcast rule includes: Obtain service information of target users; Determine a target voice broadcast order based on the service information of the target user and the original voice broadcast order; The service options are voice announced in accordance with the target voice announcement sequence.
3. The method according to claim 2, It is characterized in that The service information includes business information and historical call records; the determining the target voice broadcast order based on the service information of the target user and the original voice broadcast order includes: Acquire service options related to the business information of the target user, and determine the target voice broadcast order according to the service options related to the business information and the original voice broadcast order; or, The target voice broadcast order is determined based on the historical call records of the target user.
4. The method according to claim 3, It is characterized in that The step of determining the target voice broadcast order according to the service options related to the business information and the original voice broadcast order includes: Assigning a first priority to a service option related to the business information, and assigning a second priority to a service option other than the service option related to the business information in the original voice broadcasting order; the first priority is greater than the second priority; A target voice broadcast order corresponding to the service options is generated according to the first priority and the second priority.
5. The method according to claim 3, It is characterized in that The historical call record includes M service selection paths, where M is an integer greater than or equal to 1, and each service selection path is composed of service options selected by the target user in menus at various levels; The determining the target voice broadcast order based on the historical call records of the target user includes: For the service options of any level menu, obtaining the number of selections of the relevant service options in the service options of any level menu according to each service selection path in the M service selection paths; A target voice broadcasting order of the service options of any level of menu is generated according to the order of the number of selections of the related service options from high to low.
6. A voice broadcasting device, It is characterized in that include: An acquisition module, configured to respond to a target user's voice broadcast start instruction and acquire an original voice broadcast sequence corresponding to the service options; A determination module, used to determine a target voice broadcast rule according to the type of the target user; the target voice broadcast rule includes a first voice broadcast rule or a second voice broadcast rule, and the first voice broadcast rule and the second voice broadcast rule are used to adjust the original voice broadcast order; A broadcasting module, used for voice broadcasting the service options according to the target voice broadcasting rule; Wherein, determining the target voice broadcast rule according to the type of the target user includes: obtaining user information of the target user, and determining the type of the target user according to the user information; if the type of the target user is the first type, determining the first voice broadcast rule as the target voice broadcast rule; if the type of the target user is the second type, determining the second voice broadcast rule as the target voice broadcast rule; Among them, when the target voice broadcast rule is the first voice broadcast rule; the voice broadcasting of the service option according to the target voice broadcast rule includes: The first service option and the last service option in the original voice broadcast sequence are broadcasted; when no selection instruction is received, the service options in the first set and the second set are alternately voice broadcasted in a manner of traversing the first set in order and traversing the second set in reverse order; when the broadcasting time reaches a preset broadcasting time and no selection instruction is received, the arrangement order of the service options in the first set is adjusted, and the service options in the second set that have not been broadcasted and the service options in the adjusted first set that have not been broadcasted are alternately voice broadcasted; wherein the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast sequence, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast sequence; Alternatively, the first service option and the last service option in the original voice broadcast sequence are broadcast; starting from the second set, service options are randomly selected from the second set and the first set alternately for voice broadcast; wherein the first set and the second set are obtained by dividing the service options other than the first service option and the last service option in the original voice broadcast sequence, and the service options included in the first set are arranged before the service options included in the second set in the original voice broadcast sequence.
7. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the voice broadcast method according to any one of claims 1 to 5 is executed.
8. A computer program product, It is characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the voice broadcast method described in any one of claims 1 to 5.
